System

Abstract

A system is provided.SOLUTION: The system includes a means for inputting symptoms, desired treatment contents, and desired conditions by patients and their families, a means for receiving information input by patients and their families and transmitting the information to a generation AI model, a means for analyzing the information by the generation AI model and searching for optimal medical institutions and doctors from a database, a means for arranging information obtained from the database and providing the information to patients and their families, and a means for automatically generating referral letters and providing the referral letters to patients and their families.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] Cancer treatment is highly specialized, and choosing the right medical institution and doctor is extremely important. However, many patients and their families find it difficult and time-consuming to search for the right medical institution or doctor on their own. This prevents them from making the most appropriate medical choices, putting them at risk of delaying their treatment progress or receiving inappropriate treatment. Additionally, creating referral letters and making appointments can be time-consuming and burdensome, placing an additional burden on patients. There is a need for the development of a system that can reduce these burdens and provide appropriate medical information quickly and accurately. [Means for solving the problem]

[0005] The present invention provides a means for patients and their families to input their symptoms, desired treatment, and desired conditions. It also includes a means for receiving the information input by the patient or their family and sending it to a generative AI model. The generative AI model analyzes this information and searches a database for the most suitable medical institution and doctor. It also includes a means for organizing the searched information and providing it to the patient or their family. It also automatically generates a referral letter and provides it to the patient or their family. This allows for prompt and accurate medical information to be provided without time or location constraints. It also includes a means for supporting the appointment process at a medical institution based on the selections of the patient or their family. It also includes a means for checking the schedule of the medical institution and confirming the appointment, significantly reducing the burden on the patient and their family.

[0006] "Patients and their families" refers to people who need medical information, including those who are ill and their caregivers and supporters.

[0007] "Symptom" refers to an abnormal physical or mental state or disease-related phenomenon experienced by a patient.

[0008] "Desired treatment" refers to the specific medical procedures or treatment processes desired by the patient or their family.

[0009] "Preferences" refer to specific conditions or requirements that patients and their families have regarding medical institutions and treatment methods (e.g., geographic location, budget, duration of treatment).

[0010] "Means of input" refers to the interface (e.g., web form or application) that a user uses to provide data to a system.

[0011] A "generative AI model" refers to artificial intelligence that uses advanced natural language processing technology to analyze input data and generate and recommend information.

[0012] "Medical institution" refers to a facility that provides medical services to patients, such as a hospital, clinic, or medical office.

[0013] "Physician" refers to a qualified medical professional who provides diagnosis, treatment, and advice to patients.

[0014] A "database" refers to a collection of structured data that stores information about medical institutions and doctors.

[0015] A "referral letter" refers to a document that summarizes a patient's medical condition and treatment wishes and is prepared for the purpose of referring the patient to an appropriate medical institution or doctor.

[0016] "Reservation procedure" refers to the process of reserving a date, time, and location for consultation or treatment at a specific medical institution or doctor. [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] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. This system utilizes a generative AI model to analyze and provide medical information based on the patient's and their family's medical condition and treatment preferences, and supports the creation of referral letters and reservation procedures.

[0039] Basic structure and operation of the system

[0040] User terminal operation

[0041] Using a web application, users input their symptoms, desired treatment, and desired conditions. For example, a user might enter data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like a hospital in Tokyo that's easy to get to." This input information is sent to the server with a single click.

[0042] Server Operation

[0043] The server receives the information sent by the user. The received information is sent to the generative AI model, where analysis begins. Based on the received data, the generative AI model understands the patient's condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[0044] The generative AI model selects the most suitable medical institutions and doctors based on criteria such as "breast cancer," "latest treatments," and "located in Tokyo." The server organizes this information and prepares it for delivery to the user. It also automatically generates referral letters and saves them in the appropriate format.

[0045] Reply to user terminal

[0046] The server sends the organized medical institution information and referral letters to the user's terminal, which receives and displays the information. The user can then view detailed information on the listed medical institutions and select the most appropriate option.

[0047] For example, the user selects "Medical Institution A" from among "Medical Institution A," "Medical Institution B," and "Medical Institution C." This selection information is sent to the server, which then assists in the reservation procedure at the selected medical institution.

[0048] Reservation procedure

[0049] The server checks the schedule of the selected medical institution and confirms the reservation. At this time, adjustments are made depending on the reservation status, and once the reservation is confirmed, the information is notified to the user's terminal. The user can then check the confirmed reservation information and proceed with preparations to visit the medical institution.

[0050] Specific examples

[0051] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins its analysis. It searches the database for medical institutions that meet the conditions, and lists "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[0052] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the reservation. The user receives the confirmed reservation information and can plan their visit to the medical institution.

[0053] In this way, this invention uses a generative AI model to quickly and accurately provide patients and their families with the most suitable medical institutions and doctors they desire, thereby reducing the burden of medical care selection. Support for creating referral letters and booking procedures can also be done online, allowing patients and their families to use the service without being restricted by time or location.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. For example, they might enter "breast cancer" as the symptom, "latest treatment" as the desired treatment, and "within Tokyo" as the condition.

[0057] Step 2:

[0058] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[0059] Step 3:

[0060] The server receives data sent from the user's device and sends it to the generative AI model for analysis. The received data is stored in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[0061] Step 4:

[0062] The server's generative AI model analyzes the user's input data and searches the database for the most suitable medical institution or doctor. For example, the generative AI model extracts the best matching candidates based on the keywords "breast cancer," "latest treatment," and "Tokyo."

[0063] Step 5:

[0064] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[0065] Step 6:

[0066] The server organizes the acquired information on medical institutions and doctors and creates an information package to provide to the user. For example, it compiles detailed information on medical institutions A, B, C, etc. into a list.

[0067] Step 7:

[0068] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, and conditions.

[0069] Step 8:

[0070] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[0071] Step 9:

[0072] The user terminal receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C and the created referral letter are displayed on the screen.

[0073] Step 10:

[0074] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[0075] Step 11:

[0076] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[0077] Step 12:

[0078] The server notifies the user that the reservation has been confirmed. A reservation confirmation email or app notification is sent to the user.

[0079] Example 1

[0080] 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."

[0081] In modern medicine, it is extremely difficult for patients and their families to select the most appropriate medical institution and doctor. Especially in the case of serious illnesses, quick decisions based on reliable information are necessary. However, independently collecting and analyzing vast amounts of medical information requires time and effort, and there is a risk of making the wrong choice. Furthermore, the process of creating referral letters and making appointments is cumbersome, placing a significant burden on patients and their families. A system that solves these problems and provides patients and their families with the best medical options is needed.

[0082] 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.

[0083] In this invention, the server includes: a means for patients and their families to input their symptoms, desired treatment, and desired conditions; a means for receiving the information input by the patient and their family and sending it to the generative AI model; a means for the generative AI model to analyze the information using prompts and search a database for the most suitable medical institution and doctor; a means for organizing the information obtained from the database and providing it to the patient and their family; a means for automatically generating a referral letter and providing it to the patient and their family; a means for re-receiving information about the medical institution selected by the patient; and a means for notifying a user terminal of the medical institution's confirmed appointment information. This allows patients and their families to quickly select the most suitable medical institution and doctor based on reliable information. Furthermore, the automatic generation of referral letters and assistance with appointment procedures can reduce the burden on patients and their families.

[0084] "Patients" or "their families" are people who require medical services and their close relatives who provide support.

[0085] A "symptom" refers to a specific problem or symptom related to a patient's health.

[0086] "Treatment preference" means the specific type of medical treatment or therapy desired by the patient.

[0087] "Desired conditions" refer to the geographical, time, and facility requirements that patients and their families consider important when selecting a medical institution.

[0088] "Input means" refers to the mechanism by which a user enters and submits information using a web application or other interface.

[0089] "Receiving means" refers to a function that allows the server to receive information sent by the user.

[0090] A "generative AI model" refers to an artificial intelligence algorithm that analyzes information entered by patients and their families and selects the most appropriate medical institution and doctor.

[0091] A "prompt" is a short sentence or combination of keywords used to provide input to a generative AI model and serve as the basis for analysis.

[0092] "Database" refers to an electronic data storage system for storing data such as details, ratings, and locations of medical institutions and physicians.

[0093] "Organization means" refers to the function for organizing information obtained from a generative AI model into an easy-to-understand format.

[0094] "Means of delivery" refers to the mechanism for delivering organized information and generated referral letters to patients and their families.

[0095] A "letter of referral" refers to a referral document to a medical institution that is prepared based on the patient's medical condition and treatment wishes.

[0096] "Selected information" refers to information about a specific medical institution selected by the patient or their family from the medical institution information provided.

[0097] "Reservation procedure support means" refers to the support functions required to confirm a reservation at the selected medical institution.

[0098] "Reservation confirmation information" refers to information indicating that a reservation has been confirmed after checking the schedule of the medical institution.

[0099] The present invention provides a system for providing an online referral service that enables patients and their families to quickly and accurately select the most suitable medical institution and doctor, and supports the creation of referral letters and reservation procedures. An embodiment of this system will be described in detail below.

[0100] Basic structure and operation

[0101] User terminal operation

[0102] Users use a web application provided through a web browser on their PC or smartphone (e.g., Google Chrome, Mozilla Firefox) to input their symptoms, desired treatment, and desired conditions. For example, they input data such as "I've been diagnosed with breast cancer," "I'd like a hospital that offers the latest treatments," and "A location within Tokyo that's easy to get to." After completing the input, they click the send button to send this information to the server.

[0103] Server Operation

[0104] The server receives user-submitted information via an HTTP POST request. To process this information, the server leverages a generative AI model (e.g., GPT-4 or BERT). The received user data is transformed into a prompt like this:

[0105] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[0106] This prompt sentence is input into the generative AI model and analysis begins.

[0107] Analysis using generative AI models

[0108] The generative AI model analyzes the user's medical condition and desired conditions, and searches a database for appropriate medical institutions and doctors. The database contains detailed information on multiple medical institutions and doctors. For example, it identifies the most suitable medical institution and doctor based on the conditions "breast cancer," "latest treatment," and "within Tokyo."

[0109] Data organization and referral generation

[0110] The server integrates the information obtained from the generative AI model and prepares it for delivery to the user. This information is organized in JSON format and provided to the user via a web application. The server also automatically generates a referral letter and saves it in PDF format. This referral letter includes the patient's medical condition, desired conditions, recommended treatment, and other information.

[0111] Sending information to user terminals

[0112] The organized medical institution information and referral letter are sent to the user's device as an HTTP response, where the user can view the information and check the details on the web application.

[0113] Reservation procedure

[0114] Once the user selects the most suitable medical institution, the selection information is sent back to the server. The server then checks the schedule of the selected medical institution via API and confirms the reservation. The confirmed reservation information is then sent to the user's device. The user can then receive the confirmed reservation information and prepare for their hospital visit.

[0115] Specific examples

[0116] For example, a user enters the criteria "breast cancer," "latest treatment," and "location within Tokyo that is easy to get to." This information is sent to the server, and the generative AI model begins its analysis. The prompt is as follows:

[0117] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[0118] Based on the analysis results, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is created from the database. This information is organized and provided to the user.

[0119] When the user selects "Medical Institution A," that information is sent to the server again. The server then checks the schedule of "Medical Institution A" and sends the confirmed reservation information to the user's terminal. The user can use this information to plan their hospital visit.

[0120] This way, patients and their families can easily find good medical institutions and doctors and get the necessary procedures done quickly and efficiently.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1:

[0123] User input of information

[0124] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. At this time, they enter information such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "It should be located in Tokyo and be easy to get to" as text into the input form. Once they have completed the input, they click the send button, which sends the entered information to the server.

[0125] Input: Symptoms and wishes entered by the user into the web application

[0126] Output: The input information is sent to the server as an HTTP request.

[0127] Step 2:

[0128] Server receives information

[0129] The server receives information sent by the user via an HTTP POST request, temporarily stores the received data in JSON format, and converts it into a format that can be input to the generative AI model.

[0130] Input: User-submitted information in JSON format

[0131] Output: Prompt sentence to be input to the generative AI model

[0132] Step 3:

[0133] Analysis using generative AI models

[0134] The server inputs a prompt into the generative AI model and begins analysis. For example, the prompt might be "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo." The generative AI model uses this prompt to analyze the most suitable medical institution and doctor.

[0135] Input: prompt statement

[0136] Output: Analysis results from the generative AI model (list of optimal medical institutions and doctors)

[0137] Step 4:

[0138] Searching from the database

[0139] The server searches a database for detailed information on the most suitable medical institution and doctor based on the analysis results of the generative AI model. The database stores detailed information on hospitals and clinics, as well as the doctor's specialty and reputation. For example, based on the analysis results of the criteria "breast cancer," "latest treatment," and "within Tokyo," the server searches for "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[0140] Input: Analysis results of the generative AI model

[0141] Output: Information on the most suitable medical institution and doctor obtained from the database

[0142] Step 5:

[0143] Organizing information and generating referral letters

[0144] The server organizes the information obtained from the database and prepares it for delivery to the user. This information is consolidated into an easy-to-understand format, such as JSON. At the same time, the server automatically generates a referral letter, which describes the patient's condition, desired conditions, and recommended treatment, and is saved in PDF format.

[0145] Input: Medical institution information obtained from the database

[0146] Output: Organized medical institution information and referral letter (PDF format)

[0147] Step 6:

[0148] Sending information to user terminals

[0149] The server sends the organized medical institution information and referral letter to the user's device as an HTTP response. The user can view this information on the web application and check the details.

[0150] Input: Organized medical institution information and referral letter (PDF format)

[0151] Output: Medical institution information and referral letter displayed on the user's terminal

[0152] Step 7:

[0153] User selection of medical institution

[0154] The user views the medical institution information provided on the web application and selects the most appropriate option from "Medical Institution A," "Medical Institution B," or "Medical Institution C." The selected information is then sent back to the server.

[0155] Input: Information about the medical institution selected by the user

[0156] Output: Selection information is sent to the server

[0157] Step 8:

[0158] Server-based reservation process

[0159] The server receives the information about the medical institution selected by the user and checks the schedule of that institution. It then uses an API to connect to the medical institution's reservation system and confirms the reservation. Once the reservation is confirmed, the server notifies the user's device of the reservation confirmation information.

[0160] Input: Information about the medical institution selected by the user

[0161] Output: Confirmed reservation information is sent to the user's device.

[0162] Step 9:

[0163] User confirms reservation and prepares visit

[0164] The user can then confirm the confirmed reservation information on the web application. After confirming that the reservation information has been confirmed, the user can then prepare to visit the medical institution.

[0165] Input: Confirmed reservation information

[0166] Output: User confirms appointment and begins visit preparation

[0167] (Application example 1)

[0168] 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."

[0169] In conventional medical referral systems, there is a high risk of medical information entered by patients and their families being leaked to the outside, making security a major issue. There is also a need to improve the accuracy of analysis based on the patient's medical condition and desired conditions, which makes it difficult to find the most suitable medical institution or doctor.

[0170] 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.

[0171] In this invention, the server includes means for patients and their families to input their symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their family and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for organizing the information obtained from the database and providing it to the patient and their family, means for automatically generating a referral letter and providing it to the patient and their family, means for encrypting the input information, and means for decrypting the encrypted information. This enables quick and accurate referral to the most suitable medical institution and doctor while protecting the patient's confidential information with high security.

[0172] "Patients and their families" refers to individuals who require medical services and their supporters.

[0173] "Symptoms" refer to abnormalities or distress in the patient's body or mind.

[0174] "Desired treatment details" is information indicating the specific treatment methods and medical services desired by the patient and their family.

[0175] "Desired conditions" refers to specific requests regarding medical institutions and treatment, such as location, date and time, and specialty.

[0176] "Means of input" refers to the interface or device through which a user provides information to a system.

[0177] "Means for receiving" refers to a mechanism for receiving information sent by a user.

[0178] A "generative AI model" refers to a program that uses artificial intelligence technology to analyze input data and generate optimal answers or suggestions.

[0179] A "database" refers to a system that systematically organizes and manages information about medical institutions and doctors, making it searchable.

[0180] "Search methods" refer to algorithms or programs used to find information that meets specific criteria from a database.

[0181] "Means for organizing and presenting" refers to the mechanism for presenting the searched information to the user in an easy-to-understand format.

[0182] "Means for automatically generating a letter of introduction" refers to a program that automatically creates a letter of introduction based on information entered by the user and the results of analysis.

[0183] "Encryption methods" refers to techniques for converting information into a form that cannot be deciphered by third parties.

[0184] "Means to decrypt" refers to the technology used to restore encrypted information to its original form.

[0185] The system of the present invention provides an online referral service that introduces optimal medical institutions and doctors based on the results of analysis by a generative AI model after patients and their families input their medical information. This system includes the following means.

[0186] User terminal operation

[0187] The user terminal provides an interface for patients and their families to input information such as symptoms, desired treatment, desired conditions, etc. For example, a user might input data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like to go to a hospital in Tokyo that's easy to get to." This input information is encrypted and sent to the server.

[0188] Server Operation

[0189] The server receives the entered medical information and first decrypts the encrypted data. It then requests the generative AI model to analyze it. The generative AI model then searches the database for the most suitable medical institution and doctor based on the decrypted data. In this process, the generative AI model performs its analysis using prompts such as the following:

[0190] "Find accessible hospitals in Tokyo that offer the latest treatments for breast cancer patients."

[0191] Database search and information organization

[0192] The generative AI model searches the database for candidate medical institutions and doctors and extracts relevant information. For example, based on the criteria "breast cancer," "latest treatment," and "within Tokyo," it will select "Medical Institution A," "Medical Institution B," and "Medical Institution C." This information is then organized and prepared for provision to patients and their families.

[0193] Automatic generation of referral letters

[0194] The server automatically generates a referral letter based on the extracted information. The referral letter includes the patient's medical condition, requests, and information on recommended medical institutions and doctors. The generated referral letter is also encrypted when stored and transmitted.

[0195] Confirmation and booking process

[0196] The server sends the organized information and referral letter to the user's terminal, where the user confirms it. For example, the user selects "Medical Institution A" from "Medical Institution A," "Medical Institution B," and "Medical Institution C." The selected information is sent to the server, which checks the schedule of the selected medical institution and assists with the reservation procedure.

[0197] Hardware and software used

[0198] The system uses user devices (smartphones, tablets, PCs), a server, a generative AI model, a database, and encryption / decryption technology. As a specific example, it uses the Python Cryptography package for encryption and decryption.

[0199] example:

[0200] Data entered by the user: "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," "A location in Tokyo that is easy to get to."

[0201] Prompt for generative AI model: "Find hospitals in Tokyo that offer the latest treatments for breast cancer patients and are easy to get to."

[0202] This enables quick and accurate referral to the most appropriate medical institution or doctor while protecting patient confidential information with high security.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The user uses the terminal to input information such as symptoms, desired treatment, and desired conditions.

[0206] Input: The user enters data such as "breast cancer," "latest treatment," and "locations in Tokyo that are easy to get to."

[0207] Output: The input data

[0208] What happens: The user enters information into the interface and clicks the submit button.

[0209] Step 2:

[0210] The terminal encrypts the information entered by the user and sends it to the server.

[0211] Input: Data entered

[0212] Output: Encrypted data

[0213] Specific operation: The terminal uses the encryption module (Python Cryptography package) to encrypt the input data and sends the encrypted data to the server.

[0214] Step 3:

[0215] The server receives and decrypts the encrypted data.

[0216] Input: Encrypted data

[0217] Output: Decrypted data

[0218] Specific operation: Receives encrypted data on the server side and uses a decryption module to restore the original information.

[0219] Step 4:

[0220] The server sends the decrypted data to the generative AI model and requests it to analyze it.

[0221] Input: Decrypted data

[0222] Output: Analysis request to the generative AI model

[0223] Specific behavior: The server generates a prompt based on the content of the data,

[0224] "Find an easily accessible hospital in Tokyo that offers the latest treatments for breast cancer patients."

[0225] This prompt is sent to the generative AI model.

[0226] Step 5:

[0227] The generative AI model searches a database for the most suitable medical institution or doctor based on the prompt text.

[0228] Input: prompt statement

[0229] Output: List of medical institutions and doctors

[0230] How it works: The generative AI model analyzes the prompt, searches for corresponding database entries, and lists appropriate medical institutions and doctors.

[0231] Step 6:

[0232] The server organizes information about medical institutions and doctors obtained from the generative AI model.

[0233] Input: List of medical institutions and doctors

[0234] Output: Organized medical information

[0235] Specific operation: The server organizes the information extracted from the database according to a format and prepares it in a form that can be provided to the user.

[0236] Step 7:

[0237] The server automatically generates and encrypts a referral letter based on the organized medical information.

[0238] Input: Organized medical information

[0239] Output: Encrypted letter of introduction

[0240] Specific operation: The referral letter generation module creates a referral letter based on the listed information of medical institutions and doctors and the information entered by the user, and then encrypts it.

[0241] Step 8:

[0242] The server transmits the encrypted referral letter and medical information to the user terminal.

[0243] Input: Encrypted letter of introduction

[0244] Output: Sending data to the user's terminal

[0245] What it does: The server sends the encrypted referral letter and medical information and makes it accessible to the user.

[0246] Step 9:

[0247] The user can view the medical information and referral letter sent to them and select the most suitable medical institution and doctor.

[0248] Input: Encrypted letter of introduction

[0249] Output: User selection information

[0250] Specific operations: The device decrypts the data received and displays it in a form that can be viewed by the user. The user makes a selection and sends the selection to the server.

[0251] Step 10:

[0252] The server assists the user in making a reservation at a medical institution based on the user's selection information.

[0253] Input: User selection information

[0254] Output: Reservation information

[0255] Specific operation: The server checks the schedule of the selected medical institution and confirms the corresponding appointment.

[0256] Step 11:

[0257] The server notifies the user terminal of the information that the reservation has been confirmed.

[0258] Input: Reservation information

[0259] Output: Booking confirmation notice

[0260] Specific operation: Send a notification to the user's device and display the reservation information.

[0261] 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.

[0262] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention provides medical information and support according to the user's emotional state.

[0263] Basic structure and operation of the system

[0264] User terminal operation

[0265] The user uses a web application to input their symptoms, desired treatment, and desired conditions. For example, the user might input data such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "I would like a hospital in Tokyo that is easy to get to." This input information is sent to the server when the user clicks the "Submit" button.

[0266] Server Operation

[0267] The server receives the information sent by the user. The received information is sent to the generative AI model, which begins analyzing it. The generative AI model understands the user's medical condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[0268] Combining Emotion Engines

[0269] Here, the emotion engine recognizes the user's emotional state from the content of their input. For example, it analyzes the emotions of "anxiety," "impatience," and "calmness" from the user's input text. The emotion engine adjusts the recommendations generated by the AI ​​model based on this emotional state.

[0270] The generative AI model not only selects the most suitable medical institutions and doctors based on the criteria of "breast cancer," "latest treatments," and "located in Tokyo," but also prioritizes medical institutions and doctors that users feel more comfortable with, taking into account the state of "anxiety" recognized by the emotion engine. The server organizes this information and prepares it for provision to the user. It also automatically generates a referral letter and saves it in the appropriate format.

[0271] Reply to user terminal

[0272] The server sends the organized medical institution information and referral letters to the user's device. The user's device receives this and displays the information. The user can view detailed information about the listed medical institutions and check recommended options based on their emotional state. For example, from among "Medical Institution A," "Medical Institution B," and "Medical Institution C," the user can select "Medical Institution A," which has been rated as "reliable" by the emotion engine.

[0273] Reservation procedure

[0274] The server checks the schedule of the selected medical institution and confirms the appointment. At this time, it also provides necessary support information and resources based on the user's emotional state. For example, if a user is feeling excessive anxiety, it may provide support such as presenting psychological counseling options. Once the appointment is confirmed, the information is sent to the user's device. The user receives the confirmed appointment information and can begin preparing to visit the medical institution.

[0275] Specific examples

[0276] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins analysis. At that time, the emotion engine recognizes the emotion of "anxiety" from the user's input, and taking this result into consideration, prioritizes recommending medical institutions that can provide a greater sense of security. For example, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is displayed, but the emotion engine evaluates "Medical Institution A" as being the best for providing a sense of security.

[0277] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the appointment. Furthermore, to address the anxious emotional state, an option for psychological counseling is also provided. The user receives the confirmed appointment and additional support information, allowing them to plan their visit to the medical institution.

[0278] In this way, the present invention utilizes a generative AI model and an emotion engine to provide optimal medical information according to the user's emotional state, thereby reducing the burden of medical selection and providing safer and more reliable medical services.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] Users open the web application and enter their symptoms, desired treatment, and desired conditions. For example, they enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "I want a hospital in a convenient location in Tokyo."

[0282] Step 2:

[0283] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[0284] Step 3:

[0285] The server receives data from the user's device and sends the received information to the generative AI model and emotion engine. The received data is saved in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[0286] Step 4:

[0287] The emotion engine analyzes the user's input data and recognizes their emotional state. For example, it analyzes emotions such as "anxiety," "impatience," and "calmness." This emotional state data is passed to the generative AI model.

[0288] Step 5:

[0289] The server's generative AI model analyzes the user's symptoms and desired conditions, and also considers the emotional state from the emotion engine to search for the most suitable medical institution or doctor from the database. For example, the generative AI model extracts the best matching candidates by considering the keywords "breast cancer," "latest treatments," and "Tokyo area" as well as the emotion of "anxiety."

[0290] Step 6:

[0291] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[0292] Step 7:

[0293] The server organizes the information on medical institutions and doctors it has acquired and creates an information package that takes into account the results of the emotion engine. For example, detailed information on medical institutions A, B, and C is compiled into a list, and medical institution A is evaluated as providing the most reassurance.

[0294] Step 8:

[0295] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, conditions, and emotional state.

[0296] Step 9:

[0297] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[0298] Step 10:

[0299] The user device receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C, along with the created referral letter, are displayed on the screen. Based on the evaluation by the emotion engine, medical institution A is displayed as the most reliable.

[0300] Step 11:

[0301] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[0302] Step 12:

[0303] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[0304] Step 13:

[0305] The server notifies the user that the reservation has been confirmed. A confirmation email or app notification is sent to the user. Based on the emotion engine, additional support information may be provided, including psychological counseling options.

[0306] Through these small steps, users can feel at ease when selecting a medical institution using the emotion engine, and can easily proceed with creating a referral letter and making a reservation.

[0307] Example 2

[0308] 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."

[0309] In conventional medical information provision systems, even if patients and their families input their symptoms and desired conditions, they simply refer them to the most suitable medical institution or doctor based on that information, and do not provide sufficient support that takes into account the emotional state of each individual. This has led to the issue of it being difficult to alleviate the anxiety and psychological burden felt by patients and their families.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their families and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for analyzing the emotional state from the user's input content, means for adjusting the most suitable information based on the analyzed emotional state, means for organizing the information obtained from the database and providing it to the patient and their families, and means for automatically generating a referral letter and providing it to the patient and their families. This makes it possible to provide medical information that takes into account the emotional state of the patient and their families, thereby reducing psychological burden and providing a sense of security.

[0311] "Patients and their families" refers to users who input symptoms and treatment details, as well as their supporters.

[0312] "Symptoms" refers to the specific medical conditions or symptoms that are required when seeking treatment or diagnosis from a medical institution.

[0313] "Desired treatment content" refers to the specific treatment method, treatment policy, and type of treatment desired by the patient and their family.

[0314] "Desired conditions" refer to specific conditions or requests that patients and their families want to consider when receiving treatment, such as the characteristics of the region or medical institution, or the doctor's specialty.

[0315] "Input means" refers to an interface that allows the user to send symptoms, desired treatment, and desired conditions to the system.

[0316] "Means for receiving and transmitting to the generative AI model" refers to the mechanism for receiving data entered by a user and passing it to the generative AI model for analysis.

[0317] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze input data and find the most suitable medical institution or doctor.

[0318] "Means for searching from the database" refers to the method by which the generative AI model searches and retrieves information about medical institutions and doctors from the database.

[0319] "Means for analyzing emotional state" refers to technology for identifying and analyzing emotions from user input.

[0320] "Means for adjusting optimal information" refers to a mechanism for appropriately customizing the medical information provided to the user based on the analyzed emotional state.

[0321] "Means of organizing and providing" refers to a method of appropriately organizing information on medical institutions and doctors obtained from the generative AI model and providing it to users in a format that is easy to understand.

[0322] "Means for automatically generating and providing a letter of introduction" refers to a mechanism for automatically creating a letter of introduction to be provided to a user based on information retrieved from a database and delivering it to the user.

[0323] "Means to support the reservation procedure" refers to procedures and support for smoothly making a reservation at the medical institution selected by the user.

[0324] "Means for checking the schedule of a medical institution and confirming a reservation" refers to a system for a user to check the availability of the medical institution where the user wishes to make a reservation and confirm the reservation.

[0325] This invention is a system that provides an online referral service that introduces patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide medical information and support according to the user's emotional state.

[0326] User terminal operation

[0327] Users use the web application to enter information such as their symptoms, desired treatment, and desired conditions. Specifically, users enter information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to" into text fields. Once the information is complete, they click the "Submit" button.

[0328] Server Operation

[0329] The server receives data sent from the user's device. Once this data is received, processing begins within the server. First, the received data is passed to a generative AI model for analysis. This generative AI model is used to understand the user's symptoms, desired conditions, and other data, and then searches a database for the most suitable medical institution and doctor.

[0330] Emotion Engine Operation

[0331] The server then passes the user's input to the emotion engine, which analyzes the user's sentences and identifies emotional states such as "anxiety," "impatience," and "calmness." For example, if a user enters the sentences "I've been diagnosed with breast cancer" and "I'd like the latest treatment," the emotion engine identifies the emotion of "anxiety." Based on this emotional state, the generative AI model adjusts the medical institutions and doctors it suggests, prioritizing options that provide greater peace of mind.

[0332] Organizing and providing information

[0333] The server organizes the information on the most suitable medical institution and doctor obtained from the generative AI model and automatically generates a referral letter. This referral letter includes the reason for selection and an evaluation of the patient's comfort level based on their emotional state. The generated information and referral letter are sent to the user's device, where they can be viewed.

[0334] Selection on the user device

[0335] The user checks the provided information and selects the most appropriate option from the listed medical institutions. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C," which the emotion engine has rated as "reliable," are listed, and the user can select "Medical Institution A."

[0336] Reservation procedure

[0337] The server checks the schedule of the selected medical institution and confirms the reservation. If necessary, it also provides options such as psychological counseling. Once the reservation is confirmed, the information is sent to the user's terminal.

[0338] Specific examples

[0339] A user uses a web application to enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "It should be located in a convenient location within Tokyo," and clicks the "Submit" button. This data is sent to the server, and the generative AI model begins analysis. The emotion engine recognizes "anxiety" from the input and prioritizes recommendations for the most appropriate medical institution, taking this emotion into consideration. As a result, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, with "Medical Institution A" being evaluated as the best for providing a sense of security. The server sends this information to the user's device, and the user selects "Medical Institution A." The server then confirms the appointment, offering the option of psychological counseling. Finally, the user receives the confirmed appointment information and can begin preparing for their visit to the medical institution.

[0340] Prompt Sentence Examples

[0341] An example of a prompt sentence that a user can enter is, "I have been diagnosed with breast cancer and am looking for a hospital in Tokyo that offers the latest treatments. Please give priority to recommendations of reliable medical institutions."

[0342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0343] Step 1:

[0344] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. The input data is text information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to." Once the input is complete, the user clicks the "Submit" button to send the data to the server. The input in this case is text data, and the output is an HTTP POST request sent to the server.

[0345] Step 2:

[0346] The terminal receives data entered by the user and sends it to the server as an HTTP POST request. Specifically, it serializes the input data into JSON format and sends it to the appropriate API endpoint. The input is text data entered by the user, and the output is an HTTP request to the server.

[0347] Step 3:

[0348] The server receives data sent from the device. The received data (input) is JSON format data containing text information and desired conditions. The server parses this data and prepares it to be passed to the generative AI model. The parsed data is passed to the generative AI model as output.

[0349] Step 4:

[0350] The server passes the received user symptoms and desired condition data to the generative AI model and begins analysis. The input is text data describing the symptoms and desired conditions, and the generative AI model analyzes this to understand the user's situation. The output is a list of candidates for the most suitable medical institutions and doctors.

[0351] Step 5:

[0352] The server passes the analyzed data to the emotion engine, which analyzes the user's emotional state. Specifically, it identifies emotions such as "anxiety," "impatience," and "calmness" based on the input data. For example, it can sense "anxiety" from the text "I've been diagnosed with breast cancer" and "I hope for the latest treatment." The output is the identified emotional state, and the results of the generative AI model are adjusted as needed.

[0353] Step 6:

[0354] The server uses the emotional data obtained from the emotion engine to adjust the medical institutions and doctor candidates provided by the generative AI model. The input is the analyzed emotional state and a list of medical institutions, and the output is a list of optimal medical institutions that takes the emotional state into consideration. This allows the information provided to the user to be adjusted based on the user's emotional state.

[0355] Step 7:

[0356] The server organizes the information of the coordinated medical institutions and doctors and automatically generates a referral letter. The input is a list of coordinated medical institutions and emotion analysis data, and the output is an automatically generated referral letter and organized medical institution information. The referral letter includes the reason for recommendation and an evaluation of comfort based on the patient's emotional state.

[0357] Step 8:

[0358] The server sends the generated referral letter and organized medical institution information to the user terminal. The input is the referral letter and medical institution information, and the output is the data sent to the user terminal. The user terminal receives this and prepares to display it on the screen.

[0359] Step 9:

[0360] The user checks the provided medical institution information and referral letter. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, and the user selects "Medical Institution A," which the emotion engine evaluates as "reliable." The input is the medical institution information provided to the user, and the output is the user's selection.

[0361] Step 10:

[0362] The server checks the schedule of the medical institution selected by the user and confirms the appointment. The input is the user's selection data and the medical institution's schedule information, and the output is the confirmed appointment information. In addition, options such as psychological counseling are provided if necessary.

[0363] Step 11:

[0364] The server notifies the user terminal of the confirmed reservation information and support information. The input is the confirmed reservation information and support information, and the output is a notification sent to the user terminal. The user terminal displays the received reservation information and support information and notifies the user.

[0365] (Application example 2)

[0366] 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."

[0367] Conventional medical institution referral systems refer patients to medical institutions and doctors simply based on the symptoms and desired conditions entered, without considering the emotional state of the patient or their family. This makes it difficult to select an appropriate medical institution when users are in a mentally unstable state. Furthermore, they lack the functionality to provide appropriate psychological support to users who feel anxious. Therefore, there is a need for a system that can introduce the most appropriate medical institution while reducing the user's mental burden and providing a sense of security.

[0368] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input their symptoms, desired treatment details, desired conditions, and concerns; means for receiving the information input by the patient and their family and sending it to the generative AI model; means for the generative AI model to analyze and search a database for the most appropriate medical institution and doctor; emotion analysis means, including emotion analysis means, for analyzing the emotional state of the patient and their family; means for the generative AI model to adjust the selection of a medical institution and doctor based on the emotion analysis results; means for organizing the information obtained from the database and the emotion analysis results and providing them to the patient and their family; means for automatically generating a referral letter and providing it to the patient and their family; and means for supporting the reservation procedure. This enables the server to introduce the most appropriate medical institution and doctor based on the user's emotional state, providing peace of mind and allowing the user to receive appropriate medical services.

[0369] "Patients and their families" refers to the person with the illness and their relatives and close friends who provide support to that person.

[0370] A "symptom" is a physical or psychological symptom associated with a disease or disorder.

[0371] "Desired treatment" refers to the specific treatment methods and types of medical services desired by patients and their families.

[0372] "Desired conditions" are conditions and requests that patients and their families place particular importance on when it comes to treatment, such as location, cost, and doctor's expertise.

[0373] "Anxiety points" are psychological concerns or anxiety factors that patients and their families have regarding treatment or diagnosis.

[0374] A "generative AI model" is a model that uses artificial intelligence technology to analyze user input information and generate optimal suggestions.

[0375] A "database" is a collection of digital data used to organize and manage detailed information about medical institutions and doctors.

[0376] "Emotion analysis means" is a technology that analyzes and recognizes the emotional state of patients and their families.

[0377] "Adjustment based on the results of sentiment analysis" means changing or adjusting the content or quality of the service provided to users based on the results of sentiment analysis.

[0378] A "letter of referral" is an official document used when referring a patient to a medical institution, and is used to provide the patient's information to the doctor or institution to which the patient is referred.

[0379] "Psychological counseling options" are options and services that provide psychological support for anxiety and stress experienced by patients and their families.

[0380] The "reservation procedure" refers to the process of making an appointment in advance to receive the medical service a user desires.

[0381] This invention is a system that provides optimal information to patients and their families when searching for medical institutions and doctors, thereby reducing their psychological anxiety. The system of this invention combines a generative AI model and emotion analysis means to recommend appropriate medical institutions and doctors taking into account the user's emotional state.

[0382] System configuration

[0383] This system mainly consists of the following hardware and software:

[0384] Hardware

[0385] 1. User device: A device used by the user to input information, such as a smartphone or tablet.

[0386] 2. Server: Cloud server used for data processing and storage.

[0387] 3. Database: A database that manages information about medical institutions and doctors.

[0388] software

[0389] 1. Generative AI model: OpenAI's GPT-3 is used.

[0390] 2. Sentiment analysis method: Google Cloud Natural Language API.

[0391] System Operation

[0392] Users can use a device such as a smartphone or tablet to input their symptoms, desired treatment, desired conditions, and concerns. Specific prompts such as the following can be used:

[0393] Prompt Sentence Examples

[0394] The user is feeling anxious. Considering this situation, please suggest the following security measures: Condition: Suspicious activity has been observed recently around the home

[0395] 1. Installing security cameras

[0396] 2. Strengthening entrance doors and windows

[0397] 3. Check the contact details of nearby police stations and security companies

[0398] The information entered by the user is sent to a server. The server uses the Google Cloud Natural Language API to analyze the user's emotional state from the input. For example, an emotional state such as "anxiety" is recognized. The information along with the analyzed emotional state is then sent to a generative AI model, which searches a database for the most suitable medical institution or doctor.

[0399] The generative AI model selects the most suitable medical institutions and doctors based on the user's desired conditions and adjusts the recommendations taking into account the results of sentiment analysis. For example, if the user is feeling "anxious," it will prioritize recommendations of medical institutions that can provide greater reassurance. This allows the user to make appropriate medical choices with peace of mind.

[0400] Information and booking procedures

[0401] The server sends information about medical institutions organized based on the results of the generative AI model and emotion analysis to the user's device. The user can view the received information and select the most suitable medical institution. The server then checks the medical institution's schedule and confirms the appointment, taking into account the emotion analysis results. For example, if a user feels "anxious," it may also offer the option of psychological counseling.

[0402] Users can receive appointment confirmation and additional support information to plan their visit to a medical facility, providing peace of mind and ensuring appropriate medical services are provided.

[0403] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0404] Step 1:

[0405] Users use devices such as smartphones or tablets to input their symptoms, desired treatment, desired conditions, and concerns. This information is entered in text format and sent from the user's device to the server. The input data is used as preparation data for analysis in the next step.

[0406] Step 2:

[0407] The server receives input information from the user's device and performs emotion analysis using the Google Cloud Natural Language API. Specifically, the input text data is sent to the API, and an emotion score is obtained from it as the analysis result. The emotion analysis results are output as emotional states such as "anxiety" or "impatience."

[0408] Step 3:

[0409] The server sends the results of the sentiment analysis along with the conditions entered by the user to a generative AI model (OpenAI's GPT-3). The generative AI model uses the prompt to suggest the most suitable medical institution or doctor. Examples of prompts include, "The user is feeling anxious. Considering this situation, please suggest medical institutions with the following conditions: latest treatments" and "location within Tokyo that is easy to get to." The input data is combined with the results of the sentiment analysis to output a list of the most suitable medical institutions.

[0410] Step 4:

[0411] The server receives the list of medical institutions and doctors obtained from the generative AI model and uses that list to search a database, which contains detailed information about the medical institutions, the doctors' specialties, and their ratings. An organized list of recommended medical institutions is created based on the search results.

[0412] Step 5:

[0413] The server sends a list of recommended medical institutions to the user's terminal. This list includes medical institutions that provide a sense of security based on the results of sentiment analysis. The user can view this list and select the medical institution that best suits them. The user's selection is sent back to the server in the next step.

[0414] Step 6:

[0415] The server receives the user's selection, checks the schedule of the selected medical institution, checks the schedule against the medical institution's database to determine availability, and then generates a notification to confirm the appointment.

[0416] Step 7:

[0417] The server confirms the reservation and sends the confirmed reservation information to the user's device. Furthermore, if psychological counseling options are required based on the results of the emotion analysis, that information is also provided. This allows the user to receive all the necessary information and prepare for their visit to the medical institution with peace of mind.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] [Second embodiment]

[0422] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0433] 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."

[0434] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. This system utilizes a generative AI model to analyze and provide medical information based on the patient's and their family's medical condition and treatment preferences, and supports the creation of referral letters and reservation procedures.

[0435] Basic structure and operation of the system

[0436] User terminal operation

[0437] Using a web application, users input their symptoms, desired treatment, and desired conditions. For example, a user might enter data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like a hospital in Tokyo that's easy to get to." This input information is sent to the server with a single click.

[0438] Server Operation

[0439] The server receives the information sent by the user. The received information is sent to the generative AI model, where analysis begins. Based on the received data, the generative AI model understands the patient's condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[0440] The generative AI model selects the most suitable medical institutions and doctors based on criteria such as "breast cancer," "latest treatments," and "located in Tokyo." The server organizes this information and prepares it for delivery to the user. It also automatically generates referral letters and saves them in the appropriate format.

[0441] Reply to user terminal

[0442] The server sends the organized medical institution information and referral letters to the user's terminal, which receives and displays the information. The user can then view detailed information on the listed medical institutions and select the most appropriate option.

[0443] For example, the user selects "Medical Institution A" from among "Medical Institution A," "Medical Institution B," and "Medical Institution C." This selection information is sent to the server, which then assists in the reservation procedure at the selected medical institution.

[0444] Reservation procedure

[0445] The server checks the schedule of the selected medical institution and confirms the reservation. At this time, adjustments are made depending on the reservation status, and once the reservation is confirmed, the information is notified to the user's terminal. The user can then check the confirmed reservation information and proceed with preparations to visit the medical institution.

[0446] Specific examples

[0447] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins its analysis. It searches the database for medical institutions that meet the conditions, and lists "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[0448] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the reservation. The user receives the confirmed reservation information and can plan their visit to the medical institution.

[0449] In this way, this invention uses a generative AI model to quickly and accurately provide patients and their families with the most suitable medical institutions and doctors they desire, thereby reducing the burden of medical care selection. Support for creating referral letters and booking procedures can also be done online, allowing patients and their families to use the service without being restricted by time or location.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. For example, they might enter "breast cancer" as the symptom, "latest treatment" as the desired treatment, and "within Tokyo" as the condition.

[0453] Step 2:

[0454] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[0455] Step 3:

[0456] The server receives data sent from the user's device and sends it to the generative AI model for analysis. The received data is stored in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[0457] Step 4:

[0458] The server's generative AI model analyzes the user's input data and searches the database for the most suitable medical institution or doctor. For example, the generative AI model extracts the best matching candidates based on the keywords "breast cancer," "latest treatment," and "Tokyo."

[0459] Step 5:

[0460] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[0461] Step 6:

[0462] The server organizes the acquired information on medical institutions and doctors and creates an information package to provide to the user. For example, it compiles detailed information on medical institutions A, B, C, etc. into a list.

[0463] Step 7:

[0464] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, and conditions.

[0465] Step 8:

[0466] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[0467] Step 9:

[0468] The user terminal receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C and the created referral letter are displayed on the screen.

[0469] Step 10:

[0470] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[0471] Step 11:

[0472] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[0473] Step 12:

[0474] The server notifies the user that the reservation has been confirmed. A reservation confirmation email or app notification is sent to the user.

[0475] Example 1

[0476] 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."

[0477] In modern medicine, it is extremely difficult for patients and their families to select the most appropriate medical institution and doctor. Especially in the case of serious illnesses, quick decisions based on reliable information are necessary. However, independently collecting and analyzing vast amounts of medical information requires time and effort, and there is a risk of making the wrong choice. Furthermore, the process of creating referral letters and making appointments is cumbersome, placing a significant burden on patients and their families. A system that solves these problems and provides patients and their families with the best medical options is needed.

[0478] 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.

[0479] In this invention, the server includes: a means for patients and their families to input their symptoms, desired treatment, and desired conditions; a means for receiving the information input by the patient and their family and sending it to the generative AI model; a means for the generative AI model to analyze the information using prompts and search a database for the most suitable medical institution and doctor; a means for organizing the information obtained from the database and providing it to the patient and their family; a means for automatically generating a referral letter and providing it to the patient and their family; a means for re-receiving information about the medical institution selected by the patient; and a means for notifying a user terminal of the medical institution's confirmed appointment information. This allows patients and their families to quickly select the most suitable medical institution and doctor based on reliable information. Furthermore, the automatic generation of referral letters and assistance with appointment procedures can reduce the burden on patients and their families.

[0480] "Patients" or "their families" are people who require medical services and their close relatives who provide support.

[0481] A "symptom" refers to a specific problem or symptom related to a patient's health.

[0482] "Treatment preference" means the specific type of medical treatment or therapy desired by the patient.

[0483] "Desired conditions" refer to the geographical, time, and facility requirements that patients and their families consider important when selecting a medical institution.

[0484] "Input means" refers to the mechanism by which a user enters and submits information using a web application or other interface.

[0485] "Receiving means" refers to a function that allows the server to receive information sent by the user.

[0486] A "generative AI model" refers to an artificial intelligence algorithm that analyzes information entered by patients and their families and selects the most appropriate medical institution and doctor.

[0487] A "prompt" is a short sentence or combination of keywords used to provide input to a generative AI model and serve as the basis for analysis.

[0488] "Database" refers to an electronic data storage system for storing data such as details, ratings, and locations of medical institutions and physicians.

[0489] "Organization means" refers to the function for organizing information obtained from a generative AI model into an easy-to-understand format.

[0490] "Means of delivery" refers to the mechanism for delivering organized information and generated referral letters to patients and their families.

[0491] A "letter of referral" refers to a referral document to a medical institution that is prepared based on the patient's medical condition and treatment wishes.

[0492] "Selected information" refers to information about a specific medical institution selected by the patient or their family from the medical institution information provided.

[0493] "Reservation procedure support means" refers to the support functions required to confirm a reservation at the selected medical institution.

[0494] "Reservation confirmation information" refers to information indicating that a reservation has been confirmed after checking the schedule of the medical institution.

[0495] The present invention provides a system for providing an online referral service that enables patients and their families to quickly and accurately select the most suitable medical institution and doctor, and supports the creation of referral letters and reservation procedures. An embodiment of this system will be described in detail below.

[0496] Basic structure and operation

[0497] User terminal operation

[0498] Users use a web application provided through a web browser on their PC or smartphone (e.g., Google Chrome, Mozilla Firefox) to input their symptoms, desired treatment, and desired conditions. For example, they input data such as "I've been diagnosed with breast cancer," "I'd like a hospital that offers the latest treatments," and "A location within Tokyo that's easy to get to." After completing the input, they click the send button to send this information to the server.

[0499] Server Operation

[0500] The server receives user-submitted information via an HTTP POST request. To process this information, the server leverages a generative AI model (e.g., GPT-4 or BERT). The received user data is transformed into a prompt like this:

[0501] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[0502] This prompt sentence is input into the generative AI model and analysis begins.

[0503] Analysis using generative AI models

[0504] The generative AI model analyzes the user's medical condition and desired conditions, and searches a database for appropriate medical institutions and doctors. The database contains detailed information on multiple medical institutions and doctors. For example, it identifies the most suitable medical institution and doctor based on the conditions "breast cancer," "latest treatment," and "within Tokyo."

[0505] Data organization and referral generation

[0506] The server integrates the information obtained from the generative AI model and prepares it for delivery to the user. This information is organized in JSON format and provided to the user via a web application. The server also automatically generates a referral letter and saves it in PDF format. This referral letter includes the patient's medical condition, desired conditions, recommended treatment, and other information.

[0507] Sending information to user terminals

[0508] The organized medical institution information and referral letter are sent to the user's device as an HTTP response, where the user can view the information and check the details on the web application.

[0509] Reservation procedure

[0510] Once the user selects the most suitable medical institution, the selection information is sent back to the server. The server then checks the schedule of the selected medical institution via API and confirms the reservation. The confirmed reservation information is then sent to the user's device. The user can then receive the confirmed reservation information and prepare for their hospital visit.

[0511] Specific examples

[0512] For example, a user enters the criteria "breast cancer," "latest treatment," and "location within Tokyo that is easy to get to." This information is sent to the server, and the generative AI model begins its analysis. The prompt is as follows:

[0513] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[0514] Based on the analysis results, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is created from the database. This information is organized and provided to the user.

[0515] When the user selects "Medical Institution A," that information is sent to the server again. The server then checks the schedule of "Medical Institution A" and sends the confirmed reservation information to the user's terminal. The user can use this information to plan their hospital visit.

[0516] This way, patients and their families can easily find good medical institutions and doctors and get the necessary procedures done quickly and efficiently.

[0517] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0518] Step 1:

[0519] User input of information

[0520] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. At this time, they enter information such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "It should be located in Tokyo and be easy to get to" as text into the input form. Once they have completed the input, they click the send button, which sends the entered information to the server.

[0521] Input: Symptoms and wishes entered by the user into the web application

[0522] Output: The input information is sent to the server as an HTTP request.

[0523] Step 2:

[0524] Server receives information

[0525] The server receives information sent by the user via an HTTP POST request, temporarily stores the received data in JSON format, and converts it into a format that can be input to the generative AI model.

[0526] Input: User-submitted information in JSON format

[0527] Output: Prompt sentence to be input to the generative AI model

[0528] Step 3:

[0529] Analysis using generative AI models

[0530] The server inputs a prompt into the generative AI model and begins analysis. For example, the prompt might be "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo." The generative AI model uses this prompt to analyze the most suitable medical institution and doctor.

[0531] Input: prompt statement

[0532] Output: Analysis results from the generative AI model (list of optimal medical institutions and doctors)

[0533] Step 4:

[0534] Searching from the database

[0535] The server searches a database for detailed information on the most suitable medical institution and doctor based on the analysis results of the generative AI model. The database stores detailed information on hospitals and clinics, as well as the doctor's specialty and reputation. For example, based on the analysis results of the criteria "breast cancer," "latest treatment," and "within Tokyo," the server searches for "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[0536] Input: Analysis results of the generative AI model

[0537] Output: Information on the most suitable medical institution and doctor obtained from the database

[0538] Step 5:

[0539] Organizing information and generating referral letters

[0540] The server organizes the information obtained from the database and prepares it for delivery to the user. This information is consolidated into an easy-to-understand format, such as JSON. At the same time, the server automatically generates a referral letter, which describes the patient's condition, desired conditions, and recommended treatment, and is saved in PDF format.

[0541] Input: Medical institution information obtained from the database

[0542] Output: Organized medical institution information and referral letter (PDF format)

[0543] Step 6:

[0544] Sending information to user terminals

[0545] The server sends the organized medical institution information and referral letter to the user's device as an HTTP response. The user can view this information on the web application and check the details.

[0546] Input: Organized medical institution information and referral letter (PDF format)

[0547] Output: Medical institution information and referral letter displayed on the user's terminal

[0548] Step 7:

[0549] User selection of medical institution

[0550] The user views the medical institution information provided on the web application and selects the most appropriate option from "Medical Institution A," "Medical Institution B," or "Medical Institution C." The selected information is then sent back to the server.

[0551] Input: Information about the medical institution selected by the user

[0552] Output: Selection information is sent to the server

[0553] Step 8:

[0554] Server-based reservation process

[0555] The server receives the information about the medical institution selected by the user and checks the schedule of that institution. It then uses an API to connect to the medical institution's reservation system and confirms the reservation. Once the reservation is confirmed, the server notifies the user's device of the reservation confirmation information.

[0556] Input: Information about the medical institution selected by the user

[0557] Output: Confirmed reservation information is sent to the user's device.

[0558] Step 9:

[0559] User confirms reservation and prepares visit

[0560] The user can then confirm the confirmed reservation information on the web application. After confirming that the reservation information has been confirmed, the user can then prepare to visit the medical institution.

[0561] Input: Confirmed reservation information

[0562] Output: User confirms appointment and begins visit preparation

[0563] (Application example 1)

[0564] 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."

[0565] In conventional medical referral systems, there is a high risk of medical information entered by patients and their families being leaked to the outside, making security a major issue. There is also a need to improve the accuracy of analysis based on the patient's medical condition and desired conditions, which makes it difficult to find the most suitable medical institution or doctor.

[0566] 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.

[0567] In this invention, the server includes means for patients and their families to input their symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their family and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for organizing the information obtained from the database and providing it to the patient and their family, means for automatically generating a referral letter and providing it to the patient and their family, means for encrypting the input information, and means for decrypting the encrypted information. This enables quick and accurate referral to the most suitable medical institution and doctor while protecting the patient's confidential information with high security.

[0568] "Patients and their families" refers to individuals who require medical services and their supporters.

[0569] "Symptoms" refer to abnormalities or distress in the patient's body or mind.

[0570] "Desired treatment details" is information indicating the specific treatment methods and medical services desired by the patient and their family.

[0571] "Desired conditions" refers to specific requests regarding medical institutions and treatment, such as location, date and time, and specialty.

[0572] "Means of input" refers to the interface or device through which a user provides information to a system.

[0573] "Means for receiving" refers to a mechanism for receiving information sent by a user.

[0574] A "generative AI model" refers to a program that uses artificial intelligence technology to analyze input data and generate optimal answers or suggestions.

[0575] A "database" refers to a system that systematically organizes and manages information about medical institutions and doctors, making it searchable.

[0576] "Search methods" refer to algorithms or programs used to find information that meets specific criteria from a database.

[0577] "Means for organizing and presenting" refers to the mechanism for presenting the searched information to the user in an easy-to-understand format.

[0578] "Means for automatically generating a letter of introduction" refers to a program that automatically creates a letter of introduction based on information entered by the user and the results of analysis.

[0579] "Encryption methods" refers to techniques for converting information into a form that cannot be deciphered by third parties.

[0580] "Means to decrypt" refers to the technology used to restore encrypted information to its original form.

[0581] The system of the present invention provides an online referral service that introduces optimal medical institutions and doctors based on the results of analysis by a generative AI model after patients and their families input their medical information. This system includes the following means.

[0582] User terminal operation

[0583] The user terminal provides an interface for patients and their families to input information such as symptoms, desired treatment, desired conditions, etc. For example, a user might input data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like to go to a hospital in Tokyo that's easy to get to." This input information is encrypted and sent to the server.

[0584] Server Operation

[0585] The server receives the entered medical information and first decrypts the encrypted data. It then requests the generative AI model to analyze it. The generative AI model then searches the database for the most suitable medical institution and doctor based on the decrypted data. In this process, the generative AI model performs its analysis using prompts such as the following:

[0586] "Find accessible hospitals in Tokyo that offer the latest treatments for breast cancer patients."

[0587] Database search and information organization

[0588] The generative AI model searches the database for candidate medical institutions and doctors and extracts relevant information. For example, based on the criteria "breast cancer," "latest treatment," and "within Tokyo," it will select "Medical Institution A," "Medical Institution B," and "Medical Institution C." This information is then organized and prepared for provision to patients and their families.

[0589] Automatic generation of referral letters

[0590] The server automatically generates a referral letter based on the extracted information. The referral letter includes the patient's medical condition, requests, and information on recommended medical institutions and doctors. The generated referral letter is also encrypted when stored and transmitted.

[0591] Confirmation and booking process

[0592] The server sends the organized information and referral letter to the user's terminal, where the user confirms it. For example, the user selects "Medical Institution A" from "Medical Institution A," "Medical Institution B," and "Medical Institution C." The selected information is sent to the server, which checks the schedule of the selected medical institution and assists with the reservation procedure.

[0593] Hardware and software used

[0594] The system uses user devices (smartphones, tablets, PCs), a server, a generative AI model, a database, and encryption / decryption technology. As a specific example, it uses the Python Cryptography package for encryption and decryption.

[0595] example:

[0596] Data entered by the user: "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," "A location in Tokyo that is easy to get to."

[0597] Prompt for generative AI model: "Find hospitals in Tokyo that offer the latest treatments for breast cancer patients and are easy to get to."

[0598] This enables quick and accurate referral to the most appropriate medical institution or doctor while protecting patient confidential information with high security.

[0599] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0600] Step 1:

[0601] The user uses the terminal to input information such as symptoms, desired treatment, and desired conditions.

[0602] Input: The user enters data such as "breast cancer," "latest treatment," and "locations in Tokyo that are easy to get to."

[0603] Output: The input data

[0604] What happens: The user enters information into the interface and clicks the submit button.

[0605] Step 2:

[0606] The terminal encrypts the information entered by the user and sends it to the server.

[0607] Input: Data entered

[0608] Output: Encrypted data

[0609] Specific operation: The terminal uses the encryption module (Python Cryptography package) to encrypt the input data and sends the encrypted data to the server.

[0610] Step 3:

[0611] The server receives and decrypts the encrypted data.

[0612] Input: Encrypted data

[0613] Output: Decrypted data

[0614] Specific operation: Receives encrypted data on the server side and uses a decryption module to restore the original information.

[0615] Step 4:

[0616] The server sends the decrypted data to the generative AI model and requests it to analyze it.

[0617] Input: Decrypted data

[0618] Output: Analysis request to the generative AI model

[0619] Specific behavior: The server generates a prompt based on the content of the data,

[0620] "Find an easily accessible hospital in Tokyo that offers the latest treatments for breast cancer patients."

[0621] This prompt is sent to the generative AI model.

[0622] Step 5:

[0623] The generative AI model searches a database for the most suitable medical institution or doctor based on the prompt text.

[0624] Input: prompt statement

[0625] Output: List of medical institutions and doctors

[0626] How it works: The generative AI model analyzes the prompt, searches for corresponding database entries, and lists appropriate medical institutions and doctors.

[0627] Step 6:

[0628] The server organizes information about medical institutions and doctors obtained from the generative AI model.

[0629] Input: List of medical institutions and doctors

[0630] Output: Organized medical information

[0631] Specific operation: The server organizes the information extracted from the database according to a format and prepares it in a form that can be provided to the user.

[0632] Step 7:

[0633] The server automatically generates and encrypts a referral letter based on the organized medical information.

[0634] Input: Organized medical information

[0635] Output: Encrypted letter of introduction

[0636] Specific operation: The referral letter generation module creates a referral letter based on the listed information of medical institutions and doctors and the information entered by the user, and then encrypts it.

[0637] Step 8:

[0638] The server transmits the encrypted referral letter and medical information to the user terminal.

[0639] Input: Encrypted letter of introduction

[0640] Output: Sending data to the user's terminal

[0641] What it does: The server sends the encrypted referral letter and medical information and makes it accessible to the user.

[0642] Step 9:

[0643] The user can view the medical information and referral letter sent to them and select the most suitable medical institution and doctor.

[0644] Input: Encrypted letter of introduction

[0645] Output: User selection information

[0646] Specific operations: The device decrypts the data received and displays it in a form that can be viewed by the user. The user makes a selection and sends the selection to the server.

[0647] Step 10:

[0648] The server assists the user in making a reservation at a medical institution based on the user's selection information.

[0649] Input: User selection information

[0650] Output: Reservation information

[0651] Specific operation: The server checks the schedule of the selected medical institution and confirms the corresponding appointment.

[0652] Step 11:

[0653] The server notifies the user terminal of the information that the reservation has been confirmed.

[0654] Input: Reservation information

[0655] Output: Booking confirmation notice

[0656] Specific operation: Send a notification to the user's device and display the reservation information.

[0657] 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.

[0658] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention provides medical information and support according to the user's emotional state.

[0659] Basic structure and operation of the system

[0660] User terminal operation

[0661] The user uses a web application to input their symptoms, desired treatment, and desired conditions. For example, the user might input data such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "I would like a hospital in Tokyo that is easy to get to." This input information is sent to the server when the user clicks the "Submit" button.

[0662] Server Operation

[0663] The server receives the information sent by the user. The received information is sent to the generative AI model, which begins analyzing it. The generative AI model understands the user's medical condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[0664] Combining Emotion Engines

[0665] Here, the emotion engine recognizes the user's emotional state from the content of their input. For example, it analyzes the emotions of "anxiety," "impatience," and "calmness" from the user's input text. The emotion engine adjusts the recommendations generated by the AI ​​model based on this emotional state.

[0666] The generative AI model not only selects the most suitable medical institutions and doctors based on the criteria of "breast cancer," "latest treatments," and "located in Tokyo," but also prioritizes medical institutions and doctors that users feel more comfortable with, taking into account the state of "anxiety" recognized by the emotion engine. The server organizes this information and prepares it for provision to the user. It also automatically generates a referral letter and saves it in the appropriate format.

[0667] Reply to user terminal

[0668] The server sends the organized medical institution information and referral letters to the user's device. The user's device receives this and displays the information. The user can view detailed information about the listed medical institutions and check recommended options based on their emotional state. For example, from among "Medical Institution A," "Medical Institution B," and "Medical Institution C," the user can select "Medical Institution A," which has been rated as "reliable" by the emotion engine.

[0669] Reservation procedure

[0670] The server checks the schedule of the selected medical institution and confirms the appointment. At this time, it also provides necessary support information and resources based on the user's emotional state. For example, if a user is feeling excessive anxiety, it may provide support such as presenting psychological counseling options. Once the appointment is confirmed, the information is sent to the user's device. The user receives the confirmed appointment information and can begin preparing to visit the medical institution.

[0671] Specific examples

[0672] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins analysis. At that time, the emotion engine recognizes the emotion of "anxiety" from the user's input, and taking this result into consideration, prioritizes recommending medical institutions that can provide a greater sense of security. For example, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is displayed, but the emotion engine evaluates "Medical Institution A" as being the best for providing a sense of security.

[0673] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the appointment. Furthermore, to address the anxious emotional state, an option for psychological counseling is also provided. The user receives the confirmed appointment and additional support information, allowing them to plan their visit to the medical institution.

[0674] In this way, the present invention utilizes a generative AI model and an emotion engine to provide optimal medical information according to the user's emotional state, thereby reducing the burden of medical selection and providing safer and more reliable medical services.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] Users open the web application and enter their symptoms, desired treatment, and desired conditions. For example, they enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "I want a hospital in a convenient location in Tokyo."

[0678] Step 2:

[0679] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[0680] Step 3:

[0681] The server receives data from the user's device and sends the received information to the generative AI model and emotion engine. The received data is saved in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[0682] Step 4:

[0683] The emotion engine analyzes the user's input data and recognizes their emotional state. For example, it analyzes emotions such as "anxiety," "impatience," and "calmness." This emotional state data is passed to the generative AI model.

[0684] Step 5:

[0685] The server's generative AI model analyzes the user's symptoms and desired conditions, and also considers the emotional state from the emotion engine to search for the most suitable medical institution or doctor from the database. For example, the generative AI model extracts the best matching candidates by considering the keywords "breast cancer," "latest treatments," and "Tokyo area" as well as the emotion of "anxiety."

[0686] Step 6:

[0687] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[0688] Step 7:

[0689] The server organizes the information on medical institutions and doctors it has acquired and creates an information package that takes into account the results of the emotion engine. For example, detailed information on medical institutions A, B, and C is compiled into a list, and medical institution A is evaluated as providing the most reassurance.

[0690] Step 8:

[0691] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, conditions, and emotional state.

[0692] Step 9:

[0693] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[0694] Step 10:

[0695] The user device receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C, along with the created referral letter, are displayed on the screen. Based on the evaluation by the emotion engine, medical institution A is displayed as the most reliable.

[0696] Step 11:

[0697] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[0698] Step 12:

[0699] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[0700] Step 13:

[0701] The server notifies the user that the reservation has been confirmed. A confirmation email or app notification is sent to the user. Based on the emotion engine, additional support information may be provided, including psychological counseling options.

[0702] Through these small steps, users can feel at ease when selecting a medical institution using the emotion engine, and can easily proceed with creating a referral letter and making a reservation.

[0703] Example 2

[0704] 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."

[0705] In conventional medical information provision systems, even if patients and their families input their symptoms and desired conditions, they simply refer them to the most suitable medical institution or doctor based on that information, and do not provide sufficient support that takes into account the emotional state of each individual. This has led to the issue of it being difficult to alleviate the anxiety and psychological burden felt by patients and their families.

[0706] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their families and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for analyzing the emotional state from the user's input content, means for adjusting the most suitable information based on the analyzed emotional state, means for organizing the information obtained from the database and providing it to the patient and their families, and means for automatically generating a referral letter and providing it to the patient and their families. This makes it possible to provide medical information that takes into account the emotional state of the patient and their families, thereby reducing psychological burden and providing a sense of security.

[0707] "Patients and their families" refers to users who input symptoms and treatment details, as well as their supporters.

[0708] "Symptoms" refers to the specific medical conditions or symptoms that are required when seeking treatment or diagnosis from a medical institution.

[0709] "Desired treatment content" refers to the specific treatment method, treatment policy, and type of treatment desired by the patient and their family.

[0710] "Desired conditions" refer to specific conditions or requests that patients and their families want to consider when receiving treatment, such as the characteristics of the region or medical institution, or the doctor's specialty.

[0711] "Input means" refers to an interface that allows the user to send symptoms, desired treatment, and desired conditions to the system.

[0712] "Means for receiving and transmitting to the generative AI model" refers to the mechanism for receiving data entered by a user and passing it to the generative AI model for analysis.

[0713] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze input data and find the most suitable medical institution or doctor.

[0714] "Means for searching from the database" refers to the method by which the generative AI model searches and retrieves information about medical institutions and doctors from the database.

[0715] "Means for analyzing emotional state" refers to technology for identifying and analyzing emotions from user input.

[0716] "Means for adjusting optimal information" refers to a mechanism for appropriately customizing the medical information provided to the user based on the analyzed emotional state.

[0717] "Means of organizing and providing" refers to a method of appropriately organizing information on medical institutions and doctors obtained from the generative AI model and providing it to users in a format that is easy to understand.

[0718] "Means for automatically generating and providing a letter of introduction" refers to a mechanism for automatically creating a letter of introduction to be provided to a user based on information retrieved from a database and delivering it to the user.

[0719] "Means to support the reservation procedure" refers to procedures and support for smoothly making a reservation at the medical institution selected by the user.

[0720] "Means for checking the schedule of a medical institution and confirming a reservation" refers to a system for a user to check the availability of the medical institution where the user wishes to make a reservation and confirm the reservation.

[0721] This invention is a system that provides an online referral service that introduces patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide medical information and support according to the user's emotional state.

[0722] User terminal operation

[0723] Users use the web application to enter information such as their symptoms, desired treatment, and desired conditions. Specifically, users enter information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to" into text fields. Once the information is complete, they click the "Submit" button.

[0724] Server Operation

[0725] The server receives data sent from the user's device. Once this data is received, processing begins within the server. First, the received data is passed to a generative AI model for analysis. This generative AI model is used to understand the user's symptoms, desired conditions, and other data, and then searches a database for the most suitable medical institution and doctor.

[0726] Emotion Engine Operation

[0727] The server then passes the user's input to the emotion engine, which analyzes the user's sentences and identifies emotional states such as "anxiety," "impatience," and "calmness." For example, if a user enters the sentences "I've been diagnosed with breast cancer" and "I'd like the latest treatment," the emotion engine identifies the emotion of "anxiety." Based on this emotional state, the generative AI model adjusts the medical institutions and doctors it suggests, prioritizing options that provide greater peace of mind.

[0728] Organizing and providing information

[0729] The server organizes the information on the most suitable medical institution and doctor obtained from the generative AI model and automatically generates a referral letter. This referral letter includes the reason for selection and an evaluation of the patient's comfort level based on their emotional state. The generated information and referral letter are sent to the user's device, where they can be viewed.

[0730] Selection on the user device

[0731] The user checks the provided information and selects the most appropriate option from the listed medical institutions. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C," which the emotion engine has rated as "reliable," are listed, and the user can select "Medical Institution A."

[0732] Reservation procedure

[0733] The server checks the schedule of the selected medical institution and confirms the reservation. If necessary, it also provides options such as psychological counseling. Once the reservation is confirmed, the information is sent to the user's terminal.

[0734] Specific examples

[0735] A user uses a web application to enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "It should be located in a convenient location within Tokyo," and clicks the "Submit" button. This data is sent to the server, and the generative AI model begins analysis. The emotion engine recognizes "anxiety" from the input and prioritizes recommendations for the most appropriate medical institution, taking this emotion into consideration. As a result, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, with "Medical Institution A" being evaluated as the best for providing a sense of security. The server sends this information to the user's device, and the user selects "Medical Institution A." The server then confirms the appointment, offering the option of psychological counseling. Finally, the user receives the confirmed appointment information and can begin preparing for their visit to the medical institution.

[0736] Prompt Sentence Examples

[0737] An example of a prompt sentence that a user can enter is, "I have been diagnosed with breast cancer and am looking for a hospital in Tokyo that offers the latest treatments. Please give priority to recommendations of reliable medical institutions."

[0738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0739] Step 1:

[0740] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. The input data is text information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to." Once the input is complete, the user clicks the "Submit" button to send the data to the server. The input in this case is text data, and the output is an HTTP POST request sent to the server.

[0741] Step 2:

[0742] The terminal receives data entered by the user and sends it to the server as an HTTP POST request. Specifically, it serializes the input data into JSON format and sends it to the appropriate API endpoint. The input is text data entered by the user, and the output is an HTTP request to the server.

[0743] Step 3:

[0744] The server receives data sent from the device. The received data (input) is JSON format data containing text information and desired conditions. The server parses this data and prepares it to be passed to the generative AI model. The parsed data is passed to the generative AI model as output.

[0745] Step 4:

[0746] The server passes the received user symptoms and desired condition data to the generative AI model and begins analysis. The input is text data describing the symptoms and desired conditions, and the generative AI model analyzes this to understand the user's situation. The output is a list of candidates for the most suitable medical institutions and doctors.

[0747] Step 5:

[0748] The server passes the analyzed data to the emotion engine, which analyzes the user's emotional state. Specifically, it identifies emotions such as "anxiety," "impatience," and "calmness" based on the input data. For example, it can sense "anxiety" from the text "I've been diagnosed with breast cancer" and "I hope for the latest treatment." The output is the identified emotional state, and the results of the generative AI model are adjusted as needed.

[0749] Step 6:

[0750] The server uses the emotional data obtained from the emotion engine to adjust the medical institutions and doctor candidates provided by the generative AI model. The input is the analyzed emotional state and a list of medical institutions, and the output is a list of optimal medical institutions that takes the emotional state into consideration. This allows the information provided to the user to be adjusted based on the user's emotional state.

[0751] Step 7:

[0752] The server organizes the information of the coordinated medical institutions and doctors and automatically generates a referral letter. The input is a list of coordinated medical institutions and emotion analysis data, and the output is an automatically generated referral letter and organized medical institution information. The referral letter includes the reason for recommendation and an evaluation of comfort based on the patient's emotional state.

[0753] Step 8:

[0754] The server sends the generated referral letter and organized medical institution information to the user terminal. The input is the referral letter and medical institution information, and the output is the data sent to the user terminal. The user terminal receives this and prepares to display it on the screen.

[0755] Step 9:

[0756] The user checks the provided medical institution information and referral letter. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, and the user selects "Medical Institution A," which the emotion engine evaluates as "reliable." The input is the medical institution information provided to the user, and the output is the user's selection.

[0757] Step 10:

[0758] The server checks the schedule of the medical institution selected by the user and confirms the appointment. The input is the user's selection data and the medical institution's schedule information, and the output is the confirmed appointment information. In addition, options such as psychological counseling are provided if necessary.

[0759] Step 11:

[0760] The server notifies the user terminal of the confirmed reservation information and support information. The input is the confirmed reservation information and support information, and the output is a notification sent to the user terminal. The user terminal displays the received reservation information and support information and notifies the user.

[0761] (Application example 2)

[0762] 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."

[0763] Conventional medical institution referral systems refer patients to medical institutions and doctors simply based on the symptoms and desired conditions entered, without considering the emotional state of the patient or their family. This makes it difficult to select an appropriate medical institution when users are in a mentally unstable state. Furthermore, they lack the functionality to provide appropriate psychological support to users who feel anxious. Therefore, there is a need for a system that can introduce the most appropriate medical institution while reducing the user's mental burden and providing a sense of security.

[0764] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input their symptoms, desired treatment details, desired conditions, and concerns; means for receiving the information input by the patient and their family and sending it to the generative AI model; means for the generative AI model to analyze and search a database for the most appropriate medical institution and doctor; emotion analysis means, including emotion analysis means, for analyzing the emotional state of the patient and their family; means for the generative AI model to adjust the selection of a medical institution and doctor based on the emotion analysis results; means for organizing the information obtained from the database and the emotion analysis results and providing them to the patient and their family; means for automatically generating a referral letter and providing it to the patient and their family; and means for supporting the reservation procedure. This enables the server to introduce the most appropriate medical institution and doctor based on the user's emotional state, providing peace of mind and allowing the user to receive appropriate medical services.

[0765] "Patients and their families" refers to the person with the illness and their relatives and close friends who provide support to that person.

[0766] A "symptom" is a physical or psychological symptom associated with a disease or disorder.

[0767] "Desired treatment" refers to the specific treatment methods and types of medical services desired by patients and their families.

[0768] "Desired conditions" are conditions and requests that patients and their families place particular importance on when it comes to treatment, such as location, cost, and doctor's expertise.

[0769] "Anxiety points" are psychological concerns or anxiety factors that patients and their families have regarding treatment or diagnosis.

[0770] A "generative AI model" is a model that uses artificial intelligence technology to analyze user input information and generate optimal suggestions.

[0771] A "database" is a collection of digital data used to organize and manage detailed information about medical institutions and doctors.

[0772] "Emotion analysis means" is a technology that analyzes and recognizes the emotional state of patients and their families.

[0773] "Adjustment based on the results of sentiment analysis" means changing or adjusting the content or quality of the service provided to users based on the results of sentiment analysis.

[0774] A "letter of referral" is an official document used when referring a patient to a medical institution, and is used to provide the patient's information to the doctor or institution to which the patient is referred.

[0775] "Psychological counseling options" are options and services that provide psychological support for anxiety and stress experienced by patients and their families.

[0776] The "reservation procedure" refers to the process of making an appointment in advance to receive the medical service a user desires.

[0777] This invention is a system that provides optimal information to patients and their families when searching for medical institutions and doctors, thereby reducing their psychological anxiety. The system of this invention combines a generative AI model and emotion analysis means to recommend appropriate medical institutions and doctors taking into account the user's emotional state.

[0778] System configuration

[0779] This system mainly consists of the following hardware and software:

[0780] Hardware

[0781] 1. User device: A device used by the user to input information, such as a smartphone or tablet.

[0782] 2. Server: Cloud server used for data processing and storage.

[0783] 3. Database: A database that manages information about medical institutions and doctors.

[0784] software

[0785] 1. Generative AI model: OpenAI's GPT-3 is used.

[0786] 2. Sentiment analysis method: Google Cloud Natural Language API.

[0787] System Operation

[0788] Users can use a device such as a smartphone or tablet to input their symptoms, desired treatment, desired conditions, and concerns. Specific prompts such as the following can be used:

[0789] Prompt Sentence Examples

[0790] The user is feeling anxious. Considering this situation, please suggest the following security measures: Condition: Suspicious activity has been observed recently around the home

[0791] 1. Installing security cameras

[0792] 2. Strengthening entrance doors and windows

[0793] 3. Check the contact details of nearby police stations and security companies

[0794] The information entered by the user is sent to a server. The server uses the Google Cloud Natural Language API to analyze the user's emotional state from the input. For example, an emotional state such as "anxiety" is recognized. The information along with the analyzed emotional state is then sent to a generative AI model, which searches a database for the most suitable medical institution or doctor.

[0795] The generative AI model selects the most suitable medical institutions and doctors based on the user's desired conditions and adjusts the recommendations taking into account the results of sentiment analysis. For example, if the user is feeling "anxious," it will prioritize recommendations of medical institutions that can provide greater reassurance. This allows the user to make appropriate medical choices with peace of mind.

[0796] Information and booking procedures

[0797] The server sends information about medical institutions organized based on the results of the generative AI model and emotion analysis to the user's device. The user can view the received information and select the most suitable medical institution. The server then checks the medical institution's schedule and confirms the appointment, taking into account the emotion analysis results. For example, if a user feels "anxious," it may also offer the option of psychological counseling.

[0798] Users can receive appointment confirmation and additional support information to plan their visit to a medical facility, providing peace of mind and ensuring appropriate medical services are provided.

[0799] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0800] Step 1:

[0801] Users use devices such as smartphones or tablets to input their symptoms, desired treatment, desired conditions, and concerns. This information is entered in text format and sent from the user's device to the server. The input data is used as preparation data for analysis in the next step.

[0802] Step 2:

[0803] The server receives input information from the user's device and performs emotion analysis using the Google Cloud Natural Language API. Specifically, the input text data is sent to the API, and an emotion score is obtained from it as the analysis result. The emotion analysis results are output as emotional states such as "anxiety" or "impatience."

[0804] Step 3:

[0805] The server sends the results of the sentiment analysis along with the conditions entered by the user to a generative AI model (OpenAI's GPT-3). The generative AI model uses the prompt to suggest the most suitable medical institution or doctor. Examples of prompts include, "The user is feeling anxious. Considering this situation, please suggest medical institutions with the following conditions: latest treatments" and "location within Tokyo that is easy to get to." The input data is combined with the results of the sentiment analysis to output a list of the most suitable medical institutions.

[0806] Step 4:

[0807] The server receives the list of medical institutions and doctors obtained from the generative AI model and uses that list to search a database, which contains detailed information about the medical institutions, the doctors' specialties, and their ratings. An organized list of recommended medical institutions is created based on the search results.

[0808] Step 5:

[0809] The server sends a list of recommended medical institutions to the user's terminal. This list includes medical institutions that provide a sense of security based on the results of sentiment analysis. The user can view this list and select the medical institution that best suits them. The user's selection is sent back to the server in the next step.

[0810] Step 6:

[0811] The server receives the user's selection, checks the schedule of the selected medical institution, checks the schedule against the medical institution's database to determine availability, and then generates a notification to confirm the appointment.

[0812] Step 7:

[0813] The server confirms the reservation and sends the confirmed reservation information to the user's device. Furthermore, if psychological counseling options are required based on the results of the emotion analysis, that information is also provided. This allows the user to receive all the necessary information and prepare for their visit to the medical institution with peace of mind.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] [Third embodiment]

[0818] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0819] 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.

[0820] 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).

[0821] 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.

[0822] 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.

[0823] 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).

[0824] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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."

[0830] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. This system utilizes a generative AI model to analyze and provide medical information based on the patient's and their family's medical condition and treatment preferences, and supports the creation of referral letters and reservation procedures.

[0831] Basic structure and operation of the system

[0832] User terminal operation

[0833] Using a web application, users input their symptoms, desired treatment, and desired conditions. For example, a user might enter data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like a hospital in Tokyo that's easy to get to." This input information is sent to the server with a single click.

[0834] Server Operation

[0835] The server receives the information sent by the user. The received information is sent to the generative AI model, where analysis begins. Based on the received data, the generative AI model understands the patient's condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[0836] The generative AI model selects the most suitable medical institutions and doctors based on criteria such as "breast cancer," "latest treatments," and "located in Tokyo." The server organizes this information and prepares it for delivery to the user. It also automatically generates referral letters and saves them in the appropriate format.

[0837] Reply to user terminal

[0838] The server sends the organized medical institution information and referral letters to the user's terminal, which receives and displays the information. The user can then view detailed information on the listed medical institutions and select the most appropriate option.

[0839] For example, the user selects "Medical Institution A" from among "Medical Institution A," "Medical Institution B," and "Medical Institution C." This selection information is sent to the server, which then assists in the reservation procedure at the selected medical institution.

[0840] Reservation procedure

[0841] The server checks the schedule of the selected medical institution and confirms the reservation. At this time, adjustments are made depending on the reservation status, and once the reservation is confirmed, the information is notified to the user's terminal. The user can then check the confirmed reservation information and proceed with preparations to visit the medical institution.

[0842] Specific examples

[0843] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins its analysis. It searches the database for medical institutions that meet the conditions, and lists "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[0844] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the reservation. The user receives the confirmed reservation information and can plan their visit to the medical institution.

[0845] In this way, this invention uses a generative AI model to quickly and accurately provide patients and their families with the most suitable medical institutions and doctors they desire, thereby reducing the burden of medical care selection. Support for creating referral letters and booking procedures can also be done online, allowing patients and their families to use the service without being restricted by time or location.

[0846] The processing flow will be explained below.

[0847] Step 1:

[0848] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. For example, they might enter "breast cancer" as the symptom, "latest treatment" as the desired treatment, and "within Tokyo" as the condition.

[0849] Step 2:

[0850] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[0851] Step 3:

[0852] The server receives data sent from the user's device and sends it to the generative AI model for analysis. The received data is stored in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[0853] Step 4:

[0854] The server's generative AI model analyzes the user's input data and searches the database for the most suitable medical institution or doctor. For example, the generative AI model extracts the best matching candidates based on the keywords "breast cancer," "latest treatment," and "Tokyo."

[0855] Step 5:

[0856] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[0857] Step 6:

[0858] The server organizes the acquired information on medical institutions and doctors and creates an information package to provide to the user. For example, it compiles detailed information on medical institutions A, B, C, etc. into a list.

[0859] Step 7:

[0860] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, and conditions.

[0861] Step 8:

[0862] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[0863] Step 9:

[0864] The user terminal receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C and the created referral letter are displayed on the screen.

[0865] Step 10:

[0866] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[0867] Step 11:

[0868] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[0869] Step 12:

[0870] The server notifies the user that the reservation has been confirmed. A reservation confirmation email or app notification is sent to the user.

[0871] Example 1

[0872] 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."

[0873] In modern medicine, it is extremely difficult for patients and their families to select the most appropriate medical institution and doctor. Especially in the case of serious illnesses, quick decisions based on reliable information are necessary. However, independently collecting and analyzing vast amounts of medical information requires time and effort, and there is a risk of making the wrong choice. Furthermore, the process of creating referral letters and making appointments is cumbersome, placing a significant burden on patients and their families. A system that solves these problems and provides patients and their families with the best medical options is needed.

[0874] 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.

[0875] In this invention, the server includes: a means for patients and their families to input their symptoms, desired treatment, and desired conditions; a means for receiving the information input by the patient and their family and sending it to the generative AI model; a means for the generative AI model to analyze the information using prompts and search a database for the most suitable medical institution and doctor; a means for organizing the information obtained from the database and providing it to the patient and their family; a means for automatically generating a referral letter and providing it to the patient and their family; a means for re-receiving information about the medical institution selected by the patient; and a means for notifying a user terminal of the medical institution's confirmed appointment information. This allows patients and their families to quickly select the most suitable medical institution and doctor based on reliable information. Furthermore, the automatic generation of referral letters and assistance with appointment procedures can reduce the burden on patients and their families.

[0876] "Patients" or "their families" are people who require medical services and their close relatives who provide support.

[0877] A "symptom" refers to a specific problem or symptom related to a patient's health.

[0878] "Treatment preference" means the specific type of medical treatment or therapy desired by the patient.

[0879] "Desired conditions" refer to the geographical, time, and facility requirements that patients and their families consider important when selecting a medical institution.

[0880] "Input means" refers to the mechanism by which a user enters and submits information using a web application or other interface.

[0881] "Receiving means" refers to a function that allows the server to receive information sent by the user.

[0882] A "generative AI model" refers to an artificial intelligence algorithm that analyzes information entered by patients and their families and selects the most appropriate medical institution and doctor.

[0883] A "prompt" is a short sentence or combination of keywords used to provide input to a generative AI model and serve as the basis for analysis.

[0884] "Database" refers to an electronic data storage system for storing data such as details, ratings, and locations of medical institutions and physicians.

[0885] "Organization means" refers to the function for organizing information obtained from a generative AI model into an easy-to-understand format.

[0886] "Means of delivery" refers to the mechanism for delivering organized information and generated referral letters to patients and their families.

[0887] A "letter of referral" refers to a referral document to a medical institution that is prepared based on the patient's medical condition and treatment wishes.

[0888] "Selected information" refers to information about a specific medical institution selected by the patient or their family from the medical institution information provided.

[0889] "Reservation procedure support means" refers to the support functions required to confirm a reservation at the selected medical institution.

[0890] "Reservation confirmation information" refers to information indicating that a reservation has been confirmed after checking the schedule of the medical institution.

[0891] The present invention provides a system for providing an online referral service that enables patients and their families to quickly and accurately select the most suitable medical institution and doctor, and supports the creation of referral letters and reservation procedures. An embodiment of this system will be described in detail below.

[0892] Basic structure and operation

[0893] User terminal operation

[0894] Users use a web application provided through a web browser on their PC or smartphone (e.g., Google Chrome, Mozilla Firefox) to input their symptoms, desired treatment, and desired conditions. For example, they input data such as "I've been diagnosed with breast cancer," "I'd like a hospital that offers the latest treatments," and "A location within Tokyo that's easy to get to." After completing the input, they click the send button to send this information to the server.

[0895] Server Operation

[0896] The server receives user-submitted information via an HTTP POST request. To process this information, the server leverages a generative AI model (e.g., GPT-4 or BERT). The received user data is transformed into a prompt like this:

[0897] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[0898] This prompt sentence is input into the generative AI model and analysis begins.

[0899] Analysis using generative AI models

[0900] The generative AI model analyzes the user's medical condition and desired conditions, and searches a database for appropriate medical institutions and doctors. The database contains detailed information on multiple medical institutions and doctors. For example, it identifies the most suitable medical institution and doctor based on the conditions "breast cancer," "latest treatment," and "within Tokyo."

[0901] Data organization and referral generation

[0902] The server integrates the information obtained from the generative AI model and prepares it for delivery to the user. This information is organized in JSON format and provided to the user via a web application. The server also automatically generates a referral letter and saves it in PDF format. This referral letter includes the patient's medical condition, desired conditions, recommended treatment, and other information.

[0903] Sending information to user terminals

[0904] The organized medical institution information and referral letter are sent to the user's device as an HTTP response, where the user can view the information and check the details on the web application.

[0905] Reservation procedure

[0906] Once the user selects the most suitable medical institution, the selection information is sent back to the server. The server then checks the schedule of the selected medical institution via API and confirms the reservation. The confirmed reservation information is then sent to the user's device. The user can then receive the confirmed reservation information and prepare for their hospital visit.

[0907] Specific examples

[0908] For example, a user enters the criteria "breast cancer," "latest treatment," and "location within Tokyo that is easy to get to." This information is sent to the server, and the generative AI model begins its analysis. The prompt is as follows:

[0909] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[0910] Based on the analysis results, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is created from the database. This information is organized and provided to the user.

[0911] When the user selects "Medical Institution A," that information is sent to the server again. The server then checks the schedule of "Medical Institution A" and sends the confirmed reservation information to the user's terminal. The user can use this information to plan their hospital visit.

[0912] This way, patients and their families can easily find good medical institutions and doctors and get the necessary procedures done quickly and efficiently.

[0913] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0914] Step 1:

[0915] User input of information

[0916] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. At this time, they enter information such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "It should be located in Tokyo and be easy to get to" as text into the input form. Once they have completed the input, they click the send button, which sends the entered information to the server.

[0917] Input: Symptoms and wishes entered by the user into the web application

[0918] Output: The input information is sent to the server as an HTTP request.

[0919] Step 2:

[0920] Server receives information

[0921] The server receives information sent by the user via an HTTP POST request, temporarily stores the received data in JSON format, and converts it into a format that can be input to the generative AI model.

[0922] Input: User-submitted information in JSON format

[0923] Output: Prompt sentence to be input to the generative AI model

[0924] Step 3:

[0925] Analysis using generative AI models

[0926] The server inputs a prompt into the generative AI model and begins analysis. For example, the prompt might be "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo." The generative AI model uses this prompt to analyze the most suitable medical institution and doctor.

[0927] Input: prompt statement

[0928] Output: Analysis results from the generative AI model (list of optimal medical institutions and doctors)

[0929] Step 4:

[0930] Searching from the database

[0931] The server searches a database for detailed information on the most suitable medical institution and doctor based on the analysis results of the generative AI model. The database stores detailed information on hospitals and clinics, as well as the doctor's specialty and reputation. For example, based on the analysis results of the criteria "breast cancer," "latest treatment," and "within Tokyo," the server searches for "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[0932] Input: Analysis results of the generative AI model

[0933] Output: Information on the most suitable medical institution and doctor obtained from the database

[0934] Step 5:

[0935] Organizing information and generating referral letters

[0936] The server organizes the information obtained from the database and prepares it for delivery to the user. This information is consolidated into an easy-to-understand format, such as JSON. At the same time, the server automatically generates a referral letter, which describes the patient's condition, desired conditions, and recommended treatment, and is saved in PDF format.

[0937] Input: Medical institution information obtained from the database

[0938] Output: Organized medical institution information and referral letter (PDF format)

[0939] Step 6:

[0940] Sending information to user terminals

[0941] The server sends the organized medical institution information and referral letter to the user's device as an HTTP response. The user can view this information on the web application and check the details.

[0942] Input: Organized medical institution information and referral letter (PDF format)

[0943] Output: Medical institution information and referral letter displayed on the user's terminal

[0944] Step 7:

[0945] User selection of medical institution

[0946] The user views the medical institution information provided on the web application and selects the most appropriate option from "Medical Institution A," "Medical Institution B," or "Medical Institution C." The selected information is then sent back to the server.

[0947] Input: Information about the medical institution selected by the user

[0948] Output: Selection information is sent to the server

[0949] Step 8:

[0950] Server-based reservation process

[0951] The server receives the information about the medical institution selected by the user and checks the schedule of that institution. It then uses an API to connect to the medical institution's reservation system and confirms the reservation. Once the reservation is confirmed, the server notifies the user's device of the reservation confirmation information.

[0952] Input: Information about the medical institution selected by the user

[0953] Output: Confirmed reservation information is sent to the user's device.

[0954] Step 9:

[0955] User confirms reservation and prepares visit

[0956] The user can then confirm the confirmed reservation information on the web application. After confirming that the reservation information has been confirmed, the user can then prepare to visit the medical institution.

[0957] Input: Confirmed reservation information

[0958] Output: User confirms appointment and begins visit preparation

[0959] (Application example 1)

[0960] 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."

[0961] In conventional medical referral systems, there is a high risk of medical information entered by patients and their families being leaked to the outside, making security a major issue. There is also a need to improve the accuracy of analysis based on the patient's medical condition and desired conditions, which makes it difficult to find the most suitable medical institution or doctor.

[0962] 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.

[0963] In this invention, the server includes means for patients and their families to input their symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their family and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for organizing the information obtained from the database and providing it to the patient and their family, means for automatically generating a referral letter and providing it to the patient and their family, means for encrypting the input information, and means for decrypting the encrypted information. This enables quick and accurate referral to the most suitable medical institution and doctor while protecting the patient's confidential information with high security.

[0964] "Patients and their families" refers to individuals who require medical services and their supporters.

[0965] "Symptoms" refer to abnormalities or distress in the patient's body or mind.

[0966] "Desired treatment details" is information indicating the specific treatment methods and medical services desired by the patient and their family.

[0967] "Desired conditions" refers to specific requests regarding medical institutions and treatment, such as location, date and time, and specialty.

[0968] "Means of input" refers to the interface or device through which a user provides information to a system.

[0969] "Means for receiving" refers to a mechanism for receiving information sent by a user.

[0970] A "generative AI model" refers to a program that uses artificial intelligence technology to analyze input data and generate optimal answers or suggestions.

[0971] A "database" refers to a system that systematically organizes and manages information about medical institutions and doctors, making it searchable.

[0972] "Search methods" refer to algorithms or programs used to find information that meets specific criteria from a database.

[0973] "Means for organizing and presenting" refers to the mechanism for presenting the searched information to the user in an easy-to-understand format.

[0974] "Means for automatically generating a letter of introduction" refers to a program that automatically creates a letter of introduction based on information entered by the user and the results of analysis.

[0975] "Encryption methods" refers to techniques for converting information into a form that cannot be deciphered by third parties.

[0976] "Means to decrypt" refers to the technology used to restore encrypted information to its original form.

[0977] The system of the present invention provides an online referral service that introduces optimal medical institutions and doctors based on the results of analysis by a generative AI model after patients and their families input their medical information. This system includes the following means.

[0978] User terminal operation

[0979] The user terminal provides an interface for patients and their families to input information such as symptoms, desired treatment, desired conditions, etc. For example, a user might input data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like to go to a hospital in Tokyo that's easy to get to." This input information is encrypted and sent to the server.

[0980] Server Operation

[0981] The server receives the entered medical information and first decrypts the encrypted data. It then requests the generative AI model to analyze it. The generative AI model then searches the database for the most suitable medical institution and doctor based on the decrypted data. In this process, the generative AI model performs its analysis using prompts such as the following:

[0982] "Find accessible hospitals in Tokyo that offer the latest treatments for breast cancer patients."

[0983] Database search and information organization

[0984] The generative AI model searches the database for candidate medical institutions and doctors and extracts relevant information. For example, based on the criteria "breast cancer," "latest treatment," and "within Tokyo," it will select "Medical Institution A," "Medical Institution B," and "Medical Institution C." This information is then organized and prepared for provision to patients and their families.

[0985] Automatic generation of referral letters

[0986] The server automatically generates a referral letter based on the extracted information. The referral letter includes the patient's medical condition, requests, and information on recommended medical institutions and doctors. The generated referral letter is also encrypted when stored and transmitted.

[0987] Confirmation and booking process

[0988] The server sends the organized information and referral letter to the user's terminal, where the user confirms it. For example, the user selects "Medical Institution A" from "Medical Institution A," "Medical Institution B," and "Medical Institution C." The selected information is sent to the server, which checks the schedule of the selected medical institution and assists with the reservation procedure.

[0989] Hardware and software used

[0990] The system uses user devices (smartphones, tablets, PCs), a server, a generative AI model, a database, and encryption / decryption technology. As a specific example, it uses the Python Cryptography package for encryption and decryption.

[0991] example:

[0992] Data entered by the user: "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," "A location in Tokyo that is easy to get to."

[0993] Prompt for generative AI model: "Find hospitals in Tokyo that offer the latest treatments for breast cancer patients and are easy to get to."

[0994] This enables quick and accurate referral to the most appropriate medical institution or doctor while protecting patient confidential information with high security.

[0995] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0996] Step 1:

[0997] The user uses the terminal to input information such as symptoms, desired treatment, and desired conditions.

[0998] Input: The user enters data such as "breast cancer," "latest treatment," and "locations in Tokyo that are easy to get to."

[0999] Output: The input data

[1000] What happens: The user enters information into the interface and clicks the submit button.

[1001] Step 2:

[1002] The terminal encrypts the information entered by the user and sends it to the server.

[1003] Input: Data entered

[1004] Output: Encrypted data

[1005] Specific operation: The terminal uses the encryption module (Python Cryptography package) to encrypt the input data and sends the encrypted data to the server.

[1006] Step 3:

[1007] The server receives and decrypts the encrypted data.

[1008] Input: Encrypted data

[1009] Output: Decrypted data

[1010] Specific operation: Receives encrypted data on the server side and uses a decryption module to restore the original information.

[1011] Step 4:

[1012] The server sends the decrypted data to the generative AI model and requests it to analyze it.

[1013] Input: Decrypted data

[1014] Output: Analysis request to the generative AI model

[1015] Specific behavior: The server generates a prompt based on the content of the data,

[1016] "Find an easily accessible hospital in Tokyo that offers the latest treatments for breast cancer patients."

[1017] This prompt is sent to the generative AI model.

[1018] Step 5:

[1019] The generative AI model searches a database for the most suitable medical institution or doctor based on the prompt text.

[1020] Input: prompt statement

[1021] Output: List of medical institutions and doctors

[1022] How it works: The generative AI model analyzes the prompt, searches for corresponding database entries, and lists appropriate medical institutions and doctors.

[1023] Step 6:

[1024] The server organizes information about medical institutions and doctors obtained from the generative AI model.

[1025] Input: List of medical institutions and doctors

[1026] Output: Organized medical information

[1027] Specific operation: The server organizes the information extracted from the database according to a format and prepares it in a form that can be provided to the user.

[1028] Step 7:

[1029] The server automatically generates and encrypts a referral letter based on the organized medical information.

[1030] Input: Organized medical information

[1031] Output: Encrypted letter of introduction

[1032] Specific operation: The referral letter generation module creates a referral letter based on the listed information of medical institutions and doctors and the information entered by the user, and then encrypts it.

[1033] Step 8:

[1034] The server transmits the encrypted referral letter and medical information to the user terminal.

[1035] Input: Encrypted letter of introduction

[1036] Output: Sending data to the user's terminal

[1037] What it does: The server sends the encrypted referral letter and medical information and makes it accessible to the user.

[1038] Step 9:

[1039] The user can view the medical information and referral letter sent to them and select the most suitable medical institution and doctor.

[1040] Input: Encrypted letter of introduction

[1041] Output: User selection information

[1042] Specific operations: The device decrypts the data received and displays it in a form that can be viewed by the user. The user makes a selection and sends the selection to the server.

[1043] Step 10:

[1044] The server assists the user in making a reservation at a medical institution based on the user's selection information.

[1045] Input: User selection information

[1046] Output: Reservation information

[1047] Specific operation: The server checks the schedule of the selected medical institution and confirms the corresponding appointment.

[1048] Step 11:

[1049] The server notifies the user terminal of the information that the reservation has been confirmed.

[1050] Input: Reservation information

[1051] Output: Booking confirmation notice

[1052] Specific operation: Send a notification to the user's device and display the reservation information.

[1053] 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.

[1054] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention provides medical information and support according to the user's emotional state.

[1055] Basic structure and operation of the system

[1056] User terminal operation

[1057] The user uses a web application to input their symptoms, desired treatment, and desired conditions. For example, the user might input data such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "I would like a hospital in Tokyo that is easy to get to." This input information is sent to the server when the user clicks the "Submit" button.

[1058] Server Operation

[1059] The server receives the information sent by the user. The received information is sent to the generative AI model, which begins analyzing it. The generative AI model understands the user's medical condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[1060] Combining Emotion Engines

[1061] Here, the emotion engine recognizes the user's emotional state from the content of their input. For example, it analyzes the emotions of "anxiety," "impatience," and "calmness" from the user's input text. The emotion engine adjusts the recommendations generated by the AI ​​model based on this emotional state.

[1062] The generative AI model not only selects the most suitable medical institutions and doctors based on the criteria of "breast cancer," "latest treatments," and "located in Tokyo," but also prioritizes medical institutions and doctors that users feel more comfortable with, taking into account the state of "anxiety" recognized by the emotion engine. The server organizes this information and prepares it for provision to the user. It also automatically generates a referral letter and saves it in the appropriate format.

[1063] Reply to user terminal

[1064] The server sends the organized medical institution information and referral letters to the user's device. The user's device receives this and displays the information. The user can view detailed information about the listed medical institutions and check recommended options based on their emotional state. For example, from among "Medical Institution A," "Medical Institution B," and "Medical Institution C," the user can select "Medical Institution A," which has been rated as "reliable" by the emotion engine.

[1065] Reservation procedure

[1066] The server checks the schedule of the selected medical institution and confirms the appointment. At this time, it also provides necessary support information and resources based on the user's emotional state. For example, if a user is feeling excessive anxiety, it may provide support such as presenting psychological counseling options. Once the appointment is confirmed, the information is sent to the user's device. The user receives the confirmed appointment information and can begin preparing to visit the medical institution.

[1067] Specific examples

[1068] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins analysis. At that time, the emotion engine recognizes the emotion of "anxiety" from the user's input, and taking this result into consideration, prioritizes recommending medical institutions that can provide a greater sense of security. For example, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is displayed, but the emotion engine evaluates "Medical Institution A" as being the best for providing a sense of security.

[1069] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the appointment. Furthermore, to address the anxious emotional state, an option for psychological counseling is also provided. The user receives the confirmed appointment and additional support information, allowing them to plan their visit to the medical institution.

[1070] In this way, the present invention utilizes a generative AI model and an emotion engine to provide optimal medical information according to the user's emotional state, thereby reducing the burden of medical selection and providing safer and more reliable medical services.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] Users open the web application and enter their symptoms, desired treatment, and desired conditions. For example, they enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "I want a hospital in a convenient location in Tokyo."

[1074] Step 2:

[1075] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[1076] Step 3:

[1077] The server receives data from the user's device and sends the received information to the generative AI model and emotion engine. The received data is saved in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[1078] Step 4:

[1079] The emotion engine analyzes the user's input data and recognizes their emotional state. For example, it analyzes emotions such as "anxiety," "impatience," and "calmness." This emotional state data is passed to the generative AI model.

[1080] Step 5:

[1081] The server's generative AI model analyzes the user's symptoms and desired conditions, and also considers the emotional state from the emotion engine to search for the most suitable medical institution or doctor from the database. For example, the generative AI model extracts the best matching candidates by considering the keywords "breast cancer," "latest treatments," and "Tokyo area" as well as the emotion of "anxiety."

[1082] Step 6:

[1083] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[1084] Step 7:

[1085] The server organizes the information on medical institutions and doctors it has acquired and creates an information package that takes into account the results of the emotion engine. For example, detailed information on medical institutions A, B, and C is compiled into a list, and medical institution A is evaluated as providing the most reassurance.

[1086] Step 8:

[1087] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, conditions, and emotional state.

[1088] Step 9:

[1089] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[1090] Step 10:

[1091] The user device receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C, along with the created referral letter, are displayed on the screen. Based on the evaluation by the emotion engine, medical institution A is displayed as the most reliable.

[1092] Step 11:

[1093] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[1094] Step 12:

[1095] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[1096] Step 13:

[1097] The server notifies the user that the reservation has been confirmed. A confirmation email or app notification is sent to the user. Based on the emotion engine, additional support information may be provided, including psychological counseling options.

[1098] Through these small steps, users can feel at ease when selecting a medical institution using the emotion engine, and can easily proceed with creating a referral letter and making a reservation.

[1099] Example 2

[1100] 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."

[1101] In conventional medical information provision systems, even if patients and their families input their symptoms and desired conditions, they simply refer them to the most suitable medical institution or doctor based on that information, and do not provide sufficient support that takes into account the emotional state of each individual. This has led to the issue of it being difficult to alleviate the anxiety and psychological burden felt by patients and their families.

[1102] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their families and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for analyzing the emotional state from the user's input content, means for adjusting the most suitable information based on the analyzed emotional state, means for organizing the information obtained from the database and providing it to the patient and their families, and means for automatically generating a referral letter and providing it to the patient and their families. This makes it possible to provide medical information that takes into account the emotional state of the patient and their families, thereby reducing psychological burden and providing a sense of security.

[1103] "Patients and their families" refers to users who input symptoms and treatment details, as well as their supporters.

[1104] "Symptoms" refers to the specific medical conditions or symptoms that are required when seeking treatment or diagnosis from a medical institution.

[1105] "Desired treatment content" refers to the specific treatment method, treatment policy, and type of treatment desired by the patient and their family.

[1106] "Desired conditions" refer to specific conditions or requests that patients and their families want to consider when receiving treatment, such as the characteristics of the region or medical institution, or the doctor's specialty.

[1107] "Input means" refers to an interface that allows the user to send symptoms, desired treatment, and desired conditions to the system.

[1108] "Means for receiving and transmitting to the generative AI model" refers to the mechanism for receiving data entered by a user and passing it to the generative AI model for analysis.

[1109] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze input data and find the most suitable medical institution or doctor.

[1110] "Means for searching from the database" refers to the method by which the generative AI model searches and retrieves information about medical institutions and doctors from the database.

[1111] "Means for analyzing emotional state" refers to technology for identifying and analyzing emotions from user input.

[1112] "Means for adjusting optimal information" refers to a mechanism for appropriately customizing the medical information provided to the user based on the analyzed emotional state.

[1113] "Means of organizing and providing" refers to a method of appropriately organizing information on medical institutions and doctors obtained from the generative AI model and providing it to users in a format that is easy to understand.

[1114] "Means for automatically generating and providing a letter of introduction" refers to a mechanism for automatically creating a letter of introduction to be provided to a user based on information retrieved from a database and delivering it to the user.

[1115] "Means to support the reservation procedure" refers to procedures and support for smoothly making a reservation at the medical institution selected by the user.

[1116] "Means for checking the schedule of a medical institution and confirming a reservation" refers to a system for a user to check the availability of the medical institution where the user wishes to make a reservation and confirm the reservation.

[1117] This invention is a system that provides an online referral service that introduces patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide medical information and support according to the user's emotional state.

[1118] User terminal operation

[1119] Users use the web application to enter information such as their symptoms, desired treatment, and desired conditions. Specifically, users enter information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to" into text fields. Once the information is complete, they click the "Submit" button.

[1120] Server Operation

[1121] The server receives data sent from the user's device. Once this data is received, processing begins within the server. First, the received data is passed to a generative AI model for analysis. This generative AI model is used to understand the user's symptoms, desired conditions, and other data, and then searches a database for the most suitable medical institution and doctor.

[1122] Emotion Engine Operation

[1123] The server then passes the user's input to the emotion engine, which analyzes the user's sentences and identifies emotional states such as "anxiety," "impatience," and "calmness." For example, if a user enters the sentences "I've been diagnosed with breast cancer" and "I'd like the latest treatment," the emotion engine identifies the emotion of "anxiety." Based on this emotional state, the generative AI model adjusts the medical institutions and doctors it suggests, prioritizing options that provide greater peace of mind.

[1124] Organizing and providing information

[1125] The server organizes the information on the most suitable medical institution and doctor obtained from the generative AI model and automatically generates a referral letter. This referral letter includes the reason for selection and an evaluation of the patient's comfort level based on their emotional state. The generated information and referral letter are sent to the user's device, where they can be viewed.

[1126] Selection on the user device

[1127] The user checks the provided information and selects the most appropriate option from the listed medical institutions. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C," which the emotion engine has rated as "reliable," are listed, and the user can select "Medical Institution A."

[1128] Reservation procedure

[1129] The server checks the schedule of the selected medical institution and confirms the reservation. If necessary, it also provides options such as psychological counseling. Once the reservation is confirmed, the information is sent to the user's terminal.

[1130] Specific examples

[1131] A user uses a web application to enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "It should be located in a convenient location within Tokyo," and clicks the "Submit" button. This data is sent to the server, and the generative AI model begins analysis. The emotion engine recognizes "anxiety" from the input and prioritizes recommendations for the most appropriate medical institution, taking this emotion into consideration. As a result, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, with "Medical Institution A" being evaluated as the best for providing a sense of security. The server sends this information to the user's device, and the user selects "Medical Institution A." The server then confirms the appointment, offering the option of psychological counseling. Finally, the user receives the confirmed appointment information and can begin preparing for their visit to the medical institution.

[1132] Prompt Sentence Examples

[1133] An example of a prompt sentence that a user can enter is, "I have been diagnosed with breast cancer and am looking for a hospital in Tokyo that offers the latest treatments. Please give priority to recommendations of reliable medical institutions."

[1134] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1135] Step 1:

[1136] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. The input data is text information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to." Once the input is complete, the user clicks the "Submit" button to send the data to the server. The input in this case is text data, and the output is an HTTP POST request sent to the server.

[1137] Step 2:

[1138] The terminal receives data entered by the user and sends it to the server as an HTTP POST request. Specifically, it serializes the input data into JSON format and sends it to the appropriate API endpoint. The input is text data entered by the user, and the output is an HTTP request to the server.

[1139] Step 3:

[1140] The server receives data sent from the device. The received data (input) is JSON format data containing text information and desired conditions. The server parses this data and prepares it to be passed to the generative AI model. The parsed data is passed to the generative AI model as output.

[1141] Step 4:

[1142] The server passes the received user symptoms and desired condition data to the generative AI model and begins analysis. The input is text data describing the symptoms and desired conditions, and the generative AI model analyzes this to understand the user's situation. The output is a list of candidates for the most suitable medical institutions and doctors.

[1143] Step 5:

[1144] The server passes the analyzed data to the emotion engine, which analyzes the user's emotional state. Specifically, it identifies emotions such as "anxiety," "impatience," and "calmness" based on the input data. For example, it can sense "anxiety" from the text "I've been diagnosed with breast cancer" and "I hope for the latest treatment." The output is the identified emotional state, and the results of the generative AI model are adjusted as needed.

[1145] Step 6:

[1146] The server uses the emotional data obtained from the emotion engine to adjust the medical institutions and doctor candidates provided by the generative AI model. The input is the analyzed emotional state and a list of medical institutions, and the output is a list of optimal medical institutions that takes the emotional state into consideration. This allows the information provided to the user to be adjusted based on the user's emotional state.

[1147] Step 7:

[1148] The server organizes the information of the coordinated medical institutions and doctors and automatically generates a referral letter. The input is a list of coordinated medical institutions and emotion analysis data, and the output is an automatically generated referral letter and organized medical institution information. The referral letter includes the reason for recommendation and an evaluation of comfort based on the patient's emotional state.

[1149] Step 8:

[1150] The server sends the generated referral letter and organized medical institution information to the user terminal. The input is the referral letter and medical institution information, and the output is the data sent to the user terminal. The user terminal receives this and prepares to display it on the screen.

[1151] Step 9:

[1152] The user checks the provided medical institution information and referral letter. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, and the user selects "Medical Institution A," which the emotion engine evaluates as "reliable." The input is the medical institution information provided to the user, and the output is the user's selection.

[1153] Step 10:

[1154] The server checks the schedule of the medical institution selected by the user and confirms the appointment. The input is the user's selection data and the medical institution's schedule information, and the output is the confirmed appointment information. In addition, options such as psychological counseling are provided if necessary.

[1155] Step 11:

[1156] The server notifies the user terminal of the confirmed reservation information and support information. The input is the confirmed reservation information and support information, and the output is a notification sent to the user terminal. The user terminal displays the received reservation information and support information and notifies the user.

[1157] (Application example 2)

[1158] 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."

[1159] Conventional medical institution referral systems refer patients to medical institutions and doctors simply based on the symptoms and desired conditions entered, without considering the emotional state of the patient or their family. This makes it difficult to select an appropriate medical institution when users are in a mentally unstable state. Furthermore, they lack the functionality to provide appropriate psychological support to users who feel anxious. Therefore, there is a need for a system that can introduce the most appropriate medical institution while reducing the user's mental burden and providing a sense of security.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input their symptoms, desired treatment details, desired conditions, and concerns; means for receiving the information input by the patient and their family and sending it to the generative AI model; means for the generative AI model to analyze and search a database for the most appropriate medical institution and doctor; emotion analysis means, including emotion analysis means, for analyzing the emotional state of the patient and their family; means for the generative AI model to adjust the selection of a medical institution and doctor based on the emotion analysis results; means for organizing the information obtained from the database and the emotion analysis results and providing them to the patient and their family; means for automatically generating a referral letter and providing it to the patient and their family; and means for supporting the reservation procedure. This enables the server to introduce the most appropriate medical institution and doctor based on the user's emotional state, providing peace of mind and allowing the user to receive appropriate medical services.

[1161] "Patients and their families" refers to the person with the illness and their relatives and close friends who provide support to that person.

[1162] A "symptom" is a physical or psychological symptom associated with a disease or disorder.

[1163] "Desired treatment" refers to the specific treatment methods and types of medical services desired by patients and their families.

[1164] "Desired conditions" are conditions and requests that patients and their families place particular importance on when it comes to treatment, such as location, cost, and doctor's expertise.

[1165] "Anxiety points" are psychological concerns or anxiety factors that patients and their families have regarding treatment or diagnosis.

[1166] A "generative AI model" is a model that uses artificial intelligence technology to analyze user input information and generate optimal suggestions.

[1167] A "database" is a collection of digital data used to organize and manage detailed information about medical institutions and doctors.

[1168] "Emotion analysis means" is a technology that analyzes and recognizes the emotional state of patients and their families.

[1169] "Adjustment based on the results of sentiment analysis" means changing or adjusting the content or quality of the service provided to users based on the results of sentiment analysis.

[1170] A "letter of referral" is an official document used when referring a patient to a medical institution, and is used to provide the patient's information to the doctor or institution to which the patient is referred.

[1171] "Psychological counseling options" are options and services that provide psychological support for anxiety and stress experienced by patients and their families.

[1172] The "reservation procedure" refers to the process of making an appointment in advance to receive the medical service a user desires.

[1173] This invention is a system that provides optimal information to patients and their families when searching for medical institutions and doctors, thereby reducing their psychological anxiety. The system of this invention combines a generative AI model and emotion analysis means to recommend appropriate medical institutions and doctors taking into account the user's emotional state.

[1174] System configuration

[1175] This system mainly consists of the following hardware and software:

[1176] Hardware

[1177] 1. User device: A device used by the user to input information, such as a smartphone or tablet.

[1178] 2. Server: Cloud server used for data processing and storage.

[1179] 3. Database: A database that manages information about medical institutions and doctors.

[1180] software

[1181] 1. Generative AI model: OpenAI's GPT-3 is used.

[1182] 2. Sentiment analysis method: Google Cloud Natural Language API.

[1183] System Operation

[1184] Users can use a device such as a smartphone or tablet to input their symptoms, desired treatment, desired conditions, and concerns. Specific prompts such as the following can be used:

[1185] Prompt Sentence Examples

[1186] The user is feeling anxious. Considering this situation, please suggest the following security measures: Condition: Suspicious activity has been observed recently around the home

[1187] 1. Installing security cameras

[1188] 2. Strengthening entrance doors and windows

[1189] 3. Check the contact details of nearby police stations and security companies

[1190] The information entered by the user is sent to a server. The server uses the Google Cloud Natural Language API to analyze the user's emotional state from the input. For example, an emotional state such as "anxiety" is recognized. The information along with the analyzed emotional state is then sent to a generative AI model, which searches a database for the most suitable medical institution or doctor.

[1191] The generative AI model selects the most suitable medical institutions and doctors based on the user's desired conditions and adjusts the recommendations taking into account the results of sentiment analysis. For example, if the user is feeling "anxious," it will prioritize recommendations of medical institutions that can provide greater reassurance. This allows the user to make appropriate medical choices with peace of mind.

[1192] Information and booking procedures

[1193] The server sends information about medical institutions organized based on the results of the generative AI model and emotion analysis to the user's device. The user can view the received information and select the most suitable medical institution. The server then checks the medical institution's schedule and confirms the appointment, taking into account the emotion analysis results. For example, if a user feels "anxious," it may also offer the option of psychological counseling.

[1194] Users can receive appointment confirmation and additional support information to plan their visit to a medical facility, providing peace of mind and ensuring appropriate medical services are provided.

[1195] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1196] Step 1:

[1197] Users use devices such as smartphones or tablets to input their symptoms, desired treatment, desired conditions, and concerns. This information is entered in text format and sent from the user's device to the server. The input data is used as preparation data for analysis in the next step.

[1198] Step 2:

[1199] The server receives input information from the user's device and performs emotion analysis using the Google Cloud Natural Language API. Specifically, the input text data is sent to the API, and an emotion score is obtained from it as the analysis result. The emotion analysis results are output as emotional states such as "anxiety" or "impatience."

[1200] Step 3:

[1201] The server sends the results of the sentiment analysis along with the conditions entered by the user to a generative AI model (OpenAI's GPT-3). The generative AI model uses the prompt to suggest the most suitable medical institution or doctor. Examples of prompts include, "The user is feeling anxious. Considering this situation, please suggest medical institutions with the following conditions: latest treatments" and "location within Tokyo that is easy to get to." The input data is combined with the results of the sentiment analysis to output a list of the most suitable medical institutions.

[1202] Step 4:

[1203] The server receives the list of medical institutions and doctors obtained from the generative AI model and uses that list to search a database, which contains detailed information about the medical institutions, the doctors' specialties, and their ratings. An organized list of recommended medical institutions is created based on the search results.

[1204] Step 5:

[1205] The server sends a list of recommended medical institutions to the user's terminal. This list includes medical institutions that provide a sense of security based on the results of sentiment analysis. The user can view this list and select the medical institution that best suits them. The user's selection is sent back to the server in the next step.

[1206] Step 6:

[1207] The server receives the user's selection, checks the schedule of the selected medical institution, checks the schedule against the medical institution's database to determine availability, and then generates a notification to confirm the appointment.

[1208] Step 7:

[1209] The server confirms the reservation and sends the confirmed reservation information to the user's device. Furthermore, if psychological counseling options are required based on the results of the emotion analysis, that information is also provided. This allows the user to receive all the necessary information and prepare for their visit to the medical institution with peace of mind.

[1210] 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.

[1211] 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.

[1212] 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.

[1213] [Fourth embodiment]

[1214] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1215] 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.

[1216] 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).

[1217] 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.

[1218] 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.

[1219] 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).

[1220] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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."

[1227] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. This system utilizes a generative AI model to analyze and provide medical information based on the patient's and their family's medical condition and treatment preferences, and supports the creation of referral letters and reservation procedures.

[1228] Basic structure and operation of the system

[1229] User terminal operation

[1230] Using a web application, users input their symptoms, desired treatment, and desired conditions. For example, a user might enter data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like a hospital in Tokyo that's easy to get to." This input information is sent to the server with a single click.

[1231] Server Operation

[1232] The server receives the information sent by the user. The received information is sent to the generative AI model, where analysis begins. Based on the received data, the generative AI model understands the patient's condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[1233] The generative AI model selects the most suitable medical institutions and doctors based on criteria such as "breast cancer," "latest treatments," and "located in Tokyo." The server organizes this information and prepares it for delivery to the user. It also automatically generates referral letters and saves them in the appropriate format.

[1234] Reply to user terminal

[1235] The server sends the organized medical institution information and referral letters to the user's terminal, which receives and displays the information. The user can then view detailed information on the listed medical institutions and select the most appropriate option.

[1236] For example, the user selects "Medical Institution A" from among "Medical Institution A," "Medical Institution B," and "Medical Institution C." This selection information is sent to the server, which then assists in the reservation procedure at the selected medical institution.

[1237] Reservation procedure

[1238] The server checks the schedule of the selected medical institution and confirms the reservation. At this time, adjustments are made depending on the reservation status, and once the reservation is confirmed, the information is notified to the user's terminal. The user can then check the confirmed reservation information and proceed with preparations to visit the medical institution.

[1239] Specific examples

[1240] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins its analysis. It searches the database for medical institutions that meet the conditions, and lists "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[1241] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the reservation. The user receives the confirmed reservation information and can plan their visit to the medical institution.

[1242] In this way, this invention uses a generative AI model to quickly and accurately provide patients and their families with the most suitable medical institutions and doctors they desire, thereby reducing the burden of medical care selection. Support for creating referral letters and booking procedures can also be done online, allowing patients and their families to use the service without being restricted by time or location.

[1243] The processing flow will be explained below.

[1244] Step 1:

[1245] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. For example, they might enter "breast cancer" as the symptom, "latest treatment" as the desired treatment, and "within Tokyo" as the condition.

[1246] Step 2:

[1247] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[1248] Step 3:

[1249] The server receives data sent from the user's device and sends it to the generative AI model for analysis. The received data is stored in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[1250] Step 4:

[1251] The server's generative AI model analyzes the user's input data and searches the database for the most suitable medical institution or doctor. For example, the generative AI model extracts the best matching candidates based on the keywords "breast cancer," "latest treatment," and "Tokyo."

[1252] Step 5:

[1253] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[1254] Step 6:

[1255] The server organizes the acquired information on medical institutions and doctors and creates an information package to provide to the user. For example, it compiles detailed information on medical institutions A, B, C, etc. into a list.

[1256] Step 7:

[1257] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, and conditions.

[1258] Step 8:

[1259] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[1260] Step 9:

[1261] The user terminal receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C and the created referral letter are displayed on the screen.

[1262] Step 10:

[1263] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[1264] Step 11:

[1265] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[1266] Step 12:

[1267] The server notifies the user that the reservation has been confirmed. A reservation confirmation email or app notification is sent to the user.

[1268] Example 1

[1269] 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."

[1270] In modern medicine, it is extremely difficult for patients and their families to select the most appropriate medical institution and doctor. Especially in the case of serious illnesses, quick decisions based on reliable information are necessary. However, independently collecting and analyzing vast amounts of medical information requires time and effort, and there is a risk of making the wrong choice. Furthermore, the process of creating referral letters and making appointments is cumbersome, placing a significant burden on patients and their families. A system that solves these problems and provides patients and their families with the best medical options is needed.

[1271] 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.

[1272] In this invention, the server includes: a means for patients and their families to input their symptoms, desired treatment, and desired conditions; a means for receiving the information input by the patient and their family and sending it to the generative AI model; a means for the generative AI model to analyze the information using prompts and search a database for the most suitable medical institution and doctor; a means for organizing the information obtained from the database and providing it to the patient and their family; a means for automatically generating a referral letter and providing it to the patient and their family; a means for re-receiving information about the medical institution selected by the patient; and a means for notifying a user terminal of the medical institution's confirmed appointment information. This allows patients and their families to quickly select the most suitable medical institution and doctor based on reliable information. Furthermore, the automatic generation of referral letters and assistance with appointment procedures can reduce the burden on patients and their families.

[1273] "Patients" or "their families" are people who require medical services and their close relatives who provide support.

[1274] A "symptom" refers to a specific problem or symptom related to a patient's health.

[1275] "Treatment preference" means the specific type of medical treatment or therapy desired by the patient.

[1276] "Desired conditions" refer to the geographical, time, and facility requirements that patients and their families consider important when selecting a medical institution.

[1277] "Input means" refers to the mechanism by which a user enters and submits information using a web application or other interface.

[1278] "Receiving means" refers to a function that allows the server to receive information sent by the user.

[1279] A "generative AI model" refers to an artificial intelligence algorithm that analyzes information entered by patients and their families and selects the most appropriate medical institution and doctor.

[1280] A "prompt" is a short sentence or combination of keywords used to provide input to a generative AI model and serve as the basis for analysis.

[1281] "Database" refers to an electronic data storage system for storing data such as details, ratings, and locations of medical institutions and physicians.

[1282] "Organization means" refers to the function for organizing information obtained from a generative AI model into an easy-to-understand format.

[1283] "Means of delivery" refers to the mechanism for delivering organized information and generated referral letters to patients and their families.

[1284] A "letter of referral" refers to a referral document to a medical institution that is prepared based on the patient's medical condition and treatment wishes.

[1285] "Selected information" refers to information about a specific medical institution selected by the patient or their family from the medical institution information provided.

[1286] "Reservation procedure support means" refers to the support functions required to confirm a reservation at the selected medical institution.

[1287] "Reservation confirmation information" refers to information indicating that a reservation has been confirmed after checking the schedule of the medical institution.

[1288] The present invention provides a system for providing an online referral service that enables patients and their families to quickly and accurately select the most suitable medical institution and doctor, and supports the creation of referral letters and reservation procedures. An embodiment of this system will be described in detail below.

[1289] Basic structure and operation

[1290] User terminal operation

[1291] Users use a web application provided through a web browser on their PC or smartphone (e.g., Google Chrome, Mozilla Firefox) to input their symptoms, desired treatment, and desired conditions. For example, they input data such as "I've been diagnosed with breast cancer," "I'd like a hospital that offers the latest treatments," and "A location within Tokyo that's easy to get to." After completing the input, they click the send button to send this information to the server.

[1292] Server Operation

[1293] The server receives user-submitted information via an HTTP POST request. To process this information, the server leverages a generative AI model (e.g., GPT-4 or BERT). The received user data is transformed into a prompt like this:

[1294] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[1295] This prompt sentence is input into the generative AI model and analysis begins.

[1296] Analysis using generative AI models

[1297] The generative AI model analyzes the user's medical condition and desired conditions, and searches a database for appropriate medical institutions and doctors. The database contains detailed information on multiple medical institutions and doctors. For example, it identifies the most suitable medical institution and doctor based on the conditions "breast cancer," "latest treatment," and "within Tokyo."

[1298] Data organization and referral generation

[1299] The server integrates the information obtained from the generative AI model and prepares it for delivery to the user. This information is organized in JSON format and provided to the user via a web application. The server also automatically generates a referral letter and saves it in PDF format. This referral letter includes the patient's medical condition, desired conditions, recommended treatment, and other information.

[1300] Sending information to user terminals

[1301] The organized medical institution information and referral letter are sent to the user's device as an HTTP response, where the user can view the information and check the details on the web application.

[1302] Reservation procedure

[1303] Once the user selects the most suitable medical institution, the selection information is sent back to the server. The server then checks the schedule of the selected medical institution via API and confirms the reservation. The confirmed reservation information is then sent to the user's device. The user can then receive the confirmed reservation information and prepare for their hospital visit.

[1304] Specific examples

[1305] For example, a user enters the criteria "breast cancer," "latest treatment," and "location within Tokyo that is easy to get to." This information is sent to the server, and the generative AI model begins its analysis. The prompt is as follows:

[1306] "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo"

[1307] Based on the analysis results, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is created from the database. This information is organized and provided to the user.

[1308] When the user selects "Medical Institution A," that information is sent to the server again. The server then checks the schedule of "Medical Institution A" and sends the confirmed reservation information to the user's terminal. The user can use this information to plan their hospital visit.

[1309] This way, patients and their families can easily find good medical institutions and doctors and get the necessary procedures done quickly and efficiently.

[1310] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] User input of information

[1313] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. At this time, they enter information such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "It should be located in Tokyo and be easy to get to" as text into the input form. Once they have completed the input, they click the send button, which sends the entered information to the server.

[1314] Input: Symptoms and wishes entered by the user into the web application

[1315] Output: The input information is sent to the server as an HTTP request.

[1316] Step 2:

[1317] Server receives information

[1318] The server receives information sent by the user via an HTTP POST request, temporarily stores the received data in JSON format, and converts it into a format that can be input to the generative AI model.

[1319] Input: User-submitted information in JSON format

[1320] Output: Prompt sentence to be input to the generative AI model

[1321] Step 3:

[1322] Analysis using generative AI models

[1323] The server inputs a prompt into the generative AI model and begins analysis. For example, the prompt might be "Condition: Breast cancer, Treatment desired: Latest treatment, Location: Tokyo." The generative AI model uses this prompt to analyze the most suitable medical institution and doctor.

[1324] Input: prompt statement

[1325] Output: Analysis results from the generative AI model (list of optimal medical institutions and doctors)

[1326] Step 4:

[1327] Searching from the database

[1328] The server searches a database for detailed information on the most suitable medical institution and doctor based on the analysis results of the generative AI model. The database stores detailed information on hospitals and clinics, as well as the doctor's specialty and reputation. For example, based on the analysis results of the criteria "breast cancer," "latest treatment," and "within Tokyo," the server searches for "Medical Institution A," "Medical Institution B," and "Medical Institution C."

[1329] Input: Analysis results of the generative AI model

[1330] Output: Information on the most suitable medical institution and doctor obtained from the database

[1331] Step 5:

[1332] Organizing information and generating referral letters

[1333] The server organizes the information obtained from the database and prepares it for delivery to the user. This information is consolidated into an easy-to-understand format, such as JSON. At the same time, the server automatically generates a referral letter, which describes the patient's condition, desired conditions, and recommended treatment, and is saved in PDF format.

[1334] Input: Medical institution information obtained from the database

[1335] Output: Organized medical institution information and referral letter (PDF format)

[1336] Step 6:

[1337] Sending information to user terminals

[1338] The server sends the organized medical institution information and referral letter to the user's device as an HTTP response. The user can view this information on the web application and check the details.

[1339] Input: Organized medical institution information and referral letter (PDF format)

[1340] Output: Medical institution information and referral letter displayed on the user's terminal

[1341] Step 7:

[1342] User selection of medical institution

[1343] The user views the medical institution information provided on the web application and selects the most appropriate option from "Medical Institution A," "Medical Institution B," or "Medical Institution C." The selected information is then sent back to the server.

[1344] Input: Information about the medical institution selected by the user

[1345] Output: Selection information is sent to the server

[1346] Step 8:

[1347] Server-based reservation process

[1348] The server receives the information about the medical institution selected by the user and checks the schedule of that institution. It then uses an API to connect to the medical institution's reservation system and confirms the reservation. Once the reservation is confirmed, the server notifies the user's device of the reservation confirmation information.

[1349] Input: Information about the medical institution selected by the user

[1350] Output: Confirmed reservation information is sent to the user's device.

[1351] Step 9:

[1352] User confirms reservation and prepares visit

[1353] The user can then confirm the confirmed reservation information on the web application. After confirming that the reservation information has been confirmed, the user can then prepare to visit the medical institution.

[1354] Input: Confirmed reservation information

[1355] Output: User confirms appointment and begins visit preparation

[1356] (Application example 1)

[1357] 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."

[1358] In conventional medical referral systems, there is a high risk of medical information entered by patients and their families being leaked to the outside, making security a major issue. There is also a need to improve the accuracy of analysis based on the patient's medical condition and desired conditions, which makes it difficult to find the most suitable medical institution or doctor.

[1359] 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.

[1360] In this invention, the server includes means for patients and their families to input their symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their family and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for organizing the information obtained from the database and providing it to the patient and their family, means for automatically generating a referral letter and providing it to the patient and their family, means for encrypting the input information, and means for decrypting the encrypted information. This enables quick and accurate referral to the most suitable medical institution and doctor while protecting the patient's confidential information with high security.

[1361] "Patients and their families" refers to individuals who require medical services and their supporters.

[1362] "Symptoms" refer to abnormalities or distress in the patient's body or mind.

[1363] "Desired treatment details" is information indicating the specific treatment methods and medical services desired by the patient and their family.

[1364] "Desired conditions" refers to specific requests regarding medical institutions and treatment, such as location, date and time, and specialty.

[1365] "Means of input" refers to the interface or device through which a user provides information to a system.

[1366] "Means for receiving" refers to a mechanism for receiving information sent by a user.

[1367] A "generative AI model" refers to a program that uses artificial intelligence technology to analyze input data and generate optimal answers or suggestions.

[1368] A "database" refers to a system that systematically organizes and manages information about medical institutions and doctors, making it searchable.

[1369] "Search methods" refer to algorithms or programs used to find information that meets specific criteria from a database.

[1370] "Means for organizing and presenting" refers to the mechanism for presenting the searched information to the user in an easy-to-understand format.

[1371] "Means for automatically generating a letter of introduction" refers to a program that automatically creates a letter of introduction based on information entered by the user and the results of analysis.

[1372] "Encryption methods" refers to techniques for converting information into a form that cannot be deciphered by third parties.

[1373] "Means to decrypt" refers to the technology used to restore encrypted information to its original form.

[1374] The system of the present invention provides an online referral service that introduces optimal medical institutions and doctors based on the results of analysis by a generative AI model after patients and their families input their medical information. This system includes the following means.

[1375] User terminal operation

[1376] The user terminal provides an interface for patients and their families to input information such as symptoms, desired treatment, desired conditions, etc. For example, a user might input data such as "I've been diagnosed with breast cancer," "I'd like to go to a hospital that offers the latest treatments," and "I'd like to go to a hospital in Tokyo that's easy to get to." This input information is encrypted and sent to the server.

[1377] Server Operation

[1378] The server receives the entered medical information and first decrypts the encrypted data. It then requests the generative AI model to analyze it. The generative AI model then searches the database for the most suitable medical institution and doctor based on the decrypted data. In this process, the generative AI model performs its analysis using prompts such as the following:

[1379] "Find accessible hospitals in Tokyo that offer the latest treatments for breast cancer patients."

[1380] Database search and information organization

[1381] The generative AI model searches the database for candidate medical institutions and doctors and extracts relevant information. For example, based on the criteria "breast cancer," "latest treatment," and "within Tokyo," it will select "Medical Institution A," "Medical Institution B," and "Medical Institution C." This information is then organized and prepared for provision to patients and their families.

[1382] Automatic generation of referral letters

[1383] The server automatically generates a referral letter based on the extracted information. The referral letter includes the patient's medical condition, requests, and information on recommended medical institutions and doctors. The generated referral letter is also encrypted when stored and transmitted.

[1384] Confirmation and booking process

[1385] The server sends the organized information and referral letter to the user's terminal, where the user confirms it. For example, the user selects "Medical Institution A" from "Medical Institution A," "Medical Institution B," and "Medical Institution C." The selected information is sent to the server, which checks the schedule of the selected medical institution and assists with the reservation procedure.

[1386] Hardware and software used

[1387] The system uses user devices (smartphones, tablets, PCs), a server, a generative AI model, a database, and encryption / decryption technology. As a specific example, it uses the Python Cryptography package for encryption and decryption.

[1388] example:

[1389] Data entered by the user: "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," "A location in Tokyo that is easy to get to."

[1390] Prompt for generative AI model: "Find hospitals in Tokyo that offer the latest treatments for breast cancer patients and are easy to get to."

[1391] This enables quick and accurate referral to the most appropriate medical institution or doctor while protecting patient confidential information with high security.

[1392] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1393] Step 1:

[1394] The user uses the terminal to input information such as symptoms, desired treatment, and desired conditions.

[1395] Input: The user enters data such as "breast cancer," "latest treatment," and "locations in Tokyo that are easy to get to."

[1396] Output: The input data

[1397] What happens: The user enters information into the interface and clicks the submit button.

[1398] Step 2:

[1399] The terminal encrypts the information entered by the user and sends it to the server.

[1400] Input: Data entered

[1401] Output: Encrypted data

[1402] Specific operation: The terminal uses the encryption module (Python Cryptography package) to encrypt the input data and sends the encrypted data to the server.

[1403] Step 3:

[1404] The server receives and decrypts the encrypted data.

[1405] Input: Encrypted data

[1406] Output: Decrypted data

[1407] Specific operation: Receives encrypted data on the server side and uses a decryption module to restore the original information.

[1408] Step 4:

[1409] The server sends the decrypted data to the generative AI model and requests it to analyze it.

[1410] Input: Decrypted data

[1411] Output: Analysis request to the generative AI model

[1412] Specific behavior: The server generates a prompt based on the content of the data,

[1413] "Find an easily accessible hospital in Tokyo that offers the latest treatments for breast cancer patients."

[1414] This prompt is sent to the generative AI model.

[1415] Step 5:

[1416] The generative AI model searches a database for the most suitable medical institution or doctor based on the prompt text.

[1417] Input: prompt statement

[1418] Output: List of medical institutions and doctors

[1419] How it works: The generative AI model analyzes the prompt, searches for corresponding database entries, and lists appropriate medical institutions and doctors.

[1420] Step 6:

[1421] The server organizes information about medical institutions and doctors obtained from the generative AI model.

[1422] Input: List of medical institutions and doctors

[1423] Output: Organized medical information

[1424] Specific operation: The server organizes the information extracted from the database according to a format and prepares it in a form that can be provided to the user.

[1425] Step 7:

[1426] The server automatically generates and encrypts a referral letter based on the organized medical information.

[1427] Input: Organized medical information

[1428] Output: Encrypted letter of introduction

[1429] Specific operation: The referral letter generation module creates a referral letter based on the listed information of medical institutions and doctors and the information entered by the user, and then encrypts it.

[1430] Step 8:

[1431] The server transmits the encrypted referral letter and medical information to the user terminal.

[1432] Input: Encrypted letter of introduction

[1433] Output: Sending data to the user's terminal

[1434] What it does: The server sends the encrypted referral letter and medical information and makes it accessible to the user.

[1435] Step 9:

[1436] The user can view the medical information and referral letter sent to them and select the most suitable medical institution and doctor.

[1437] Input: Encrypted letter of introduction

[1438] Output: User selection information

[1439] Specific operations: The device decrypts the data received and displays it in a form that can be viewed by the user. The user makes a selection and sends the selection to the server.

[1440] Step 10:

[1441] The server assists the user in making a reservation at a medical institution based on the user's selection information.

[1442] Input: User selection information

[1443] Output: Reservation information

[1444] Specific operation: The server checks the schedule of the selected medical institution and confirms the corresponding appointment.

[1445] Step 11:

[1446] The server notifies the user terminal of the information that the reservation has been confirmed.

[1447] Input: Reservation information

[1448] Output: Booking confirmation notice

[1449] Specific operation: Send a notification to the user's device and display the reservation information.

[1450] 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.

[1451] This invention is a system that provides an online referral service that introduces cancer patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, this invention provides medical information and support according to the user's emotional state.

[1452] Basic structure and operation of the system

[1453] User terminal operation

[1454] The user uses a web application to input their symptoms, desired treatment, and desired conditions. For example, the user might input data such as "I have been diagnosed with breast cancer," "I would like to go to a hospital that offers the latest treatments," and "I would like a hospital in Tokyo that is easy to get to." This input information is sent to the server when the user clicks the "Submit" button.

[1455] Server Operation

[1456] The server receives the information sent by the user. The received information is sent to the generative AI model, which begins analyzing it. The generative AI model understands the user's medical condition and desired conditions, and searches a database for the most suitable medical institution or doctor. The database contains detailed information about hospitals and clinics, as well as the doctor's specialty and reputation.

[1457] Combining Emotion Engines

[1458] Here, the emotion engine recognizes the user's emotional state from the content of their input. For example, it analyzes the emotions of "anxiety," "impatience," and "calmness" from the user's input text. The emotion engine adjusts the recommendations generated by the AI ​​model based on this emotional state.

[1459] The generative AI model not only selects the most suitable medical institutions and doctors based on the criteria of "breast cancer," "latest treatments," and "located in Tokyo," but also prioritizes medical institutions and doctors that users feel more comfortable with, taking into account the state of "anxiety" recognized by the emotion engine. The server organizes this information and prepares it for provision to the user. It also automatically generates a referral letter and saves it in the appropriate format.

[1460] Reply to user terminal

[1461] The server sends the organized medical institution information and referral letters to the user's device. The user's device receives this and displays the information. The user can view detailed information about the listed medical institutions and check recommended options based on their emotional state. For example, from among "Medical Institution A," "Medical Institution B," and "Medical Institution C," the user can select "Medical Institution A," which has been rated as "reliable" by the emotion engine.

[1462] Reservation procedure

[1463] The server checks the schedule of the selected medical institution and confirms the appointment. At this time, it also provides necessary support information and resources based on the user's emotional state. For example, if a user is feeling excessive anxiety, it may provide support such as presenting psychological counseling options. Once the appointment is confirmed, the information is sent to the user's device. The user receives the confirmed appointment information and can begin preparing to visit the medical institution.

[1464] Specific examples

[1465] As a specific example of use, let's say a user enters the conditions "breast cancer," "latest treatment," and "easy-to-access location within Tokyo." This information is sent to the server, and the generative AI model begins analysis. At that time, the emotion engine recognizes the emotion of "anxiety" from the user's input, and taking this result into consideration, prioritizes recommending medical institutions that can provide a greater sense of security. For example, a list of "Medical Institution A," "Medical Institution B," and "Medical Institution C" is displayed, but the emotion engine evaluates "Medical Institution A" as being the best for providing a sense of security.

[1466] The server sends this information to the user's terminal, and the user selects "Medical Institution A." The server then checks the schedule of "Medical Institution A" and confirms the appointment. Furthermore, to address the anxious emotional state, an option for psychological counseling is also provided. The user receives the confirmed appointment and additional support information, allowing them to plan their visit to the medical institution.

[1467] In this way, the present invention utilizes a generative AI model and an emotion engine to provide optimal medical information according to the user's emotional state, thereby reducing the burden of medical selection and providing safer and more reliable medical services.

[1468] The processing flow will be explained below.

[1469] Step 1:

[1470] Users open the web application and enter their symptoms, desired treatment, and desired conditions. For example, they enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "I want a hospital in a convenient location in Tokyo."

[1471] Step 2:

[1472] The user clicks the "Submit" button to send the entered information to the server. The form data is sent to the server in JSON format.

[1473] Step 3:

[1474] The server receives data from the user's device and sends the received information to the generative AI model and emotion engine. The received data is saved in the format {"Symptoms": "Breast cancer", "Desired treatment": "Latest treatment", "Condition": "Within Tokyo"}.

[1475] Step 4:

[1476] The emotion engine analyzes the user's input data and recognizes their emotional state. For example, it analyzes emotions such as "anxiety," "impatience," and "calmness." This emotional state data is passed to the generative AI model.

[1477] Step 5:

[1478] The server's generative AI model analyzes the user's symptoms and desired conditions, and also considers the emotional state from the emotion engine to search for the most suitable medical institution or doctor from the database. For example, the generative AI model extracts the best matching candidates by considering the keywords "breast cancer," "latest treatments," and "Tokyo area" as well as the emotion of "anxiety."

[1479] Step 6:

[1480] The server queries the database based on the information retrieved by the generative AI model to obtain detailed information about medical institutions and doctors. It then sends an SQL query to the database to retrieve information about medical institutions and doctors that meet the criteria.

[1481] Step 7:

[1482] The server organizes the information on medical institutions and doctors it has acquired and creates an information package that takes into account the results of the emotion engine. For example, detailed information on medical institutions A, B, and C is compiled into a list, and medical institution A is evaluated as providing the most reassurance.

[1483] Step 8:

[1484] The server uses the generative AI model to automatically generate a referral letter to the most appropriate medical institution, which includes information such as the user's symptoms, treatment preferences, conditions, and emotional state.

[1485] Step 9:

[1486] The server sends the list of medical institution information and the referral letter to the user's terminal. The generated referral letter and list of medical institutions are returned to the user's terminal in JSON format.

[1487] Step 10:

[1488] The user device receives the data sent from the server and displays it in an appropriate format. Detailed information about medical institutions A, B, and C, along with the created referral letter, are displayed on the screen. Based on the evaluation by the emotion engine, medical institution A is displayed as the most reliable.

[1489] Step 11:

[1490] The user selects an appropriate medical institution from the ones presented and clicks the selection button. For example, the user selects "Medical Institution A."

[1491] Step 12:

[1492] The user's selection information is sent to the server, which then assists in the online reservation procedure with the selected medical institution. The server then checks the schedule of "Medical Institution A" and confirms the reservation.

[1493] Step 13:

[1494] The server notifies the user that the reservation has been confirmed. A confirmation email or app notification is sent to the user. Based on the emotion engine, additional support information may be provided, including psychological counseling options.

[1495] Through these small steps, users can feel at ease when selecting a medical institution using the emotion engine, and can easily proceed with creating a referral letter and making a reservation.

[1496] Example 2

[1497] 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."

[1498] In conventional medical information provision systems, even if patients and their families input their symptoms and desired conditions, they simply refer them to the most suitable medical institution or doctor based on that information, and do not provide sufficient support that takes into account the emotional state of each individual. This has led to the issue of it being difficult to alleviate the anxiety and psychological burden felt by patients and their families.

[1499] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input symptoms, desired treatment contents, and desired conditions, means for receiving the information input by the patient and their families and sending it to the generative AI model, means for the generative AI model to analyze and search a database for the most suitable medical institution and doctor, means for analyzing the emotional state from the user's input content, means for adjusting the most suitable information based on the analyzed emotional state, means for organizing the information obtained from the database and providing it to the patient and their families, and means for automatically generating a referral letter and providing it to the patient and their families. This makes it possible to provide medical information that takes into account the emotional state of the patient and their families, thereby reducing psychological burden and providing a sense of security.

[1500] "Patients and their families" refers to users who input symptoms and treatment details, as well as their supporters.

[1501] "Symptoms" refers to the specific medical conditions or symptoms that are required when seeking treatment or diagnosis from a medical institution.

[1502] "Desired treatment content" refers to the specific treatment method, treatment policy, and type of treatment desired by the patient and their family.

[1503] "Desired conditions" refer to specific conditions or requests that patients and their families want to consider when receiving treatment, such as the characteristics of the region or medical institution, or the doctor's specialty.

[1504] "Input means" refers to an interface that allows the user to send symptoms, desired treatment, and desired conditions to the system.

[1505] "Means for receiving and transmitting to the generative AI model" refers to the mechanism for receiving data entered by a user and passing it to the generative AI model for analysis.

[1506] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze input data and find the most suitable medical institution or doctor.

[1507] "Means for searching from the database" refers to the method by which the generative AI model searches and retrieves information about medical institutions and doctors from the database.

[1508] "Means for analyzing emotional state" refers to technology for identifying and analyzing emotions from user input.

[1509] "Means for adjusting optimal information" refers to a mechanism for appropriately customizing the medical information provided to the user based on the analyzed emotional state.

[1510] "Means of organizing and providing" refers to a method of appropriately organizing information on medical institutions and doctors obtained from the generative AI model and providing it to users in a format that is easy to understand.

[1511] "Means for automatically generating and providing a letter of introduction" refers to a mechanism for automatically creating a letter of introduction to be provided to a user based on information retrieved from a database and delivering it to the user.

[1512] "Means to support the reservation procedure" refers to procedures and support for smoothly making a reservation at the medical institution selected by the user.

[1513] "Means for checking the schedule of a medical institution and confirming a reservation" refers to a system for a user to check the availability of the medical institution where the user wishes to make a reservation and confirm the reservation.

[1514] This invention is a system that provides an online referral service that introduces patients and their families to the most suitable medical institutions and doctors. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide medical information and support according to the user's emotional state.

[1515] User terminal operation

[1516] Users use the web application to enter information such as their symptoms, desired treatment, and desired conditions. Specifically, users enter information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to" into text fields. Once the information is complete, they click the "Submit" button.

[1517] Server Operation

[1518] The server receives data sent from the user's device. Once this data is received, processing begins within the server. First, the received data is passed to a generative AI model for analysis. This generative AI model is used to understand the user's symptoms, desired conditions, and other data, and then searches a database for the most suitable medical institution and doctor.

[1519] Emotion Engine Operation

[1520] The server then passes the user's input to the emotion engine, which analyzes the user's sentences and identifies emotional states such as "anxiety," "impatience," and "calmness." For example, if a user enters the sentences "I've been diagnosed with breast cancer" and "I'd like the latest treatment," the emotion engine identifies the emotion of "anxiety." Based on this emotional state, the generative AI model adjusts the medical institutions and doctors it suggests, prioritizing options that provide greater peace of mind.

[1521] Organizing and providing information

[1522] The server organizes the information on the most suitable medical institution and doctor obtained from the generative AI model and automatically generates a referral letter. This referral letter includes the reason for selection and an evaluation of the patient's comfort level based on their emotional state. The generated information and referral letter are sent to the user's device, where they can be viewed.

[1523] Selection on the user device

[1524] The user checks the provided information and selects the most appropriate option from the listed medical institutions. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C," which the emotion engine has rated as "reliable," are listed, and the user can select "Medical Institution A."

[1525] Reservation procedure

[1526] The server checks the schedule of the selected medical institution and confirms the reservation. If necessary, it also provides options such as psychological counseling. Once the reservation is confirmed, the information is sent to the user's terminal.

[1527] Specific examples

[1528] A user uses a web application to enter data such as "I've been diagnosed with breast cancer," "I want a hospital that offers the latest treatments," and "It should be located in a convenient location within Tokyo," and clicks the "Submit" button. This data is sent to the server, and the generative AI model begins analysis. The emotion engine recognizes "anxiety" from the input and prioritizes recommendations for the most appropriate medical institution, taking this emotion into consideration. As a result, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, with "Medical Institution A" being evaluated as the best for providing a sense of security. The server sends this information to the user's device, and the user selects "Medical Institution A." The server then confirms the appointment, offering the option of psychological counseling. Finally, the user receives the confirmed appointment information and can begin preparing for their visit to the medical institution.

[1529] Prompt Sentence Examples

[1530] An example of a prompt sentence that a user can enter is, "I have been diagnosed with breast cancer and am looking for a hospital in Tokyo that offers the latest treatments. Please give priority to recommendations of reliable medical institutions."

[1531] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1532] Step 1:

[1533] The user opens the web application and enters their symptoms, desired treatment, and desired conditions. The input data is text information such as "I have been diagnosed with breast cancer," "I would like the latest treatment," and "A location in Tokyo that is easy to get to." Once the input is complete, the user clicks the "Submit" button to send the data to the server. The input in this case is text data, and the output is an HTTP POST request sent to the server.

[1534] Step 2:

[1535] The terminal receives data entered by the user and sends it to the server as an HTTP POST request. Specifically, it serializes the input data into JSON format and sends it to the appropriate API endpoint. The input is text data entered by the user, and the output is an HTTP request to the server.

[1536] Step 3:

[1537] The server receives data sent from the device. The received data (input) is JSON format data containing text information and desired conditions. The server parses this data and prepares it to be passed to the generative AI model. The parsed data is passed to the generative AI model as output.

[1538] Step 4:

[1539] The server passes the received user symptoms and desired condition data to the generative AI model and begins analysis. The input is text data describing the symptoms and desired conditions, and the generative AI model analyzes this to understand the user's situation. The output is a list of candidates for the most suitable medical institutions and doctors.

[1540] Step 5:

[1541] The server passes the analyzed data to the emotion engine, which analyzes the user's emotional state. Specifically, it identifies emotions such as "anxiety," "impatience," and "calmness" based on the input data. For example, it can sense "anxiety" from the text "I've been diagnosed with breast cancer" and "I hope for the latest treatment." The output is the identified emotional state, and the results of the generative AI model are adjusted as needed.

[1542] Step 6:

[1543] The server uses the emotional data obtained from the emotion engine to adjust the medical institutions and doctor candidates provided by the generative AI model. The input is the analyzed emotional state and a list of medical institutions, and the output is a list of optimal medical institutions that takes the emotional state into consideration. This allows the information provided to the user to be adjusted based on the user's emotional state.

[1544] Step 7:

[1545] The server organizes the information of the coordinated medical institutions and doctors and automatically generates a referral letter. The input is a list of coordinated medical institutions and emotion analysis data, and the output is an automatically generated referral letter and organized medical institution information. The referral letter includes the reason for recommendation and an evaluation of comfort based on the patient's emotional state.

[1546] Step 8:

[1547] The server sends the generated referral letter and organized medical institution information to the user terminal. The input is the referral letter and medical institution information, and the output is the data sent to the user terminal. The user terminal receives this and prepares to display it on the screen.

[1548] Step 9:

[1549] The user checks the provided medical institution information and referral letter. For example, "Medical Institution A," "Medical Institution B," and "Medical Institution C" are listed, and the user selects "Medical Institution A," which the emotion engine evaluates as "reliable." The input is the medical institution information provided to the user, and the output is the user's selection.

[1550] Step 10:

[1551] The server checks the schedule of the medical institution selected by the user and confirms the appointment. The input is the user's selection data and the medical institution's schedule information, and the output is the confirmed appointment information. In addition, options such as psychological counseling are provided if necessary.

[1552] Step 11:

[1553] The server notifies the user terminal of the confirmed reservation information and support information. The input is the confirmed reservation information and support information, and the output is a notification sent to the user terminal. The user terminal displays the received reservation information and support information and notifies the user.

[1554] (Application example 2)

[1555] 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."

[1556] Conventional medical institution referral systems refer patients to medical institutions and doctors simply based on the symptoms and desired conditions entered, without considering the emotional state of the patient or their family. This makes it difficult to select an appropriate medical institution when users are in a mentally unstable state. Furthermore, they lack the functionality to provide appropriate psychological support to users who feel anxious. Therefore, there is a need for a system that can introduce the most appropriate medical institution while reducing the user's mental burden and providing a sense of security.

[1557] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for patients and their families to input their symptoms, desired treatment details, desired conditions, and concerns; means for receiving the information input by the patient and their family and sending it to the generative AI model; means for the generative AI model to analyze and search a database for the most appropriate medical institution and doctor; emotion analysis means, including emotion analysis means, for analyzing the emotional state of the patient and their family; means for the generative AI model to adjust the selection of a medical institution and doctor based on the emotion analysis results; means for organizing the information obtained from the database and the emotion analysis results and providing them to the patient and their family; means for automatically generating a referral letter and providing it to the patient and their family; and means for supporting the reservation procedure. This enables the server to introduce the most appropriate medical institution and doctor based on the user's emotional state, providing peace of mind and allowing the user to receive appropriate medical services.

[1558] "Patients and their families" refers to the person with the illness and their relatives and close friends who provide support to that person.

[1559] A "symptom" is a physical or psychological symptom associated with a disease or disorder.

[1560] "Desired treatment" refers to the specific treatment methods and types of medical services desired by patients and their families.

[1561] "Desired conditions" are conditions and requests that patients and their families place particular importance on when it comes to treatment, such as location, cost, and doctor's expertise.

[1562] "Anxiety points" are psychological concerns or anxiety factors that patients and their families have regarding treatment or diagnosis.

[1563] A "generative AI model" is a model that uses artificial intelligence technology to analyze user input information and generate optimal suggestions.

[1564] A "database" is a collection of digital data used to organize and manage detailed information about medical institutions and doctors.

[1565] "Emotion analysis means" is a technology that analyzes and recognizes the emotional state of patients and their families.

[1566] "Adjustment based on the results of sentiment analysis" means changing or adjusting the content or quality of the service provided to users based on the results of sentiment analysis.

[1567] A "letter of referral" is an official document used when referring a patient to a medical institution, and is used to provide the patient's information to the doctor or institution to which the patient is referred.

[1568] "Psychological counseling options" are options and services that provide psychological support for anxiety and stress experienced by patients and their families.

[1569] The "reservation procedure" refers to the process of making an appointment in advance to receive the medical service a user desires.

[1570] This invention is a system that provides optimal information to patients and their families when searching for medical institutions and doctors, thereby reducing their psychological anxiety. The system of this invention combines a generative AI model and emotion analysis means to recommend appropriate medical institutions and doctors taking into account the user's emotional state.

[1571] System configuration

[1572] This system mainly consists of the following hardware and software:

[1573] Hardware

[1574] 1. User device: A device used by the user to input information, such as a smartphone or tablet.

[1575] 2. Server: Cloud server used for data processing and storage.

[1576] 3. Database: A database that manages information about medical institutions and doctors.

[1577] software

[1578] 1. Generative AI model: OpenAI's GPT-3 is used.

[1579] 2. Sentiment analysis method: Google Cloud Natural Language API.

[1580] System Operation

[1581] Users can use a device such as a smartphone or tablet to input their symptoms, desired treatment, desired conditions, and concerns. Specific prompts such as the following can be used:

[1582] Prompt Sentence Examples

[1583] The user is feeling anxious. Considering this situation, please suggest the following security measures: Condition: Suspicious activity has been observed recently around the home

[1584] 1. Installing security cameras

[1585] 2. Strengthening entrance doors and windows

[1586] 3. Check the contact details of nearby police stations and security companies

[1587] The information entered by the user is sent to a server. The server uses the Google Cloud Natural Language API to analyze the user's emotional state from the input. For example, an emotional state such as "anxiety" is recognized. The information along with the analyzed emotional state is then sent to a generative AI model, which searches a database for the most suitable medical institution or doctor.

[1588] The generative AI model selects the most suitable medical institutions and doctors based on the user's desired conditions and adjusts the recommendations taking into account the results of sentiment analysis. For example, if the user is feeling "anxious," it will prioritize recommendations of medical institutions that can provide greater reassurance. This allows the user to make appropriate medical choices with peace of mind.

[1589] Information and booking procedures

[1590] The server sends information about medical institutions organized based on the results of the generative AI model and emotion analysis to the user's device. The user can view the received information and select the most suitable medical institution. The server then checks the medical institution's schedule and confirms the appointment, taking into account the emotion analysis results. For example, if a user feels "anxious," it may also offer the option of psychological counseling.

[1591] Users can receive appointment confirmation and additional support information to plan their visit to a medical facility, providing peace of mind and ensuring appropriate medical services are provided.

[1592] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1593] Step 1:

[1594] Users use devices such as smartphones or tablets to input their symptoms, desired treatment, desired conditions, and concerns. This information is entered in text format and sent from the user's device to the server. The input data is used as preparation data for analysis in the next step.

[1595] Step 2:

[1596] The server receives input information from the user's device and performs emotion analysis using the Google Cloud Natural Language API. Specifically, the input text data is sent to the API, and an emotion score is obtained from it as the analysis result. The emotion analysis results are output as emotional states such as "anxiety" or "impatience."

[1597] Step 3:

[1598] The server sends the results of the sentiment analysis along with the conditions entered by the user to a generative AI model (OpenAI's GPT-3). The generative AI model uses the prompt to suggest the most suitable medical institution or doctor. Examples of prompts include, "The user is feeling anxious. Considering this situation, please suggest medical institutions with the following conditions: latest treatments" and "location within Tokyo that is easy to get to." The input data is combined with the results of the sentiment analysis to output a list of the most suitable medical institutions.

[1599] Step 4:

[1600] The server receives the list of medical institutions and doctors obtained from the generative AI model and uses that list to search a database, which contains detailed information about the medical institutions, the doctors' specialties, and their ratings. An organized list of recommended medical institutions is created based on the search results.

[1601] Step 5:

[1602] The server sends a list of recommended medical institutions to the user's terminal. This list includes medical institutions that provide a sense of security based on the results of sentiment analysis. The user can view this list and select the medical institution that best suits them. The user's selection is sent back to the server in the next step.

[1603] Step 6:

[1604] The server receives the user's selection, checks the schedule of the selected medical institution, checks the schedule against the medical institution's database to determine availability, and then generates a notification to confirm the appointment.

[1605] Step 7:

[1606] The server confirms the reservation and sends the confirmed reservation information to the user's device. Furthermore, if psychological counseling options are required based on the results of the emotion analysis, that information is also provided. This allows the user to receive all the necessary information and prepare for their visit to the medical institution with peace of mind.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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. E...

Claims

1. A means for patients and their families to input their symptoms, desired treatment, and desired conditions, A means for receiving and transmitting patient and family input information to the generative AI model; The generative AI model analyzes and searches the database for the most suitable medical institution and doctor, A means of organizing and providing information from the database to patients and their families; A system that includes a means to automatically generate and provide referral letters to patients and their families.

2. 2. The system according to claim 1, further comprising means for supporting a procedure for making an appointment with a medical institution based on a selection of a patient or his / her family.

3. 2. The system according to claim 1, further comprising means for checking the schedule of a medical institution and confirming an appointment.

Images