System

Abstract

A system is provided.SOLUTION: A system includes a means for inputting basic information of a user and storing the basic information in a database, a means for the user to input symptoms in an emergency, a means for analyzing the input symptoms and the basic information using a generated AI model and determining an appropriate medical facility and handling method, a means for notifying the user of the determination result, and a means for providing transportation as necessary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, finding an appropriate medical institution is difficult when someone suddenly falls ill at night or on a holiday. In particular, there are many cases where people are unsure whether to call an ambulance and end up using one even when the symptoms are minor. Furthermore, during times when public transportation is unavailable or when there is no other means of transportation, it is difficult to reach a medical institution on one's own. This has led to an increase in the number of ambulance dispatches, creating a serious problem of delayed response for seriously ill patients who truly require an ambulance. To solve these problems, a system is needed that can quickly and accurately guide people to appropriate medical institutions and treatment methods, and also provide transportation as needed. [Means for solving the problem]

[0005] This invention stores the user's basic information in a database and provides a means for inputting symptoms in the event of an emergency. This allows a generative AI model to analyze the symptoms and basic information and determine whether an ambulance should be called or whether the user should go to an appropriate medical institution. It also provides a means for quickly notifying the user of the results of the determination. Furthermore, it also provides a means for arranging transportation as needed, and by linking with a ride-hailing service, allows users to quickly travel to a medical institution from their home or on the go. The system also incorporates a means for converting voice input into text data and a means for identifying the nearest medical institution using location information, thereby helping users receive appropriate medical care.

[0006] "User" refers to an individual who uses this system.

[0007] "Basic information" refers to data about the user, such as age, gender, chronic illnesses, and information from wearable devices.

[0008] "Symptoms" refer to physical discomfort or abnormalities that users input in an emergency.

[0009] "Database" refers to an information storage system for storing basic information about users and other necessary data.

[0010] A "generative AI model" refers to an artificial intelligence model that analyzes a user's symptoms and basic information and determines the appropriate medical institution and response method.

[0011] "Judgment" refers to the judgment made by the generative AI model based on the analysis results.

[0012] "Notification" refers to the means of communicating the results of the generative AI model to the user.

[0013] "Transportation" refers to the means a user uses to travel to a medical facility, such as ride-hailing services or public transportation.

[0014] A "ride-hailing service" refers to a service that arranges vehicles for users and assists them in their travels.

[0015] "Voice input" refers to a means by which a user inputs information by voice.

[0016] "Character data" refers to text-format data generated based on voice input.

[0017] "Location information" refers to information that indicates a user's current location.

[0018] "Medical institution" refers to a place where medical examinations and treatment are provided, such as a hospital or clinic. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed.

[0041] Specifically, this is achieved by the user using a smartphone or tablet. The system registers the user's basic information in a database in advance, and in the event of an emergency, the user enters their symptoms and runs an analysis using a generative AI model. The analysis results suggest the optimal response, whether to call an ambulance or go directly to the nearest medical institution. It also arranges transportation if necessary.

[0042] Processing flow

[0043] 1. User information registration

[0044] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0045] Examples:

[0046] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0047] 2. Enter your symptoms

[0048] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen.

[0049] Examples:

[0050] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0051] 3. Analysis and Judgment

[0052] The device sends the entered symptoms and registered basic information to the server, which uses an AI model to analyze the data and determine whether an ambulance should be called and which medical institution the patient should go to. The server then sends the result of its decision to the device.

[0053] Examples:

[0054] The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that an ambulance should be called.

[0055] 4. Providing transportation

[0056] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0057] Examples:

[0058] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0059] As described above, the present invention is a system that helps users receive prompt and appropriate medical care in emergencies. The system allows users to register their basic information in advance, and in the event of an emergency, the system inputs their symptoms, which are analyzed by a generative AI model and suggest the optimal response method. Furthermore, it provides transportation as needed, enabling users to quickly access the appropriate medical institution.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The device displays an input screen to receive basic information from the user. The user enters their age, gender, chronic illnesses, and wearable device information, and then presses the send button. The device then encrypts this information and sends it to the server.

[0063] Step 2:

[0064] The server saves the user's basic information received from the device in a database, and once the saving is complete, the server returns a success message to the device.

[0065] Step 3:

[0066] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen for the user.

[0067] Step 4:

[0068] The device sends symptom data and basic information confirmed by the user to the server, which receives this data and inputs it into the AI ​​model for analysis.

[0069] Step 5:

[0070] The server uses an AI model to analyze the input symptom data and basic information, determine the appropriate response, and generate a judgment result that is sent to the device.

[0071] Step 6:

[0072] The device then notifies the user of the results of the assessment received from the server, including whether to call an ambulance or which medical facility to go to.

[0073] Step 7:

[0074] If a user needs to call an ambulance, they press a button on their device to dispatch an ambulance, which then contacts emergency services and dispatches an ambulance.

[0075] Step 8:

[0076] If the user selects self-transportation, the device prompts the user to select a mode of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and receives vehicle information and an estimated arrival time.

[0077] Step 9:

[0078] The device will then notify the user of the vehicle information and estimated arrival time received from the ride-hailing service, and the user will then be directed to the nearest medical facility.

[0079] The above are the processing steps of the program of the present invention. The specific operations performed at each step enable the user to receive prompt and appropriate medical treatment.

[0080] Example 1

[0081] 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."

[0082] Conventional emergency medical support systems have struggled to provide appropriate and prompt responses when a patient suddenly becomes unwell. Furthermore, they have had problems identifying the most appropriate medical institution or response method due to insufficient analysis of user input. Furthermore, they have also failed to provide comprehensive transportation options to reduce the stress and anxiety users experience during emergencies.

[0083] 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.

[0084] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, means for encrypting information when transmitting and receiving data, and means for converting symptoms input by voice by the user into text data and displaying a confirmation screen. This helps users receive prompt and accurate medical response in an emergency and enables more comprehensive emergency medical support by providing transportation as needed.

[0085] "Basic user information" refers to general personal medical and health information, such as the user's age, gender, medical history, and wearable device information.

[0086] The "symptom input means" is a means for the user to input symptoms by voice or text when the user feels suddenly unwell.

[0087] The "generative AI model" is an artificial intelligence model that analyzes the user's symptoms and basic information entered and determines the appropriate medical institution and response method.

[0088] The "judgment result notification means" is a means for notifying the user of the analysis results of the generative AI model.

[0089] "Transportation means provision means" refers to a means for providing users with transportation means necessary in an emergency (such as an ambulance or a ride-hailing service).

[0090] "Data encryption means" refers to encryption technology used to securely protect a user's personal information and symptom data when transmitting and receiving the information.

[0091] The "voice-to-text conversion means" is a means for converting the symptoms input by the user into text data and accurately confirming them.

[0092] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed. Specifically, it is realized by the user using a smartphone or tablet device. This system mainly includes the following means.

[0093] User information registration method

[0094] Using the application, users enter basic information such as age, gender, chronic illnesses, and wearable device information. The device then encrypts this information and sends it to the server, which then stores it in a database.

[0095] Example: A user starts an app, enters their age (30), gender (female), and chronic illness (diabetes), and presses the send button. The device sends this information to the server, which then stores it in a database.

[0096] Symptom input method

[0097] If a user feels unwell in an emergency, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen.

[0098] Example: A user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0099] Analysis methods using generative AI models

[0100] The device sends the entered symptoms and registered basic information to the server. The server analyzes the data using a generative AI model and determines whether to call an ambulance or which medical institution the patient should go to. The server then sends the result of the decision to the device.

[0101] Example: The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that "an ambulance should be called."

[0102] Notification of the results of the assessment

[0103] The user is notified of the judgment result. The terminal receives the judgment result from the server and displays it to the user. This notification enables the user to quickly take the next action.

[0104] Example: If the server determines that an ambulance is needed, it notifies the user that "an ambulance should be called."

[0105] Means of transportation provision

[0106] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle information and estimated arrival time.

[0107] Example: If the server determines that the symptoms are mild, the device will suggest to the user, "Go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user, "A vehicle will arrive in 5 minutes."

[0108] Prompt Sentence Examples

[0109] Below is an example of a prompt sentence.

[0110] "I'm a 30-year-old woman with diabetes. What emergency measures should I take if I experience shortness of breath?"

[0111] To implement this invention, devices such as smartphones and tablets, a server to manage the database, a generative AI model to perform analysis, technology to convert voice into text data, encryption technology to ensure security, etc. are required. This will enable users to receive prompt and accurate medical treatment in an emergency and provide transportation as needed.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1: Register your user information

[0114] Device:

[0115] The user launches the app on their smartphone or tablet and enters basic information (age, gender, chronic illnesses, wearable device information). This input data is encrypted on the device and sent to the server. For example, the user enters "30 years old," "female," and "diabetes."

[0116] server:

[0117] The server decrypts the received encrypted data and stores it in a database, including the user's age, gender, and medical conditions.

[0118] input:

[0119] User basic information (age, gender, chronic illness, wearable device information)

[0120] output:

[0121] User information stored in a database

[0122] Step 2: Enter your symptoms

[0123] user:

[0124] If you feel unwell in an emergency, open the app and enter your symptoms by voice or text. For example, you can enter "shortness of breath" by voice.

[0125] Device:

[0126] The device converts the input voice data into text data and displays it to the user on a confirmation screen. When the user presses the confirmation button, the text data is sent to the server.

[0127] input:

[0128] User voice or text input of symptoms

[0129] output:

[0130] Symptom text data sent to the server

[0131] Step 3: Symptom analysis and diagnosis

[0132] server:

[0133] The server receives symptom data sent from the device and basic user information stored in a database. It uses a generative AI model to analyze this data and determine whether an ambulance is needed or whether guidance to the nearest medical facility is appropriate. For example, it might analyze the combination of "shortness of breath" and "diabetes" to determine whether an ambulance is needed.

[0134] input:

[0135] Symptom text data, user information stored in the database

[0136] output:

[0137] Judgment result (e.g., ambulance required)

[0138] Step 4: Notification of the decision

[0139] server:

[0140] The server then sends the analysis results of the generated AI model to the device, which include information on whether an ambulance is needed and which medical facility the patient should go to.

[0141] Device:

[0142] The device then notifies the user of the results of the assessment. For example, it may say, "You should call an ambulance." If the condition is judged to be mild, it may suggest, "Go to the nearest medical institution."

[0143] input:

[0144] Analysis results of generative AI model

[0145] output:

[0146] User Notification

[0147] Step 5: Providing transportation

[0148] Device:

[0149] If the result of the assessment is that an ambulance is not necessary, the device presents an interface that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and notifies the user of the vehicle information and estimated arrival time.

[0150] input:

[0151] User Selection (Ride-Hailing Service)

[0152] output:

[0153] Vehicle information and estimated arrival time notifications

[0154] These are the specific processing steps of this system. At each step, the necessary data processing or calculation is performed based on the input data, and the results are output to the next step or to the user. As a concrete example, there is a series of steps in which a user registers basic information such as "age 30," "female," and "diabetes," and then vocally inputs the symptom "shortness of breath."

[0155] (Application example 1)

[0156] 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."

[0157] In conventional emergency medical support systems, it is difficult for users to quickly identify appropriate medical institutions and response methods in the event of an emergency, and transportation arrangements are often insufficient. This makes it difficult for users to receive prompt and appropriate medical treatment in the event of an emergency. The present invention aims to solve these problems and support users in receiving appropriate and prompt medical treatment in the event of an emergency.

[0158] 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.

[0159] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, and means for notifying the user of transportation arrangement information, thereby enabling the user to receive prompt and appropriate medical treatment in an emergency.

[0160] "Basic information" refers to personal information that is registered in advance in a database, such as the user's age, gender, medical history, and wearable device information.

[0161] "Symptom input" refers to the act of a user providing the application with the symptoms of illness they experience during an emergency through voice recognition or text input.

[0162] A "generative AI model" is an artificial intelligence algorithm used to analyze collected basic user information and symptom inputs and determine appropriate medical responses.

[0163] The "judgment result" is information that indicates the optimal course of action the user should take and the medical institution they should go to, based on data analyzed by the generative AI model.

[0164] "Transportation" refers to the means of transportation necessary for users to access appropriate medical facilities, such as ride-hailing services and ambulances.

[0165] "Transportation arrangement information" refers to details of the transportation method selected by the user, such as vehicle information and estimated arrival time in the case of a ride-hailing service, or arrival time in the case of an ambulance.

[0166] The system for realizing the present invention comprises a server, a terminal, and a user. A specific embodiment of the system is shown below.

[0167] System Configuration

[0168] 1. Server:

[0169] The server stores the user's basic information in a database and, in the event of an emergency, analyzes the symptoms and basic information entered using a generative AI model. It has the function of notifying the user of the diagnosis result and information on transportation arrangements. The software used includes a Django server and a PostgreSQL database.

[0170] 2. Terminal:

[0171] The device is a smartphone or tablet operated by the user. The device provides a UI for inputting and sending basic user information, and displays a symptom input screen in an emergency. It also includes a function to convert voice input into text data.

[0172] 3. User:

[0173] Users register basic information such as their age, gender, and chronic illnesses in advance through the device, and in the event of an emergency, they can receive emergency medical support by entering their symptoms into the device.

[0174] Program processing

[0175] The server runs a generative AI model using the collected basic information and symptom data to determine the appropriate medical institution and response method. The generative AI model uses advanced natural language processing algorithms such as GPT-4 and BERT. The server notifies the device of the result of the assessment in real time and, if necessary, arranges transportation using a ride-hailing service API (e.g., Uber API).

[0176] Specific examples

[0177] Register basic information:

[0178] The user launches the app and enters their age, gender, chronic illnesses, etc. For example, if a user registers "30 years old, female, diabetes," the device encrypts this information and sends it to the server, which then stores it in a database.

[0179] Enter your symptoms:

[0180] In an emergency, the user can say "I'm short of breath" by voice. The device converts the voice into text data and displays a confirmation screen.

[0181] Analysis and determination:

[0182] The server runs a generative AI model based on the symptom of "shortness of breath" and the chronic illness of "diabetes" to determine whether an ambulance should be called.

[0183] Transportation arrangements:

[0184] If the injury is determined to be minor, the server will connect with the ride-hailing service and notify the user that a vehicle will arrive in five minutes.

[0185] Prompt Sentence Examples

[0186] "I'm currently having trouble breathing. I have diabetes. Based on my location, please tell me the best medical facility and transportation options."

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] The user enters basic information (age, gender, chronic illnesses, etc.) on the device.

[0190] Specific behavior:

[0191] The device encrypts the basic information entered and sends it to the server, which stores the received data in a database.

[0192] Input: User's basic information (e.g., age, gender, chronic illness)

[0193] Output: Encrypted basic information data, saved in database

[0194] Step 2:

[0195] Users enter symptoms in case of an emergency.

[0196] Specific behavior:

[0197] The device displays a symptom input screen, and the user inputs symptoms by voice or text. In the case of voice input, the device converts the voice data into text data and displays a confirmation screen.

[0198] Input: Voice or text input of symptoms (e.g., "shortness of breath")

[0199] Output: Symptom information converted from voice to text data

[0200] Step 3:

[0201] The terminal sends the input symptoms and basic information to the server.

[0202] Specific behavior:

[0203] The device sends symptom information and basic information together to the server, which receives this data and begins analyzing it.

[0204] Input: Symptom information, basic information

[0205] Output: Data package for analysis

[0206] Step 4:

[0207] The server analyzes the data using a generative AI model and determines the appropriate medical institution and response method.

[0208] Specific behavior:

[0209] A generative AI model (e.g., GPT-4 or BERT) on the server analyzes the data using symptom information and basic information to determine whether to call an ambulance or go to a nearby medical facility.

[0210] Input: Symptom information, basic information

[0211] Output: Medical institution and response method decision result

[0212] Step 5:

[0213] The server transmits the determination result to the terminal.

[0214] Specific behavior:

[0215] The server sends the analysis results of the generated AI model to the user's device and notifies them of the appropriate response.

[0216] Input: Medical institution and response method judgment results

[0217] Output: Notification information (e.g. "You should call an ambulance")

[0218] Step 6:

[0219] The terminal provides transportation as needed.

[0220] Specific behavior:

[0221] If the user's symptoms are determined to be mild, the device will prompt the user to select a ride-hailing service. When the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0222] Input: User's transportation method selection information

[0223] Output: Ride dispatch information (e.g., "The vehicle will arrive in 5 minutes")

[0224] Step 7:

[0225] The server notifies the user of transportation arrangement information.

[0226] Specific behavior:

[0227] The server transmits the vehicle information and estimated arrival time received from the dispatch service to the terminal and notifies the user.

[0228] Input: Vehicle dispatch information

[0229] Output: Notification information for the user (e.g. "The vehicle will arrive in 5 minutes")

[0230] 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.

[0231] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[0232] Specifically, this system will be implemented using smartphones and tablet devices. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions, and the system adjusts the judgment results accordingly. Transportation will also be provided if necessary.

[0233] Processing flow

[0234] 1. User information registration

[0235] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0236] Examples:

[0237] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0238] 2. Enter your symptoms

[0239] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[0240] Examples:

[0241] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0242] 3. Analysis and Emotion Recognition

[0243] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[0244] Examples:

[0245] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[0246] 4. Notification of the decision

[0247] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[0248] Examples:

[0249] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[0250] 5. Providing transportation

[0251] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0252] Examples:

[0253] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0254] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The device displays a registration screen for the user to enter basic information. The user enters their age, gender, chronic illnesses, and wearable device information, and clicks the "Submit" button. The device then encrypts this information and sends it to the server.

[0258] Step 2:

[0259] The server analyzes the user's basic information received from the device and saves it in a database. Once the saving is complete, the server returns a success message to the device. The device notifies the user that "registration is complete."

[0260] Step 3:

[0261] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen. The user confirms their symptoms and presses the "Send" button.

[0262] Step 4:

[0263] The device sends the symptom data submitted by the user and basic information registered in advance to the server. The server receives this data and inputs it into the emotion engine. The emotion engine recognizes emotions from the user's voice and text data and generates emotion data.

[0264] Step 5:

[0265] Once the emotion engine has generated the emotion data, the server inputs it into the generative AI model, which analyzes the user's symptoms, basic information, and emotion data to determine the appropriate medical response. Specifically, it determines whether to call an ambulance or go to the nearest medical facility.

[0266] Step 6:

[0267] The server obtains the judgment results of the generative AI model and sends them to the device. The device then notifies the user of the judgment results, for example, by displaying a message such as "You should call an ambulance" or "You should go to the nearest medical institution."

[0268] Step 7:

[0269] When a user wants to call an ambulance, the user clicks the "Call an ambulance" button on the device. The device contacts the emergency service and dispatches an ambulance. The server receives the ambulance dispatch information from the emergency service and notifies the device. The device notifies the user that "the ambulance is arriving."

[0270] Step 8:

[0271] If the user selects self-transportation, the device displays a screen that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service. The ride-hailing service replies with vehicle information and estimated arrival time to the server, which then sends it to the device. The device notifies the user, "A vehicle has been arranged. Estimated arrival time is 10 minutes later."

[0272] In this way, the present invention provides a series of processes for users to receive prompt and appropriate medical treatment. By combining a generative AI model with an emotion engine, the system provides appropriate medical treatment that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[0273] Example 2

[0274] 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."

[0275] In modern society, there is a demand for prompt and appropriate medical treatment for sudden illnesses, but it is difficult for users to quickly identify appropriate medical institutions and treatment methods. Furthermore, medical treatments that do not take into account the user's emotional state may not achieve optimal results. This creates a problem where users do not receive appropriate treatment in an emergency.

[0276] The identification process by the identification 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 inputting basic information of a user and saving it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for performing analysis in combination with an emotion engine that recognizes emotions from the user's voice and text data, means for notifying the user of the determination result, and means for providing transportation as necessary. This enables the user to receive prompt and accurate medical response in an emergency, and realizes an optimal response that takes the user's emotional state into consideration.

[0277] "Basic user information" refers to personal information such as the user's age, gender, chronic illnesses, and health-related data obtained from wearable devices.

[0278] "Means for storing in a database" refers to a storage system that safely stores input information and allows quick access when needed.

[0279] The "means for inputting symptoms" is an interface that allows the user to input the symptoms of the illness they are currently experiencing, and supports voice recognition or text input.

[0280] A "generative AI model" is a machine learning model used to analyze input data and determine appropriate medical responses and support methods.

[0281] An "emotion engine" is a software component that analyzes and recognizes a user's emotional state from their voice and text data.

[0282] The "means for notifying the user of the determination results" refers to the communication means and display means for notifying the user of the analysis results from the server on the user's terminal.

[0283] "Means for providing transportation" refers to a function that arranges transportation such as a ride-hailing service so that users can quickly travel to the nearest medical institution.

[0284] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[0285] The entire system is implemented using smartphones and tablets. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions and adjust the judgment results accordingly. Transportation can also be provided if necessary.

[0286] Registering user information

[0287] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0288] Examples:

[0289] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0290] Enter symptoms

[0291] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[0292] Examples:

[0293] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0294] Analysis and Emotion Recognition

[0295] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[0296] Examples:

[0297] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[0298] Notification of the results

[0299] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[0300] Examples:

[0301] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[0302] Providing transportation

[0303] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0304] Examples:

[0305] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0306] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[0307] Example prompt sentence:

[0308] Let's say a user types "shortness of breath" and the emotion engine detects a high level of stress from the user's tone of voice. The generative AI model analyzes this and determines that "an ambulance should be called." The corresponding prompt sentence is as follows:

[0309] "The user uses the app and inputs 'shortness of breath' through voice recognition. The emotion engine detects a high level of stress from the tone of the voice. Based on this information, please analyze the appropriate response."

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1:

[0312] Registering user information

[0313] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information. The entered information is processed as follows:

[0314] Input: Age, gender, chronic illness, wearable device information

[0315] Data processing: The device encrypts the information entered

[0316] Output: Encrypted user information data

[0317] Specifically, the user launches the app, enters the required information in each field, and presses the send button. The device then encrypts this information and sends it to the server.

[0318] Step 2:

[0319] Encrypted storage of user information

[0320] The server receives the encrypted user information data and stores it in a database.

[0321] Input: Encrypted user information data

[0322] Data processing: Convert to database format

[0323] Output: User information record stored in the database

[0324] Specifically, the server creates and saves a new user information record in the database based on the received data.

[0325] Step 3:

[0326] Enter symptoms

[0327] When a user feels unwell, the device launches the app and displays a symptom entry screen, where the user can enter their symptoms using voice recognition or text input.

[0328] Input: User's symptoms (voice or text)

[0329] Data processing: Converting voice data into text data (in the case of voice input)

[0330] Output: Symptom data in text format

[0331] Specifically, if a user voice-inputs "shortness of breath," the device will collect the voice using the microphone, convert it into text, and display it on a confirmation screen.

[0332] Step 4:

[0333] Submitting symptom data and basic information

[0334] The device sends the confirmed symptom data and basic information about the user to the server.

[0335] Input: Symptom data in text format, basic information

[0336] Data processing: Convert to transmission format

[0337] Output: Request data to the server

[0338] Specifically, the terminal generates and transmits a request to transmit symptom data and basic information to the server.

[0339] Step 5:

[0340] Emotion Recognition and Analysis

[0341] The server uses an emotion engine to recognize emotions from the user's voice and text data, and sends the analyzed data to the generative AI model.

[0342] Input: Symptom data, basic information, voice / text data

[0343] Data processing: sentiment analysis, generating input data for generative AI models

[0344] Output: Emotion data, analysis results of generative AI model

[0345] Specifically, the server analyzes voice and text data to determine the emotional state, then inputs the emotional and symptom data into a generative AI model to analyze the optimal response.

[0346] Step 6:

[0347] Notification of the results

[0348] The server sends the analysis results of the generative AI model to the device, which then notifies the user of the results.

[0349] Input: Analysis results of the generative AI model

[0350] Data processing: generating notification messages

[0351] Output: Notification data sent to the user's terminal

[0352] Specifically, the server sends the analysis results to the device, and the device displays a notification to the user, such as a message saying, "You should call an ambulance."

[0353] Step 7:

[0354] Providing transportation

[0355] The terminal displays a screen for selecting a means of transportation as necessary, depending on the determination result from the server. If the user selects a ride-hailing service, the terminal sends a request to the ride-hailing service and notifies the user of the arrangement results.

[0356] Input: Select ride service, request ride

[0357] Data processing: Generate a dispatch request and send it to the service API

[0358] Output: Arrangement result from the ride dispatch service

[0359] Specifically, when a user selects a ride-hailing service, the device uses the ride-hailing service's API to arrange a vehicle and notifies the user of that information, such as "The vehicle will arrive in 5 minutes."

[0360] (Application example 2)

[0361] 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."

[0362] In modern society, there is a demand for prompt and appropriate responses to sudden illnesses. However, it is difficult for users to properly recognize their own illness and receive prompt responses that take into account their emotional state. Providing transportation as needed is also a challenge. In such cases, conventional systems do not take the user's emotional state into account, which can result in delayed appropriate responses, so more advanced and rapid response measures are needed.

[0363] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0364] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for analyzing the user's emotions using emotion recognition technology and adjusting the determination result based on the analysis result, means for notifying the user of the determination result, and means for providing transportation as needed. This enables the user to receive appropriate and prompt medical treatment that takes into account their emotional state.

[0365] "Basic User Information" refers to basic profile data entered into an electronic device, such as a user's age, gender, medical conditions, and geographic location.

[0366] A "database" is a place or system where data in digital form is stored in an organized manner.

[0367] "Symptoms" are medical conditions that describe changes in physical condition or discomfort experienced by a User during an Emergency.

[0368] A "generative AI model" is an artificial intelligence model that analyzes input data and provides appropriate results and advice.

[0369] "Emotion recognition technology" is a technology that determines emotions from a user's voice or text input and grasps their state.

[0370] The "judgment result" is information about the appropriate medical institution and response method provided as a result of analysis using a generative AI model and emotion recognition technology.

[0371] "Notification" is the act of informing a user of information via an electronic device.

[0372] "Transportation" means a means of transporting a User to a designated location as needed.

[0373] A "vehicle dispatch service" is a service that arranges a vehicle in response to a user's request.

[0374] This invention is a system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and further provides a more appropriate response by combining it with emotion recognition technology that recognizes the user's emotions. Specific embodiments of this system are described below.

[0375] First, users enter basic information using a smartphone or tablet, including age, gender, chronic illnesses, and wearable device information (heart rate, blood pressure, etc.). This information is encrypted and sent to a server where it is stored in a database.

[0376] Next, if the user feels unwell in an emergency, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the entered voice data into text data and display a confirmation screen.

[0377] The device then sends the entered symptom data and the user's basic information to a server. The server uses emotion recognition technology to analyze the user's emotional state from their voice and text data, and uses a generative AI model to determine the appropriate medical institution and response method based on the analysis results. The server then sends the result of the determination to the device and notifies the user. For example, this may include whether to call an ambulance or which medical institution to go to.

[0378] If necessary, the device will provide transportation. If an ambulance is not required, the user can select a ride-hailing service, and the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0379] As a concrete example, consider the case where a user voice-inputs "I'm short of breath." In this case, emotion recognition technology recognizes a high level of stress from the user's tone of voice. The generative AI model analyzes the combination of symptoms and high stress levels and determines that "an ambulance should be called." This information is then sent to the device and displayed to the user.

[0380] Furthermore, if the symptoms are judged to be mild, the system will suggest to the user to "go to the nearest medical institution," and if the user selects a ride-hailing service, the system will notify the user that "a vehicle will arrive in 5 minutes."

[0381] An example of a prompt is:

[0382] One possible text could be, "The newly developed 'emergency medical response security app' is a system that allows users to quickly input their symptoms when they feel unwell, and uses emotion recognition technology and a generative AI model to provide the most appropriate medical response. For example, if a user suddenly feels shortness of breath, they can register their symptoms via voice input, and emotion recognition technology will analyze their stress level. We are working to implement a function where the AI ​​model will determine the appropriate response and, if necessary, arrange for a vehicle to be dispatched."

[0383] This allows users to receive appropriate and prompt medical treatment that takes their emotional state into account.

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] Registering basic user information

[0387] Using a smartphone or tablet, the user enters basic information such as age, gender, chronic illnesses, and wearable device information. This information is encrypted by the device and sent to a server. The server stores this data in a database. At this stage, the input is the user's basic information, and the output is the data stored in the database.

[0388] Step 2:

[0389] Enter symptoms

[0390] When a user feels unwell, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the entered voice data into text data using voice recognition technology and prompts the user to confirm the conversion result. The input here is the user's voice or text symptom information, and the output is the symptom information converted into text data.

[0391] Step 3:

[0392] Submitting symptoms and basic information

[0393] The terminal sends the converted symptom data and the user's basic information to the server, which stores the received symptom data and basic information for processing. At this stage, the input is the converted symptom data and basic information, and the output is the data sent to the server.

[0394] Step 4:

[0395] Emotion Recognition and Analysis

[0396] The server uses emotion recognition technology to determine the user's emotional state from their voice or text input. The emotion recognition engine generates the user's emotional data and inputs the generated emotional data and symptom data into a generative AI model. The generative AI model analyzes the symptom and emotional data and determines the optimal response method and medical institution. The inputs in this process are the emotional data and symptom data, and the output is the analysis results.

[0397] Step 5:

[0398] Notification of the results

[0399] The server sends the analysis results of the generative AI model to the device. The device notifies the user of the results and suggests appropriate medical institutions and measures to take. For example, this may include "You should call an ambulance" or "Go to the nearest medical institution." The input at this stage is the analysis results, and the output is a notification to the user.

[0400] Step 6:

[0401] Providing transportation

[0402] If necessary, the device will suggest transportation options to the user. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle and estimated arrival time. The input here is the user's ride-hailing request, and the output is the ride-hailing service arrangement information.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] [Second embodiment]

[0407] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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."

[0419] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed.

[0420] Specifically, this is achieved by the user using a smartphone or tablet. The system registers the user's basic information in a database in advance, and in the event of an emergency, the user enters their symptoms and runs an analysis using a generative AI model. The analysis results suggest the optimal response, whether to call an ambulance or go directly to the nearest medical institution. It also arranges transportation if necessary.

[0421] Processing flow

[0422] 1. User information registration

[0423] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0424] Examples:

[0425] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0426] 2. Enter your symptoms

[0427] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen.

[0428] Examples:

[0429] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0430] 3. Analysis and Judgment

[0431] The device sends the entered symptoms and registered basic information to the server, which uses an AI model to analyze the data and determine whether an ambulance should be called and which medical institution the patient should go to. The server then sends the result of its decision to the device.

[0432] Examples:

[0433] The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that an ambulance should be called.

[0434] 4. Providing transportation

[0435] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0436] Examples:

[0437] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0438] As described above, the present invention is a system that helps users receive prompt and appropriate medical care in emergencies. The system allows users to register their basic information in advance, and in the event of an emergency, the system inputs their symptoms, which are analyzed by a generative AI model and suggest the optimal response method. Furthermore, it provides transportation as needed, enabling users to quickly access the appropriate medical institution.

[0439] The processing flow will be explained below.

[0440] Step 1:

[0441] The device displays an input screen to receive basic information from the user. The user enters their age, gender, chronic illnesses, and wearable device information, and then presses the send button. The device then encrypts this information and sends it to the server.

[0442] Step 2:

[0443] The server saves the user's basic information received from the device in a database, and once the saving is complete, the server returns a success message to the device.

[0444] Step 3:

[0445] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen for the user.

[0446] Step 4:

[0447] The device sends symptom data and basic information confirmed by the user to the server, which receives this data and inputs it into the AI ​​model for analysis.

[0448] Step 5:

[0449] The server uses an AI model to analyze the input symptom data and basic information, determine the appropriate response, and generate a judgment result that is sent to the device.

[0450] Step 6:

[0451] The device then notifies the user of the results of the assessment received from the server, including whether to call an ambulance or which medical facility to go to.

[0452] Step 7:

[0453] If a user needs to call an ambulance, they press a button on their device to dispatch an ambulance, which then contacts emergency services and dispatches an ambulance.

[0454] Step 8:

[0455] If the user selects self-transportation, the device prompts the user to select a mode of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and receives vehicle information and an estimated arrival time.

[0456] Step 9:

[0457] The device will then notify the user of the vehicle information and estimated arrival time received from the ride-hailing service, and the user will then be directed to the nearest medical facility.

[0458] The above are the processing steps of the program of the present invention. The specific operations performed at each step enable the user to receive prompt and appropriate medical treatment.

[0459] Example 1

[0460] 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."

[0461] Conventional emergency medical support systems have struggled to provide appropriate and prompt responses when a patient suddenly becomes unwell. Furthermore, they have had problems identifying the most appropriate medical institution or response method due to insufficient analysis of user input. Furthermore, they have also failed to provide comprehensive transportation options to reduce the stress and anxiety users experience during emergencies.

[0462] 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.

[0463] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, means for encrypting information when transmitting and receiving data, and means for converting symptoms input by voice by the user into text data and displaying a confirmation screen. This helps users receive prompt and accurate medical response in an emergency and enables more comprehensive emergency medical support by providing transportation as needed.

[0464] "Basic user information" refers to general personal medical and health information, such as the user's age, gender, medical history, and wearable device information.

[0465] The "symptom input means" is a means for the user to input symptoms by voice or text when the user feels suddenly unwell.

[0466] The "generative AI model" is an artificial intelligence model that analyzes the user's symptoms and basic information entered and determines the appropriate medical institution and response method.

[0467] The "judgment result notification means" is a means for notifying the user of the analysis results of the generative AI model.

[0468] "Transportation means provision means" refers to a means for providing users with transportation means necessary in an emergency (such as an ambulance or a ride-hailing service).

[0469] "Data encryption means" refers to encryption technology used to securely protect a user's personal information and symptom data when transmitting and receiving the information.

[0470] The "voice-to-text conversion means" is a means for converting the symptoms input by the user into text data and accurately confirming them.

[0471] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed. Specifically, it is realized by the user using a smartphone or tablet device. This system mainly includes the following means.

[0472] User information registration method

[0473] Using the application, users enter basic information such as age, gender, chronic illnesses, and wearable device information. The device then encrypts this information and sends it to the server, which then stores it in a database.

[0474] Example: A user starts an app, enters their age (30), gender (female), and chronic illness (diabetes), and presses the send button. The device sends this information to the server, which then stores it in a database.

[0475] Symptom input method

[0476] If a user feels unwell in an emergency, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen.

[0477] Example: A user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0478] Analysis methods using generative AI models

[0479] The device sends the entered symptoms and registered basic information to the server. The server analyzes the data using a generative AI model and determines whether to call an ambulance or which medical institution the patient should go to. The server then sends the result of the decision to the device.

[0480] Example: The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that "an ambulance should be called."

[0481] Notification of the results of the assessment

[0482] The user is notified of the judgment result. The terminal receives the judgment result from the server and displays it to the user. This notification enables the user to quickly take the next action.

[0483] Example: If the server determines that an ambulance is needed, it notifies the user that "an ambulance should be called."

[0484] Means of transportation provision

[0485] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle information and estimated arrival time.

[0486] Example: If the server determines that the symptoms are mild, the device will suggest to the user, "Go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user, "A vehicle will arrive in 5 minutes."

[0487] Prompt Sentence Examples

[0488] Below is an example of a prompt sentence.

[0489] "I'm a 30-year-old woman with diabetes. What emergency measures should I take if I experience shortness of breath?"

[0490] To implement this invention, devices such as smartphones and tablets, a server to manage the database, a generative AI model to perform analysis, technology to convert voice into text data, encryption technology to ensure security, etc. are required. This will enable users to receive prompt and accurate medical treatment in an emergency and provide transportation as needed.

[0491] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0492] Step 1: Register your user information

[0493] Device:

[0494] The user launches the app on their smartphone or tablet and enters basic information (age, gender, chronic illnesses, wearable device information). This input data is encrypted on the device and sent to the server. For example, the user enters "30 years old," "female," and "diabetes."

[0495] server:

[0496] The server decrypts the received encrypted data and stores it in a database, including the user's age, gender, and medical conditions.

[0497] input:

[0498] User basic information (age, gender, chronic illness, wearable device information)

[0499] output:

[0500] User information stored in a database

[0501] Step 2: Enter your symptoms

[0502] user:

[0503] If you feel unwell in an emergency, open the app and enter your symptoms by voice or text. For example, you can enter "shortness of breath" by voice.

[0504] Device:

[0505] The device converts the input voice data into text data and displays it to the user on a confirmation screen. When the user presses the confirmation button, the text data is sent to the server.

[0506] input:

[0507] User voice or text input of symptoms

[0508] output:

[0509] Symptom text data sent to the server

[0510] Step 3: Symptom analysis and diagnosis

[0511] server:

[0512] The server receives symptom data sent from the device and basic user information stored in a database. It uses a generative AI model to analyze this data and determine whether an ambulance is needed or whether guidance to the nearest medical facility is appropriate. For example, it might analyze the combination of "shortness of breath" and "diabetes" to determine whether an ambulance is needed.

[0513] input:

[0514] Symptom text data, user information stored in the database

[0515] output:

[0516] Judgment result (e.g., ambulance required)

[0517] Step 4: Notification of the decision

[0518] server:

[0519] The server then sends the analysis results of the generated AI model to the device, which include information on whether an ambulance is needed and which medical facility the patient should go to.

[0520] Device:

[0521] The device then notifies the user of the results of the assessment. For example, it may say, "You should call an ambulance." If the condition is judged to be mild, it may suggest, "Go to the nearest medical institution."

[0522] input:

[0523] Analysis results of generative AI model

[0524] output:

[0525] User Notification

[0526] Step 5: Providing transportation

[0527] Device:

[0528] If the result of the assessment is that an ambulance is not necessary, the device presents an interface that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and notifies the user of the vehicle information and estimated arrival time.

[0529] input:

[0530] User Selection (Ride-Hailing Service)

[0531] output:

[0532] Vehicle information and estimated arrival time notifications

[0533] These are the specific processing steps of this system. At each step, the necessary data processing or calculation is performed based on the input data, and the results are output to the next step or to the user. As a concrete example, there is a series of steps in which a user registers basic information such as "age 30," "female," and "diabetes," and then vocally inputs the symptom "shortness of breath."

[0534] (Application example 1)

[0535] 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."

[0536] In conventional emergency medical support systems, it is difficult for users to quickly identify appropriate medical institutions and response methods in the event of an emergency, and transportation arrangements are often insufficient. This makes it difficult for users to receive prompt and appropriate medical treatment in the event of an emergency. The present invention aims to solve these problems and support users in receiving appropriate and prompt medical treatment in the event of an emergency.

[0537] 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.

[0538] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, and means for notifying the user of transportation arrangement information, thereby enabling the user to receive prompt and appropriate medical treatment in an emergency.

[0539] "Basic information" refers to personal information that is registered in advance in a database, such as the user's age, gender, medical history, and wearable device information.

[0540] "Symptom input" refers to the act of a user providing the application with the symptoms of illness they experience during an emergency through voice recognition or text input.

[0541] A "generative AI model" is an artificial intelligence algorithm used to analyze collected basic user information and symptom inputs and determine appropriate medical responses.

[0542] The "judgment result" is information that indicates the optimal course of action the user should take and the medical institution they should go to, based on data analyzed by the generative AI model.

[0543] "Transportation" refers to the means of transportation necessary for users to access appropriate medical facilities, such as ride-hailing services and ambulances.

[0544] "Transportation arrangement information" refers to details of the transportation method selected by the user, such as vehicle information and estimated arrival time in the case of a ride-hailing service, or arrival time in the case of an ambulance.

[0545] The system for realizing the present invention comprises a server, a terminal, and a user. A specific embodiment of the system is shown below.

[0546] System Configuration

[0547] 1. Server:

[0548] The server stores the user's basic information in a database and, in the event of an emergency, analyzes the symptoms and basic information entered using a generative AI model. It has the function of notifying the user of the diagnosis result and information on transportation arrangements. The software used includes a Django server and a PostgreSQL database.

[0549] 2. Terminal:

[0550] The device is a smartphone or tablet operated by the user. The device provides a UI for inputting and sending basic user information, and displays a symptom input screen in an emergency. It also includes a function to convert voice input into text data.

[0551] 3. User:

[0552] Users register basic information such as their age, gender, and chronic illnesses in advance through the device, and in the event of an emergency, they can receive emergency medical support by entering their symptoms into the device.

[0553] Program processing

[0554] The server runs a generative AI model using the collected basic information and symptom data to determine the appropriate medical institution and response method. The generative AI model uses advanced natural language processing algorithms such as GPT-4 and BERT. The server notifies the device of the result of the assessment in real time and, if necessary, arranges transportation using a ride-hailing service API (e.g., Uber API).

[0555] Specific examples

[0556] Register basic information:

[0557] The user launches the app and enters their age, gender, chronic illnesses, etc. For example, if a user registers "30 years old, female, diabetes," the device encrypts this information and sends it to the server, which then stores it in a database.

[0558] Enter your symptoms:

[0559] In an emergency, the user can say "I'm short of breath" by voice. The device converts the voice into text data and displays a confirmation screen.

[0560] Analysis and determination:

[0561] The server runs a generative AI model based on the symptom of "shortness of breath" and the chronic illness of "diabetes" to determine whether an ambulance should be called.

[0562] Transportation arrangements:

[0563] If the injury is determined to be minor, the server will connect with the ride-hailing service and notify the user that a vehicle will arrive in five minutes.

[0564] Prompt Sentence Examples

[0565] "I'm currently having trouble breathing. I have diabetes. Based on my location, please tell me the best medical facility and transportation options."

[0566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0567] Step 1:

[0568] The user enters basic information (age, gender, chronic illnesses, etc.) on the device.

[0569] Specific behavior:

[0570] The device encrypts the basic information entered and sends it to the server, which stores the received data in a database.

[0571] Input: User's basic information (e.g., age, gender, chronic illness)

[0572] Output: Encrypted basic information data, saved in database

[0573] Step 2:

[0574] Users enter symptoms in case of an emergency.

[0575] Specific behavior:

[0576] The device displays a symptom input screen, and the user inputs symptoms by voice or text. In the case of voice input, the device converts the voice data into text data and displays a confirmation screen.

[0577] Input: Voice or text input of symptoms (e.g., "shortness of breath")

[0578] Output: Symptom information converted from voice to text data

[0579] Step 3:

[0580] The terminal sends the input symptoms and basic information to the server.

[0581] Specific behavior:

[0582] The device sends symptom information and basic information together to the server, which receives this data and begins analyzing it.

[0583] Input: Symptom information, basic information

[0584] Output: Data package for analysis

[0585] Step 4:

[0586] The server analyzes the data using a generative AI model and determines the appropriate medical institution and response method.

[0587] Specific behavior:

[0588] A generative AI model (e.g., GPT-4 or BERT) on the server analyzes the data using symptom information and basic information to determine whether to call an ambulance or go to a nearby medical facility.

[0589] Input: Symptom information, basic information

[0590] Output: Medical institution and response method decision result

[0591] Step 5:

[0592] The server transmits the determination result to the terminal.

[0593] Specific behavior:

[0594] The server sends the analysis results of the generated AI model to the user's device and notifies them of the appropriate response.

[0595] Input: Medical institution and response method judgment results

[0596] Output: Notification information (e.g. "You should call an ambulance")

[0597] Step 6:

[0598] The terminal provides transportation as needed.

[0599] Specific behavior:

[0600] If the user's symptoms are determined to be mild, the device will prompt the user to select a ride-hailing service. When the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0601] Input: User's transportation method selection information

[0602] Output: Ride dispatch information (e.g., "The vehicle will arrive in 5 minutes")

[0603] Step 7:

[0604] The server notifies the user of transportation arrangement information.

[0605] Specific behavior:

[0606] The server transmits the vehicle information and estimated arrival time received from the dispatch service to the terminal and notifies the user.

[0607] Input: Vehicle dispatch information

[0608] Output: Notification information for the user (e.g. "The vehicle will arrive in 5 minutes")

[0609] 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.

[0610] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[0611] Specifically, this system will be implemented using smartphones and tablet devices. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions, and the system adjusts the judgment results accordingly. Transportation will also be provided if necessary.

[0612] Processing flow

[0613] 1. User information registration

[0614] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0615] Examples:

[0616] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0617] 2. Enter your symptoms

[0618] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[0619] Examples:

[0620] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0621] 3. Analysis and Emotion Recognition

[0622] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[0623] Examples:

[0624] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[0625] 4. Notification of the decision

[0626] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[0627] Examples:

[0628] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[0629] 5. Providing transportation

[0630] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0631] Examples:

[0632] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0633] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] The device displays a registration screen for the user to enter basic information. The user enters their age, gender, chronic illnesses, and wearable device information, and clicks the "Submit" button. The device then encrypts this information and sends it to the server.

[0637] Step 2:

[0638] The server analyzes the user's basic information received from the device and saves it in a database. Once the saving is complete, the server returns a success message to the device. The device notifies the user that "registration is complete."

[0639] Step 3:

[0640] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen. The user confirms their symptoms and presses the "Send" button.

[0641] Step 4:

[0642] The device sends the symptom data submitted by the user and basic information registered in advance to the server. The server receives this data and inputs it into the emotion engine. The emotion engine recognizes emotions from the user's voice and text data and generates emotion data.

[0643] Step 5:

[0644] Once the emotion engine has generated the emotion data, the server inputs it into the generative AI model, which analyzes the user's symptoms, basic information, and emotion data to determine the appropriate medical response. Specifically, it determines whether to call an ambulance or go to the nearest medical facility.

[0645] Step 6:

[0646] The server obtains the judgment results of the generative AI model and sends them to the device. The device then notifies the user of the judgment results, for example, by displaying a message such as "You should call an ambulance" or "You should go to the nearest medical institution."

[0647] Step 7:

[0648] When a user wants to call an ambulance, the user clicks the "Call an ambulance" button on the device. The device contacts the emergency service and dispatches an ambulance. The server receives the ambulance dispatch information from the emergency service and notifies the device. The device notifies the user that "the ambulance is arriving."

[0649] Step 8:

[0650] If the user selects self-transportation, the device displays a screen that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service. The ride-hailing service replies with vehicle information and estimated arrival time to the server, which then sends it to the device. The device notifies the user, "A vehicle has been arranged. Estimated arrival time is 10 minutes later."

[0651] In this way, the present invention provides a series of processes for users to receive prompt and appropriate medical treatment. By combining a generative AI model with an emotion engine, the system provides appropriate medical treatment that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[0652] Example 2

[0653] 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."

[0654] In modern society, there is a demand for prompt and appropriate medical treatment for sudden illnesses, but it is difficult for users to quickly identify appropriate medical institutions and treatment methods. Furthermore, medical treatments that do not take into account the user's emotional state may not achieve optimal results. This creates a problem where users do not receive appropriate treatment in an emergency.

[0655] The identification process by the identification 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 inputting basic information of a user and saving it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for performing analysis in combination with an emotion engine that recognizes emotions from the user's voice and text data, means for notifying the user of the determination result, and means for providing transportation as necessary. This enables the user to receive prompt and accurate medical response in an emergency, and realizes an optimal response that takes the user's emotional state into consideration.

[0656] "Basic user information" refers to personal information such as the user's age, gender, chronic illnesses, and health-related data obtained from wearable devices.

[0657] "Means for storing in a database" refers to a storage system that safely stores input information and allows quick access when needed.

[0658] The "means for inputting symptoms" is an interface that allows the user to input the symptoms of the illness they are currently experiencing, and supports voice recognition or text input.

[0659] A "generative AI model" is a machine learning model used to analyze input data and determine appropriate medical responses and support methods.

[0660] An "emotion engine" is a software component that analyzes and recognizes a user's emotional state from their voice and text data.

[0661] The "means for notifying the user of the determination results" refers to the communication means and display means for notifying the user of the analysis results from the server on the user's terminal.

[0662] "Means for providing transportation" refers to a function that arranges transportation such as a ride-hailing service so that users can quickly travel to the nearest medical institution.

[0663] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[0664] The entire system is implemented using smartphones and tablets. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions and adjust the judgment results accordingly. Transportation can also be provided if necessary.

[0665] Registering user information

[0666] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0667] Examples:

[0668] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0669] Enter symptoms

[0670] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[0671] Examples:

[0672] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0673] Analysis and Emotion Recognition

[0674] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[0675] Examples:

[0676] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[0677] Notification of the results

[0678] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[0679] Examples:

[0680] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[0681] Providing transportation

[0682] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0683] Examples:

[0684] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0685] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[0686] Example prompt sentence:

[0687] Let's say a user types "shortness of breath" and the emotion engine detects a high level of stress from the user's tone of voice. The generative AI model analyzes this and determines that "an ambulance should be called." The corresponding prompt sentence is as follows:

[0688] "The user uses the app and inputs 'shortness of breath' through voice recognition. The emotion engine detects a high level of stress from the tone of the voice. Based on this information, please analyze the appropriate response."

[0689] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0690] Step 1:

[0691] Registering user information

[0692] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information. The entered information is processed as follows:

[0693] Input: Age, gender, chronic illness, wearable device information

[0694] Data processing: The device encrypts the information entered

[0695] Output: Encrypted user information data

[0696] Specifically, the user launches the app, enters the required information in each field, and presses the send button. The device then encrypts this information and sends it to the server.

[0697] Step 2:

[0698] Encrypted storage of user information

[0699] The server receives the encrypted user information data and stores it in a database.

[0700] Input: Encrypted user information data

[0701] Data processing: Convert to database format

[0702] Output: User information record stored in the database

[0703] Specifically, the server creates and saves a new user information record in the database based on the received data.

[0704] Step 3:

[0705] Enter symptoms

[0706] When a user feels unwell, the device launches the app and displays a symptom entry screen, where the user can enter their symptoms using voice recognition or text input.

[0707] Input: User's symptoms (voice or text)

[0708] Data processing: Converting voice data into text data (in the case of voice input)

[0709] Output: Symptom data in text format

[0710] Specifically, if a user voice-inputs "shortness of breath," the device will collect the voice using the microphone, convert it into text, and display it on a confirmation screen.

[0711] Step 4:

[0712] Submitting symptom data and basic information

[0713] The device sends the confirmed symptom data and basic information about the user to the server.

[0714] Input: Symptom data in text format, basic information

[0715] Data processing: Convert to transmission format

[0716] Output: Request data to the server

[0717] Specifically, the terminal generates and transmits a request to transmit symptom data and basic information to the server.

[0718] Step 5:

[0719] Emotion Recognition and Analysis

[0720] The server uses an emotion engine to recognize emotions from the user's voice and text data, and sends the analyzed data to the generative AI model.

[0721] Input: Symptom data, basic information, voice / text data

[0722] Data processing: sentiment analysis, generating input data for generative AI models

[0723] Output: Emotion data, analysis results of generative AI model

[0724] Specifically, the server analyzes voice and text data to determine the emotional state, then inputs the emotional and symptom data into a generative AI model to analyze the optimal response.

[0725] Step 6:

[0726] Notification of the results

[0727] The server sends the analysis results of the generative AI model to the device, which then notifies the user of the results.

[0728] Input: Analysis results of the generative AI model

[0729] Data processing: generating notification messages

[0730] Output: Notification data sent to the user's terminal

[0731] Specifically, the server sends the analysis results to the device, and the device displays a notification to the user, such as a message saying, "You should call an ambulance."

[0732] Step 7:

[0733] Providing transportation

[0734] The terminal displays a screen for selecting a means of transportation as necessary, depending on the determination result from the server. If the user selects a ride-hailing service, the terminal sends a request to the ride-hailing service and notifies the user of the arrangement results.

[0735] Input: Select ride service, request ride

[0736] Data processing: Generate a dispatch request and send it to the service API

[0737] Output: Arrangement result from the ride dispatch service

[0738] Specifically, when a user selects a ride-hailing service, the device uses the ride-hailing service's API to arrange a vehicle and notifies the user of that information, such as "The vehicle will arrive in 5 minutes."

[0739] (Application example 2)

[0740] 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."

[0741] In modern society, there is a demand for prompt and appropriate responses to sudden illnesses. However, it is difficult for users to properly recognize their own illness and receive prompt responses that take into account their emotional state. Providing transportation as needed is also a challenge. In such cases, conventional systems do not take the user's emotional state into account, which can result in delayed appropriate responses, so more advanced and rapid response measures are needed.

[0742] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0743] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for analyzing the user's emotions using emotion recognition technology and adjusting the determination result based on the analysis result, means for notifying the user of the determination result, and means for providing transportation as needed. This enables the user to receive appropriate and prompt medical treatment that takes into account their emotional state.

[0744] "Basic User Information" refers to basic profile data entered into an electronic device, such as a user's age, gender, medical conditions, and geographic location.

[0745] A "database" is a place or system where data in digital form is stored in an organized manner.

[0746] "Symptoms" are medical conditions that describe changes in physical condition or discomfort experienced by a User during an Emergency.

[0747] A "generative AI model" is an artificial intelligence model that analyzes input data and provides appropriate results and advice.

[0748] "Emotion recognition technology" is a technology that determines emotions from a user's voice or text input and grasps their state.

[0749] The "judgment result" is information about the appropriate medical institution and response method provided as a result of analysis using a generative AI model and emotion recognition technology.

[0750] "Notification" is the act of informing a user of information via an electronic device.

[0751] "Transportation" means a means of transporting a User to a designated location as needed.

[0752] A "vehicle dispatch service" is a service that arranges a vehicle in response to a user's request.

[0753] This invention is a system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and further provides a more appropriate response by combining it with emotion recognition technology that recognizes the user's emotions. Specific embodiments of this system are described below.

[0754] First, users enter basic information using a smartphone or tablet, including age, gender, chronic illnesses, and wearable device information (heart rate, blood pressure, etc.). This information is encrypted and sent to a server where it is stored in a database.

[0755] Next, if the user feels unwell in an emergency, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the entered voice data into text data and display a confirmation screen.

[0756] The device then sends the entered symptom data and the user's basic information to a server. The server uses emotion recognition technology to analyze the user's emotional state from their voice and text data, and uses a generative AI model to determine the appropriate medical institution and response method based on the analysis results. The server then sends the result of the determination to the device and notifies the user. For example, this may include whether to call an ambulance or which medical institution to go to.

[0757] If necessary, the device will provide transportation. If an ambulance is not required, the user can select a ride-hailing service, and the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0758] As a concrete example, consider the case where a user voice-inputs "I'm short of breath." In this case, emotion recognition technology recognizes a high level of stress from the user's tone of voice. The generative AI model analyzes the combination of symptoms and high stress levels and determines that "an ambulance should be called." This information is then sent to the device and displayed to the user.

[0759] Furthermore, if the symptoms are judged to be mild, the system will suggest to the user to "go to the nearest medical institution," and if the user selects a ride-hailing service, the system will notify the user that "a vehicle will arrive in 5 minutes."

[0760] An example of a prompt is:

[0761] One possible text could be, "The newly developed 'emergency medical response security app' is a system that allows users to quickly input their symptoms when they feel unwell, and uses emotion recognition technology and a generative AI model to provide the most appropriate medical response. For example, if a user suddenly feels shortness of breath, they can register their symptoms via voice input, and emotion recognition technology will analyze their stress level. We are working to implement a function where the AI ​​model will determine the appropriate response and, if necessary, arrange for a vehicle to be dispatched."

[0762] This allows users to receive appropriate and prompt medical treatment that takes their emotional state into account.

[0763] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0764] Step 1:

[0765] Registering basic user information

[0766] Using a smartphone or tablet, the user enters basic information such as age, gender, chronic illnesses, and wearable device information. This information is encrypted by the device and sent to a server. The server stores this data in a database. At this stage, the input is the user's basic information, and the output is the data stored in the database.

[0767] Step 2:

[0768] Enter symptoms

[0769] When a user feels unwell, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the entered voice data into text data using voice recognition technology and prompts the user to confirm the conversion result. The input here is the user's voice or text symptom information, and the output is the symptom information converted into text data.

[0770] Step 3:

[0771] Submitting symptoms and basic information

[0772] The terminal sends the converted symptom data and the user's basic information to the server, which stores the received symptom data and basic information for processing. At this stage, the input is the converted symptom data and basic information, and the output is the data sent to the server.

[0773] Step 4:

[0774] Emotion Recognition and Analysis

[0775] The server uses emotion recognition technology to determine the user's emotional state from their voice or text input. The emotion recognition engine generates the user's emotional data and inputs the generated emotional data and symptom data into a generative AI model. The generative AI model analyzes the symptom and emotional data and determines the optimal response method and medical institution. The inputs in this process are the emotional data and symptom data, and the output is the analysis results.

[0776] Step 5:

[0777] Notification of the results

[0778] The server sends the analysis results of the generative AI model to the device. The device notifies the user of the results and suggests appropriate medical institutions and measures to take. For example, this may include "You should call an ambulance" or "Go to the nearest medical institution." The input at this stage is the analysis results, and the output is a notification to the user.

[0779] Step 6:

[0780] Providing transportation

[0781] If necessary, the device will suggest transportation options to the user. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle and estimated arrival time. The input here is the user's ride-hailing request, and the output is the ride-hailing service arrangement information.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] [Third embodiment]

[0786] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0787] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0788] 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).

[0789] 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.

[0790] 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.

[0791] 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).

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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."

[0798] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed.

[0799] Specifically, this is achieved by the user using a smartphone or tablet. The system registers the user's basic information in a database in advance, and in the event of an emergency, the user enters their symptoms and runs an analysis using a generative AI model. The analysis results suggest the optimal response, whether to call an ambulance or go directly to the nearest medical institution. It also arranges transportation if necessary.

[0800] Processing flow

[0801] 1. User information registration

[0802] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0803] Examples:

[0804] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0805] 2. Enter your symptoms

[0806] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen.

[0807] Examples:

[0808] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0809] 3. Analysis and Judgment

[0810] The device sends the entered symptoms and registered basic information to the server, which uses an AI model to analyze the data and determine whether an ambulance should be called and which medical institution the patient should go to. The server then sends the result of its decision to the device.

[0811] Examples:

[0812] The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that an ambulance should be called.

[0813] 4. Providing transportation

[0814] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0815] Examples:

[0816] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[0817] As described above, the present invention is a system that helps users receive prompt and appropriate medical care in emergencies. The system allows users to register their basic information in advance, and in the event of an emergency, the system inputs their symptoms, which are analyzed by a generative AI model and suggest the optimal response method. Furthermore, it provides transportation as needed, enabling users to quickly access the appropriate medical institution.

[0818] The processing flow will be explained below.

[0819] Step 1:

[0820] The device displays an input screen to receive basic information from the user. The user enters their age, gender, chronic illnesses, and wearable device information, and then presses the send button. The device then encrypts this information and sends it to the server.

[0821] Step 2:

[0822] The server saves the user's basic information received from the device in a database, and once the saving is complete, the server returns a success message to the device.

[0823] Step 3:

[0824] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen for the user.

[0825] Step 4:

[0826] The device sends symptom data and basic information confirmed by the user to the server, which receives this data and inputs it into the AI ​​model for analysis.

[0827] Step 5:

[0828] The server uses an AI model to analyze the input symptom data and basic information, determine the appropriate response, and generate a judgment result that is sent to the device.

[0829] Step 6:

[0830] The device then notifies the user of the results of the assessment received from the server, including whether to call an ambulance or which medical facility to go to.

[0831] Step 7:

[0832] If a user needs to call an ambulance, they press a button on their device to dispatch an ambulance, which then contacts emergency services and dispatches an ambulance.

[0833] Step 8:

[0834] If the user selects self-transportation, the device prompts the user to select a mode of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and receives vehicle information and an estimated arrival time.

[0835] Step 9:

[0836] The device will then notify the user of the vehicle information and estimated arrival time received from the ride-hailing service, and the user will then be directed to the nearest medical facility.

[0837] The above are the processing steps of the program of the present invention. The specific operations performed at each step enable the user to receive prompt and appropriate medical treatment.

[0838] Example 1

[0839] 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."

[0840] Conventional emergency medical support systems have struggled to provide appropriate and prompt responses when a patient suddenly becomes unwell. Furthermore, they have had problems identifying the most appropriate medical institution or response method due to insufficient analysis of user input. Furthermore, they have also failed to provide comprehensive transportation options to reduce the stress and anxiety users experience during emergencies.

[0841] 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.

[0842] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, means for encrypting information when transmitting and receiving data, and means for converting symptoms input by voice by the user into text data and displaying a confirmation screen. This helps users receive prompt and accurate medical response in an emergency and enables more comprehensive emergency medical support by providing transportation as needed.

[0843] "Basic user information" refers to general personal medical and health information, such as the user's age, gender, medical history, and wearable device information.

[0844] The "symptom input means" is a means for the user to input symptoms by voice or text when the user feels suddenly unwell.

[0845] The "generative AI model" is an artificial intelligence model that analyzes the user's symptoms and basic information entered and determines the appropriate medical institution and response method.

[0846] The "judgment result notification means" is a means for notifying the user of the analysis results of the generative AI model.

[0847] "Transportation means provision means" refers to a means for providing users with transportation means necessary in an emergency (such as an ambulance or a ride-hailing service).

[0848] "Data encryption means" refers to encryption technology used to securely protect a user's personal information and symptom data when transmitting and receiving the information.

[0849] The "voice-to-text conversion means" is a means for converting the symptoms input by the user into text data and accurately confirming them.

[0850] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed. Specifically, it is realized by the user using a smartphone or tablet device. This system mainly includes the following means.

[0851] User information registration method

[0852] Using the application, users enter basic information such as age, gender, chronic illnesses, and wearable device information. The device then encrypts this information and sends it to the server, which then stores it in a database.

[0853] Example: A user starts an app, enters their age (30), gender (female), and chronic illness (diabetes), and presses the send button. The device sends this information to the server, which then stores it in a database.

[0854] Symptom input method

[0855] If a user feels unwell in an emergency, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen.

[0856] Example: A user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[0857] Analysis methods using generative AI models

[0858] The device sends the entered symptoms and registered basic information to the server. The server analyzes the data using a generative AI model and determines whether to call an ambulance or which medical institution the patient should go to. The server then sends the result of the decision to the device.

[0859] Example: The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that "an ambulance should be called."

[0860] Notification of the results of the assessment

[0861] The user is notified of the judgment result. The terminal receives the judgment result from the server and displays it to the user. This notification enables the user to quickly take the next action.

[0862] Example: If the server determines that an ambulance is needed, it notifies the user that "an ambulance should be called."

[0863] Means of transportation provision

[0864] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle information and estimated arrival time.

[0865] Example: If the server determines that the symptoms are mild, the device will suggest to the user, "Go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user, "A vehicle will arrive in 5 minutes."

[0866] Prompt Sentence Examples

[0867] Below is an example of a prompt sentence.

[0868] "I'm a 30-year-old woman with diabetes. What emergency measures should I take if I experience shortness of breath?"

[0869] To implement this invention, devices such as smartphones and tablets, a server to manage the database, a generative AI model to perform analysis, technology to convert voice into text data, encryption technology to ensure security, etc. are required. This will enable users to receive prompt and accurate medical treatment in an emergency and provide transportation as needed.

[0870] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0871] Step 1: Register your user information

[0872] Device:

[0873] The user launches the app on their smartphone or tablet and enters basic information (age, gender, chronic illnesses, wearable device information). This input data is encrypted on the device and sent to the server. For example, the user enters "30 years old," "female," and "diabetes."

[0874] server:

[0875] The server decrypts the received encrypted data and stores it in a database, including the user's age, gender, and medical conditions.

[0876] input:

[0877] User basic information (age, gender, chronic illness, wearable device information)

[0878] output:

[0879] User information stored in a database

[0880] Step 2: Enter your symptoms

[0881] user:

[0882] If you feel unwell in an emergency, open the app and enter your symptoms by voice or text. For example, you can enter "shortness of breath" by voice.

[0883] Device:

[0884] The device converts the input voice data into text data and displays it to the user on a confirmation screen. When the user presses the confirmation button, the text data is sent to the server.

[0885] input:

[0886] User voice or text input of symptoms

[0887] output:

[0888] Symptom text data sent to the server

[0889] Step 3: Symptom analysis and diagnosis

[0890] server:

[0891] The server receives symptom data sent from the device and basic user information stored in a database. It uses a generative AI model to analyze this data and determine whether an ambulance is needed or whether guidance to the nearest medical facility is appropriate. For example, it might analyze the combination of "shortness of breath" and "diabetes" to determine whether an ambulance is needed.

[0892] input:

[0893] Symptom text data, user information stored in the database

[0894] output:

[0895] Judgment result (e.g., ambulance required)

[0896] Step 4: Notification of the decision

[0897] server:

[0898] The server then sends the analysis results of the generated AI model to the device, which include information on whether an ambulance is needed and which medical facility the patient should go to.

[0899] Device:

[0900] The device then notifies the user of the results of the assessment. For example, it may say, "You should call an ambulance." If the condition is judged to be mild, it may suggest, "Go to the nearest medical institution."

[0901] input:

[0902] Analysis results of generative AI model

[0903] output:

[0904] User Notification

[0905] Step 5: Providing transportation

[0906] Device:

[0907] If the result of the assessment is that an ambulance is not necessary, the device presents an interface that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and notifies the user of the vehicle information and estimated arrival time.

[0908] input:

[0909] User Selection (Ride-Hailing Service)

[0910] output:

[0911] Vehicle information and estimated arrival time notifications

[0912] These are the specific processing steps of this system. At each step, the necessary data processing or calculation is performed based on the input data, and the results are output to the next step or to the user. As a concrete example, there is a series of steps in which a user registers basic information such as "age 30," "female," and "diabetes," and then vocally inputs the symptom "shortness of breath."

[0913] (Application example 1)

[0914] 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."

[0915] In conventional emergency medical support systems, it is difficult for users to quickly identify appropriate medical institutions and response methods in the event of an emergency, and transportation arrangements are often insufficient. This makes it difficult for users to receive prompt and appropriate medical treatment in the event of an emergency. The present invention aims to solve these problems and support users in receiving appropriate and prompt medical treatment in the event of an emergency.

[0916] 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.

[0917] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, and means for notifying the user of transportation arrangement information, thereby enabling the user to receive prompt and appropriate medical treatment in an emergency.

[0918] "Basic information" refers to personal information that is registered in advance in a database, such as the user's age, gender, medical history, and wearable device information.

[0919] "Symptom input" refers to the act of a user providing the application with the symptoms of illness they experience during an emergency through voice recognition or text input.

[0920] A "generative AI model" is an artificial intelligence algorithm used to analyze collected basic user information and symptom inputs and determine appropriate medical responses.

[0921] The "judgment result" is information that indicates the optimal course of action the user should take and the medical institution they should go to, based on data analyzed by the generative AI model.

[0922] "Transportation" refers to the means of transportation necessary for users to access appropriate medical facilities, such as ride-hailing services and ambulances.

[0923] "Transportation arrangement information" refers to details of the transportation method selected by the user, such as vehicle information and estimated arrival time in the case of a ride-hailing service, or arrival time in the case of an ambulance.

[0924] The system for realizing the present invention comprises a server, a terminal, and a user. A specific embodiment of the system is shown below.

[0925] System Configuration

[0926] 1. Server:

[0927] The server stores the user's basic information in a database and, in the event of an emergency, analyzes the symptoms and basic information entered using a generative AI model. It has the function of notifying the user of the diagnosis result and information on transportation arrangements. The software used includes a Django server and a PostgreSQL database.

[0928] 2. Terminal:

[0929] The device is a smartphone or tablet operated by the user. The device provides a UI for inputting and sending basic user information, and displays a symptom input screen in an emergency. It also includes a function to convert voice input into text data.

[0930] 3. User:

[0931] Users register basic information such as their age, gender, and chronic illnesses in advance through the device, and in the event of an emergency, they can receive emergency medical support by entering their symptoms into the device.

[0932] Program processing

[0933] The server runs a generative AI model using the collected basic information and symptom data to determine the appropriate medical institution and response method. The generative AI model uses advanced natural language processing algorithms such as GPT-4 and BERT. The server notifies the device of the result of the assessment in real time and, if necessary, arranges transportation using a ride-hailing service API (e.g., Uber API).

[0934] Specific examples

[0935] Register basic information:

[0936] The user launches the app and enters their age, gender, chronic illnesses, etc. For example, if a user registers "30 years old, female, diabetes," the device encrypts this information and sends it to the server, which then stores it in a database.

[0937] Enter your symptoms:

[0938] In an emergency, the user can say "I'm short of breath" by voice. The device converts the voice into text data and displays a confirmation screen.

[0939] Analysis and determination:

[0940] The server runs a generative AI model based on the symptom of "shortness of breath" and the chronic illness of "diabetes" to determine whether an ambulance should be called.

[0941] Transportation arrangements:

[0942] If the injury is determined to be minor, the server will connect with the ride-hailing service and notify the user that a vehicle will arrive in five minutes.

[0943] Prompt Sentence Examples

[0944] "I'm currently having trouble breathing. I have diabetes. Based on my location, please tell me the best medical facility and transportation options."

[0945] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0946] Step 1:

[0947] The user enters basic information (age, gender, chronic illnesses, etc.) on the device.

[0948] Specific behavior:

[0949] The device encrypts the basic information entered and sends it to the server, which stores the received data in a database.

[0950] Input: User's basic information (e.g., age, gender, chronic illness)

[0951] Output: Encrypted basic information data, saved in database

[0952] Step 2:

[0953] Users enter symptoms in case of an emergency.

[0954] Specific behavior:

[0955] The device displays a symptom input screen, and the user inputs symptoms by voice or text. In the case of voice input, the device converts the voice data into text data and displays a confirmation screen.

[0956] Input: Voice or text input of symptoms (e.g., "shortness of breath")

[0957] Output: Symptom information converted from voice to text data

[0958] Step 3:

[0959] The terminal sends the input symptoms and basic information to the server.

[0960] Specific behavior:

[0961] The device sends symptom information and basic information together to the server, which receives this data and begins analyzing it.

[0962] Input: Symptom information, basic information

[0963] Output: Data package for analysis

[0964] Step 4:

[0965] The server analyzes the data using a generative AI model and determines the appropriate medical institution and response method.

[0966] Specific behavior:

[0967] A generative AI model (e.g., GPT-4 or BERT) on the server analyzes the data using symptom information and basic information to determine whether to call an ambulance or go to a nearby medical facility.

[0968] Input: Symptom information, basic information

[0969] Output: Medical institution and response method decision result

[0970] Step 5:

[0971] The server transmits the determination result to the terminal.

[0972] Specific behavior:

[0973] The server sends the analysis results of the generated AI model to the user's device and notifies them of the appropriate response.

[0974] Input: Medical institution and response method judgment results

[0975] Output: Notification information (e.g. "You should call an ambulance")

[0976] Step 6:

[0977] The terminal provides transportation as needed.

[0978] Specific behavior:

[0979] If the user's symptoms are determined to be mild, the device will prompt the user to select a ride-hailing service. When the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[0980] Input: User's transportation method selection information

[0981] Output: Ride dispatch information (e.g., "The vehicle will arrive in 5 minutes")

[0982] Step 7:

[0983] The server notifies the user of transportation arrangement information.

[0984] Specific behavior:

[0985] The server transmits the vehicle information and estimated arrival time received from the dispatch service to the terminal and notifies the user.

[0986] Input: Vehicle dispatch information

[0987] Output: Notification information for the user (e.g. "The vehicle will arrive in 5 minutes")

[0988] 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.

[0989] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[0990] Specifically, this system will be implemented using smartphones and tablet devices. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions, and the system adjusts the judgment results accordingly. Transportation will also be provided if necessary.

[0991] Processing flow

[0992] 1. User information registration

[0993] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[0994] Examples:

[0995] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[0996] 2. Enter your symptoms

[0997] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[0998] Examples:

[0999] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[1000] 3. Analysis and Emotion Recognition

[1001] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[1002] Examples:

[1003] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[1004] 4. Notification of the decision

[1005] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[1006] Examples:

[1007] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[1008] 5. Providing transportation

[1009] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1010] Examples:

[1011] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[1012] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[1013] The processing flow will be explained below.

[1014] Step 1:

[1015] The device displays a registration screen for the user to enter basic information. The user enters their age, gender, chronic illnesses, and wearable device information, and clicks the "Submit" button. The device then encrypts this information and sends it to the server.

[1016] Step 2:

[1017] The server analyzes the user's basic information received from the device and saves it in a database. Once the saving is complete, the server returns a success message to the device. The device notifies the user that "registration is complete."

[1018] Step 3:

[1019] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen. The user confirms their symptoms and presses the "Send" button.

[1020] Step 4:

[1021] The device sends the symptom data submitted by the user and basic information registered in advance to the server. The server receives this data and inputs it into the emotion engine. The emotion engine recognizes emotions from the user's voice and text data and generates emotion data.

[1022] Step 5:

[1023] Once the emotion engine has generated the emotion data, the server inputs it into the generative AI model, which analyzes the user's symptoms, basic information, and emotion data to determine the appropriate medical response. Specifically, it determines whether to call an ambulance or go to the nearest medical facility.

[1024] Step 6:

[1025] The server obtains the judgment results of the generative AI model and sends them to the device. The device then notifies the user of the judgment results, for example, by displaying a message such as "You should call an ambulance" or "You should go to the nearest medical institution."

[1026] Step 7:

[1027] When a user wants to call an ambulance, the user clicks the "Call an ambulance" button on the device. The device contacts the emergency service and dispatches an ambulance. The server receives the ambulance dispatch information from the emergency service and notifies the device. The device notifies the user that "the ambulance is arriving."

[1028] Step 8:

[1029] If the user selects self-transportation, the device displays a screen that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service. The ride-hailing service replies with vehicle information and estimated arrival time to the server, which then sends it to the device. The device notifies the user, "A vehicle has been arranged. Estimated arrival time is 10 minutes later."

[1030] In this way, the present invention provides a series of processes for users to receive prompt and appropriate medical treatment. By combining a generative AI model with an emotion engine, the system provides appropriate medical treatment that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[1031] Example 2

[1032] 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."

[1033] In modern society, there is a demand for prompt and appropriate medical treatment for sudden illnesses, but it is difficult for users to quickly identify appropriate medical institutions and treatment methods. Furthermore, medical treatments that do not take into account the user's emotional state may not achieve optimal results. This creates a problem where users do not receive appropriate treatment in an emergency.

[1034] The identification process by the identification 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 inputting basic information of a user and saving it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for performing analysis in combination with an emotion engine that recognizes emotions from the user's voice and text data, means for notifying the user of the determination result, and means for providing transportation as necessary. This enables the user to receive prompt and accurate medical response in an emergency, and realizes an optimal response that takes the user's emotional state into consideration.

[1035] "Basic user information" refers to personal information such as the user's age, gender, chronic illnesses, and health-related data obtained from wearable devices.

[1036] "Means for storing in a database" refers to a storage system that safely stores input information and allows quick access when needed.

[1037] The "means for inputting symptoms" is an interface that allows the user to input the symptoms of the illness they are currently experiencing, and supports voice recognition or text input.

[1038] A "generative AI model" is a machine learning model used to analyze input data and determine appropriate medical responses and support methods.

[1039] An "emotion engine" is a software component that analyzes and recognizes a user's emotional state from their voice and text data.

[1040] The "means for notifying the user of the determination results" refers to the communication means and display means for notifying the user of the analysis results from the server on the user's terminal.

[1041] "Means for providing transportation" refers to a function that arranges transportation such as a ride-hailing service so that users can quickly travel to the nearest medical institution.

[1042] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[1043] The entire system is implemented using smartphones and tablets. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions and adjust the judgment results accordingly. Transportation can also be provided if necessary.

[1044] Registering user information

[1045] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[1046] Examples:

[1047] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[1048] Enter symptoms

[1049] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[1050] Examples:

[1051] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[1052] Analysis and Emotion Recognition

[1053] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[1054] Examples:

[1055] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[1056] Notification of the results

[1057] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[1058] Examples:

[1059] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[1060] Providing transportation

[1061] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1062] Examples:

[1063] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[1064] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[1065] Example prompt sentence:

[1066] Let's say a user types "shortness of breath" and the emotion engine detects a high level of stress from the user's tone of voice. The generative AI model analyzes this and determines that "an ambulance should be called." The corresponding prompt sentence is as follows:

[1067] "The user uses the app and inputs 'shortness of breath' through voice recognition. The emotion engine detects a high level of stress from the tone of the voice. Based on this information, please analyze the appropriate response."

[1068] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1069] Step 1:

[1070] Registering user information

[1071] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information. The entered information is processed as follows:

[1072] Input: Age, gender, chronic illness, wearable device information

[1073] Data processing: The device encrypts the information entered

[1074] Output: Encrypted user information data

[1075] Specifically, the user launches the app, enters the required information in each field, and presses the send button. The device then encrypts this information and sends it to the server.

[1076] Step 2:

[1077] Encrypted storage of user information

[1078] The server receives the encrypted user information data and stores it in a database.

[1079] Input: Encrypted user information data

[1080] Data processing: Convert to database format

[1081] Output: User information record stored in the database

[1082] Specifically, the server creates and saves a new user information record in the database based on the received data.

[1083] Step 3:

[1084] Enter symptoms

[1085] When a user feels unwell, the device launches the app and displays a symptom entry screen, where the user can enter their symptoms using voice recognition or text input.

[1086] Input: User's symptoms (voice or text)

[1087] Data processing: Converting voice data into text data (in the case of voice input)

[1088] Output: Symptom data in text format

[1089] Specifically, if a user voice-inputs "shortness of breath," the device will collect the voice using the microphone, convert it into text, and display it on a confirmation screen.

[1090] Step 4:

[1091] Submitting symptom data and basic information

[1092] The device sends the confirmed symptom data and basic information about the user to the server.

[1093] Input: Symptom data in text format, basic information

[1094] Data processing: Convert to transmission format

[1095] Output: Request data to the server

[1096] Specifically, the terminal generates and transmits a request to transmit symptom data and basic information to the server.

[1097] Step 5:

[1098] Emotion Recognition and Analysis

[1099] The server uses an emotion engine to recognize emotions from the user's voice and text data, and sends the analyzed data to the generative AI model.

[1100] Input: Symptom data, basic information, voice / text data

[1101] Data processing: sentiment analysis, generating input data for generative AI models

[1102] Output: Emotion data, analysis results of generative AI model

[1103] Specifically, the server analyzes voice and text data to determine the emotional state, then inputs the emotional and symptom data into a generative AI model to analyze the optimal response.

[1104] Step 6:

[1105] Notification of the results

[1106] The server sends the analysis results of the generative AI model to the device, which then notifies the user of the results.

[1107] Input: Analysis results of the generative AI model

[1108] Data processing: generating notification messages

[1109] Output: Notification data sent to the user's terminal

[1110] Specifically, the server sends the analysis results to the device, and the device displays a notification to the user, such as a message saying, "You should call an ambulance."

[1111] Step 7:

[1112] Providing transportation

[1113] The terminal displays a screen for selecting a means of transportation as necessary, depending on the determination result from the server. If the user selects a ride-hailing service, the terminal sends a request to the ride-hailing service and notifies the user of the arrangement results.

[1114] Input: Select ride service, request ride

[1115] Data processing: Generate a dispatch request and send it to the service API

[1116] Output: Arrangement result from the ride dispatch service

[1117] Specifically, when a user selects a ride-hailing service, the device uses the ride-hailing service's API to arrange a vehicle and notifies the user of that information, such as "The vehicle will arrive in 5 minutes."

[1118] (Application example 2)

[1119] 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."

[1120] In modern society, there is a demand for prompt and appropriate responses to sudden illnesses. However, it is difficult for users to properly recognize their own illness and receive prompt responses that take into account their emotional state. Providing transportation as needed is also a challenge. In such cases, conventional systems do not take the user's emotional state into account, which can result in delayed appropriate responses, so more advanced and rapid response measures are needed.

[1121] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1122] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for analyzing the user's emotions using emotion recognition technology and adjusting the determination result based on the analysis result, means for notifying the user of the determination result, and means for providing transportation as needed. This enables the user to receive appropriate and prompt medical treatment that takes into account their emotional state.

[1123] "Basic User Information" refers to basic profile data entered into an electronic device, such as a user's age, gender, medical conditions, and geographic location.

[1124] A "database" is a place or system where data in digital form is stored in an organized manner.

[1125] "Symptoms" are medical conditions that describe changes in physical condition or discomfort experienced by a User during an Emergency.

[1126] A "generative AI model" is an artificial intelligence model that analyzes input data and provides appropriate results and advice.

[1127] "Emotion recognition technology" is a technology that determines emotions from a user's voice or text input and grasps their state.

[1128] The "judgment result" is information about the appropriate medical institution and response method provided as a result of analysis using a generative AI model and emotion recognition technology.

[1129] "Notification" is the act of informing a user of information via an electronic device.

[1130] "Transportation" means a means of transporting a User to a designated location as needed.

[1131] A "vehicle dispatch service" is a service that arranges a vehicle in response to a user's request.

[1132] This invention is a system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and further provides a more appropriate response by combining it with emotion recognition technology that recognizes the user's emotions. Specific embodiments of this system are described below.

[1133] First, users enter basic information using a smartphone or tablet, including age, gender, chronic illnesses, and wearable device information (heart rate, blood pressure, etc.). This information is encrypted and sent to a server where it is stored in a database.

[1134] Next, if the user feels unwell in an emergency, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the entered voice data into text data and display a confirmation screen.

[1135] The device then sends the entered symptom data and the user's basic information to a server. The server uses emotion recognition technology to analyze the user's emotional state from their voice and text data, and uses a generative AI model to determine the appropriate medical institution and response method based on the analysis results. The server then sends the result of the determination to the device and notifies the user. For example, this may include whether to call an ambulance or which medical institution to go to.

[1136] If necessary, the device will provide transportation. If an ambulance is not required, the user can select a ride-hailing service, and the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1137] As a concrete example, consider the case where a user voice-inputs "I'm short of breath." In this case, emotion recognition technology recognizes a high level of stress from the user's tone of voice. The generative AI model analyzes the combination of symptoms and high stress levels and determines that "an ambulance should be called." This information is then sent to the device and displayed to the user.

[1138] Furthermore, if the symptoms are judged to be mild, the system will suggest to the user to "go to the nearest medical institution," and if the user selects a ride-hailing service, the system will notify the user that "a vehicle will arrive in 5 minutes."

[1139] An example of a prompt is:

[1140] One possible text could be, "The newly developed 'emergency medical response security app' is a system that allows users to quickly input their symptoms when they feel unwell, and uses emotion recognition technology and a generative AI model to provide the most appropriate medical response. For example, if a user suddenly feels shortness of breath, they can register their symptoms via voice input, and emotion recognition technology will analyze their stress level. We are working to implement a function where the AI ​​model will determine the appropriate response and, if necessary, arrange for a vehicle to be dispatched."

[1141] This allows users to receive appropriate and prompt medical treatment that takes their emotional state into account.

[1142] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1143] Step 1:

[1144] Registering basic user information

[1145] Using a smartphone or tablet, the user enters basic information such as age, gender, chronic illnesses, and wearable device information. This information is encrypted by the device and sent to a server. The server stores this data in a database. At this stage, the input is the user's basic information, and the output is the data stored in the database.

[1146] Step 2:

[1147] Enter symptoms

[1148] When a user feels unwell, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the entered voice data into text data using voice recognition technology and prompts the user to confirm the conversion result. The input here is the user's voice or text symptom information, and the output is the symptom information converted into text data.

[1149] Step 3:

[1150] Submitting symptoms and basic information

[1151] The terminal sends the converted symptom data and the user's basic information to the server, which stores the received symptom data and basic information for processing. At this stage, the input is the converted symptom data and basic information, and the output is the data sent to the server.

[1152] Step 4:

[1153] Emotion Recognition and Analysis

[1154] The server uses emotion recognition technology to determine the user's emotional state from their voice or text input. The emotion recognition engine generates the user's emotional data and inputs the generated emotional data and symptom data into a generative AI model. The generative AI model analyzes the symptom and emotional data and determines the optimal response method and medical institution. The inputs in this process are the emotional data and symptom data, and the output is the analysis results.

[1155] Step 5:

[1156] Notification of the results

[1157] The server sends the analysis results of the generative AI model to the device. The device notifies the user of the results and suggests appropriate medical institutions and measures to take. For example, this may include "You should call an ambulance" or "Go to the nearest medical institution." The input at this stage is the analysis results, and the output is a notification to the user.

[1158] Step 6:

[1159] Providing transportation

[1160] If necessary, the device will suggest transportation options to the user. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle and estimated arrival time. The input here is the user's ride-hailing request, and the output is the ride-hailing service arrangement information.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] [Fourth embodiment]

[1165] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1166] 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.

[1167] 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).

[1168] 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.

[1169] 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.

[1170] 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).

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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."

[1178] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed.

[1179] Specifically, this is achieved by the user using a smartphone or tablet. The system registers the user's basic information in a database in advance, and in the event of an emergency, the user enters their symptoms and runs an analysis using a generative AI model. The analysis results suggest the optimal response, whether to call an ambulance or go directly to the nearest medical institution. It also arranges transportation if necessary.

[1180] Processing flow

[1181] 1. User information registration

[1182] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[1183] Examples:

[1184] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[1185] 2. Enter your symptoms

[1186] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen.

[1187] Examples:

[1188] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[1189] 3. Analysis and Judgment

[1190] The device sends the entered symptoms and registered basic information to the server, which uses an AI model to analyze the data and determine whether an ambulance should be called and which medical institution the patient should go to. The server then sends the result of its decision to the device.

[1191] Examples:

[1192] The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that an ambulance should be called.

[1193] 4. Providing transportation

[1194] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1195] Examples:

[1196] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[1197] As described above, the present invention is a system that helps users receive prompt and appropriate medical care in emergencies. The system allows users to register their basic information in advance, and in the event of an emergency, the system inputs their symptoms, which are analyzed by a generative AI model and suggest the optimal response method. Furthermore, it provides transportation as needed, enabling users to quickly access the appropriate medical institution.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The device displays an input screen to receive basic information from the user. The user enters their age, gender, chronic illnesses, and wearable device information, and then presses the send button. The device then encrypts this information and sends it to the server.

[1201] Step 2:

[1202] The server saves the user's basic information received from the device in a database, and once the saving is complete, the server returns a success message to the device.

[1203] Step 3:

[1204] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text data and display a confirmation screen for the user.

[1205] Step 4:

[1206] The device sends symptom data and basic information confirmed by the user to the server, which receives this data and inputs it into the AI ​​model for analysis.

[1207] Step 5:

[1208] The server uses an AI model to analyze the input symptom data and basic information, determine the appropriate response, and generate a judgment result that is sent to the device.

[1209] Step 6:

[1210] The device then notifies the user of the results of the assessment received from the server, including whether to call an ambulance or which medical facility to go to.

[1211] Step 7:

[1212] If a user needs to call an ambulance, they press a button on their device to dispatch an ambulance, which then contacts emergency services and dispatches an ambulance.

[1213] Step 8:

[1214] If the user selects self-transportation, the device prompts the user to select a mode of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and receives vehicle information and an estimated arrival time.

[1215] Step 9:

[1216] The device will then notify the user of the vehicle information and estimated arrival time received from the ride-hailing service, and the user will then be directed to the nearest medical facility.

[1217] The above are the processing steps of the program of the present invention. The specific operations performed at each step enable the user to receive prompt and appropriate medical treatment.

[1218] Example 1

[1219] 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."

[1220] Conventional emergency medical support systems have struggled to provide appropriate and prompt responses when a patient suddenly becomes unwell. Furthermore, they have had problems identifying the most appropriate medical institution or response method due to insufficient analysis of user input. Furthermore, they have also failed to provide comprehensive transportation options to reduce the stress and anxiety users experience during emergencies.

[1221] 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.

[1222] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, means for encrypting information when transmitting and receiving data, and means for converting symptoms input by voice by the user into text data and displaying a confirmation screen. This helps users receive prompt and accurate medical response in an emergency and enables more comprehensive emergency medical support by providing transportation as needed.

[1223] "Basic user information" refers to general personal medical and health information, such as the user's age, gender, medical history, and wearable device information.

[1224] The "symptom input means" is a means for the user to input symptoms by voice or text when the user feels suddenly unwell.

[1225] The "generative AI model" is an artificial intelligence model that analyzes the user's symptoms and basic information entered and determines the appropriate medical institution and response method.

[1226] The "judgment result notification means" is a means for notifying the user of the analysis results of the generative AI model.

[1227] "Transportation means provision means" refers to a means for providing users with transportation means necessary in an emergency (such as an ambulance or a ride-hailing service).

[1228] "Data encryption means" refers to encryption technology used to securely protect a user's personal information and symptom data when transmitting and receiving the information.

[1229] The "voice-to-text conversion means" is a means for converting the symptoms input by the user into text data and accurately confirming them.

[1230] This invention is an emergency medical support system that quickly identifies appropriate medical institutions and response methods when a user suddenly feels unwell, and provides transportation as needed. Specifically, it is realized by the user using a smartphone or tablet device. This system mainly includes the following means.

[1231] User information registration method

[1232] Using the application, users enter basic information such as age, gender, chronic illnesses, and wearable device information. The device then encrypts this information and sends it to the server, which then stores it in a database.

[1233] Example: A user starts an app, enters their age (30), gender (female), and chronic illness (diabetes), and presses the send button. The device sends this information to the server, which then stores it in a database.

[1234] Symptom input method

[1235] If a user feels unwell in an emergency, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen.

[1236] Example: A user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[1237] Analysis methods using generative AI models

[1238] The device sends the entered symptoms and registered basic information to the server. The server analyzes the data using a generative AI model and determines whether to call an ambulance or which medical institution the patient should go to. The server then sends the result of the decision to the device.

[1239] Example: The server analyzes the combination of "shortness of breath" and "diabetes" and determines that an ambulance is needed. The server sends the result of the analysis to the device, which then notifies the user that "an ambulance should be called."

[1240] Notification of the results of the assessment

[1241] The user is notified of the judgment result. The terminal receives the judgment result from the server and displays it to the user. This notification enables the user to quickly take the next action.

[1242] Example: If the server determines that an ambulance is needed, it notifies the user that "an ambulance should be called."

[1243] Means of transportation provision

[1244] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle information and estimated arrival time.

[1245] Example: If the server determines that the symptoms are mild, the device will suggest to the user, "Go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user, "A vehicle will arrive in 5 minutes."

[1246] Prompt Sentence Examples

[1247] Below is an example of a prompt sentence.

[1248] "I'm a 30-year-old woman with diabetes. What emergency measures should I take if I experience shortness of breath?"

[1249] To implement this invention, devices such as smartphones and tablets, a server to manage the database, a generative AI model to perform analysis, technology to convert voice into text data, encryption technology to ensure security, etc. are required. This will enable users to receive prompt and accurate medical treatment in an emergency and provide transportation as needed.

[1250] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1251] Step 1: Register your user information

[1252] Device:

[1253] The user launches the app on their smartphone or tablet and enters basic information (age, gender, chronic illnesses, wearable device information). This input data is encrypted on the device and sent to the server. For example, the user enters "30 years old," "female," and "diabetes."

[1254] server:

[1255] The server decrypts the received encrypted data and stores it in a database, including the user's age, gender, and medical conditions.

[1256] input:

[1257] User basic information (age, gender, chronic illness, wearable device information)

[1258] output:

[1259] User information stored in a database

[1260] Step 2: Enter your symptoms

[1261] user:

[1262] If you feel unwell in an emergency, open the app and enter your symptoms by voice or text. For example, you can enter "shortness of breath" by voice.

[1263] Device:

[1264] The device converts the input voice data into text data and displays it to the user on a confirmation screen. When the user presses the confirmation button, the text data is sent to the server.

[1265] input:

[1266] User voice or text input of symptoms

[1267] output:

[1268] Symptom text data sent to the server

[1269] Step 3: Symptom analysis and diagnosis

[1270] server:

[1271] The server receives symptom data sent from the device and basic user information stored in a database. It uses a generative AI model to analyze this data and determine whether an ambulance is needed or whether guidance to the nearest medical facility is appropriate. For example, it might analyze the combination of "shortness of breath" and "diabetes" to determine whether an ambulance is needed.

[1272] input:

[1273] Symptom text data, user information stored in the database

[1274] output:

[1275] Judgment result (e.g., ambulance required)

[1276] Step 4: Notification of the decision

[1277] server:

[1278] The server then sends the analysis results of the generated AI model to the device, which include information on whether an ambulance is needed and which medical facility the patient should go to.

[1279] Device:

[1280] The device then notifies the user of the results of the assessment. For example, it may say, "You should call an ambulance." If the condition is judged to be mild, it may suggest, "Go to the nearest medical institution."

[1281] input:

[1282] Analysis results of generative AI model

[1283] output:

[1284] User Notification

[1285] Step 5: Providing transportation

[1286] Device:

[1287] If the result of the assessment is that an ambulance is not necessary, the device presents an interface that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service and notifies the user of the vehicle information and estimated arrival time.

[1288] input:

[1289] User Selection (Ride-Hailing Service)

[1290] output:

[1291] Vehicle information and estimated arrival time notifications

[1292] These are the specific processing steps of this system. At each step, the necessary data processing or calculation is performed based on the input data, and the results are output to the next step or to the user. As a concrete example, there is a series of steps in which a user registers basic information such as "age 30," "female," and "diabetes," and then vocally inputs the symptom "shortness of breath."

[1293] (Application example 1)

[1294] 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."

[1295] In conventional emergency medical support systems, it is difficult for users to quickly identify appropriate medical institutions and response methods in the event of an emergency, and transportation arrangements are often insufficient. This makes it difficult for users to receive prompt and appropriate medical treatment in the event of an emergency. The present invention aims to solve these problems and support users in receiving appropriate and prompt medical treatment in the event of an emergency.

[1296] 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.

[1297] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for notifying the user of the determination result, means for providing transportation as needed, and means for notifying the user of transportation arrangement information, thereby enabling the user to receive prompt and appropriate medical treatment in an emergency.

[1298] "Basic information" refers to personal information that is registered in advance in a database, such as the user's age, gender, medical history, and wearable device information.

[1299] "Symptom input" refers to the act of a user providing the application with the symptoms of illness they experience during an emergency through voice recognition or text input.

[1300] A "generative AI model" is an artificial intelligence algorithm used to analyze collected basic user information and symptom inputs and determine appropriate medical responses.

[1301] The "judgment result" is information that indicates the optimal course of action the user should take and the medical institution they should go to, based on data analyzed by the generative AI model.

[1302] "Transportation" refers to the means of transportation necessary for users to access appropriate medical facilities, such as ride-hailing services and ambulances.

[1303] "Transportation arrangement information" refers to details of the transportation method selected by the user, such as vehicle information and estimated arrival time in the case of a ride-hailing service, or arrival time in the case of an ambulance.

[1304] The system for realizing the present invention comprises a server, a terminal, and a user. A specific embodiment of the system is shown below.

[1305] System Configuration

[1306] 1. Server:

[1307] The server stores the user's basic information in a database and, in the event of an emergency, analyzes the symptoms and basic information entered using a generative AI model. It has the function of notifying the user of the diagnosis result and information on transportation arrangements. The software used includes a Django server and a PostgreSQL database.

[1308] 2. Terminal:

[1309] The device is a smartphone or tablet operated by the user. The device provides a UI for inputting and sending basic user information, and displays a symptom input screen in an emergency. It also includes a function to convert voice input into text data.

[1310] 3. User:

[1311] Users register basic information such as their age, gender, and chronic illnesses in advance through the device, and in the event of an emergency, they can receive emergency medical support by entering their symptoms into the device.

[1312] Program processing

[1313] The server runs a generative AI model using the collected basic information and symptom data to determine the appropriate medical institution and response method. The generative AI model uses advanced natural language processing algorithms such as GPT-4 and BERT. The server notifies the device of the result of the assessment in real time and, if necessary, arranges transportation using a ride-hailing service API (e.g., Uber API).

[1314] Specific examples

[1315] Register basic information:

[1316] The user launches the app and enters their age, gender, chronic illnesses, etc. For example, if a user registers "30 years old, female, diabetes," the device encrypts this information and sends it to the server, which then stores it in a database.

[1317] Enter your symptoms:

[1318] In an emergency, the user can say "I'm short of breath" by voice. The device converts the voice into text data and displays a confirmation screen.

[1319] Analysis and determination:

[1320] The server runs a generative AI model based on the symptom of "shortness of breath" and the chronic illness of "diabetes" to determine whether an ambulance should be called.

[1321] Transportation arrangements:

[1322] If the injury is determined to be minor, the server will connect with the ride-hailing service and notify the user that a vehicle will arrive in five minutes.

[1323] Prompt Sentence Examples

[1324] "I'm currently having trouble breathing. I have diabetes. Based on my location, please tell me the best medical facility and transportation options."

[1325] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1326] Step 1:

[1327] The user enters basic information (age, gender, chronic illnesses, etc.) on the device.

[1328] Specific behavior:

[1329] The device encrypts the basic information entered and sends it to the server, which stores the received data in a database.

[1330] Input: User's basic information (e.g., age, gender, chronic illness)

[1331] Output: Encrypted basic information data, saved in database

[1332] Step 2:

[1333] Users enter symptoms in case of an emergency.

[1334] Specific behavior:

[1335] The device displays a symptom input screen, and the user inputs symptoms by voice or text. In the case of voice input, the device converts the voice data into text data and displays a confirmation screen.

[1336] Input: Voice or text input of symptoms (e.g., "shortness of breath")

[1337] Output: Symptom information converted from voice to text data

[1338] Step 3:

[1339] The terminal sends the input symptoms and basic information to the server.

[1340] Specific behavior:

[1341] The device sends symptom information and basic information together to the server, which receives this data and begins analyzing it.

[1342] Input: Symptom information, basic information

[1343] Output: Data package for analysis

[1344] Step 4:

[1345] The server analyzes the data using a generative AI model and determines the appropriate medical institution and response method.

[1346] Specific behavior:

[1347] A generative AI model (e.g., GPT-4 or BERT) on the server analyzes the data using symptom information and basic information to determine whether to call an ambulance or go to a nearby medical facility.

[1348] Input: Symptom information, basic information

[1349] Output: Medical institution and response method decision result

[1350] Step 5:

[1351] The server transmits the determination result to the terminal.

[1352] Specific behavior:

[1353] The server sends the analysis results of the generated AI model to the user's device and notifies them of the appropriate response.

[1354] Input: Medical institution and response method judgment results

[1355] Output: Notification information (e.g. "You should call an ambulance")

[1356] Step 6:

[1357] The terminal provides transportation as needed.

[1358] Specific behavior:

[1359] If the user's symptoms are determined to be mild, the device will prompt the user to select a ride-hailing service. When the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1360] Input: User's transportation method selection information

[1361] Output: Ride dispatch information (e.g., "The vehicle will arrive in 5 minutes")

[1362] Step 7:

[1363] The server notifies the user of transportation arrangement information.

[1364] Specific behavior:

[1365] The server transmits the vehicle information and estimated arrival time received from the dispatch service to the terminal and notifies the user.

[1366] Input: Vehicle dispatch information

[1367] Output: Notification information for the user (e.g. "The vehicle will arrive in 5 minutes")

[1368] 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.

[1369] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[1370] Specifically, this system will be implemented using smartphones and tablet devices. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions, and the system adjusts the judgment results accordingly. Transportation will also be provided if necessary.

[1371] Processing flow

[1372] 1. User information registration

[1373] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[1374] Examples:

[1375] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[1376] 2. Enter your symptoms

[1377] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[1378] Examples:

[1379] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[1380] 3. Analysis and Emotion Recognition

[1381] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[1382] Examples:

[1383] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[1384] 4. Notification of the decision

[1385] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[1386] Examples:

[1387] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[1388] 5. Providing transportation

[1389] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1390] Examples:

[1391] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[1392] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[1393] The processing flow will be explained below.

[1394] Step 1:

[1395] The device displays a registration screen for the user to enter basic information. The user enters their age, gender, chronic illnesses, and wearable device information, and clicks the "Submit" button. The device then encrypts this information and sends it to the server.

[1396] Step 2:

[1397] The server analyzes the user's basic information received from the device and saves it in a database. Once the saving is complete, the server returns a success message to the device. The device notifies the user that "registration is complete."

[1398] Step 3:

[1399] In an emergency, if a user feels unwell, the device will display a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the voice data into text data and displays a confirmation screen. The user confirms their symptoms and presses the "Send" button.

[1400] Step 4:

[1401] The device sends the symptom data submitted by the user and basic information registered in advance to the server. The server receives this data and inputs it into the emotion engine. The emotion engine recognizes emotions from the user's voice and text data and generates emotion data.

[1402] Step 5:

[1403] Once the emotion engine has generated the emotion data, the server inputs it into the generative AI model, which analyzes the user's symptoms, basic information, and emotion data to determine the appropriate medical response. Specifically, it determines whether to call an ambulance or go to the nearest medical facility.

[1404] Step 6:

[1405] The server obtains the judgment results of the generative AI model and sends them to the device. The device then notifies the user of the judgment results, for example, by displaying a message such as "You should call an ambulance" or "You should go to the nearest medical institution."

[1406] Step 7:

[1407] When a user wants to call an ambulance, the user clicks the "Call an ambulance" button on the device. The device contacts the emergency service and dispatches an ambulance. The server receives the ambulance dispatch information from the emergency service and notifies the device. The device notifies the user that "the ambulance is arriving."

[1408] Step 8:

[1409] If the user selects self-transportation, the device displays a screen that allows the user to select a means of transportation. If the user selects a ride-hailing service, the device sends a request to the ride-hailing service. The ride-hailing service replies with vehicle information and estimated arrival time to the server, which then sends it to the device. The device notifies the user, "A vehicle has been arranged. Estimated arrival time is 10 minutes later."

[1410] In this way, the present invention provides a series of processes for users to receive prompt and appropriate medical treatment. By combining a generative AI model with an emotion engine, the system provides appropriate medical treatment that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[1411] Example 2

[1412] 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."

[1413] In modern society, there is a demand for prompt and appropriate medical treatment for sudden illnesses, but it is difficult for users to quickly identify appropriate medical institutions and treatment methods. Furthermore, medical treatments that do not take into account the user's emotional state may not achieve optimal results. This creates a problem where users do not receive appropriate treatment in an emergency.

[1414] The identification process by the identification 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 inputting basic information of a user and saving it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for performing analysis in combination with an emotion engine that recognizes emotions from the user's voice and text data, means for notifying the user of the determination result, and means for providing transportation as necessary. This enables the user to receive prompt and accurate medical response in an emergency, and realizes an optimal response that takes the user's emotional state into consideration.

[1415] "Basic user information" refers to personal information such as the user's age, gender, chronic illnesses, and health-related data obtained from wearable devices.

[1416] "Means for storing in a database" refers to a storage system that safely stores input information and allows quick access when needed.

[1417] The "means for inputting symptoms" is an interface that allows the user to input the symptoms of the illness they are currently experiencing, and supports voice recognition or text input.

[1418] A "generative AI model" is a machine learning model used to analyze input data and determine appropriate medical responses and support methods.

[1419] An "emotion engine" is a software component that analyzes and recognizes a user's emotional state from their voice and text data.

[1420] The "means for notifying the user of the determination results" refers to the communication means and display means for notifying the user of the analysis results from the server on the user's terminal.

[1421] "Means for providing transportation" refers to a function that arranges transportation such as a ride-hailing service so that users can quickly travel to the nearest medical institution.

[1422] This invention is an emergency medical support system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and provides a more appropriate response by combining it with an emotion engine that recognizes the user's emotions.

[1423] The entire system is implemented using smartphones and tablets. First, the user's basic information is registered in a database in advance, and in the event of an emergency, symptoms are entered and analyzed using a generative AI model. Furthermore, an emotion engine is used to recognize the user's emotions and adjust the judgment results accordingly. Transportation can also be provided if necessary.

[1424] Registering user information

[1425] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information, and then sends this data to a server, which stores the received data in a database.

[1426] Examples:

[1427] The user launches the app, enters the required information in each field, and presses the submit button. The device encrypts this information and sends it to the server. The server stores the data in a database. For example, the user enters age "30," gender "female," and chronic illness "diabetes."

[1428] Enter symptoms

[1429] In an emergency, if a user feels unwell, the device will launch the app and display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the voice data into text and display a confirmation screen.

[1430] Examples:

[1431] The user speaks "I'm short of breath." The device converts the speech to text and displays "I'm short of breath" to the user for confirmation.

[1432] Analysis and Emotion Recognition

[1433] The device sends the input symptom data and basic information to a server. The server uses an emotion engine to recognize emotions from the user's voice and text data and sends the emotion data to a generative AI model. The generative AI model analyzes the symptom and emotion data and determines the appropriate response.

[1434] Examples:

[1435] The user types "shortness of breath," and the emotion engine recognizes stress and anxiety from the user's tone of voice and text input. The emotion engine determines that the user is in a high stress state and provides this information to the AI ​​model. The AI ​​model analyzes the combination of "shortness of breath" and "high stress" and determines that an ambulance should be called.

[1436] Notification of the results

[1437] The server then sends the resulting analysis to the device, which then notifies the user of the results, including whether to call an ambulance or which medical facility to go to.

[1438] Examples:

[1439] The server determines from the analysis results that "an ambulance should be called" and sends this information to the device, which then notifies the user by displaying "an ambulance should be called."

[1440] Providing transportation

[1441] If an ambulance is not needed, the device will prompt the user to select a transportation method. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1442] Examples:

[1443] If the server determines that the symptoms are mild, the device will suggest to the user to "go to the nearest medical institution." If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user that "a vehicle will arrive in 5 minutes."

[1444] As such, this invention is a system that helps users receive prompt and appropriate medical care in emergencies. By combining a generative AI model with an emotion engine, it provides more appropriate medical care that takes into account the user's emotional state. It also provides transportation if necessary, creating an environment where users can quickly access the appropriate medical institution.

[1445] Example prompt sentence:

[1446] Let's say a user types "shortness of breath" and the emotion engine detects a high level of stress from the user's tone of voice. The generative AI model analyzes this and determines that "an ambulance should be called." The corresponding prompt sentence is as follows:

[1447] "The user uses the app and inputs 'shortness of breath' through voice recognition. The emotion engine detects a high level of stress from the tone of the voice. Based on this information, please analyze the appropriate response."

[1448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1449] Step 1:

[1450] Registering user information

[1451] The device prompts the user to enter information such as age, gender, chronic illnesses, and wearable device information. The entered information is processed as follows:

[1452] Input: Age, gender, chronic illness, wearable device information

[1453] Data processing: The device encrypts the information entered

[1454] Output: Encrypted user information data

[1455] Specifically, the user launches the app, enters the required information in each field, and presses the send button. The device then encrypts this information and sends it to the server.

[1456] Step 2:

[1457] Encrypted storage of user information

[1458] The server receives the encrypted user information data and stores it in a database.

[1459] Input: Encrypted user information data

[1460] Data processing: Convert to database format

[1461] Output: User information record stored in the database

[1462] Specifically, the server creates and saves a new user information record in the database based on the received data.

[1463] Step 3:

[1464] Enter symptoms

[1465] When a user feels unwell, the device launches the app and displays a symptom entry screen, where the user can enter their symptoms using voice recognition or text input.

[1466] Input: User's symptoms (voice or text)

[1467] Data processing: Converting voice data into text data (in the case of voice input)

[1468] Output: Symptom data in text format

[1469] Specifically, if a user voice-inputs "shortness of breath," the device will collect the voice using the microphone, convert it into text, and display it on a confirmation screen.

[1470] Step 4:

[1471] Submitting symptom data and basic information

[1472] The device sends the confirmed symptom data and basic information about the user to the server.

[1473] Input: Symptom data in text format, basic information

[1474] Data processing: Convert to transmission format

[1475] Output: Request data to the server

[1476] Specifically, the terminal generates and transmits a request to transmit symptom data and basic information to the server.

[1477] Step 5:

[1478] Emotion Recognition and Analysis

[1479] The server uses an emotion engine to recognize emotions from the user's voice and text data, and sends the analyzed data to the generative AI model.

[1480] Input: Symptom data, basic information, voice / text data

[1481] Data processing: sentiment analysis, generating input data for generative AI models

[1482] Output: Emotion data, analysis results of generative AI model

[1483] Specifically, the server analyzes voice and text data to determine the emotional state, then inputs the emotional and symptom data into a generative AI model to analyze the optimal response.

[1484] Step 6:

[1485] Notification of the results

[1486] The server sends the analysis results of the generative AI model to the device, which then notifies the user of the results.

[1487] Input: Analysis results of the generative AI model

[1488] Data processing: generating notification messages

[1489] Output: Notification data sent to the user's terminal

[1490] Specifically, the server sends the analysis results to the device, and the device displays a notification to the user, such as a message saying, "You should call an ambulance."

[1491] Step 7:

[1492] Providing transportation

[1493] The terminal displays a screen for selecting a means of transportation as necessary, depending on the determination result from the server. If the user selects a ride-hailing service, the terminal sends a request to the ride-hailing service and notifies the user of the arrangement results.

[1494] Input: Select ride service, request ride

[1495] Data processing: Generate a dispatch request and send it to the service API

[1496] Output: Arrangement result from the ride dispatch service

[1497] Specifically, when a user selects a ride-hailing service, the device uses the ride-hailing service's API to arrange a vehicle and notifies the user of that information, such as "The vehicle will arrive in 5 minutes."

[1498] (Application example 2)

[1499] 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."

[1500] In modern society, there is a demand for prompt and appropriate responses to sudden illnesses. However, it is difficult for users to properly recognize their own illness and receive prompt responses that take into account their emotional state. Providing transportation as needed is also a challenge. In such cases, conventional systems do not take the user's emotional state into account, which can result in delayed appropriate responses, so more advanced and rapid response measures are needed.

[1501] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1502] In this invention, the server includes means for inputting basic user information and storing it in a database, means for the user to input symptoms in an emergency, means for analyzing the input symptoms and basic information using a generative AI model and determining an appropriate medical institution and response method, means for analyzing the user's emotions using emotion recognition technology and adjusting the determination result based on the analysis result, means for notifying the user of the determination result, and means for providing transportation as needed. This enables the user to receive appropriate and prompt medical treatment that takes into account their emotional state.

[1503] "Basic User Information" refers to basic profile data entered into an electronic device, such as a user's age, gender, medical conditions, and geographic location.

[1504] A "database" is a place or system where data in digital form is stored in an organized manner.

[1505] "Symptoms" are medical conditions that describe changes in physical condition or discomfort experienced by a User during an Emergency.

[1506] A "generative AI model" is an artificial intelligence model that analyzes input data and provides appropriate results and advice.

[1507] "Emotion recognition technology" is a technology that determines emotions from a user's voice or text input and grasps their state.

[1508] The "judgment result" is information about the appropriate medical institution and response method provided as a result of analysis using a generative AI model and emotion recognition technology.

[1509] "Notification" is the act of informing a user of information via an electronic device.

[1510] "Transportation" means a means of transporting a User to a designated location as needed.

[1511] A "vehicle dispatch service" is a service that arranges a vehicle in response to a user's request.

[1512] This invention is a system that, when a user suddenly feels unwell, quickly identifies the appropriate medical institution and response method based on the user's symptoms and basic information, and further provides a more appropriate response by combining it with emotion recognition technology that recognizes the user's emotions. Specific embodiments of this system are described below.

[1513] First, users enter basic information using a smartphone or tablet, including age, gender, chronic illnesses, and wearable device information (heart rate, blood pressure, etc.). This information is encrypted and sent to a server where it is stored in a database.

[1514] Next, if the user feels unwell in an emergency, the device will display a symptom entry screen. The user can enter their symptoms using voice recognition or text input. The device will convert the entered voice data into text data and display a confirmation screen.

[1515] The device then sends the entered symptom data and the user's basic information to a server. The server uses emotion recognition technology to analyze the user's emotional state from their voice and text data, and uses a generative AI model to determine the appropriate medical institution and response method based on the analysis results. The server then sends the result of the determination to the device and notifies the user. For example, this may include whether to call an ambulance or which medical institution to go to.

[1516] If necessary, the device will provide transportation. If an ambulance is not required, the user can select a ride-hailing service, and the device will send a request to the ride-hailing service and notify the user of the vehicle information and estimated arrival time.

[1517] As a concrete example, consider the case where a user voice-inputs "I'm short of breath." In this case, emotion recognition technology recognizes a high level of stress from the user's tone of voice. The generative AI model analyzes the combination of symptoms and high stress levels and determines that "an ambulance should be called." This information is then sent to the device and displayed to the user.

[1518] Furthermore, if the symptoms are judged to be mild, the system will suggest to the user to "go to the nearest medical institution," and if the user selects a ride-hailing service, the system will notify the user that "a vehicle will arrive in 5 minutes."

[1519] An example of a prompt is:

[1520] One possible text could be, "The newly developed 'emergency medical response security app' is a system that allows users to quickly input their symptoms when they feel unwell, and uses emotion recognition technology and a generative AI model to provide the most appropriate medical response. For example, if a user suddenly feels shortness of breath, they can register their symptoms via voice input, and emotion recognition technology will analyze their stress level. We are working to implement a function where the AI ​​model will determine the appropriate response and, if necessary, arrange for a vehicle to be dispatched."

[1521] This allows users to receive appropriate and prompt medical treatment that takes their emotional state into account.

[1522] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1523] Step 1:

[1524] Registering basic user information

[1525] Using a smartphone or tablet, the user enters basic information such as age, gender, chronic illnesses, and wearable device information. This information is encrypted by the device and sent to a server. The server stores this data in a database. At this stage, the input is the user's basic information, and the output is the data stored in the database.

[1526] Step 2:

[1527] Enter symptoms

[1528] When a user feels unwell, the device displays a symptom entry screen. The user enters their symptoms using voice recognition or text input. The device converts the entered voice data into text data using voice recognition technology and prompts the user to confirm the conversion result. The input here is the user's voice or text symptom information, and the output is the symptom information converted into text data.

[1529] Step 3:

[1530] Submitting symptoms and basic information

[1531] The terminal sends the converted symptom data and the user's basic information to the server, which stores the received symptom data and basic information for processing. At this stage, the input is the converted symptom data and basic information, and the output is the data sent to the server.

[1532] Step 4:

[1533] Emotion Recognition and Analysis

[1534] The server uses emotion recognition technology to determine the user's emotional state from their voice or text input. The emotion recognition engine generates the user's emotional data and inputs the generated emotional data and symptom data into a generative AI model. The generative AI model analyzes the symptom and emotional data and determines the optimal response method and medical institution. The inputs in this process are the emotional data and symptom data, and the output is the analysis results.

[1535] Step 5:

[1536] Notification of the results

[1537] The server sends the analysis results of the generative AI model to the device. The device notifies the user of the results and suggests appropriate medical institutions and measures to take. For example, this may include "You should call an ambulance" or "Go to the nearest medical institution." The input at this stage is the analysis results, and the output is a notification to the user.

[1538] Step 6:

[1539] Providing transportation

[1540] If necessary, the device will suggest transportation options to the user. If the user selects a ride-hailing service, the device will send a request to the ride-hailing service and notify the user of the arranged vehicle and estimated arrival time. The input here is the user's ride-hailing request, and the output is the ride-hailing service arrangement information.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1546] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1547] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1548] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1549] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1550] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1551] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1552] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1553] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1554] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1555] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1556] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1557] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1558] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1559] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1560] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1561] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1562] The following is further disclosed regarding the above embodiment.

[1563] (Claim 1)

[1564] A means to input basic user information and store it in a database;

[1565] a means for users to input symptoms in an emergency;

[1566] A means to analyze the input symptoms and basic information using a generative AI model and determine the appropriate medical institution and response method.

[1567] A means for notifying the user of the determination result;

[1568] a means of providing transportation when necessary;

[1569] A system including:

[1570] (Claim 2)

[1571] 10. The system of claim 1, further comprising means for converting a user's voice input into text data.

[1572] (Claim 3)

[1573] The system according to claim 1, further comprising means for coordinating with a ride-hailing service to arrange transportation for the user.

[1574] (Claim 4)

[1575] 10. The system of claim 1, further comprising means for automatically calling an ambulance based on the determination result.

[1576] (Claim 5)

[1577] 10. The system of claim 1, further comprising means for utilizing the location information to identify the medical institution closest to the user's current location.

[1578] "Example 1"

[1579] (Claim 1)

[1580] A means to input basic user information and store it in a database;

[1581] a means for users to input symptoms in an emergency;

[1582] A means to analyze the input symptoms and basic information using a generative AI model and determine the appropriate medical institution and response method.

[1583] A means for notifying the user of the determination result;

[1584] a means of providing transportation when necessary;

[1585] means for encrypting information when transmitting and receiving data;

[1586] A means for converting symptoms input by voice by the user into text data and displaying a confirmation screen;

[1587] A system including:

[1588] (Claim 2)

[1589] 10. The system of claim 1, further comprising means for converting a user's voice input into text data.

[1590] (Claim 3)

[1591] The system according to claim 1, further comprising means for coordinating with a ride-hailing service to arrange transportation for the user.

[1592] "Application Example 1"

[1593] (Claim 1)

[1594] A means to input basic user information and store it in a database;

[1595] a means for users to input symptoms in an emergency;

[1596] A means to analyze the input symptoms and basic information using a generative AI model and determine the appropriate medical institution and response method.

[1597] A means for notifying the user of the determination result;

[1598] a means of providing transportation when necessary;

[1599] a means for notifying the user of transportation arrangement information;

[1600] A system including:

[1601] (Claim 2)

[1602] 10. The system of claim 1, further comprising means for converting a user's voice input into text data.

[1603] (Claim 3)

[1604] The system according to claim 1, further comprising means for coordinating with a ride-hailing service to arrange transportation for the user.

[1605] "Example 2: Combining Emotion Engines"

[1606] (Claim 1)

[1607] A means to input basic user information and store it in a database;

[1608] a means for users to input symptoms in an emergency;

[1609] A means to analyze the input symptoms and basic information using a generative AI model and determine the appropriate medical institution and response method.

[1610] A method for analyzing by combining an emotion engine that recognizes emotions from user voice and text data, and

[1611] A means for notifying the user of the determination result;

[1612] a means of providing transportation when necessary;

[1613] A system including:

[1614] (Claim 2)

[1615] 10. The system of claim 1, further comprising means for converting a user's voice input into text data.

[1616] (Claim 3)

[1617] The system according to claim 1, further comprising means for coordinating with a ride-hailing service to arrange transportation for the user.

[1618] "Application example 2 when combining emotion engines"

[1619] (Claim 1)

[1620] A means to input basic user information and store it in a database;

[1621] a means for users to input symptoms in an emergency;

[1622] A means to analyze the input symptoms and basic information using a generative AI model and determine the appropriate medical institution and response method.

[1623] A means for analyzing the user's emotions using emotion recognition technology and adjusting the determination result based on the analysis result;

[1624] A means for notifying the user of the determination result;

[1625] a means of providing transportation when necessary;

[1626] A system including:

[1627] (Claim 2)

[1628] 10. The system of claim 1, further comprising means for converting a user's voice input into text data.

[1629] (Claim 3)

[1630] The system according to claim 1, further comprising means for coordinating with a ride-hailing service to arrange transportation for the user. [Explanation of symbols]

[1631] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to input basic user information and store it in a database; a means for users to input symptoms in an emergency; A means to analyze the input symptoms and basic information using a generative AI model and determine the appropriate medical institution and response method. A means for notifying the user of the determination result; a means of providing transportation when necessary; A system including:

2. 10. The system of claim 1, further comprising means for converting a user's voice input into text data.

3. The system according to claim 1 , further comprising means for coordinating with a ride-hailing service to arrange transportation for the user.

4. The system of claim 1 further comprising means for automatically calling an ambulance based on the determination result.

5. The system of claim 1 , further comprising means for utilizing the location information to identify the medical institution closest to the user's current location.

Images