System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving medical history information, diagnosis results, and submission destination information input by a user; means for storing the received information in a database; means for searching the database for a medical history and a diagnosis history based on an ID of the user; means for generating an optimal audit trail according to a submission destination using generation artificial intelligence based on a search result; means for creating a file in which the generated audit trail and an easy-to-understand comment of a medical condition are integrated; means for storing the integrated file in a cloud and notifying a relevant submission destination; and means for notifying the user of completion of submission.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] Under the current system, different medical certificates are required for each medical history and diagnosis, and creating and submitting them takes a great deal of time and effort. Furthermore, the information required varies depending on the recipient, and the documents contain difficult-to-understand technical terms, which can lead to a lack of understanding on the recipient's side. It is necessary to resolve these issues and standardize and streamline medical certificates and related documents. [Means for solving the problem]

[0005] The present invention solves the above problems by introducing the following means: A system receives medical history information, diagnosis results, and submission destination information from a user and stores this information in a database. Based on the medical history and diagnosis history obtained from the database, artificial intelligence is used to generate an optimal trail tailored to the submission destination. The generated trail is created as an integrated file along with easy-to-understand medical condition comments. This integrated file is stored in the cloud and notified to the relevant submission destination. The user is also notified when submission is complete. This speeds up and streamlines the process of generating and submitting medical certificates and related documents.

[0006] "User" refers to a person who uses the system to input medical history information and diagnostic results.

[0007] "Medical history information" refers to information about a user's past illnesses and treatment experiences.

[0008] "Diagnostic results" refers to the content and results of a diagnosis made by a doctor to a user.

[0009] "Submission information" refers to information about the insurance company, pension service, workers' compensation insurance office, etc. to which the medical certificate or evidence is submitted.

[0010] "Database" refers to a system or location for storing and managing a user's medical history information, diagnosis results, submission information, etc.

[0011] "Generative artificial intelligence" refers to software or systems that use artificial intelligence technology to automatically generate optimal evidence from medical history and diagnostic records.

[0012] "Trail" refers to documents and data files containing detailed information about diagnoses and medical conditions.

[0013] "Symptom comment" refers to a description of the condition written in easy-to-understand language that avoids technical jargon.

[0014] "Integrated file" refers to a document or data file that combines the generated evidence and medical condition comments into one.

[0015] "Cloud" refers to a distributed computing environment for storing and processing data and programs via the Internet.

[0016] "Notification" refers to the means by which the system notifies users and recipients of information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention relates to a system for unifying and issuing evidence for medical information, etc. Specifically, it is a system that allows users to input medical history information and diagnosis results, and generate and submit optimal evidence based on that information. This system unifies evidence using the cloud, and provides information to the recipient quickly and accurately.

[0039] System Overview

[0040] This system consists of three main components: the user, the terminal, and the server. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information.

[0041] Program processing

[0042] User Input Processing

[0043] The terminal provides the user with an interface for entering medical history information (e.g., disease name, diagnosis results, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office). The entered data is sent to the server by pressing the confirm button.

[0044] Sending and storing information

[0045] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database. To confirm that the storage was successful, the server records the results in a log and sends a notification of the completion of storage to the terminal.

[0046] Medical and diagnostic history search

[0047] The server searches the cloud database for the user's medical history and diagnosis based on their ID, and the retrieved information is temporarily stored in a cache for later processing.

[0048] Starting Trail Generation

[0049] The server requests processing from the artificial intelligence generator based on the patient's medical history and diagnosis. The AI ​​generator automatically generates evidence in different formats for each recipient. For example, details of treatment and prognosis are sent to insurance companies, disability grades are sent to the Pension Service, and work-related details are sent to workers' compensation insurance offices.

[0050] Auto-generated comments

[0051] The server uses generative AI to automatically generate easy-to-understand comments about the patient's condition, which are written in simple language and avoid technical jargon.

[0052] Creation of an integrated file of evidence and comments

[0053] The server combines the generated evidence and medical condition comments into a single file, typically in PDF or Word format.

[0054] Save the merged file and notify the recipient

[0055] The server stores the integrated files in the cloud and notifies the relevant submitters via email or a cloud notification system.

[0056] User Notification

[0057] The server sends a notification to the user that the submission has been completed. The user can check the notification on their own device and confirm that the submission has been successful.

[0058] Specific examples

[0059] For example, if user A enters "high blood pressure" as medical history information, "blood pressure management required" as diagnosis result, and "insurance company" as the submission destination, the system operates as follows.

[0060] 1. The user enters information through the terminal and sends it to the server.

[0061] 2. The server stores the information in a cloud database and searches for medical history and diagnostic history.

[0062] 3. The server uses generative AI to create an optimal trail for the insurance company.

[0063] 4. The server automatically generates easy-to-understand medical condition comments.

[0064] 5. The server combines the evidence and comments and generates a PDF file.

[0065] 6. The server saves the file to the cloud and notifies the insurance company.

[0066] 7. The server sends a notification to the user that the submission is complete.

[0067] This process saves users the trouble of creating complicated medical certificates, and allows recipients to receive the information quickly and accurately.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The terminal provides the user with an interface for inputting medical history information and submission destination information. The user inputs medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.).

[0071] Step 2:

[0072] The terminal will verify all the information entered by the user and provide a send button, which will send the entered data to the server.

[0073] Step 3:

[0074] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database, verifies that the storage is successful, and records the results in a log.

[0075] Step 4:

[0076] The server uses the user's ID to search the cloud database for medical history and diagnosis based on the saved user data, retrieves the search results, and temporarily stores them in a cache.

[0077] Step 5:

[0078] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which then generates the optimal evidence for each recipient. The AI ​​generator creates evidence including treatment details for insurance companies, disability grades for pension agencies, and work-related details for workers' compensation insurance offices.

[0079] Step 6:

[0080] The server uses artificial intelligence to automatically generate medical condition comments that are easy for anyone to understand. The generated comments are written in easy-to-understand language, avoiding technical jargon.

[0081] Step 7:

[0082] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[0083] Step 8:

[0084] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[0085] Step 9:

[0086] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[0087] Step 10:

[0088] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0089] Step 11:

[0090] The user checks the notification content on the terminal and, if necessary, contacts the recipient and provides additional information.

[0091] Example 1

[0092] 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."

[0093] In conventional medical information systems, the process of users entering medical history information and diagnosis results, generating appropriate evidence based on that information, and submitting it was extremely cumbersome. Converting the information into a format appropriate for the recipient was also time-consuming and laborious. Furthermore, it was difficult to explain the condition in an easy-to-understand format, making the medical information submission process a significant burden for general users without specialized knowledge.

[0094] 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.

[0095] In this invention, the server includes means for receiving disease information, diagnosis results, and recipient information entered by the user, means for storing the received information in a storage device, means for searching past medical records from the storage device based on the user's identification information, means for generating an optimal trail for the recipient using generation artificial intelligence, means for creating a document that integrates the generated trail with an easy-to-understand explanation of the disease, means for storing the integrated document in data storage and notifying the relevant recipient, and means for notifying the user that submission is complete. This allows the user to simply enter medical history information and diagnosis results, automatically generate an optimal trail, and quickly submit it to the recipient. Furthermore, the explanation of the condition is written in simple language that avoids technical jargon, making the information available to the user and the recipient in an easy-to-understand format.

[0096] "User" means an individual or organization that uses the system to input and submit disease information and diagnosis results.

[0097] "Disease information" refers to information such as the name of the disease, symptoms, diagnosis results, diagnosis date, doctor's name, etc., entered by the user.

[0098] "Diagnostic results" refers to information indicating the results of a diagnosis made by a doctor or medical institution, and includes treatment plans, prognosis forecasts, and the like.

[0099] "Recipient information" refers to information about the recipient of the information provided, such as an insurance institution, a pension institution, or a workers' compensation insurance institution, designated by the user.

[0100] "Storage" refers to a database or other storage system for storing received information.

[0101] "Identification information" refers to information that uniquely identifies a user, such as a user ID or other identifier.

[0102] "Past medical records" include information such as the user's medical history, past medical history, and past diagnostic results.

[0103] "Generative AI" refers to an AI system that uses pre-trained algorithms to automatically generate appropriate evidence and comments based on user input.

[0104] "Evidence" refers to documents and data generated based on input information that prove the information to the recipient.

[0105] "Explanation" refers to a simple, non-technical explanation of the disease or diagnosis that accompanies the generated evidence.

[0106] "Document" refers to data in a file format that integrates evidence and explanations, and includes formats such as PDF and Word.

[0107] "Data Storage" refers to cloud storage or other storage systems for storing integrated documents.

[0108] "Notification" refers to a message or alert that notifies the user or recipient that data has been saved or submitted.

[0109] This invention is a system that allows users to input disease information and diagnosis results, and generate and submit optimal evidence based on that information. This system uses the cloud to unify evidence and provide information to recipients quickly and accurately. Each component of the system and its specific operation are described below.

[0110] System configuration

[0111] This system consists of three main components: users, terminals, and servers.

[0112] User: Enters disease information and diagnosis results and provides the information to the recipient.

[0113] Terminal: Provides an interface for users to enter and confirm information and sends data to the server.

[0114] Server: Stores the received data, generates evidence using a generative AI model, and notifies the recipient and user.

[0115] Hardware and software used

[0116] Device: Input device such as a computer, tablet, or smartphone.

[0117] Cloud databases: Cloud databases such as Amazon RDS, Google Cloud Firestore, etc.

[0118] Cache system: A cache system with fast access, such as Redis.

[0119] Generative AI models: Generative AI such as OpenAI GPT-3, Google BERT, etc.

[0120] Data storage: Cloud storage such as Amazon S3, Google Drive.

[0121] PDF generation libraries: Open source tools such as ReportLab, Apache POI, etc.

[0122] Specific operation of the system

[0123] 1. User Input Processing

[0124] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Taro Tanaka), and recipient information (e.g., insurance company).

[0125] The device displays a preview screen for the user to confirm and send the input data, and when the user presses the "Send" button, the input data is sent to the server.

[0126] 2. Transmission and storage of information

[0127] The server stores the disease information, diagnosis results, and provider information received from the user in a cloud database. If the storage is successful, the server records "Data storage completed" in the log file and sends a notification of the storage completion to the terminal.

[0128] 3. Medical and diagnostic history search

[0129] The server retrieves past medical records from a cloud database based on the user's identification information and temporarily stores the retrieved information in a cache that can be accessed quickly.

[0130] 4. Starting the trail generation

[0131] The server requests the generative AI model to generate a trail based on the medical history and diagnosis history. It then constructs a prompt and sends an API request. For example, it sends a prompt that reads, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company. Include the following information: details of treatment, prognosis."

[0132] 5. Automatic comment generation

[0133] The server sends an additional prompt to the generative AI model, asking it to generate an easy-to-understand disease description, such as "Please explain the condition in simple terms, avoiding technical jargon."

[0134] 6. Creating an integrated file of evidence and comments

[0135] The server combines the generated evidence and disease descriptions into a single combined file. Tools such as ReportLab or Apache POI are used to generate documents in PDF and Word formats.

[0136] 7. Saving the integrated file and notifying the recipient

[0137] The server stores the integrated file in cloud storage and sends an email or API request to the recipient to provide a download link for the file.

[0138] 8. Notice to Users

[0139] The server sends a notification to the user that submission has been completed, and the user checks the notification content on the terminal.

[0140] Specific examples

[0141] For example, if a user is diagnosed with "high blood pressure" and enters information to submit to an insurance company, the system operates in the following manner.

[0142] 1. The user enters and transmits information through the terminal.

[0143] 2. The server stores the information in a cloud database and searches past medical records.

[0144] 3. The server requests the generative AI model to generate evidence for the insurance company.

[0145] 4. The server automatically generates a simple explanation of the disease.

[0146] 5. The server combines the evidence and description and generates a PDF file.

[0147] 6. The server saves the file to the cloud and notifies the insurance company.

[0148] 7. The server sends a notification to the user that the submission is complete.

[0149] This system allows users and recipients to receive information quickly and accurately, significantly reducing the effort required to submit medical history information.

[0150] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0151] Step 1:

[0152] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Tanaka Taro), and recipient information (e.g., insurance company). The user inputs this information. When the user presses the "Send" button, the input data (disease information, diagnosis results, recipient information) is sent to the server.

[0153] Step 2:

[0154] The server temporarily loads the disease information, diagnosis results, and provider information received from the user into memory. It then saves the information to a cloud database (e.g., Amazon RDS, Google Cloud Firestore) using an INSERT query. If the save is successful, the server records "Data saving completed" in the log file and sends a save completion notification to the terminal. This notification includes the message "Data saving completed."

[0155] Step 3:

[0156] The server retrieves past medical records from a cloud database based on the user's identity, for example, using a SELECT query like "SELECT FROM medical_records WHERE user_id = '12345'", and temporarily stores the retrieved information in a fast-access cache (e.g., Redis) for quick access later.

[0157] Step 4:

[0158] The server sends a prompt to the generative artificial intelligence (generative AI model) to generate a trail. For example, it might send a prompt like, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company to which you provide the service. Include the following information: details of treatment, prognosis." The prompt is passed to the generative AI model, which processes the data for generating the trail. The generative AI model generates the trail data and returns it to the server in JSON format or another format.

[0159] Step 5:

[0160] The server sends an additional prompt to the generative AI model to generate an easy-to-understand disease explanation comment. For example, it sends a prompt such as, "Please explain the condition in simple terms, avoiding technical jargon." The generative AI model generates a disease explanation comment and returns it to the server.

[0161] Step 6:

[0162] The server combines the generated evidence and symptom description comments to create a single combined file (PDF or Word file). This is done using an open source PDF generation library (e.g., ReportLab, Apache POI). The server checks the format and content of the file, saves the created combined file to a data storage service (e.g., Amazon S3, Google Drive), and calls the API used to save the combined file to confirm that it was successfully saved.

[0163] Step 7:

[0164] The server retrieves the URL of the saved integrated file and notifies the recipient. The recipient is notified via email or API request, and the notification includes a link to download the file. For example, an insurance company receives a message saying, "A new trail has been generated. Please download it from the link below."

[0165] Step 8:

[0166] The server sends a notification to the user that the submission has been completed. The notification includes the message "Submission completed successfully," and the user can check the notification on their device. This lets the user know that the procedure has been completed.

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] Conventional medical information management systems have the ability to generate evidence based on medical history information and diagnosis results entered by users, but it is difficult to respond in real time when the user's health condition changes.In addition, there is a need for faster and more accurate generation of medical evidence by linking with health monitoring systems installed in vehicles.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes means for receiving health condition information, medical diagnosis results, and reporting destination information entered by the user, means for storing the received information in a database, means for searching the database for past health records and diagnosis history based on the user's ID, means for generating an optimal trail according to the reporting destination using artificial intelligence based on the search results, means for generating a medical trail in real time based on health data collected from sensors in the vehicle, means for creating a file that integrates the generated trail with easy-to-understand comments on the health condition, means for saving the integrated file in the cloud and notifying the relevant reporting destinations, and means for notifying the user that the report has been completed. This enables rapid and accurate generation and reporting of a medical trail even when the user's health condition changes.

[0172] "Health status information" refers to physiological data such as the user's heart rate, body temperature, and respiratory rate, as well as information about symptoms.

[0173] "Medical diagnosis results" refers to information indicating medical judgments, including the details of diagnoses and test results by doctors.

[0174] "Report destination information" is information about the organization or institution to which the generated medical trail should be sent, such as an insurance institution or medical institution.

[0175] "Generative artificial intelligence" is a system that uses artificial intelligence technology to automatically perform a specific task (in this case, generating medical trails).

[0176] "Past health records" are historical information about health conditions previously entered by a user or reported by a medical institution.

[0177] "Diagnostic history" is information that records the details of past medical diagnoses regarding the user.

[0178] "In-vehicle sensors" are devices placed inside self-driving vehicles that measure and collect the user's heart rate, body temperature, breathing rate, etc. in real time.

[0179] A "medical trail" is an official record of medical information generated based on the user's health condition and diagnosis results, and is to be submitted to the reporting destination.

[0180] A "generated trail" is a medical trail that conforms to a specific format and is created by generated artificial intelligence.

[0181] An "easy-to-understand comment on health status" is an explanatory text about the user's health status written in simple language, avoiding technical jargon.

[0182] An "integrated file" is a single file containing the generated medical records and easy-to-understand comments about the health condition.

[0183] The "cloud" is a distributed computer network environment that stores data and provides services over the Internet.

[0184] The "means for notifying the completion of the report" is a communication means for notifying the user that the generation and submission of the medical trail has been completed.

[0185] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[0186] overview

[0187] This invention is a system that monitors the user's health condition in real time inside an autonomous vehicle, generates a medical trail based on that information using artificial intelligence, and promptly transmits it to the required recipient. The system mainly consists of the user's device (such as a smartphone), sensors installed in the autonomous vehicle, a cloud server, and artificial intelligence.

[0188] System Configuration

[0189] Hardware

[0190] 1. Device: A device such as a smartphone or tablet that allows users to input health status information and medical diagnosis results.

[0191] 2. Sensors: Devices installed inside the autonomous vehicle to measure physiological data, such as heart rate monitors, thermometers, and breathing sensors.

[0192] 3. Server: A central processing unit located on the cloud that receives and stores data from users and generates medical trails through artificial intelligence.

[0193] software

[0194] 1. Database: A cloud database that stores user input information, medical history, and diagnostic history.

[0195] 2. Generative Artificial Intelligence: An AI system that generates a medical trail based on the user's health status information and medical diagnosis results, depending on the recipient.

[0196] 3. Cloud Notification System: A cloud-based communication system for sending medical trails to the submission destination and notifying users when submission is complete.

[0197] Processing flow

[0198] First, the user inputs their health information and medical diagnosis results using a device such as a smartphone. The input data is sent from the device to a cloud server and stored in a database. The server searches for past health records and diagnosis history based on the user's ID, and uses sensors in the autonomous vehicle to collect the latest health data as needed.

[0199] Based on the collected data, the server uses artificial intelligence to generate a medical trail according to the recipient (e.g., insurance institution, medical institution, etc.). This medical trail is created as an integrated file with user-friendly comments and stored in the cloud. The relevant recipient is then notified, and the user is also notified that submission has been completed.

[0200] Specific examples

[0201] For example, suppose a user suddenly becomes ill in a self-driving vehicle and the following measurements are collected by sensors:

[0202] Heart rate: 95

[0203] Body temperature: 37.8℃

[0204] Breathing rate: 25

[0205] This data is sent in real time to the cloud, where Generative Artificial Intelligence generates a medical trail based on the following prompts:

[0206] Prompt Sentence Examples

[0207] "Generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8°C, Respiratory rate: 25, User ID: user123"

[0208] The generated medical trail is submitted to insurance agencies and medical institutions, and users are notified of the submission status via their smartphones. This process allows users to receive prompt and accurate medical treatment.

[0209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0210] Step 1:

[0211] The user uses the device to input health status information and medical diagnosis results, including heart rate, body temperature, respiratory rate, and doctor's diagnosis results. The device then transmits this data to a cloud server.

[0212] Step 2:

[0213] The server stores the health status information and medical diagnosis results received from the device in a database. The input is the health data including the user's ID, and the stored data will be used in later steps.

[0214] Step 3:

[0215] The server retrieves the past health records and medical history from the database based on the user's ID. The user ID is given as input, and the past health records and medical history are obtained as output.

[0216] Step 4:

[0217] The server uses sensors in the vehicle to monitor the user's real-time health data. The sensor data is input, and heart rate, body temperature, and respiratory rate are collected. This data is then sent to the cloud server.

[0218] Step 5:

[0219] The server uses artificial intelligence based on the collected data to generate the optimal medical trail for the recipient. This process uses the following prompt: "Please generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8℃, Respiratory rate: 25, User ID: user123." The generated trail is obtained as output.

[0220] Step 6:

[0221] The server integrates the generated evidence and easy-to-understand health status comments to create an integrated file. The input is the generated evidence and comments, and the output is an integrated file (e.g., PDF).

[0222] Step 7:

[0223] The server stores the integrated file in the cloud and notifies the relevant recipients. The input is the integrated file, and the output is notification information. Notifications are sent via email or a cloud notification system.

[0224] Step 8:

[0225] The server notifies the user that submission is complete. The input is notification completion information to the submission destination, and the output is a notification message to the user. The user can check this notification on their smartphone.

[0226] 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.

[0227] This invention relates to a system that efficiently manages medical history information and diagnosis results from users, recognizes the user's emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze the user's emotions and can adjust the content of evidence and comments based on the results.

[0228] System Overview

[0229] This system consists of four main components: the user, the terminal, the server, and the emotion engine. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information. Furthermore, the emotion engine is used to analyze the user's emotions and optimizes the trail and comments taking the results into account.

[0230] Program processing

[0231] User Input Processing

[0232] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office).The terminal also incorporates the necessary sensors and analysis algorithms to enable the emotion engine to recognize the user's emotions when entering information.

[0233] Sending and storing information

[0234] The terminal transmits the information entered by the user and the emotion data recognized by the emotion engine to the server. When the user presses the send button, the input data and the emotion data are sent together.

[0235] Data storage and retrieval

[0236] The server stores the medical history information, diagnosis results, submission destination information, and emotion data received from the user in a cloud database, confirms that the storage is successful, and records the results in a log.

[0237] The server searches the cloud database for the user's medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[0238] Starting Trail Generation

[0239] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which generates the optimal trail for each submission destination. The AI ​​generator creates trails in different formats for each submission destination.

[0240] Auto-generated comments

[0241] The server uses generative artificial intelligence to automatically generate understandable medical condition comments, which are tailored based on the user's emotions analyzed by the emotion engine.

[0242] Creation of an integrated file of evidence and comments

[0243] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[0244] Save the merged file and notify the recipient

[0245] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[0246] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[0247] User Notification

[0248] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0249] Specific examples

[0250] For example, if user B enters "diabetes" as medical history information, "blood sugar management required" as diagnosis result, and "Pension Service" as submission destination, the system will operate as follows.

[0251] 1. The user inputs information through the terminal, and the emotion engine recognizes the user's emotions (e.g., anxiety, relief, etc.) at the time of input.

[0252] 2. The server stores the user's information and emotional data in a cloud database and searches for medical history and diagnosis history.

[0253] 3. The server uses generative AI to create optimal evidence for the pension agency.

[0254] 4. The server uses generative AI to automatically generate easy-to-understand medical commentary based on data from the emotion engine.

[0255] 5. The server merges the evidence and comments and generates a PDF file.

[0256] 6. The server saves the file to the cloud and notifies the Pension Service.

[0257] 7. The server sends a notification to the user that the submission is complete.

[0258] 8. The user checks the notification on the device and, if necessary, contacts the recipient and provides additional information.

[0259] This process allows users to utilize an emotionally sensitive trail, ensuring that recipients receive information quickly and appropriately.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.). It also collects emotion data via devices such as sensors, microphones, and cameras, which are necessary for the emotion engine to recognize the emotion of the user when entering information.

[0263] Step 2:

[0264] The user enters medical history information and submission destination information through the terminal interface, and the terminal automatically recognizes the user's emotions. The user confirms the entered data and presses the send button.

[0265] Step 3:

[0266] The terminal transmits the medical history information, diagnosis results, submission destination information, and emotion data entered by the user to the server. The server checks the format of the transmitted data and displays a confirmation message to the user that transmission has been completed.

[0267] Step 4:

[0268] The server saves the data received from the user to the cloud database, and logs the successful completion of the saving process to confirm the completion of the saving.

[0269] Step 5:

[0270] The server searches the cloud database for medical history and diagnosis history based on the user's ID, retrieves the search results, and temporarily stores them in a cache. It then performs an error check on the retrieved data.

[0271] Step 6:

[0272] The server inputs the acquired medical history and diagnosis history, data received from the user, and emotional data into the artificial intelligence generator, which then generates the optimal trail for each submission destination. The generator AI automatically generates trails in different formats for each submission destination.

[0273] Step 7:

[0274] The server uses generative artificial intelligence to automatically generate a medical comment that is easy for anyone to understand, and the comment is adjusted based on the user's emotions analyzed by the emotion engine.

[0275] Step 8:

[0276] The server integrates the generated evidence and medical condition comments into a single integrated file (PDF or Word format), and performs error checking to ensure that the information contained in the file is complete.

[0277] Step 9:

[0278] The server saves the merged file to the cloud, logs the successful completion of the saving process, and confirms the result.

[0279] Step 10:

[0280] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, workers' compensation insurance offices, etc.) that the integrated file has been saved. Notifications are sent via email or a cloud notification system, and include an access link and any additional information required.

[0281] Step 11:

[0282] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0283] Step 12:

[0284] The user uses the terminal to check the contents of the notification, and if necessary, contacts the recipient and provides additional information.

[0285] Examples:

[0286] For example, if User D enters "high blood pressure" as medical history information, "requires continuous blood pressure management" as diagnosis, and "insurance company" as the recipient, the system operates as follows:

[0287] 1. The user inputs information through the device, and the device uses an emotion engine to recognize the user's emotions at the time of input (e.g., anxiety, relief, joy, etc.).

[0288] 2. The user checks all the information and presses the send button.

[0289] 3. The device sends the user data and emotion data to the server.

[0290] 4. The server stores the data in a cloud database.

[0291] 5. The server searches the medical history and diagnostic history and caches the results.

[0292] 6. The server uses generative AI to create an optimal trail for the insurance company.

[0293] 7. Based on the data from the emotion engine, the server automatically generates easy-to-understand comments about the patient's condition that avoid technical jargon.

[0294] 8. The server merges the evidence and comments and generates a PDF file.

[0295] 9. The server saves the file to the cloud and notifies the insurance company.

[0296] 10. The server sends a notification to the user that the submission is complete.

[0297] 11. The user checks the notification content on the device and contacts the recipient if necessary.

[0298] This process allows users to provide information to recipients quickly and accurately with a highly efficient and sensitive trail.

[0299] Example 2

[0300] 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."

[0301] Conventional management systems for medical history information and diagnosis results have difficulty generating optimal evidence and commentary on medical conditions that take user emotions into account. Furthermore, the need to accommodate different formats for each submission destination requires a great deal of effort, which not only takes time and effort for users but also causes delays in information submission. This has led to issues such as an inability to adequately respond in situations where prompt and appropriate information provision is required.

[0302] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0303] In this invention, the server includes means for receiving medical history information, diagnosis results, and submission destination information entered by the user, means for saving the received information and emotion data in a database, means for searching the database for the medical history and diagnosis history based on the user's ID, means for generating an optimal trail for the submission destination based on the search results and taking the emotion data into consideration using a generative AI model, means for automatically generating an easy-to-understand comment explaining the condition based on the generated trail and the user's emotions, means for creating a file integrating the generated trail and the easy-to-understand comment explaining the condition, means for saving the integrated file in the cloud and notifying the relevant submission destination, and means for notifying the user of completion of submission. This enables the rapid generation and submission of an optimal trail and comment explaining the condition while taking the user's emotions into consideration.

[0304] "Medical history information" is a general term for medical-related information such as illnesses the user has had in the past, diagnosis history at medical institutions, and treatment details.

[0305] The "diagnosis result" is information such as the user's current health condition, disease name, and need for treatment, which is obtained based on a diagnosis by a doctor.

[0306] "Submission destination information" refers to information about the institution or organization (e.g., insurance institution, pension institution, labor insurance institution) to which the user submits medical history information or diagnosis results.

[0307] "Emotion data" is data indicating the user's emotional state that is acquired when the user's medical history information and diagnosis results are input, and is analyzed by the emotion engine.

[0308] An "emotion engine" is a set of algorithms and sensors that recognize emotions by analyzing the user's facial expressions, voice, etc., and outputs the user's emotional state as data.

[0309] "Generative AI model" refers to the advanced artificial intelligence (AI) algorithms used to optimize the evidence and medical description comments for each submission.

[0310] "Evidence" refers to the official report or medical certificate generated based on the user's medical history and diagnosis results, and is created in a format appropriate for the recipient.

[0311] The "symptom explanation comment" is a supplementary comment to explain the user's condition in an easy-to-understand manner, and is automatically generated while avoiding technical terms and taking into consideration the user's emotional state.

[0312] An "integrated file" is a file that centrally compiles the generated evidence and commentary on the medical condition, and is saved in a format such as PDF or Word.

[0313] "Cloud" refers to a virtual data center that stores and processes data via the Internet, and serves as a storage location for user information and generated files.

[0314] "Notification" is a communication method for informing a user or a submission destination of the completion of an important process, such as the completion of saving or submission of information.

[0315] This invention is a system that efficiently manages medical history information and diagnosis results from users, recognizes user emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze user emotions and can adjust the content of evidence and comments based on the results. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[0316] The device provides an interface for users to input medical history information and diagnosis results. The device is equipped with the necessary sensors and analysis algorithms to implement the emotion engine. For example, devices such as a camera and microphone can be used to analyze the user's facial expressions and voice and obtain emotion data.

[0317] The medical history information, diagnosis results, and submission destination information entered by the user are sent from the device to the server. The sent information is stored in a cloud database by the server. The server searches the database for medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[0318] Next, the server generates evidence using a generative AI model. The generative AI model receives the user's medical history and diagnosis results as input and creates the optimal evidence for each submission destination. The generated evidence is provided in a different format for each submission destination. For example, there is a format for insurance institutions, a format for pension institutions, a format for labor insurance institutions, etc.

[0319] Furthermore, the server automatically generates an easy-to-understand comment explaining the patient's condition using a generative AI model based on the user's emotions analyzed by the emotion engine. The emotion engine takes the user's emotions into consideration and generates a comment that provides a sense of security. This comment is then integrated with the generated evidence to create a single integrated file (e.g., PDF or Word format).

[0320] The integrated file is saved to the cloud by the server. The server records the successful save completion in a log and notifies the relevant submitting parties via email or the cloud notification system. A notification of the completion of submission is also sent to the user. This allows the user to check the notification on their own device and, if necessary, contact the submitting parties to provide additional information.

[0321] For example, if a user enters "diabetes" as medical history information, "blood sugar management required" as diagnosis, and "pension institution" as destination, the system operates as follows: The device enters the user's information, and the emotion engine recognizes the user's emotions at the time of entry (e.g., anxiety, relief, etc.). The server then stores the user's information and emotion data in a cloud database and searches for medical history and diagnosis history. A generative AI model is used to create an optimal evidence trail for the pension institution, and easy-to-understand medical condition comments are automatically generated based on the emotion engine data. The server combines the evidence trail and comments, generates a PDF file, stores it in the cloud, and notifies the pension institution. Finally, a notification that submission is complete is sent to the user.

[0322] Examples of input prompts for generative AI models include:

[0323] Please create a trail for User B to submit. The submission is to a pension institution, the medical history information is "Diabetes," and the diagnosis result is "Needs blood sugar management." The user's emotion is "Anxiety." Please add a polite comment to reassure the anxious user.

[0324] Based on this prompt, the generative AI model can generate optimal evidence for pension institutions and medical condition explanation comments that take into account the user's emotions.

[0325] The above is an embodiment of the present invention.

[0326] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0327] System program processing flow

[0328] Step 1:

[0329] The user enters medical history information, diagnosis results, and submission information

[0330] Input: User's medical history information (e.g., diabetes), diagnosis results (e.g., blood sugar management required), submission destination information (e.g., pension institution)

[0331] How it works: The user enters information using the interface provided by the device, which is equipped with a camera and microphone for analyzing the input form and emotions.

[0332] Output: Input data (medical history information, diagnosis results, submission destination information), emotion data

[0333] Step 2:

[0334] The device sends input data and emotion data to the server.

[0335] Input: Information entered by the user and emotional data recognized by the emotion engine

[0336] How it works: When the user presses the send button, the device encrypts the data and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0337] Output: Data sent to the server

[0338] Step 3:

[0339] The server stores the received data in a cloud database.

[0340] Input: Medical history information, diagnosis results, submission destination information, emotional data sent from the device

[0341] Operation: The server saves the received data to the cloud database, verifies the success of the saving process, and records the result in a log.

[0342] Output: Data saved in the cloud database, log of saved data

[0343] Step 4:

[0344] The server searches the cloud database for medical history and diagnosis history based on the user ID.

[0345] Input: User ID, data stored in the cloud database

[0346] How it works: The server searches the cloud database using the user ID and executes SQL queries such as retrieving medical history and diagnostic history. The retrieved data is temporarily stored in a cache.

[0347] Output: Medical history data, diagnostic history data, cached data

[0348] Step 5:

[0349] The server generates evidence using the generative AI model

[0350] Input: Acquired medical history data, diagnosis history data, submission destination information

[0351] How it works: The server inputs this data into the generative AI model and generates the optimal trail for the submission destination. By inputting a prompt sentence into the generative AI model, the appropriate trail format is obtained.

[0352] Output: The generated trail

[0353] Step 6:

[0354] The server automatically generates a comment explaining the patient's condition based on the emotional data.

[0355] Input: Emotion data, generated evidence

[0356] How it works: Based on the results of the emotion engine, the server uses a generative AI model to automatically generate a comment explaining the patient's condition while taking into consideration the user's emotions.

[0357] Output: Comment explaining the condition

[0358] Step 7:

[0359] The server merges the trail and comments and creates a merged file.

[0360] Input: Generated evidence, symptom description comment

[0361] How it works: The server aggregates these data and generates a single file in PDF or Word format, using an integrated file generation library for formatting.

[0362] Output: Unified file

[0363] Step 8:

[0364] The server saves the integrated file in the cloud and notifies the relevant submitter.

[0365] Input: merged file

[0366] How it works: The server saves the merged file to cloud storage, logs the save completion, and then notifies the relevant submitters via email or cloud notification system.

[0367] Output: Integrated file stored in the cloud, notification to recipient

[0368] Step 9:

[0369] The server notifies the user that the submission is complete.

[0370] Input: Submission completion information, user contact information

[0371] Behavior: The server will notify the user that submission is complete via SMS, email, etc.

[0372] Output: User notification

[0373] Step 10:

[0374] The user reviews the notification and provides additional information if necessary.

[0375] Input: Notification of submission completion

[0376] How it works: The user reviews the notification on their device and, if necessary, contacts the person who submitted it to provide additional information.

[0377] Output: Correspondence record with the recipient, additional information

[0378] These processing steps enable the generation and submission of quick and optimal evidence and commentary on the medical condition, while taking into consideration the user's feelings.

[0379] (Application example 2)

[0380] 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."

[0381] Conventional systems for managing medical history information and diagnostic results have had difficulty generating appropriate evidence and comments while taking user emotions into consideration. Furthermore, they have been unable to provide countermeasures for security-related issues that reflect user emotions, which can lead to a decline in user satisfaction. The present invention aims to solve these problems and provide information that takes user emotions into consideration.

[0382] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving medical history information, diagnosis results, and submission destination information entered by the user; means for saving the received information in a database; means for searching the database for medical history and diagnosis history based on the user's identification information; means for generating an optimal trail for the submission destination using artificial intelligence based on the search results; means for creating a file that integrates the generated trail and easy-to-understand comments about the medical condition; means for saving the integrated file in a cloud environment and notifying the relevant submission destination; means for notifying the user that submission is complete; means for recognizing the user's emotions using an emotion engine and adjusting the content of the generated trail and comments; and means for the user to input security-related issues and generate optimal countermeasures and emotional support comments based on the input content and emotions. This makes it possible to provide information that takes the user's emotions into consideration, thereby improving user satisfaction.

[0383] "Medical history information" refers to information related to illnesses and health that a user has experienced in the past and present.

[0384] A "diagnosis result" is a judgment or conclusion reached by a doctor or other expert regarding a particular medical condition or disease after assessing the user's health condition.

[0385] "Submission destination information" refers to information about the recipient or organization (for example, insurance company, pension service, worker's accident compensation insurance office, etc.) to which the user provides medical history information or diagnosis results.

[0386] A "database" is a system for storing, searching, and managing information received from users in an organized and efficient manner. It can also be stored in a cloud environment.

[0387] "Identification information" refers to information (such as an identifier or ID) that identifies a user and is used to link past records and diagnostic history.

[0388] "Generative Artificial Intelligence" is a system that utilizes machine learning and deep learning technologies to automatically generate optimal evidence and comments based on input data.

[0389] A "trail" is a formal document or report generated based on a user's medical history and diagnosis. It is used for insurance claims, pension applications, etc.

[0390] "Easy-to-understand comments" are medical explanations and advice that have been rewritten to avoid technical jargon and be easy for the general public to understand.

[0391] A "cloud environment" refers to the use of servers and storage provided over the Internet, and is an environment that allows for flexible data storage and processing.

[0392] An "emotion engine" is a system that analyzes input data such as voice and facial expressions to recognize the user's emotions.

[0393] "Security-related issues" are safety and security issues and concerns that users face in their daily lives and online.

[0394] A "solution" is a solution or course of action that is considered most appropriate for a particular problem or situation.

[0395] "Emotional support comments" are comments such as comforting, encouraging, and instructing that are created with consideration for the user's emotional state.

[0396] This invention is a system that efficiently manages medical history information and diagnosis results entered by users, recognizes the user's emotions using an emotion engine, and provides appropriate evidence and comments based on the results. Another object of this invention is to provide emotion-sensitive countermeasures and emotional support comments when a user enters a security-related issue.

[0397] System configuration

[0398] The system consists of the following components:

[0399] 1. User Device

[0400] A dedicated application is installed on devices such as smartphones and PCs, where users can enter information such as medical history, diagnosis results, and security-related issues.

[0401] It has a built-in emotion engine that analyzes the user's emotions using the camera and microphone.

[0402] 2. Server

[0403] It is deployed in a cloud environment and stores data, analyzes it, generates trails, and provides notifications.

[0404] The main software used includes a database system, a generative AI model, and an email notification system. Specific examples of use include the use of Google Cloud Platform and AWS (Amazon Web Services).

[0405] 3. Database

[0406] A system for efficiently storing and managing information received from users, such as Firebase Firestore or AWS DynamoDB.

[0407] 4. Generative AI Models

[0408] It is an artificial intelligence system that generates optimal evidence and comments based on user-entered information and sentiment data. For example, OpenAI's GPT-3 model is used.

[0409] Program processing description

[0410] The role of each component and its processing are explained below.

[0411] 1. User Device

[0412] Users enter their medical history, diagnosis results, and security-related issues through the application, and the emotion engine uses the camera and microphone to analyze the user's voice and facial expressions to capture emotional data.

[0413] The acquired input data and emotion data are encrypted using SSL / TLS and sent to the cloud server.

[0414] 2. Server

[0415] The server stores the received data in a database and searches for medical history and diagnostic history based on the user's identification information.

[0416] Based on the search results and current diagnostic results, the results are input into a generative AI model to generate optimal evidence and easy-to-understand comments.

[0417] In addition, for security-related issues, the system generates optimal countermeasures and emotional support comments based on emotional data analyzed by the emotion engine.

[0418] 3. Generative AI Models

[0419] The generated evidence and comments are temporarily saved in JSON format or similar.

[0420] It is then output as a PDF or Word document and stored in a cloud environment.

[0421] 4. Notification System

[0422] After the merged file is saved, email and cloud notifications are sent to relevant recipients, such as insurance companies and security companies.

[0423] A notification will also be sent to the user, who can view it in the application.

[0424] Specific examples

[0425] As a concrete example, the following prompt sentence is generated:

[0426] If a user enters a security-related problem such as "I lost my house keys," the system operates as follows:

[0427] 1. Information is input through the user's device, and the emotion engine recognizes the emotion "anxiety."

[0428] 2. The server stores user information and emotional data in a cloud database and uses a generative AI model to create optimal responses.

[0429] 3. A prompt like the following will be generated:

[0430] “The problem you entered is ‘I lost my house keys.’ Our system recognized ‘anxiety’ as your current emotion.

[0431] Best practice:

[0432] Please stay calm and double check the area around the entrance.

[0433] If you can't find it, contact your nearest police station.

[0434] Please follow the instructions below. The phone number for xxxx Police Station is xxxxx."

[0435] 4. The server saves the generated content as a PDF file in the cloud and notifies the user and necessary authorities.

[0436] In this way, the embodiments of the invention allow for the construction of a system that provides optimal information based on the user's input and emotions.

[0437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0438] Step 1:

[0439] The user uses the device to input medical history information, diagnosis results, or security-related issues. The device receives the user's input data and simultaneously analyzes data from the camera and microphone using an emotion engine to recognize and acquire the user's emotions (e.g., anxiety, relief). The input data includes the name of the disease, the date of diagnosis, and details of the problem. The input data and emotion data are generated as output.

[0440] Step 2:

[0441] The device sends input data and emotion data to the cloud server. This data is encrypted and securely transferred using SSL / TLS. The output is the data received by the server.

[0442] Step 3:

[0443] The server stores the received input data and emotion data in a database system. At this time, the user's medical history and diagnosis history are searched from the database using the user's identification information as a key. The search results are then saved in temporary storage as output.

[0444] Step 4:

[0445] The server inputs the search results and current input data into a generative AI model to generate optimal evidence and comments. This generative AI model uses, for example, OpenAI's GPT-3. The search results and current input data are given as input, and the generated evidence and comments are obtained as output.

[0446] Step 5:

[0447] The server creates an integrated file (e.g., a PDF file) based on the generated evidence and comments. This file contains content adjusted to take into account the user's feelings. The generated evidence and comments are given as input, and the integrated file is obtained as output.

[0448] Step 6:

[0449] The server saves the integrated file in the cloud environment. After confirming that it has been saved, it sends a notification to the relevant recipients (e.g., insurance companies, pension institutions, security agencies). The storage path of the integrated file is given as input, and the notification is sent as output.

[0450] Step 7:

[0451] The server notifies the user that the integrated file has been saved and that the submission destination has been notified. The terminal receives this notification, and the process is completed when the user confirms it. Notification information is given as input, and a notification is sent to the user terminal as output.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Second embodiment]

[0456] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0467] 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."

[0468] This invention relates to a system for unifying and issuing evidence for medical information, etc. Specifically, it is a system that allows users to input medical history information and diagnosis results, and generate and submit optimal evidence based on that information. This system unifies evidence using the cloud, and provides information to the recipient quickly and accurately.

[0469] System Overview

[0470] This system consists of three main components: the user, the terminal, and the server. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information.

[0471] Program processing

[0472] User Input Processing

[0473] The terminal provides the user with an interface for entering medical history information (e.g., disease name, diagnosis results, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office). The entered data is sent to the server by pressing the confirm button.

[0474] Sending and storing information

[0475] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database. To confirm that the storage was successful, the server records the results in a log and sends a notification of the completion of storage to the terminal.

[0476] Medical and diagnostic history search

[0477] The server searches the cloud database for the user's medical history and diagnosis based on their ID, and the retrieved information is temporarily stored in a cache for later processing.

[0478] Starting Trail Generation

[0479] The server requests processing from the artificial intelligence generator based on the patient's medical history and diagnosis. The AI ​​generator automatically generates evidence in different formats for each recipient. For example, details of treatment and prognosis are sent to insurance companies, disability grades are sent to the Pension Service, and work-related details are sent to workers' compensation insurance offices.

[0480] Auto-generated comments

[0481] The server uses generative AI to automatically generate easy-to-understand comments about the patient's condition, which are written in simple language and avoid technical jargon.

[0482] Creation of an integrated file of evidence and comments

[0483] The server combines the generated evidence and medical condition comments into a single file, typically in PDF or Word format.

[0484] Save the merged file and notify the recipient

[0485] The server stores the integrated files in the cloud and notifies the relevant submitters via email or a cloud notification system.

[0486] User Notification

[0487] The server sends a notification to the user that the submission has been completed. The user can check the notification on their device and confirm that the submission has been successful.

[0488] Specific examples

[0489] For example, if user A enters "high blood pressure" as medical history information, "blood pressure management required" as diagnosis result, and "insurance company" as the submission destination, the system operates as follows.

[0490] 1. The user enters information through the terminal and sends it to the server.

[0491] 2. The server stores the information in a cloud database and searches for medical history and diagnostic history.

[0492] 3. The server uses generative AI to create an optimal trail for the insurance company.

[0493] 4. The server automatically generates easy-to-understand medical condition comments.

[0494] 5. The server combines the evidence and comments and generates a PDF file.

[0495] 6. The server saves the file to the cloud and notifies the insurance company.

[0496] 7. The server sends a notification to the user that the submission is complete.

[0497] This process saves users the trouble of creating complicated medical certificates, and allows recipients to receive the information quickly and accurately.

[0498] The processing flow will be explained below.

[0499] Step 1:

[0500] The terminal provides the user with an interface for inputting medical history information and submission destination information. The user inputs medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.).

[0501] Step 2:

[0502] The terminal will verify all the information entered by the user and provide a send button, which will send the entered data to the server.

[0503] Step 3:

[0504] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database, verifies that the storage is successful, and records the results in a log.

[0505] Step 4:

[0506] The server uses the user's ID to search the cloud database for medical history and diagnosis based on the saved user data, retrieves the search results, and temporarily stores them in a cache.

[0507] Step 5:

[0508] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which then generates the optimal evidence for each recipient. The AI ​​generator creates evidence including treatment details for insurance companies, disability grades for pension agencies, and work-related details for workers' compensation insurance offices.

[0509] Step 6:

[0510] The server uses artificial intelligence to automatically generate medical condition comments that are easy for anyone to understand. The generated comments are written in easy-to-understand language, avoiding technical jargon.

[0511] Step 7:

[0512] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[0513] Step 8:

[0514] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[0515] Step 9:

[0516] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[0517] Step 10:

[0518] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0519] Step 11:

[0520] The user checks the notification content on the terminal and, if necessary, contacts the recipient and provides additional information.

[0521] Example 1

[0522] 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."

[0523] In conventional medical information systems, the process of users entering medical history information and diagnosis results, generating appropriate evidence based on that information, and submitting it was extremely cumbersome. Converting the information into a format appropriate for the recipient was also time-consuming and laborious. Furthermore, it was difficult to explain the condition in an easy-to-understand format, making the medical information submission process a significant burden for general users without specialized knowledge.

[0524] 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.

[0525] In this invention, the server includes means for receiving disease information, diagnosis results, and recipient information entered by the user, means for storing the received information in a storage device, means for searching past medical records from the storage device based on the user's identification information, means for generating an optimal trail for the recipient using generation artificial intelligence, means for creating a document that integrates the generated trail with an easy-to-understand explanation of the disease, means for storing the integrated document in data storage and notifying the relevant recipient, and means for notifying the user that submission is complete. This allows the user to simply enter medical history information and diagnosis results, automatically generate an optimal trail, and quickly submit it to the recipient. Furthermore, the explanation of the condition is written in simple language that avoids technical jargon, making the information available to the user and the recipient in an easy-to-understand format.

[0526] "User" means an individual or organization that uses the system to input and submit disease information and diagnosis results.

[0527] "Disease information" refers to information such as the name of the disease, symptoms, diagnosis results, diagnosis date, doctor's name, etc., entered by the user.

[0528] "Diagnostic results" refers to information indicating the results of a diagnosis made by a doctor or medical institution, and includes treatment plans, prognosis forecasts, and the like.

[0529] "Recipient information" refers to information about the recipient of the information provided, such as an insurance institution, a pension institution, or a workers' compensation insurance institution, designated by the user.

[0530] "Storage" refers to a database or other storage system for storing received information.

[0531] "Identification information" refers to information that uniquely identifies a user, such as a user ID or other identifier.

[0532] "Past medical records" include information such as the user's medical history, past medical history, and past diagnostic results.

[0533] "Generative AI" refers to an AI system that uses pre-trained algorithms to automatically generate appropriate evidence and comments based on user input.

[0534] "Evidence" refers to documents and data generated based on input information that prove the information to the recipient.

[0535] "Explanation" refers to a simple, non-technical explanation of the disease or diagnosis that accompanies the generated evidence.

[0536] "Document" refers to data in a file format that integrates evidence and explanations, and includes formats such as PDF and Word.

[0537] "Data Storage" refers to cloud storage or other storage systems for storing integrated documents.

[0538] "Notification" refers to a message or alert that notifies the user or recipient that data has been saved or submitted.

[0539] This invention is a system that allows users to input disease information and diagnosis results, and generate and submit optimal evidence based on that information. This system uses the cloud to unify evidence and provide information to recipients quickly and accurately. Each component of the system and its specific operation are described below.

[0540] System configuration

[0541] This system consists of three main components: users, terminals, and servers.

[0542] User: Enters disease information and diagnosis results and provides the information to the recipient.

[0543] Terminal: Provides an interface for users to enter and confirm information and sends data to the server.

[0544] Server: Stores the received data, generates evidence using a generative AI model, and notifies the recipient and user.

[0545] Hardware and software used

[0546] Device: Input device such as a computer, tablet, or smartphone.

[0547] Cloud databases: Cloud databases such as Amazon RDS, Google Cloud Firestore, etc.

[0548] Cache system: A cache system with fast access, such as Redis.

[0549] Generative AI models: Generative AI such as OpenAI GPT-3, Google BERT, etc.

[0550] Data storage: Cloud storage such as Amazon S3, Google Drive.

[0551] PDF generation libraries: Open source tools such as ReportLab, Apache POI, etc.

[0552] Specific operation of the system

[0553] 1. User Input Processing

[0554] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Taro Tanaka), and recipient information (e.g., insurance company).

[0555] The device displays a preview screen for the user to confirm and send the input data, and when the user presses the "Send" button, the input data is sent to the server.

[0556] 2. Transmission and storage of information

[0557] The server stores the disease information, diagnosis results, and provider information received from the user in a cloud database. If the storage is successful, the server records "Data storage completed" in the log file and sends a notification of the storage completion to the terminal.

[0558] 3. Medical and diagnostic history search

[0559] The server retrieves past medical records from a cloud database based on the user's identification information and temporarily stores the retrieved information in a cache that can be accessed quickly.

[0560] 4. Starting the trail generation

[0561] The server requests the generative AI model to generate a trail based on the medical history and diagnosis history. It then constructs a prompt and sends an API request. For example, it sends a prompt that reads, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company. Include the following information: details of treatment, prognosis."

[0562] 5. Automatic comment generation

[0563] The server sends an additional prompt to the generative AI model, asking it to generate an easy-to-understand disease description, such as "Please explain the condition in simple terms, avoiding technical jargon."

[0564] 6. Creating an integrated file of evidence and comments

[0565] The server combines the generated evidence and disease descriptions into a single combined file. Tools such as ReportLab or Apache POI are used to generate documents in PDF and Word formats.

[0566] 7. Saving the integrated file and notifying the recipient

[0567] The server stores the integrated file in cloud storage and sends an email or API request to the recipient to provide a download link for the file.

[0568] 8. Notice to Users

[0569] The server sends a notification to the user that submission has been completed, and the user checks the notification content on the terminal.

[0570] Specific examples

[0571] For example, if a user is diagnosed with "high blood pressure" and enters information to submit to an insurance company, the system operates in the following manner.

[0572] 1. The user enters and transmits information through the terminal.

[0573] 2. The server stores the information in a cloud database and searches past medical records.

[0574] 3. The server requests the generative AI model to generate evidence for the insurance company.

[0575] 4. The server automatically generates a simple explanation of the disease.

[0576] 5. The server combines the evidence and description and generates a PDF file.

[0577] 6. The server saves the file to the cloud and notifies the insurance company.

[0578] 7. The server sends a notification to the user that the submission is complete.

[0579] This system allows users and recipients to receive information quickly and accurately, significantly reducing the effort required to submit medical history information.

[0580] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0581] Step 1:

[0582] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Tanaka Taro), and recipient information (e.g., insurance company). The user inputs this information. When the user presses the "Send" button, the input data (disease information, diagnosis results, recipient information) is sent to the server.

[0583] Step 2:

[0584] The server temporarily loads the disease information, diagnosis results, and provider information received from the user into memory. It then saves the information to a cloud database (e.g., Amazon RDS, Google Cloud Firestore) using an INSERT query. If the save is successful, the server records "Data saving completed" in the log file and sends a save completion notification to the terminal. This notification includes the message "Data saving completed."

[0585] Step 3:

[0586] The server retrieves past medical records from a cloud database based on the user's identity, for example, using a SELECT query like "SELECT FROM medical_records WHERE user_id = '12345'", and temporarily stores the retrieved information in a fast-access cache (e.g., Redis) for quick access later.

[0587] Step 4:

[0588] The server sends a prompt to the generative artificial intelligence (generative AI model) to generate a trail. For example, it might send a prompt like, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company to which you provide the service. Include the following information: details of treatment, prognosis." The prompt is passed to the generative AI model, which processes the data for generating the trail. The generative AI model generates the trail data and returns it to the server in JSON format or another format.

[0589] Step 5:

[0590] The server sends an additional prompt to the generative AI model to generate an easy-to-understand disease explanation comment. For example, it sends a prompt such as, "Please explain the condition in simple terms, avoiding technical jargon." The generative AI model generates a disease explanation comment and returns it to the server.

[0591] Step 6:

[0592] The server combines the generated evidence and symptom description comments to create a single combined file (PDF or Word file). This is done using an open source PDF generation library (e.g., ReportLab, Apache POI). The server checks the format and content of the file, saves the created combined file to a data storage service (e.g., Amazon S3, Google Drive), and calls the API used to save the combined file to confirm that it was successfully saved.

[0593] Step 7:

[0594] The server retrieves the URL of the saved integrated file and notifies the recipient. The recipient is notified via email or API request, and the notification includes a link to download the file. For example, an insurance company receives a message saying, "A new trail has been generated. Please download it from the link below."

[0595] Step 8:

[0596] The server sends a notification to the user that the submission has been completed. The notification includes the message "Submission completed successfully," and the user can check the notification on their device. This lets the user know that the procedure has been completed.

[0597] (Application example 1)

[0598] 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."

[0599] Conventional medical information management systems have the ability to generate evidence based on medical history information and diagnosis results entered by users, but it is difficult to respond in real time when the user's health condition changes.In addition, there is a need for faster and more accurate generation of medical evidence by linking with health monitoring systems installed in vehicles.

[0600] 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.

[0601] In this invention, the server includes means for receiving health condition information, medical diagnosis results, and reporting destination information entered by the user, means for storing the received information in a database, means for searching the database for past health records and diagnosis history based on the user's ID, means for generating an optimal trail according to the reporting destination using artificial intelligence based on the search results, means for generating a medical trail in real time based on health data collected from sensors in the vehicle, means for creating a file that integrates the generated trail with easy-to-understand comments on the health condition, means for saving the integrated file in the cloud and notifying the relevant reporting destinations, and means for notifying the user that the report has been completed. This enables rapid and accurate generation and reporting of a medical trail even when the user's health condition changes.

[0602] "Health status information" refers to physiological data such as the user's heart rate, body temperature, and respiratory rate, as well as information about symptoms.

[0603] "Medical diagnosis results" refers to information indicating medical judgments, including the details of diagnoses and test results by doctors.

[0604] "Report destination information" is information about the organization or institution to which the generated medical trail should be sent, such as an insurance institution or medical institution.

[0605] "Generative artificial intelligence" is a system that uses artificial intelligence technology to automatically perform a specific task (in this case, generating medical trails).

[0606] "Past health records" are historical information about health conditions previously entered by a user or reported by a medical institution.

[0607] "Diagnostic history" is information that records the details of past medical diagnoses regarding the user.

[0608] "In-vehicle sensors" are devices placed inside self-driving vehicles that measure and collect the user's heart rate, body temperature, breathing rate, etc. in real time.

[0609] A "medical trail" is an official record of medical information generated based on the user's health condition and diagnosis results, and is to be submitted to the reporting destination.

[0610] A "generated trail" is a medical trail that conforms to a specific format and is created by generated artificial intelligence.

[0611] An "easy-to-understand comment on health status" is an explanatory text about the user's health status written in simple language, avoiding technical jargon.

[0612] An "integrated file" is a single file containing the generated medical records and easy-to-understand comments about the health condition.

[0613] The "cloud" is a distributed computer network environment that stores data and provides services over the Internet.

[0614] The "means for notifying the completion of the report" is a communication means for notifying the user that the generation and submission of the medical trail has been completed.

[0615] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[0616] overview

[0617] This invention is a system that monitors the user's health condition in real time inside an autonomous vehicle, generates a medical trail based on that information using artificial intelligence, and promptly transmits it to the required recipient. The system mainly consists of the user's device (such as a smartphone), sensors installed in the autonomous vehicle, a cloud server, and artificial intelligence.

[0618] System Configuration

[0619] Hardware

[0620] 1. Device: A device such as a smartphone or tablet that allows users to input health status information and medical diagnosis results.

[0621] 2. Sensors: Devices installed inside the autonomous vehicle to measure physiological data, such as heart rate monitors, thermometers, and breathing sensors.

[0622] 3. Server: A central processing unit located on the cloud that receives and stores data from users and generates medical trails through artificial intelligence.

[0623] software

[0624] 1. Database: A cloud database that stores user input information, medical history, and diagnostic history.

[0625] 2. Generative Artificial Intelligence: An AI system that generates a medical trail based on the user's health status information and medical diagnosis results, depending on the recipient.

[0626] 3. Cloud Notification System: A cloud-based communication system for sending medical trails to the submission destination and notifying users when submission is complete.

[0627] Processing flow

[0628] First, the user inputs their health information and medical diagnosis results using a device such as a smartphone. The input data is sent from the device to a cloud server and stored in a database. The server searches for past health records and diagnosis history based on the user's ID, and uses sensors in the autonomous vehicle to collect the latest health data as needed.

[0629] Based on the collected data, the server uses artificial intelligence to generate a medical trail according to the recipient (e.g., insurance institution, medical institution, etc.). This medical trail is created as an integrated file with user-friendly comments and stored in the cloud. The relevant recipient is then notified, and the user is also notified that submission has been completed.

[0630] Specific examples

[0631] For example, suppose a user suddenly becomes ill in a self-driving vehicle and the following measurements are collected by sensors:

[0632] Heart rate: 95

[0633] Body temperature: 37.8℃

[0634] Breathing rate: 25

[0635] This data is sent in real time to the cloud, where Generative Artificial Intelligence generates a medical trail based on the following prompts:

[0636] Prompt Sentence Examples

[0637] "Generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8°C, Respiratory rate: 25, User ID: user123"

[0638] The generated medical trail is submitted to insurance agencies and medical institutions, and users are notified of the submission status via their smartphones. This process allows users to receive prompt and accurate medical treatment.

[0639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0640] Step 1:

[0641] The user uses the device to input health status information and medical diagnosis results, including heart rate, body temperature, respiratory rate, and doctor's diagnosis results. The device then transmits this data to a cloud server.

[0642] Step 2:

[0643] The server stores the health status information and medical diagnosis results received from the device in a database. The input is the health data including the user's ID, and the stored data will be used in later steps.

[0644] Step 3:

[0645] The server retrieves the past health records and medical history from the database based on the user's ID. The user ID is given as input, and the past health records and medical history are obtained as output.

[0646] Step 4:

[0647] The server uses sensors in the vehicle to monitor the user's real-time health data. The sensor data is input, and heart rate, body temperature, and respiratory rate are collected. This data is then sent to the cloud server.

[0648] Step 5:

[0649] The server uses artificial intelligence based on the collected data to generate the optimal medical trail for the recipient. This process uses the following prompt: "Please generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8℃, Respiratory rate: 25, User ID: user123." The generated trail is obtained as output.

[0650] Step 6:

[0651] The server integrates the generated evidence and easy-to-understand health status comments to create an integrated file. The input is the generated evidence and comments, and the output is an integrated file (e.g., PDF).

[0652] Step 7:

[0653] The server stores the integrated file in the cloud and notifies the relevant recipients. The input is the integrated file, and the output is notification information. Notifications are sent via email or a cloud notification system.

[0654] Step 8:

[0655] The server notifies the user that submission is complete. The input is notification completion information to the submission destination, and the output is a notification message to the user. The user can check this notification on their smartphone.

[0656] 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.

[0657] This invention relates to a system that efficiently manages medical history information and diagnosis results from users, recognizes the user's emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze the user's emotions and can adjust the content of evidence and comments based on the results.

[0658] System Overview

[0659] This system consists of four main components: the user, the terminal, the server, and the emotion engine. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information. Furthermore, the emotion engine is used to analyze the user's emotions and optimizes the trail and comments taking the results into account.

[0660] Program processing

[0661] User Input Processing

[0662] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office).The terminal also incorporates the necessary sensors and analysis algorithms to enable the emotion engine to recognize the user's emotions when entering information.

[0663] Sending and storing information

[0664] The terminal transmits the information entered by the user and the emotion data recognized by the emotion engine to the server. When the user presses the send button, the input data and the emotion data are sent together.

[0665] Data storage and retrieval

[0666] The server stores the medical history information, diagnosis results, submission destination information, and emotion data received from the user in a cloud database, confirms that the storage is successful, and records the results in a log.

[0667] The server searches the cloud database for the user's medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[0668] Starting Trail Generation

[0669] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which generates the optimal trail for each submission destination. The AI ​​generator creates trails in different formats for each submission destination.

[0670] Auto-generated comments

[0671] The server uses generative artificial intelligence to automatically generate understandable medical condition comments, which are tailored based on the user's emotions analyzed by the emotion engine.

[0672] Creation of an integrated file of evidence and comments

[0673] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[0674] Save the merged file and notify the recipient

[0675] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[0676] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[0677] User Notification

[0678] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0679] Specific examples

[0680] For example, if user B enters "diabetes" as medical history information, "blood sugar management required" as diagnosis result, and "Pension Service" as submission destination, the system will operate as follows.

[0681] 1. The user inputs information through the terminal, and the emotion engine recognizes the user's emotions (e.g., anxiety, relief, etc.) at the time of input.

[0682] 2. The server stores the user's information and emotional data in a cloud database and searches for medical history and diagnosis history.

[0683] 3. The server uses generative AI to create optimal evidence for the pension agency.

[0684] 4. The server uses generative AI to automatically generate easy-to-understand medical commentary based on data from the emotion engine.

[0685] 5. The server merges the evidence and comments and generates a PDF file.

[0686] 6. The server saves the file to the cloud and notifies the Pension Service.

[0687] 7. The server sends a notification to the user that the submission is complete.

[0688] 8. The user checks the notification on the device and, if necessary, contacts the recipient and provides additional information.

[0689] This process allows users to utilize an emotionally sensitive trail, ensuring that recipients receive information quickly and appropriately.

[0690] The processing flow will be explained below.

[0691] Step 1:

[0692] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.). It also collects emotion data via devices such as sensors, microphones, and cameras, which are necessary for the emotion engine to recognize the emotion of the user when entering information.

[0693] Step 2:

[0694] The user enters medical history information and submission destination information through the terminal interface, and the terminal automatically recognizes the user's emotions. The user confirms the entered data and presses the send button.

[0695] Step 3:

[0696] The terminal transmits the medical history information, diagnosis results, submission destination information, and emotion data entered by the user to the server. The server checks the format of the transmitted data and displays a confirmation message to the user that transmission has been completed.

[0697] Step 4:

[0698] The server saves the data received from the user to the cloud database, and logs the successful completion of the saving process to confirm the completion of the saving.

[0699] Step 5:

[0700] The server searches the cloud database for medical history and diagnosis history based on the user's ID, retrieves the search results, and temporarily stores them in a cache. It then performs an error check on the retrieved data.

[0701] Step 6:

[0702] The server inputs the acquired medical history and diagnosis history, data received from the user, and emotional data into the artificial intelligence generator, which then generates the optimal trail for each submission destination. The generator AI automatically generates trails in different formats for each submission destination.

[0703] Step 7:

[0704] The server uses generative artificial intelligence to automatically generate a medical comment that is easy for anyone to understand, and the comment is adjusted based on the user's emotions analyzed by the emotion engine.

[0705] Step 8:

[0706] The server integrates the generated evidence and medical condition comments into a single integrated file (PDF or Word format), and performs error checking to ensure that the information contained in the file is complete.

[0707] Step 9:

[0708] The server saves the merged file to the cloud, logs the successful completion of the saving process, and confirms the result.

[0709] Step 10:

[0710] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, workers' compensation insurance offices, etc.) that the integrated file has been saved. Notifications are sent via email or a cloud notification system, and include an access link and any additional information required.

[0711] Step 11:

[0712] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0713] Step 12:

[0714] The user uses the terminal to check the contents of the notification, and if necessary, contacts the recipient and provides additional information.

[0715] Examples:

[0716] For example, if User D enters "high blood pressure" as medical history information, "requires continuous blood pressure management" as diagnosis, and "insurance company" as the recipient, the system operates as follows:

[0717] 1. The user inputs information through the device, and the device uses an emotion engine to recognize the user's emotions at the time of input (e.g., anxiety, relief, joy, etc.).

[0718] 2. The user checks all the information and presses the send button.

[0719] 3. The device sends the user data and emotion data to the server.

[0720] 4. The server stores the data in a cloud database.

[0721] 5. The server searches the medical history and diagnostic history and caches the results.

[0722] 6. The server uses generative AI to create an optimal trail for the insurance company.

[0723] 7. Based on the data from the emotion engine, the server automatically generates easy-to-understand comments about the patient's condition that avoid technical jargon.

[0724] 8. The server merges the evidence and comments and generates a PDF file.

[0725] 9. The server saves the file to the cloud and notifies the insurance company.

[0726] 10. The server sends a notification to the user that the submission is complete.

[0727] 11. The user checks the notification content on the device and contacts the recipient if necessary.

[0728] This process allows users to provide information to recipients quickly and accurately with a highly efficient and sensitive trail.

[0729] Example 2

[0730] 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."

[0731] Conventional management systems for medical history information and diagnosis results have difficulty generating optimal evidence and commentary on medical conditions that take user emotions into account. Furthermore, the need to accommodate different formats for each submission destination requires a great deal of effort, which not only takes time and effort for users but also causes delays in information submission. This has led to issues such as an inability to adequately respond in situations where prompt and appropriate information provision is required.

[0732] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0733] In this invention, the server includes means for receiving medical history information, diagnosis results, and submission destination information entered by the user, means for saving the received information and emotion data in a database, means for searching the database for the medical history and diagnosis history based on the user's ID, means for generating an optimal trail for the submission destination based on the search results and taking the emotion data into consideration using a generative AI model, means for automatically generating an easy-to-understand comment explaining the condition based on the generated trail and the user's emotions, means for creating a file integrating the generated trail and the easy-to-understand comment explaining the condition, means for saving the integrated file in the cloud and notifying the relevant submission destination, and means for notifying the user of completion of submission. This enables the rapid generation and submission of an optimal trail and comment explaining the condition while taking the user's emotions into consideration.

[0734] "Medical history information" is a general term for medical-related information such as illnesses the user has had in the past, diagnosis history at medical institutions, and treatment details.

[0735] The "diagnosis result" is information such as the user's current health condition, disease name, and need for treatment, which is obtained based on a diagnosis by a doctor.

[0736] "Submission destination information" refers to information about the institution or organization (e.g., insurance institution, pension institution, labor insurance institution) to which the user submits medical history information or diagnosis results.

[0737] "Emotion data" is data indicating the user's emotional state that is acquired when the user's medical history information and diagnosis results are input, and is analyzed by the emotion engine.

[0738] An "emotion engine" is a set of algorithms and sensors that recognize emotions by analyzing the user's facial expressions, voice, etc., and outputs the user's emotional state as data.

[0739] "Generative AI model" refers to the advanced artificial intelligence (AI) algorithms used to optimize the evidence and medical description comments for each submission.

[0740] "Evidence" refers to the official report or medical certificate generated based on the user's medical history and diagnosis results, and is created in a format appropriate for the recipient.

[0741] The "symptom explanation comment" is a supplementary comment to explain the user's condition in an easy-to-understand manner, and is automatically generated while avoiding technical terms and taking into consideration the user's emotional state.

[0742] An "integrated file" is a file that centrally compiles the generated evidence and commentary on the medical condition, and is saved in a format such as PDF or Word.

[0743] "Cloud" refers to a virtual data center that stores and processes data via the Internet, and serves as a storage location for user information and generated files.

[0744] "Notification" is a communication method for informing a user or a submission destination of the completion of an important process, such as the completion of saving or submission of information.

[0745] This invention is a system that efficiently manages medical history information and diagnosis results from users, recognizes user emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze user emotions and can adjust the content of evidence and comments based on the results. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[0746] The device provides an interface for users to input medical history information and diagnosis results. The device is equipped with the necessary sensors and analysis algorithms to implement the emotion engine. For example, devices such as a camera and microphone can be used to analyze the user's facial expressions and voice and obtain emotion data.

[0747] The medical history information, diagnosis results, and submission destination information entered by the user are sent from the device to the server. The sent information is stored in a cloud database by the server. The server searches the database for medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[0748] Next, the server generates evidence using a generative AI model. The generative AI model receives the user's medical history and diagnosis results as input and creates the optimal evidence for each submission destination. The generated evidence is provided in a different format for each submission destination. For example, there is a format for insurance institutions, a format for pension institutions, a format for labor insurance institutions, etc.

[0749] Furthermore, the server automatically generates an easy-to-understand comment explaining the patient's condition using a generative AI model based on the user's emotions analyzed by the emotion engine. The emotion engine takes the user's emotions into consideration and generates a comment that provides a sense of security. This comment is then integrated with the generated evidence to create a single integrated file (e.g., PDF or Word format).

[0750] The integrated file is saved to the cloud by the server. The server records the successful save completion in a log and notifies the relevant submitting parties via email or the cloud notification system. A notification of the completion of submission is also sent to the user. This allows the user to check the notification on their own device and, if necessary, contact the submitting parties to provide additional information.

[0751] For example, if a user enters "diabetes" as medical history information, "blood sugar management required" as diagnosis, and "pension institution" as destination, the system operates as follows: The device enters the user's information, and the emotion engine recognizes the user's emotions at the time of entry (e.g., anxiety, relief, etc.). The server then stores the user's information and emotion data in a cloud database and searches for medical history and diagnosis history. A generative AI model is used to create an optimal evidence trail for the pension institution, and easy-to-understand medical condition comments are automatically generated based on the emotion engine data. The server combines the evidence trail and comments, generates a PDF file, stores it in the cloud, and notifies the pension institution. Finally, a notification that submission is complete is sent to the user.

[0752] Examples of input prompts for generative AI models include:

[0753] Please create a trail for User B to submit. The submission is to a pension institution, the medical history information is "Diabetes," and the diagnosis result is "Needs blood sugar management." The user's emotion is "Anxiety." Please add a polite comment to reassure the anxious user.

[0754] Based on this prompt, the generative AI model can generate optimal evidence for pension institutions and medical condition explanation comments that take into account the user's emotions.

[0755] The above is an embodiment of the present invention.

[0756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0757] System program processing flow

[0758] Step 1:

[0759] The user enters medical history information, diagnosis results, and submission information

[0760] Input: User's medical history information (e.g., diabetes), diagnosis results (e.g., blood sugar management required), submission destination information (e.g., pension institution)

[0761] How it works: The user enters information using the interface provided by the device, which is equipped with a camera and microphone for analyzing the input form and emotions.

[0762] Output: Input data (medical history information, diagnosis results, submission destination information), emotion data

[0763] Step 2:

[0764] The device sends input data and emotion data to the server.

[0765] Input: Information entered by the user and emotional data recognized by the emotion engine

[0766] How it works: When the user presses the send button, the device encrypts the data and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0767] Output: Data sent to the server

[0768] Step 3:

[0769] The server stores the received data in a cloud database.

[0770] Input: Medical history information, diagnosis results, submission destination information, emotional data sent from the device

[0771] Operation: The server saves the received data to the cloud database, verifies the success of the saving process, and records the result in a log.

[0772] Output: Data saved in the cloud database, log of saved data

[0773] Step 4:

[0774] The server searches the cloud database for medical history and diagnosis history based on the user ID.

[0775] Input: User ID, data stored in the cloud database

[0776] How it works: The server searches the cloud database using the user ID and executes SQL queries such as retrieving medical history and diagnostic history. The retrieved data is temporarily stored in a cache.

[0777] Output: Medical history data, diagnostic history data, cached data

[0778] Step 5:

[0779] The server generates evidence using the generative AI model

[0780] Input: Acquired medical history data, diagnosis history data, submission destination information

[0781] How it works: The server inputs this data into the generative AI model and generates the optimal trail for the submission destination. By inputting a prompt sentence into the generative AI model, the appropriate trail format is obtained.

[0782] Output: The generated trail

[0783] Step 6:

[0784] The server automatically generates a comment explaining the patient's condition based on the emotional data.

[0785] Input: Emotion data, generated evidence

[0786] How it works: Based on the results of the emotion engine, the server uses a generative AI model to automatically generate a comment explaining the patient's condition while taking into consideration the user's emotions.

[0787] Output: Comment explaining the condition

[0788] Step 7:

[0789] The server merges the trail and comments and creates a merged file.

[0790] Input: Generated evidence, symptom description comment

[0791] How it works: The server aggregates these data and generates a single file in PDF or Word format, using an integrated file generation library for formatting.

[0792] Output: Unified file

[0793] Step 8:

[0794] The server saves the integrated file in the cloud and notifies the relevant submitter.

[0795] Input: merged file

[0796] How it works: The server saves the merged file to cloud storage, logs the save completion, and then notifies the relevant submitters via email or cloud notification system.

[0797] Output: Integrated file stored in the cloud, notification to recipient

[0798] Step 9:

[0799] The server notifies the user that the submission is complete.

[0800] Input: Submission completion information, user contact information

[0801] Behavior: The server will notify the user that submission is complete via SMS, email, etc.

[0802] Output: User notification

[0803] Step 10:

[0804] The user reviews the notification and provides additional information if necessary.

[0805] Input: Notification of submission completion

[0806] How it works: The user reviews the notification on their device and, if necessary, contacts the person who submitted it to provide additional information.

[0807] Output: Correspondence record with the recipient, additional information

[0808] These processing steps enable the generation and submission of quick and optimal evidence and commentary on the medical condition, while taking into consideration the user's feelings.

[0809] (Application example 2)

[0810] 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."

[0811] Conventional systems for managing medical history information and diagnostic results have had difficulty generating appropriate evidence and comments while taking user emotions into consideration. Furthermore, they have been unable to provide countermeasures for security-related issues that reflect user emotions, which can lead to a decline in user satisfaction. The present invention aims to solve these problems and provide information that takes user emotions into consideration.

[0812] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving medical history information, diagnosis results, and submission destination information entered by the user; means for saving the received information in a database; means for searching the database for medical history and diagnosis history based on the user's identification information; means for generating an optimal trail for the submission destination using artificial intelligence based on the search results; means for creating a file that integrates the generated trail and easy-to-understand comments about the medical condition; means for saving the integrated file in a cloud environment and notifying the relevant submission destination; means for notifying the user that submission is complete; means for recognizing the user's emotions using an emotion engine and adjusting the content of the generated trail and comments; and means for the user to input security-related issues and generate optimal countermeasures and emotional support comments based on the input content and emotions. This makes it possible to provide information that takes the user's emotions into consideration, thereby improving user satisfaction.

[0813] "Medical history information" refers to information related to illnesses and health that a user has experienced in the past and present.

[0814] A "diagnosis result" is a judgment or conclusion reached by a doctor or other expert regarding a particular medical condition or disease after assessing the user's health condition.

[0815] "Submission destination information" refers to information about the recipient or organization (for example, insurance company, pension service, worker's accident compensation insurance office, etc.) to which the user provides medical history information or diagnosis results.

[0816] A "database" is a system for storing, searching, and managing information received from users in an organized and efficient manner. It can also be stored in a cloud environment.

[0817] "Identification information" refers to information (such as an identifier or ID) that identifies a user and is used to link past records and diagnostic history.

[0818] "Generative Artificial Intelligence" is a system that utilizes machine learning and deep learning technologies to automatically generate optimal evidence and comments based on input data.

[0819] A "trail" is a formal document or report generated based on a user's medical history and diagnosis. It is used for insurance claims, pension applications, etc.

[0820] "Easy-to-understand comments" are medical explanations and advice that have been rewritten to avoid technical jargon and be easy for the general public to understand.

[0821] A "cloud environment" refers to the use of servers and storage provided over the Internet, and is an environment that allows for flexible data storage and processing.

[0822] An "emotion engine" is a system that analyzes input data such as voice and facial expressions to recognize the user's emotions.

[0823] "Security-related issues" are safety and security issues and concerns that users face in their daily lives and online.

[0824] A "solution" is a solution or course of action that is considered most appropriate for a particular problem or situation.

[0825] "Emotional support comments" are comments such as comforting, encouraging, and instructing that are created with consideration for the user's emotional state.

[0826] This invention is a system that efficiently manages medical history information and diagnosis results entered by users, recognizes the user's emotions using an emotion engine, and provides appropriate evidence and comments based on the results. Another object of this invention is to provide emotion-sensitive countermeasures and emotional support comments when a user enters a security-related issue.

[0827] System configuration

[0828] The system consists of the following components:

[0829] 1. User Device

[0830] A dedicated application is installed on devices such as smartphones and PCs, where users can enter information such as medical history, diagnosis results, and security-related issues.

[0831] It has a built-in emotion engine that analyzes the user's emotions using the camera and microphone.

[0832] 2. Server

[0833] It is deployed in a cloud environment and stores data, analyzes it, generates trails, and provides notifications.

[0834] The main software used includes a database system, a generative AI model, and an email notification system. Specific examples of use include the use of Google Cloud Platform and AWS (Amazon Web Services).

[0835] 3. Database

[0836] A system for efficiently storing and managing information received from users, such as Firebase Firestore or AWS DynamoDB.

[0837] 4. Generative AI Models

[0838] It is an artificial intelligence system that generates optimal evidence and comments based on user-entered information and sentiment data. For example, OpenAI's GPT-3 model is used.

[0839] Program processing description

[0840] The role of each component and its processing are explained below.

[0841] 1. User Device

[0842] Users enter their medical history, diagnosis results, and security-related issues through the application, and the emotion engine uses the camera and microphone to analyze the user's voice and facial expressions to capture emotional data.

[0843] The acquired input data and emotion data are encrypted using SSL / TLS and sent to the cloud server.

[0844] 2. Server

[0845] The server stores the received data in a database and searches for medical history and diagnostic history based on the user's identification information.

[0846] Based on the search results and current diagnostic results, the results are input into a generative AI model to generate optimal evidence and easy-to-understand comments.

[0847] In addition, for security-related issues, the system generates optimal countermeasures and emotional support comments based on emotional data analyzed by the emotion engine.

[0848] 3. Generative AI Models

[0849] The generated evidence and comments are temporarily saved in JSON format or similar.

[0850] It is then output as a PDF or Word document and stored in a cloud environment.

[0851] 4. Notification System

[0852] After the merged file is saved, email and cloud notifications are sent to relevant recipients, such as insurance companies and security companies.

[0853] A notification will also be sent to the user, who can view it in the application.

[0854] Specific examples

[0855] As a concrete example, the following prompt sentence is generated:

[0856] If a user enters a security-related problem such as "I lost my house keys," the system operates as follows:

[0857] 1. Information is input through the user's device, and the emotion engine recognizes the emotion "anxiety."

[0858] 2. The server stores user information and emotional data in a cloud database and uses a generative AI model to create optimal responses.

[0859] 3. A prompt like the following will be generated:

[0860] “The problem you entered is ‘I lost my house keys.’ Our system recognized ‘anxiety’ as your current emotion.

[0861] Best practice:

[0862] Please stay calm and double check the area around the entrance.

[0863] If you can't find it, contact your nearest police station.

[0864] Please follow the instructions below. The phone number for xxxx Police Station is xxxxx."

[0865] 4. The server saves the generated content as a PDF file in the cloud and notifies the user and necessary authorities.

[0866] In this way, the embodiments of the invention allow for the construction of a system that provides optimal information based on the user's input and emotions.

[0867] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0868] Step 1:

[0869] The user uses the device to input medical history information, diagnosis results, or security-related issues. The device receives the user's input data and simultaneously analyzes data from the camera and microphone using an emotion engine to recognize and acquire the user's emotions (e.g., anxiety, relief). The input data includes the name of the disease, the date of diagnosis, and details of the problem. The input data and emotion data are generated as output.

[0870] Step 2:

[0871] The device sends input data and emotion data to the cloud server. This data is encrypted and securely transferred using SSL / TLS. The output is the data received by the server.

[0872] Step 3:

[0873] The server stores the received input data and emotion data in a database system. At this time, the user's medical history and diagnosis history are searched from the database using the user's identification information as a key. The search results are then saved in temporary storage as output.

[0874] Step 4:

[0875] The server inputs the search results and current input data into a generative AI model to generate optimal evidence and comments. This generative AI model uses, for example, OpenAI's GPT-3. The search results and current input data are given as input, and the generated evidence and comments are obtained as output.

[0876] Step 5:

[0877] The server creates an integrated file (e.g., a PDF file) based on the generated evidence and comments. This file contains content adjusted to take into account the user's feelings. The generated evidence and comments are given as input, and the integrated file is obtained as output.

[0878] Step 6:

[0879] The server saves the integrated file in the cloud environment. After confirming that it has been saved, it sends a notification to the relevant recipients (e.g., insurance companies, pension institutions, security agencies). The storage path of the integrated file is given as input, and the notification is sent as output.

[0880] Step 7:

[0881] The server notifies the user that the integrated file has been saved and that the submission destination has been notified. The terminal receives this notification, and the process is completed when the user confirms it. Notification information is given as input, and a notification is sent to the user terminal as output.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] [Third embodiment]

[0886] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0887] 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.

[0888] 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).

[0889] 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.

[0890] 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.

[0891] 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).

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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."

[0898] This invention relates to a system for unifying and issuing evidence for medical information, etc. Specifically, it is a system that allows users to input medical history information and diagnosis results, and generate and submit optimal evidence based on that information. This system unifies evidence using the cloud, and provides information to the recipient quickly and accurately.

[0899] System Overview

[0900] This system consists of three main components: the user, the terminal, and the server. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information.

[0901] Program processing

[0902] User Input Processing

[0903] The terminal provides the user with an interface for entering medical history information (e.g., disease name, diagnosis results, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office). The entered data is sent to the server by pressing the confirm button.

[0904] Sending and storing information

[0905] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database. To confirm that the storage was successful, the server records the results in a log and sends a notification of the completion of storage to the terminal.

[0906] Medical and diagnostic history search

[0907] The server searches the cloud database for the user's medical history and diagnosis based on their ID, and the retrieved information is temporarily stored in a cache for later processing.

[0908] Starting Trail Generation

[0909] The server requests processing from the artificial intelligence generator based on the patient's medical history and diagnosis. The AI ​​generator automatically generates evidence in different formats for each recipient. For example, details of treatment and prognosis are sent to insurance companies, disability grades are sent to the Pension Service, and work-related details are sent to workers' compensation insurance offices.

[0910] Auto-generated comments

[0911] The server uses generative AI to automatically generate easy-to-understand comments about the patient's condition, which are written in simple language and avoid technical jargon.

[0912] Creation of an integrated file of evidence and comments

[0913] The server combines the generated evidence and medical condition comments into a single file, typically in PDF or Word format.

[0914] Save the merged file and notify the recipient

[0915] The server stores the integrated files in the cloud and notifies the relevant submitters via email or a cloud notification system.

[0916] User Notification

[0917] The server sends a notification to the user that the submission has been completed. The user can check the notification on their device and confirm that the submission has been successful.

[0918] Specific examples

[0919] For example, if user A enters "high blood pressure" as medical history information, "blood pressure management required" as diagnosis result, and "insurance company" as the submission destination, the system operates as follows.

[0920] 1. The user enters information through the terminal and sends it to the server.

[0921] 2. The server stores the information in a cloud database and searches for medical history and diagnostic history.

[0922] 3. The server uses generative AI to create an optimal trail for the insurance company.

[0923] 4. The server automatically generates easy-to-understand medical condition comments.

[0924] 5. The server combines the evidence and comments and generates a PDF file.

[0925] 6. The server saves the file to the cloud and notifies the insurance company.

[0926] 7. The server sends a notification to the user that the submission is complete.

[0927] This process saves users the trouble of creating complicated medical certificates, and allows recipients to receive the information quickly and accurately.

[0928] The processing flow will be explained below.

[0929] Step 1:

[0930] The terminal provides the user with an interface for inputting medical history information and submission destination information. The user inputs medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.).

[0931] Step 2:

[0932] The terminal will verify all the information entered by the user and provide a send button, which will send the entered data to the server.

[0933] Step 3:

[0934] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database, verifies that the storage is successful, and records the results in a log.

[0935] Step 4:

[0936] The server uses the user's ID to search the cloud database for medical history and diagnosis based on the saved user data, retrieves the search results, and temporarily stores them in a cache.

[0937] Step 5:

[0938] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which then generates the optimal evidence for each recipient. The AI ​​generator creates evidence including treatment details for insurance companies, disability grades for pension agencies, and work-related details for workers' compensation insurance offices.

[0939] Step 6:

[0940] The server uses artificial intelligence to automatically generate medical condition comments that are easy for anyone to understand. The generated comments are written in easy-to-understand language, avoiding technical jargon.

[0941] Step 7:

[0942] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[0943] Step 8:

[0944] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[0945] Step 9:

[0946] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[0947] Step 10:

[0948] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[0949] Step 11:

[0950] The user checks the notification content on the terminal and, if necessary, contacts the recipient and provides additional information.

[0951] Example 1

[0952] 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."

[0953] In conventional medical information systems, the process of users entering medical history information and diagnosis results, generating appropriate evidence based on that information, and submitting it was extremely cumbersome. Converting the information into a format appropriate for the recipient was also time-consuming and laborious. Furthermore, it was difficult to explain the condition in an easy-to-understand format, making the medical information submission process a significant burden for general users without specialized knowledge.

[0954] 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.

[0955] In this invention, the server includes means for receiving disease information, diagnosis results, and recipient information entered by the user, means for storing the received information in a storage device, means for searching past medical records from the storage device based on the user's identification information, means for generating an optimal trail for the recipient using generation artificial intelligence, means for creating a document that integrates the generated trail with an easy-to-understand explanation of the disease, means for storing the integrated document in data storage and notifying the relevant recipient, and means for notifying the user that submission is complete. This allows the user to simply enter medical history information and diagnosis results, automatically generate an optimal trail, and quickly submit it to the recipient. Furthermore, the explanation of the condition is written in simple language that avoids technical jargon, making the information available to the user and the recipient in an easy-to-understand format.

[0956] "User" means an individual or organization that uses the system to input and submit disease information and diagnosis results.

[0957] "Disease information" refers to information such as the name of the disease, symptoms, diagnosis results, diagnosis date, doctor's name, etc., entered by the user.

[0958] "Diagnostic results" refers to information indicating the results of a diagnosis made by a doctor or medical institution, and includes treatment plans, prognosis forecasts, and the like.

[0959] "Recipient information" refers to information about the recipient of the information provided, such as an insurance institution, a pension institution, or a workers' compensation insurance institution, designated by the user.

[0960] "Storage" refers to a database or other storage system for storing received information.

[0961] "Identification information" refers to information that uniquely identifies a user, such as a user ID or other identifier.

[0962] "Past medical records" include information such as the user's medical history, past medical history, and past diagnostic results.

[0963] "Generative AI" refers to an AI system that uses pre-trained algorithms to automatically generate appropriate evidence and comments based on user input.

[0964] "Evidence" refers to documents and data generated based on input information that prove the information to the recipient.

[0965] "Explanation" refers to a simple, non-technical explanation of the disease or diagnosis that accompanies the generated evidence.

[0966] "Document" refers to data in a file format that integrates evidence and explanations, and includes formats such as PDF and Word.

[0967] "Data Storage" refers to cloud storage or other storage systems for storing integrated documents.

[0968] "Notification" refers to a message or alert that notifies the user or recipient that data has been saved or submitted.

[0969] This invention is a system that allows users to input disease information and diagnosis results, and generate and submit optimal evidence based on that information. This system uses the cloud to unify evidence and provide information to recipients quickly and accurately. Each component of the system and its specific operation are described below.

[0970] System configuration

[0971] This system consists of three main components: users, terminals, and servers.

[0972] User: Enters disease information and diagnosis results and provides the information to the recipient.

[0973] Terminal: Provides an interface for users to enter and confirm information and sends data to the server.

[0974] Server: Stores the received data, generates evidence using a generative AI model, and notifies the recipient and user.

[0975] Hardware and software used

[0976] Device: Input device such as a computer, tablet, or smartphone.

[0977] Cloud databases: Cloud databases such as Amazon RDS, Google Cloud Firestore, etc.

[0978] Cache system: A cache system with fast access, such as Redis.

[0979] Generative AI models: Generative AI such as OpenAI GPT-3, Google BERT, etc.

[0980] Data storage: Cloud storage such as Amazon S3, Google Drive.

[0981] PDF generation libraries: Open source tools such as ReportLab, Apache POI, etc.

[0982] Specific operation of the system

[0983] 1. User Input Processing

[0984] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Taro Tanaka), and recipient information (e.g., insurance company).

[0985] The device displays a preview screen for the user to confirm and send the input data, and when the user presses the "Send" button, the input data is sent to the server.

[0986] 2. Transmission and storage of information

[0987] The server stores the disease information, diagnosis results, and provider information received from the user in a cloud database. If the storage is successful, the server records "Data storage completed" in the log file and sends a notification of the storage completion to the terminal.

[0988] 3. Medical and diagnostic history search

[0989] The server retrieves past medical records from a cloud database based on the user's identification information and temporarily stores the retrieved information in a cache that can be accessed quickly.

[0990] 4. Starting the trail generation

[0991] The server requests the generative AI model to generate a trail based on the medical history and diagnosis history. It then constructs a prompt and sends an API request. For example, it sends a prompt that reads, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company. Include the following information: details of treatment, prognosis."

[0992] 5. Automatic comment generation

[0993] The server sends an additional prompt to the generative AI model, asking it to generate an easy-to-understand disease description, such as "Please explain the condition in simple terms, avoiding technical jargon."

[0994] 6. Creating an integrated file of evidence and comments

[0995] The server combines the generated evidence and disease descriptions into a single combined file. Tools such as ReportLab or Apache POI are used to generate documents in PDF and Word formats.

[0996] 7. Saving the integrated file and notifying the recipient

[0997] The server stores the integrated file in cloud storage and sends an email or API request to the recipient to provide a download link for the file.

[0998] 8. Notice to Users

[0999] The server sends a notification to the user that submission has been completed, and the user checks the notification content on the terminal.

[1000] Specific examples

[1001] For example, if a user is diagnosed with "high blood pressure" and enters information to submit to an insurance company, the system operates in the following manner.

[1002] 1. The user enters and transmits information through the terminal.

[1003] 2. The server stores the information in a cloud database and searches past medical records.

[1004] 3. The server requests the generative AI model to generate evidence for the insurance company.

[1005] 4. The server automatically generates a simple explanation of the disease.

[1006] 5. The server combines the evidence and description and generates a PDF file.

[1007] 6. The server saves the file to the cloud and notifies the insurance company.

[1008] 7. The server sends a notification to the user that the submission is complete.

[1009] This system allows users and recipients to receive information quickly and accurately, significantly reducing the effort required to submit medical history information.

[1010] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1011] Step 1:

[1012] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Tanaka Taro), and recipient information (e.g., insurance company). The user inputs this information. When the user presses the "Send" button, the input data (disease information, diagnosis results, recipient information) is sent to the server.

[1013] Step 2:

[1014] The server temporarily loads the disease information, diagnosis results, and provider information received from the user into memory. It then saves the information to a cloud database (e.g., Amazon RDS, Google Cloud Firestore) using an INSERT query. If the save is successful, the server records "Data saving completed" in the log file and sends a save completion notification to the terminal. This notification includes the message "Data saving completed."

[1015] Step 3:

[1016] The server retrieves past medical records from a cloud database based on the user's identity, for example, using a SELECT query like "SELECT FROM medical_records WHERE user_id = '12345'", and temporarily stores the retrieved information in a fast-access cache (e.g., Redis) for quick access later.

[1017] Step 4:

[1018] The server sends a prompt to the generative artificial intelligence (generative AI model) to generate a trail. For example, it might send a prompt like, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company to which you provide the service. Include the following information: details of treatment, prognosis." The prompt is passed to the generative AI model, which processes the data for generating the trail. The generative AI model generates the trail data and returns it to the server in JSON format or another format.

[1019] Step 5:

[1020] The server sends an additional prompt to the generative AI model to generate an easy-to-understand disease explanation comment. For example, it sends a prompt such as, "Please explain the condition in simple terms, avoiding technical jargon." The generative AI model generates a disease explanation comment and returns it to the server.

[1021] Step 6:

[1022] The server combines the generated evidence and symptom description comments to create a single combined file (PDF or Word file). This is done using an open source PDF generation library (e.g., ReportLab, Apache POI). The server checks the format and content of the file, saves the created combined file to a data storage service (e.g., Amazon S3, Google Drive), and calls the API used to save the combined file to confirm that it was successfully saved.

[1023] Step 7:

[1024] The server retrieves the URL of the saved integrated file and notifies the recipient. The recipient is notified via email or API request, and the notification includes a link to download the file. For example, an insurance company receives a message saying, "A new trail has been generated. Please download it from the link below."

[1025] Step 8:

[1026] The server sends a notification to the user that the submission has been completed. The notification includes the message "Submission completed successfully," and the user can check the notification on their device. This lets the user know that the procedure has been completed.

[1027] (Application example 1)

[1028] 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."

[1029] Conventional medical information management systems have the ability to generate evidence based on medical history information and diagnosis results entered by users, but it is difficult to respond in real time when the user's health condition changes.In addition, there is a need for faster and more accurate generation of medical evidence by linking with health monitoring systems installed in vehicles.

[1030] 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.

[1031] In this invention, the server includes means for receiving health condition information, medical diagnosis results, and reporting destination information entered by the user, means for storing the received information in a database, means for searching the database for past health records and diagnosis history based on the user's ID, means for generating an optimal trail according to the reporting destination using artificial intelligence based on the search results, means for generating a medical trail in real time based on health data collected from sensors in the vehicle, means for creating a file that integrates the generated trail with easy-to-understand comments on the health condition, means for saving the integrated file in the cloud and notifying the relevant reporting destinations, and means for notifying the user that the report has been completed. This enables rapid and accurate generation and reporting of a medical trail even when the user's health condition changes.

[1032] "Health status information" refers to physiological data such as the user's heart rate, body temperature, and respiratory rate, as well as information about symptoms.

[1033] "Medical diagnosis results" refers to information indicating medical judgments, including the details of diagnoses and test results by doctors.

[1034] "Report destination information" is information about the organization or institution to which the generated medical trail should be sent, such as an insurance institution or medical institution.

[1035] "Generative artificial intelligence" is a system that uses artificial intelligence technology to automatically perform a specific task (in this case, generating medical trails).

[1036] "Past health records" are historical information about health conditions previously entered by a user or reported by a medical institution.

[1037] "Diagnostic history" is information that records the details of past medical diagnoses regarding the user.

[1038] "In-vehicle sensors" are devices placed inside self-driving vehicles that measure and collect the user's heart rate, body temperature, breathing rate, etc. in real time.

[1039] A "medical trail" is an official record of medical information generated based on the user's health condition and diagnosis results, and is to be submitted to the reporting destination.

[1040] A "generated trail" is a medical trail that conforms to a specific format and is created by generated artificial intelligence.

[1041] An "easy-to-understand comment on health status" is an explanatory text about the user's health status written in simple language, avoiding technical jargon.

[1042] An "integrated file" is a single file containing the generated medical records and easy-to-understand comments about the health condition.

[1043] The "cloud" is a distributed computer network environment that stores data and provides services over the Internet.

[1044] The "means for notifying the completion of the report" is a communication means for notifying the user that the generation and submission of the medical trail has been completed.

[1045] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[1046] overview

[1047] This invention is a system that monitors the user's health condition in real time inside an autonomous vehicle, generates a medical trail based on that information using artificial intelligence, and promptly transmits it to the required recipient. The system mainly consists of the user's device (such as a smartphone), sensors installed in the autonomous vehicle, a cloud server, and artificial intelligence.

[1048] System Configuration

[1049] Hardware

[1050] 1. Device: A device such as a smartphone or tablet that allows users to input health status information and medical diagnosis results.

[1051] 2. Sensors: Devices installed inside the autonomous vehicle to measure physiological data, such as heart rate monitors, thermometers, and breathing sensors.

[1052] 3. Server: A central processing unit located on the cloud that receives and stores data from users and generates medical trails through artificial intelligence.

[1053] software

[1054] 1. Database: A cloud database that stores user input information, medical history, and diagnostic history.

[1055] 2. Generative Artificial Intelligence: An AI system that generates a medical trail based on the user's health status information and medical diagnosis results, depending on the recipient.

[1056] 3. Cloud Notification System: A cloud-based communication system for sending medical trails to the submission destination and notifying users when submission is complete.

[1057] Processing flow

[1058] First, the user inputs their health information and medical diagnosis results using a device such as a smartphone. The input data is sent from the device to a cloud server and stored in a database. The server searches for past health records and diagnosis history based on the user's ID, and uses sensors in the autonomous vehicle to collect the latest health data as needed.

[1059] Based on the collected data, the server uses artificial intelligence to generate a medical trail according to the recipient (e.g., insurance institution, medical institution, etc.). This medical trail is created as an integrated file with user-friendly comments and stored in the cloud. The relevant recipient is then notified, and the user is also notified that submission has been completed.

[1060] Specific examples

[1061] For example, suppose a user suddenly becomes ill in a self-driving vehicle and the following measurements are collected by sensors:

[1062] Heart rate: 95

[1063] Body temperature: 37.8℃

[1064] Breathing rate: 25

[1065] This data is sent in real time to the cloud, where Generative Artificial Intelligence generates a medical trail based on the following prompts:

[1066] Prompt Sentence Examples

[1067] "Generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8°C, Respiratory rate: 25, User ID: user123"

[1068] The generated medical trail is submitted to insurance agencies and medical institutions, and users are notified of the submission status via their smartphones. This process allows users to receive prompt and accurate medical treatment.

[1069] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1070] Step 1:

[1071] The user uses the device to input health status information and medical diagnosis results, including heart rate, body temperature, respiratory rate, and doctor's diagnosis results. The device then transmits this data to a cloud server.

[1072] Step 2:

[1073] The server stores the health status information and medical diagnosis results received from the device in a database. The input is the health data including the user's ID, and the stored data will be used in later steps.

[1074] Step 3:

[1075] The server retrieves the past health records and diagnosis history from the database based on the user's ID. The user ID is given as input, and the past health records and diagnosis history are obtained as output.

[1076] Step 4:

[1077] The server uses sensors in the vehicle to monitor the user's real-time health data. The sensor data is input, and heart rate, body temperature, and respiratory rate are collected. This data is then sent to the cloud server.

[1078] Step 5:

[1079] The server uses artificial intelligence based on the collected data to generate the optimal medical trail for the recipient. This process uses the following prompt: "Please generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8℃, Respiratory rate: 25, User ID: user123." The generated trail is obtained as output.

[1080] Step 6:

[1081] The server integrates the generated evidence and easy-to-understand health status comments to create an integrated file. The input is the generated evidence and comments, and the output is an integrated file (e.g., PDF).

[1082] Step 7:

[1083] The server stores the integrated file in the cloud and notifies the relevant recipients. The input is the integrated file, and the output is notification information. Notifications are sent via email or a cloud notification system.

[1084] Step 8:

[1085] The server notifies the user that submission is complete. The input is notification completion information to the submission destination, and the output is a notification message to the user. The user can check this notification on their smartphone.

[1086] 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.

[1087] This invention relates to a system that efficiently manages medical history information and diagnosis results from users, recognizes the user's emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze the user's emotions and can adjust the content of evidence and comments based on the results.

[1088] System Overview

[1089] This system consists of four main components: the user, the terminal, the server, and the emotion engine. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information. Furthermore, the emotion engine is used to analyze the user's emotions and optimizes the trail and comments taking the results into account.

[1090] Program processing

[1091] User Input Processing

[1092] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office).The terminal also incorporates the necessary sensors and analysis algorithms to enable the emotion engine to recognize the user's emotions when entering information.

[1093] Sending and storing information

[1094] The terminal transmits the information entered by the user and the emotion data recognized by the emotion engine to the server. When the user presses the send button, the input data and the emotion data are sent together.

[1095] Data storage and retrieval

[1096] The server stores the medical history information, diagnosis results, submission destination information, and emotion data received from the user in a cloud database, confirms that the storage is successful, and records the results in a log.

[1097] The server searches the cloud database for the user's medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[1098] Starting Trail Generation

[1099] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which generates the optimal trail for each submission destination. The AI ​​generator creates trails in different formats for each submission destination.

[1100] Auto-generated comments

[1101] The server uses generative artificial intelligence to automatically generate understandable medical condition comments, which are tailored based on the user's emotions analyzed by the emotion engine.

[1102] Creation of an integrated file of evidence and comments

[1103] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[1104] Save the merged file and notify the recipient

[1105] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[1106] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[1107] User Notification

[1108] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[1109] Specific examples

[1110] For example, if user B enters "diabetes" as medical history information, "blood sugar management required" as diagnosis result, and "Pension Service" as submission destination, the system will operate as follows.

[1111] 1. The user inputs information through the terminal, and the emotion engine recognizes the user's emotions (e.g., anxiety, relief, etc.) at the time of input.

[1112] 2. The server stores the user's information and emotional data in a cloud database and searches for medical history and diagnosis history.

[1113] 3. The server uses generative AI to create optimal evidence for the pension agency.

[1114] 4. The server uses generative AI to automatically generate easy-to-understand medical commentary based on data from the emotion engine.

[1115] 5. The server merges the evidence and comments and generates a PDF file.

[1116] 6. The server saves the file to the cloud and notifies the Pension Service.

[1117] 7. The server sends a notification to the user that the submission is complete.

[1118] 8. The user checks the notification on the device and, if necessary, contacts the recipient and provides additional information.

[1119] This process allows users to utilize an emotionally sensitive trail, ensuring that recipients receive information quickly and appropriately.

[1120] The processing flow will be explained below.

[1121] Step 1:

[1122] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.). It also collects emotion data via devices such as sensors, microphones, and cameras, which are necessary for the emotion engine to recognize the emotion of the user when entering information.

[1123] Step 2:

[1124] The user enters medical history information and submission destination information through the terminal interface, and the terminal automatically recognizes the user's emotions. The user confirms the entered data and presses the send button.

[1125] Step 3:

[1126] The terminal transmits the medical history information, diagnosis results, submission destination information, and emotion data entered by the user to the server. The server checks the format of the transmitted data and displays a confirmation message to the user that transmission has been completed.

[1127] Step 4:

[1128] The server saves the data received from the user to the cloud database, and logs the successful completion of the saving process to confirm the completion of the saving.

[1129] Step 5:

[1130] The server searches the cloud database for medical history and diagnosis history based on the user's ID, retrieves the search results, and temporarily stores them in a cache. It then performs an error check on the retrieved data.

[1131] Step 6:

[1132] The server inputs the acquired medical history and diagnosis history, data received from the user, and emotional data into the artificial intelligence generator, which then generates the optimal trail for each submission destination. The generator AI automatically generates trails in different formats for each submission destination.

[1133] Step 7:

[1134] The server uses generative artificial intelligence to automatically generate understandable medical condition comments, which are adjusted based on the user's emotions analyzed by an emotion engine.

[1135] Step 8:

[1136] The server integrates the generated evidence and medical condition comments into a single integrated file (PDF or Word format), and performs error checking to ensure that the information contained in the file is complete.

[1137] Step 9:

[1138] The server saves the merged file to the cloud, logs the successful completion of the saving process, and confirms the result.

[1139] Step 10:

[1140] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, workers' compensation insurance offices, etc.) that the integrated file has been saved. Notifications are sent via email or a cloud notification system, and include an access link and any additional information required.

[1141] Step 11:

[1142] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[1143] Step 12:

[1144] The user uses the terminal to check the contents of the notification, and if necessary, contacts the recipient and provides additional information.

[1145] Examples:

[1146] For example, if User D enters "high blood pressure" as medical history information, "requires continuous blood pressure management" as diagnosis, and "insurance company" as the recipient, the system operates as follows:

[1147] 1. The user inputs information through the device, and the device uses an emotion engine to recognize the user's emotions at the time of input (e.g., anxiety, relief, joy, etc.).

[1148] 2. The user checks all the information and presses the send button.

[1149] 3. The device sends the user data and emotion data to the server.

[1150] 4. The server stores the data in a cloud database.

[1151] 5. The server searches the medical history and diagnostic history and caches the results.

[1152] 6. The server uses generative AI to create an optimal evidence trail for the insurance company.

[1153] 7. Based on the data from the emotion engine, the server automatically generates easy-to-understand comments about the patient's condition that avoid technical jargon.

[1154] 8. The server combines the evidence and comments and generates a PDF file.

[1155] 9. The server saves the file to the cloud and notifies the insurance company.

[1156] 10. The server sends a notification to the user that the submission is complete.

[1157] 11. The user checks the notification on the device and contacts the recipient if necessary.

[1158] This process allows users to provide information to recipients quickly and accurately with a highly efficient and sensitive trail.

[1159] Example 2

[1160] 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."

[1161] Conventional management systems for medical history information and diagnosis results have difficulty generating optimal evidence and commentary on medical conditions that take user emotions into account. Furthermore, the need to accommodate different formats for each submission destination requires a great deal of effort, which not only takes time and effort for users but also causes delays in information submission. This has led to issues such as an inability to adequately respond in situations where prompt and appropriate information provision is required.

[1162] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1163] In this invention, the server includes means for receiving medical history information, diagnosis results, and submission destination information entered by the user, means for saving the received information and emotion data in a database, means for searching the database for the medical history and diagnosis history based on the user's ID, means for generating an optimal trail for the submission destination based on the search results and taking the emotion data into consideration using a generative AI model, means for automatically generating an easy-to-understand comment explaining the condition based on the generated trail and the user's emotions, means for creating a file integrating the generated trail and the easy-to-understand comment explaining the condition, means for saving the integrated file in the cloud and notifying the relevant submission destination, and means for notifying the user of completion of submission. This enables the rapid generation and submission of an optimal trail and comment explaining the condition while taking the user's emotions into consideration.

[1164] "Medical history information" is a general term for medical-related information such as illnesses the user has had in the past, diagnosis history at medical institutions, and treatment details.

[1165] The "diagnosis result" is information such as the user's current health condition, disease name, and need for treatment, which is obtained based on a diagnosis by a doctor.

[1166] "Submission destination information" refers to information about the institution or organization (e.g., insurance institution, pension institution, labor insurance institution) to which the user submits medical history information or diagnosis results.

[1167] "Emotion data" is data indicating the user's emotional state that is acquired when the user's medical history information and diagnosis results are input, and is analyzed by the emotion engine.

[1168] An "emotion engine" is a set of algorithms and sensors that recognize emotions by analyzing the user's facial expressions, voice, etc., and outputs the user's emotional state as data.

[1169] "Generative AI model" refers to the advanced artificial intelligence (AI) algorithms used to optimize the evidence and medical description comments for each submission.

[1170] "Evidence" refers to the official report or medical certificate generated based on the user's medical history and diagnosis results, and is created in a format appropriate for the recipient.

[1171] The "symptom explanation comment" is a supplementary comment to explain the user's condition in an easy-to-understand manner, and is automatically generated while avoiding technical terms and taking into consideration the user's emotional state.

[1172] An "integrated file" is a file that centrally compiles the generated evidence and commentary on the medical condition, and is saved in a format such as PDF or Word.

[1173] "Cloud" refers to a virtual data center that stores and processes data via the Internet, and serves as a storage location for user information and generated files.

[1174] "Notification" is a communication method for informing a user or a submission destination of the completion of an important process, such as the completion of saving or submission of information.

[1175] This invention is a system that efficiently manages medical history information and diagnosis results from users, recognizes user emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze user emotions and can adjust the content of evidence and comments based on the results. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[1176] The device provides an interface for users to input medical history information and diagnosis results. The device is equipped with the necessary sensors and analysis algorithms to implement the emotion engine. For example, devices such as a camera and microphone can be used to analyze the user's facial expressions and voice and obtain emotion data.

[1177] The medical history information, diagnosis results, and submission destination information entered by the user are sent from the device to the server. The sent information is stored in a cloud database by the server. The server searches the database for medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[1178] Next, the server generates evidence using a generative AI model. The generative AI model receives the user's medical history and diagnosis results as input and creates the optimal evidence for each submission destination. The generated evidence is provided in a different format for each submission destination. For example, there is a format for insurance institutions, a format for pension institutions, a format for labor insurance institutions, etc.

[1179] Furthermore, the server automatically generates an easy-to-understand comment explaining the patient's condition using a generative AI model based on the user's emotions analyzed by the emotion engine. The emotion engine takes the user's emotions into consideration and generates a comment that provides a sense of security. This comment is then integrated with the generated evidence to create a single integrated file (e.g., PDF or Word format).

[1180] The integrated file is saved to the cloud by the server. The server records the successful save completion in a log and notifies the relevant submitting parties via email or the cloud notification system. A notification of the completion of submission is also sent to the user. This allows the user to check the notification on their own device and, if necessary, contact the submitting parties to provide additional information.

[1181] For example, if a user enters "diabetes" as medical history information, "blood sugar management required" as diagnosis, and "pension institution" as destination, the system operates as follows: The device enters the user's information, and the emotion engine recognizes the user's emotions at the time of entry (e.g., anxiety, relief, etc.). The server then stores the user's information and emotion data in a cloud database and searches for medical history and diagnosis history. A generative AI model is used to create an optimal evidence trail for the pension institution, and easy-to-understand medical condition comments are automatically generated based on the emotion engine data. The server combines the evidence trail and comments, generates a PDF file, stores it in the cloud, and notifies the pension institution. Finally, a notification that submission is complete is sent to the user.

[1182] Examples of input prompts for generative AI models include:

[1183] Please create a trail for User B to submit. The submission is to a pension institution, the medical history information is "Diabetes," and the diagnosis result is "Needs blood sugar management." The user's emotion is "Anxiety." Please add a polite comment to reassure the anxious user.

[1184] Based on this prompt, the generative AI model can generate optimal evidence for pension institutions and medical condition explanation comments that take into account the user's emotions.

[1185] The above is an embodiment of the present invention.

[1186] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1187] System program processing flow

[1188] Step 1:

[1189] The user enters medical history information, diagnosis results, and submission information

[1190] Input: User's medical history information (e.g., diabetes), diagnosis results (e.g., blood sugar management required), submission destination information (e.g., pension institution)

[1191] How it works: The user enters information using the interface provided by the device, which is equipped with a camera and microphone for analyzing the input form and emotions.

[1192] Output: Input data (medical history information, diagnosis results, submission destination information), emotion data

[1193] Step 2:

[1194] The device sends input data and emotion data to the server.

[1195] Input: Information entered by the user and emotional data recognized by the emotion engine

[1196] How it works: When the user presses the send button, the device encrypts the data and sends it to the server using a secure communication protocol (e.g., HTTPS).

[1197] Output: Data sent to the server

[1198] Step 3:

[1199] The server stores the received data in a cloud database.

[1200] Input: Medical history information, diagnosis results, submission destination information, emotional data sent from the device

[1201] Operation: The server saves the received data to the cloud database, verifies the success of the saving process, and records the result in a log.

[1202] Output: Data saved in the cloud database, log of saved data

[1203] Step 4:

[1204] The server searches the cloud database for medical history and diagnosis history based on the user ID.

[1205] Input: User ID, data stored in the cloud database

[1206] How it works: The server searches the cloud database using the user ID and executes SQL queries such as retrieving medical history and diagnostic history. The retrieved data is temporarily stored in a cache.

[1207] Output: Medical history data, diagnostic history data, cached data

[1208] Step 5:

[1209] The server generates evidence using the generative AI model

[1210] Input: Acquired medical history data, diagnosis history data, submission destination information

[1211] How it works: The server inputs this data into the generative AI model and generates the optimal trail for the submission destination. By inputting a prompt sentence into the generative AI model, the appropriate trail format is obtained.

[1212] Output: The generated trail

[1213] Step 6:

[1214] The server automatically generates a comment explaining the patient's condition based on the emotional data.

[1215] Input: Emotion data, generated evidence

[1216] How it works: Based on the results of the emotion engine, the server uses a generative AI model to automatically generate a comment explaining the patient's condition while taking into consideration the user's emotions.

[1217] Output: Comment explaining the condition

[1218] Step 7:

[1219] The server merges the trail and comments and creates a merged file.

[1220] Input: Generated evidence, symptom description comment

[1221] How it works: The server aggregates these data and generates a single file in PDF or Word format, using an integrated file generation library for formatting.

[1222] Output: Unified file

[1223] Step 8:

[1224] The server saves the integrated file in the cloud and notifies the relevant submitter.

[1225] Input: merged file

[1226] How it works: The server saves the merged file to cloud storage, logs the save completion, and then notifies the relevant submitters via email or cloud notification system.

[1227] Output: Integrated file stored in the cloud, notification to recipient

[1228] Step 9:

[1229] The server notifies the user that the submission is complete.

[1230] Input: Submission completion information, user contact information

[1231] Behavior: The server will notify the user that submission is complete via SMS, email, etc.

[1232] Output: User notification

[1233] Step 10:

[1234] The user reviews the notification and provides additional information if necessary.

[1235] Input: Notification of submission completion

[1236] How it works: The user reviews the notification on their device and, if necessary, contacts the person who submitted it to provide additional information.

[1237] Output: Correspondence record with the recipient, additional information

[1238] These processing steps enable the generation and submission of quick and optimal evidence and commentary on the medical condition, while taking into consideration the user's feelings.

[1239] (Application example 2)

[1240] 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."

[1241] Conventional systems for managing medical history information and diagnostic results have had difficulty generating appropriate evidence and comments while taking user emotions into consideration. Furthermore, they have been unable to provide countermeasures for security-related issues that reflect user emotions, which can lead to a decline in user satisfaction. The present invention aims to solve these problems and provide information that takes user emotions into consideration.

[1242] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving medical history information, diagnosis results, and submission destination information entered by the user; means for saving the received information in a database; means for searching the database for medical history and diagnosis history based on the user's identification information; means for generating an optimal trail for the submission destination using artificial intelligence based on the search results; means for creating a file that integrates the generated trail and easy-to-understand comments about the medical condition; means for saving the integrated file in a cloud environment and notifying the relevant submission destination; means for notifying the user that submission is complete; means for recognizing the user's emotions using an emotion engine and adjusting the content of the generated trail and comments; and means for the user to input security-related issues and generate optimal countermeasures and emotional support comments based on the input content and emotions. This makes it possible to provide information that takes the user's emotions into consideration, thereby improving user satisfaction.

[1243] "Medical history information" refers to information related to illnesses and health that a user has experienced in the past and present.

[1244] A "diagnosis result" is a judgment or conclusion reached by a doctor or other expert regarding a particular medical condition or disease after assessing the user's health condition.

[1245] "Submission destination information" refers to information about the recipient or organization (for example, insurance company, pension service, worker's accident compensation insurance office, etc.) to which the user provides medical history information or diagnosis results.

[1246] A "database" is a system for storing, searching, and managing information received from users in an organized and efficient manner. It can also be stored in a cloud environment.

[1247] "Identification information" refers to information (such as an identifier or ID) that identifies a user and is used to link past records and diagnostic history.

[1248] "Generative Artificial Intelligence" is a system that utilizes machine learning and deep learning technologies to automatically generate optimal evidence and comments based on input data.

[1249] A "trail" is a formal document or report generated based on a user's medical history and diagnosis. It is used for insurance claims, pension applications, etc.

[1250] "Easy-to-understand comments" are medical explanations and advice that have been rewritten to avoid technical jargon and be easy for the general public to understand.

[1251] A "cloud environment" refers to the use of servers and storage provided over the Internet, and is an environment that allows for flexible data storage and processing.

[1252] An "emotion engine" is a system that analyzes input data such as voice and facial expressions to recognize the user's emotions.

[1253] "Security-related issues" are safety and security issues and concerns that users face in their daily lives and online.

[1254] A "solution" is a solution or course of action that is considered most appropriate for a particular problem or situation.

[1255] "Emotional support comments" are comments such as comforting, encouraging, and instructing that are created with consideration for the user's emotional state.

[1256] This invention is a system that efficiently manages medical history information and diagnosis results entered by users, recognizes the user's emotions using an emotion engine, and provides appropriate evidence and comments based on the results. Another object of this invention is to provide emotion-sensitive countermeasures and emotional support comments when a user enters a security-related issue.

[1257] System configuration

[1258] The system consists of the following components:

[1259] 1. User Device

[1260] A dedicated application is installed on devices such as smartphones and PCs, where users can enter information such as medical history, diagnosis results, and security-related issues.

[1261] It has a built-in emotion engine that analyzes the user's emotions using the camera and microphone.

[1262] 2. Server

[1263] It is deployed in a cloud environment and stores data, analyzes it, generates trails, and provides notifications.

[1264] The main software used includes a database system, a generative AI model, and an email notification system. Specific examples of use include the use of Google Cloud Platform and AWS (Amazon Web Services).

[1265] 3. Database

[1266] A system for efficiently storing and managing information received from users, such as Firebase Firestore or AWS DynamoDB.

[1267] 4. Generative AI Models

[1268] It is an artificial intelligence system that generates optimal evidence and comments based on user-entered information and sentiment data. For example, OpenAI's GPT-3 model is used.

[1269] Program processing description

[1270] The role of each component and its processing are explained below.

[1271] 1. User Device

[1272] Users enter their medical history, diagnosis results, and security-related issues through the application, and the emotion engine uses the camera and microphone to analyze the user's voice and facial expressions to capture emotional data.

[1273] The acquired input data and emotion data are encrypted using SSL / TLS and sent to the cloud server.

[1274] 2. Server

[1275] The server stores the received data in a database and searches for medical history and diagnostic history based on the user's identification information.

[1276] Based on the search results and current diagnostic results, the results are input into a generative AI model to generate optimal evidence and easy-to-understand comments.

[1277] In addition, for security-related issues, the system generates optimal countermeasures and emotional support comments based on emotional data analyzed by the emotion engine.

[1278] 3. Generative AI Models

[1279] The generated evidence and comments are temporarily saved in JSON format or similar.

[1280] It is then output as a PDF or Word document and stored in a cloud environment.

[1281] 4. Notification System

[1282] After the merged file is saved, email and cloud notifications are sent to relevant recipients, such as insurance companies and security companies.

[1283] A notification will also be sent to the user, who can view it in the application.

[1284] Specific examples

[1285] As a concrete example, the following prompt sentence is generated:

[1286] If a user enters a security-related problem such as "I lost my house keys," the system operates as follows:

[1287] 1. Information is input through the user's device, and the emotion engine recognizes the emotion "anxiety."

[1288] 2. The server stores user information and emotional data in a cloud database and uses a generative AI model to create optimal responses.

[1289] 3. A prompt like the following will be generated:

[1290] “The problem you entered is ‘I lost my house keys.’ Our system recognized ‘anxiety’ as your current emotion.

[1291] Best practice:

[1292] Please stay calm and double check the area around the entrance.

[1293] If you can't find it, contact your nearest police station.

[1294] Please follow the instructions below. The phone number for xxxx Police Station is xxxxx."

[1295] 4. The server saves the generated content as a PDF file in the cloud and notifies the user and necessary authorities.

[1296] In this way, the embodiments of the invention allow for the construction of a system that provides optimal information based on the user's input and emotions.

[1297] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1298] Step 1:

[1299] The user uses the device to input medical history information, diagnosis results, or security-related issues. The device receives the user's input data and simultaneously analyzes data from the camera and microphone using an emotion engine to recognize and acquire the user's emotions (e.g., anxiety, relief). The input data includes the name of the disease, the date of diagnosis, and details of the problem. The input data and emotion data are generated as output.

[1300] Step 2:

[1301] The device sends input data and emotion data to the cloud server. This data is encrypted and securely transferred using SSL / TLS. The output is the data received by the server.

[1302] Step 3:

[1303] The server stores the received input data and emotion data in a database system. At this time, the user's medical history and diagnosis history are searched from the database using the user's identification information as a key. The search results are then saved in temporary storage as an output.

[1304] Step 4:

[1305] The server inputs the search results and current input data into a generative AI model to generate optimal evidence and comments. This generative AI model uses, for example, OpenAI's GPT-3. The search results and current input data are given as input, and the generated evidence and comments are obtained as output.

[1306] Step 5:

[1307] The server creates an integrated file (e.g., a PDF file) based on the generated evidence and comments. This file contains content tailored to the user's feelings. The generated evidence and comments are given as input, and the integrated file is obtained as output.

[1308] Step 6:

[1309] The server saves the integrated file in the cloud environment. After confirming that it has been saved, it sends a notification to the relevant recipients (e.g., insurance companies, pension institutions, security agencies). The storage path of the integrated file is given as input, and the notification is sent as output.

[1310] Step 7:

[1311] The server notifies the user that the integrated file has been saved and that the submission destination has been notified. The terminal receives this notification, and the process is completed when the user confirms it. Notification information is given as input, and a notification is sent to the user terminal as output.

[1312] 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.

[1313] 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.

[1314] 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.

[1315] [Fourth embodiment]

[1316] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1317] 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.

[1318] 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).

[1319] 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.

[1320] 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.

[1321] 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).

[1322] 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.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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."

[1329] This invention relates to a system for unifying and issuing evidence for medical information, etc. Specifically, it is a system that allows users to input medical history information and diagnosis results, and generate and submit optimal evidence based on that information. This system unifies evidence using the cloud, and provides information to the recipient quickly and accurately.

[1330] System Overview

[1331] This system consists of three main components: the user, the terminal, and the server. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information.

[1332] Program processing

[1333] User Input Processing

[1334] The terminal provides the user with an interface for entering medical history information (e.g., disease name, diagnosis results, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office). The entered data is sent to the server by pressing the confirm button.

[1335] Sending and storing information

[1336] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database. To confirm that the storage was successful, the server records the results in a log and sends a notification of the completion of storage to the terminal.

[1337] Medical and diagnostic history search

[1338] The server searches the cloud database for the user's medical history and diagnosis based on their ID, and the retrieved information is temporarily stored in a cache for later processing.

[1339] Starting Trail Generation

[1340] The server requests processing from the artificial intelligence generator based on the patient's medical history and diagnosis. The AI ​​generator automatically generates evidence in different formats for each recipient. For example, details of treatment and prognosis are sent to insurance companies, disability grades are sent to the Pension Service, and work-related details are sent to workers' compensation insurance offices.

[1341] Auto-generated comments

[1342] The server uses generative AI to automatically generate easy-to-understand comments about the patient's condition, which are written in simple language and avoid technical jargon.

[1343] Creation of an integrated file of evidence and comments

[1344] The server combines the generated evidence and medical condition comments into a single file, typically in PDF or Word format.

[1345] Save the merged file and notify the recipient

[1346] The server stores the integrated files in the cloud and notifies the relevant submitters via email or a cloud notification system.

[1347] User Notification

[1348] The server sends a notification to the user that the submission has been completed. The user can check the notification on their own device and confirm that the submission has been successful.

[1349] Specific examples

[1350] For example, if user A enters "high blood pressure" as medical history information, "blood pressure management required" as diagnosis result, and "insurance company" as the submission destination, the system operates as follows.

[1351] 1. The user enters information through the terminal and sends it to the server.

[1352] 2. The server stores the information in a cloud database and searches for medical history and diagnostic history.

[1353] 3. The server uses generative AI to create an optimal trail for the insurance company.

[1354] 4. The server automatically generates easy-to-understand medical condition comments.

[1355] 5. The server combines the evidence and comments and generates a PDF file.

[1356] 6. The server saves the file to the cloud and notifies the insurance company.

[1357] 7. The server sends a notification to the user that the submission is complete.

[1358] This process saves users the trouble of creating complicated medical certificates, and allows recipients to receive the information quickly and accurately.

[1359] The processing flow will be explained below.

[1360] Step 1:

[1361] The terminal provides the user with an interface for inputting medical history information and submission destination information. The user inputs medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.).

[1362] Step 2:

[1363] The terminal will verify all the information entered by the user and provide a send button, which will send the entered data to the server.

[1364] Step 3:

[1365] The server stores the medical history information, diagnosis results, and submission destination information received from the user in a cloud database, verifies that the storage is successful, and records the results in a log.

[1366] Step 4:

[1367] The server uses the user's ID to search the cloud database for medical history and diagnosis based on the saved user data, retrieves the search results, and temporarily stores them in a cache.

[1368] Step 5:

[1369] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which then generates the optimal evidence for each recipient. The AI ​​generator creates evidence including treatment details for insurance companies, disability grades for pension agencies, and work-related details for workers' compensation insurance offices.

[1370] Step 6:

[1371] The server uses artificial intelligence to automatically generate medical condition comments that are easy for anyone to understand. The generated comments are written in easy-to-understand language, avoiding technical jargon.

[1372] Step 7:

[1373] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[1374] Step 8:

[1375] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[1376] Step 9:

[1377] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[1378] Step 10:

[1379] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[1380] Step 11:

[1381] The user checks the notification content on the terminal and, if necessary, contacts the recipient and provides additional information.

[1382] Example 1

[1383] 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."

[1384] In conventional medical information systems, the process of users entering medical history information and diagnosis results, generating appropriate evidence based on that information, and submitting it was extremely cumbersome. Converting the data into a format appropriate for the recipient was also time-consuming and laborious. Furthermore, it was difficult to explain the condition in an easy-to-understand format, making the medical information submission process a significant burden for general users without specialized knowledge.

[1385] 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.

[1386] In this invention, the server includes means for receiving disease information, diagnosis results, and recipient information entered by the user, means for storing the received information in a storage device, means for searching past medical records from the storage device based on the user's identification information, means for generating an optimal trail for the recipient using artificial intelligence, means for creating a document that integrates the generated trail with an easy-to-understand explanation of the disease, means for storing the integrated document in data storage and notifying the relevant recipient, and means for notifying the user that submission is complete. This allows the user to easily input medical history information and diagnosis results, automatically generate an optimal trail, and quickly submit it to the recipient. Furthermore, the explanation of the condition is written in simple language that avoids technical jargon, making the information easy to understand for the user and the recipient.

[1387] "User" means an individual or organization that uses the system to input and submit disease information and diagnosis results.

[1388] "Disease information" refers to information such as the name of the disease, symptoms, diagnosis results, diagnosis date, doctor's name, etc., entered by the user.

[1389] "Diagnostic results" refers to information indicating the results of a diagnosis made by a doctor or medical institution, and includes treatment plans, prognosis forecasts, and the like.

[1390] "Recipient information" refers to information about the recipient of the information provided, such as an insurance institution, a pension institution, or a workers' compensation insurance institution, designated by the user.

[1391] "Storage" refers to a database or other storage system for storing received information.

[1392] "Identification information" refers to information that uniquely identifies a user, such as a user ID or other identifier.

[1393] "Past medical records" include information such as the user's medical history, past medical history, and past diagnostic results.

[1394] "Generative AI" refers to an AI system that uses pre-trained algorithms to automatically generate appropriate evidence and comments based on user input.

[1395] "Evidence" refers to documents and data generated based on input information that prove the information to the recipient.

[1396] "Explanation" refers to a simple, non-technical explanation of the disease or diagnosis that accompanies the generated evidence.

[1397] "Document" refers to data in a file format that integrates evidence and explanations, and includes formats such as PDF and Word.

[1398] "Data Storage" refers to cloud storage or other storage systems for storing integrated documents.

[1399] "Notification" refers to a message or alert that notifies the user or recipient that data has been saved or submitted.

[1400] This invention is a system that allows users to input disease information and diagnosis results, and generate and submit optimal evidence based on that information. This system uses the cloud to unify evidence and provide information to recipients quickly and accurately. Each component of the system and its specific operation are described below.

[1401] System configuration

[1402] This system consists of three main components: users, terminals, and servers.

[1403] User: Enters disease information and diagnosis results and provides the information to the recipient.

[1404] Terminal: Provides an interface for users to enter and confirm information and sends data to the server.

[1405] Server: Stores the received data, generates evidence using a generative AI model, and notifies the recipient and user.

[1406] Hardware and software used

[1407] Device: Input device such as a computer, tablet, or smartphone.

[1408] Cloud databases: Cloud databases such as Amazon RDS, Google Cloud Firestore, etc.

[1409] Cache system: A cache system with fast access, such as Redis.

[1410] Generative AI models: Generative AI such as OpenAI GPT-3, Google BERT, etc.

[1411] Data storage: Cloud storage such as Amazon S3, Google Drive.

[1412] PDF generation libraries: Open source tools such as ReportLab, Apache POI, etc.

[1413] Specific operation of the system

[1414] 1. User Input Processing

[1415] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Taro Tanaka), and recipient information (e.g., insurance company).

[1416] The device displays a preview screen for the user to confirm and send the input data, and when the user presses the "Send" button, the input data is sent to the server.

[1417] 2. Transmission and storage of information

[1418] The server stores the disease information, diagnosis results, and provider information received from the user in a cloud database. If the storage is successful, the server records "Data storage completed" in the log file and sends a notification of the storage completion to the terminal.

[1419] 3. Medical and diagnostic history search

[1420] The server retrieves past medical records from a cloud database based on the user's identification information and temporarily stores the retrieved information in a cache that can be accessed quickly.

[1421] 4. Starting the trail generation

[1422] The server requests the generative AI model to generate a trail based on the medical history and diagnosis history. It then constructs a prompt and sends an API request. For example, it sends a prompt that reads, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company. Include the following information: details of treatment, prognosis."

[1423] 5. Automatic comment generation

[1424] The server sends an additional prompt to the generative AI model, asking it to generate an easy-to-understand disease description, such as "Please explain the condition in simple terms, avoiding technical jargon."

[1425] 6. Creating an integrated file of evidence and comments

[1426] The server combines the generated evidence and disease descriptions into a single combined file. Tools such as ReportLab or Apache POI are used to generate documents in PDF and Word formats.

[1427] 7. Saving the integrated file and notifying the recipient

[1428] The server stores the integrated file in cloud storage and sends an email or API request to the recipient to provide a download link for the file.

[1429] 8. Notice to Users

[1430] The server sends a notification to the user that submission has been completed, and the user checks the notification content on the terminal.

[1431] Specific examples

[1432] For example, if a user is diagnosed with "high blood pressure" and enters information to submit to an insurance company, the system operates in the following manner.

[1433] 1. The user enters and transmits information through the terminal.

[1434] 2. The server stores the information in a cloud database and searches past medical records.

[1435] 3. The server requests the generative AI model to generate evidence for the insurance company.

[1436] 4. The server automatically generates a simple explanation of the disease.

[1437] 5. The server combines the evidence and description and generates a PDF file.

[1438] 6. The server saves the file to the cloud and notifies the insurance company.

[1439] 7. The server sends a notification to the user that the submission is complete.

[1440] This system allows users and recipients to receive information quickly and accurately, significantly reducing the effort required to submit medical history information.

[1441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1442] Step 1:

[1443] The terminal provides the user with an interface for inputting disease information (e.g., disease name, high blood pressure), diagnosis results (e.g., blood pressure management required), diagnosis date (e.g., October 1, 2023), doctor's name (e.g., Tanaka Taro), and recipient information (e.g., insurance company). The user inputs this information. When the user presses the "Send" button, the input data (disease information, diagnosis results, recipient information) is sent to the server.

[1444] Step 2:

[1445] The server temporarily loads the disease information, diagnosis results, and provider information received from the user into memory. It then saves the information to a cloud database (e.g., Amazon RDS, Google Cloud Firestore) using an INSERT query. If the save is successful, the server records "Data saving completed" in the log file and sends a save completion notification to the terminal. This notification includes the message "Data saving completed."

[1446] Step 3:

[1447] The server retrieves past medical records from a cloud database based on the user's identity, for example, using a SELECT query like "SELECT FROM medical_records WHERE user_id = '12345'", and temporarily stores the retrieved information in a fast-access cache (e.g., Redis) for quick access later.

[1448] Step 4:

[1449] The server sends a prompt to the generative artificial intelligence (generative AI model) to generate a trail. For example, it might send a prompt like, "Regarding the user's diagnosis of high blood pressure, please create an appropriate trail for the insurance company to which you provide the service. Include the following information: details of treatment, prognosis." The prompt is passed to the generative AI model, which processes the data for generating the trail. The generative AI model generates the trail data and returns it to the server in JSON format or another format.

[1450] Step 5:

[1451] The server sends an additional prompt to the generative AI model to generate an easy-to-understand disease explanation comment. For example, it sends a prompt such as, "Please explain the condition in simple terms, avoiding technical jargon." The generative AI model generates a disease explanation comment and returns it to the server.

[1452] Step 6:

[1453] The server combines the generated evidence and symptom description comments to create a single combined file (PDF or Word file). This is done using an open source PDF generation library (e.g., ReportLab, Apache POI). The server checks the format and content of the file, saves the created combined file to a data storage service (e.g., Amazon S3, Google Drive), and calls the API used to save the combined file to confirm that it was successfully saved.

[1454] Step 7:

[1455] The server retrieves the URL of the saved integrated file and notifies the recipient. The recipient is notified via email or API request, and the notification includes a link to download the file. For example, an insurance company receives a message saying, "A new trail has been generated. Please download it from the link below."

[1456] Step 8:

[1457] The server sends a notification to the user that the submission has been completed. The notification includes the message "Submission completed successfully," and the user can check the notification on their device. This lets the user know that the procedure has been completed.

[1458] (Application example 1)

[1459] 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."

[1460] Conventional medical information management systems have the ability to generate evidence based on medical history information and diagnosis results entered by users, but it is difficult to respond in real time when the user's health condition changes.In addition, there is a need for faster and more accurate generation of medical evidence by linking with health monitoring systems installed in vehicles.

[1461] 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.

[1462] In this invention, the server includes means for receiving health condition information, medical diagnosis results, and reporting destination information entered by the user, means for storing the received information in a database, means for searching the database for past health records and diagnosis history based on the user's ID, means for generating an optimal trail according to the reporting destination using artificial intelligence based on the search results, means for generating a medical trail in real time based on health data collected from sensors in the vehicle, means for creating a file that integrates the generated trail with easy-to-understand comments on the health condition, means for saving the integrated file in the cloud and notifying the relevant reporting destinations, and means for notifying the user that the report has been completed. This enables rapid and accurate generation and reporting of a medical trail even when the user's health condition changes.

[1463] "Health status information" refers to physiological data such as the user's heart rate, body temperature, and respiratory rate, as well as information about symptoms.

[1464] "Medical diagnosis results" refers to information indicating medical judgments, including the details of diagnoses and test results by doctors.

[1465] "Report destination information" is information about the organization or institution to which the generated medical trail should be sent, such as an insurance institution or medical institution.

[1466] "Generative artificial intelligence" is a system that uses artificial intelligence technology to automatically perform a specific task (in this case, generating medical trails).

[1467] "Past health records" are historical information about health conditions previously entered by a user or reported by a medical institution.

[1468] "Diagnostic history" is information that records the details of past medical diagnoses regarding the user.

[1469] "In-vehicle sensors" are devices placed inside self-driving vehicles that measure and collect the user's heart rate, body temperature, breathing rate, etc. in real time.

[1470] A "medical trail" is an official record of medical information generated based on the user's health condition and diagnosis results, and is to be submitted to the reporting destination.

[1471] A "generated trail" is a medical trail that conforms to a specific format and is created by generated artificial intelligence.

[1472] An "easy-to-understand comment on health status" is an explanatory text about the user's health status written in simple language, avoiding technical jargon.

[1473] An "integrated file" is a single file containing the generated medical records and easy-to-understand comments about the health condition.

[1474] The "cloud" is a distributed computer network environment that stores data and provides services over the Internet.

[1475] The "means for notifying the completion of the report" is a communication means for notifying the user that the generation and submission of the medical trail has been completed.

[1476] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below.

[1477] overview

[1478] This invention is a system that monitors the user's health condition in real time inside an autonomous vehicle, generates a medical trail based on that information using artificial intelligence, and promptly transmits it to the required recipient. The system mainly consists of the user's device (such as a smartphone), sensors installed in the autonomous vehicle, a cloud server, and artificial intelligence.

[1479] System Configuration

[1480] Hardware

[1481] 1. Device: A device such as a smartphone or tablet that allows users to input health status information and medical diagnosis results.

[1482] 2. Sensors: Devices installed inside the autonomous vehicle to measure physiological data, such as heart rate monitors, thermometers, and breathing sensors.

[1483] 3. Server: A central processing unit located on the cloud that receives and stores data from users and generates medical trails through artificial intelligence.

[1484] software

[1485] 1. Database: A cloud database that stores user input information, medical history, and diagnostic history.

[1486] 2. Generative Artificial Intelligence: An AI system that generates a medical trail based on the user's health status information and medical diagnosis results, depending on the recipient.

[1487] 3. Cloud Notification System: A cloud-based communication system for sending medical trails to the submission destination and notifying users when submission is complete.

[1488] Processing flow

[1489] First, the user inputs their health information and medical diagnosis results using a device such as a smartphone. The input data is sent from the device to a cloud server and stored in a database. The server searches for past health records and diagnosis history based on the user's ID, and uses sensors in the autonomous vehicle to collect the latest health data as needed.

[1490] Based on the collected data, the server uses artificial intelligence to generate a medical trail according to the recipient (e.g., insurance institution, medical institution, etc.). This medical trail is created as an integrated file with user-friendly comments and stored in the cloud. The relevant recipient is then notified, and the user is also notified that submission has been completed.

[1491] Specific examples

[1492] For example, suppose a user suddenly becomes ill in a self-driving vehicle and the following measurements are collected by sensors:

[1493] Heart rate: 95

[1494] Body temperature: 37.8℃

[1495] Breathing rate: 25

[1496] This data is sent in real time to the cloud, where Generative Artificial Intelligence generates a medical trail based on the following prompts:

[1497] Prompt Sentence Examples

[1498] "Generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8°C, Respiratory rate: 25, User ID: user123"

[1499] The generated medical trail is submitted to insurance agencies and medical institutions, and users are notified of the submission status via their smartphones. This process allows users to receive prompt and accurate medical treatment.

[1500] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1501] Step 1:

[1502] The user uses the device to input health status information and medical diagnosis results, including heart rate, body temperature, respiratory rate, and doctor's diagnosis results. The device then transmits this data to a cloud server.

[1503] Step 2:

[1504] The server stores the health status information and medical diagnosis results received from the device in a database. The input is the health data including the user's ID, and the stored data will be used in later steps.

[1505] Step 3:

[1506] The server retrieves the past health records and diagnosis history from the database based on the user's ID. The user ID is given as input, and the past health records and diagnosis history are obtained as output.

[1507] Step 4:

[1508] The server uses sensors in the vehicle to monitor the user's real-time health data. The sensor data is input, and heart rate, body temperature, and respiratory rate are collected. This data is then sent to the cloud server.

[1509] Step 5:

[1510] The server uses artificial intelligence based on the collected data to generate the optimal medical trail for the recipient. This process uses the following prompt: "Please generate a medical trail based on the following health data: Heart rate: 95, Body temperature: 37.8℃, Respiratory rate: 25, User ID: user123." The generated trail is obtained as output.

[1511] Step 6:

[1512] The server integrates the generated evidence and easy-to-understand health status comments to create an integrated file. The input is the generated evidence and comments, and the output is an integrated file (e.g., PDF).

[1513] Step 7:

[1514] The server stores the integrated file in the cloud and notifies the relevant recipients. The input is the integrated file, and the output is notification information. Notifications are sent via email or a cloud notification system.

[1515] Step 8:

[1516] The server notifies the user that submission is complete. The input is notification completion information to the submission destination, and the output is a notification message to the user. The user can check this notification on their smartphone.

[1517] 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.

[1518] This invention relates to a system that efficiently manages medical history information and diagnosis results from users, recognizes the user's emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze the user's emotions and can adjust the content of evidence and comments based on the results.

[1519] System Overview

[1520] This system consists of four main components: the user, the terminal, the server, and the emotion engine. The user inputs medical history information and diagnosis results through the terminal, and the server generates an optimal trail based on this information. Furthermore, the emotion engine is used to analyze the user's emotions and optimizes the trail and comments taking the results into account.

[1521] Program processing

[1522] User Input Processing

[1523] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office).The terminal also incorporates the necessary sensors and analysis algorithms so that the emotion engine can recognize the user's emotions when entering information.

[1524] Sending and storing information

[1525] The terminal transmits the information entered by the user and the emotion data recognized by the emotion engine to the server. When the user presses the send button, the input data and the emotion data are sent together.

[1526] Data storage and retrieval

[1527] The server stores the medical history information, diagnosis results, submission destination information, and emotion data received from the user in a cloud database, confirms that the storage is successful, and records the results in a log.

[1528] The server searches the cloud database for the user's medical history and diagnosis history based on the user's ID and temporarily stores the retrieved data in a cache.

[1529] Starting Trail Generation

[1530] The server inputs medical history and diagnostic history data into the artificial intelligence generator, which generates the optimal trail for each submission destination. The AI ​​generator creates trails in different formats for each submission destination.

[1531] Auto-generated comments

[1532] The server uses generative artificial intelligence to automatically generate understandable medical condition comments, which are tailored based on the user's emotions analyzed by the emotion engine.

[1533] Creation of an integrated file of evidence and comments

[1534] The server integrates the generated evidence and medical condition comments into a single integrated file, typically in PDF or Word format.

[1535] Save the merged file and notify the recipient

[1536] The server saves the merged file to the cloud, verifies that the save was successful, and logs the result.

[1537] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, and workers' compensation insurance offices) that the integrated file has been saved. Notifications are sent via email or a cloud notification system.

[1538] User Notification

[1539] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[1540] Specific examples

[1541] For example, if user B enters "diabetes" as medical history information, "blood sugar management required" as diagnosis result, and "Pension Service" as submission destination, the system will operate as follows.

[1542] 1. The user inputs information through the terminal, and the emotion engine recognizes the user's emotions (e.g., anxiety, relief, etc.) at the time of input.

[1543] 2. The server stores the user's information and emotional data in a cloud database and searches for medical history and diagnosis history.

[1544] 3. The server uses generative AI to create optimal evidence for the pension agency.

[1545] 4. The server uses generative AI to automatically generate easy-to-understand medical commentary based on data from the emotion engine.

[1546] 5. The server merges the evidence and comments and generates a PDF file.

[1547] 6. The server saves the file to the cloud and notifies the Pension Service.

[1548] 7. The server sends a notification to the user that the submission is complete.

[1549] 8. The user checks the notification on the device and, if necessary, contacts the recipient and provides additional information.

[1550] This process allows users to utilize an emotionally sensitive trail, ensuring that recipients receive information quickly and appropriately.

[1551] The processing flow will be explained below.

[1552] Step 1:

[1553] The terminal provides the user with an interface for inputting medical history information (e.g., disease name, diagnosis result, diagnosis date, doctor's name) and submission destination information (e.g., insurance company, pension service, workers' compensation insurance office, etc.). It also collects emotion data via devices such as sensors, microphones, and cameras, which are necessary for the emotion engine to recognize the emotion of the user when entering information.

[1554] Step 2:

[1555] The user enters medical history information and submission destination information through the terminal interface, and the terminal automatically recognizes the user's emotions. The user confirms the entered data and presses the send button.

[1556] Step 3:

[1557] The terminal transmits the medical history information, diagnosis results, submission destination information, and emotion data entered by the user to the server. The server checks the format of the transmitted data and displays a confirmation message to the user that transmission has been completed.

[1558] Step 4:

[1559] The server saves the data received from the user to the cloud database, and logs the successful completion of the saving process to confirm the completion of the saving.

[1560] Step 5:

[1561] The server searches the cloud database for medical history and diagnosis history based on the user's ID, retrieves the search results, and temporarily stores them in a cache. It then performs an error check on the retrieved data.

[1562] Step 6:

[1563] The server inputs the acquired medical history and diagnosis history, data received from the user, and emotional data into the artificial intelligence generator, which then generates the optimal trail for each submission destination. The generator AI automatically generates trails in different formats for each submission destination.

[1564] Step 7:

[1565] The server uses generative artificial intelligence to automatically generate understandable medical condition comments, which are adjusted based on the user's emotions analyzed by an emotion engine.

[1566] Step 8:

[1567] The server integrates the generated evidence and medical condition comments into a single integrated file (PDF or Word format), and performs error checking to ensure that the information contained in the file is complete.

[1568] Step 9:

[1569] The server saves the merged file to the cloud, logs the successful completion of the saving process, and confirms the result.

[1570] Step 10:

[1571] The server notifies the relevant submitting parties (e.g., insurance companies, pension agencies, workers' compensation insurance offices, etc.) that the integrated file has been saved. Notifications are sent via email or a cloud notification system, and include an access link and any additional information required.

[1572] Step 11:

[1573] The server also sends a notification to the user that the submission has been completed. The user can check the notification on their own device and understand that the submission has been completed successfully.

[1574] Step 12:

[1575] The user uses the terminal to check the contents of the notification, and if necessary, contacts the recipient and provides additional information.

[1576] Examples:

[1577] For example, if User D enters "high blood pressure" as medical history information, "requires continuous blood pressure management" as diagnosis, and "insurance company" as the recipient, the system operates as follows:

[1578] 1. The user inputs information through the device, and the device uses an emotion engine to recognize the user's emotions at the time of input (e.g., anxiety, relief, joy, etc.).

[1579] 2. The user checks all the information and presses the send button.

[1580] 3. The device sends the user data and emotion data to the server.

[1581] 4. The server stores the data in a cloud database.

[1582] 5. The server searches the medical history and diagnostic history and caches the results.

[1583] 6. The server uses generative AI to create an optimal trail for the insurance company.

[1584] 7. Based on the data from the emotion engine, the server automatically generates easy-to-understand comments about the patient's condition that avoid technical jargon.

[1585] 8. The server merges the evidence and comments and generates a PDF file.

[1586] 9. The server saves the file to the cloud and notifies the insurance company.

[1587] 10. The server sends a notification to the user that the submission is complete.

[1588] 11. The user checks the notification on the device and contacts the recipient if necessary.

[1589] This process allows users to provide information to recipients quickly and accurately with a highly efficient and sensitive trail.

[1590] Example 2

[1591] 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."

[1592] Conventional management systems for medical history information and diagnosis results have difficulty generating optimal evidence and commentary on medical conditions that take user emotions into account. Furthermore, the need to accommodate different formats for each submission destination requires a great deal of effort, which not only takes time and effort for users but also causes delays in information submission. This has led to issues such as an inability to adequately respond in situations where prompt and appropriate information provision is required.

[1593] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1594] In this invention, the server includes means for receiving medical history information, diagnosis results, and submission destination information entered by the user, means for saving the received information and emotion data in a database, means for searching the database for the medical history and diagnosis history based on the user's ID, means for generating an optimal trail for the submission destination based on the search results and taking the emotion data into consideration using a generative AI model, means for automatically generating an easy-to-understand comment explaining the condition based on the generated trail and the user's emotions, means for creating a file integrating the generated trail and the easy-to-understand comment explaining the condition, means for saving the integrated file in the cloud and notifying the relevant submission destination, and means for notifying the user of completion of submission. This enables the rapid generation and submission of an optimal trail and comment explaining the condition while taking the user's emotions into consideration.

[1595] "Medical history information" is a general term for medical-related information such as illnesses the user has had in the past, diagnosis history at medical institutions, and treatment details.

[1596] The "diagnosis result" is information such as the user's current health condition, disease name, and need for treatment, which is obtained based on a diagnosis by a doctor.

[1597] "Submission destination information" refers to information about the institution or organization (e.g., insurance institution, pension institution, labor insurance institution) to which the user submits medical history information or diagnosis results.

[1598] "Emotion data" is data indicating the user's emotional state that is acquired when the user's medical history information and diagnosis results are input, and is analyzed by the emotion engine.

[1599] An "emotion engine" is a set of algorithms and sensors that recognize emotions by analyzing the user's facial expressions, voice, etc., and outputs the user's emotional state as data.

[1600] "Generative AI model" refers to the advanced artificial intelligence (AI) algorithms used to optimize the evidence and medical description comments for each submission.

[1601] "Evidence" refers to the official report or medical certificate generated based on the user's medical history and diagnosis results, and is created in a format appropriate for the recipient.

[1602] The "symptom explanation comment" is a supplementary comment to explain the user's condition in an easy-to-understand manner, and is automatically generated while avoiding technical terms and taking into consideration the user's emotional state.

[1603] An "integrated file" is a file that centrally compiles the generated evidence and commentary on the medical condition, and is saved in a format such as PDF or Word.

[1604] "Cloud" refers to a virtual data center that stores and processes data via the Internet, and serves as a storage location for user information and generated files.

[1605] "Notification" is a communication method for informing a user or a submission destination of the completion of an important process, such as the completion of saving or submission of information.

[1606] This invention is a system that efficiently manages medical history information and diagnosis results from users, recognizes user emotions by combining it with an emotion engine, and provides appropriate information to the recipient. This system uses the emotion engine to analyze user emotions and can adjust the content of evidence and comments based on the results. This system consists of four main components: the user, the terminal, the server, and the emotion engine.

[1607] The device provides an interface for users to input medical history information and diagnosis results. The device is equipped with the necessary sensors and analysis algorithms to implement the emotion engine. For example, devices such as a camera and microphone can be used to analyze the user's facial expressions and voice and obtain emotion data.

[1608] The medical history information, diagnosis results, and submission destination information entered by the user are sent from the device to the server. The sent information is stored in a cloud database by the server. The server searches the database for medical history and diagnosis history based on the user's ID, and temporarily stores the retrieved data in a cache.

[1609] Next, the server generates evidence using a generative AI model. The generative AI model receives the user's medical history and diagnosis results as input and creates the optimal evidence for each submission destination. The generated evidence is provided in a different format for each submission destination. For example, there is a format for insurance institutions, a format for pension institutions, a format for labor insurance institutions, etc.

[1610] Furthermore, the server automatically generates an easy-to-understand comment explaining the patient's condition using a generative AI model based on the user's emotions analyzed by the emotion engine. The emotion engine takes the user's emotions into consideration and generates a comment that provides a sense of security. This comment is then integrated with the generated evidence to create a single integrated file (e.g., PDF or Word format).

[1611] The integrated file is saved to the cloud by the server. The server records the successful save completion in a log and notifies the relevant submitting parties via email or the cloud notification system. A notification of the completion of submission is also sent to the user. This allows the user to check the notification on their own device and, if necessary, contact the submitting parties to provide additional information.

[1612] For example, if a user enters "diabetes" as medical history information, "blood sugar management required" as diagnosis, and "pension institution" as destination, the system operates as follows: The device enters the user's information, and the emotion engine recognizes the user's emotions at the time of entry (e.g., anxiety, relief, etc.). The server then stores the user's information and emotion data in a cloud database and searches for medical history and diagnosis history. A generative AI model is used to create an optimal evidence trail for the pension institution, and easy-to-understand medical condition comments are automatically generated based on the emotion engine data. The server combines the evidence trail and comments, generates a PDF file, stores it in the cloud, and notifies the pension institution. Finally, a notification that submission is complete is sent to the user.

[1613] Examples of input prompts for generative AI models include:

[1614] Please create a trail for User B to submit. The submission is to a pension institution, the medical history information is "Diabetes," and the diagnosis result is "Needs blood sugar management." The user's emotion is "Anxiety." Please add a polite comment to reassure the anxious user.

[1615] Based on this prompt, the generative AI model can generate optimal evidence for pension institutions and medical condition explanation comments that take into account the user's emotions.

[1616] The above is an embodiment of the present invention.

[1617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1618] System program processing flow

[1619] Step 1:

[1620] The user enters medical history information, diagnosis results, and submission information

[1621] Input: User's medical history information (e.g., diabetes), diagnosis results (e.g., blood sugar management required), submission destination information (e.g., pension institution)

[1622] How it works: The user enters information using the interface provided by the device, which is equipped with a camera and microphone for analyzing the input form and emotions.

[1623] Output: Input data (medical history information, diagnosis results, submission destination information), emotion data

[1624] Step 2:

[1625] The device sends input data and emotion data to the server.

[1626] Input: Information entered by the user and emotional data recognized by the emotion engine

[1627] How it works: When the user presses the send button, the device encrypts the data and sends it to the server using a secure communication protocol (e.g., HTTPS).

[1628] Output: Data sent to the server

[1629] Step 3:

[1630] The server stores the received data in a cloud database.

[1631] Input: Medical history information, diagnosis results, submission destination information, emotional data sent from the device

[1632] Operation: The server saves the received data to the cloud database, verifies the success of the saving process, and records the result in a log.

[1633] Output: Data saved in the cloud database, log of saved data

[1634] Step 4:

[1635] The server searches the cloud database for medical history and diagnosis history based on the user ID.

[1636] Input: User ID, data stored in the cloud database

[1637] How it works: The server searches the cloud database using the user ID and executes SQL queries such as retrieving medical history and diagnostic history. The retrieved data is temporarily stored in a cache.

[1638] Output: Medical history data, diagnostic history data, cached data

[1639] Step 5:

[1640] The server generates evidence using the generative AI model

[1641] Input: Acquired medical history data, diagnosis history data, submission destination information

[1642] How it works: The server inputs this data into the generative AI model and generates the optimal trail for the submission destination. By inputting a prompt sentence into the generative AI model, the appropriate trail format is obtained.

[1643] Output: The generated trail

[1644] Step 6:

[1645] The server automatically generates a comment explaining the patient's condition based on the emotional data.

[1646] Input: Emotion data, generated evidence

[1647] How it works: Based on the results of the emotion engine, the server uses a generative AI model to automatically generate a comment explaining the patient's condition while taking into consideration the user's emotions.

[1648] Output: Comment explaining the condition

[1649] Step 7:

[1650] The server merges the trail and comments and creates a merged file.

[1651] Input: Generated evidence, symptom description comment

[1652] How it works: The server aggregates these data and generates a single file in PDF or Word format, using an integrated file generation library for formatting.

[1653] Output: Unified file

[1654] Step 8:

[1655] The server saves the integrated file in the cloud and notifies the relevant submitter.

[1656] Input: merged file

[1657] How it works: The server saves the merged file to cloud storage, logs the save completion, and then notifies the relevant submitters via email or cloud notification system.

[1658] Output: Integrated file stored in the cloud, notification to recipient

[1659] Step 9:

[1660] The server notifies the user that the submission is complete.

[1661] Input: Submission completion information, user contact information

[1662] Behavior: The server will notify the user that submission is complete via SMS, email, etc.

[1663] Output: User notification

[1664] Step 10:

[1665] The user reviews the notification and provides additional information if necessary.

[1666] Input: Notification of submission completion

[1667] How it works: The user reviews the notification on their device and, if necessary, contacts the person who submitted it to provide additional information.

[1668] Output: Correspondence record with the recipient, additional information

[1669] These processing steps enable the generation and submission of quick and optimal evidence and commentary on the medical condition, while taking into consideration the user's feelings.

[1670] (Application example 2)

[1671] 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."

[1672] Conventional systems for managing medical history information and diagnostic results have had difficulty generating appropriate evidence and comments while taking user emotions into consideration. Furthermore, they have been unable to provide countermeasures for security-related issues that reflect user emotions, which can lead to a decline in user satisfaction. The present invention aims to solve these problems and provide information that takes user emotions into consideration.

[1673] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for receiving medical history information, diagnosis results, and submission destination information entered by the user; means for saving the received information in a database; means for searching the database for medical history and diagnosis history based on the user's identification information; means for generating an optimal trail for the submission destination using artificial intelligence based on the search results; means for creating a file that integrates the generated trail and easy-to-understand comments about the medical condition; means for saving the integrated file in a cloud environment and notifying the relevant submission destination; means for notifying the user that submission is complete; means for recognizing the user's emotions using an emotion engine and adjusting the content of the generated trail and comments; and means for the user to input security-related issues and generate optimal countermeasures and emotional support comments based on the input content and emotions. This makes it possible to provide information that takes the user's emotions into consideration, thereby improving user satisfaction.

[1674] "Medical history information" refers to information related to illnesses and health that a user has experienced in the past and present.

[1675] A "diagnosis result" is a judgment or conclusion reached by a doctor or other expert regarding a particular medical condition or disease after assessing the user's health condition.

[1676] "Submission destination information" refers to information about the recipient or organization (for example, insurance company, pension service, worker's accident compensation insurance office, etc.) to which the user provides medical history information or diagnosis results.

[1677] A "database" is a system for storing, searching, and managing information received from users in an organized and efficient manner. It can also be stored in a cloud environment.

[1678] "Identification information" refers to information (such as an identifier or ID) that identifies a user and is used to link past records and diagnostic history.

[1679] "Generative Artificial Intelligence" is a system that utilizes machine learning and deep learning technologies to automatically generate optimal evidence and comments based on input data.

[1680] A "trail" is a formal document or report generated based on a user's medical history and diagnosis. It is used for insurance claims, pension applications, etc.

[1681] "Easy-to-understand comments" are medical explanations and advice that have been rewritten to avoid technical jargon and be easy for the general public to understand.

[1682] A "cloud environment" refers to the use of servers and storage provided over the Internet, and is an environment that allows for flexible data storage and processing.

[1683] An "emotion engine" is a system that analyzes input data such as voice and facial expressions to recognize the user's emotions.

[1684] "Security-related issues" are safety and security issues and concerns that users face in their daily lives and online.

[1685] A "solution" is a solution or course of action that is considered most appropriate for a particular problem or situation.

[1686] "Emotional support comments" are comments such as comforting, encouraging, and instructing that are created with consideration for the user's emotional state.

[1687] This invention is a system that efficiently manages medical history information and diagnosis results entered by users, recognizes the user's emotions using an emotion engine, and provides appropriate evidence and comments based on the results. Another object of this invention is to provide emotion-sensitive countermeasures and emotional support comments when a user enters a security-related issue.

[1688] System configuration

[1689] The system consists of the following components:

[1690] 1. User Device

[1691] A dedicated application is installed on devices such as smartphones and PCs, where users can enter information such as medical history, diagnosis results, and security-related issues.

[1692] It has a built-in emotion engine that analyzes the user's emotions using the camera and microphone.

[1693] 2. Server

[1694] It is deployed in a cloud environment and stores data, analyzes it, generates trails, and provides notifications.

[1695] The main software used includes a database system, a generative AI model, and an email notification system. Specific examples of use include the use of Google Cloud Platform and AWS (Amazon Web Services).

[1696] 3. Database

[1697] A system for efficiently storing and managing information received from users, such as Firebase Firestore or AWS DynamoDB.

[1698] 4. Generative AI Models

[1699] It is an artificial intelligence system that generates optimal evidence and comments based on user-entered information and sentiment data. For example, OpenAI's GPT-3 model is used.

[1700] Program processing description

[1701] The role of each component and its processing are explained below.

[1702] 1. User Device

[1703] Users enter their medical history, diagnosis results, and security-related issues through the application, and the emotion engine uses the camera and microphone to analyze the user's voice and facial expressions to capture emotional data.

[1704] The acquired input data and emotion data are encrypted using SSL / TLS and sent to the cloud server.

[1705] 2. Server

[1706] The server stores the received data in a database and searches for medical history and diagnostic history based on the user's identification information.

[1707] Based on the search results and current diagnostic results, the results are input into a generative AI model to generate optimal evidence and easy-to-understand comments.

[1708] In addition, for security-related issues, the system generates optimal countermeasures and emotional support comments based on emotional data analyzed by the emotion engine.

[1709] 3. Generative AI Models

[1710] The generated evidence and comments are temporarily saved in JSON format or similar.

[1711] It is then output as a PDF or Word document and stored in a cloud environment.

[1712] 4. Notification System

[1713] After the merged file is saved, email and cloud notifications are sent to relevant recipients, such as insurance companies and security companies.

[1714] A notification will also be sent to the user, who can view it in the application.

[1715] Specific examples

[1716] As a concrete example, the following prompt sentence is generated:

[1717] If a user enters a security-related problem such as "I lost my house keys," the system operates as follows:

[1718] 1. Information is input through the user's device, and the emotion engine recognizes the emotion "anxiety."

[1719] 2. The server stores user information and emotional data in a cloud database and uses a generative AI model to create optimal responses.

[1720] 3. A prompt like the following will be generated:

[1721] “The problem you entered is ‘I lost my house keys.’ Our system recognized ‘anxiety’ as your current emotion.

[1722] Best practice:

[1723] Please stay calm and double check the area around the entrance.

[1724] If you can't find it, contact your nearest police station.

[1725] Please follow the instructions below. The phone number for xxxx Police Station is xxxxx."

[1726] 4. The server saves the generated content as a PDF file in the cloud and notifies the user and necessary authorities.

[1727] In this way, the embodiments of the invention allow for the construction of a system that provides optimal information based on the user's input and emotions.

[1728] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1729] Step 1:

[1730] The user uses the device to input medical history information, diagnosis results, or security-related issues. The device receives the user's input data and simultaneously analyzes data from the camera and microphone using an emotion engine to recognize and acquire the user's emotions (e.g., anxiety, relief). The input data includes the name of the disease, the date of diagnosis, and details of the problem. The input data and emotion data are generated as output.

[1731] Step 2:

[1732] The device sends input data and emotion data to the cloud server. This data is encrypted and securely transferred using SSL / TLS. The output is the data received by the server.

[1733] Step 3:

[1734] The server stores the received input data and emotion data in a database system. At this time, the user's medical history and diagnosis history are searched from the database using the user's identification information as a key. The search results are then saved in temporary storage as an output.

[1735] Step 4:

[1736] The server inputs the search results and current input data into a generative AI model to generate optimal evidence and comments. This generative AI model uses, for example, OpenAI's GPT-3. The search results and current input data are given as input, and the generated evidence and comments are obtained as output.

[1737] Step 5:

[1738] The server creates an integrated file (e.g., a PDF file) based on the generated evidence and comments. This file contains content tailored to the user's feelings. The generated evidence and comments are given as input, and the integrated file is obtained as output.

[1739] Step 6:

[1740] The server saves the integrated file in the cloud environment. After confirming that it has been saved, it sends a notification to the relevant recipients (e.g., insurance companies, pension institutions, security agencies). The storage path of the integrated file is given as input, and the notification is sent as output.

[1741] Step 7:

[1742] The server notifies the user that the integrated file has been saved and that the submission destination has been notified. The terminal receives this notification, and the process is completed when the user confirms it. Notification information is given as input, and a notification is sent to the user terminal as output.

[1743] 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.

[1744] 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.

[1745] 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.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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).

[1750] 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.

[1751] 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."

[1752] 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.

[1753] 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).

[1754] 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.

[1755] 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 sp...

Claims

1. means for receiving medical history information, diagnosis results, and submission destination information entered by a user; a means for storing the received information in a database; and A means for searching the database for medical history and diagnostic history based on the user's ID; A means for generating an optimal trail according to the submission destination using artificial intelligence based on the search results; A means of creating a file that integrates the generated evidence with easy-to-understand comments on the pathology; A means of storing the consolidated file in the cloud and notifying the relevant submission destinations; and means for notifying the user of completion of the submission.

2. 2. The system according to claim 1, wherein the generated evidence is provided in different formats depending on the destination, such as an insurance company, a pension service, or a workers' compensation insurance office.

3. 2. The system according to claim 1, further comprising means for automatically generating, by means of artificial intelligence, an easily understandable comment explaining the condition, while avoiding technical terms as much as possible.

Images