system

Abstract

Provide a system. [Solution] A medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language; a terminal means for receiving medical consultation details input by a user; a server means for transmitting the medical consultation content to the generative artificial intelligence and returning a generated response to the terminal means; A health management data analysis means for collecting data from a health management app and analyzing it using generative artificial intelligence; A means for providing the results of the analysis to users; A system including:

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] Due to an aging society and the spread of infectious diseases, the number of patients who find it difficult to visit hospitals is increasing. This could lead to an increase in patients unable to receive appropriate medical care, widening health disparities. In addition, the shortage of medical professionals and their increasing burden are becoming problems, necessitating the establishment of efficient medical care delivery methods. Furthermore, when patients are unfamiliar with specialized terminology and technology, medical consultations and health management can sometimes be difficult to carry out smoothly. This invention aims to solve these issues, realize equality in medical care, and provide an environment where patients can receive medical support with peace of mind. [Means for solving the problem]

[0005] The present invention provides a system that includes a medical consultation chatbot that utilizes generative artificial intelligence to respond in natural language, a terminal that receives medical consultation content input from a user, a server that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the terminal, a health management data analysis that collects data from a health management app and analyzes it using the generative artificial intelligence, and a means for providing the analysis results to the user. This system allows patients with mobility issues and users unfamiliar with medical consultations to receive appropriate medical support. Furthermore, the system can continuously improve its services through feedback, allowing it to continue providing support tailored to user needs.

[0006] "Generative AI" refers to an AI model that generates natural language in response to user input, such as technology like GPT.

[0007] "Medical consultation chatbot means" refers to a function that provides an interface for users to make medical consultations and uses generative artificial intelligence to respond to users' questions in natural language.

[0008] "Terminal means" refers to a device (e.g., smartphone, tablet, PC) that allows a user to access the system via the Internet and conduct medical consultations and exchange various information.

[0009] "Server means" refers to a computer system that operates generative artificial intelligence, processes the contents of medical consultations from users, generates responses, and sends them back to terminal means.

[0010] "Health management data analysis means" refers to a function that analyzes data collected from health management applications and provides information about the user's health status and recommended actions using generative artificial intelligence.

[0011] "Feedback means" refers to a function for collecting feedback provided by users and using it to improve the system. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] This invention is a medical consultation chatbot system that uses generative artificial intelligence, and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[0034] The system includes the following means:

[0035] 1. User Registration

[0036] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[0037] (2) The user enters their username, password, and email address into the form and submits the registration information from their device.

[0038] (3) The server processes the received user information, hashes the password, and stores it in the database.

[0039] 2. Interacting with a chatbot

[0040] (1) The user launches the chatbot from their device and begins a medical consultation.

[0041] (2) The terminal sends the questions and inquiries entered by the user to the server.

[0042] (3) The server uses generative artificial intelligence to analyze the user message and generate an appropriate response.

[0043] (4) The server sends the generated response to the terminal, which displays the response to the user.

[0044] Examples:

[0045] When a user types, "I haven't been sleeping well lately. What should I do?", the generative AI responds, "Reviewing your sleep environment and increasing your daytime activity may be effective. If necessary, I recommend consulting a doctor."

[0046] 3. Health Management Data Analysis

[0047] (1) The user allows the health management app to link with the health support AI system.

[0048] (2) The device sends the data collected from the health management app to the server.

[0049] (3) The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions.

[0050] (4) The device notifies the user of the analysis results, and the user manages their health based on the results.

[0051] Examples:

[0052] It analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[0053] 4. Feedback Collection

[0054] (1) After using the system, the user fills out the provided feedback form on the terminal.

[0055] (2) The device sends the user's feedback to the server.

[0056] (3) The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[0057] Examples:

[0058] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in a database and uses it to improve the system in the future.

[0059] In this way, the health support AI system provides efficient and safe medical consultations and health management support by linking users, devices, and servers, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[0060] The processing flow will be explained below.

[0061] Detailed Process Steps of the Detailed Description

[0062] User Registration

[0063] Step 1:

[0064] The user launches the health support AI system app on their device and accesses the membership registration form.

[0065] Step 2:

[0066] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[0067] Step 3:

[0068] The server analyzes the received user information and hashes the password for security purposes.

[0069] Step 4:

[0070] The server stores the hashed passwords and other user data in a database.

[0071] Interacting with a chatbot

[0072] Step 1:

[0073] The user launches the chatbot from their device and accesses the screen for medical consultation.

[0074] Step 2:

[0075] The device sends the questions and inquiries entered by the user to the server.

[0076] Step 3:

[0077] The server passes the received user message to a generative artificial intelligence, which generates an appropriate response.

[0078] Step 4:

[0079] The server receives the generated response and sends it back to the terminal.

[0080] Step 5:

[0081] The terminal displays the generated response to the user.

[0082] Examples:

[0083] When a user types, "I haven't been sleeping well lately. What should I do?", the server uses generative artificial intelligence to generate a response: "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[0084] Health management data analysis

[0085] Step 1:

[0086] The user allows the health management app to link with the health support AI system.

[0087] Step 2:

[0088] The device sends the data collected from the health management app to the server.

[0089] Step 3:

[0090] The server passes the received health data to generative artificial intelligence, which then analyzes the data.

[0091] Step 4:

[0092] The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[0093] Step 5:

[0094] The device will notify the user of the analysis results.

[0095] Examples:

[0096] It analyzes heart rate and sleep data collected from health management apps and generates feedback to notify the user, such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[0097] Feedback collection

[0098] Step 1:

[0099] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[0100] Step 2:

[0101] The terminal transmits the input feedback to the server.

[0102] Step 3:

[0103] The server stores the received feedback data in a database.

[0104] Step 4:

[0105] The server periodically extracts the feedback data from the database and performs analysis.

[0106] Step 5:

[0107] The server will improve the system based on the results of the feedback analysis.

[0108] Examples:

[0109] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this information in a database and references it at a future improvement meeting to help improve the system.

[0110] In this way, this system efficiently performs a series of processes from user registration to medical consultation, health management data analysis, and feedback collection, providing comprehensive medical support to users.

[0111] Example 1

[0112] 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."

[0113] Modern healthcare systems require the provision of appropriate medical support to patients with mobility issues and users unfamiliar with medical consultations. However, existing medical consultation systems and health management apps face numerous challenges in terms of user registration, usability of dialogue interfaces, and feedback collection and utilization. For example, it is difficult to provide prompt and accurate medical advice to patients who have difficulty visiting hospitals. Furthermore, the system for providing user feedback is inadequate, slowing down service improvement. Furthermore, the functionality for effectively analyzing health data and recommending appropriate actions to users is limited. These challenges ultimately increase the risk of patients neglecting their health management.

[0114] 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.

[0115] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an information processing device means that receives the medical consultation content entered by the user, a server means that transmits the medical consultation content to the generative artificial intelligence and returns the generated response to the information processing device means, a health management data analysis means that collects data from the health management app and analyzes it using the generative artificial intelligence, a feedback means that provides the analysis results to the user, a user registration means that receives user registration information, hashes the password, and stores it in a database, and a feedback collection means that receives feedback after using the system, stores it in a database, and periodically analyzes it. This allows users to easily register and receive medical consultations in a natural, interactive format through the generative artificial intelligence, and manage their health based on the provided feedback. The system also accumulates and periodically analyzes user feedback, thereby improving the quality of its services.

[0116] "Generative AI" is an artificial intelligence technology for generating responses in natural language, and refers to algorithms that primarily use deep learning to generate appropriate outputs for various inputs.

[0117] "Medical consultation chatbot means" refers to a method and apparatus that uses generative artificial intelligence to automatically generate responses to a user's medical consultation.

[0118] "Information processing device means" refers to a device or application that has the function of receiving input from a user and transmitting data to a server via a communications network.

[0119] The term "server means" refers to a server device that receives input data from a user, generates a response using generative artificial intelligence, and returns the response to the information processing device means.

[0120] "Health management data analysis means" refers to a means for analyzing data collected from a health management app, and refers to a function that uses generative artificial intelligence to evaluate the user's health condition and recommend appropriate actions.

[0121] "Feedback means" refers to a means for providing responses and analysis results generated by generative artificial intelligence to users.

[0122] "User registration means" refers to a device or program that has the function of collecting information required when a user registers with the system, hashing the password, and storing the information in a database.

[0123] "Feedback collection means" refers to a means that has the function of receiving feedback from users after using the system, storing it in a database, and periodically analyzing it.

[0124] The present invention is a medical consultation chatbot system that uses generative artificial intelligence and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations. This invention includes the following means.

[0125] 1. User Registration Method

[0126] A user launches the Health Support AI System application using a device (e.g., PC, smartphone, tablet) and accesses the membership registration form. The user enters a username, password, and email address in the form and taps the submit button, sending the registration information from the device to the server. The server receives the received user information, hashes the password, and stores it in a database (e.g., MySQL (registered trademark), PostgreSQL).

[0127] 2. Medical consultation chatbot means

[0128] The user activates the chatbot function from their device to begin a medical consultation. The device then sends the question and consultation details entered by the user to the server. The server uses generative AI (e.g., GPT-3 (registered trademark), ChatGPT (registered trademark)) to analyze the user message and generate an appropriate response. The server then sends the generated response to the device, which displays the response to the user. For example, if a user enters, "I've been having trouble sleeping lately. What should I do?", the server will use a generative AI model to respond, "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, I recommend consulting a doctor."

[0129] 3. Health management data analysis tools

[0130] The user allows a health management app (e.g., Apple Health, GOOGLE FI (registered trademark)) to link with the health support AI system. The device sends data collected from the health management app to a server. The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions. The device notifies the user of the analysis results, and the user manages their health based on the results. As a specific example, the server analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[0131] 4. Feedback methods

[0132] After using the system, users access the provided feedback form and enter their feedback. The terminal then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system. For example, if a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in the database and uses it for future system improvements.

[0133] In this way, the health support AI system of the present invention provides efficient and safe medical consultations and health management support through collaboration between users, terminals, and servers. This system allows patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] User registration process

[0136] Step 1:

[0137] The user launches the health support AI system application on their device. The app is launched by tapping the app icon on the device's home screen. The input is "tapping the app icon" and the output is "launching the app."

[0138] Step 2:

[0139] The user taps the registration button in the application to access the registration form. The form displays fields for entering a username, password, and email address. The input is "tap the registration button" and the output is "display the registration form."

[0140] Step 3:

[0141] The user enters the required information into the form and taps the submit button. The device sends the entered username, password, and email address to the server. The input is "user registration information" and the output is "send information."

[0142] Step 4:

[0143] The server receives the user information from the terminal and hashes the password. Here, the password is securely hashed using Python's bcrypt library. The input is "user registration information" and the output is "hashed password."

[0144] Step 5:

[0145] The server stores the hashed password and other user information in a database by generating an SQL query to insert the information into the appropriate columns. The input is the hashed password and user information, and the output is to store it in the database.

[0146] Medical consultation chatbot processing flow

[0147] Step 1:

[0148] The user activates the chatbot function on their device and starts a medical consultation by tapping the "medical consultation" button in the app. The input is "tapping the medical consultation button" and the output is "activating the chatbot."

[0149] Step 2:

[0150] The user enters a question or request on the chat screen and taps the send button. The device then sends this information to the server. The input is the user's question, and the output is a message sent to the server.

[0151] Step 3:

[0152] The server inputs the question sent by the user as a prompt to a generative AI (e.g., GPT-3). The generative AI analyzes the user message and generates an appropriate response. The input is the "user's question" and the output is the "generated response."

[0153] Step 4:

[0154] The server sends the generated response to the terminal, which then displays it to the user. Specifically, the AI's response message is displayed on the chat screen. The input is the "generated response" and the output is "display to the user."

[0155] Health management data analysis process flow

[0156] Step 1:

[0157] The user allows the health management app to link with the health support AI system. They tap the "Link" button on the app settings screen and grant the necessary access permissions. The input is "tap the link button" and the output is "allow link settings."

[0158] Step 2:

[0159] The device sends data collected from the health management app to the server. Collected data includes the number of steps, heart rate, sleep data, etc. The input is "health management data" and the output is "transmission to the server."

[0160] Step 3:

[0161] The server analyzes the collected health data using generative artificial intelligence. Specifically, it processes the data using Python libraries (e.g., Pandas) and machine learning models. The input is "health management data" and the output is "analysis results."

[0162] Step 4:

[0163] The server notifies the user of the analysis results, which are then displayed on the device. The analysis results include an assessment of the user's health status and recommended actions. The input is the "analysis results" and the output is "notification to the user." For example, the message might read, "Recent data suggests that your stress level is increasing. Try to spend more time relaxing."

[0164] Feedback collection process flow

[0165] Step 1:

[0166] After using the system, users access the provided feedback form and enter their impressions and suggestions for improvement. The input is "feedback input content" and the output is "input to the feedback form."

[0167] Step 2:

[0168] The terminal sends the feedback content entered by the user to the server. The input is "feedback content" and the output is "transmission to server."

[0169] Step 3:

[0170] The server saves the received feedback data in a database. Specifically, it generates an SQL query and inserts it into the database. The input is "feedback content" and the output is "saving to database."

[0171] Step 4:

[0172] The server periodically analyzes the accumulated feedback data and uses it to improve the system. It uses Python data analysis tools (e.g., Pandas, Matplotlib). The input is "feedback data" and the output is "analysis results and system improvement proposals."

[0173] In this way, the health support AI system of the present invention provides medical consultation and health management support efficiently and safely through a series of processing steps in which the user, terminal, and server work together.

[0174] (Application example 1)

[0175] 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."

[0176] The present invention relates to a system that monitors the health status of employees in real time and provides appropriate healthcare advice. Its purpose is to support worker health management and abnormality detection in order to improve work efficiency, particularly in work environments such as factories. Conventional health management methods have the problem of ineffective collection and analysis of health data, leading to inadequate management of worker health.

[0177] 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.

[0178] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, a terminal means that receives medical consultation content input from a user, a means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the terminal means, a health management data analysis means that collects data from a health management app and analyzes it with the generative artificial intelligence, a means that provides the user with the analysis results, a means that acquires health data from a wearable device worn by a worker and analyzes it with the generative artificial intelligence, and a means that provides the worker with health advice based on the analysis results. This makes it possible to monitor the health status of workers in real time and provide appropriate health care advice.

[0179] "Generative AI" is an AI technology that has the ability to automatically generate appropriate responses in natural language based on user input.

[0180] A "medical consultation chatbot" is a system that uses generative artificial intelligence to provide appropriate responses in natural language to users' medical questions and inquiries.

[0181] "Terminal means" refers to a means by which a user inputs and transmits medical consultation details using an input device (e.g., smartphone, tablet, computer, etc.).

[0182] The "server means" is a central management system for transmitting the medical consultation content sent by the user to the generative artificial intelligence and returning the generated response to the user's terminal.

[0183] The "health management data analysis means" is a system that uses generative artificial intelligence to analyze data collected from health management apps, evaluate the user's health status, and generate recommended actions and advice.

[0184] "Providing means" refers to the means for notifying or displaying to the user the analysis results and responses generated by the generative artificial intelligence.

[0185] A "wearable device" is a device (e.g., smartwatch, fitness tracker, etc.) that can be worn by a user at all times and is a device for collecting health data (e.g., heart rate, number of steps, sleep data, etc.).

[0186] "Healthcare advice" refers to recommendations and advice regarding health management provided to the user based on the analysis results obtained by the health data analysis means.

[0187] The system of the present invention aims to improve workers' work efficiency and support their health management by monitoring the health status of workers in working environments such as factories in real time and providing appropriate health care advice using generative artificial intelligence.

[0188] The system consists of the following components:

[0189] 1. Medical consultation chatbot using generative artificial intelligence:

[0190] Users input questions about their health in natural language. The generative AI analyzes the input and generates appropriate responses. These responses are provided to the user via a terminal.

[0191] 2. Terminal means:

[0192] The user inputs the details of the medical consultation using a terminal (e.g., a smartphone, tablet, or computer). Data is also acquired from a wearable device (e.g., a smart watch) worn by the worker. The terminal means transmits this data to the server means.

[0193] 3. Server means:

[0194] The server receives input data from the user and transmits the raw data to the generative artificial intelligence. The server then transmits the generated response back to the terminal. The server includes a health management data analysis means for analyzing the health data collected from the wearable device.

[0195] 4. Healthcare data analysis tools:

[0196] Generative AI analyzes data collected from health management apps and wearable devices to assess the user's health status, and generates appropriate health advice for workers based on the analysis results.

[0197] 5. Means of provision:

[0198] This is a means of notifying or displaying the generated analysis results and responses from the medical consultation chatbot to the user, allowing the user to immediately check the analysis results and take appropriate action.

[0199] As a specific example, if a wearable device records data such as "heart rate 110, steps 15,000, sleep time 5 hours, stress level high," generative AI will analyze this and generate advice such as "Take a break and hydrate. We recommend that you rest early so that it doesn't affect your work tomorrow."

[0200] Prompt Sentence Examples

[0201] "Analyze the following health data and provide recommendations. Health data: heart rate 110, steps 15000, sleep hours 5, stress level high"

[0202] In this way, it is possible to provide health management and real-time healthcare advice to factory workers. The main hardware used includes smartwatches and fitness trackers, and the main software uses Aiohttp (asynchronous HTTP communication) and generative artificial intelligence APIs (e.g., OpenAI® API).

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

[0204] Step 1:

[0205] The user launches the medical consultation chatbot application on their device and accesses the health support AI system. The user enters their username, password, and email address into the membership registration form and submits the registration information. This information is sent to the server, which hashes the password and then stores the registration information in a database. This completes user registration.

[0206] Input: Username, Password, Email Address

[0207] Output: User registration information

[0208] Step 2:

[0209] The user launches the chatbot from their device and begins a medical consultation. The questions and consultation details entered by the user are sent from the device to the server. The server uses generative artificial intelligence to analyze the user's message and generate an appropriate response. The generated response is then sent from the server to the device and displayed to the user.

[0210] Input: User's question or inquiry

[0211] Output: Response by generative artificial intelligence

[0212] Step 3:

[0213] Health data such as heart rate, number of steps, sleep time, and stress level are collected from wearable devices (e.g., smartwatches) worn by workers. This data is sent to a server via the device. The server uses generative artificial intelligence to analyze the health data, evaluate the user's health condition, and generate analysis results.

[0214] Input: Health data (heart rate, steps, sleep time, stress level)

[0215] Output: Health status assessment and analysis results

[0216] Step 4:

[0217] The server generates appropriate health advice based on the analysis results and sends it to the device, which then notifies or displays the advice to the user, allowing the user to take action accordingly.

[0218] Input: Analysis results

[0219] Output: Health advice

[0220] Step 5:

[0221] After using the system, users fill out the provided feedback form on their device. The device then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[0222] Input: User feedback

[0223] Output: Improvement proposals or materials for system improvement

[0224] In this way, users, devices, and servers can work together to monitor and manage workers' health status in real time and provide appropriate advice.

[0225] 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.

[0226] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes the user's emotions, and aims to provide appropriate and emotionally sensitive medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[0227] The system includes the following means:

[0228] 1. User Registration

[0229] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[0230] (2) The user enters their username, password, and email address into the form and sends it from their device to the server.

[0231] (3) The server processes the received user information and hashes the password for security purposes.

[0232] (4) The server stores the hashed passwords and other user data in a database.

[0233] 2. Interacting with a chatbot

[0234] (1) The user launches the chatbot from their device and accesses the screen for medical consultation.

[0235] (2) The terminal sends the questions and inquiries entered by the user to the server.

[0236] (3) The server passes the received user message to the emotion engine and analyzes the emotion along with the user message.

[0237] (4) The server processes the user message along with the analyzed emotions using generative artificial intelligence and generates an appropriate response.

[0238] (5) The server receives the generated response and returns it to the terminal.

[0239] (6) The terminal displays the generated response to the user.

[0240] Examples:

[0241] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a gentle, encouraging response, such as "Reviewing your sleep environment and increasing your daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[0242] 3. Health Management Data Analysis

[0243] (1) The user allows the health management app to link with the health support AI system.

[0244] (2) The device sends the data collected from the health management app to the server.

[0245] (3) The server passes the received health data to the generative artificial intelligence, which then analyzes the data.

[0246] (4) The server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[0247] (5) The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[0248] (6) The device notifies the user of the analysis results, and the user manages their health based on the results.

[0249] Examples:

[0250] The system analyzes heart rate and sleep data collected from health management apps, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[0251] 4. Feedback Collection

[0252] (1) After using the system, the user opens the provided feedback form on their terminal and enters their feedback.

[0253] (2) The terminal transmits the input feedback to the server.

[0254] (3) The server stores the received feedback data in a database.

[0255] (4) The server periodically extracts the feedback data from the database and analyzes it.

[0256] (5) The server improves the system based on the results of the analysis of the feedback.

[0257] Examples:

[0258] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[0259] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[0260] The processing flow will be explained below.

[0261] Detailed Process Steps of the Detailed Description

[0262] User Registration

[0263] Step 1:

[0264] The user launches the health support AI system application on their device and accesses the membership registration form.

[0265] Step 2:

[0266] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[0267] Step 3:

[0268] The server analyzes the received user information and hashes the password for security purposes.

[0269] Step 4:

[0270] The server stores the hashed passwords and other user data in a database.

[0271] Interacting with a chatbot

[0272] Step 1:

[0273] The user launches the chatbot from their device and accesses the screen for medical consultation.

[0274] Step 2:

[0275] The device sends the questions and inquiries entered by the user to the server.

[0276] Step 3:

[0277] The server passes the user message to the emotion engine, which analyzes the user's emotion.

[0278] Step 4:

[0279] The server passes the analyzed emotional information to a generative AI, which generates a response based on the user message and emotional information.

[0280] Step 5:

[0281] The server receives the generated response and sends it back to the terminal.

[0282] Step 6:

[0283] The terminal displays the generated response to the user.

[0284] Examples:

[0285] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a response saying, "Reviewing your sleeping environment and increasing daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[0286] Health management data analysis

[0287] Step 1:

[0288] The user allows linking with the health management app.

[0289] Step 2:

[0290] The device sends the data collected from the health management app to the server.

[0291] Step 3:

[0292] The server passes the received health data to an emotion engine and analyzes the user's emotional information.

[0293] Step 4:

[0294] The server passes emotional information and health data to a generative AI for data analysis.

[0295] Step 5:

[0296] The server receives the analysis results and sends them to the terminal.

[0297] Step 6:

[0298] The device will notify the user of the analysis results.

[0299] Examples:

[0300] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[0301] Feedback collection

[0302] Step 1:

[0303] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[0304] Step 2:

[0305] The terminal transmits the input feedback to the server.

[0306] Step 3:

[0307] The server stores the received feedback in a database.

[0308] Step 4:

[0309] The server periodically extracts the feedback data from the database and performs analysis.

[0310] Step 5:

[0311] The server will improve the system based on the results of the feedback analysis.

[0312] Examples:

[0313] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[0314] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[0315] Example 2

[0316] 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."

[0317] The problem that this invention aims to solve is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. Current medical consultation systems often return uniform responses without considering the user's emotions, resulting in a lack of trust and security. Furthermore, they lack the functionality to comprehensively analyze health management data and provide feedback to the user, making it difficult for users to properly understand their own health status.

[0318] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an input device means that receives the medical consultation content input by the user, a processing device means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the input device means, a processing device means that includes an emotion engine that recognizes the user's emotions to perform emotion analysis, a health management data analysis means that collects data from a health management app and analyzes it using the generative artificial intelligence, and a providing means that provides the analysis results to the user. This makes it possible to provide a response that takes the user's emotions into consideration and to perform comprehensive health management data analysis, allowing the user to more appropriately understand their health condition.

[0319] "Generative AI" is an AI system that uses large amounts of data to generate natural language, allowing for smooth dialogue with users.

[0320] A "medical consultation chatbot means" is a means that uses generative artificial intelligence to generate responses in natural language to users' medical questions and consultation details.

[0321] The "input device means" refers to a digital device that provides an interface for users to input questions or inquiries, and includes, for example, a smartphone or computer.

[0322] "Processing device means" refers to a server or cloud computing environment that receives input from a user and performs appropriate processing using generative artificial intelligence or an emotion analysis engine.

[0323] An "emotion engine" is software or a system that has the ability to analyze user input and identify emotions, and is used to process information taking into account the user's psychological state.

[0324] The "health management data analysis means" is a system that has the function of analyzing data collected from a health management app using generative artificial intelligence and outputting the results.

[0325] "Means of provision" refers to the interface for providing analysis results, chatbot responses, etc. to users, and is a device or function that enables users to receive appropriate information.

[0326] The above are definitions of important terms related to the present invention.

[0327] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes user emotions. The goal is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. This system is explained in the following sections:

[0328] User Registration

[0329] First, a user launches the Health Support AI System application on a device (smartphone or computer) and accesses the membership registration form. They enter their username, password, and email address into the form, which is then sent from the device to the server. The server processes the received user information and hashes the password using the SHA-256 algorithm. The hashed password and other user data are then stored in a database such as MySQL or PostgreSQL.

[0330] Interacting with a chatbot

[0331] The user launches the chatbot from their device and accesses the screen for medical consultations. The device sends the question and consultation details entered by the user to the server. The server passes the received message to the Microsoft (registered trademark) Text Analytics API and analyzes the user's emotions. The server then uses the API of generative AI (OpenAI GPT-3) to generate an appropriate response based on the analyzed emotions and consultation details. The generated response is sent back from the server to the device, which then displays it to the user.

[0332] Examples:

[0333] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety. The generative AI generates a gentle, encouraging response, saying, "Reviewing your sleep environment and increasing daytime activity may be effective. We also recommend consulting a doctor if necessary." This response is sent to the device and displayed to the user.

[0334] Health management data analysis

[0335] The user allows a health management app (such as Apple Health or GOOGLE FIT (registered trademark)) to link with the health support AI system. The device sends data collected from the health management app to the server. The server passes the received data to the generative AI, which analyzes the data. Furthermore, the server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results. The server sends the analysis results to the device, which then notifies the user of the analysis results.

[0336] Examples:

[0337] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[0338] Feedback collection

[0339] After using the system, the user opens the provided feedback form on their device and enters their feedback. The device then sends the entered feedback to the server. The server stores the received feedback data in a database, periodically extracts the feedback data from the database, and analyzes it. The system is improved based on the analysis results.

[0340] Examples:

[0341] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[0342] The system provides responses that take the user's emotions into consideration, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind. It also provides specific advice based on the analysis of health management data, allowing users to better understand their own health condition.

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] User Registration

[0345] Step 1:

[0346] The user launches the health support AI system application on their device and accesses the membership registration form.

[0347] Input: None

[0348] Output: Display of member registration form

[0349] Specific operation: When the application is launched, the device browser or in-app browser displays a web page with a membership registration form.

[0350] Step 2:

[0351] The user enters their "username," "password," and "email address" in the form and presses the "Register" button.

[0352] Input: Username, Password, Email Address

[0353] Output: Registration data in JSON format

[0354] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[0355] Step 3:

[0356] The server receives the received user information and hashes the password using the SHA-256 algorithm.

[0357] Input: Registration data in JSON format

[0358] Output: Hashed password

[0359] What happens: The server parses the user information and hashes the password field with the SHA-256 algorithm.

[0360] Step 4:

[0361] The server stores hashed passwords and other user data in a database.

[0362] Input: Hashed passwords and other user data

[0363] Output: Save registration data to database

[0364] Specific operation: The server executes the generated SQL query and stores the data in a database such as MySQL or PostgreSQL.

[0365] Interacting with a chatbot

[0366] Step 1:

[0367] The user launches the chatbot from their device and accesses the medical consultation screen.

[0368] Input: None

[0369] Output: Display of medical consultation interface

[0370] What it does: The app or web browser displays an interface for medical consultation.

[0371] Step 2:

[0372] The user inputs the question or inquiry and presses the send button.

[0373] Input: Question or inquiry

[0374] Output: Message data in JSON format

[0375] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[0376] Step 3:

[0377] The server passes the received user message to the emotion engine and analyzes the user's emotion.

[0378] Input: Message data in JSON format

[0379] Output: Emotion analysis results

[0380] Specific operation: The server sends message data to an emotion engine (such as Microsoft Text Analytics API) and receives the emotion analysis results.

[0381] Step 4:

[0382] The server uses generative AI to input the analyzed emotions and messages as prompts and generate an appropriate response.

[0383] Input: Sentiment analysis results, user message

[0384] Output: The generated response

[0385] Specific operation: The server sends the emotion analysis results and messages as prompts to the generative AI (such as OpenAI GPT-3) and receives the generated responses.

[0386] Step 5:

[0387] The server generates a response and sends it back to the terminal.

[0388] Input: Generated response

[0389] Output: Response data in JSON format

[0390] Specific operation: The server sends the generated response data to the terminal.

[0391] Step 6:

[0392] The terminal displays the response received from the server to the user.

[0393] Input: Response data in JSON format

[0394] Output: Response displayed on the screen

[0395] Specific behavior: The device parses the received data and displays the response in the user interface.

[0396] Health management data analysis

[0397] Step 1:

[0398] The user allows the health management app to link with the health support AI system.

[0399] Input: Collaboration permission settings

[0400] Output: Connection permission confirmation message

[0401] Specific operation: When the user sets permission for linking within the app, the health management app will begin data linking.

[0402] Step 2:

[0403] The device sends the data collected from the health management app to the server.

[0404] Input: Collected health data

[0405] Output: Health data in JSON format

[0406] Specific operation: The terminal converts the collected data into JSON format and sends it to the server.

[0407] Step 3:

[0408] The server passes the received data to the generative AI, which then analyzes the data.

[0409] Input: Health data in JSON format

[0410] Output: Analysis results

[0411] Specific operation: The server sends data to the generative AI and receives the analysis results.

[0412] Step 4:

[0413] The server monitors stress levels based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[0414] Input: Analysis data from generative AI, emotion analysis results

[0415] Output: Detailed analysis results

[0416] Specific operation: The server integrates the results of the emotion engine with the health data to generate a comprehensive analysis result.

[0417] Step 5:

[0418] The server transmits the analysis results to the terminal.

[0419] Input: Detailed analysis results

[0420] Output: Parsed results in JSON format

[0421] Specific operation: The server sends the generated analysis result data to the terminal.

[0422] Step 6:

[0423] The device notifies the user of the analysis results.

[0424] Input: Parsed result in JSON format

[0425] Output: Analysis results displayed on the screen

[0426] Specific operation: The device parses the analysis results received and displays them as notifications in the user interface.

[0427] Feedback collection

[0428] Step 1:

[0429] After using the system, the user opens the provided feedback form on the terminal.

[0430] Input: None

[0431] Output: Feedback form displayed

[0432] Specific operation: When the user clicks on the feedback form link after using the service, the form will be displayed.

[0433] Step 2:

[0434] The user enters the feedback and presses the send button.

[0435] Input: Feedback

[0436] Output: Feedback data in JSON format

[0437] Specific operation: The device converts the input feedback into JSON format and sends it to the server.

[0438] Step 3:

[0439] The server stores the received feedback data in a database.

[0440] Input: Feedback data in JSON format

[0441] Output: Save to database

[0442] Specific operation: The server registers the feedback data in a database.

[0443] Step 4:

[0444] The server periodically extracts the feedback data from the database and performs analysis.

[0445] Input: Feedback data in the database

[0446] Output: Analysis results

[0447] Specific operation: The server periodically extracts feedback data from the database and analyzes it using techniques such as natural language processing.

[0448] Step 5:

[0449] The server will improve the system based on the results of the analysis of the feedback.

[0450] Input: Feedback analysis results

[0451] Output: Improved system

[0452] Specific operation: The server takes into account the feedback analysis results and implements system improvements such as chatbot responses and user interface.

[0453] The above is a detailed flow of the processing of this system's program. By specifically performing a series of data processing and data calculations from input to output at each processing step, it is possible to provide high-quality medical support to users.

[0454] (Application example 2)

[0455] 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."

[0456] In today's world, security threats exploiting the Internet are rapidly increasing, increasing the information security risks for individuals and businesses. The risks are particularly severe for people with mobility issues, such as the elderly, people with disabilities, and people with chronic illnesses, who often lack specialized security knowledge. There is a need for systems that allow these people to receive appropriate security consultations and support from home. It is also important to provide appropriate advice that takes into account the user's emotions, but existing systems lack the ability to analyze and respond to emotions, making improving user satisfaction a challenge.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0458] In this invention, the server includes security consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, terminal means that receives security consultation content input from a user, server means that transmits the security consultation content to the generative artificial intelligence and returns a generated response to the terminal means, security management data analysis means that collects data from a security management app and analyzes it with the generative artificial intelligence, means that provides the analysis results to the user, emotion engine means that recognizes emotions, and means that collect feedback and improve the system. This enables people who have difficulty moving around to receive appropriate security advice from home that takes emotions into consideration.

[0459] "Generative AI" is an AI system that generates natural language and provides a response to user input.

[0460] The "security consultation chatbot means that responds in natural language" is a system that uses generative artificial intelligence to respond in natural language to security-related questions and inquiries.

[0461] The "terminal means for receiving security consultation details input by the user" refers to a device or system for receiving security-related questions and consultation details input by the user at a terminal.

[0462] The "server means for returning the generated response to the terminal means" is a server for transmitting the answer generated by the generative artificial intelligence to the terminal.

[0463] A "security management app" is software for managing and monitoring a user's security status.

[0464] The "security management data analysis means" is a system that analyzes data collected from the security management app and generates appropriate advice and suggestions for users.

[0465] The "emotion engine means for recognizing emotions" is a system that analyzes emotions from user input and reflects that information in responses.

[0466] "Means for collecting feedback and improving the system" refers to the processes and means for collecting user evaluations and opinions and using them to improve the performance and functionality of the system.

[0467] "Elderly, disabled and chronically ill people with mobility issues" refers to elderly people, people with disabilities or patients with long-term health problems who have difficulty moving freely due to physical limitations.

[0468] "Appropriate security consultation and support" means providing professional and accurate advice and assistance to users regarding security issues and questions they may have.

[0469] This invention is a system that uses generative artificial intelligence and an emotion engine to provide natural responses to security-related problems and inquiries that users have. Specific embodiments are described below.

[0470] First, a user accesses the system using a device such as a smartphone or PC. The user creates an account and enters basic information such as name, password, and email address. This operation causes the device to send the entered information to the server, which then stores it in a database.

[0471] Next, the user inputs a security question or inquiry into the chatbot. For example, they send a message like, "I often receive phishing emails. What should I do about them?" At this time, the emotion engine analyzes the message and evaluates the user's emotional state in order to recognize their emotions. If emotions such as anxiety or worry are detected, the data is sent to the server taking this into consideration.

[0472] The server analyzes the received data using generative artificial intelligence and generates an appropriate response. The generated response takes into account the user's emotional state and provides specific and reassuring information, such as "First, check the sender and links in the email, and if they seem suspicious, never click on them. It is also important to keep your security software up to date." The device then displays this response to the user.

[0473] For users using security management apps, logs and alert data collected from the app are also transferred to the server. The server then analyzes this data using generative artificial intelligence to assess the user's stress level and the system's security status. For example, it generates feedback such as, "Recent data indicates that many security alerts have been generated. We recommend a comprehensive review of your system." and notifies the user.

[0474] To collect feedback, users can fill out a feedback form after using the system. The terminal sends the entered feedback to the server, which stores it in a database. This information is periodically analyzed and used to improve the system.

[0475] The hardware and software used includes:

[0476] Hardware: smartphones, PCs, servers

[0477] Software: Python, SQLite, EmotionEngine (emotion engine library), AIResponseGenerator (generative artificial intelligence library)

[0478] Examples:

[0479] A user asks, "I've been receiving a lot of phishing emails lately. What should I do?"

[0480] The emotion engine recognizes the user's "anxiety," and the generative artificial intelligence generates a response such as, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[0481] Example prompt sentence:

[0482] A user asked, "I've been receiving a lot of phishing emails lately. What should I do?"

[0483] The emotion engine recognized the user's "anxiety."

[0484] Generate a response that is appropriate and reassuring in this context.

[0485] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0486] Step 1:

[0487] A user accesses the system and creates an account.

[0488] Input: Username, Password, Email Address

[0489] Specific operation: The user accesses the system's membership registration form using a device such as a smartphone or PC. They enter basic information such as their username, password, and email address into the form and press the submit button.

[0490] Output: User information sent from the device to the server

[0491] Step 2:

[0492] The server processes the received user information and stores it in a database.

[0493] Input: User information sent from the device (username, password, email address)

[0494] What it does: The server hashes the information it receives for security purposes and stores the user information in a database along with the hashed password.

[0495] Output: User information stored in the database

[0496] Step 3:

[0497] The user inputs a question or inquiry into the security consultation chatbot.

[0498] Input: Questions or inquiries about security

[0499] Specific operation: The user accesses the system's chatbot screen, enters the content of their inquiry in text, and presses the send button.

[0500] Output: Consultation details sent from the device to the server

[0501] Step 4:

[0502] The server analyzes the consultation content received by the server using an emotion engine and evaluates the emotional state.

[0503] Input: User's inquiry

[0504] Specific operation: The server passes the received consultation content to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes emotions such as "anxiety" and "worry" and returns the results.

[0505] Output: Sentiment analysis result (e.g., "anxiety")

[0506] Step 5:

[0507] The server passes the results of the emotion engine to a generative artificial intelligence system, which generates an appropriate response.

[0508] Input: Consultation details, emotion analysis results

[0509] Specific operation: The server uses generative AI to generate an appropriate response based on the content of the consultation and the results of emotion analysis. For example, if a user consults about phishing scams and detects "anxiety," the server will respond by saying, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[0510] Output: The generated response

[0511] Step 6:

[0512] The server sends the generated response back to the user terminal.

[0513] Input: Generated response

[0514] Specific operation: The server sends the generated response data to the terminal.

[0515] Output: The response displayed on the user's terminal

[0516] Step 7:

[0517] The user terminal displays the response on the screen.

[0518] Input: The response sent by the server

[0519] Specific operation: The terminal displays the received response on the screen and notifies the user.

[0520] Output: The response displayed to the user

[0521] Step 8:

[0522] The user sends the collected data from the security management app to the server.

[0523] Input: Data from security management apps (logs, alerts, etc.)

[0524] Specific operation: The user launches the security management app and allows data collection and transmission. The device sends the data collected from the app to the server.

[0525] Output: Security data sent to the server

[0526] Step 9:

[0527] The server analyzes the security data and generates appropriate feedback.

[0528] Input: Security Data

[0529] How it works: The server uses generative artificial intelligence to analyze the collected data and evaluate the user's stress level and the system's security status. For example, if a large number of security alerts are detected, the server generates feedback such as "We recommend a comprehensive review of the system."

[0530] Output: Generated feedback

[0531] Step 10:

[0532] The user terminal displays the generated feedback on the screen.

[0533] Input: Feedback sent by the server

[0534] Specific operation: The device displays the received feedback on the screen and notifies the user.

[0535] Output: Feedback displayed to the user

[0536] Step 11:

[0537] The user fills in the feedback form and submits it.

[0538] Input: Feedback

[0539] Specific operation: After using the system, the user accesses the feedback form, enters their evaluation and opinions, and presses the submit button.

[0540] Output: Feedback sent from the device to the server

[0541] Step 12:

[0542] The server stores the received feedback in a database and analyzes it periodically.

[0543] Input: Feedback sent by the user

[0544] Specific operation: The server stores the received feedback in a database, analyzes the data periodically, and uses the results to improve the system's performance and functionality.

[0545] Output: Feedback data stored in a database and system improvement suggestions

[0546] 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.

[0547] 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 (registered trademark) (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.

[0548] 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.

[0549] [Second embodiment]

[0550] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0551] 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.

[0552] 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).

[0553] 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.

[0554] 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.

[0555] 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).

[0556] 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.

[0557] 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.

[0558] 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.

[0559] 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.

[0560] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0561] 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."

[0562] This invention is a medical consultation chatbot system that uses generative artificial intelligence, and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[0563] The system includes the following means:

[0564] 1. User Registration

[0565] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[0566] (2) The user enters their username, password, and email address into the form and submits the registration information from their device.

[0567] (3) The server processes the received user information, hashes the password, and stores it in the database.

[0568] 2. Interacting with a chatbot

[0569] (1) The user launches the chatbot from their device and begins a medical consultation.

[0570] (2) The terminal sends the questions and inquiries entered by the user to the server.

[0571] (3) The server uses generative artificial intelligence to analyze the user message and generate an appropriate response.

[0572] (4) The server sends the generated response to the terminal, which displays the response to the user.

[0573] Examples:

[0574] When a user types, "I haven't been sleeping well lately. What should I do?", the generative AI responds, "Reviewing your sleep environment and increasing your daytime activity may be effective. If necessary, I recommend consulting a doctor."

[0575] 3. Health Management Data Analysis

[0576] (1) The user allows the health management app to link with the health support AI system.

[0577] (2) The device sends the data collected from the health management app to the server.

[0578] (3) The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions.

[0579] (4) The device notifies the user of the analysis results, and the user manages their health based on the results.

[0580] Examples:

[0581] It analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[0582] 4. Feedback Collection

[0583] (1) After using the system, the user fills out the provided feedback form on the terminal.

[0584] (2) The device sends the user's feedback to the server.

[0585] (3) The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[0586] Examples:

[0587] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in a database and uses it to improve the system in the future.

[0588] In this way, the health support AI system provides efficient and safe medical consultations and health management support by linking users, devices, and servers, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[0589] The processing flow will be explained below.

[0590] Detailed Process Steps of the Detailed Description

[0591] User Registration

[0592] Step 1:

[0593] The user launches the health support AI system app on their device and accesses the membership registration form.

[0594] Step 2:

[0595] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[0596] Step 3:

[0597] The server analyzes the received user information and hashes the password for security purposes.

[0598] Step 4:

[0599] The server stores the hashed passwords and other user data in a database.

[0600] Interacting with a chatbot

[0601] Step 1:

[0602] The user launches the chatbot from their device and accesses the screen for medical consultation.

[0603] Step 2:

[0604] The device sends the questions and inquiries entered by the user to the server.

[0605] Step 3:

[0606] The server passes the received user message to a generative artificial intelligence, which generates an appropriate response.

[0607] Step 4:

[0608] The server receives the generated response and sends it back to the terminal.

[0609] Step 5:

[0610] The terminal displays the generated response to the user.

[0611] Examples:

[0612] When a user types, "I haven't been sleeping well lately. What should I do?", the server uses generative artificial intelligence to generate a response: "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[0613] Health management data analysis

[0614] Step 1:

[0615] The user allows the health management app to link with the health support AI system.

[0616] Step 2:

[0617] The device sends the data collected from the health management app to the server.

[0618] Step 3:

[0619] The server passes the received health data to generative artificial intelligence, which then analyzes the data.

[0620] Step 4:

[0621] The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[0622] Step 5:

[0623] The device will notify the user of the analysis results.

[0624] Examples:

[0625] It analyzes heart rate and sleep data collected from health management apps and generates feedback to notify the user, such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[0626] Feedback collection

[0627] Step 1:

[0628] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[0629] Step 2:

[0630] The terminal transmits the input feedback to the server.

[0631] Step 3:

[0632] The server stores the received feedback data in a database.

[0633] Step 4:

[0634] The server periodically extracts the feedback data from the database and performs analysis.

[0635] Step 5:

[0636] The server will improve the system based on the results of the feedback analysis.

[0637] Examples:

[0638] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this information in a database and references it at a future improvement meeting to help improve the system.

[0639] In this way, this system efficiently performs a series of processes from user registration to medical consultation, health management data analysis, and feedback collection, providing comprehensive medical support to users.

[0640] Example 1

[0641] 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."

[0642] Modern healthcare systems require the provision of appropriate medical support to patients with mobility issues and users unfamiliar with medical consultations. However, existing medical consultation systems and health management apps face numerous challenges in terms of user registration, usability of dialogue interfaces, and feedback collection and utilization. For example, it is difficult to provide prompt and accurate medical advice to patients who have difficulty visiting hospitals. Furthermore, the system for providing user feedback is inadequate, slowing down service improvement. Furthermore, the functionality for effectively analyzing health data and recommending appropriate actions to users is limited. These challenges ultimately increase the risk of patients neglecting their health management.

[0643] 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.

[0644] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an information processing device means that receives the medical consultation content entered by the user, a server means that transmits the medical consultation content to the generative artificial intelligence and returns the generated response to the information processing device means, a health management data analysis means that collects data from the health management app and analyzes it using the generative artificial intelligence, a feedback means that provides the analysis results to the user, a user registration means that receives user registration information, hashes the password, and stores it in a database, and a feedback collection means that receives feedback after using the system, stores it in a database, and periodically analyzes it. This allows users to easily register and receive medical consultations in a natural, interactive format through the generative artificial intelligence, and manage their health based on the provided feedback. The system also accumulates and periodically analyzes user feedback, thereby improving the quality of its services.

[0645] "Generative AI" is an artificial intelligence technology for generating responses in natural language, and refers to algorithms that primarily use deep learning to generate appropriate outputs for various inputs.

[0646] "Medical consultation chatbot means" refers to a method and apparatus that uses generative artificial intelligence to automatically generate responses to a user's medical consultation.

[0647] "Information processing device means" refers to a device or application that has the function of receiving input from a user and transmitting data to a server via a communications network.

[0648] The term "server means" refers to a server device that receives input data from a user, generates a response using generative artificial intelligence, and returns the response to the information processing device means.

[0649] "Health management data analysis means" refers to a means for analyzing data collected from a health management app, and refers to a function that uses generative artificial intelligence to evaluate the user's health condition and recommend appropriate actions.

[0650] "Feedback means" refers to a means for providing responses and analysis results generated by generative artificial intelligence to users.

[0651] "User registration means" refers to a device or program that has the function of collecting information required when a user registers with the system, hashing the password, and storing the information in a database.

[0652] "Feedback collection means" refers to a means that has the function of receiving feedback from users after using the system, storing it in a database, and periodically analyzing it.

[0653] The present invention is a medical consultation chatbot system that uses generative artificial intelligence and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations. This invention includes the following means.

[0654] 1. User Registration Method

[0655] The user launches the Health Support AI System application using a device (e.g., PC, smartphone, tablet) and accesses the membership registration form. The user enters their username, password, and email address in the form and taps the submit button, sending the registration information from the device to the server. The server receives the received user information, hashes the password, and stores it in a database (e.g., MySQL, PostgreSQL).

[0656] 2. Medical consultation chatbot means

[0657] The user activates the chatbot function from their device and begins a medical consultation. The device then sends the question and consultation details entered by the user to the server. The server uses generative AI (e.g., GPT-3, ChatGPT) to analyze the user message and generate an appropriate response. The server then sends the generated response to the device, which then displays the response to the user. For example, if a user enters, "I've been having trouble sleeping lately. What should I do?", the server will use a generative AI model to respond, "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, I recommend consulting a doctor."

[0658] 3. Health management data analysis tools

[0659] The user allows a health management app (e.g., Apple Health, Google (registered trademark) Fit) to link with the health support AI system. The device sends data collected from the health management app to a server. The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions. The device notifies the user of the analysis results, and the user manages their health based on the results. As a specific example, the server analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[0660] 4. Feedback methods

[0661] After using the system, users access the provided feedback form and enter their feedback. The terminal then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system. For example, if a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in the database and uses it for future system improvements.

[0662] In this way, the health support AI system of the present invention provides efficient and safe medical consultations and health management support through collaboration between users, terminals, and servers. This system allows patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[0663] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0664] User registration process

[0665] Step 1:

[0666] The user launches the health support AI system application on their device. The app is launched by tapping the app icon on the device's home screen. The input is "tapping the app icon" and the output is "launching the app."

[0667] Step 2:

[0668] The user taps the registration button in the application to access the registration form. The form displays fields for entering a username, password, and email address. The input is "tap the registration button" and the output is "display the registration form."

[0669] Step 3:

[0670] The user enters the required information into the form and taps the submit button. The device sends the entered username, password, and email address to the server. The input is "user registration information" and the output is "send information."

[0671] Step 4:

[0672] The server receives the user information from the terminal and hashes the password. Here, the password is securely hashed using Python's bcrypt library. The input is "user registration information" and the output is "hashed password."

[0673] Step 5:

[0674] The server stores the hashed password and other user information in a database by generating an SQL query to insert the information into the appropriate columns. The input is the hashed password and user information, and the output is to store it in the database.

[0675] Medical consultation chatbot processing flow

[0676] Step 1:

[0677] The user activates the chatbot function on their device and starts a medical consultation by tapping the "medical consultation" button in the app. The input is "tapping the medical consultation button" and the output is "activating the chatbot."

[0678] Step 2:

[0679] The user enters a question or request on the chat screen and taps the send button. The device then sends this information to the server. The input is the user's question, and the output is a message sent to the server.

[0680] Step 3:

[0681] The server inputs the question sent by the user as a prompt to a generative AI (e.g., GPT-3). The generative AI analyzes the user message and generates an appropriate response. The input is the "user's question" and the output is the "generated response."

[0682] Step 4:

[0683] The server sends the generated response to the terminal, which then displays it to the user. Specifically, the AI's response message is displayed on the chat screen. The input is the "generated response" and the output is "display to the user."

[0684] Health management data analysis process flow

[0685] Step 1:

[0686] The user allows the health management app to link with the health support AI system. They tap the "Link" button on the app settings screen and grant the necessary access permissions. The input is "tap the link button" and the output is "allow link settings."

[0687] Step 2:

[0688] The device sends data collected from the health management app to the server. Collected data includes the number of steps, heart rate, sleep data, etc. The input is "health management data" and the output is "transmission to the server."

[0689] Step 3:

[0690] The server analyzes the collected health data using generative artificial intelligence. Specifically, it processes the data using Python libraries (e.g., Pandas) and machine learning models. The input is "health management data" and the output is "analysis results."

[0691] Step 4:

[0692] The server notifies the user of the analysis results, which are then displayed on the device. The analysis results include an assessment of the user's health status and recommended actions. The input is the "analysis results" and the output is "notification to the user." For example, the message might read, "Recent data suggests that your stress level is increasing. Try to spend more time relaxing."

[0693] Feedback collection process flow

[0694] Step 1:

[0695] After using the system, users access the provided feedback form and enter their impressions and suggestions for improvement. The input is "feedback input content" and the output is "input to the feedback form."

[0696] Step 2:

[0697] The terminal sends the feedback content entered by the user to the server. The input is "feedback content" and the output is "transmission to server."

[0698] Step 3:

[0699] The server saves the received feedback data in a database. Specifically, it generates an SQL query and inserts it into the database. The input is "feedback content" and the output is "saving to database."

[0700] Step 4:

[0701] The server periodically analyzes the accumulated feedback data and uses it to improve the system. It uses Python data analysis tools (e.g., Pandas, Matplotlib). The input is "feedback data" and the output is "analysis results and system improvement proposals."

[0702] In this way, the health support AI system of the present invention provides medical consultation and health management support efficiently and safely through a series of processing steps in which the user, terminal, and server work together.

[0703] (Application example 1)

[0704] 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."

[0705] The present invention relates to a system that monitors the health status of employees in real time and provides appropriate healthcare advice. Its purpose is to support worker health management and abnormality detection in order to improve work efficiency, particularly in work environments such as factories. Conventional health management methods have the problem of ineffective collection and analysis of health data, leading to inadequate management of worker health.

[0706] 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.

[0707] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, a terminal means that receives medical consultation content input from a user, a means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the terminal means, a health management data analysis means that collects data from a health management app and analyzes it with the generative artificial intelligence, a means that provides the user with the analysis results, a means that acquires health data from a wearable device worn by a worker and analyzes it with the generative artificial intelligence, and a means that provides the worker with health advice based on the analysis results. This makes it possible to monitor the health status of workers in real time and provide appropriate health care advice.

[0708] "Generative AI" is an AI technology that has the ability to automatically generate appropriate responses in natural language based on user input.

[0709] A "medical consultation chatbot" is a system that uses generative artificial intelligence to provide appropriate responses in natural language to users' medical questions and inquiries.

[0710] "Terminal means" refers to a means by which a user inputs and transmits medical consultation details using an input device (e.g., smartphone, tablet, computer, etc.).

[0711] The "server means" is a central management system for transmitting the medical consultation content sent by the user to the generative artificial intelligence and returning the generated response to the user's terminal.

[0712] The "health management data analysis means" is a system that uses generative artificial intelligence to analyze data collected from health management apps, evaluate the user's health status, and generate recommended actions and advice.

[0713] "Providing means" refers to the means for notifying or displaying to the user the analysis results and responses generated by the generative artificial intelligence.

[0714] A "wearable device" is a device (e.g., smartwatch, fitness tracker, etc.) that can be worn by a user at all times and is a device for collecting health data (e.g., heart rate, number of steps, sleep data, etc.).

[0715] "Healthcare advice" refers to recommendations and advice regarding health management provided to the user based on the analysis results obtained by the health data analysis means.

[0716] The system of the present invention aims to improve workers' work efficiency and support their health management by monitoring the health status of workers in working environments such as factories in real time and providing appropriate health care advice using generative artificial intelligence.

[0717] The system consists of the following components:

[0718] 1. Medical consultation chatbot using generative artificial intelligence:

[0719] Users input questions about their health in natural language. The generative AI analyzes the input and generates appropriate responses. These responses are provided to the user via a terminal.

[0720] 2. Terminal means:

[0721] The user inputs the details of the medical consultation using a terminal (e.g., a smartphone, tablet, or computer). Data is also acquired from a wearable device (e.g., a smart watch) worn by the worker. The terminal means transmits this data to the server means.

[0722] 3. Server means:

[0723] The server receives input data from the user and transmits the raw data to the generative artificial intelligence. The server then transmits the generated response back to the terminal. The server includes a health management data analysis means for analyzing the health data collected from the wearable device.

[0724] 4. Healthcare data analysis tools:

[0725] Generative AI analyzes data collected from health management apps and wearable devices to assess the user's health status, and generates appropriate health advice for workers based on the analysis results.

[0726] 5. Means of provision:

[0727] This is a means of notifying or displaying the generated analysis results and responses from the medical consultation chatbot to the user, allowing the user to immediately check the analysis results and take appropriate action.

[0728] As a specific example, if a wearable device records data such as "heart rate 110, steps 15,000, sleep time 5 hours, stress level high," generative AI will analyze this and generate advice such as "Take a break and hydrate. We recommend that you rest early so that it doesn't affect your work tomorrow."

[0729] Prompt Sentence Examples

[0730] "Analyze the following health data and provide recommendations. Health data: heart rate 110, steps 15000, sleep hours 5, stress level high"

[0731] In this way, it is possible to provide health management and real-time healthcare advice to factory workers. The main hardware used includes smartwatches and fitness trackers, and the main software uses Aiohttp (asynchronous HTTP communication) and generative artificial intelligence APIs (e.g., OpenAI API).

[0732] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0733] Step 1:

[0734] The user launches the medical consultation chatbot application on their device and accesses the health support AI system. The user enters their username, password, and email address into the membership registration form and submits the registration information. This information is sent to the server, which hashes the password and then stores the registration information in a database. This completes user registration.

[0735] Input: Username, Password, Email Address

[0736] Output: User registration information

[0737] Step 2:

[0738] The user launches the chatbot from their device and begins a medical consultation. The questions and consultation details entered by the user are sent from the device to the server. The server uses generative artificial intelligence to analyze the user's message and generate an appropriate response. The generated response is then sent from the server to the device and displayed to the user.

[0739] Input: User's question or inquiry

[0740] Output: Response by generative artificial intelligence

[0741] Step 3:

[0742] Health data such as heart rate, number of steps, sleep time, and stress level are collected from wearable devices (e.g., smartwatches) worn by workers. This data is sent to a server via the device. The server uses generative artificial intelligence to analyze the health data, evaluate the user's health condition, and generate analysis results.

[0743] Input: Health data (heart rate, steps, sleep time, stress level)

[0744] Output: Health status assessment and analysis results

[0745] Step 4:

[0746] The server generates appropriate health advice based on the analysis results and sends it to the device, which then notifies or displays the advice to the user, allowing the user to take action accordingly.

[0747] Input: Analysis results

[0748] Output: Health advice

[0749] Step 5:

[0750] After using the system, users fill out the provided feedback form on their device. The device then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[0751] Input: User feedback

[0752] Output: Improvement proposals or materials for system improvement

[0753] In this way, users, devices, and servers can work together to monitor and manage workers' health status in real time and provide appropriate advice.

[0754] 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.

[0755] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes the user's emotions, and aims to provide appropriate and emotionally sensitive medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[0756] The system includes the following means:

[0757] 1. User Registration

[0758] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[0759] (2) The user enters their username, password, and email address into the form and sends it from their device to the server.

[0760] (3) The server processes the received user information and hashes the password for security purposes.

[0761] (4) The server stores the hashed passwords and other user data in a database.

[0762] 2. Interacting with a chatbot

[0763] (1) The user launches the chatbot from their device and accesses the screen for medical consultation.

[0764] (2) The terminal sends the questions and inquiries entered by the user to the server.

[0765] (3) The server passes the received user message to the emotion engine and analyzes the emotion along with the user message.

[0766] (4) The server processes the user message along with the analyzed emotions using generative artificial intelligence and generates an appropriate response.

[0767] (5) The server receives the generated response and returns it to the terminal.

[0768] (6) The terminal displays the generated response to the user.

[0769] Examples:

[0770] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a gentle, encouraging response, such as "Reviewing your sleep environment and increasing your daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[0771] 3. Health Management Data Analysis

[0772] (1) The user allows the health management app to link with the health support AI system.

[0773] (2) The device sends the data collected from the health management app to the server.

[0774] (3) The server passes the received health data to the generative artificial intelligence, which then analyzes the data.

[0775] (4) The server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[0776] (5) The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[0777] (6) The device notifies the user of the analysis results, and the user manages their health based on the results.

[0778] Examples:

[0779] The system analyzes heart rate and sleep data collected from health management apps, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[0780] 4. Feedback Collection

[0781] (1) After using the system, the user opens the provided feedback form on their terminal and enters their feedback.

[0782] (2) The terminal transmits the input feedback to the server.

[0783] (3) The server stores the received feedback data in a database.

[0784] (4) The server periodically extracts the feedback data from the database and analyzes it.

[0785] (5) The server improves the system based on the results of the analysis of the feedback.

[0786] Examples:

[0787] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[0788] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[0789] The processing flow will be explained below.

[0790] Detailed Process Steps of the Detailed Description

[0791] User Registration

[0792] Step 1:

[0793] The user launches the health support AI system application on their device and accesses the membership registration form.

[0794] Step 2:

[0795] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[0796] Step 3:

[0797] The server analyzes the received user information and hashes the password for security purposes.

[0798] Step 4:

[0799] The server stores the hashed passwords and other user data in a database.

[0800] Interacting with a chatbot

[0801] Step 1:

[0802] The user launches the chatbot from their device and accesses the screen for medical consultation.

[0803] Step 2:

[0804] The device sends the questions and inquiries entered by the user to the server.

[0805] Step 3:

[0806] The server passes the user message to the emotion engine, which analyzes the user's emotion.

[0807] Step 4:

[0808] The server passes the analyzed emotional information to a generative AI, which generates a response based on the user message and emotional information.

[0809] Step 5:

[0810] The server receives the generated response and sends it back to the terminal.

[0811] Step 6:

[0812] The terminal displays the generated response to the user.

[0813] Examples:

[0814] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a response saying, "Reviewing your sleeping environment and increasing daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[0815] Health management data analysis

[0816] Step 1:

[0817] The user allows linking with the health management app.

[0818] Step 2:

[0819] The device sends the data collected from the health management app to the server.

[0820] Step 3:

[0821] The server passes the received health data to an emotion engine and analyzes the user's emotional information.

[0822] Step 4:

[0823] The server passes emotional information and health data to a generative AI for data analysis.

[0824] Step 5:

[0825] The server receives the analysis results and sends them to the terminal.

[0826] Step 6:

[0827] The device will notify the user of the analysis results.

[0828] Examples:

[0829] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[0830] Feedback collection

[0831] Step 1:

[0832] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[0833] Step 2:

[0834] The terminal transmits the input feedback to the server.

[0835] Step 3:

[0836] The server stores the received feedback in a database.

[0837] Step 4:

[0838] The server periodically extracts the feedback data from the database and performs analysis.

[0839] Step 5:

[0840] The server will improve the system based on the results of the feedback analysis.

[0841] Examples:

[0842] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[0843] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[0844] Example 2

[0845] 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."

[0846] The problem that this invention aims to solve is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. Current medical consultation systems often return uniform responses without considering the user's emotions, resulting in a lack of trust and security. Furthermore, they lack the functionality to comprehensively analyze health management data and provide feedback to the user, making it difficult for users to properly understand their own health status.

[0847] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an input device means that receives the medical consultation content input by the user, a processing device means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the input device means, a processing device means that includes an emotion engine that recognizes the user's emotions to perform emotion analysis, a health management data analysis means that collects data from a health management app and analyzes it using the generative artificial intelligence, and a providing means that provides the analysis results to the user. This makes it possible to provide a response that takes the user's emotions into consideration and to perform comprehensive health management data analysis, allowing the user to more appropriately understand their health condition.

[0848] "Generative AI" is an AI system that uses large amounts of data to generate natural language, allowing for smooth dialogue with users.

[0849] A "medical consultation chatbot means" is a means that uses generative artificial intelligence to generate responses in natural language to users' medical questions and consultation details.

[0850] The "input device means" refers to a digital device that provides an interface for users to input questions or inquiries, and includes, for example, a smartphone or computer.

[0851] "Processing device means" refers to a server or cloud computing environment that receives input from a user and performs appropriate processing using generative artificial intelligence or an emotion analysis engine.

[0852] An "emotion engine" is software or a system that has the ability to analyze user input and identify emotions, and is used to process information taking into account the user's psychological state.

[0853] The "health management data analysis means" is a system that has the function of analyzing data collected from a health management app using generative artificial intelligence and outputting the results.

[0854] "Means of provision" refers to the interface for providing analysis results, chatbot responses, etc. to users, and is a device or function that enables users to receive appropriate information.

[0855] The above are definitions of important terms related to the present invention.

[0856] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes user emotions. The goal is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. This system is explained in the following sections:

[0857] User Registration

[0858] First, a user launches the Health Support AI System application on a device (smartphone or computer) and accesses the membership registration form. They enter their username, password, and email address into the form, which is then sent from the device to the server. The server processes the received user information and hashes the password using the SHA-256 algorithm. The hashed password and other user data are then stored in a database such as MySQL or PostgreSQL.

[0859] Interacting with a chatbot

[0860] The user launches the chatbot from their device and accesses the screen for medical consultations. The device sends the question and consultation details entered by the user to the server. The server passes the received message to the Microsoft Text Analytics API and analyzes the user's emotions. The server then uses the API of generative AI (OpenAI GPT-3) to generate an appropriate response based on the analyzed emotions and consultation details. The generated response is sent back from the server to the device, which then displays it to the user.

[0861] Examples:

[0862] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety. The generative AI generates a gentle, encouraging response, saying, "Reviewing your sleep environment and increasing daytime activity may be effective. We also recommend consulting a doctor if necessary." This response is sent to the device and displayed to the user.

[0863] Health management data analysis

[0864] The user allows a health management app (such as Apple Health or Google Fit) to connect with the health support AI system. The device sends data collected from the health management app to the server. The server passes the received data to the generative AI for data analysis. Furthermore, the server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results. The server sends the analysis results to the device, which then notifies the user of the results.

[0865] Examples:

[0866] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[0867] Feedback collection

[0868] After using the system, the user opens the provided feedback form on their device and enters their feedback. The device then sends the entered feedback to the server. The server stores the received feedback data in a database, periodically extracts the feedback data from the database, and analyzes it. The system is improved based on the analysis results.

[0869] Examples:

[0870] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[0871] The system provides responses that take the user's emotions into consideration, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind. It also provides specific advice based on the analysis of health management data, allowing users to better understand their own health condition.

[0872] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0873] User Registration

[0874] Step 1:

[0875] The user launches the health support AI system application on their device and accesses the membership registration form.

[0876] Input: None

[0877] Output: Display of member registration form

[0878] Specific operation: When the application is launched, the device browser or in-app browser displays a web page with a membership registration form.

[0879] Step 2:

[0880] The user enters their "username," "password," and "email address" in the form and presses the "Register" button.

[0881] Input: Username, Password, Email Address

[0882] Output: Registration data in JSON format

[0883] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[0884] Step 3:

[0885] The server receives the received user information and hashes the password using the SHA-256 algorithm.

[0886] Input: Registration data in JSON format

[0887] Output: Hashed password

[0888] What happens: The server parses the user information and hashes the password field with the SHA-256 algorithm.

[0889] Step 4:

[0890] The server stores hashed passwords and other user data in a database.

[0891] Input: Hashed passwords and other user data

[0892] Output: Save registration data to database

[0893] Specific operation: The server executes the generated SQL query and stores the data in a database such as MySQL or PostgreSQL.

[0894] Interacting with a chatbot

[0895] Step 1:

[0896] The user launches the chatbot from their device and accesses the medical consultation screen.

[0897] Input: None

[0898] Output: Display of medical consultation interface

[0899] What it does: The app or web browser displays an interface for medical consultation.

[0900] Step 2:

[0901] The user inputs the question or inquiry and presses the send button.

[0902] Input: Question or inquiry

[0903] Output: Message data in JSON format

[0904] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[0905] Step 3:

[0906] The server passes the received user message to the emotion engine and analyzes the user's emotion.

[0907] Input: Message data in JSON format

[0908] Output: Emotion analysis results

[0909] Specific operation: The server sends message data to an emotion engine (such as Microsoft Text Analytics API) and receives the emotion analysis results.

[0910] Step 4:

[0911] The server uses generative AI to input the analyzed emotions and messages as prompts and generate an appropriate response.

[0912] Input: Sentiment analysis results, user message

[0913] Output: The generated response

[0914] Specific operation: The server sends the emotion analysis results and messages as prompts to the generative AI (such as OpenAI GPT-3) and receives the generated responses.

[0915] Step 5:

[0916] The server generates a response and sends it back to the terminal.

[0917] Input: Generated response

[0918] Output: Response data in JSON format

[0919] Specific operation: The server sends the generated response data to the terminal.

[0920] Step 6:

[0921] The terminal displays the response received from the server to the user.

[0922] Input: Response data in JSON format

[0923] Output: Response displayed on the screen

[0924] Specific behavior: The device parses the received data and displays the response in the user interface.

[0925] Health management data analysis

[0926] Step 1:

[0927] The user allows the health management app to link with the health support AI system.

[0928] Input: Collaboration permission settings

[0929] Output: Connection permission confirmation message

[0930] Specific operation: When the user sets permission for linking within the app, the health management app will begin data linking.

[0931] Step 2:

[0932] The device sends the data collected from the health management app to the server.

[0933] Input: Collected health data

[0934] Output: Health data in JSON format

[0935] Specific operation: The terminal converts the collected data into JSON format and sends it to the server.

[0936] Step 3:

[0937] The server passes the received data to the generative AI, which then analyzes the data.

[0938] Input: Health data in JSON format

[0939] Output: Analysis results

[0940] Specific operation: The server sends data to the generative AI and receives the analysis results.

[0941] Step 4:

[0942] The server monitors stress levels based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[0943] Input: Analysis data from generative AI, emotion analysis results

[0944] Output: Detailed analysis results

[0945] Specific operation: The server integrates the results of the emotion engine with the health data to generate a comprehensive analysis result.

[0946] Step 5:

[0947] The server transmits the analysis results to the terminal.

[0948] Input: Detailed analysis results

[0949] Output: Parsed results in JSON format

[0950] Specific operation: The server sends the generated analysis result data to the terminal.

[0951] Step 6:

[0952] The device notifies the user of the analysis results.

[0953] Input: Parsed result in JSON format

[0954] Output: Analysis results displayed on the screen

[0955] Specific operation: The device parses the analysis results received and displays them as notifications in the user interface.

[0956] Feedback collection

[0957] Step 1:

[0958] After using the system, the user opens the provided feedback form on the terminal.

[0959] Input: None

[0960] Output: Feedback form displayed

[0961] Specific operation: When the user clicks on the feedback form link after using the service, the form will be displayed.

[0962] Step 2:

[0963] The user enters the feedback and presses the send button.

[0964] Input: Feedback

[0965] Output: Feedback data in JSON format

[0966] Specific operation: The device converts the input feedback into JSON format and sends it to the server.

[0967] Step 3:

[0968] The server stores the received feedback data in a database.

[0969] Input: Feedback data in JSON format

[0970] Output: Save to database

[0971] Specific operation: The server registers the feedback data in a database.

[0972] Step 4:

[0973] The server periodically extracts the feedback data from the database and performs analysis.

[0974] Input: Feedback data in the database

[0975] Output: Analysis results

[0976] Specific operation: The server periodically extracts feedback data from the database and analyzes it using techniques such as natural language processing.

[0977] Step 5:

[0978] The server will improve the system based on the results of the analysis of the feedback.

[0979] Input: Feedback analysis results

[0980] Output: Improved system

[0981] Specific operation: The server takes into account the feedback analysis results and implements system improvements such as chatbot responses and user interface.

[0982] The above is a detailed flow of the processing of this system's program. By specifically performing a series of data processing and data calculations from input to output at each processing step, it is possible to provide high-quality medical support to users.

[0983] (Application example 2)

[0984] 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."

[0985] In today's world, security threats exploiting the Internet are rapidly increasing, increasing the information security risks for individuals and businesses. The risks are particularly severe for people with mobility issues, such as the elderly, people with disabilities, and people with chronic illnesses, who often lack specialized security knowledge. There is a need for systems that allow these people to receive appropriate security consultations and support from home. It is also important to provide appropriate advice that takes into account the user's emotions, but existing systems lack the ability to analyze and respond to emotions, making improving user satisfaction a challenge.

[0986] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0987] In this invention, the server includes security consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, terminal means that receives security consultation content input from a user, server means that transmits the security consultation content to the generative artificial intelligence and returns a generated response to the terminal means, security management data analysis means that collects data from a security management app and analyzes it with the generative artificial intelligence, means that provides the analysis results to the user, emotion engine means that recognizes emotions, and means that collect feedback and improve the system. This enables people who have difficulty moving around to receive appropriate security advice from home that takes emotions into consideration.

[0988] "Generative AI" is an AI system that generates natural language and provides a response to user input.

[0989] The "security consultation chatbot means that responds in natural language" is a system that uses generative artificial intelligence to respond in natural language to security-related questions and inquiries.

[0990] The "terminal means for receiving security consultation details input by the user" refers to a device or system for receiving security-related questions and consultation details input by the user at a terminal.

[0991] The "server means for returning the generated response to the terminal means" is a server for transmitting the answer generated by the generative artificial intelligence to the terminal.

[0992] A "security management app" is software for managing and monitoring a user's security status.

[0993] The "security management data analysis means" is a system that analyzes data collected from the security management app and generates appropriate advice and suggestions for users.

[0994] The "emotion engine means for recognizing emotions" is a system that analyzes emotions from user input and reflects that information in responses.

[0995] "Means for collecting feedback and improving the system" refers to the processes and means for collecting user evaluations and opinions and using them to improve the performance and functionality of the system.

[0996] "Elderly, disabled and chronically ill people with mobility issues" refers to elderly people, people with disabilities or patients with long-term health problems who have difficulty moving freely due to physical limitations.

[0997] "Appropriate security consultation and support" means providing professional and accurate advice and assistance to users regarding security issues and questions they may have.

[0998] This invention is a system that uses generative artificial intelligence and an emotion engine to provide natural responses to security-related problems and inquiries that users have. Specific embodiments are described below.

[0999] First, a user accesses the system using a device such as a smartphone or PC. The user creates an account and enters basic information such as name, password, and email address. This operation causes the device to send the entered information to the server, which then stores it in a database.

[1000] Next, the user inputs a security question or inquiry into the chatbot. For example, they send a message like, "I often receive phishing emails. What should I do about them?" At this time, the emotion engine analyzes the message and evaluates the user's emotional state in order to recognize their emotions. If emotions such as anxiety or worry are detected, the data is sent to the server taking this into consideration.

[1001] The server analyzes the received data using generative artificial intelligence and generates an appropriate response. The generated response takes into account the user's emotional state and provides specific and reassuring information, such as "First, check the sender and links in the email, and if they seem suspicious, never click on them. It is also important to keep your security software up to date." The device then displays this response to the user.

[1002] For users using security management apps, logs and alert data collected from the app are also transferred to the server. The server then analyzes this data using generative artificial intelligence to assess the user's stress level and the system's security status. For example, it generates feedback such as, "Recent data indicates that many security alerts have been generated. We recommend a comprehensive review of your system." and notifies the user.

[1003] To collect feedback, users can fill out a feedback form after using the system. The terminal sends the entered feedback to the server, which stores it in a database. This information is periodically analyzed and used to improve the system.

[1004] The hardware and software used includes:

[1005] Hardware: smartphones, PCs, servers

[1006] Software: Python, SQLite, EmotionEngine (emotion engine library), AIResponseGenerator (generative artificial intelligence library)

[1007] Examples:

[1008] A user asks, "I've been receiving a lot of phishing emails lately. What should I do?"

[1009] The emotion engine recognizes the user's "anxiety," and the generative artificial intelligence generates a response such as, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[1010] Example prompt sentence:

[1011] A user asked, "I've been receiving a lot of phishing emails lately. What should I do?"

[1012] The emotion engine recognized the user's "anxiety."

[1013] Generate a response that is appropriate and reassuring in this context.

[1014] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1015] Step 1:

[1016] A user accesses the system and creates an account.

[1017] Input: Username, Password, Email Address

[1018] Specific operation: The user accesses the system's membership registration form using a device such as a smartphone or PC. They enter basic information such as their username, password, and email address into the form and press the submit button.

[1019] Output: User information sent from the device to the server

[1020] Step 2:

[1021] The server processes the received user information and stores it in a database.

[1022] Input: User information sent from the device (username, password, email address)

[1023] What it does: The server hashes the information it receives for security purposes and stores the user information in a database along with the hashed password.

[1024] Output: User information stored in the database

[1025] Step 3:

[1026] The user inputs a question or inquiry into the security consultation chatbot.

[1027] Input: Questions or inquiries about security

[1028] Specific operation: The user accesses the system's chatbot screen, enters the content of their inquiry in text, and presses the send button.

[1029] Output: Consultation details sent from the device to the server

[1030] Step 4:

[1031] The server analyzes the consultation content received by the server using an emotion engine and evaluates the emotional state.

[1032] Input: User's inquiry

[1033] Specific operation: The server passes the received consultation content to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes emotions such as "anxiety" and "worry" and returns the results.

[1034] Output: Sentiment analysis result (e.g., "anxiety")

[1035] Step 5:

[1036] The server passes the results of the emotion engine to a generative artificial intelligence system, which generates an appropriate response.

[1037] Input: Consultation details, emotion analysis results

[1038] Specific operation: The server uses generative AI to generate an appropriate response based on the content of the consultation and the results of emotion analysis. For example, if a user consults about phishing scams and detects "anxiety," the server will respond by saying, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[1039] Output: The generated response

[1040] Step 6:

[1041] The server sends the generated response back to the user terminal.

[1042] Input: Generated response

[1043] Specific operation: The server sends the generated response data to the terminal.

[1044] Output: The response displayed on the user's terminal

[1045] Step 7:

[1046] The user terminal displays the response on the screen.

[1047] Input: The response sent by the server

[1048] Specific operation: The terminal displays the received response on the screen and notifies the user.

[1049] Output: The response displayed to the user

[1050] Step 8:

[1051] The user sends the collected data from the security management app to the server.

[1052] Input: Data from security management apps (logs, alerts, etc.)

[1053] Specific operation: The user launches the security management app and allows data collection and transmission. The device sends the data collected from the app to the server.

[1054] Output: Security data sent to the server

[1055] Step 9:

[1056] The server analyzes the security data and generates appropriate feedback.

[1057] Input: Security Data

[1058] How it works: The server uses generative artificial intelligence to analyze the collected data and evaluate the user's stress level and the system's security status. For example, if a large number of security alerts are detected, the server generates feedback such as "We recommend a comprehensive review of the system."

[1059] Output: Generated feedback

[1060] Step 10:

[1061] The user terminal displays the generated feedback on the screen.

[1062] Input: Feedback sent by the server

[1063] Specific operation: The device displays the received feedback on the screen and notifies the user.

[1064] Output: Feedback displayed to the user

[1065] Step 11:

[1066] The user fills in the feedback form and submits it.

[1067] Input: Feedback

[1068] Specific operation: After using the system, the user accesses the feedback form, enters their evaluation and opinions, and presses the submit button.

[1069] Output: Feedback sent from the device to the server

[1070] Step 12:

[1071] The server stores the received feedback in a database and analyzes it periodically.

[1072] Input: Feedback sent by the user

[1073] Specific operation: The server stores the received feedback in a database, analyzes the data periodically, and uses the results to improve the system's performance and functionality.

[1074] Output: Feedback data stored in a database and system improvement suggestions

[1075] 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.

[1076] 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.

[1077] 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.

[1078] [Third embodiment]

[1079] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1080] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1081] 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).

[1082] 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.

[1083] 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.

[1084] 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).

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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."

[1091] This invention is a medical consultation chatbot system that uses generative artificial intelligence, and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[1092] The system includes the following means:

[1093] 1. User Registration

[1094] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[1095] (2) The user enters their username, password, and email address into the form and submits the registration information from their device.

[1096] (3) The server processes the received user information, hashes the password, and stores it in the database.

[1097] 2. Interacting with a chatbot

[1098] (1) The user launches the chatbot from their device and begins a medical consultation.

[1099] (2) The terminal sends the questions and inquiries entered by the user to the server.

[1100] (3) The server uses generative artificial intelligence to analyze the user message and generate an appropriate response.

[1101] (4) The server sends the generated response to the terminal, which displays the response to the user.

[1102] Examples:

[1103] When a user types, "I haven't been sleeping well lately. What should I do?", the generative AI responds, "Reviewing your sleep environment and increasing your daytime activity may be effective. If necessary, I recommend consulting a doctor."

[1104] 3. Health Management Data Analysis

[1105] (1) The user allows the health management app to link with the health support AI system.

[1106] (2) The device sends the data collected from the health management app to the server.

[1107] (3) The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions.

[1108] (4) The device notifies the user of the analysis results, and the user manages their health based on the results.

[1109] Examples:

[1110] It analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[1111] 4. Feedback Collection

[1112] (1) After using the system, the user fills out the provided feedback form on the terminal.

[1113] (2) The device sends the user's feedback to the server.

[1114] (3) The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[1115] Examples:

[1116] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in a database and uses it to improve the system in the future.

[1117] In this way, the health support AI system provides efficient and safe medical consultations and health management support by linking users, devices, and servers, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[1118] The processing flow will be explained below.

[1119] Detailed Process Steps of the Detailed Description

[1120] User Registration

[1121] Step 1:

[1122] The user launches the health support AI system app on their device and accesses the membership registration form.

[1123] Step 2:

[1124] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[1125] Step 3:

[1126] The server analyzes the received user information and hashes the password for security purposes.

[1127] Step 4:

[1128] The server stores the hashed passwords and other user data in a database.

[1129] Interacting with a chatbot

[1130] Step 1:

[1131] The user launches the chatbot from their device and accesses the screen for medical consultation.

[1132] Step 2:

[1133] The device sends the questions and inquiries entered by the user to the server.

[1134] Step 3:

[1135] The server passes the received user message to a generative artificial intelligence, which generates an appropriate response.

[1136] Step 4:

[1137] The server receives the generated response and sends it back to the terminal.

[1138] Step 5:

[1139] The terminal displays the generated response to the user.

[1140] Examples:

[1141] When a user types, "I haven't been sleeping well lately. What should I do?", the server uses generative artificial intelligence to generate a response: "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[1142] Health management data analysis

[1143] Step 1:

[1144] The user allows the health management app to link with the health support AI system.

[1145] Step 2:

[1146] The device sends the data collected from the health management app to the server.

[1147] Step 3:

[1148] The server passes the received health data to generative artificial intelligence, which then analyzes the data.

[1149] Step 4:

[1150] The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[1151] Step 5:

[1152] The device will notify the user of the analysis results.

[1153] Examples:

[1154] It analyzes heart rate and sleep data collected from health management apps and generates feedback to notify the user, such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[1155] Feedback collection

[1156] Step 1:

[1157] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[1158] Step 2:

[1159] The terminal transmits the input feedback to the server.

[1160] Step 3:

[1161] The server stores the received feedback data in a database.

[1162] Step 4:

[1163] The server periodically extracts the feedback data from the database and performs analysis.

[1164] Step 5:

[1165] The server will improve the system based on the results of the feedback analysis.

[1166] Examples:

[1167] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this information in a database and references it at a future improvement meeting to help improve the system.

[1168] In this way, this system efficiently performs a series of processes from user registration to medical consultation, health management data analysis, and feedback collection, providing comprehensive medical support to users.

[1169] Example 1

[1170] 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."

[1171] Modern healthcare systems require the provision of appropriate medical support to patients with mobility issues and users unfamiliar with medical consultations. However, existing medical consultation systems and health management apps face numerous challenges in terms of user registration, usability of dialogue interfaces, and feedback collection and utilization. For example, it is difficult to provide prompt and accurate medical advice to patients who have difficulty visiting hospitals. Furthermore, the system for providing user feedback is inadequate, slowing down service improvement. Furthermore, the functionality for effectively analyzing health data and recommending appropriate actions to users is limited. These challenges ultimately increase the risk of patients neglecting their health management.

[1172] 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.

[1173] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an information processing device means that receives the medical consultation content entered by the user, a server means that transmits the medical consultation content to the generative artificial intelligence and returns the generated response to the information processing device means, a health management data analysis means that collects data from the health management app and analyzes it using the generative artificial intelligence, a feedback means that provides the analysis results to the user, a user registration means that receives user registration information, hashes the password, and stores it in a database, and a feedback collection means that receives feedback after using the system, stores it in a database, and periodically analyzes it. This allows users to easily register and receive medical consultations in a natural, interactive format through the generative artificial intelligence, and manage their health based on the provided feedback. The system also accumulates and periodically analyzes user feedback, thereby improving the quality of its services.

[1174] "Generative AI" is an artificial intelligence technology for generating responses in natural language, and refers to algorithms that primarily use deep learning to generate appropriate outputs for various inputs.

[1175] "Medical consultation chatbot means" refers to a method and apparatus that uses generative artificial intelligence to automatically generate responses to a user's medical consultation.

[1176] "Information processing device means" refers to a device or application that has the function of receiving input from a user and transmitting data to a server via a communications network.

[1177] The term "server means" refers to a server device that receives input data from a user, generates a response using generative artificial intelligence, and returns the response to the information processing device means.

[1178] "Health management data analysis means" refers to a means for analyzing data collected from a health management app, and refers to a function that uses generative artificial intelligence to evaluate the user's health condition and recommend appropriate actions.

[1179] "Feedback means" refers to a means for providing responses and analysis results generated by generative artificial intelligence to users.

[1180] "User registration means" refers to a device or program that has the function of collecting information required when a user registers with the system, hashing the password, and storing the information in a database.

[1181] "Feedback collection means" refers to a means that has the function of receiving feedback from users after using the system, storing it in a database, and periodically analyzing it.

[1182] The present invention is a medical consultation chatbot system that uses generative artificial intelligence and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations. This invention includes the following means.

[1183] 1. User Registration Method

[1184] The user launches the Health Support AI System application using a device (e.g., PC, smartphone, tablet) and accesses the membership registration form. The user enters their username, password, and email address in the form and taps the submit button, sending the registration information from the device to the server. The server receives the received user information, hashes the password, and stores it in a database (e.g., MySQL, PostgreSQL).

[1185] 2. Medical consultation chatbot means

[1186] The user activates the chatbot function from their device and begins a medical consultation. The device then sends the question and consultation details entered by the user to the server. The server uses generative AI (e.g., GPT-3, ChatGPT) to analyze the user message and generate an appropriate response. The server then sends the generated response to the device, which then displays the response to the user. For example, if a user enters, "I've been having trouble sleeping lately. What should I do?", the server will use a generative AI model to respond, "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, I recommend consulting a doctor."

[1187] 3. Health management data analysis tools

[1188] The user allows a health management app (e.g., Apple Health, Google Fit) to connect with a health support AI system. The device sends data collected from the health management app to a server. The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions. The device notifies the user of the analysis results, and the user manages their health based on the results. As a specific example, the server analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[1189] 4. Feedback methods

[1190] After using the system, users access the provided feedback form and enter their feedback. The terminal then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system. For example, if a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in the database and uses it for future system improvements.

[1191] In this way, the health support AI system of the present invention provides efficient and safe medical consultations and health management support through collaboration between users, terminals, and servers. This system allows patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[1192] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1193] User registration process

[1194] Step 1:

[1195] The user launches the health support AI system application on their device. The app is launched by tapping the app icon on the device's home screen. The input is "tapping the app icon" and the output is "launching the app."

[1196] Step 2:

[1197] The user taps the registration button in the application to access the registration form. The form displays fields for entering a username, password, and email address. The input is "tap the registration button" and the output is "display the registration form."

[1198] Step 3:

[1199] The user enters the required information into the form and taps the submit button. The device sends the entered username, password, and email address to the server. The input is "user registration information" and the output is "send information."

[1200] Step 4:

[1201] The server receives the user information from the terminal and hashes the password. Here, the password is securely hashed using Python's bcrypt library. The input is "user registration information" and the output is "hashed password."

[1202] Step 5:

[1203] The server stores the hashed password and other user information in a database by generating an SQL query to insert the information into the appropriate columns. The input is the hashed password and user information, and the output is to store it in the database.

[1204] Medical consultation chatbot processing flow

[1205] Step 1:

[1206] The user activates the chatbot function on their device and starts a medical consultation by tapping the "medical consultation" button in the app. The input is "tapping the medical consultation button" and the output is "activating the chatbot."

[1207] Step 2:

[1208] The user enters a question or request on the chat screen and taps the send button. The device then sends this information to the server. The input is the user's question, and the output is a message sent to the server.

[1209] Step 3:

[1210] The server inputs the question sent by the user as a prompt to a generative AI (e.g., GPT-3). The generative AI analyzes the user message and generates an appropriate response. The input is the "user's question" and the output is the "generated response."

[1211] Step 4:

[1212] The server sends the generated response to the terminal, which then displays it to the user. Specifically, the AI's response message is displayed on the chat screen. The input is the "generated response" and the output is "display to the user."

[1213] Health management data analysis process flow

[1214] Step 1:

[1215] The user allows the health management app to link with the health support AI system. They tap the "Link" button on the app settings screen and grant the necessary access permissions. The input is "tap the link button" and the output is "allow link settings."

[1216] Step 2:

[1217] The device sends data collected from the health management app to the server. Collected data includes the number of steps, heart rate, sleep data, etc. The input is "health management data" and the output is "transmission to the server."

[1218] Step 3:

[1219] The server analyzes the collected health data using generative artificial intelligence. Specifically, it processes the data using Python libraries (e.g., Pandas) and machine learning models. The input is "health management data" and the output is "analysis results."

[1220] Step 4:

[1221] The server notifies the user of the analysis results, which are then displayed on the device. The analysis results include an assessment of the user's health status and recommended actions. The input is the "analysis results" and the output is "notification to the user." For example, the message might read, "Recent data suggests that your stress level is increasing. Try to spend more time relaxing."

[1222] Feedback collection process flow

[1223] Step 1:

[1224] After using the system, users access the provided feedback form and enter their impressions and suggestions for improvement. The input is "feedback input content" and the output is "input to the feedback form."

[1225] Step 2:

[1226] The terminal sends the feedback content entered by the user to the server. The input is "feedback content" and the output is "transmission to server."

[1227] Step 3:

[1228] The server saves the received feedback data in a database. Specifically, it generates an SQL query and inserts it into the database. The input is "feedback content" and the output is "saving to database."

[1229] Step 4:

[1230] The server periodically analyzes the accumulated feedback data and uses it to improve the system. It uses Python data analysis tools (e.g., Pandas, Matplotlib). The input is "feedback data" and the output is "analysis results and system improvement proposals."

[1231] In this way, the health support AI system of the present invention provides medical consultation and health management support efficiently and safely through a series of processing steps in which the user, terminal, and server work together.

[1232] (Application example 1)

[1233] 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."

[1234] The present invention relates to a system that monitors the health status of employees in real time and provides appropriate healthcare advice. Its purpose is to support worker health management and abnormality detection in order to improve work efficiency, particularly in work environments such as factories. Conventional health management methods have the problem of ineffective collection and analysis of health data, leading to inadequate management of worker health.

[1235] 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.

[1236] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, a terminal means that receives medical consultation content input from a user, a means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the terminal means, a health management data analysis means that collects data from a health management app and analyzes it with the generative artificial intelligence, a means that provides the user with the analysis results, a means that acquires health data from a wearable device worn by a worker and analyzes it with the generative artificial intelligence, and a means that provides the worker with health advice based on the analysis results. This makes it possible to monitor the health status of workers in real time and provide appropriate health care advice.

[1237] "Generative AI" is an AI technology that has the ability to automatically generate appropriate responses in natural language based on user input.

[1238] A "medical consultation chatbot" is a system that uses generative artificial intelligence to provide appropriate responses in natural language to users' medical questions and inquiries.

[1239] "Terminal means" refers to a means by which a user inputs and transmits medical consultation details using an input device (e.g., smartphone, tablet, computer, etc.).

[1240] The "server means" is a central management system for transmitting the medical consultation content sent by the user to the generative artificial intelligence and returning the generated response to the user's terminal.

[1241] The "health management data analysis means" is a system that uses generative artificial intelligence to analyze data collected from health management apps, evaluate the user's health status, and generate recommended actions and advice.

[1242] "Providing means" refers to the means for notifying or displaying to the user the analysis results and responses generated by the generative artificial intelligence.

[1243] A "wearable device" is a device (e.g., smartwatch, fitness tracker, etc.) that can be worn by a user at all times and is a device for collecting health data (e.g., heart rate, number of steps, sleep data, etc.).

[1244] "Healthcare advice" refers to recommendations and advice regarding health management provided to the user based on the analysis results obtained by the health data analysis means.

[1245] The system of the present invention aims to improve workers' work efficiency and support their health management by monitoring the health status of workers in working environments such as factories in real time and providing appropriate health care advice using generative artificial intelligence.

[1246] The system consists of the following components:

[1247] 1. Medical consultation chatbot using generative artificial intelligence:

[1248] Users input questions about their health in natural language. The generative AI analyzes the input and generates appropriate responses. These responses are provided to the user via a terminal.

[1249] 2. Terminal means:

[1250] The user inputs the details of the medical consultation using a terminal (e.g., a smartphone, tablet, or computer). Data is also acquired from a wearable device (e.g., a smart watch) worn by the worker. The terminal means transmits this data to the server means.

[1251] 3. Server means:

[1252] The server receives input data from the user and transmits the raw data to the generative artificial intelligence. The server then transmits the generated response back to the terminal. The server includes a health management data analysis means for analyzing the health data collected from the wearable device.

[1253] 4. Healthcare data analysis tools:

[1254] Generative AI analyzes data collected from health management apps and wearable devices to assess the user's health status, and generates appropriate health advice for workers based on the analysis results.

[1255] 5. Means of provision:

[1256] This is a means of notifying or displaying the generated analysis results and responses from the medical consultation chatbot to the user, allowing the user to immediately check the analysis results and take appropriate action.

[1257] As a specific example, if a wearable device records data such as "heart rate 110, steps 15,000, sleep time 5 hours, stress level high," generative AI will analyze this and generate advice such as "Take a break and hydrate. We recommend that you rest early so that it doesn't affect your work tomorrow."

[1258] Prompt Sentence Examples

[1259] "Analyze the following health data and provide recommendations. Health data: heart rate 110, steps 15000, sleep hours 5, stress level high"

[1260] In this way, it is possible to provide health management and real-time healthcare advice to factory workers. The main hardware used includes smartwatches and fitness trackers, and the main software uses Aiohttp (asynchronous HTTP communication) and generative artificial intelligence APIs (e.g., OpenAI API).

[1261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1262] Step 1:

[1263] The user launches the medical consultation chatbot application on their device and accesses the health support AI system. The user enters their username, password, and email address into the membership registration form and submits the registration information. This information is sent to the server, which hashes the password and then stores the registration information in a database. This completes user registration.

[1264] Input: Username, Password, Email Address

[1265] Output: User registration information

[1266] Step 2:

[1267] The user launches the chatbot from their device and begins a medical consultation. The questions and consultation details entered by the user are sent from the device to the server. The server uses generative artificial intelligence to analyze the user's message and generate an appropriate response. The generated response is then sent from the server to the device and displayed to the user.

[1268] Input: User's question or inquiry

[1269] Output: Response by generative artificial intelligence

[1270] Step 3:

[1271] Health data such as heart rate, number of steps, sleep time, and stress level are collected from wearable devices (e.g., smartwatches) worn by workers. This data is sent to a server via the device. The server uses generative artificial intelligence to analyze the health data, evaluate the user's health condition, and generate analysis results.

[1272] Input: Health data (heart rate, steps, sleep time, stress level)

[1273] Output: Health status assessment and analysis results

[1274] Step 4:

[1275] The server generates appropriate health advice based on the analysis results and sends it to the device, which then notifies or displays the advice to the user, allowing the user to take action accordingly.

[1276] Input: Analysis results

[1277] Output: Health advice

[1278] Step 5:

[1279] After using the system, users fill out the provided feedback form on their device. The device then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[1280] Input: User feedback

[1281] Output: Improvement proposals or materials for system improvement

[1282] In this way, users, devices, and servers can work together to monitor and manage workers' health status in real time and provide appropriate advice.

[1283] 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.

[1284] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes the user's emotions, and aims to provide appropriate and emotionally sensitive medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[1285] The system includes the following means:

[1286] 1. User Registration

[1287] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[1288] (2) The user enters their username, password, and email address into the form and sends it from their device to the server.

[1289] (3) The server processes the received user information and hashes the password for security purposes.

[1290] (4) The server stores the hashed passwords and other user data in a database.

[1291] 2. Interacting with a chatbot

[1292] (1) The user launches the chatbot from their device and accesses the screen for medical consultation.

[1293] (2) The terminal sends the questions and inquiries entered by the user to the server.

[1294] (3) The server passes the received user message to the emotion engine and analyzes the emotion along with the user message.

[1295] (4) The server processes the user message along with the analyzed emotions using generative artificial intelligence and generates an appropriate response.

[1296] (5) The server receives the generated response and returns it to the terminal.

[1297] (6) The terminal displays the generated response to the user.

[1298] Examples:

[1299] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a gentle, encouraging response, such as "Reviewing your sleep environment and increasing your daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[1300] 3. Health Management Data Analysis

[1301] (1) The user allows the health management app to link with the health support AI system.

[1302] (2) The device sends the data collected from the health management app to the server.

[1303] (3) The server passes the received health data to the generative artificial intelligence, which then analyzes the data.

[1304] (4) The server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[1305] (5) The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[1306] (6) The device notifies the user of the analysis results, and the user manages their health based on the results.

[1307] Examples:

[1308] The system analyzes heart rate and sleep data collected from health management apps, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[1309] 4. Feedback Collection

[1310] (1) After using the system, the user opens the provided feedback form on their terminal and enters their feedback.

[1311] (2) The terminal transmits the input feedback to the server.

[1312] (3) The server stores the received feedback data in a database.

[1313] (4) The server periodically extracts the feedback data from the database and analyzes it.

[1314] (5) The server improves the system based on the results of the analysis of the feedback.

[1315] Examples:

[1316] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[1317] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[1318] The processing flow will be explained below.

[1319] Detailed Process Steps of the Detailed Description

[1320] User Registration

[1321] Step 1:

[1322] The user launches the health support AI system application on their device and accesses the membership registration form.

[1323] Step 2:

[1324] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[1325] Step 3:

[1326] The server analyzes the received user information and hashes the password for security purposes.

[1327] Step 4:

[1328] The server stores the hashed passwords and other user data in a database.

[1329] Interacting with a chatbot

[1330] Step 1:

[1331] The user launches the chatbot from their device and accesses the screen for medical consultation.

[1332] Step 2:

[1333] The device sends the questions and inquiries entered by the user to the server.

[1334] Step 3:

[1335] The server passes the user message to the emotion engine, which analyzes the user's emotion.

[1336] Step 4:

[1337] The server passes the analyzed emotional information to a generative AI, which generates a response based on the user message and emotional information.

[1338] Step 5:

[1339] The server receives the generated response and sends it back to the terminal.

[1340] Step 6:

[1341] The terminal displays the generated response to the user.

[1342] Examples:

[1343] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a response saying, "Reviewing your sleeping environment and increasing daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[1344] Health management data analysis

[1345] Step 1:

[1346] The user allows linking with the health management app.

[1347] Step 2:

[1348] The device sends the data collected from the health management app to the server.

[1349] Step 3:

[1350] The server passes the received health data to an emotion engine and analyzes the user's emotional information.

[1351] Step 4:

[1352] The server passes emotional information and health data to a generative AI for data analysis.

[1353] Step 5:

[1354] The server receives the analysis results and sends them to the terminal.

[1355] Step 6:

[1356] The device will notify the user of the analysis results.

[1357] Examples:

[1358] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[1359] Feedback collection

[1360] Step 1:

[1361] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[1362] Step 2:

[1363] The terminal transmits the input feedback to the server.

[1364] Step 3:

[1365] The server stores the received feedback in a database.

[1366] Step 4:

[1367] The server periodically extracts the feedback data from the database and performs analysis.

[1368] Step 5:

[1369] The server will improve the system based on the results of the feedback analysis.

[1370] Examples:

[1371] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[1372] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[1373] Example 2

[1374] 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."

[1375] The problem that this invention aims to solve is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. Current medical consultation systems often return uniform responses without considering the user's emotions, resulting in a lack of trust and security. Furthermore, they lack the functionality to comprehensively analyze health management data and provide feedback to the user, making it difficult for users to properly understand their own health status.

[1376] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an input device means that receives the medical consultation content input by the user, a processing device means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the input device means, a processing device means that includes an emotion engine that recognizes the user's emotions to perform emotion analysis, a health management data analysis means that collects data from a health management app and analyzes it using the generative artificial intelligence, and a providing means that provides the analysis results to the user. This makes it possible to provide a response that takes the user's emotions into consideration and to perform comprehensive health management data analysis, allowing the user to more appropriately understand their health condition.

[1377] "Generative AI" is an AI system that uses large amounts of data to generate natural language, allowing for smooth dialogue with users.

[1378] A "medical consultation chatbot means" is a means that uses generative artificial intelligence to generate responses in natural language to users' medical questions and consultation details.

[1379] The "input device means" refers to a digital device that provides an interface for users to input questions or inquiries, and includes, for example, a smartphone or computer.

[1380] "Processing device means" refers to a server or cloud computing environment that receives input from a user and performs appropriate processing using generative artificial intelligence or an emotion analysis engine.

[1381] An "emotion engine" is software or a system that has the ability to analyze user input and identify emotions, and is used to process information taking into account the user's psychological state.

[1382] The "health management data analysis means" is a system that has the function of analyzing data collected from a health management app using generative artificial intelligence and outputting the results.

[1383] "Means of provision" refers to the interface for providing analysis results, chatbot responses, etc. to users, and is a device or function that enables users to receive appropriate information.

[1384] The above are definitions of important terms related to the present invention.

[1385] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes user emotions. The goal is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. This system is explained in the following sections:

[1386] User Registration

[1387] First, a user launches the Health Support AI System application on a device (smartphone or computer) and accesses the membership registration form. They enter their username, password, and email address into the form, which is then sent from the device to the server. The server processes the received user information and hashes the password using the SHA-256 algorithm. The hashed password and other user data are then stored in a database such as MySQL or PostgreSQL.

[1388] Interacting with a chatbot

[1389] The user launches the chatbot from their device and accesses the screen for medical consultations. The device sends the question and consultation details entered by the user to the server. The server passes the received message to the Microsoft Text Analytics API and analyzes the user's emotions. The server then uses the API of generative AI (OpenAI GPT-3) to generate an appropriate response based on the analyzed emotions and consultation details. The generated response is sent back from the server to the device, which then displays it to the user.

[1390] Examples:

[1391] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety. The generative AI generates a gentle, encouraging response, saying, "Reviewing your sleep environment and increasing daytime activity may be effective. We also recommend consulting a doctor if necessary." This response is sent to the device and displayed to the user.

[1392] Health management data analysis

[1393] The user allows a health management app (such as Apple Health or Google Fit) to connect with the health support AI system. The device sends data collected from the health management app to the server. The server passes the received data to the generative AI for data analysis. Furthermore, the server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results. The server sends the analysis results to the device, which then notifies the user of the results.

[1394] Examples:

[1395] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[1396] Feedback collection

[1397] After using the system, the user opens the provided feedback form on their device and enters their feedback. The device then sends the entered feedback to the server. The server stores the received feedback data in a database, periodically extracts the feedback data from the database, and analyzes it. The system is improved based on the analysis results.

[1398] Examples:

[1399] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[1400] The system provides responses that take the user's emotions into consideration, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind. It also provides specific advice based on the analysis of health management data, allowing users to better understand their own health condition.

[1401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1402] User Registration

[1403] Step 1:

[1404] The user launches the health support AI system application on their device and accesses the membership registration form.

[1405] Input: None

[1406] Output: Display of member registration form

[1407] Specific operation: When the application is launched, the device browser or in-app browser displays a web page with a membership registration form.

[1408] Step 2:

[1409] The user enters their "username," "password," and "email address" in the form and presses the "Register" button.

[1410] Input: Username, Password, Email Address

[1411] Output: Registration data in JSON format

[1412] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[1413] Step 3:

[1414] The server receives the received user information and hashes the password using the SHA-256 algorithm.

[1415] Input: Registration data in JSON format

[1416] Output: Hashed password

[1417] What happens: The server parses the user information and hashes the password field with the SHA-256 algorithm.

[1418] Step 4:

[1419] The server stores hashed passwords and other user data in a database.

[1420] Input: Hashed passwords and other user data

[1421] Output: Save registration data to database

[1422] Specific operation: The server executes the generated SQL query and stores the data in a database such as MySQL or PostgreSQL.

[1423] Interacting with a chatbot

[1424] Step 1:

[1425] The user launches the chatbot from their device and accesses the medical consultation screen.

[1426] Input: None

[1427] Output: Display of medical consultation interface

[1428] What it does: The app or web browser displays an interface for medical consultation.

[1429] Step 2:

[1430] The user inputs the question or inquiry and presses the send button.

[1431] Input: Question or inquiry

[1432] Output: Message data in JSON format

[1433] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[1434] Step 3:

[1435] The server passes the received user message to the emotion engine and analyzes the user's emotion.

[1436] Input: Message data in JSON format

[1437] Output: Emotion analysis results

[1438] Specific operation: The server sends message data to an emotion engine (such as Microsoft Text Analytics API) and receives the emotion analysis results.

[1439] Step 4:

[1440] The server uses generative AI to input the analyzed emotions and messages as prompts and generate an appropriate response.

[1441] Input: Sentiment analysis results, user message

[1442] Output: The generated response

[1443] Specific operation: The server sends the emotion analysis results and messages as prompts to the generative AI (such as OpenAI GPT-3) and receives the generated responses.

[1444] Step 5:

[1445] The server generates a response and sends it back to the terminal.

[1446] Input: Generated response

[1447] Output: Response data in JSON format

[1448] Specific operation: The server sends the generated response data to the terminal.

[1449] Step 6:

[1450] The terminal displays the response received from the server to the user.

[1451] Input: Response data in JSON format

[1452] Output: Response displayed on the screen

[1453] Specific behavior: The device parses the received data and displays the response in the user interface.

[1454] Health management data analysis

[1455] Step 1:

[1456] The user allows the health management app to link with the health support AI system.

[1457] Input: Collaboration permission settings

[1458] Output: Connection permission confirmation message

[1459] Specific operation: When the user sets permission for linking within the app, the health management app will begin data linking.

[1460] Step 2:

[1461] The device sends the data collected from the health management app to the server.

[1462] Input: Collected health data

[1463] Output: Health data in JSON format

[1464] Specific operation: The terminal converts the collected data into JSON format and sends it to the server.

[1465] Step 3:

[1466] The server passes the received data to the generative AI, which then analyzes the data.

[1467] Input: Health data in JSON format

[1468] Output: Analysis results

[1469] Specific operation: The server sends data to the generative AI and receives the analysis results.

[1470] Step 4:

[1471] The server monitors stress levels based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[1472] Input: Analysis data from generative AI, emotion analysis results

[1473] Output: Detailed analysis results

[1474] Specific operation: The server integrates the results of the emotion engine with the health data to generate a comprehensive analysis result.

[1475] Step 5:

[1476] The server transmits the analysis results to the terminal.

[1477] Input: Detailed analysis results

[1478] Output: Parsed results in JSON format

[1479] Specific operation: The server sends the generated analysis result data to the terminal.

[1480] Step 6:

[1481] The device notifies the user of the analysis results.

[1482] Input: Parsed result in JSON format

[1483] Output: Analysis results displayed on the screen

[1484] Specific operation: The device parses the analysis results received and displays them as notifications in the user interface.

[1485] Feedback collection

[1486] Step 1:

[1487] After using the system, the user opens the provided feedback form on the terminal.

[1488] Input: None

[1489] Output: Feedback form displayed

[1490] Specific operation: When the user clicks on the feedback form link after using the service, the form will be displayed.

[1491] Step 2:

[1492] The user enters the feedback and presses the send button.

[1493] Input: Feedback

[1494] Output: Feedback data in JSON format

[1495] Specific operation: The device converts the input feedback into JSON format and sends it to the server.

[1496] Step 3:

[1497] The server stores the received feedback data in a database.

[1498] Input: Feedback data in JSON format

[1499] Output: Save to database

[1500] Specific operation: The server registers the feedback data in a database.

[1501] Step 4:

[1502] The server periodically extracts the feedback data from the database and performs analysis.

[1503] Input: Feedback data in the database

[1504] Output: Analysis results

[1505] Specific operation: The server periodically extracts feedback data from the database and analyzes it using techniques such as natural language processing.

[1506] Step 5:

[1507] The server will improve the system based on the results of the analysis of the feedback.

[1508] Input: Feedback analysis results

[1509] Output: Improved system

[1510] Specific operation: The server takes into account the feedback analysis results and implements system improvements such as chatbot responses and user interface.

[1511] The above is a detailed flow of the processing of this system's program. By specifically performing a series of data processing and data calculations from input to output at each processing step, it is possible to provide high-quality medical support to users.

[1512] (Application example 2)

[1513] 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."

[1514] In today's world, security threats exploiting the Internet are rapidly increasing, increasing the information security risks for individuals and businesses. The risks are particularly severe for people with mobility issues, such as the elderly, people with disabilities, and people with chronic illnesses, who often lack specialized security knowledge. There is a need for systems that allow these people to receive appropriate security consultations and support from home. It is also important to provide appropriate advice that takes into account the user's emotions, but existing systems lack the ability to analyze and respond to emotions, making improving user satisfaction a challenge.

[1515] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1516] In this invention, the server includes security consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, terminal means that receives security consultation content input from a user, server means that transmits the security consultation content to the generative artificial intelligence and returns a generated response to the terminal means, security management data analysis means that collects data from a security management app and analyzes it with the generative artificial intelligence, means that provides the analysis results to the user, emotion engine means that recognizes emotions, and means that collect feedback and improve the system. This enables people who have difficulty moving around to receive appropriate security advice from home that takes emotions into consideration.

[1517] "Generative AI" is an AI system that generates natural language and provides a response to user input.

[1518] The "security consultation chatbot means that responds in natural language" is a system that uses generative artificial intelligence to respond in natural language to security-related questions and inquiries.

[1519] The "terminal means for receiving security consultation details input by the user" refers to a device or system for receiving security-related questions and consultation details input by the user at a terminal.

[1520] The "server means for returning the generated response to the terminal means" is a server for transmitting the answer generated by the generative artificial intelligence to the terminal.

[1521] A "security management app" is software for managing and monitoring a user's security status.

[1522] The "security management data analysis means" is a system that analyzes data collected from the security management app and generates appropriate advice and suggestions for users.

[1523] The "emotion engine means for recognizing emotions" is a system that analyzes emotions from user input and reflects that information in responses.

[1524] "Means for collecting feedback and improving the system" refers to the processes and means for collecting user evaluations and opinions and using them to improve the performance and functionality of the system.

[1525] "Elderly, disabled and chronically ill people with mobility issues" refers to elderly people, people with disabilities or patients with long-term health problems who have difficulty moving freely due to physical limitations.

[1526] "Appropriate security consultation and support" means providing professional and accurate advice and assistance to users regarding security issues and questions they may have.

[1527] This invention is a system that uses generative artificial intelligence and an emotion engine to provide natural responses to security-related problems and inquiries that users have. Specific embodiments are described below.

[1528] First, a user accesses the system using a device such as a smartphone or PC. The user creates an account and enters basic information such as name, password, and email address. This operation causes the device to send the entered information to the server, which then stores it in a database.

[1529] Next, the user inputs a security question or inquiry into the chatbot. For example, they send a message like, "I often receive phishing emails. What should I do about them?" At this time, the emotion engine analyzes the message and evaluates the user's emotional state in order to recognize their emotions. If emotions such as anxiety or worry are detected, the data is sent to the server taking this into consideration.

[1530] The server analyzes the received data using generative artificial intelligence and generates an appropriate response. The generated response takes into account the user's emotional state and provides specific and reassuring information, such as "First, check the sender and links in the email, and if they seem suspicious, never click on them. It is also important to keep your security software up to date." The device then displays this response to the user.

[1531] For users using security management apps, logs and alert data collected from the app are also transferred to the server. The server then analyzes this data using generative artificial intelligence to assess the user's stress level and the system's security status. For example, it generates feedback such as, "Recent data indicates that many security alerts have been generated. We recommend a comprehensive review of your system." and notifies the user.

[1532] To collect feedback, users can fill out a feedback form after using the system. The terminal sends the entered feedback to the server, which stores it in a database. This information is periodically analyzed and used to improve the system.

[1533] The hardware and software used includes:

[1534] Hardware: smartphones, PCs, servers

[1535] Software: Python, SQLite, EmotionEngine (emotion engine library), AIResponseGenerator (generative artificial intelligence library)

[1536] Examples:

[1537] A user asks, "I've been receiving a lot of phishing emails lately. What should I do?"

[1538] The emotion engine recognizes the user's "anxiety," and the generative artificial intelligence generates a response such as, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[1539] Example prompt sentence:

[1540] A user asked, "I've been receiving a lot of phishing emails lately. What should I do?"

[1541] The emotion engine recognized the user's "anxiety."

[1542] Generate a response that is appropriate and reassuring in this context.

[1543] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1544] Step 1:

[1545] A user accesses the system and creates an account.

[1546] Input: Username, Password, Email Address

[1547] Specific operation: The user accesses the system's membership registration form using a device such as a smartphone or PC. They enter basic information such as their username, password, and email address into the form and press the submit button.

[1548] Output: User information sent from the device to the server

[1549] Step 2:

[1550] The server processes the received user information and stores it in a database.

[1551] Input: User information sent from the device (username, password, email address)

[1552] What it does: The server hashes the information it receives for security purposes and stores the user information in a database along with the hashed password.

[1553] Output: User information stored in the database

[1554] Step 3:

[1555] The user inputs a question or inquiry into the security consultation chatbot.

[1556] Input: Questions or inquiries about security

[1557] Specific operation: The user accesses the system's chatbot screen, enters the content of their inquiry in text, and presses the send button.

[1558] Output: Consultation details sent from the device to the server

[1559] Step 4:

[1560] The server analyzes the consultation content received by the server using an emotion engine and evaluates the emotional state.

[1561] Input: User's inquiry

[1562] Specific operation: The server passes the received consultation content to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes emotions such as "anxiety" and "worry" and returns the results.

[1563] Output: Sentiment analysis result (e.g., "anxiety")

[1564] Step 5:

[1565] The server passes the results of the emotion engine to a generative artificial intelligence system, which generates an appropriate response.

[1566] Input: Consultation details, emotion analysis results

[1567] Specific operation: The server uses generative AI to generate an appropriate response based on the content of the consultation and the results of emotion analysis. For example, if a user consults about phishing scams and detects "anxiety," the server will respond by saying, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[1568] Output: The generated response

[1569] Step 6:

[1570] The server sends the generated response back to the user terminal.

[1571] Input: Generated response

[1572] Specific operation: The server sends the generated response data to the terminal.

[1573] Output: The response displayed on the user's terminal

[1574] Step 7:

[1575] The user terminal displays the response on the screen.

[1576] Input: The response sent by the server

[1577] Specific operation: The terminal displays the received response on the screen and notifies the user.

[1578] Output: The response displayed to the user

[1579] Step 8:

[1580] The user sends the collected data from the security management app to the server.

[1581] Input: Data from security management apps (logs, alerts, etc.)

[1582] Specific operation: The user launches the security management app and allows data collection and transmission. The device sends the data collected from the app to the server.

[1583] Output: Security data sent to the server

[1584] Step 9:

[1585] The server analyzes the security data and generates appropriate feedback.

[1586] Input: Security Data

[1587] How it works: The server uses generative artificial intelligence to analyze the collected data and evaluate the user's stress level and the system's security status. For example, if a large number of security alerts are detected, the server generates feedback such as "We recommend a comprehensive review of the system."

[1588] Output: Generated feedback

[1589] Step 10:

[1590] The user terminal displays the generated feedback on the screen.

[1591] Input: Feedback sent by the server

[1592] Specific operation: The device displays the received feedback on the screen and notifies the user.

[1593] Output: Feedback displayed to the user

[1594] Step 11:

[1595] The user fills in the feedback form and submits it.

[1596] Input: Feedback

[1597] Specific operation: After using the system, the user accesses the feedback form, enters their evaluation and opinions, and presses the submit button.

[1598] Output: Feedback sent from the device to the server

[1599] Step 12:

[1600] The server stores the received feedback in a database and analyzes it periodically.

[1601] Input: Feedback sent by the user

[1602] Specific operation: The server stores the received feedback in a database, analyzes the data periodically, and uses the results to improve the system's performance and functionality.

[1603] Output: Feedback data stored in a database and system improvement suggestions

[1604] 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.

[1605] 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.

[1606] 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.

[1607] [Fourth embodiment]

[1608] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1609] 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.

[1610] 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).

[1611] 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.

[1612] 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.

[1613] 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).

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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."

[1621] This invention is a medical consultation chatbot system that uses generative artificial intelligence, and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[1622] The system includes the following means:

[1623] 1. User Registration

[1624] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[1625] (2) The user enters their username, password, and email address into the form and submits the registration information from their device.

[1626] (3) The server processes the received user information, hashes the password, and stores it in the database.

[1627] 2. Interacting with a chatbot

[1628] (1) The user launches the chatbot from their device and begins a medical consultation.

[1629] (2) The terminal sends the questions and inquiries entered by the user to the server.

[1630] (3) The server uses generative artificial intelligence to analyze the user message and generate an appropriate response.

[1631] (4) The server sends the generated response to the terminal, which displays the response to the user.

[1632] Examples:

[1633] When a user types, "I haven't been sleeping well lately. What should I do?", the generative AI responds, "Reviewing your sleep environment and increasing your daytime activity may be effective. If necessary, I recommend consulting a doctor."

[1634] 3. Health Management Data Analysis

[1635] (1) The user allows the health management app to link with the health support AI system.

[1636] (2) The device sends the data collected from the health management app to the server.

[1637] (3) The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions.

[1638] (4) The device notifies the user of the analysis results, and the user manages their health based on the results.

[1639] Examples:

[1640] It analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[1641] 4. Feedback Collection

[1642] (1) After using the system, the user fills out the provided feedback form on the terminal.

[1643] (2) The device sends the user's feedback to the server.

[1644] (3) The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[1645] Examples:

[1646] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in a database and uses it to improve the system in the future.

[1647] In this way, the health support AI system provides efficient and safe medical consultations and health management support by linking users, devices, and servers, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[1648] The processing flow will be explained below.

[1649] Detailed Process Steps of the Detailed Description

[1650] User Registration

[1651] Step 1:

[1652] The user launches the health support AI system app on their device and accesses the membership registration form.

[1653] Step 2:

[1654] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[1655] Step 3:

[1656] The server analyzes the received user information and hashes the password for security purposes.

[1657] Step 4:

[1658] The server stores the hashed passwords and other user data in a database.

[1659] Interacting with a chatbot

[1660] Step 1:

[1661] The user launches the chatbot from their device and accesses the screen for medical consultation.

[1662] Step 2:

[1663] The device sends the questions and inquiries entered by the user to the server.

[1664] Step 3:

[1665] The server passes the received user message to a generative artificial intelligence, which generates an appropriate response.

[1666] Step 4:

[1667] The server receives the generated response and sends it back to the terminal.

[1668] Step 5:

[1669] The terminal displays the generated response to the user.

[1670] Examples:

[1671] When a user types, "I haven't been sleeping well lately. What should I do?", the server uses generative artificial intelligence to generate a response: "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[1672] Health management data analysis

[1673] Step 1:

[1674] The user allows the health management app to link with the health support AI system.

[1675] Step 2:

[1676] The device sends the data collected from the health management app to the server.

[1677] Step 3:

[1678] The server passes the received health data to generative artificial intelligence, which then analyzes the data.

[1679] Step 4:

[1680] The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[1681] Step 5:

[1682] The device will notify the user of the analysis results.

[1683] Examples:

[1684] It analyzes heart rate and sleep data collected from health management apps and generates feedback to notify the user, such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[1685] Feedback collection

[1686] Step 1:

[1687] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[1688] Step 2:

[1689] The terminal transmits the input feedback to the server.

[1690] Step 3:

[1691] The server stores the received feedback data in a database.

[1692] Step 4:

[1693] The server periodically extracts the feedback data from the database and performs analysis.

[1694] Step 5:

[1695] The server will improve the system based on the results of the feedback analysis.

[1696] Examples:

[1697] When a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this information in a database and references it at a future improvement meeting to help improve the system.

[1698] In this way, this system efficiently performs a series of processes from user registration to medical consultation, health management data analysis, and feedback collection, providing comprehensive medical support to users.

[1699] Example 1

[1700] 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."

[1701] Modern healthcare systems require the provision of appropriate medical support to patients with mobility issues and users unfamiliar with medical consultations. However, existing medical consultation systems and health management apps face numerous challenges in terms of user registration, usability of dialogue interfaces, and feedback collection and utilization. For example, it is difficult to provide prompt and accurate medical advice to patients who have difficulty visiting hospitals. Furthermore, the system for providing user feedback is inadequate, slowing down service improvement. Furthermore, the functionality for effectively analyzing health data and recommending appropriate actions to users is limited. These challenges ultimately increase the risk of patients neglecting their health management.

[1702] 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.

[1703] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an information processing device means that receives the medical consultation content entered by the user, a server means that transmits the medical consultation content to the generative artificial intelligence and returns the generated response to the information processing device means, a health management data analysis means that collects data from the health management app and analyzes it using the generative artificial intelligence, a feedback means that provides the analysis results to the user, a user registration means that receives user registration information, hashes the password, and stores it in a database, and a feedback collection means that receives feedback after using the system, stores it in a database, and periodically analyzes it. This allows users to easily register and receive medical consultations in a natural, interactive format through the generative artificial intelligence, and manage their health based on the provided feedback. The system also accumulates and periodically analyzes user feedback, thereby improving the quality of its services.

[1704] "Generative AI" is an artificial intelligence technology for generating responses in natural language, and refers to algorithms that primarily use deep learning to generate appropriate outputs for various inputs.

[1705] "Medical consultation chatbot means" refers to a method and apparatus that uses generative artificial intelligence to automatically generate responses to a user's medical consultation.

[1706] "Information processing device means" refers to a device or application that has the function of receiving input from a user and transmitting data to a server via a communications network.

[1707] The term "server means" refers to a server device that receives input data from a user, generates a response using generative artificial intelligence, and returns the response to the information processing device means.

[1708] "Health management data analysis means" refers to a means for analyzing data collected from a health management app, and refers to a function that uses generative artificial intelligence to evaluate the user's health condition and recommend appropriate actions.

[1709] "Feedback means" refers to a means for providing responses and analysis results generated by generative artificial intelligence to users.

[1710] "User registration means" refers to a device or program that has the function of collecting information required when a user registers with the system, hashing the password, and storing the information in a database.

[1711] "Feedback collection means" refers to a means that has the function of receiving feedback from users after using the system, storing it in a database, and periodically analyzing it.

[1712] The present invention is a medical consultation chatbot system that uses generative artificial intelligence and aims to provide appropriate medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations. This invention includes the following means.

[1713] 1. User Registration Method

[1714] The user launches the Health Support AI System application using a device (e.g., PC, smartphone, tablet) and accesses the membership registration form. The user enters their username, password, and email address in the form and taps the submit button, sending the registration information from the device to the server. The server receives the received user information, hashes the password, and stores it in a database (e.g., MySQL, PostgreSQL).

[1715] 2. Medical consultation chatbot means

[1716] The user activates the chatbot function from their device and begins a medical consultation. The device then sends the question and consultation details entered by the user to the server. The server uses generative AI (e.g., GPT-3, ChatGPT) to analyze the user message and generate an appropriate response. The server then sends the generated response to the device, which then displays the response to the user. For example, if a user enters, "I've been having trouble sleeping lately. What should I do?", the server will use a generative AI model to respond, "Reviewing your sleep environment and increasing daytime activity may be effective. If necessary, I recommend consulting a doctor."

[1717] 3. Health management data analysis tools

[1718] The user allows a health management app (e.g., Apple Health, Google Fit) to connect with a health support AI system. The device sends data collected from the health management app to a server. The server uses generative artificial intelligence to analyze the health data and generate information about the user's health status and recommended actions. The device notifies the user of the analysis results, and the user manages their health based on the results. As a specific example, the server analyzes the user's heart rate and sleep data and provides feedback such as, "Recent data suggests that your stress level is increasing. You should spend more time relaxing."

[1719] 4. Feedback methods

[1720] After using the system, users access the provided feedback form and enter their feedback. The terminal then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system. For example, if a user provides feedback such as "The consultation was very helpful. There is nothing in particular that needs improvement," the server stores this in the database and uses it for future system improvements.

[1721] In this way, the health support AI system of the present invention provides efficient and safe medical consultations and health management support through collaboration between users, terminals, and servers. This system allows patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind.

[1722] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1723] User registration process

[1724] Step 1:

[1725] The user launches the health support AI system application on their device. The app is launched by tapping the app icon on the device's home screen. The input is "tapping the app icon" and the output is "launching the app."

[1726] Step 2:

[1727] The user taps the registration button in the application to access the registration form. The form displays fields for entering a username, password, and email address. The input is "tap the registration button" and the output is "display the registration form."

[1728] Step 3:

[1729] The user enters the required information into the form and taps the submit button. The device sends the entered username, password, and email address to the server. The input is "user registration information" and the output is "send information."

[1730] Step 4:

[1731] The server receives the user information from the terminal and hashes the password. Here, the password is securely hashed using Python's bcrypt library. The input is "user registration information" and the output is "hashed password."

[1732] Step 5:

[1733] The server stores the hashed password and other user information in a database by generating an SQL query to insert the information into the appropriate columns. The input is the hashed password and user information, and the output is to store it in the database.

[1734] Medical consultation chatbot processing flow

[1735] Step 1:

[1736] The user activates the chatbot function on their device and starts a medical consultation by tapping the "medical consultation" button in the app. The input is "tapping the medical consultation button" and the output is "activating the chatbot."

[1737] Step 2:

[1738] The user enters a question or request on the chat screen and taps the send button. The device then sends this information to the server. The input is the user's question, and the output is a message sent to the server.

[1739] Step 3:

[1740] The server inputs the question sent by the user as a prompt to a generative AI (e.g., GPT-3). The generative AI analyzes the user message and generates an appropriate response. The input is the "user's question" and the output is the "generated response."

[1741] Step 4:

[1742] The server sends the generated response to the terminal, which then displays it to the user. Specifically, the AI's response message is displayed on the chat screen. The input is the "generated response" and the output is "display to the user."

[1743] Health management data analysis process flow

[1744] Step 1:

[1745] The user allows the health management app to link with the health support AI system. They tap the "Link" button on the app settings screen and grant the necessary access permissions. The input is "tap the link button" and the output is "allow link settings."

[1746] Step 2:

[1747] The device sends data collected from the health management app to the server. Collected data includes the number of steps, heart rate, sleep data, etc. The input is "health management data" and the output is "transmission to the server."

[1748] Step 3:

[1749] The server analyzes the collected health data using generative artificial intelligence. Specifically, it processes the data using Python libraries (e.g., Pandas) and machine learning models. The input is "health management data" and the output is "analysis results."

[1750] Step 4:

[1751] The server notifies the user of the analysis results, which are then displayed on the device. The analysis results include an assessment of the user's health status and recommended actions. The input is the "analysis results" and the output is "notification to the user." For example, the message might read, "Recent data suggests that your stress level is increasing. Try to spend more time relaxing."

[1752] Feedback collection process flow

[1753] Step 1:

[1754] After using the system, users access the provided feedback form and enter their impressions and suggestions for improvement. The input is "feedback input content" and the output is "input to the feedback form."

[1755] Step 2:

[1756] The terminal sends the feedback content entered by the user to the server. The input is "feedback content" and the output is "transmission to server."

[1757] Step 3:

[1758] The server saves the received feedback data in a database. Specifically, it generates an SQL query and inserts it into the database. The input is "feedback content" and the output is "saving to database."

[1759] Step 4:

[1760] The server periodically analyzes the accumulated feedback data and uses it to improve the system. It uses Python data analysis tools (e.g., Pandas, Matplotlib). The input is "feedback data" and the output is "analysis results and system improvement proposals."

[1761] In this way, the health support AI system of the present invention provides medical consultation and health management support efficiently and safely through a series of processing steps in which the user, terminal, and server work together.

[1762] (Application example 1)

[1763] 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."

[1764] The present invention relates to a system that monitors the health status of employees in real time and provides appropriate healthcare advice. Its purpose is to support worker health management and abnormality detection in order to improve work efficiency, particularly in work environments such as factories. Conventional health management methods have the problem of ineffective collection and analysis of health data, leading to inadequate management of worker health.

[1765] 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.

[1766] In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, a terminal means that receives medical consultation content input from a user, a means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the terminal means, a health management data analysis means that collects data from a health management app and analyzes it with the generative artificial intelligence, a means that provides the user with the analysis results, a means that acquires health data from a wearable device worn by a worker and analyzes it with the generative artificial intelligence, and a means that provides the worker with health advice based on the analysis results. This makes it possible to monitor the health status of workers in real time and provide appropriate health care advice.

[1767] "Generative AI" is an AI technology that has the ability to automatically generate appropriate responses in natural language based on user input.

[1768] A "medical consultation chatbot" is a system that uses generative artificial intelligence to provide appropriate responses in natural language to users' medical questions and inquiries.

[1769] "Terminal means" refers to a means by which a user inputs and transmits medical consultation details using an input device (e.g., smartphone, tablet, computer, etc.).

[1770] The "server means" is a central management system for transmitting the medical consultation content sent by the user to the generative artificial intelligence and returning the generated response to the user's terminal.

[1771] The "health management data analysis means" is a system that uses generative artificial intelligence to analyze data collected from health management apps, evaluate the user's health status, and generate recommended actions and advice.

[1772] "Providing means" refers to the means for notifying or displaying to the user the analysis results and responses generated by the generative artificial intelligence.

[1773] A "wearable device" is a device (e.g., smartwatch, fitness tracker, etc.) that can be worn by a user at all times and is a device for collecting health data (e.g., heart rate, number of steps, sleep data, etc.).

[1774] "Healthcare advice" refers to recommendations and advice regarding health management provided to the user based on the analysis results obtained by the health data analysis means.

[1775] The system of the present invention aims to improve workers' work efficiency and support their health management by monitoring the health status of workers in working environments such as factories in real time and providing appropriate health care advice using generative artificial intelligence.

[1776] The system consists of the following components:

[1777] 1. Medical consultation chatbot using generative artificial intelligence:

[1778] Users input questions about their health in natural language. The generative AI analyzes the input and generates appropriate responses. These responses are provided to the user via a terminal.

[1779] 2. Terminal means:

[1780] The user inputs the details of the medical consultation using a terminal (e.g., a smartphone, tablet, or computer). Data is also acquired from a wearable device (e.g., a smart watch) worn by the worker. The terminal means transmits this data to the server means.

[1781] 3. Server means:

[1782] The server receives input data from the user and transmits the raw data to the generative artificial intelligence. The server then transmits the generated response back to the terminal. The server includes a health management data analysis means for analyzing the health data collected from the wearable device.

[1783] 4. Healthcare data analysis tools:

[1784] Generative AI analyzes data collected from health management apps and wearable devices to assess the user's health status, and generates appropriate health advice for workers based on the analysis results.

[1785] 5. Means of provision:

[1786] This is a means of notifying or displaying the generated analysis results and responses from the medical consultation chatbot to the user, allowing the user to immediately check the analysis results and take appropriate action.

[1787] As a specific example, if a wearable device records data such as "heart rate 110, steps 15,000, sleep time 5 hours, stress level high," generative AI will analyze this and generate advice such as "Take a break and hydrate. We recommend that you rest early so that it doesn't affect your work tomorrow."

[1788] Prompt Sentence Examples

[1789] "Analyze the following health data and provide recommendations. Health data: heart rate 110, steps 15000, sleep hours 5, stress level high"

[1790] In this way, it is possible to provide health management and real-time healthcare advice to factory workers. The main hardware used includes smartwatches and fitness trackers, and the main software uses Aiohttp (asynchronous HTTP communication) and generative artificial intelligence APIs (e.g., OpenAI API).

[1791] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1792] Step 1:

[1793] The user launches the medical consultation chatbot application on their device and accesses the health support AI system. The user enters their username, password, and email address into the membership registration form and submits the registration information. This information is sent to the server, which hashes the password and then stores the registration information in a database. This completes user registration.

[1794] Input: Username, Password, Email Address

[1795] Output: User registration information

[1796] Step 2:

[1797] The user launches the chatbot from their device and begins a medical consultation. The questions and consultation details entered by the user are sent from the device to the server. The server uses generative artificial intelligence to analyze the user's message and generate an appropriate response. The generated response is then sent from the server to the device and displayed to the user.

[1798] Input: User's question or inquiry

[1799] Output: Response by generative artificial intelligence

[1800] Step 3:

[1801] Health data such as heart rate, number of steps, sleep time, and stress level are collected from wearable devices (e.g., smartwatches) worn by workers. This data is sent to a server via the device. The server uses generative artificial intelligence to analyze the health data, evaluate the user's health condition, and generate analysis results.

[1802] Input: Health data (heart rate, steps, sleep time, stress level)

[1803] Output: Health status assessment and analysis results

[1804] Step 4:

[1805] The server generates appropriate health advice based on the analysis results and sends it to the device, which then notifies or displays the advice to the user, allowing the user to take action accordingly.

[1806] Input: Analysis results

[1807] Output: Health advice

[1808] Step 5:

[1809] After using the system, users fill out the provided feedback form on their device. The device then sends the user's feedback to the server. The server stores the feedback data in a database and periodically analyzes it to help improve the system.

[1810] Input: User feedback

[1811] Output: Improvement proposals or materials for system improvement

[1812] In this way, users, devices, and servers can work together to monitor and manage workers' health status in real time and provide appropriate advice.

[1813] 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.

[1814] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes the user's emotions, and aims to provide appropriate and emotionally sensitive medical support to patients who have difficulty moving around and users who are unfamiliar with medical consultations.

[1815] The system includes the following means:

[1816] 1. User Registration

[1817] (1) The user launches the health support AI system application on their device and accesses the membership registration form.

[1818] (2) The user enters their username, password, and email address into the form and sends it from their device to the server.

[1819] (3) The server processes the received user information and hashes the password for security purposes.

[1820] (4) The server stores the hashed passwords and other user data in a database.

[1821] 2. Interacting with a chatbot

[1822] (1) The user launches the chatbot from their device and accesses the screen for medical consultation.

[1823] (2) The terminal sends the questions and inquiries entered by the user to the server.

[1824] (3) The server passes the received user message to the emotion engine and analyzes the emotion along with the user message.

[1825] (4) The server processes the user message along with the analyzed emotions using generative artificial intelligence and generates an appropriate response.

[1826] (5) The server receives the generated response and returns it to the terminal.

[1827] (6) The terminal displays the generated response to the user.

[1828] Examples:

[1829] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a gentle, encouraging response, such as "Reviewing your sleep environment and increasing your daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[1830] 3. Health Management Data Analysis

[1831] (1) The user allows the health management app to link with the health support AI system.

[1832] (2) The device sends the data collected from the health management app to the server.

[1833] (3) The server passes the received health data to the generative artificial intelligence, which then analyzes the data.

[1834] (4) The server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[1835] (5) The server receives the analysis results from the generative artificial intelligence and sends them to the terminal.

[1836] (6) The device notifies the user of the analysis results, and the user manages their health based on the results.

[1837] Examples:

[1838] The system analyzes heart rate and sleep data collected from health management apps, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[1839] 4. Feedback Collection

[1840] (1) After using the system, the user opens the provided feedback form on their terminal and enters their feedback.

[1841] (2) The terminal transmits the input feedback to the server.

[1842] (3) The server stores the received feedback data in a database.

[1843] (4) The server periodically extracts the feedback data from the database and analyzes it.

[1844] (5) The server improves the system based on the results of the analysis of the feedback.

[1845] Examples:

[1846] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[1847] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[1848] The processing flow will be explained below.

[1849] Detailed Process Steps of the Detailed Description

[1850] User Registration

[1851] Step 1:

[1852] The user launches the health support AI system application on their device and accesses the membership registration form.

[1853] Step 2:

[1854] The user enters a user name, password, and email address into the form and sends it from the terminal to the server.

[1855] Step 3:

[1856] The server analyzes the received user information and hashes the password for security purposes.

[1857] Step 4:

[1858] The server stores the hashed passwords and other user data in a database.

[1859] Interacting with a chatbot

[1860] Step 1:

[1861] The user launches the chatbot from their device and accesses the screen for medical consultation.

[1862] Step 2:

[1863] The device sends the questions and inquiries entered by the user to the server.

[1864] Step 3:

[1865] The server passes the user message to the emotion engine, which analyzes the user's emotion.

[1866] Step 4:

[1867] The server passes the analyzed emotional information to a generative AI, which generates a response based on the user message and emotional information.

[1868] Step 5:

[1869] The server receives the generated response and sends it back to the terminal.

[1870] Step 6:

[1871] The terminal displays the generated response to the user.

[1872] Examples:

[1873] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety, and uses generative artificial intelligence to generate a response saying, "Reviewing your sleeping environment and increasing daytime activity may be effective. Also, if necessary, we recommend consulting a doctor." This response is sent to the device and displayed to the user.

[1874] Health management data analysis

[1875] Step 1:

[1876] The user allows linking with the health management app.

[1877] Step 2:

[1878] The device sends the data collected from the health management app to the server.

[1879] Step 3:

[1880] The server passes the received health data to an emotion engine and analyzes the user's emotional information.

[1881] Step 4:

[1882] The server passes emotional information and health data to a generative AI for data analysis.

[1883] Step 5:

[1884] The server receives the analysis results and sends them to the terminal.

[1885] Step 6:

[1886] The device will notify the user of the analysis results.

[1887] Examples:

[1888] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes the data as "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[1889] Feedback collection

[1890] Step 1:

[1891] After using the system, the user opens the provided feedback form on the terminal and enters feedback.

[1892] Step 2:

[1893] The terminal transmits the input feedback to the server.

[1894] Step 3:

[1895] The server stores the received feedback in a database.

[1896] Step 4:

[1897] The server periodically extracts the feedback data from the database and performs analysis.

[1898] Step 5:

[1899] The server will improve the system based on the results of the feedback analysis.

[1900] Examples:

[1901] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[1902] In this way, by combining this emotion engine, the system can provide responses that take the user's emotions into consideration and respond more appropriately to their needs. By using this system, patients with mobility issues and users unfamiliar with medical consultations can receive medical support with peace of mind.

[1903] Example 2

[1904] 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."

[1905] The problem that this invention aims to solve is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. Current medical consultation systems often return uniform responses without considering the user's emotions, resulting in a lack of trust and security. Furthermore, they lack the functionality to comprehensively analyze health management data and provide feedback to the user, making it difficult for users to properly understand their own health status.

[1906] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a medical consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, an input device means that receives the medical consultation content input by the user, a processing device means that transmits the medical consultation content to the generative artificial intelligence and returns a generated response to the input device means, a processing device means that includes an emotion engine that recognizes the user's emotions to perform emotion analysis, a health management data analysis means that collects data from a health management app and analyzes it using the generative artificial intelligence, and a providing means that provides the analysis results to the user. This makes it possible to provide a response that takes the user's emotions into consideration and to perform comprehensive health management data analysis, allowing the user to more appropriately understand their health condition.

[1907] "Generative AI" is an AI system that uses large amounts of data to generate natural language, allowing for smooth dialogue with users.

[1908] A "medical consultation chatbot means" is a means that uses generative artificial intelligence to generate responses in natural language to users' medical questions and consultation details.

[1909] The "input device means" refers to a digital device that provides an interface for users to input questions or inquiries, and includes, for example, a smartphone or computer.

[1910] "Processing device means" refers to a server or cloud computing environment that receives input from a user and performs appropriate processing using generative artificial intelligence or an emotion analysis engine.

[1911] An "emotion engine" is software or a system that has the ability to analyze user input and identify emotions, and is used to process information taking into account the user's psychological state.

[1912] The "health management data analysis means" is a system that has the function of analyzing data collected from a health management app using generative artificial intelligence and outputting the results.

[1913] "Means of provision" refers to the interface for providing analysis results, chatbot responses, etc. to users, and is a device or function that enables users to receive appropriate information.

[1914] The above are definitions of important terms related to the present invention.

[1915] This invention combines a medical consultation chatbot system using generative artificial intelligence with an emotion engine that recognizes user emotions. The goal is to provide appropriate and emotionally sensitive medical support to patients with mobility issues and users who are unfamiliar with medical consultations. This system is explained in the following sections:

[1916] User Registration

[1917] First, a user launches the Health Support AI System application on a device (smartphone or computer) and accesses the membership registration form. They enter their username, password, and email address into the form, which is then sent from the device to the server. The server processes the received user information and hashes the password using the SHA-256 algorithm. The hashed password and other user data are then stored in a database such as MySQL or PostgreSQL.

[1918] Interacting with a chatbot

[1919] The user launches the chatbot from their device and accesses the screen for medical consultations. The device sends the question and consultation details entered by the user to the server. The server passes the received message to the Microsoft Text Analytics API and analyzes the user's emotions. The server then uses the API of generative AI (OpenAI GPT-3) to generate an appropriate response based on the analyzed emotions and consultation details. The generated response is sent back from the server to the device, which then displays it to the user.

[1920] Examples:

[1921] When a user enters a message expressing anxiety, such as "I haven't been sleeping well lately. What should I do?", the server uses an emotion engine to recognize the user's anxiety. The generative AI generates a gentle, encouraging response, saying, "Reviewing your sleep environment and increasing daytime activity may be effective. We also recommend consulting a doctor if necessary." This response is sent to the device and displayed to the user.

[1922] Health management data analysis

[1923] The user allows a health management app (such as Apple Health or Google Fit) to connect with the health support AI system. The device sends data collected from the health management app to the server. The server passes the received data to the generative AI for data analysis. Furthermore, the server monitors the user's stress level based on the emotions recognized by the emotion engine and reflects this in the analysis results. The server sends the analysis results to the device, which then notifies the user of the results.

[1924] Examples:

[1925] Heart rate and sleep data collected from health management apps are analyzed, and if the emotion engine recognizes "stress," it generates feedback and notifies the user, saying, "Recent data suggests that your stress level is increasing. It's time to spend more time relaxing."

[1926] Feedback collection

[1927] After using the system, the user opens the provided feedback form on their device and enters their feedback. The device then sends the entered feedback to the server. The server stores the received feedback data in a database, periodically extracts the feedback data from the database, and analyzes it. The system is improved based on the analysis results.

[1928] Examples:

[1929] When a user provides feedback such as, "The consultation was very helpful, but I would like more specific advice," the server stores this in a database and, based on the analysis results, improves the system to make responses more specific.

[1930] The system provides responses that take the user's emotions into consideration, allowing patients with mobility issues and users unfamiliar with medical consultations to receive medical support with peace of mind. It also provides specific advice based on the analysis of health management data, allowing users to better understand their own health condition.

[1931] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1932] User Registration

[1933] Step 1:

[1934] The user launches the health support AI system application on their device and accesses the membership registration form.

[1935] Input: None

[1936] Output: Display of member registration form

[1937] Specific operation: When the application is launched, the device browser or in-app browser displays a web page with a membership registration form.

[1938] Step 2:

[1939] The user enters their "username," "password," and "email address" in the form and presses the "Register" button.

[1940] Input: Username, Password, Email Address

[1941] Output: Registration data in JSON format

[1942] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[1943] Step 3:

[1944] The server receives the received user information and hashes the password using the SHA-256 algorithm.

[1945] Input: Registration data in JSON format

[1946] Output: Hashed password

[1947] What happens: The server parses the user information and hashes the password field with the SHA-256 algorithm.

[1948] Step 4:

[1949] The server stores hashed passwords and other user data in a database.

[1950] Input: Hashed passwords and other user data

[1951] Output: Save registration data to database

[1952] Specific operation: The server executes the generated SQL query and stores the data in a database such as MySQL or PostgreSQL.

[1953] Interacting with a chatbot

[1954] Step 1:

[1955] The user launches the chatbot from their device and accesses the medical consultation screen.

[1956] Input: None

[1957] Output: Display of medical consultation interface

[1958] What it does: The app or web browser displays an interface for medical consultation.

[1959] Step 2:

[1960] The user inputs the question or inquiry and presses the send button.

[1961] Input: Question or inquiry

[1962] Output: Message data in JSON format

[1963] Specific operation: The terminal converts the data entered by the user into JSON format and sends it to the server.

[1964] Step 3:

[1965] The server passes the received user message to the emotion engine and analyzes the user's emotion.

[1966] Input: Message data in JSON format

[1967] Output: Emotion analysis results

[1968] Specific operation: The server sends message data to an emotion engine (such as Microsoft Text Analytics API) and receives the emotion analysis results.

[1969] Step 4:

[1970] The server uses generative AI to input the analyzed emotions and messages as prompts and generate an appropriate response.

[1971] Input: Sentiment analysis results, user message

[1972] Output: The generated response

[1973] Specific operation: The server sends the emotion analysis results and messages as prompts to the generative AI (such as OpenAI GPT-3) and receives the generated responses.

[1974] Step 5:

[1975] The server generates a response and sends it back to the terminal.

[1976] Input: Generated response

[1977] Output: Response data in JSON format

[1978] Specific operation: The server sends the generated response data to the terminal.

[1979] Step 6:

[1980] The terminal displays the response received from the server to the user.

[1981] Input: Response data in JSON format

[1982] Output: Response displayed on the screen

[1983] Specific behavior: The device parses the received data and displays the response in the user interface.

[1984] Health management data analysis

[1985] Step 1:

[1986] The user allows the health management app to link with the health support AI system.

[1987] Input: Collaboration permission settings

[1988] Output: Connection permission confirmation message

[1989] Specific operation: When the user sets permission for linking within the app, the health management app will begin data linking.

[1990] Step 2:

[1991] The device sends the data collected from the health management app to the server.

[1992] Input: Collected health data

[1993] Output: Health data in JSON format

[1994] Specific operation: The terminal converts the collected data into JSON format and sends it to the server.

[1995] Step 3:

[1996] The server passes the received data to the generative AI, which then analyzes the data.

[1997] Input: Health data in JSON format

[1998] Output: Analysis results

[1999] Specific operation: The server sends data to the generative AI and receives the analysis results.

[2000] Step 4:

[2001] The server monitors stress levels based on the emotions recognized by the emotion engine and reflects this in the analysis results.

[2002] Input: Analysis data from generative AI, emotion analysis results

[2003] Output: Detailed analysis results

[2004] Specific operation: The server integrates the results of the emotion engine with the health data to generate a comprehensive analysis result.

[2005] Step 5:

[2006] The server transmits the analysis results to the terminal.

[2007] Input: Detailed analysis results

[2008] Output: Parsed results in JSON format

[2009] Specific operation: The server sends the generated analysis result data to the terminal.

[2010] Step 6:

[2011] The device notifies the user of the analysis results.

[2012] Input: Parsed result in JSON format

[2013] Output: Analysis results displayed on the screen

[2014] Specific operation: The device parses the analysis results received and displays them as notifications in the user interface.

[2015] Feedback collection

[2016] Step 1:

[2017] After using the system, the user opens the provided feedback form on the terminal.

[2018] Input: None

[2019] Output: Feedback form displayed

[2020] Specific operation: When the user clicks on the feedback form link after using the service, the form will be displayed.

[2021] Step 2:

[2022] The user enters the feedback and presses the send button.

[2023] Input: Feedback

[2024] Output: Feedback data in JSON format

[2025] Specific operation: The device converts the input feedback into JSON format and sends it to the server.

[2026] Step 3:

[2027] The server stores the received feedback data in a database.

[2028] Input: Feedback data in JSON format

[2029] Output: Save to database

[2030] Specific operation: The server registers the feedback data in a database.

[2031] Step 4:

[2032] The server periodically extracts the feedback data from the database and performs analysis.

[2033] Input: Feedback data in the database

[2034] Output: Analysis results

[2035] Specific operation: The server periodically extracts feedback data from the database and analyzes it using techniques such as natural language processing.

[2036] Step 5:

[2037] The server will improve the system based on the results of the analysis of the feedback.

[2038] Input: Feedback analysis results

[2039] Output: Improved system

[2040] Specific operation: The server takes into account the feedback analysis results and implements system improvements such as chatbot responses and user interface.

[2041] The above is a detailed flow of the processing of this system's program. By specifically performing a series of data processing and data calculations from input to output at each processing step, it is possible to provide high-quality medical support to users.

[2042] (Application example 2)

[2043] 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."

[2044] In today's world, security threats exploiting the Internet are rapidly increasing, increasing the information security risks for individuals and businesses. The risks are particularly severe for people with mobility issues, such as the elderly, people with disabilities, and people with chronic illnesses, who often lack specialized security knowledge. There is a need for systems that allow these people to receive appropriate security consultations and support from home. It is also important to provide appropriate advice that takes into account the user's emotions, but existing systems lack the ability to analyze and respond to emotions, making improving user satisfaction a challenge.

[2045] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2046] In this invention, the server includes security consultation chatbot means that utilizes generative artificial intelligence to respond in natural language, terminal means that receives security consultation content input from a user, server means that transmits the security consultation content to the generative artificial intelligence and returns a generated response to the terminal means, security management data analysis means that collects data from a security management app and analyzes it with the generative artificial intelligence, means that provides the analysis results to the user, emotion engine means that recognizes emotions, and means that collect feedback and improve the system. This enables people who have difficulty moving around to receive appropriate security advice from home that takes emotions into consideration.

[2047] "Generative AI" is an AI system that generates natural language and provides a response to user input.

[2048] The "security consultation chatbot means that responds in natural language" is a system that uses generative artificial intelligence to respond in natural language to security-related questions and inquiries.

[2049] The "terminal means for receiving security consultation details input by the user" refers to a device or system for receiving security-related questions and consultation details input by the user at a terminal.

[2050] The "server means for returning the generated response to the terminal means" is a server for transmitting the answer generated by the generative artificial intelligence to the terminal.

[2051] A "security management app" is software for managing and monitoring a user's security status.

[2052] The "security management data analysis means" is a system that analyzes data collected from the security management app and generates appropriate advice and suggestions for users.

[2053] The "emotion engine means for recognizing emotions" is a system that analyzes emotions from user input and reflects that information in responses.

[2054] "Means for collecting feedback and improving the system" refers to the processes and means for collecting user evaluations and opinions and using them to improve the performance and functionality of the system.

[2055] "Elderly, disabled and chronically ill people with mobility issues" refers to elderly people, people with disabilities or patients with long-term health problems who have difficulty moving freely due to physical limitations.

[2056] "Appropriate security consultation and support" means providing professional and accurate advice and assistance to users regarding security issues and questions they may have.

[2057] This invention is a system that uses generative artificial intelligence and an emotion engine to provide natural responses to security-related problems and inquiries that users have. Specific embodiments are described below.

[2058] First, a user accesses the system using a device such as a smartphone or PC. The user creates an account and enters basic information such as name, password, and email address. This operation causes the device to send the entered information to the server, which then stores it in a database.

[2059] Next, the user inputs a security question or inquiry into the chatbot. For example, they send a message like, "I often receive phishing emails. What should I do about them?" At this time, the emotion engine analyzes the message and evaluates the user's emotional state in order to recognize their emotions. If emotions such as anxiety or worry are detected, the data is sent to the server taking this into consideration.

[2060] The server analyzes the received data using generative artificial intelligence and generates an appropriate response. The generated response takes into account the user's emotional state and provides specific and reassuring information, such as "First, check the sender and links in the email, and if they seem suspicious, never click on them. It is also important to keep your security software up to date." The device then displays this response to the user.

[2061] For users using security management apps, logs and alert data collected from the app are also transferred to the server. The server then analyzes this data using generative artificial intelligence to assess the user's stress level and the system's security status. For example, it generates feedback such as, "Recent data indicates that many security alerts have been generated. We recommend a comprehensive review of your system." and notifies the user.

[2062] To collect feedback, users can fill out a feedback form after using the system. The terminal sends the entered feedback to the server, which stores it in a database. This information is periodically analyzed and used to improve the system.

[2063] The hardware and software used includes:

[2064] Hardware: smartphones, PCs, servers

[2065] Software: Python, SQLite, EmotionEngine (emotion engine library), AIResponseGenerator (generative artificial intelligence library)

[2066] Examples:

[2067] A user asks, "I've been receiving a lot of phishing emails lately. What should I do?"

[2068] The emotion engine recognizes the user's "anxiety," and the generative artificial intelligence generates a response such as, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[2069] Example prompt sentence:

[2070] A user asked, "I've been receiving a lot of phishing emails lately. What should I do?"

[2071] The emotion engine recognized the user's "anxiety."

[2072] Generate a response that is appropriate and reassuring in this context.

[2073] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2074] Step 1:

[2075] A user accesses the system and creates an account.

[2076] Input: Username, Password, Email Address

[2077] Specific operation: The user accesses the system's membership registration form using a device such as a smartphone or PC. They enter basic information such as their username, password, and email address into the form and press the submit button.

[2078] Output: User information sent from the device to the server

[2079] Step 2:

[2080] The server processes the received user information and stores it in a database.

[2081] Input: User information sent from the device (username, password, email address)

[2082] What it does: The server hashes the information it receives for security purposes and stores the user information in a database along with the hashed password.

[2083] Output: User information stored in the database

[2084] Step 3:

[2085] The user inputs a question or inquiry into the security consultation chatbot.

[2086] Input: Questions or inquiries about security

[2087] Specific operation: The user accesses the system's chatbot screen, enters the content of their inquiry in text, and presses the send button.

[2088] Output: Consultation details sent from the device to the server

[2089] Step 4:

[2090] The server analyzes the consultation content received by the server using an emotion engine and evaluates the emotional state.

[2091] Input: User's inquiry

[2092] Specific operation: The server passes the received consultation content to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes emotions such as "anxiety" and "worry" and returns the results.

[2093] Output: Sentiment analysis result (e.g., "anxiety")

[2094] Step 5:

[2095] The server passes the results of the emotion engine to a generative artificial intelligence system, which generates an appropriate response.

[2096] Input: Consultation details, emotion analysis results

[2097] Specific operation: The server uses generative AI to generate an appropriate response based on the content of the consultation and the results of emotion analysis. For example, if a user consults about phishing scams and detects "anxiety," the server will respond by saying, "First, check the sender of the email and the link, and if it seems suspicious, never click on it."

[2098] Output: The generated response

[2099] Step 6:

[2100] The server sends the generated response back to the user terminal.

[2101] Input: Generated response

[2102] Specific operation: The server sends the generated response data to the terminal.

[2103] Output: The response displayed on the user's terminal

[2104] Step 7:

[2105] The user terminal displays the response on the screen.

[2106] Input: The response sent by the server

[2107] Specific operation: The terminal displays the received response on the screen and notifies the user.

[2108] Output: The response displayed to the user

[2109] Step 8:

[2110] The user sends the collected data from the security management app to the server.

[2111] Input: Data from security management apps (logs, alerts, etc.)

[2112] Specific operation: The user launches the security management app and allows data collection and transmission. The device sends the data collected from the app to the server.

[2113] Output: Security data sent to the server

[2114] Step 9:

[2115] The server analyzes the security data and generates appropriate feedback.

[2116] Input: Security Data

[2117] How it works: The server uses generative artificial intelligence to analyze the collected data and evaluate the user's stress level and the system's security status. For example, if a large number of security alerts are detected, the server generates feedback such as "We recommend a comprehensive review of the system."

[2118] Output: Generated feedback

[2119] Step 10:

[2120] The user terminal displays the generated feedback on the screen.

[2121] Input: Feedback sent by the server

[2122] Specific operation: The device displays the received feedback on the screen and notifies the user.

[2123] Output: Feedback displayed to the user

[2124] Step 11:

[2125] The user fills in the feedback form and submits it.

[2126] Input: Feedback

[2127] Specific operation: After using the system, the user accesses the feedback form, enters their evaluation and opinions, and presses the submit button.

[2128] Output: Feedback sent from the device to the server

[2129] Step 12:

[2130] The server stores the received feedback in a database and analyzes it periodically.

[2131] Input: Feedback sent by the user

[2132] Specific operation: The server stores the received feedback in a database, analyzes the data periodically, and uses the results to improve the system's performance and functionality.

[2133] Output: Feedback data stored in a database and system improvement suggestions

[2134] 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.

[2135] 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.

[2136] 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.

[2137] 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.

[2138] 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.

[2139] 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.

[2140] 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).

[2141] 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.

[2142] 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."

[2143] 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," ha...

Claims

1. A medical consultation chatbot that uses generative artificial intelligence to respond in natural language; a terminal means for receiving medical consultation details input by a user; a server means for transmitting the medical consultation content to the generative artificial intelligence and returning a generated response to the terminal means; A health management data analysis means for collecting data from a health management app and analyzing it using generative artificial intelligence; A means for providing the results of the analysis to users; A system including:

2. The system according to claim 1, which targets people who have difficulty visiting hospitals, such as the elderly, people with disabilities, and people with chronic diseases.

3. The system of claim 1 , further comprising a feedback means for providing a response generated by the medical consultation chatbot means to a user.

Images