System

Abstract

To provide a system for performing an interactive medical examination.SOLUTION: A means for a user to start a medical interview, a means for transmitting a request of the user to a server, a means for the server to generate first question data and transmit the first question data to the terminal, a means for the terminal to display the question received from the server to the user, a means for the user to input an answer to the question, a means for transmitting the answer of the user to the server, and a means for the server to analyze the answer of the user; A system comprising: means for generating next question data; means for displaying the next question received by the terminal from the server to the user; means for generating and displaying the next question by a repetitive process; means for finally transmitting answer data of all questions to the server when a medical inquiry is completed; and means for storing final diagnosis data and notifying a doctor as necessary by the server.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional medical questionnaire tablet systems have a large number of questions and options, making them cumbersome and burdensome to use, especially for emergency patients. This makes it difficult to quickly obtain the necessary information and properly understand the patient's condition. Furthermore, inputting a large number of questions can increase stress and make it difficult to obtain accurate answers. There is a need for a system that can solve these issues and make medical interviews proceed more smoothly. [Means for solving the problem]

[0005] The present invention provides a system for conducting an interactive medical interview. The system includes: a means for a user to start the medical interview; a means for transmitting a user request to a server; a means for the server to generate initial question data and transmit it to a terminal; a means for the terminal to display the question received from the server to the user; a means for the user to input an answer to the question; a means for transmitting the user's answer to the server; a means for the server to analyze the user's answer and generate the next question data; a means for the terminal to display the next question received from the server to the user; a means for generating and displaying the next question through a repeating process; a means for finally transmitting the answer data for all questions to the server when the medical interview is complete; and a means for the server to save final diagnosis data and notify a doctor as necessary. This allows the user to easily proceed with the medical interview in an interactive format, making it possible to conduct a medical interview quickly and accurately, especially for emergency patients.

[0006] A "user" is an individual who uses the system and is interviewed.

[0007] A "terminal" is an electronic device that allows a user to start a medical interview, input answers, and communicate with the server. Examples include smartphones and tablets.

[0008] A "server" is a computer system that generates and manages medical interview data and communicates with terminals.

[0009] "Question data" is data that is generated by the server and sent to the terminal, and includes the content of a question to the user.

[0010] The "initial question" is the first question presented to the user when he or she begins the medical interview.

[0011] "Response data" is data that includes the answers given by the user to each question.

[0012] "Dynamic generation" is the process of generating the next question in real time based on the user's answers.

[0013] A "medical interview" is a series of questions and answers to gather information about a user's health and symptoms.

[0014] "Diagnostic data" is the final medical information generated based on the information provided by the user.

[0015] "Physician notification means" refers to the means used by the server to communicate the final diagnosis data to the physician, such as email or an administrative dashboard. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system that allows a user to proceed with a medical interview in an interactive format. The processing of the program of this system will be specifically explained below in natural language.

[0038] System Overview

[0039] In this system, the user conducts a medical interview using a device such as a tablet or smartphone, and the next question is dynamically generated from the server based on the answers. Finally, all the answer data is notified to the doctor.

[0040] Program processing

[0041] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This operation starts the medical interview session.

[0042] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0043] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0044] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0045] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[0046] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[0047] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[0048] For example, if a user answers "I have a stomachache," the server dynamically generates a question such as "How bad is the pain? Mild, moderate, severe?" and displays it to the user.

[0049] 8. This iterative process continues until all necessary questions have been asked. At each step, the server analyzes the user's answers and dynamically generates appropriate questions.

[0050] 9. After all questions have been answered, the terminal displays a message to the user saying "Interview completed." At the same time, all answer data is finally sent to the server.

[0051] 10. The server saves the final diagnosis data and notifies the doctor if necessary, allowing the doctor to provide appropriate diagnosis and treatment based on the user's medical history.

[0052] This system is particularly useful for emergency patients, as it allows for quick and accurate medical interviews without placing a burden on the user.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user presses the inquiry start button on the terminal to start the inquiry.

[0056] Specific action: Touch a button on the screen of a tablet or smartphone.

[0057] Step 2:

[0058] The terminal receives the user's request and sends a request to start an interview to the server.

[0059] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[0060] Step 3:

[0061] The server receives the request to start the medical interview and generates the initial question data.

[0062] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[0063] Step 4:

[0064] The server returns the generated initial question data to the terminal.

[0065] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[0066] Step 5:

[0067] The terminal analyzes the initial question data received from the server and displays it to the user.

[0068] Specific operation: Parse the JSON data and display the question text on the screen.

[0069] Step 6:

[0070] The user enters an answer to the initial question.

[0071] Specific actions: Enter text using the software keyboard and touch the send button.

[0072] Step 7:

[0073] The terminal sends the user's answer to the server.

[0074] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[0075] Step 8:

[0076] The server analyzes the user's answers and generates the next question data.

[0077] Specific behavior: Uses the rules engine to select the appropriate next question, fills in the answer content in a question template, and generates a JSON-formatted response.

[0078] Step 9:

[0079] The server generates the next question data and sends it to the terminal.

[0080] Specific operation: The following question data is sent in JSON format as an HTTP response.

[0081] Step 10:

[0082] The terminal analyzes the next question data received from the server and displays it to the user.

[0083] Specific behavior: Parse the JSON data and display the following question text on the screen.

[0084] Step 11:

[0085] Repeat steps 6 through 10 until all necessary questions have been asked.

[0086] Specific operation: Repeat the process of inputting a user answer, sending it to the server, and generating and displaying the next question.

[0087] Step 12:

[0088] The terminal confirms that all questions have been completed and displays a message to the user that the interview is complete.

[0089] Specific action: The text "Medical interview completed" is displayed on the screen.

[0090] Step 13:

[0091] The terminal finally transmits all response data to the server.

[0092] Specific operation: The answer data for all questions is converted into a list in JSON format and sent to the server via an HTTP request.

[0093] Step 14:

[0094] The server stores the final diagnosis data and notifies the doctor if necessary.

[0095] Specific actions: Saves the user's response history in a database and triggers notifications to the doctor, including sending emails and updating the admin interface.

[0096] Example 1

[0097] 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."

[0098] Conventional medical interview systems have the problem that it is difficult to dynamically generate the next question based on the user's answers, and only fixed questions can be displayed. Furthermore, as the user progresses through the medical interview, it is difficult to effectively exchange questions and answers, making it difficult for doctors to quickly and accurately obtain the information they need to make an appropriate diagnosis. This has led to problems, particularly in emergencies and for emergency patients, making it difficult to provide prompt and accurate responses.

[0099] 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.

[0100] In this invention, the server includes a means for analyzing the user's answers and generating the next question data, a means for dynamically generating the next question data using a generative AI model, and a means for saving the final diagnosis data and notifying the doctor as necessary. This enables dynamic question generation based on the user's answers, enabling the doctor to efficiently obtain information for a quick and accurate diagnosis.

[0101] "User" refers to an individual or patient who uses the system to conduct a medical interview.

[0102] The term "terminal device" refers to an electronic device, such as a tablet or smartphone, that a user uses to conduct a medical interview.

[0103] "Information processing device" refers to a central control device that functions as a server, receives user requests, and generates, analyzes, and stores data.

[0104] "Initial question data" refers to data including the content of the first question presented to the user at the start of the medical interview session.

[0105] "Next question data" refers to data that contains the question to be presented next, which is dynamically generated based on the user's answer.

[0106] "Generative AI model" refers to an artificial intelligence model (e.g., GPT-3 (registered trademark)) that generates the next best question based on user input.

[0107] "User answers" refers to the text or choices entered by the user for each question.

[0108] "Diagnostic data" refers to the final data provided by the server to the doctor based on all interview results.

[0109] "Notification means" refers to a communication means (e.g., email notification or message application) for transmitting final diagnosis data to a doctor.

[0110] This invention relates to a system that allows a user to proceed with an interview in an interactive format. The system aims to dynamically generate the next question based mainly on the user's input and provide the doctor with final diagnostic data.

[0111] Required Hardware and Software

[0112] Hardware:

[0113] Terminal devices such as tablets and smartphones

[0114] Information processing device (server)

[0115] software:

[0116] Front-end: Web application using HTML, CSS, and JavaScript (registered trademark)

[0117] Backend: A server program using Python or Node.js

[0118] Database: MySQL (registered trademark) or PostgreSQL

[0119] AI generative models: such as OpenAI's GPT-3

[0120] Program processing overview

[0121] Starting a Session

[0122] The user starts the medical interview using a terminal device such as a tablet or smartphone. At this time, the user presses a button to start the medical interview, which starts the session. For example, the user can start the process by pressing the "Start Medical Interview" button on a tablet while in a hospital waiting room.

[0123] First question generation and display

[0124] The terminal device receives the user's request and transmits this information to the information processing device. The information processing device processes this request, generates initial question data, and transmits it to the terminal device. The terminal device displays the received initial question data to the user, and the user inputs an answer in a specified field. For example, the initial question, "Where does it hurt?", is displayed.

[0125] Next question generation and iterative process

[0126] When the user enters an answer to a question and presses the send button, the answer data is sent again to the information processing device. The information processing device analyzes the user's answer and dynamically generates the next question data using a generative AI model (e.g., GPT-3). This process is repeated until all necessary questions have been completed. For example, in response to the answer "My stomach hurts," the next question generated is "How bad is the pain?"

[0127] Final diagnostic data storage and notification

[0128] After all questions have been answered, the terminal device displays a message to the user saying "The medical interview is complete." At the same time, all answer data is finally sent to the information processing device. The information processing device saves the final diagnosis data and notifies the doctor if necessary. This allows the doctor to obtain information necessary for a quick and accurate diagnosis.

[0129] Prompt Sentence Examples

[0130] Below are some example prompts to input to a generative AI model:

[0131] User input: "My stomach hurts"

[0132] Prompt to input to the generative AI model:

[0133] "If the user says 'I have a stomach ache,' generate the next appropriate question."

[0134] Based on this prompt, the generative AI model generates appropriate questions such as "How bad is your pain?" Applying this method makes it possible to realize flexible medical interviews based on the user's answers. This system provides effective and efficient medical interviews, enabling rapid response, especially in emergency situations and for emergency patients.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1:

[0137] The user presses the medical interview start button. This operation starts the medical interview session. The input is the user's operation, and the output is the generation of a medical interview start request by the terminal. A specific operation is when the user clicks the "medical interview start" button on a tablet or smartphone. In response to this operation, the terminal sends a request including metadata such as the user ID and session ID to the information processing device.

[0138] Step 2:

[0139] The terminal receives the user's request and sends it to the information processing device. The input is the user's request, and the output is the transmission of request data from the terminal to the information processing device. Specifically, JavaScript on the terminal catches the user's operation and sends a medical interview start request in JSON format to the information processing device.

[0140] Step 3:

[0141] The server receives a request to start the medical interview, generates the initial question data, and sends it to the terminal. The input is the request data received from the terminal, and the output is the initial question data. A Python script on the server receives the request, queries the database to obtain the "initial question," and returns it to the terminal in JSON format.

[0142] Step 4:

[0143] The device displays the initial question data it receives to the user. The input is the question data from the server, and the output is the question displayed to the user. Specifically, JavaScript parses the JSON data returned from the server, generates HTML elements, and displays the initial question, such as "Where does it hurt?", to the user.

[0144] Step 5:

[0145] The user inputs an answer to the question and presses the send button. The input is the user's answer, and the output is the transmission of the answer data from the terminal to the server. As a specific example, the user inputs "My stomach hurts" and presses the send button. This operation sends the answer data from the terminal to the server.

[0146] Step 6:

[0147] The server receives the user's answer and analyzes it. The input is the user's answer data, and the output is the generation of the next question data. Specifically, the server's Python script receives the answer data, inputs it as a prompt to the generative AI model (e.g., GPT-3), and generates the next question. An example of a prompt sentence is, "If the user says, 'My stomach hurts,' please generate the next appropriate question."

[0148] Step 7:

[0149] The server generates the next question and sends it to the terminal. The input is the next question data from the generative AI model, and the output is data sent to the terminal. The server sends the generated question to the terminal in JSON format.

[0150] Step 8:

[0151] The terminal displays the next question to the user. This process is repeated until the user has answered all questions. The input is the next question data from the server, and the output is the question displayed to the user. In concrete terms, JavaScript displays the next question, and the user enters the answer again.

[0152] Step 9:

[0153] After all questions have been asked, the terminal displays a message to the user saying "The medical interview has been completed." The input is the fact that all questions have been asked, and the output is the display of a completion message to the user. Specifically, the message "The medical interview has been completed. Thank you." is displayed on the screen.

[0154] Step 10:

[0155] The server saves the final diagnosis data and notifies the doctor. The input is all response data, and the output is saving and notifying the final diagnosis data. Specifically, the server saves all response data in a database and notifies the doctor via email or a notification system as needed.

[0156] This enables dynamic question generation based on the user's answers, enabling doctors to efficiently obtain information that allows them to make prompt and accurate diagnoses.

[0157] (Application example 1)

[0158] 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."

[0159] Conventional food delivery systems have the drawback of requiring users to select menu items and specify customization options, resulting in complex and inefficient operations. This has led to low user satisfaction and a lengthy ordering process. In particular, when users are unsure of their choices and ordering options, it can take a lot of effort to complete the order.

[0160] 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.

[0161] In this invention, the server includes a means for the user to start an order, a means for transmitting the user's request to the server, and a means for the server to generate initial question data and transmit it to the terminal, thereby enabling the user to smoothly select and customize menus interactively.

[0162] "User" refers to the person utilizing the system who initiates and progresses the ordering process.

[0163] "Means for initiating an order" refers to the operation or interface that allows a user to start the ordering process in the delivery system.

[0164] "Means for sending a request to a server" refers to a communication means for sending initial information or a request to a server based on a user's operation.

[0165] The "means for generating initial question data and transmitting it to the terminal" refers to a process by which the server generates a question to be presented to the user initially and transmits it to the user's terminal.

[0166] The "means for displaying to the user the question received by the terminal from the server" refers to a function for visually showing to the user the question received by the user's terminal from the server.

[0167] "Means for a user to input an answer to a question" refers to a function that allows a user to input an answer to a question from a server using a terminal.

[0168] "Means for transmitting the user's answer to the server" refers to a communication means for transmitting the answer entered by the user to the server.

[0169] "Means for the server to analyze the user's answer and generate the next question data" refers to the analysis and generation function that enables the server to automatically generate the next question based on the user's answer.

[0170] "Means for displaying the next question received by the terminal from the server to the user" refers to a function for the user's terminal to receive questions that are generated one after another and display them to the user.

[0171] "Means for generating and displaying the next question through an iterative process" refers to a system for continuously generating and displaying questions based on the user's answers.

[0172] "Means for finally transmitting answer data for all questions to the server when an order is completed" refers to means for finally transmitting answer data for all questions to the server when a user's order is completed.

[0173] "Means for the server to save the final order data and notify the service provider as necessary" refers to the function that enables the server to save all order data and notify the delivery service provider of that information as necessary.

[0174] The present invention relates to a food delivery system that allows users to interactively place orders. A specific implementation of this system will be described below.

[0175] System Overview:

[0176] In this system, users place food delivery orders using devices such as smartphones or tablets, and the server dynamically generates the next questions based on the answers. All answer data is finally sent to the service provider.

[0177] Hardware and software used:

[0178] Hardware: Smartphones, tablets

[0179] Software: Flask (a Python microframework), server (NGINX, Apache (registered trademark), etc. can be used)

[0180] Data processing and calculation:

[0181] 1. To begin an order, the user presses the Start Order button on the terminal. This action starts an ordering session.

[0182] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0183] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0184] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0185] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[0186] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[0187] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[0188] This iterative process continues until all necessary questions have been asked, with the server analyzing the user's answers at each step and dynamically generating appropriate questions.

[0189] Specific examples of behavior:

[0190] When a user initiates an order, the following interaction takes place:

[0191] Example prompt sentence:

[0192] 1. "Let's start ordering. What would you like? Pizza, burger, or salad?"

[0193] 2. The user answers "pizza"

[0194] 3. "Choose your pizza size: small, medium, or large?"

[0195] 4. The user answers "medium"

[0196] 5. "What toppings would you like to add to your medium pizza? Cheese, bacon?"

[0197] In this way, the user answers questions one by one, and when all information has been provided, the order data is sent to the server and, if necessary, notified to the service provider.

[0198] This system allows users to efficiently and intuitively navigate the food delivery ordering process.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The user presses the order start button.

[0202] Input: User operation (pressing the order start button)

[0203] Output: Order session start request

[0204] Specific operation: When the user presses the order start button on the terminal, the terminal sends the user's request to the server, which starts the order.

[0205] Step 2:

[0206] The terminal receives the user's request and sends it to the server.

[0207] Input: User action (request to start an order)

[0208] Output: Initial question generation request

[0209] Specific operation: The terminal sends the user's request to the server, and the server begins preparations to generate the first question.

[0210] Step 3:

[0211] The server generates the initial question data and sends it to the terminal.

[0212] Input: Initial question generation request

[0213] Output: First question data

[0214] Specific operation: The server generates a question about the menu that the user should first choose (e.g., what would you like to order?) and sends that data to the terminal.

[0215] Step 4:

[0216] The terminal displays the question received from the server to the user.

[0217] Input: First question data

[0218] Output: The question displayed to the user

[0219] Specific operation: The terminal displays the initial question received from the server to the user and provides an interface for the user to input an answer.

[0220] Step 5:

[0221] The user enters an answer to the question, and the terminal sends the answer to the server.

[0222] Input: User's answer

[0223] Output: User's request to send an answer

[0224] Specific operation: The user enters an answer to the question displayed on the terminal and presses the send button. The terminal then sends the answer to the server.

[0225] Step 6:

[0226] The server analyzes the user's answers and generates the next question data.

[0227] Input: User's answer

[0228] Output: Next question data

[0229] Specific operation: The server analyzes the user's answer and generates the next appropriate question. For example, if the answer is "pizza," the next question generated is "Please choose the size of pizza."

[0230] Step 7:

[0231] The server generates the next question and sends it to the terminal, which displays it to the user.

[0232] Input: Next question data

[0233] Output: The next question displayed on the user's screen

[0234] Specific operation: The server generates the next question and sends it to the terminal, which displays it to the user. The user then enters the answer again.

[0235] Step 8:

[0236] Repeat this process until all necessary questions have been answered.

[0237] Input: Repeat previous step

[0238] Output: Final response data

[0239] Specific behavior: Continue this cycle of questions and answers until the user has answered all questions.

[0240] Step 9:

[0241] When the order is completed, the terminal finally transmits the answer data for all questions to the server.

[0242] Input: Answers to all questions

[0243] Output: Final order data transmission request

[0244] Specific operation: When the user inputs the final answer and presses the send button, the terminal finally sends all the answer data to the server.

[0245] Step 10:

[0246] The server stores the final order data and notifies the service provider if necessary.

[0247] Input: Final order data

[0248] Output: Stored order data and notifications

[0249] Specific operation: The server stores the final order data and notifies the delivery service provider of that data as necessary.

[0250] 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.

[0251] The present invention relates to a system that can conduct a dialogue-style medical interview while recognizing the user's emotions. The program processing of this system will be specifically explained below in natural language.

[0252] System Overview

[0253] This system allows users to use a terminal to answer questions, and the server dynamically generates the next questions based on the user's answers. It also incorporates an emotion engine that recognizes the user's emotions and dynamically changes the way questions are phrased based on their emotions. It also has a function to monitor stress levels and provide relaxation content as needed.

[0254] Program processing

[0255] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This starts the medical interview session.

[0256] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0257] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0258] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0259] 5. The device sends the user's answer to the server, which analyzes the answer and uses an emotion engine to recognize the user's emotion.

[0260] Examples of emotion engines

[0261] For example, if a user answers "I have a stomachache," and the emotion engine recognizes from the user's tone of voice and facial expression that they are under high stress, the next question will be changed from "How bad is the pain?" to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[0262] 6. The server dynamically generates the next question data based on the user's emotions and sends it to the terminal. This question data takes into account the user's emotional state.

[0263] 7. The terminal analyzes the next question data received from the server and displays it to the user. The user then enters the answer to the next question.

[0264] 8. The user enters and submits an answer to the question. This process is repeated until all of the user's questions have been answered.

[0265] For example, if a user responds with "it hurts a lot," and the emotion engine recognizes this as high stress, the system will display a message to the user suggesting relaxation techniques and deep breathing.

[0266] 9. After all questions have been answered, the device displays a message to the user saying, "The interview is complete. Thank you for your hard work." At the same time, all answer data and sentiment analysis data are finally sent to the server.

[0267] 10. The server saves the final diagnosis data and notifies the doctor if necessary. The doctor can then provide an appropriate diagnosis and treatment based on the user's interview details and emotional data.

[0268] This system is particularly useful for emergency patients, as it allows for quick and accurate interviews without placing a burden on the user. Furthermore, by using an emotion engine, the system can take the user's emotional state into consideration during the interview, enabling more friendly and effective communication.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] The user presses the inquiry start button on the terminal to start the inquiry.

[0272] Specific action: Touch a button on the screen of a tablet or smartphone.

[0273] Step 2:

[0274] The terminal receives the user's request and sends a request to start an interview to the server.

[0275] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[0276] Step 3:

[0277] The server receives the request to start the medical interview and generates the initial question data.

[0278] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[0279] Step 4:

[0280] The server returns the generated initial question data to the terminal.

[0281] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[0282] Step 5:

[0283] The terminal analyzes the initial question data received from the server and displays it to the user.

[0284] Specific operation: Parse the JSON data and display the question text on the screen.

[0285] Step 6:

[0286] The user enters an answer to the initial question.

[0287] Specific actions: Enter text using the software keyboard and touch the send button.

[0288] Step 7:

[0289] The terminal sends the user's answer to the server.

[0290] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[0291] Step 8:

[0292] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[0293] Specific operation: Executes an algorithm to determine emotions based on voice tone, facial expressions, input speed and strength, etc.

[0294] Step 9:

[0295] The server dynamically generates the next question data based on the user's emotions and sends it to the terminal.

[0296] Specific operation: The system uses a rules engine to select the appropriate next question, embeds expressions that take into account the user's emotional state in the question template, and generates a JSON-formatted response.

[0297] Step 10:

[0298] The terminal analyzes the next question data received from the server and displays it to the user.

[0299] Specific operation: Analyzes the JSON data and displays the next question text on the screen, reflecting the emotional state.

[0300] Step 11:

[0301] The user answers the following questions and submits.

[0302] Specific actions: Enter text using the software keyboard and touch the send button.

[0303] Step 12:

[0304] The terminal sends the user's answer to the server, which generates the next question.

[0305] Specific operation: The answer data is converted into JSON format and sent to the server via an HTTP request. The server again uses the emotion engine to recognize the user's emotion and the rule engine to select the next question.

[0306] Step 13:

[0307] Repeat steps 8 through 12 until all necessary questions have been asked.

[0308] Specific operation: User inputs answer, sends it to the server, recognizes emotion, and generates and displays the next question, repeating this process.

[0309] Step 14:

[0310] After all questions have been answered, the terminal displays a message to the user indicating that the interview is complete.

[0311] Specific action: Display the text "The medical interview has been completed. Thank you for your hard work" on the screen.

[0312] Step 15:

[0313] The device finally transmits all response data and sentiment analysis data to the server.

[0314] Specific operation: The answer data and sentiment analysis data for all questions are converted into JSON format and sent to the server via an HTTP request.

[0315] Step 16:

[0316] The server stores the final diagnosis data and notifies the doctor if necessary.

[0317] Specific behavior: Stores the user's response history and emotion data in a database and triggers notifications to doctors, including sending emails and updating the management interface.

[0318] This series of processes allows the user to proceed with the medical interview in a friendly dialogue format that takes into account the user's emotional state, making it possible to collect information quickly and accurately, especially for emergency patients.

[0319] Example 2

[0320] 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."

[0321] Conventional medical interview systems have problems in that they ask questions without considering the user's emotions, which can cause stress to the user or prevent them from obtaining appropriate information. This can increase the user's psychological burden, especially in emergencies, making it difficult to conduct an accurate medical interview. Furthermore, because the system does not consider the user's emotional state, it is insufficient to provide relaxation methods or appropriate responses to the user.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0323] In this invention, the server includes means for analyzing the user's answers, recognizing emotions using a sentiment analysis engine, and generating next question data, means for providing relaxation content according to the user's emotional state, and means for saving the user's answer data and sentiment analysis data and notifying the doctor as necessary. This allows for a friendly and effective medical interview to be conducted while taking the user's emotions into consideration, reducing the user's psychological burden and enabling more accurate information to be collected.

[0324] "User" refers to an individual who uses the system to take a medical interview.

[0325] "Device" refers to the hardware device (e.g., smartphone, tablet, PC) used by the user to complete the interview.

[0326] A "medical interview start button" is an interface element that is displayed on a terminal to allow a user to start a medical interview session.

[0327] A "request" refers to the data format used to send operations and input data that a user performs on a system to a server.

[0328] A "server" is a central control system that receives requests and processes or generates data.

[0329] The "initial question data" is data that is generated by the server when a medical interview session is started and includes the content of the question that is first presented to the user.

[0330] An "emotion analysis engine" is software or algorithms that analyze a user's responses, tone of voice, facial expressions, etc. to recognize the user's emotional state.

[0331] The "next question data" is data that is dynamically generated by the server based on the user's answer and emotional state, and includes the content of the question to be presented to the user next.

[0332] "Relaxation content" refers to information and suggestions to reduce the user's psychological burden that are provided when the user's emotional state, particularly a high-stress state, is recognized.

[0333] "Emotion analysis data" refers to data regarding a user's emotional state obtained by an emotion analysis engine.

[0334] "Final diagnostic data" refers to final diagnostic information including user response data and emotion analysis data collected throughout the entire interview process.

[0335] The present invention relates to a system that conducts an interview in an interactive format while recognizing the user's emotions. In this system, the user uses a terminal to conduct an interview, and the server dynamically generates the next question based on the user's answers. Furthermore, the system incorporates a sentiment analysis engine and has the function of dynamically changing the way questions are phrased based on the user's emotions. It also has the function of monitoring the user's stress level and providing relaxation content as needed.

[0336] Hardware and software used

[0337] Hardware

[0338] Device (e.g. smartphone, tablet, PC)

[0339] Server (e.g. cloud server, on-premise server)

[0340] software

[0341] Interaction Management Applications

[0342] Sentiment analysis engine (e.g., IBM Watson®, Microsoft® Azure® Emotion API)

[0343] Overview of program processing

[0344] The system operates in the following steps:

[0345] 1. The user presses the start button on the device to start the medical interview session.

[0346] 2. The device sends the user's request to the server, and the server generates the initial question data and sends it to the device.

[0347] 3. The server generates the initial question data, and the device displays the received question to the user.

[0348] 4. The user enters the answer to the question, and the device sends the answer to the server.

[0349] 5. The server analyzes the user's answers and uses a sentiment analysis engine to recognize the user's emotions.

[0350] 6. The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[0351] 7. The terminal analyzes the next question data and displays it to the user.

[0352] 8. The user answers the next question and this process is repeated until all of the user's questions have been answered.

[0353] 9. After all questions have been completed, the device will display the message "The medical interview is complete. Thank you for your hard work." and send all response data and emotion analysis data to the server.

[0354] 10. The server stores the final diagnosis data and notifies the doctor if necessary.

[0355] Specific examples

[0356] For example, if a user answers "I have a stomachache," the emotion analysis engine will recognize from the user's tone of voice and facial expression that they are under high stress. In this case, the next question will be changed from "Please tell me the level of pain," to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[0357] Example prompts to input to the generative AI model

[0358] "When the user answers 'My stomach hurts', generate the next question taking into account their emotions."

[0359] This system provides a fast and accurate interview process while minimizing the psychological burden on the user. In addition, by incorporating a sentiment analysis engine, it realizes friendly and effective communication while taking into account the user's emotions, making it particularly useful in emergencies and high-stress situations.

[0360] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0361] Step 1:

[0362] The user presses the inquiry start button on the terminal to start the inquiry session.

[0363] Specific operation: The user taps the "Start medical interview" button displayed on the smartphone screen. As input, a medical interview start request is generated. As output, an event indicating that the medical interview session has started is generated.

[0364] Step 2:

[0365] The terminal generates a request to start an interview and sends it to the server.

[0366] Specific operation: The terminal generates a medical interview start request including the user ID and the current date and time, and sends it to the server via the Internet. The input is the user's tap event, and the output is the transmission of the medical interview start request.

[0367] Step 3:

[0368] The server receives the request to start the medical interview and generates the initial question data.

[0369] Specific operation: The server generates data including a question such as "Where does it hurt?" as the first question. The input is a request to start the medical interview, and the output is the first question data.

[0370] Step 4:

[0371] The server sends the initial question data to the terminal.

[0372] Specific operation: The process of sending query data generated by the server to the terminal. The input is the initial query data, and the output is sending the data to the terminal.

[0373] Step 5:

[0374] The terminal receives the initial question data and displays it to the user.

[0375] Specific operation: The terminal displays the initial question data received from the server on the screen. The input is the received question data, and the output is what is displayed to the user.

[0376] Step 6:

[0377] The user enters an answer to the question, and the terminal sends the answer to the server.

[0378] Specific operation: The user enters an answer in the text box and clicks the send button. The terminal sends this answer data to the server. The input is the user's answer data, and the output is the transmission of the answer data.

[0379] Step 7:

[0380] The server analyzes the user's responses and uses a sentiment analysis engine to recognize the user's emotions.

[0381] Specific operation: The server applies an analysis algorithm to analyze the user's response data, voice tone, and facial expressions. The input is the user's response data, and the output is the emotion analysis result.

[0382] Step 8:

[0383] The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[0384] Specific operation: The server generates the next question data taking into account the user's emotional state and sends it to the device. For example, instead of a general question such as "Please tell me the level of pain," it generates a friendly question such as "It sounds like you're in a lot of pain. How bad is it?" The input is the emotion analysis result, and the output is the next question data.

[0385] Step 9:

[0386] The terminal analyzes the next question data and displays it to the user.

[0387] Specific operation: The terminal displays the next question data it has received. The input is the next question data, and the output is what is displayed to the user.

[0388] Step 10:

[0389] The user answers the next question and the process repeats until all of the user's questions have been answered.

[0390] Specific operation: The user enters an answer to the next question and submits it. This process is repeated. The input is the questions that are generated one after another and the user's answer data to those questions, and the output is the final accumulation of answer data.

[0391] Step 11:

[0392] After all questions have been completed, the device displays the message "The medical interview is complete. Thank you for your hard work." and sends all response data and emotion analysis data to the server.

[0393] Specific operation: When the user answers the last question, the terminal displays a completion message and sends all data to the server. The input is the final answer data, and the output is the display of the completion message and the sending of data.

[0394] Step 12:

[0395] The server stores the final diagnosis data and notifies the doctor if necessary.

[0396] Specific operation: The server stores all received data and sends alerts to doctors via email or notification systems (e.g., Slack, Teams, etc.). The input is the submitted response data and sentiment analysis data, and the output is the storage of the final diagnosis data and notification to the doctor.

[0397] (Application example 2)

[0398] 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."

[0399] Current factory environments lack systems that can properly recognize workers' emotions and stress levels and provide feedback and relaxation suggestions based on that information. This can have a negative impact on work efficiency and workers' mental health. It is necessary to accurately grasp workers' emotional states and provide appropriate follow-up when checking the progress of work and adjusting tasks on-site. Currently, there are no means to solve these issues, and improvements to the work environment are stalled.

[0400] 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.

[0401] In this invention, the server includes means for recognizing the user's emotions using an emotion engine, means for dynamically generating the next question data based on the emotion and sending it to the terminal, and means for the emotion engine to monitor the user's stress level and suggest relaxation methods as necessary. This makes it possible to accurately grasp the emotions and stress levels of workers and provide appropriate feedback and suggestions in real time.

[0402] "User" refers to a person who uses the system.

[0403] "Medical interview" refers to the process of gathering information by asking questions about a user's health status and symptoms.

[0404] A "request" refers to data or a request that a user sends to a server.

[0405] "Server" means a computer system that processes user requests and generates and transmits query data and other information.

[0406] "Initial question data" refers to information about the first question that the server presents to the user at the start of the medical interview.

[0407] "Terminal" means a device operated by a user to exchange information with a server.

[0408] An "emotion engine" refers to a system that analyzes a user's emotional state from their responses, voice, facial expressions, etc.

[0409] "Emotion" indicates the user's psychological and sensory state and is recognized by the system.

[0410] The "stress level" is an index that indicates the degree of stress that the user is feeling.

[0411] "Relaxation methods" refer to methods and suggestions for reducing stress and relaxing the user.

[0412] "Dynamic generation" means that new questions are generated in real time based on the user's answers and emotional state.

[0413] "Feedback" refers to the information or suggestions that the system returns in response to the user's answers.

[0414] "Diagnostic data" refers to data including the results of a user's medical interview and emotion analysis.

[0415] The system for realizing this invention is a combination of a server, a terminal, an emotion engine, and a relaxation suggestion engine. A specific description of this system is given below.

[0416] System Overview

[0417] The system works in a factory environment by connecting with devices used by workers to recognize their emotions and stress levels and provide feedback in real time.

[0418] Hardware and software used

[0419] Terminal: A device operated by a worker, such as a smartphone, tablet, or smart glasses.

[0420] Server: A computer system that processes various requests and analyzes and stores data. Often uses cloud services such as Amazon Web Services (AWS (registered trademark)).

[0421] Emotion engine: Software that analyzes emotional states. Examples include Google Cloud's Emotion Analysis API and Microsoft Azure's Emotion Recognition API.

[0422] Relaxation suggestion engine: A software module that suggests relaxation methods based on stress levels.

[0423] Processing flow

[0424] 1. The user operates the terminal and starts a medical interview session with this system.

[0425] 2. The device receives the user's input and sends the request to the server.

[0426] 3. The server generates the initial question data and sends it to the terminal.

[0427] 4. The device displays the question to the user, and the user enters the answer.

[0428] 5. The device sends the user's answer to the server.

[0429] 6. The server analyzes the user's answers and uses an emotion engine to recognize the user's emotions.

[0430] 7. The server dynamically generates the next question data based on the recognized emotion and sends it to the device.

[0431] 8. The terminal displays the next question to the user, and the user enters the answer. This process is repeated until all necessary questions have been answered.

[0432] 9. The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[0433] 10. After all questions are completed, the device will display a message indicating the session is over and all data will be saved on the server.

[0434] Specific use cases

[0435] For example, if a worker answers, "I'm working long hours today," the emotion engine will interpret the answer as "stress." The next question will then be, "That's tough. Shall we take a short break? Take a deep breath and relax," and the relaxation suggestion engine will be activated.

[0436] Prompt Sentence Examples

[0437] "You've been working long hours today. It's tough. Let's take a break. Take a deep breath and relax."

[0438] This system makes it possible to accurately grasp the emotional state of workers and provide appropriate feedback and suggestions for stress reduction.

[0439] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0440] Step 1:

[0441] The user operates the terminal and presses the inquiry start button to start the inquiry session.

[0442] Input: User initiates interview.

[0443] Output: The terminal generates a request to start an interview and sends it to the server.

[0444] Step 2:

[0445] The terminal receives the user's request to start the medical interview and transmits this information to the server.

[0446] Input: The request to start the interview sent by the user using the terminal.

[0447] Output: Received by the server as a trigger to generate the initial question data.

[0448] Step 3:

[0449] The server generates the initial question data and sends it to the terminal.

[0450] Input: A request to start an interview from the terminal.

[0451] Data processing: The server selects the first question of the medical interview based on the request to start the medical interview.

[0452] Output: Sends the initial question data to the terminal.

[0453] Step 4:

[0454] The terminal displays the question received from the server to the user.

[0455] Input: The initial question data sent by the server.

[0456] Output: The initial question is displayed on the terminal screen.

[0457] Step 5:

[0458] The user enters an answer to the question.

[0459] Input: The user's answer to the question displayed on the terminal.

[0460] Output: The device prepares the response data to send to the server.

[0461] Step 6:

[0462] The terminal sends the user's answer to the server.

[0463] Input: The answer data entered by the user.

[0464] Output: Send the answer data to the server.

[0465] Step 7:

[0466] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[0467] Input: User response data sent from the device.

[0468] Data calculation: The emotion engine analyzes voice tone and facial expressions based on response data to determine emotional state.

[0469] Output: Recognized emotion data.

[0470] Step 8:

[0471] The server dynamically generates the next question data based on the recognized emotion and sends it to the terminal.

[0472] Input: Recognized emotion data and previous response data.

[0473] Data processing: Dynamically generate new question content and expressions taking into account emotional data.

[0474] Output: Send the next question data to the terminal.

[0475] Step 9:

[0476] The terminal displays the next question to the user, and the user enters an answer to the next question. This process is repeated until all necessary questions have been answered.

[0477] Input: Next question data sent from the server.

[0478] Output: The following question will be displayed on the terminal screen:

[0479] Step 10:

[0480] The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[0481] Input: User response data and sentiment data.

[0482] Data calculation: Evaluate stress levels and recommend relaxation methods if necessary.

[0483] Output: Send relaxation suggestion data to device.

[0484] Step 11:

[0485] After all questions are completed, the terminal will display a message stating the end of the session and all data will be saved on the server.

[0486] Input: Completed response data and sentiment analysis data.

[0487] Data processing: Organize and store data on the server.

[0488] Output: Session termination message and saved data.

[0489] 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.

[0490] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0491] 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.

[0492] [Second embodiment]

[0493] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0494] 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.

[0495] 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).

[0496] 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.

[0497] 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.

[0498] 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).

[0499] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0504] 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."

[0505] The present invention relates to a system that allows a user to proceed with a medical interview in an interactive format. The processing of the program of this system will be specifically explained below in natural language.

[0506] System Overview

[0507] In this system, the user conducts a medical interview using a device such as a tablet or smartphone, and the next question is dynamically generated from the server based on the answers. Finally, all the answer data is notified to the doctor.

[0508] Program processing

[0509] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This operation starts the medical interview session.

[0510] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0511] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0512] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0513] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[0514] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[0515] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[0516] For example, if a user answers "I have a stomachache," the server dynamically generates a question such as "How bad is the pain? Mild, moderate, severe?" and displays it to the user.

[0517] 8. This iterative process continues until all necessary questions have been asked. At each step, the server analyzes the user's answers and dynamically generates appropriate questions.

[0518] 9. After all questions have been answered, the terminal displays a message to the user saying "Interview completed." At the same time, all answer data is finally sent to the server.

[0519] 10. The server saves the final diagnosis data and notifies the doctor if necessary, allowing the doctor to provide appropriate diagnosis and treatment based on the user's medical history.

[0520] This system is particularly useful for emergency patients, as it allows for quick and accurate medical interviews without placing a burden on the user.

[0521] The processing flow will be explained below.

[0522] Step 1:

[0523] The user presses the inquiry start button on the terminal to start the inquiry.

[0524] Specific action: Touch a button on the screen of a tablet or smartphone.

[0525] Step 2:

[0526] The terminal receives the user's request and sends a request to start an interview to the server.

[0527] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[0528] Step 3:

[0529] The server receives the request to start the medical interview and generates the initial question data.

[0530] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[0531] Step 4:

[0532] The server returns the generated initial question data to the terminal.

[0533] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[0534] Step 5:

[0535] The terminal analyzes the initial question data received from the server and displays it to the user.

[0536] Specific operation: Parse the JSON data and display the question text on the screen.

[0537] Step 6:

[0538] The user enters an answer to the initial question.

[0539] Specific actions: Enter text using the software keyboard and touch the send button.

[0540] Step 7:

[0541] The terminal sends the user's answer to the server.

[0542] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[0543] Step 8:

[0544] The server analyzes the user's answers and generates the next question data.

[0545] Specific behavior: Uses the rules engine to select the appropriate next question, fills in the answer content in a question template, and generates a JSON-formatted response.

[0546] Step 9:

[0547] The server generates the next question data and sends it to the terminal.

[0548] Specific operation: The following question data is sent in JSON format as an HTTP response.

[0549] Step 10:

[0550] The terminal analyzes the next question data received from the server and displays it to the user.

[0551] Specific behavior: Parse the JSON data and display the following question text on the screen.

[0552] Step 11:

[0553] Repeat steps 6 through 10 until all necessary questions have been asked.

[0554] Specific operation: Repeat the process of inputting a user answer, sending it to the server, and generating and displaying the next question.

[0555] Step 12:

[0556] The terminal confirms that all questions have been completed and displays a message to the user that the interview is complete.

[0557] Specific action: The text "Medical interview completed" is displayed on the screen.

[0558] Step 13:

[0559] The terminal finally transmits all response data to the server.

[0560] Specific operation: The answer data for all questions is converted into a list in JSON format and sent to the server via an HTTP request.

[0561] Step 14:

[0562] The server stores the final diagnosis data and notifies the doctor if necessary.

[0563] Specific actions: Saves the user's response history in a database and triggers notifications to the doctor, including sending emails and updating the admin interface.

[0564] Example 1

[0565] 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."

[0566] Conventional medical interview systems have the problem that it is difficult to dynamically generate the next question based on the user's answers, and only fixed questions can be displayed. Furthermore, as the user progresses through the medical interview, it is difficult to effectively exchange questions and answers, making it difficult for doctors to quickly and accurately obtain the information they need to make an appropriate diagnosis. This has led to problems, particularly in emergencies and for emergency patients, making it difficult to provide prompt and accurate responses.

[0567] 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.

[0568] In this invention, the server includes a means for analyzing the user's answers and generating the next question data, a means for dynamically generating the next question data using a generative AI model, and a means for saving the final diagnosis data and notifying the doctor as necessary. This enables dynamic question generation based on the user's answers, enabling the doctor to efficiently obtain information for a quick and accurate diagnosis.

[0569] "User" refers to an individual or patient who uses the system to conduct a medical interview.

[0570] The term "terminal device" refers to an electronic device, such as a tablet or smartphone, that a user uses to conduct a medical interview.

[0571] "Information processing device" refers to a central control device that functions as a server, receives user requests, and generates, analyzes, and stores data.

[0572] "Initial question data" refers to data including the content of the first question presented to the user at the start of the medical interview session.

[0573] "Next question data" refers to data that contains the question to be presented next, which is dynamically generated based on the user's answer.

[0574] A "generative AI model" refers to an artificial intelligence model (e.g., GPT-3) that generates the next best question based on user input.

[0575] "User answers" refers to the text or choices entered by the user for each question.

[0576] "Diagnostic data" refers to the final data provided by the server to the doctor based on all interview results.

[0577] "Notification means" refers to a communication means (e.g., email notification or message application) for transmitting final diagnosis data to a doctor.

[0578] This invention relates to a system that allows a user to proceed with an interview in an interactive format. The system aims to dynamically generate the next question based mainly on the user's input and provide the doctor with final diagnostic data.

[0579] Required Hardware and Software

[0580] Hardware:

[0581] Terminal devices such as tablets and smartphones

[0582] Information processing device (server)

[0583] software:

[0584] Frontend: Web application using HTML, CSS, and JavaScript

[0585] Backend: A server program using Python or Node.js

[0586] Database: MySQL or PostgreSQL

[0587] AI generative models, such as OpenAI's GPT-3

[0588] Program processing overview

[0589] Starting a Session

[0590] The user starts the medical interview using a terminal device such as a tablet or smartphone. At this time, the user presses a button to start the medical interview, which starts the session. For example, the user can start the process by pressing the "Start Medical Interview" button on a tablet while in a hospital waiting room.

[0591] First question generation and display

[0592] The terminal device receives the user's request and transmits this information to the information processing device. The information processing device processes this request, generates initial question data, and transmits it to the terminal device. The terminal device displays the received initial question data to the user, and the user inputs an answer in a specified field. For example, the initial question, "Where does it hurt?", is displayed.

[0593] Next question generation and iterative process

[0594] When the user enters an answer to a question and presses the send button, the answer data is sent again to the information processing device. The information processing device analyzes the user's answer and dynamically generates the next question data using a generative AI model (e.g., GPT-3). This process is repeated until all necessary questions have been completed. For example, in response to the answer "My stomach hurts," the next question generated is "How bad is the pain?"

[0595] Final diagnostic data storage and notification

[0596] After all questions have been answered, the terminal device displays a message to the user saying "The medical interview is complete." At the same time, all answer data is finally sent to the information processing device. The information processing device saves the final diagnosis data and notifies the doctor if necessary. This allows the doctor to obtain information necessary for a quick and accurate diagnosis.

[0597] Prompt Sentence Examples

[0598] Below are some example prompts to input to a generative AI model:

[0599] User input: "My stomach hurts"

[0600] Prompt to input to the generative AI model:

[0601] "If the user says 'I have a stomach ache,' generate the next appropriate question."

[0602] Based on this prompt, the generative AI model generates appropriate questions such as "How bad is your pain?" Applying this method makes it possible to realize flexible medical interviews based on the user's answers. This system provides effective and efficient medical interviews, enabling rapid response, especially in emergency situations and for emergency patients.

[0603] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The user presses the medical interview start button. This operation starts the medical interview session. The input is the user's operation, and the output is the generation of a medical interview start request by the terminal. A specific operation is when the user clicks the "medical interview start" button on a tablet or smartphone. In response to this operation, the terminal sends a request including metadata such as the user ID and session ID to the information processing device.

[0606] Step 2:

[0607] The terminal receives the user's request and sends it to the information processing device. The input is the user's request, and the output is the transmission of request data from the terminal to the information processing device. Specifically, JavaScript on the terminal catches the user's operation and sends a medical interview start request in JSON format to the information processing device.

[0608] Step 3:

[0609] The server receives a request to start the medical interview, generates the initial question data, and sends it to the terminal. The input is the request data received from the terminal, and the output is the initial question data. A Python script on the server receives the request, queries the database to obtain the "initial question," and returns it to the terminal in JSON format.

[0610] Step 4:

[0611] The device displays the initial question data it receives to the user. The input is the question data from the server, and the output is the question displayed to the user. Specifically, JavaScript parses the JSON data returned from the server, generates HTML elements, and displays the initial question, such as "Where does it hurt?", to the user.

[0612] Step 5:

[0613] The user inputs an answer to the question and presses the send button. The input is the user's answer, and the output is the transmission of the answer data from the terminal to the server. As a specific example, the user inputs "My stomach hurts" and presses the send button. This operation sends the answer data from the terminal to the server.

[0614] Step 6:

[0615] The server receives the user's answer and analyzes it. The input is the user's answer data, and the output is the generation of the next question data. Specifically, the server's Python script receives the answer data, inputs it as a prompt to the generative AI model (e.g., GPT-3), and generates the next question. An example of a prompt sentence is, "If the user says, 'My stomach hurts,' please generate the next appropriate question."

[0616] Step 7:

[0617] The server generates the next question and sends it to the terminal. The input is the next question data from the generative AI model, and the output is data sent to the terminal. The server sends the generated question to the terminal in JSON format.

[0618] Step 8:

[0619] The terminal displays the next question to the user. This process is repeated until the user has answered all questions. The input is the next question data from the server, and the output is the question displayed to the user. In concrete terms, JavaScript displays the next question, and the user enters the answer again.

[0620] Step 9:

[0621] After all questions have been asked, the terminal displays a message to the user saying "The medical interview has been completed." The input is the fact that all questions have been asked, and the output is the display of a completion message to the user. Specifically, the message "The medical interview has been completed. Thank you." is displayed on the screen.

[0622] Step 10:

[0623] The server saves the final diagnosis data and notifies the doctor. The input is all response data, and the output is saving and notifying the final diagnosis data. Specifically, the server saves all response data in a database and notifies the doctor via email or a notification system as needed.

[0624] This enables dynamic question generation based on the user's answers, enabling doctors to efficiently obtain information that allows them to make prompt and accurate diagnoses.

[0625] (Application example 1)

[0626] 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."

[0627] Conventional food delivery systems have the drawback of requiring users to select menu items and specify customization options, resulting in complex and inefficient operations. This has led to low user satisfaction and a lengthy ordering process. In particular, when users are unsure of their choices and ordering options, it can take a lot of effort to complete the order.

[0628] 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.

[0629] In this invention, the server includes a means for the user to start an order, a means for transmitting the user's request to the server, and a means for the server to generate initial question data and transmit it to the terminal, thereby enabling the user to smoothly select and customize menus interactively.

[0630] "User" refers to the person utilizing the system who initiates and progresses the ordering process.

[0631] "Means for initiating an order" refers to the operation or interface that allows a user to start the ordering process in the delivery system.

[0632] "Means for sending a request to a server" refers to a communication means for sending initial information or a request to a server based on a user's operation.

[0633] The "means for generating initial question data and transmitting it to the terminal" refers to a process by which the server generates a question to be presented to the user initially and transmits it to the user's terminal.

[0634] The "means for displaying to the user the question received by the terminal from the server" refers to a function for visually showing to the user the question received by the user's terminal from the server.

[0635] "Means for a user to input an answer to a question" refers to a function that allows a user to input an answer to a question from a server using a terminal.

[0636] "Means for transmitting the user's answer to the server" refers to a communication means for transmitting the answer entered by the user to the server.

[0637] "Means for the server to analyze the user's answer and generate the next question data" refers to the analysis and generation function that enables the server to automatically generate the next question based on the user's answer.

[0638] "Means for displaying the next question received by the terminal from the server to the user" refers to a function for the user's terminal to receive questions that are generated one after another and display them to the user.

[0639] "Means for generating and displaying the next question through an iterative process" refers to a system for continuously generating and displaying questions based on the user's answers.

[0640] "Means for finally transmitting answer data for all questions to the server when an order is completed" refers to means for finally transmitting answer data for all questions to the server when a user's order is completed.

[0641] "Means for the server to save the final order data and notify the service provider as necessary" refers to the function that enables the server to save all order data and notify the delivery service provider of that information as necessary.

[0642] The present invention relates to a food delivery system that allows users to interactively place orders. A specific implementation of this system will be described below.

[0643] System Overview:

[0644] In this system, users place food delivery orders using devices such as smartphones or tablets, and the server dynamically generates the next questions based on the answers. All answer data is finally sent to the service provider.

[0645] Hardware and software used:

[0646] Hardware: Smartphones, tablets

[0647] Software: Flask (a Python microframework), server (NGINX, Apache, etc. can be used)

[0648] Data processing and calculation:

[0649] 1. To begin an order, the user presses the Start Order button on the terminal. This action starts an ordering session.

[0650] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0651] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0652] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0653] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[0654] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[0655] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[0656] This iterative process continues until all necessary questions have been asked, with the server analyzing the user's answers at each step and dynamically generating appropriate questions.

[0657] Specific examples of behavior:

[0658] When a user initiates an order, the following interaction takes place:

[0659] Example prompt sentence:

[0660] 1. "Let's start ordering. What would you like? Pizza, burger, or salad?"

[0661] 2. The user answers "pizza"

[0662] 3. "Choose your pizza size: small, medium, or large?"

[0663] 4. The user answers "medium"

[0664] 5. "What toppings would you like to add to your medium pizza? Cheese, bacon?"

[0665] In this way, the user answers questions one by one, and when all information has been provided, the order data is sent to the server and, if necessary, notified to the service provider.

[0666] This system allows users to efficiently and intuitively navigate the food delivery ordering process.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] The user presses the order start button.

[0670] Input: User operation (pressing the order start button)

[0671] Output: Order session start request

[0672] Specific operation: When the user presses the order start button on the terminal, the terminal sends the user's request to the server, which starts the order.

[0673] Step 2:

[0674] The terminal receives the user's request and sends it to the server.

[0675] Input: User action (request to start an order)

[0676] Output: Initial question generation request

[0677] Specific operation: The terminal sends the user's request to the server, and the server begins preparations to generate the first question.

[0678] Step 3:

[0679] The server generates the initial question data and sends it to the terminal.

[0680] Input: Initial question generation request

[0681] Output: First question data

[0682] Specific operation: The server generates a question about the menu that the user should first choose (e.g., what would you like to order?) and sends that data to the terminal.

[0683] Step 4:

[0684] The terminal displays the question received from the server to the user.

[0685] Input: First question data

[0686] Output: The question displayed to the user

[0687] Specific operation: The terminal displays the initial question received from the server to the user and provides an interface for the user to input an answer.

[0688] Step 5:

[0689] The user enters an answer to the question, and the terminal sends the answer to the server.

[0690] Input: User's answer

[0691] Output: User's request to send an answer

[0692] Specific operation: The user enters an answer to the question displayed on the terminal and presses the send button. The terminal then sends the answer to the server.

[0693] Step 6:

[0694] The server analyzes the user's answers and generates the next question data.

[0695] Input: User's answer

[0696] Output: Next question data

[0697] Specific operation: The server analyzes the user's answer and generates the next appropriate question. For example, if the answer is "pizza," the next question generated is "Please choose the size of pizza."

[0698] Step 7:

[0699] The server generates the next question and sends it to the terminal, which displays it to the user.

[0700] Input: Next question data

[0701] Output: The next question displayed on the user's screen

[0702] Specific operation: The server generates the next question and sends it to the terminal, which displays it to the user. The user then enters the answer again.

[0703] Step 8:

[0704] Repeat this process until all necessary questions have been answered.

[0705] Input: Repeat previous step

[0706] Output: Final response data

[0707] Specific behavior: Continue this cycle of questions and answers until the user has answered all questions.

[0708] Step 9:

[0709] When the order is completed, the terminal finally transmits the answer data for all questions to the server.

[0710] Input: Answers to all questions

[0711] Output: Final order data transmission request

[0712] Specific operation: When the user inputs the final answer and presses the send button, the terminal finally sends all the answer data to the server.

[0713] Step 10:

[0714] The server stores the final order data and notifies the service provider if necessary.

[0715] Input: Final order data

[0716] Output: Stored order data and notifications

[0717] Specific operation: The server stores the final order data and notifies the delivery service provider of that data as necessary.

[0718] 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.

[0719] The present invention relates to a system that can conduct a dialogue-style medical interview while recognizing the user's emotions. The program processing of this system will be specifically explained below in natural language.

[0720] System Overview

[0721] This system allows users to use a terminal to answer questions, and the server dynamically generates the next questions based on the user's answers. It also incorporates an emotion engine that recognizes the user's emotions and dynamically changes the way questions are phrased based on their emotions. It also has a function to monitor stress levels and provide relaxation content as needed.

[0722] Program processing

[0723] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This starts the medical interview session.

[0724] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0725] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0726] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0727] 5. The device sends the user's answer to the server, which analyzes the answer and uses an emotion engine to recognize the user's emotion.

[0728] Examples of emotion engines

[0729] For example, if a user answers "I have a stomachache," and the emotion engine recognizes from the user's tone of voice and facial expression that they are under high stress, the next question will be changed from "How bad is the pain?" to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[0730] 6. The server dynamically generates the next question data based on the user's emotions and sends it to the terminal. This question data takes into account the user's emotional state.

[0731] 7. The terminal analyzes the next question data received from the server and displays it to the user. The user then enters the answer to the next question.

[0732] 8. The user enters and submits an answer to the question. This process is repeated until all of the user's questions have been answered.

[0733] For example, if a user responds with "it hurts a lot," and the emotion engine recognizes this as high stress, the system will display a message to the user suggesting relaxation techniques and deep breathing.

[0734] 9. After all questions have been answered, the device displays a message to the user saying, "The interview is complete. Thank you for your hard work." At the same time, all answer data and sentiment analysis data are finally sent to the server.

[0735] 10. The server saves the final diagnosis data and notifies the doctor if necessary. The doctor can then provide an appropriate diagnosis and treatment based on the user's interview details and emotional data.

[0736] This system is particularly useful for emergency patients, as it allows for quick and accurate interviews without placing a burden on the user. Furthermore, by using an emotion engine, the system can take the user's emotional state into consideration during the interview, enabling more friendly and effective communication.

[0737] The processing flow will be explained below.

[0738] Step 1:

[0739] The user presses the inquiry start button on the terminal to start the inquiry.

[0740] Specific action: Touch a button on the screen of a tablet or smartphone.

[0741] Step 2:

[0742] The terminal receives the user's request and sends a request to start an interview to the server.

[0743] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[0744] Step 3:

[0745] The server receives the request to start the medical interview and generates the initial question data.

[0746] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[0747] Step 4:

[0748] The server returns the generated initial question data to the terminal.

[0749] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[0750] Step 5:

[0751] The terminal analyzes the initial question data received from the server and displays it to the user.

[0752] Specific operation: Parse the JSON data and display the question text on the screen.

[0753] Step 6:

[0754] The user enters an answer to the initial question.

[0755] Specific actions: Enter text using the software keyboard and touch the send button.

[0756] Step 7:

[0757] The terminal sends the user's answer to the server.

[0758] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[0759] Step 8:

[0760] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[0761] Specific operation: Executes an algorithm to determine emotions based on voice tone, facial expressions, input speed and strength, etc.

[0762] Step 9:

[0763] The server dynamically generates the next question data based on the user's emotions and sends it to the terminal.

[0764] Specific operation: The system uses a rules engine to select the appropriate next question, embeds expressions that take into account the user's emotional state in the question template, and generates a JSON-formatted response.

[0765] Step 10:

[0766] The terminal analyzes the next question data received from the server and displays it to the user.

[0767] Specific operation: Analyzes the JSON data and displays the next question text on the screen, reflecting the emotional state.

[0768] Step 11:

[0769] The user answers the following questions and submits.

[0770] Specific actions: Enter text using the software keyboard and touch the send button.

[0771] Step 12:

[0772] The terminal sends the user's answer to the server, which generates the next question.

[0773] Specific operation: The answer data is converted into JSON format and sent to the server via an HTTP request. The server again uses the emotion engine to recognize the user's emotion and the rule engine to select the next question.

[0774] Step 13:

[0775] Repeat steps 8 through 12 until all necessary questions have been asked.

[0776] Specific operation: User inputs answer, sends it to the server, recognizes emotion, and generates and displays the next question, repeating this process.

[0777] Step 14:

[0778] After all questions have been answered, the terminal displays a message to the user indicating that the interview is complete.

[0779] Specific action: Display the text "The medical interview has been completed. Thank you for your hard work" on the screen.

[0780] Step 15:

[0781] The device finally transmits all response data and sentiment analysis data to the server.

[0782] Specific operation: The answer data and sentiment analysis data for all questions are converted into JSON format and sent to the server via an HTTP request.

[0783] Step 16:

[0784] The server stores the final diagnosis data and notifies the doctor if necessary.

[0785] Specific behavior: Stores the user's response history and emotion data in a database and triggers notifications to doctors, including sending emails and updating the management interface.

[0786] This series of processes allows the user to proceed with the medical interview in a friendly dialogue format that takes into account the user's emotional state, making it possible to collect information quickly and accurately, especially for emergency patients.

[0787] Example 2

[0788] 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."

[0789] Conventional medical interview systems have problems in that they ask questions without considering the user's emotions, which can cause stress to the user or prevent them from obtaining appropriate information. This can increase the user's psychological burden, especially in emergencies, making it difficult to conduct an accurate medical interview. Furthermore, because the system does not consider the user's emotional state, it is insufficient to provide relaxation methods or appropriate responses to the user.

[0790] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0791] In this invention, the server includes means for analyzing the user's answers, recognizing emotions using a sentiment analysis engine, and generating next question data, means for providing relaxation content according to the user's emotional state, and means for saving the user's answer data and sentiment analysis data and notifying the doctor as necessary. This allows for a friendly and effective medical interview to be conducted while taking the user's emotions into consideration, reducing the user's psychological burden and enabling more accurate information to be collected.

[0792] "User" refers to an individual who uses the system to take a medical interview.

[0793] "Device" refers to the hardware device (e.g., smartphone, tablet, PC) used by the user to complete the interview.

[0794] A "medical interview start button" is an interface element that is displayed on a terminal to allow a user to start a medical interview session.

[0795] A "request" refers to the data format used to send operations and input data that a user performs on a system to a server.

[0796] A "server" is a central control system that receives requests and processes or generates data.

[0797] The "initial question data" is data that is generated by the server when a medical interview session is started and includes the content of the question that is first presented to the user.

[0798] An "emotion analysis engine" is software or algorithms that analyze a user's responses, tone of voice, facial expressions, etc. to recognize the user's emotional state.

[0799] The "next question data" is data that is dynamically generated by the server based on the user's answer and emotional state, and includes the content of the question to be presented to the user next.

[0800] "Relaxation content" refers to information and suggestions to reduce the user's psychological burden that are provided when the user's emotional state, particularly a high-stress state, is recognized.

[0801] "Emotion analysis data" refers to data regarding a user's emotional state obtained by an emotion analysis engine.

[0802] "Final diagnostic data" refers to final diagnostic information including user response data and emotion analysis data collected throughout the entire interview process.

[0803] The present invention relates to a system that conducts an interview in an interactive format while recognizing the user's emotions. In this system, the user uses a terminal to conduct an interview, and the server dynamically generates the next question based on the user's answers. Furthermore, the system incorporates a sentiment analysis engine and has the function of dynamically changing the way questions are phrased based on the user's emotions. It also has the function of monitoring the user's stress level and providing relaxation content as needed.

[0804] Hardware and software used

[0805] Hardware

[0806] Device (e.g. smartphone, tablet, PC)

[0807] Server (e.g. cloud server, on-premise server)

[0808] software

[0809] Interaction Management Applications

[0810] Sentiment analysis engines (e.g., IBM Watson, Microsoft Azure Emotion API)

[0811] Overview of program processing

[0812] The system operates in the following steps:

[0813] 1. The user presses the start button on the device to start the medical interview session.

[0814] 2. The device sends the user's request to the server, and the server generates the initial question data and sends it to the device.

[0815] 3. The server generates the initial question data, and the device displays the received question to the user.

[0816] 4. The user enters the answer to the question, and the device sends the answer to the server.

[0817] 5. The server analyzes the user's answers and uses a sentiment analysis engine to recognize the user's emotions.

[0818] 6. The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[0819] 7. The terminal analyzes the next question data and displays it to the user.

[0820] 8. The user answers the next question and this process is repeated until all of the user's questions have been answered.

[0821] 9. After all questions have been completed, the device will display the message "The medical interview is complete. Thank you for your hard work." and send all response data and emotion analysis data to the server.

[0822] 10. The server stores the final diagnosis data and notifies the doctor if necessary.

[0823] Specific examples

[0824] For example, if a user answers "I have a stomachache," the emotion analysis engine will recognize from the user's tone of voice and facial expression that they are under high stress. In this case, the next question will be changed from "Please tell me the level of pain," to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[0825] Example prompts to input to the generative AI model

[0826] "When the user answers 'My stomach hurts', generate the next question taking into account their emotions."

[0827] This system provides a fast and accurate interview process while minimizing the psychological burden on the user. In addition, by incorporating a sentiment analysis engine, it realizes friendly and effective communication while taking into account the user's emotions, making it particularly useful in emergencies and high-stress situations.

[0828] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0829] Step 1:

[0830] The user presses the inquiry start button on the terminal to start the inquiry session.

[0831] Specific operation: The user taps the "Start medical interview" button displayed on the smartphone screen. As input, a medical interview start request is generated. As output, an event indicating that the medical interview session has started is generated.

[0832] Step 2:

[0833] The terminal generates a request to start an interview and sends it to the server.

[0834] Specific operation: The terminal generates a medical interview start request including the user ID and the current date and time, and sends it to the server via the Internet. The input is the user's tap event, and the output is the transmission of the medical interview start request.

[0835] Step 3:

[0836] The server receives the request to start the medical interview and generates the initial question data.

[0837] Specific operation: The server generates data including a question such as "Where does it hurt?" as the first question. The input is a request to start the medical interview, and the output is the first question data.

[0838] Step 4:

[0839] The server sends the initial question data to the terminal.

[0840] Specific operation: The process of sending query data generated by the server to the terminal. The input is the initial query data, and the output is sending the data to the terminal.

[0841] Step 5:

[0842] The terminal receives the initial question data and displays it to the user.

[0843] Specific operation: The terminal displays the initial question data received from the server on the screen. The input is the received question data, and the output is what is displayed to the user.

[0844] Step 6:

[0845] The user enters an answer to the question, and the terminal sends the answer to the server.

[0846] Specific operation: The user enters an answer in the text box and clicks the send button. The terminal sends this answer data to the server. The input is the user's answer data, and the output is the transmission of the answer data.

[0847] Step 7:

[0848] The server analyzes the user's responses and uses a sentiment analysis engine to recognize the user's emotions.

[0849] Specific operation: The server applies an analysis algorithm to analyze the user's response data, voice tone, and facial expressions. The input is the user's response data, and the output is the emotion analysis result.

[0850] Step 8:

[0851] The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[0852] Specific operation: The server generates the next question data taking into account the user's emotional state and sends it to the device. For example, instead of a general question such as "Please tell me the level of pain," it generates a friendly question such as "It sounds like you're in a lot of pain. How bad is it?" The input is the emotion analysis result, and the output is the next question data.

[0853] Step 9:

[0854] The terminal analyzes the next question data and displays it to the user.

[0855] Specific operation: The terminal displays the next question data it has received. The input is the next question data, and the output is what is displayed to the user.

[0856] Step 10:

[0857] The user answers the next question and the process repeats until all of the user's questions have been answered.

[0858] Specific operation: The user enters an answer to the next question and submits it. This process is repeated. The input is the questions that are generated one after another and the user's answer data to those questions, and the output is the final accumulation of answer data.

[0859] Step 11:

[0860] After all questions have been completed, the device displays the message "The medical interview is complete. Thank you for your hard work." and sends all response data and emotion analysis data to the server.

[0861] Specific operation: When the user answers the last question, the terminal displays a completion message and sends all data to the server. The input is the final answer data, and the output is the display of the completion message and the sending of data.

[0862] Step 12:

[0863] The server stores the final diagnosis data and notifies the doctor if necessary.

[0864] Specific operation: The server stores all received data and sends alerts to doctors via email or notification systems (e.g., Slack, Teams, etc.). The input is the submitted response data and sentiment analysis data, and the output is the storage of the final diagnosis data and notification to the doctor.

[0865] (Application example 2)

[0866] 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."

[0867] Current factory environments lack systems that can properly recognize workers' emotions and stress levels and provide feedback and relaxation suggestions based on that information. This can have a negative impact on work efficiency and workers' mental health. It is necessary to accurately grasp workers' emotional states and provide appropriate follow-up when checking the progress of work and adjusting tasks on-site. Currently, there are no means to solve these issues, and improvements to the work environment are stalled.

[0868] 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.

[0869] In this invention, the server includes means for recognizing the user's emotions using an emotion engine, means for dynamically generating the next question data based on the emotion and sending it to the terminal, and means for the emotion engine to monitor the user's stress level and suggest relaxation methods as necessary. This makes it possible to accurately grasp the emotions and stress levels of workers and provide appropriate feedback and suggestions in real time.

[0870] "User" refers to a person who uses the system.

[0871] "Medical interview" refers to the process of gathering information by asking questions about a user's health status and symptoms.

[0872] A "request" refers to data or a request that a user sends to a server.

[0873] "Server" means a computer system that processes user requests and generates and transmits query data and other information.

[0874] "Initial question data" refers to information about the first question that the server presents to the user at the start of the medical interview.

[0875] "Terminal" means a device operated by a user to exchange information with a server.

[0876] An "emotion engine" refers to a system that analyzes a user's emotional state from their responses, voice, facial expressions, etc.

[0877] "Emotion" indicates the user's psychological and sensory state and is recognized by the system.

[0878] The "stress level" is an index that indicates the degree of stress that the user is feeling.

[0879] "Relaxation methods" refer to methods and suggestions for reducing stress and relaxing the user.

[0880] "Dynamic generation" means that new questions are generated in real time based on the user's answers and emotional state.

[0881] "Feedback" refers to the information or suggestions that the system returns in response to the user's answers.

[0882] "Diagnostic data" refers to data including the results of a user's medical interview and emotion analysis.

[0883] The system for realizing this invention is a combination of a server, a terminal, an emotion engine, and a relaxation suggestion engine. A specific description of this system is given below.

[0884] System Overview

[0885] The system works in a factory environment by connecting with devices used by workers to recognize their emotions and stress levels and provide feedback in real time.

[0886] Hardware and software used

[0887] Terminal: A device operated by a worker, such as a smartphone, tablet, or smart glasses.

[0888] Server: A computer system that processes various requests and analyzes and stores data. Often uses cloud services such as Amazon Web Services (AWS).

[0889] Emotion engine: Software that analyzes emotional states. Examples include Google Cloud's Emotion Analysis API and Microsoft Azure's Emotion Recognition API.

[0890] Relaxation suggestion engine: A software module that suggests relaxation methods based on stress levels.

[0891] Processing flow

[0892] 1. The user operates the terminal and starts a medical interview session with this system.

[0893] 2. The device receives the user's input and sends the request to the server.

[0894] 3. The server generates the initial question data and sends it to the terminal.

[0895] 4. The device displays the question to the user, and the user enters the answer.

[0896] 5. The device sends the user's answer to the server.

[0897] 6. The server analyzes the user's answers and uses an emotion engine to recognize the user's emotions.

[0898] 7. The server dynamically generates the next question data based on the recognized emotion and sends it to the device.

[0899] 8. The terminal displays the next question to the user, and the user enters the answer. This process is repeated until all necessary questions have been answered.

[0900] 9. The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[0901] 10. After all questions are completed, the device will display a message indicating the session is over and all data will be saved on the server.

[0902] Specific use cases

[0903] For example, if a worker answers, "I'm working long hours today," the emotion engine will interpret the answer as "stress." The next question will then be, "That's tough. Shall we take a short break? Take a deep breath and relax," and the relaxation suggestion engine will be activated.

[0904] Prompt Sentence Examples

[0905] "You've been working long hours today. It's tough. Let's take a break. Take a deep breath and relax."

[0906] This system makes it possible to accurately grasp the emotional state of workers and provide appropriate feedback and suggestions for stress reduction.

[0907] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0908] Step 1:

[0909] The user operates the terminal and presses the inquiry start button to start the inquiry session.

[0910] Input: User initiates interview.

[0911] Output: The terminal generates a request to start an interview and sends it to the server.

[0912] Step 2:

[0913] The terminal receives the user's request to start the medical interview and transmits this information to the server.

[0914] Input: The request to start the interview sent by the user using the terminal.

[0915] Output: Received by the server as a trigger to generate the initial question data.

[0916] Step 3:

[0917] The server generates the initial question data and sends it to the terminal.

[0918] Input: A request to start an interview from the terminal.

[0919] Data processing: The server selects the first question of the medical interview based on the request to start the medical interview.

[0920] Output: Sends the initial question data to the terminal.

[0921] Step 4:

[0922] The terminal displays the question received from the server to the user.

[0923] Input: The initial question data sent by the server.

[0924] Output: The initial question is displayed on the terminal screen.

[0925] Step 5:

[0926] The user enters an answer to the question.

[0927] Input: The user's answer to the question displayed on the terminal.

[0928] Output: The device prepares the response data to send to the server.

[0929] Step 6:

[0930] The terminal sends the user's answer to the server.

[0931] Input: The answer data entered by the user.

[0932] Output: Send the answer data to the server.

[0933] Step 7:

[0934] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[0935] Input: User response data sent from the device.

[0936] Data calculation: The emotion engine analyzes voice tone and facial expressions based on response data to determine emotional state.

[0937] Output: Recognized emotion data.

[0938] Step 8:

[0939] The server dynamically generates the next question data based on the recognized emotion and sends it to the terminal.

[0940] Input: Recognized emotion data and previous response data.

[0941] Data processing: Dynamically generate new question content and expressions taking into account emotional data.

[0942] Output: Send the next question data to the terminal.

[0943] Step 9:

[0944] The terminal displays the next question to the user, and the user enters an answer to the next question. This process is repeated until all necessary questions have been answered.

[0945] Input: Next question data sent from the server.

[0946] Output: The following question will be displayed on the terminal screen:

[0947] Step 10:

[0948] The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[0949] Input: User response data and sentiment data.

[0950] Data calculation: Evaluate stress levels and recommend relaxation methods if necessary.

[0951] Output: Send relaxation suggestion data to device.

[0952] Step 11:

[0953] After all questions are completed, the terminal will display a message stating the end of the session and all data will be saved on the server.

[0954] Input: Completed response data and sentiment analysis data.

[0955] Data processing: Organize and store data on the server.

[0956] Output: Session termination message and saved data.

[0957] 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.

[0958] 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.

[0959] 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.

[0960] [Third embodiment]

[0961] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0962] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0963] 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).

[0964] 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.

[0965] 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.

[0966] 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).

[0967] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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."

[0973] The present invention relates to a system that allows a user to proceed with a medical interview in an interactive format. The processing of the program of this system will be specifically explained below in natural language.

[0974] System Overview

[0975] In this system, the user conducts a medical interview using a device such as a tablet or smartphone, and the next question is dynamically generated from the server based on the answers. Finally, all the answer data is notified to the doctor.

[0976] Program processing

[0977] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This operation starts the medical interview session.

[0978] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[0979] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[0980] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[0981] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[0982] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[0983] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[0984] For example, if a user answers "I have a stomachache," the server dynamically generates a question such as "How bad is the pain? Mild, moderate, severe?" and displays it to the user.

[0985] 8. This iterative process continues until all necessary questions have been asked. At each step, the server analyzes the user's answers and dynamically generates appropriate questions.

[0986] 9. After all questions have been answered, the terminal displays a message to the user saying "Interview completed." At the same time, all answer data is finally sent to the server.

[0987] 10. The server saves the final diagnosis data and notifies the doctor if necessary, allowing the doctor to provide appropriate diagnosis and treatment based on the user's medical history.

[0988] This system is particularly useful for emergency patients, as it allows for quick and accurate medical interviews without placing a burden on the user.

[0989] The processing flow will be explained below.

[0990] Step 1:

[0991] The user presses the inquiry start button on the terminal to start the inquiry.

[0992] Specific action: Touch a button on the screen of a tablet or smartphone.

[0993] Step 2:

[0994] The terminal receives the user's request and sends a request to start an interview to the server.

[0995] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[0996] Step 3:

[0997] The server receives the request to start the medical interview and generates the initial question data.

[0998] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[0999] Step 4:

[1000] The server returns the generated initial question data to the terminal.

[1001] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[1002] Step 5:

[1003] The terminal analyzes the initial question data received from the server and displays it to the user.

[1004] Specific operation: Parse the JSON data and display the question text on the screen.

[1005] Step 6:

[1006] The user enters an answer to the initial question.

[1007] Specific actions: Enter text using the software keyboard and touch the send button.

[1008] Step 7:

[1009] The terminal sends the user's answer to the server.

[1010] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[1011] Step 8:

[1012] The server analyzes the user's answers and generates the next question data.

[1013] Specific behavior: Uses the rules engine to select the appropriate next question, fills in the answer content in a question template, and generates a JSON-formatted response.

[1014] Step 9:

[1015] The server generates the next question data and sends it to the terminal.

[1016] Specific operation: The following question data is sent in JSON format as an HTTP response.

[1017] Step 10:

[1018] The terminal analyzes the next question data received from the server and displays it to the user.

[1019] Specific behavior: Parse the JSON data and display the following question text on the screen.

[1020] Step 11:

[1021] Repeat steps 6 through 10 until all necessary questions have been asked.

[1022] Specific operation: Repeat the process of inputting a user answer, sending it to the server, and generating and displaying the next question.

[1023] Step 12:

[1024] The terminal confirms that all questions have been completed and displays a message to the user that the interview is complete.

[1025] Specific action: The text "Medical interview completed" is displayed on the screen.

[1026] Step 13:

[1027] The terminal finally transmits all response data to the server.

[1028] Specific operation: The answer data for all questions is converted into a list in JSON format and sent to the server via an HTTP request.

[1029] Step 14:

[1030] The server stores the final diagnosis data and notifies the doctor if necessary.

[1031] Specific actions: Saves the user's response history in a database and triggers notifications to the doctor, including sending emails and updating the admin interface.

[1032] Example 1

[1033] 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."

[1034] Conventional medical interview systems have the problem that it is difficult to dynamically generate the next question based on the user's answers, and only fixed questions can be displayed. Furthermore, as the user progresses through the medical interview, it is difficult to effectively exchange questions and answers, making it difficult for doctors to quickly and accurately obtain the information they need to make an appropriate diagnosis. This has led to problems, particularly in emergencies and for emergency patients, making it difficult to provide prompt and accurate responses.

[1035] 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.

[1036] In this invention, the server includes a means for analyzing the user's answers and generating the next question data, a means for dynamically generating the next question data using a generative AI model, and a means for saving the final diagnosis data and notifying the doctor as necessary. This enables dynamic question generation based on the user's answers, enabling the doctor to efficiently obtain information for a quick and accurate diagnosis.

[1037] "User" refers to an individual or patient who uses the system to conduct a medical interview.

[1038] The term "terminal device" refers to an electronic device, such as a tablet or smartphone, that a user uses to conduct a medical interview.

[1039] "Information processing device" refers to a central control device that functions as a server, receives user requests, and generates, analyzes, and stores data.

[1040] "Initial question data" refers to data including the content of the first question presented to the user at the start of the medical interview session.

[1041] "Next question data" refers to data that contains the question to be presented next, which is dynamically generated based on the user's answer.

[1042] A "generative AI model" refers to an artificial intelligence model (e.g., GPT-3) that generates the next best question based on user input.

[1043] "User answers" refers to the text or choices entered by the user for each question.

[1044] "Diagnostic data" refers to the final data provided by the server to the doctor based on all interview results.

[1045] "Notification means" refers to a communication means (e.g., email notification or message application) for transmitting final diagnosis data to a doctor.

[1046] This invention relates to a system that allows a user to proceed with an interview in an interactive format. The system aims to dynamically generate the next question based mainly on the user's input and provide the doctor with final diagnostic data.

[1047] Required Hardware and Software

[1048] Hardware:

[1049] Terminal devices such as tablets and smartphones

[1050] Information processing device (server)

[1051] software:

[1052] Frontend: Web application using HTML, CSS, and JavaScript

[1053] Backend: A server program using Python or Node.js

[1054] Database: MySQL or PostgreSQL

[1055] AI generative models, such as OpenAI's GPT-3

[1056] Program processing overview

[1057] Starting a Session

[1058] The user starts the medical interview using a terminal device such as a tablet or smartphone. At this time, the user presses a button to start the medical interview, which starts the session. For example, the user can start the process by pressing the "Start Medical Interview" button on a tablet while in a hospital waiting room.

[1059] First question generation and display

[1060] The terminal device receives the user's request and transmits this information to the information processing device. The information processing device processes this request, generates initial question data, and transmits it to the terminal device. The terminal device displays the received initial question data to the user, and the user inputs an answer in a specified field. For example, the initial question, "Where does it hurt?", is displayed.

[1061] Next question generation and iterative process

[1062] When the user enters an answer to a question and presses the send button, the answer data is sent again to the information processing device. The information processing device analyzes the user's answer and dynamically generates the next question data using a generative AI model (e.g., GPT-3). This process is repeated until all necessary questions have been completed. For example, in response to the answer "My stomach hurts," the next question generated is "How bad is the pain?"

[1063] Final diagnostic data storage and notification

[1064] After all questions have been answered, the terminal device displays a message to the user saying "The medical interview is complete." At the same time, all answer data is finally sent to the information processing device. The information processing device saves the final diagnosis data and notifies the doctor if necessary. This allows the doctor to obtain information necessary for a quick and accurate diagnosis.

[1065] Prompt Sentence Examples

[1066] Below are some example prompts to input to a generative AI model:

[1067] User input: "My stomach hurts"

[1068] Prompt to input to the generative AI model:

[1069] "If the user says 'I have a stomach ache,' generate the next appropriate question."

[1070] Based on this prompt, the generative AI model generates appropriate questions such as "How bad is your pain?" Applying this method makes it possible to realize flexible medical interviews based on the user's answers. This system provides effective and efficient medical interviews, enabling rapid response, especially in emergency situations and for emergency patients.

[1071] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1072] Step 1:

[1073] The user presses the medical interview start button. This operation starts the medical interview session. The input is the user's operation, and the output is the generation of a medical interview start request by the terminal. A specific operation is when the user clicks the "medical interview start" button on a tablet or smartphone. In response to this operation, the terminal sends a request including metadata such as the user ID and session ID to the information processing device.

[1074] Step 2:

[1075] The terminal receives the user's request and sends it to the information processing device. The input is the user's request, and the output is the transmission of request data from the terminal to the information processing device. Specifically, JavaScript on the terminal catches the user's operation and sends a medical interview start request in JSON format to the information processing device.

[1076] Step 3:

[1077] The server receives a request to start the medical interview, generates the initial question data, and sends it to the terminal. The input is the request data received from the terminal, and the output is the initial question data. A Python script on the server receives the request, queries the database to obtain the "initial question," and returns it to the terminal in JSON format.

[1078] Step 4:

[1079] The device displays the initial question data it receives to the user. The input is the question data from the server, and the output is the question displayed to the user. Specifically, JavaScript parses the JSON data returned from the server, generates HTML elements, and displays the initial question, such as "Where does it hurt?", to the user.

[1080] Step 5:

[1081] The user inputs an answer to the question and presses the send button. The input is the user's answer, and the output is the transmission of the answer data from the terminal to the server. As a specific example, the user inputs "My stomach hurts" and presses the send button. This operation sends the answer data from the terminal to the server.

[1082] Step 6:

[1083] The server receives the user's answer and analyzes it. The input is the user's answer data, and the output is the generation of the next question data. Specifically, the server's Python script receives the answer data, inputs it as a prompt to the generative AI model (e.g., GPT-3), and generates the next question. An example of a prompt sentence is, "If the user says, 'My stomach hurts,' please generate the next appropriate question."

[1084] Step 7:

[1085] The server generates the next question and sends it to the terminal. The input is the next question data from the generative AI model, and the output is data sent to the terminal. The server sends the generated question to the terminal in JSON format.

[1086] Step 8:

[1087] The terminal displays the next question to the user. This process is repeated until the user has answered all questions. The input is the next question data from the server, and the output is the question displayed to the user. In concrete terms, JavaScript displays the next question, and the user enters the answer again.

[1088] Step 9:

[1089] After all questions have been asked, the terminal displays a message to the user saying "The medical interview has been completed." The input is the fact that all questions have been asked, and the output is the display of a completion message to the user. Specifically, the message "The medical interview has been completed. Thank you." is displayed on the screen.

[1090] Step 10:

[1091] The server saves the final diagnosis data and notifies the doctor. The input is all response data, and the output is saving and notifying the final diagnosis data. Specifically, the server saves all response data in a database and notifies the doctor via email or a notification system as needed.

[1092] This enables dynamic question generation based on the user's answers, enabling doctors to efficiently obtain information that allows them to make prompt and accurate diagnoses.

[1093] (Application example 1)

[1094] 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."

[1095] Conventional food delivery systems have the drawback of requiring users to select menu items and specify customization options, resulting in complex and inefficient operations. This has led to low user satisfaction and a lengthy ordering process. In particular, when users are unsure of their choices and ordering options, it can take a lot of effort to complete the order.

[1096] 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.

[1097] In this invention, the server includes a means for the user to start an order, a means for transmitting the user's request to the server, and a means for the server to generate initial question data and transmit it to the terminal, thereby enabling the user to smoothly select and customize menus interactively.

[1098] "User" refers to the person utilizing the system who initiates and progresses the ordering process.

[1099] "Means for initiating an order" refers to the operation or interface that allows a user to start the ordering process in the delivery system.

[1100] "Means for sending a request to a server" refers to a communication means for sending initial information or a request to a server based on a user's operation.

[1101] The "means for generating initial question data and transmitting it to the terminal" refers to a process by which the server generates a question to be presented to the user initially and transmits it to the user's terminal.

[1102] The "means for displaying to the user the question received by the terminal from the server" refers to a function for visually showing to the user the question received by the user's terminal from the server.

[1103] "Means for a user to input an answer to a question" refers to a function that allows a user to input an answer to a question from a server using a terminal.

[1104] "Means for transmitting the user's answer to the server" refers to a communication means for transmitting the answer entered by the user to the server.

[1105] "Means for the server to analyze the user's answer and generate the next question data" refers to the analysis and generation function that enables the server to automatically generate the next question based on the user's answer.

[1106] "Means for displaying the next question received by the terminal from the server to the user" refers to a function for the user's terminal to receive questions that are generated one after another and display them to the user.

[1107] "Means for generating and displaying the next question through an iterative process" refers to a system for continuously generating and displaying questions based on the user's answers.

[1108] "Means for finally transmitting answer data for all questions to the server when an order is completed" refers to means for finally transmitting answer data for all questions to the server when a user's order is completed.

[1109] "Means for the server to save the final order data and notify the service provider as necessary" refers to the function that enables the server to save all order data and notify the delivery service provider of that information as necessary.

[1110] The present invention relates to a food delivery system that allows users to interactively place orders. A specific implementation of this system will be described below.

[1111] System Overview:

[1112] In this system, users place food delivery orders using devices such as smartphones or tablets, and the server dynamically generates the next questions based on the answers. All answer data is finally sent to the service provider.

[1113] Hardware and software used:

[1114] Hardware: Smartphones, tablets

[1115] Software: Flask (a Python microframework), server (NGINX, Apache, etc. can be used)

[1116] Data processing and calculation:

[1117] 1. To begin an order, the user presses the Start Order button on the terminal. This action starts an ordering session.

[1118] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[1119] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[1120] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[1121] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[1122] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[1123] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[1124] This iterative process continues until all necessary questions have been asked, with the server analyzing the user's answers at each step and dynamically generating appropriate questions.

[1125] Specific examples of behavior:

[1126] When a user initiates an order, the following interaction takes place:

[1127] Example prompt sentence:

[1128] 1. "Let's start ordering. What would you like? Pizza, burger, or salad?"

[1129] 2. The user answers "pizza"

[1130] 3. "Choose your pizza size: small, medium, or large?"

[1131] 4. The user answers "medium"

[1132] 5. "What toppings would you like to add to your medium pizza? Cheese, bacon?"

[1133] In this way, the user answers questions one by one, and when all information has been provided, the order data is sent to the server and, if necessary, notified to the service provider.

[1134] This system allows users to efficiently and intuitively navigate the food delivery ordering process.

[1135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1136] Step 1:

[1137] The user presses the order start button.

[1138] Input: User operation (pressing the order start button)

[1139] Output: Order session start request

[1140] Specific operation: When the user presses the order start button on the terminal, the terminal sends the user's request to the server, which starts the order.

[1141] Step 2:

[1142] The terminal receives the user's request and sends it to the server.

[1143] Input: User action (request to start an order)

[1144] Output: Initial question generation request

[1145] Specific operation: The terminal sends the user's request to the server, and the server begins preparations to generate the first question.

[1146] Step 3:

[1147] The server generates the initial question data and sends it to the terminal.

[1148] Input: Initial question generation request

[1149] Output: First question data

[1150] Specific operation: The server generates a question about the menu that the user should first choose (e.g., what would you like to order?) and sends that data to the terminal.

[1151] Step 4:

[1152] The terminal displays the question received from the server to the user.

[1153] Input: First question data

[1154] Output: The question displayed to the user

[1155] Specific operation: The terminal displays the initial question received from the server to the user and provides an interface for the user to input an answer.

[1156] Step 5:

[1157] The user enters an answer to the question, and the terminal sends the answer to the server.

[1158] Input: User's answer

[1159] Output: User's request to send an answer

[1160] Specific operation: The user enters an answer to the question displayed on the terminal and presses the send button. The terminal then sends the answer to the server.

[1161] Step 6:

[1162] The server analyzes the user's answers and generates the next question data.

[1163] Input: User's answer

[1164] Output: Next question data

[1165] Specific operation: The server analyzes the user's answer and generates the next appropriate question. For example, if the answer is "pizza," the next question generated is "Please choose the size of pizza."

[1166] Step 7:

[1167] The server generates the next question and sends it to the terminal, which displays it to the user.

[1168] Input: Next question data

[1169] Output: The next question displayed on the user's screen

[1170] Specific operation: The server generates the next question and sends it to the terminal, which displays it to the user. The user then enters the answer again.

[1171] Step 8:

[1172] Repeat this process until all necessary questions have been answered.

[1173] Input: Repeat previous step

[1174] Output: Final response data

[1175] Specific behavior: Continue this cycle of questions and answers until the user has answered all questions.

[1176] Step 9:

[1177] When the order is completed, the terminal finally transmits the answer data for all questions to the server.

[1178] Input: Answers to all questions

[1179] Output: Final order data transmission request

[1180] Specific operation: When the user inputs the final answer and presses the send button, the terminal finally sends all the answer data to the server.

[1181] Step 10:

[1182] The server stores the final order data and notifies the service provider if necessary.

[1183] Input: Final order data

[1184] Output: Stored order data and notifications

[1185] Specific operation: The server stores the final order data and notifies the delivery service provider of that data as necessary.

[1186] 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.

[1187] The present invention relates to a system that can conduct a dialogue-style medical interview while recognizing the user's emotions. The program processing of this system will be specifically explained below in natural language.

[1188] System Overview

[1189] This system allows users to use a terminal to answer questions, and the server dynamically generates the next questions based on the user's answers. It also incorporates an emotion engine that recognizes the user's emotions and dynamically changes the way questions are phrased based on their emotions. It also has a function to monitor stress levels and provide relaxation content as needed.

[1190] Program processing

[1191] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This starts the medical interview session.

[1192] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[1193] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[1194] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[1195] 5. The device sends the user's answer to the server, which analyzes the answer and uses an emotion engine to recognize the user's emotion.

[1196] Examples of emotion engines

[1197] For example, if a user answers "I have a stomachache," and the emotion engine recognizes from the user's tone of voice and facial expression that they are under high stress, the next question will be changed from "How bad is the pain?" to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[1198] 6. The server dynamically generates the next question data based on the user's emotions and sends it to the terminal. This question data takes into account the user's emotional state.

[1199] 7. The terminal analyzes the next question data received from the server and displays it to the user. The user then enters the answer to the next question.

[1200] 8. The user enters and submits an answer to the question. This process is repeated until all of the user's questions have been answered.

[1201] For example, if a user responds with "it hurts a lot," and the emotion engine recognizes this as high stress, the system will display a message to the user suggesting relaxation techniques and deep breathing.

[1202] 9. After all questions have been answered, the device displays a message to the user saying, "The interview is complete. Thank you for your hard work." At the same time, all answer data and sentiment analysis data are finally sent to the server.

[1203] 10. The server saves the final diagnosis data and notifies the doctor if necessary. The doctor can then provide an appropriate diagnosis and treatment based on the user's interview details and emotional data.

[1204] This system is particularly useful for emergency patients, as it allows for quick and accurate interviews without placing a burden on the user. Furthermore, by using an emotion engine, the system can take the user's emotional state into consideration during the interview, enabling more friendly and effective communication.

[1205] The processing flow will be explained below.

[1206] Step 1:

[1207] The user presses the inquiry start button on the terminal to start the inquiry.

[1208] Specific action: Touch a button on the screen of a tablet or smartphone.

[1209] Step 2:

[1210] The terminal receives the user's request and sends a request to start an interview to the server.

[1211] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[1212] Step 3:

[1213] The server receives the request to start the medical interview and generates the initial question data.

[1214] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[1215] Step 4:

[1216] The server returns the generated initial question data to the terminal.

[1217] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[1218] Step 5:

[1219] The terminal analyzes the initial question data received from the server and displays it to the user.

[1220] Specific operation: Parse the JSON data and display the question text on the screen.

[1221] Step 6:

[1222] The user enters an answer to the initial question.

[1223] Specific actions: Enter text using the software keyboard and touch the send button.

[1224] Step 7:

[1225] The terminal sends the user's answer to the server.

[1226] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[1227] Step 8:

[1228] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[1229] Specific operation: Executes an algorithm to determine emotions based on voice tone, facial expressions, input speed and strength, etc.

[1230] Step 9:

[1231] The server dynamically generates the next question data based on the user's emotions and sends it to the terminal.

[1232] Specific operation: The system uses a rules engine to select the appropriate next question, embeds expressions that take into account the user's emotional state in the question template, and generates a JSON-formatted response.

[1233] Step 10:

[1234] The terminal analyzes the next question data received from the server and displays it to the user.

[1235] Specific operation: Analyzes the JSON data and displays the next question text on the screen, reflecting the emotional state.

[1236] Step 11:

[1237] The user answers the following questions and submits.

[1238] Specific actions: Enter text using the software keyboard and touch the send button.

[1239] Step 12:

[1240] The terminal sends the user's answer to the server, which generates the next question.

[1241] Specific operation: The answer data is converted into JSON format and sent to the server via an HTTP request. The server again uses the emotion engine to recognize the user's emotion and the rule engine to select the next question.

[1242] Step 13:

[1243] Repeat steps 8 through 12 until all necessary questions have been asked.

[1244] Specific operation: User inputs answer, sends it to the server, recognizes emotion, and generates and displays the next question, repeating this process.

[1245] Step 14:

[1246] After all questions have been answered, the terminal displays a message to the user indicating that the interview is complete.

[1247] Specific action: Display the text "The medical interview has been completed. Thank you for your hard work" on the screen.

[1248] Step 15:

[1249] The device finally transmits all response data and sentiment analysis data to the server.

[1250] Specific operation: The answer data and sentiment analysis data for all questions are converted into JSON format and sent to the server via an HTTP request.

[1251] Step 16:

[1252] The server stores the final diagnosis data and notifies the doctor if necessary.

[1253] Specific behavior: Stores the user's response history and emotion data in a database and triggers notifications to doctors, including sending emails and updating the management interface.

[1254] This series of processes allows the user to proceed with the medical interview in a friendly dialogue format that takes into account the user's emotional state, making it possible to collect information quickly and accurately, especially for emergency patients.

[1255] Example 2

[1256] 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."

[1257] Conventional medical interview systems have problems in that they ask questions without considering the user's emotions, which can cause stress to the user or prevent them from obtaining appropriate information. This can increase the user's psychological burden, especially in emergencies, making it difficult to conduct an accurate medical interview. Furthermore, because the system does not consider the user's emotional state, it is insufficient to provide relaxation methods or appropriate responses to the user.

[1258] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1259] In this invention, the server includes means for analyzing the user's answers, recognizing emotions using a sentiment analysis engine, and generating next question data, means for providing relaxation content according to the user's emotional state, and means for saving the user's answer data and sentiment analysis data and notifying the doctor as necessary. This allows for a friendly and effective medical interview to be conducted while taking the user's emotions into consideration, reducing the user's psychological burden and enabling more accurate information to be collected.

[1260] "User" refers to an individual who uses the system to take a medical interview.

[1261] "Device" refers to the hardware device (e.g., smartphone, tablet, PC) used by the user to complete the interview.

[1262] A "medical interview start button" is an interface element that is displayed on a terminal to allow a user to start a medical interview session.

[1263] A "request" refers to the data format used to send operations and input data that a user performs on a system to a server.

[1264] A "server" is a central control system that receives requests and processes or generates data.

[1265] The "initial question data" is data that is generated by the server when a medical interview session is started and includes the content of the question that is first presented to the user.

[1266] An "emotion analysis engine" is software or algorithms that analyze a user's responses, tone of voice, facial expressions, etc. to recognize the user's emotional state.

[1267] The "next question data" is data that is dynamically generated by the server based on the user's answer and emotional state, and includes the content of the question to be presented to the user next.

[1268] "Relaxation content" refers to information and suggestions to reduce the user's psychological burden that are provided when the user's emotional state, particularly a high-stress state, is recognized.

[1269] "Emotion analysis data" refers to data regarding a user's emotional state obtained by an emotion analysis engine.

[1270] "Final diagnostic data" refers to final diagnostic information including user response data and emotion analysis data collected throughout the entire interview process.

[1271] The present invention relates to a system that conducts an interview in an interactive format while recognizing the user's emotions. In this system, the user uses a terminal to conduct an interview, and the server dynamically generates the next question based on the user's answers. Furthermore, the system incorporates a sentiment analysis engine and has the function of dynamically changing the way questions are phrased based on the user's emotions. It also has the function of monitoring the user's stress level and providing relaxation content as needed.

[1272] Hardware and software used

[1273] Hardware

[1274] Device (e.g. smartphone, tablet, PC)

[1275] Server (e.g. cloud server, on-premise server)

[1276] software

[1277] Interaction Management Applications

[1278] Sentiment analysis engines (e.g., IBM Watson, Microsoft Azure Emotion API)

[1279] Overview of program processing

[1280] The system operates in the following steps:

[1281] 1. The user presses the start button on the device to start the medical interview session.

[1282] 2. The device sends the user's request to the server, and the server generates the initial question data and sends it to the device.

[1283] 3. The server generates the initial question data, and the device displays the received question to the user.

[1284] 4. The user enters the answer to the question, and the device sends the answer to the server.

[1285] 5. The server analyzes the user's answers and uses a sentiment analysis engine to recognize the user's emotions.

[1286] 6. The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[1287] 7. The terminal analyzes the next question data and displays it to the user.

[1288] 8. The user answers the next question and this process is repeated until all of the user's questions have been answered.

[1289] 9. After all questions have been completed, the device will display the message "The medical interview is complete. Thank you for your hard work." and send all response data and emotion analysis data to the server.

[1290] 10. The server stores the final diagnosis data and notifies the doctor if necessary.

[1291] Specific examples

[1292] For example, if a user answers "I have a stomachache," the emotion analysis engine will recognize from the user's tone of voice and facial expression that they are under high stress. In this case, the next question will be changed from "Please tell me the level of pain," to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[1293] Example prompts to input to the generative AI model

[1294] "When the user answers 'My stomach hurts', generate the next question taking into account their emotions."

[1295] This system provides a fast and accurate interview process while minimizing the psychological burden on the user. In addition, by incorporating a sentiment analysis engine, it realizes friendly and effective communication while taking into account the user's emotions, making it particularly useful in emergencies and high-stress situations.

[1296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1297] Step 1:

[1298] The user presses the inquiry start button on the terminal to start the inquiry session.

[1299] Specific operation: The user taps the "Start medical interview" button displayed on the smartphone screen. As input, a medical interview start request is generated. As output, an event indicating that the medical interview session has started is generated.

[1300] Step 2:

[1301] The terminal generates a request to start an interview and sends it to the server.

[1302] Specific operation: The terminal generates a medical interview start request including the user ID and the current date and time, and sends it to the server via the Internet. The input is the user's tap event, and the output is the transmission of the medical interview start request.

[1303] Step 3:

[1304] The server receives the request to start the medical interview and generates the initial question data.

[1305] Specific operation: The server generates data including a question such as "Where does it hurt?" as the first question. The input is a request to start the medical interview, and the output is the first question data.

[1306] Step 4:

[1307] The server sends the initial question data to the terminal.

[1308] Specific operation: The process of sending query data generated by the server to the terminal. The input is the initial query data, and the output is sending the data to the terminal.

[1309] Step 5:

[1310] The terminal receives the initial question data and displays it to the user.

[1311] Specific operation: The terminal displays the initial question data received from the server on the screen. The input is the received question data, and the output is what is displayed to the user.

[1312] Step 6:

[1313] The user enters an answer to the question, and the terminal sends the answer to the server.

[1314] Specific operation: The user enters an answer in the text box and clicks the send button. The terminal sends this answer data to the server. The input is the user's answer data, and the output is the transmission of the answer data.

[1315] Step 7:

[1316] The server analyzes the user's responses and uses a sentiment analysis engine to recognize the user's emotions.

[1317] Specific operation: The server applies an analysis algorithm to analyze the user's response data, voice tone, and facial expressions. The input is the user's response data, and the output is the emotion analysis result.

[1318] Step 8:

[1319] The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[1320] Specific operation: The server generates the next question data taking into account the user's emotional state and sends it to the device. For example, instead of a general question such as "Please tell me the level of pain," it generates a friendly question such as "It sounds like you're in a lot of pain. How bad is it?" The input is the emotion analysis result, and the output is the next question data.

[1321] Step 9:

[1322] The terminal analyzes the next question data and displays it to the user.

[1323] Specific operation: The terminal displays the next question data it has received. The input is the next question data, and the output is what is displayed to the user.

[1324] Step 10:

[1325] The user answers the next question and the process repeats until all of the user's questions have been answered.

[1326] Specific operation: The user enters an answer to the next question and submits it. This process is repeated. The input is the questions that are generated one after another and the user's answer data to those questions, and the output is the final accumulation of answer data.

[1327] Step 11:

[1328] After all questions have been completed, the device displays the message "The medical interview is complete. Thank you for your hard work." and sends all response data and emotion analysis data to the server.

[1329] Specific operation: When the user answers the last question, the terminal displays a completion message and sends all data to the server. The input is the final answer data, and the output is the display of the completion message and the sending of data.

[1330] Step 12:

[1331] The server stores the final diagnosis data and notifies the doctor if necessary.

[1332] Specific operation: The server stores all received data and sends alerts to doctors via email or notification systems (e.g., Slack, Teams, etc.). The input is the submitted response data and sentiment analysis data, and the output is the storage of the final diagnosis data and notification to the doctor.

[1333] (Application example 2)

[1334] 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."

[1335] Current factory environments lack systems that can properly recognize workers' emotions and stress levels and provide feedback and relaxation suggestions based on that information. This can have a negative impact on work efficiency and workers' mental health. It is necessary to accurately grasp workers' emotional states and provide appropriate follow-up when checking the progress of work and adjusting tasks on-site. Currently, there are no means to solve these issues, and improvements to the work environment are stalled.

[1336] 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.

[1337] In this invention, the server includes means for recognizing the user's emotions using an emotion engine, means for dynamically generating the next question data based on the emotion and sending it to the terminal, and means for the emotion engine to monitor the user's stress level and suggest relaxation methods as necessary. This makes it possible to accurately grasp the emotions and stress levels of workers and provide appropriate feedback and suggestions in real time.

[1338] "User" refers to a person who uses the system.

[1339] "Medical interview" refers to the process of gathering information by asking questions about a user's health status and symptoms.

[1340] A "request" refers to data or a request that a user sends to a server.

[1341] "Server" means a computer system that processes user requests and generates and transmits query data and other information.

[1342] "Initial question data" refers to information about the first question that the server presents to the user at the start of the medical interview.

[1343] "Terminal" means a device operated by a user to exchange information with a server.

[1344] An "emotion engine" refers to a system that analyzes a user's emotional state from their responses, voice, facial expressions, etc.

[1345] "Emotion" indicates the user's psychological and sensory state and is recognized by the system.

[1346] The "stress level" is an index that indicates the degree of stress that the user is feeling.

[1347] "Relaxation methods" refer to methods and suggestions for reducing stress and relaxing the user.

[1348] "Dynamic generation" means that new questions are generated in real time based on the user's answers and emotional state.

[1349] "Feedback" refers to the information or suggestions that the system returns in response to the user's answers.

[1350] "Diagnostic data" refers to data including the results of a user's medical interview and emotion analysis.

[1351] The system for realizing this invention is a combination of a server, a terminal, an emotion engine, and a relaxation suggestion engine. A specific description of this system is given below.

[1352] System Overview

[1353] The system works in a factory environment by connecting with devices used by workers to recognize their emotions and stress levels and provide feedback in real time.

[1354] Hardware and software used

[1355] Terminal: A device operated by a worker, such as a smartphone, tablet, or smart glasses.

[1356] Server: A computer system that processes various requests and analyzes and stores data. Often uses cloud services such as Amazon Web Services (AWS).

[1357] Emotion engine: Software that analyzes emotional states. Examples include Google Cloud's Emotion Analysis API and Microsoft Azure's Emotion Recognition API.

[1358] Relaxation suggestion engine: A software module that suggests relaxation methods based on stress levels.

[1359] Processing flow

[1360] 1. The user operates the terminal and starts a medical interview session with this system.

[1361] 2. The device receives the user's input and sends the request to the server.

[1362] 3. The server generates the initial question data and sends it to the terminal.

[1363] 4. The device displays the question to the user, and the user enters the answer.

[1364] 5. The device sends the user's answer to the server.

[1365] 6. The server analyzes the user's answers and uses an emotion engine to recognize the user's emotions.

[1366] 7. The server dynamically generates the next question data based on the recognized emotion and sends it to the device.

[1367] 8. The terminal displays the next question to the user, and the user enters the answer. This process is repeated until all necessary questions have been answered.

[1368] 9. The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[1369] 10. After all questions are completed, the device will display a message indicating the session is over and all data will be saved on the server.

[1370] Specific use cases

[1371] For example, if a worker answers, "I'm working long hours today," the emotion engine will interpret the answer as "stress." The next question will then be, "That's tough. Shall we take a short break? Take a deep breath and relax," and the relaxation suggestion engine will be activated.

[1372] Prompt Sentence Examples

[1373] "You've been working long hours today. It's tough. Let's take a break. Take a deep breath and relax."

[1374] This system makes it possible to accurately grasp the emotional state of workers and provide appropriate feedback and suggestions for stress reduction.

[1375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1376] Step 1:

[1377] The user operates the terminal and presses the inquiry start button to start the inquiry session.

[1378] Input: User initiates interview.

[1379] Output: The terminal generates a request to start an interview and sends it to the server.

[1380] Step 2:

[1381] The terminal receives the user's request to start the medical interview and transmits this information to the server.

[1382] Input: The request to start the interview sent by the user using the terminal.

[1383] Output: Received by the server as a trigger to generate the initial question data.

[1384] Step 3:

[1385] The server generates the initial question data and sends it to the terminal.

[1386] Input: A request to start an interview from the terminal.

[1387] Data processing: The server selects the first question of the medical interview based on the request to start the medical interview.

[1388] Output: Sends the initial question data to the terminal.

[1389] Step 4:

[1390] The terminal displays the question received from the server to the user.

[1391] Input: The initial question data sent by the server.

[1392] Output: The initial question is displayed on the terminal screen.

[1393] Step 5:

[1394] The user enters an answer to the question.

[1395] Input: The user's answer to the question displayed on the terminal.

[1396] Output: The device prepares the response data to send to the server.

[1397] Step 6:

[1398] The terminal sends the user's answer to the server.

[1399] Input: The answer data entered by the user.

[1400] Output: Send the answer data to the server.

[1401] Step 7:

[1402] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[1403] Input: User response data sent from the device.

[1404] Data calculation: The emotion engine analyzes voice tone and facial expressions based on response data to determine emotional state.

[1405] Output: Recognized emotion data.

[1406] Step 8:

[1407] The server dynamically generates the next question data based on the recognized emotion and sends it to the terminal.

[1408] Input: Recognized emotion data and previous response data.

[1409] Data processing: Dynamically generate new question content and expressions taking into account emotional data.

[1410] Output: Send the next question data to the terminal.

[1411] Step 9:

[1412] The terminal displays the next question to the user, and the user enters an answer to the next question. This process is repeated until all necessary questions have been answered.

[1413] Input: Next question data sent from the server.

[1414] Output: The following question will be displayed on the terminal screen:

[1415] Step 10:

[1416] The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[1417] Input: User response data and sentiment data.

[1418] Data calculation: Evaluate stress levels and recommend relaxation methods if necessary.

[1419] Output: Send relaxation suggestion data to device.

[1420] Step 11:

[1421] After all questions are completed, the terminal will display a message stating the end of the session and all data will be saved on the server.

[1422] Input: Completed response data and sentiment analysis data.

[1423] Data processing: Organize and store data on the server.

[1424] Output: Session termination message and saved data.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] [Fourth embodiment]

[1429] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1430] 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.

[1431] 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).

[1432] 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.

[1433] 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.

[1434] 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).

[1435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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."

[1442] The present invention relates to a system that allows a user to proceed with a medical interview in an interactive format. The processing of the program of this system will be specifically explained below in natural language.

[1443] System Overview

[1444] In this system, the user conducts a medical interview using a device such as a tablet or smartphone, and the next question is dynamically generated from the server based on the answers. Finally, all the answer data is notified to the doctor.

[1445] Program processing

[1446] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This operation starts the medical interview session.

[1447] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[1448] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[1449] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[1450] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[1451] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[1452] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[1453] For example, if a user answers "I have a stomachache," the server dynamically generates a question such as "How bad is the pain? Mild, moderate, severe?" and displays it to the user.

[1454] 8. This iterative process continues until all necessary questions have been asked. At each step, the server analyzes the user's answers and dynamically generates appropriate questions.

[1455] 9. After all questions have been answered, the terminal displays a message to the user saying "Interview completed." At the same time, all answer data is finally sent to the server.

[1456] 10. The server saves the final diagnosis data and notifies the doctor if necessary, allowing the doctor to provide appropriate diagnosis and treatment based on the user's medical history.

[1457] This system is particularly useful for emergency patients, as it allows for quick and accurate medical interviews without placing a burden on the user.

[1458] The processing flow will be explained below.

[1459] Step 1:

[1460] The user presses the inquiry start button on the terminal to start the inquiry.

[1461] Specific action: Touch a button on the screen of a tablet or smartphone.

[1462] Step 2:

[1463] The terminal receives the user's request and sends a request to start an interview to the server.

[1464] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[1465] Step 3:

[1466] The server receives the request to start the medical interview and generates the initial question data.

[1467] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[1468] Step 4:

[1469] The server returns the generated initial question data to the terminal.

[1470] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[1471] Step 5:

[1472] The terminal analyzes the initial question data received from the server and displays it to the user.

[1473] Specific operation: Parse the JSON data and display the question text on the screen.

[1474] Step 6:

[1475] The user enters an answer to the initial question.

[1476] Specific actions: Enter text using the software keyboard and touch the send button.

[1477] Step 7:

[1478] The terminal sends the user's answer to the server.

[1479] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[1480] Step 8:

[1481] The server analyzes the user's answers and generates the next question data.

[1482] Specific behavior: Uses the rules engine to select the appropriate next question, fills in the answer content in a question template, and generates a JSON-formatted response.

[1483] Step 9:

[1484] The server generates the next question data and sends it to the terminal.

[1485] Specific operation: The following question data is sent in JSON format as an HTTP response.

[1486] Step 10:

[1487] The terminal analyzes the next question data received from the server and displays it to the user.

[1488] Specific behavior: Parse the JSON data and display the following question text on the screen.

[1489] Step 11:

[1490] Repeat steps 6 through 10 until all necessary questions have been asked.

[1491] Specific operation: Repeat the process of inputting a user answer, sending it to the server, and generating and displaying the next question.

[1492] Step 12:

[1493] The terminal confirms that all questions have been completed and displays a message to the user that the interview is complete.

[1494] Specific action: The text "Medical interview completed" is displayed on the screen.

[1495] Step 13:

[1496] The terminal finally transmits all response data to the server.

[1497] Specific operation: The answer data for all questions is converted into a list in JSON format and sent to the server via an HTTP request.

[1498] Step 14:

[1499] The server stores the final diagnosis data and notifies the doctor if necessary.

[1500] Specific actions: Saves the user's response history in a database and triggers notifications to the doctor, including sending emails and updating the admin interface.

[1501] Example 1

[1502] 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."

[1503] Conventional medical interview systems have the problem that it is difficult to dynamically generate the next question based on the user's answers, and only fixed questions can be displayed. Furthermore, as the user progresses through the medical interview, it is difficult to effectively exchange questions and answers, making it difficult for doctors to quickly and accurately obtain the information they need to make an appropriate diagnosis. This has led to problems, particularly in emergencies and for emergency patients, making it difficult to provide prompt and accurate responses.

[1504] 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.

[1505] In this invention, the server includes a means for analyzing the user's answers and generating the next question data, a means for dynamically generating the next question data using a generative AI model, and a means for saving the final diagnosis data and notifying the doctor as necessary. This enables dynamic question generation based on the user's answers, enabling the doctor to efficiently obtain information for a quick and accurate diagnosis.

[1506] "User" refers to an individual or patient who uses the system to conduct a medical interview.

[1507] The term "terminal device" refers to an electronic device, such as a tablet or smartphone, that a user uses to conduct a medical interview.

[1508] "Information processing device" refers to a central control device that functions as a server, receives user requests, and generates, analyzes, and stores data.

[1509] "Initial question data" refers to data including the content of the first question presented to the user at the start of the medical interview session.

[1510] "Next question data" refers to data that contains the question to be presented next, which is dynamically generated based on the user's answer.

[1511] A "generative AI model" refers to an artificial intelligence model (e.g., GPT-3) that generates the next best question based on user input.

[1512] "User answers" refers to the text or choices entered by the user for each question.

[1513] "Diagnostic data" refers to the final data provided by the server to the doctor based on all interview results.

[1514] "Notification means" refers to a communication means (e.g., email notification or message application) for transmitting final diagnosis data to a doctor.

[1515] This invention relates to a system that allows a user to proceed with an interview in an interactive format. The system aims to dynamically generate the next question based mainly on the user's input and provide the doctor with final diagnostic data.

[1516] Required Hardware and Software

[1517] Hardware:

[1518] Terminal devices such as tablets and smartphones

[1519] Information processing device (server)

[1520] software:

[1521] Frontend: Web application using HTML, CSS, and JavaScript

[1522] Backend: A server program using Python or Node.js

[1523] Database: MySQL or PostgreSQL

[1524] AI generative models, such as OpenAI's GPT-3

[1525] Program processing overview

[1526] Starting a Session

[1527] The user starts the medical interview using a terminal device such as a tablet or smartphone. At this time, the user presses a button to start the medical interview, which starts the session. For example, the user can start the process by pressing the "Start Medical Interview" button on a tablet while in a hospital waiting room.

[1528] First question generation and display

[1529] The terminal device receives the user's request and transmits this information to the information processing device. The information processing device processes this request, generates initial question data, and transmits it to the terminal device. The terminal device displays the received initial question data to the user, and the user inputs an answer in a specified field. For example, the initial question, "Where does it hurt?", is displayed.

[1530] Next question generation and iterative process

[1531] When the user enters an answer to a question and presses the send button, the answer data is sent again to the information processing device. The information processing device analyzes the user's answer and dynamically generates the next question data using a generative AI model (e.g., GPT-3). This process is repeated until all necessary questions have been completed. For example, in response to the answer "My stomach hurts," the next question generated is "How bad is the pain?"

[1532] Final diagnostic data storage and notification

[1533] After all questions have been answered, the terminal device displays a message to the user saying "The medical interview is complete." At the same time, all answer data is finally sent to the information processing device. The information processing device saves the final diagnosis data and notifies the doctor if necessary. This allows the doctor to obtain information necessary for a quick and accurate diagnosis.

[1534] Prompt Sentence Examples

[1535] Below are some example prompts to input to a generative AI model:

[1536] User input: "My stomach hurts"

[1537] Prompt to input to the generative AI model:

[1538] "If the user says 'I have a stomach ache,' generate the next appropriate question."

[1539] Based on this prompt, the generative AI model generates appropriate questions such as "How bad is your pain?" Applying this method makes it possible to realize flexible medical interviews based on the user's answers. This system provides effective and efficient medical interviews, enabling rapid response, especially in emergency situations and for emergency patients.

[1540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1541] Step 1:

[1542] The user presses the medical interview start button. This operation starts the medical interview session. The input is the user's operation, and the output is the generation of a medical interview start request by the terminal. A specific operation is when the user clicks the "medical interview start" button on a tablet or smartphone. In response to this operation, the terminal sends a request including metadata such as the user ID and session ID to the information processing device.

[1543] Step 2:

[1544] The terminal receives the user's request and sends it to the information processing device. The input is the user's request, and the output is the transmission of request data from the terminal to the information processing device. Specifically, JavaScript on the terminal catches the user's operation and sends a medical interview start request in JSON format to the information processing device.

[1545] Step 3:

[1546] The server receives a request to start the medical interview, generates the initial question data, and sends it to the terminal. The input is the request data received from the terminal, and the output is the initial question data. A Python script on the server receives the request, queries the database to obtain the "initial question," and returns it to the terminal in JSON format.

[1547] Step 4:

[1548] The device displays the initial question data it receives to the user. The input is the question data from the server, and the output is the question displayed to the user. Specifically, JavaScript parses the JSON data returned from the server, generates HTML elements, and displays the initial question, such as "Where does it hurt?", to the user.

[1549] Step 5:

[1550] The user inputs an answer to the question and presses the send button. The input is the user's answer, and the output is the transmission of the answer data from the terminal to the server. As a specific example, the user inputs "My stomach hurts" and presses the send button. This operation sends the answer data from the terminal to the server.

[1551] Step 6:

[1552] The server receives the user's answer and analyzes it. The input is the user's answer data, and the output is the generation of the next question data. Specifically, the server's Python script receives the answer data, inputs it as a prompt to the generative AI model (e.g., GPT-3), and generates the next question. An example of a prompt sentence is, "If the user says, 'My stomach hurts,' please generate the next appropriate question."

[1553] Step 7:

[1554] The server generates the next question and sends it to the terminal. The input is the next question data from the generative AI model, and the output is data sent to the terminal. The server sends the generated question to the terminal in JSON format.

[1555] Step 8:

[1556] The terminal displays the next question to the user. This process is repeated until the user has answered all questions. The input is the next question data from the server, and the output is the question displayed to the user. In concrete terms, JavaScript displays the next question, and the user enters the answer again.

[1557] Step 9:

[1558] After all questions have been asked, the terminal displays a message to the user saying "The medical interview has been completed." The input is the fact that all questions have been asked, and the output is the display of a completion message to the user. Specifically, the message "The medical interview has been completed. Thank you." is displayed on the screen.

[1559] Step 10:

[1560] The server saves the final diagnosis data and notifies the doctor. The input is all response data, and the output is saving and notifying the final diagnosis data. Specifically, the server saves all response data in a database and notifies the doctor via email or a notification system as needed.

[1561] This enables dynamic question generation based on the user's answers, enabling doctors to efficiently obtain information that allows them to make prompt and accurate diagnoses.

[1562] (Application example 1)

[1563] 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."

[1564] Conventional food delivery systems have the drawback of requiring users to select menu items and specify customization options, resulting in complex and inefficient operations. This has led to low user satisfaction and a lengthy ordering process. In particular, when users are unsure of their choices and ordering options, it can take a lot of effort to complete the order.

[1565] 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.

[1566] In this invention, the server includes a means for the user to start an order, a means for transmitting the user's request to the server, and a means for the server to generate initial question data and transmit it to the terminal, thereby enabling the user to smoothly select and customize menus interactively.

[1567] "User" refers to the person utilizing the system who initiates and progresses the ordering process.

[1568] "Means for initiating an order" refers to the operation or interface that allows a user to start the ordering process in the delivery system.

[1569] "Means for sending a request to a server" refers to a communication means for sending initial information or a request to a server based on a user's operation.

[1570] The "means for generating initial question data and transmitting it to the terminal" refers to a process by which the server generates a question to be presented to the user initially and transmits it to the user's terminal.

[1571] The "means for displaying to the user the question received by the terminal from the server" refers to a function for visually showing to the user the question received by the user's terminal from the server.

[1572] "Means for a user to input an answer to a question" refers to a function that allows a user to input an answer to a question from a server using a terminal.

[1573] "Means for transmitting the user's answer to the server" refers to a communication means for transmitting the answer entered by the user to the server.

[1574] "Means for the server to analyze the user's answer and generate the next question data" refers to the analysis and generation function that enables the server to automatically generate the next question based on the user's answer.

[1575] "Means for displaying the next question received by the terminal from the server to the user" refers to a function for the user's terminal to receive questions that are generated one after another and display them to the user.

[1576] "Means for generating and displaying the next question through an iterative process" refers to a system for continuously generating and displaying questions based on the user's answers.

[1577] "Means for finally transmitting answer data for all questions to the server when an order is completed" refers to means for finally transmitting answer data for all questions to the server when a user's order is completed.

[1578] "Means for the server to save the final order data and notify the service provider as necessary" refers to the function that enables the server to save all order data and notify the delivery service provider of that information as necessary.

[1579] The present invention relates to a food delivery system that allows users to interactively place orders. A specific implementation of this system will be described below.

[1580] System Overview:

[1581] In this system, users place food delivery orders using devices such as smartphones or tablets, and the server dynamically generates the next questions based on the answers. All answer data is finally sent to the service provider.

[1582] Hardware and software used:

[1583] Hardware: Smartphones, tablets

[1584] Software: Flask (a Python microframework), server (NGINX, Apache, etc. can be used)

[1585] Data processing and calculation:

[1586] 1. To begin an order, the user presses the Start Order button on the terminal. This action starts an ordering session.

[1587] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[1588] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[1589] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[1590] 5. The user enters the answer to the question and presses the send button, which sends the user's answer from the device to the server.

[1591] 6. The server analyzes the user's answers and dynamically generates the next question based on them, a process that is based on algorithms and rules engines configured on the server side.

[1592] 7. The server generates the next question and sends it to the terminal. The terminal displays the question data to the user and prompts the user to enter the answer again.

[1593] This iterative process continues until all necessary questions have been asked, with the server analyzing the user's answers at each step and dynamically generating appropriate questions.

[1594] Specific examples of behavior:

[1595] When a user initiates an order, the following interaction takes place:

[1596] Example prompt sentence:

[1597] 1. "Let's start ordering. What would you like? Pizza, burger, or salad?"

[1598] 2. The user answers "pizza"

[1599] 3. "Choose your pizza size: small, medium, or large?"

[1600] 4. The user answers "medium"

[1601] 5. "What toppings would you like to add to your medium pizza? Cheese, bacon?"

[1602] In this way, the user answers questions one by one, and when all information has been provided, the order data is sent to the server and, if necessary, notified to the service provider.

[1603] This system allows users to efficiently and intuitively navigate the food delivery ordering process.

[1604] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1605] Step 1:

[1606] The user presses the order start button.

[1607] Input: User operation (pressing the order start button)

[1608] Output: Order session start request

[1609] Specific operation: When the user presses the order start button on the terminal, the terminal sends the user's request to the server, which starts the order.

[1610] Step 2:

[1611] The terminal receives the user's request and sends it to the server.

[1612] Input: User action (request to start an order)

[1613] Output: Initial question generation request

[1614] Specific operation: The terminal sends the user's request to the server, and the server begins preparations to generate the first question.

[1615] Step 3:

[1616] The server generates the initial question data and sends it to the terminal.

[1617] Input: Initial question generation request

[1618] Output: First question data

[1619] Specific operation: The server generates a question about the menu that the user should first choose (e.g., what would you like to order?) and sends that data to the terminal.

[1620] Step 4:

[1621] The terminal displays the question received from the server to the user.

[1622] Input: First question data

[1623] Output: The question displayed to the user

[1624] Specific operation: The terminal displays the initial question received from the server to the user and provides an interface for the user to input an answer.

[1625] Step 5:

[1626] The user enters an answer to the question, and the terminal sends the answer to the server.

[1627] Input: User's answer

[1628] Output: User's request to send an answer

[1629] Specific operation: The user enters an answer to the question displayed on the terminal and presses the send button. The terminal then sends the answer to the server.

[1630] Step 6:

[1631] The server analyzes the user's answers and generates the next question data.

[1632] Input: User's answer

[1633] Output: Next question data

[1634] Specific operation: The server analyzes the user's answer and generates the next appropriate question. For example, if the answer is "pizza," the next question generated is "Please choose the size of pizza."

[1635] Step 7:

[1636] The server generates the next question and sends it to the terminal, which displays it to the user.

[1637] Input: Next question data

[1638] Output: The next question displayed on the user's screen

[1639] Specific operation: The server generates the next question and sends it to the terminal, which displays it to the user. The user then enters the answer again.

[1640] Step 8:

[1641] Repeat this process until all necessary questions have been answered.

[1642] Input: Repeat previous step

[1643] Output: Final response data

[1644] Specific behavior: Continue this cycle of questions and answers until the user has answered all questions.

[1645] Step 9:

[1646] When the order is completed, the terminal finally transmits the answer data for all questions to the server.

[1647] Input: Answers to all questions

[1648] Output: Final order data transmission request

[1649] Specific operation: When the user inputs the final answer and presses the send button, the terminal finally sends all the answer data to the server.

[1650] Step 10:

[1651] The server stores the final order data and notifies the service provider if necessary.

[1652] Input: Final order data

[1653] Output: Stored order data and notifications

[1654] Specific operation: The server stores the final order data and notifies the delivery service provider of that data as necessary.

[1655] 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.

[1656] The present invention relates to a system that can conduct a dialogue-style medical interview while recognizing the user's emotions. The program processing of this system will be specifically explained below in natural language.

[1657] System Overview

[1658] This system allows users to use a terminal to answer questions, and the server dynamically generates the next questions based on the user's answers. It also incorporates an emotion engine that recognizes the user's emotions and dynamically changes the way questions are phrased based on their emotions. It also has a function to monitor stress levels and provide relaxation content as needed.

[1659] Program processing

[1660] 1. To start the medical interview, the user presses the medical interview start button on the terminal. This starts the medical interview session.

[1661] 2. The device receives the user's request and sends this information to the server, which processes the request and generates the initial question data.

[1662] 3. The server generates the initial question data and sends it to the terminal. The initial question data contains the initial question to the user.

[1663] 4. The terminal receives the initial question data and displays the question to the user, who then enters the answer in the designated field.

[1664] 5. The device sends the user's answer to the server, which analyzes the answer and uses an emotion engine to recognize the user's emotion.

[1665] Examples of emotion engines

[1666] For example, if a user answers "I have a stomachache," and the emotion engine recognizes from the user's tone of voice and facial expression that they are under high stress, the next question will be changed from "How bad is the pain?" to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[1667] 6. The server dynamically generates the next question data based on the user's emotions and sends it to the terminal. This question data takes into account the user's emotional state.

[1668] 7. The terminal analyzes the next question data received from the server and displays it to the user. The user then enters the answer to the next question.

[1669] 8. The user enters and submits an answer to the question. This process is repeated until all of the user's questions have been answered.

[1670] For example, if a user responds with "it hurts a lot," and the emotion engine recognizes this as high stress, the system will display a message to the user suggesting relaxation techniques and deep breathing.

[1671] 9. After all questions have been answered, the device displays a message to the user saying, "The interview is complete. Thank you for your hard work." At the same time, all answer data and sentiment analysis data are finally sent to the server.

[1672] 10. The server saves the final diagnosis data and notifies the doctor if necessary. The doctor can then provide an appropriate diagnosis and treatment based on the user's interview details and emotional data.

[1673] This system is particularly useful for emergency patients, as it allows for quick and accurate interviews without placing a burden on the user. Furthermore, by using an emotion engine, the system can take the user's emotional state into consideration during the interview, enabling more friendly and effective communication.

[1674] The processing flow will be explained below.

[1675] Step 1:

[1676] The user presses the inquiry start button on the terminal to start the inquiry.

[1677] Specific action: Touch a button on the screen of a tablet or smartphone.

[1678] Step 2:

[1679] The terminal receives the user's request and sends a request to start an interview to the server.

[1680] Specific operation: An HTTP request is sent to the server. This request includes the user ID and session information.

[1681] Step 3:

[1682] The server receives the request to start the medical interview and generates the initial question data.

[1683] Specific operation: Reads the initial question template from the database and generates the question text as a JSON format response.

[1684] Step 4:

[1685] The server returns the generated initial question data to the terminal.

[1686] Specific operation: The initial question data is sent in JSON format as an HTTP response.

[1687] Step 5:

[1688] The terminal analyzes the initial question data received from the server and displays it to the user.

[1689] Specific operation: Parse the JSON data and display the question text on the screen.

[1690] Step 6:

[1691] The user enters an answer to the initial question.

[1692] Specific actions: Enter text using the software keyboard and touch the send button.

[1693] Step 7:

[1694] The terminal sends the user's answer to the server.

[1695] Specific operation: Converts user input data into JSON format and sends it to the server via an HTTP request.

[1696] Step 8:

[1697] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[1698] Specific operation: Executes an algorithm to determine emotions based on voice tone, facial expressions, input speed and strength, etc.

[1699] Step 9:

[1700] The server dynamically generates the next question data based on the user's emotions and sends it to the terminal.

[1701] Specific operation: The system uses a rules engine to select the appropriate next question, embeds expressions that take into account the user's emotional state in the question template, and generates a JSON-formatted response.

[1702] Step 10:

[1703] The terminal analyzes the next question data received from the server and displays it to the user.

[1704] Specific operation: Analyzes the JSON data and displays the next question text on the screen, reflecting the emotional state.

[1705] Step 11:

[1706] The user answers the following questions and submits.

[1707] Specific actions: Enter text using the software keyboard and touch the send button.

[1708] Step 12:

[1709] The terminal sends the user's answer to the server, which generates the next question.

[1710] Specific operation: The answer data is converted into JSON format and sent to the server via an HTTP request. The server again uses the emotion engine to recognize the user's emotion and the rule engine to select the next question.

[1711] Step 13:

[1712] Repeat steps 8 through 12 until all necessary questions have been asked.

[1713] Specific operation: User inputs answer, sends it to the server, recognizes emotion, and generates and displays the next question, repeating this process.

[1714] Step 14:

[1715] After all questions have been answered, the terminal displays a message to the user indicating that the interview is complete.

[1716] Specific action: Display the text "The medical interview has been completed. Thank you for your hard work" on the screen.

[1717] Step 15:

[1718] The device finally transmits all response data and sentiment analysis data to the server.

[1719] Specific operation: The answer data and sentiment analysis data for all questions are converted into JSON format and sent to the server via an HTTP request.

[1720] Step 16:

[1721] The server stores the final diagnosis data and notifies the doctor if necessary.

[1722] Specific behavior: Stores the user's response history and emotion data in a database and triggers notifications to doctors, including sending emails and updating the management interface.

[1723] This series of processes allows the user to proceed with the medical interview in a friendly dialogue format that takes into account the user's emotional state, making it possible to collect information quickly and accurately, especially for emergency patients.

[1724] Example 2

[1725] 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."

[1726] Conventional medical interview systems have problems in that they ask questions without considering the user's emotions, which can cause stress to the user or prevent them from obtaining appropriate information. This can increase the user's psychological burden, especially in emergencies, making it difficult to conduct an accurate medical interview. Furthermore, because the system does not consider the user's emotional state, it is insufficient to provide relaxation methods or appropriate responses to the user.

[1727] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1728] In this invention, the server includes means for analyzing the user's answers, recognizing emotions using a sentiment analysis engine, and generating next question data, means for providing relaxation content according to the user's emotional state, and means for saving the user's answer data and sentiment analysis data and notifying the doctor as necessary. This allows for a friendly and effective medical interview to be conducted while taking the user's emotions into consideration, reducing the user's psychological burden and enabling more accurate information to be collected.

[1729] "User" refers to an individual who uses the system to take a medical interview.

[1730] "Device" refers to the hardware device (e.g., smartphone, tablet, PC) used by the user to complete the interview.

[1731] A "medical interview start button" is an interface element that is displayed on a terminal to allow a user to start a medical interview session.

[1732] A "request" refers to the data format used to send operations and input data that a user performs on a system to a server.

[1733] A "server" is a central control system that receives requests and processes or generates data.

[1734] The "initial question data" is data that is generated by the server when a medical interview session is started and includes the content of the question that is first presented to the user.

[1735] An "emotion analysis engine" is software or algorithms that analyze a user's responses, tone of voice, facial expressions, etc. to recognize the user's emotional state.

[1736] The "next question data" is data that is dynamically generated by the server based on the user's answer and emotional state, and includes the content of the question to be presented to the user next.

[1737] "Relaxation content" refers to information and suggestions to reduce the user's psychological burden that are provided when the user's emotional state, particularly a high-stress state, is recognized.

[1738] "Emotion analysis data" refers to data regarding a user's emotional state obtained by an emotion analysis engine.

[1739] "Final diagnostic data" refers to final diagnostic information including user response data and emotion analysis data collected throughout the entire interview process.

[1740] The present invention relates to a system that conducts an interview in an interactive format while recognizing the user's emotions. In this system, the user uses a terminal to conduct an interview, and the server dynamically generates the next question based on the user's answers. Furthermore, the system incorporates a sentiment analysis engine and has the function of dynamically changing the way questions are phrased based on the user's emotions. It also has the function of monitoring the user's stress level and providing relaxation content as needed.

[1741] Hardware and software used

[1742] Hardware

[1743] Device (e.g. smartphone, tablet, PC)

[1744] Server (e.g. cloud server, on-premise server)

[1745] software

[1746] Interaction Management Applications

[1747] Sentiment analysis engines (e.g., IBM Watson, Microsoft Azure Emotion API)

[1748] Overview of program processing

[1749] The system operates in the following steps:

[1750] 1. The user presses the start button on the device to start the medical interview session.

[1751] 2. The device sends the user's request to the server, and the server generates the initial question data and sends it to the device.

[1752] 3. The server generates the initial question data, and the device displays the received question to the user.

[1753] 4. The user enters the answer to the question, and the device sends the answer to the server.

[1754] 5. The server analyzes the user's answers and uses a sentiment analysis engine to recognize the user's emotions.

[1755] 6. The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[1756] 7. The terminal analyzes the next question data and displays it to the user.

[1757] 8. The user answers the next question and this process is repeated until all of the user's questions have been answered.

[1758] 9. After all questions have been completed, the device will display the message "The medical interview is complete. Thank you for your hard work." and send all response data and emotion analysis data to the server.

[1759] 10. The server stores the final diagnosis data and notifies the doctor if necessary.

[1760] Specific examples

[1761] For example, if a user answers "I have a stomachache," the emotion analysis engine will recognize from the user's tone of voice and facial expression that they are under high stress. In this case, the next question will be changed from "Please tell me the level of pain," to a more friendly phrase such as "It sounds like the pain is severe and painful. How bad is it?"

[1762] Example prompts to input to the generative AI model

[1763] "When the user answers 'My stomach hurts', generate the next question taking into account their emotions."

[1764] This system provides a fast and accurate interview process while minimizing the psychological burden on the user. In addition, by incorporating a sentiment analysis engine, it realizes friendly and effective communication while taking into account the user's emotions, making it particularly useful in emergencies and high-stress situations.

[1765] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1766] Step 1:

[1767] The user presses the inquiry start button on the terminal to start the inquiry session.

[1768] Specific operation: The user taps the "Start medical interview" button displayed on the smartphone screen. As input, a medical interview start request is generated. As output, an event indicating that the medical interview session has started is generated.

[1769] Step 2:

[1770] The terminal generates a request to start an interview and sends it to the server.

[1771] Specific operation: The terminal generates a medical interview start request including the user ID and the current date and time, and sends it to the server via the Internet. The input is the user's tap event, and the output is the transmission of the medical interview start request.

[1772] Step 3:

[1773] The server receives the request to start the medical interview and generates the initial question data.

[1774] Specific operation: The server generates data including a question such as "Where does it hurt?" as the first question. The input is a request to start the medical interview, and the output is the first question data.

[1775] Step 4:

[1776] The server sends the initial question data to the terminal.

[1777] Specific operation: The process of sending query data generated by the server to the terminal. The input is the initial query data, and the output is sending the data to the terminal.

[1778] Step 5:

[1779] The terminal receives the initial question data and displays it to the user.

[1780] Specific operation: The terminal displays the initial question data received from the server on the screen. The input is the received question data, and the output is what is displayed to the user.

[1781] Step 6:

[1782] The user enters an answer to the question, and the terminal sends the answer to the server.

[1783] Specific operation: The user enters an answer in the text box and clicks the send button. The terminal sends this answer data to the server. The input is the user's answer data, and the output is the transmission of the answer data.

[1784] Step 7:

[1785] The server analyzes the user's responses and uses a sentiment analysis engine to recognize the user's emotions.

[1786] Specific operation: The server applies an analysis algorithm to analyze the user's response data, voice tone, and facial expressions. The input is the user's response data, and the output is the emotion analysis result.

[1787] Step 8:

[1788] The server dynamically generates the next question data based on the emotion and sends it to the terminal.

[1789] Specific operation: The server generates the next question data taking into account the user's emotional state and sends it to the device. For example, instead of a general question such as "Please tell me the level of pain," it generates a friendly question such as "It sounds like you're in a lot of pain. How bad is it?" The input is the emotion analysis result, and the output is the next question data.

[1790] Step 9:

[1791] The terminal analyzes the next question data and displays it to the user.

[1792] Specific operation: The terminal displays the next question data it has received. The input is the next question data, and the output is what is displayed to the user.

[1793] Step 10:

[1794] The user answers the next question and the process repeats until all of the user's questions have been answered.

[1795] Specific operation: The user enters an answer to the next question and submits it. This process is repeated. The input is the questions that are generated one after another and the user's answer data to those questions, and the output is the final accumulation of answer data.

[1796] Step 11:

[1797] After all questions have been completed, the device displays the message "The medical interview is complete. Thank you for your hard work." and sends all response data and emotion analysis data to the server.

[1798] Specific operation: When the user answers the last question, the terminal displays a completion message and sends all data to the server. The input is the final answer data, and the output is the display of the completion message and the sending of data.

[1799] Step 12:

[1800] The server stores the final diagnosis data and notifies the doctor if necessary.

[1801] Specific operation: The server stores all received data and sends alerts to doctors via email or notification systems (e.g., Slack, Teams, etc.). The input is the submitted response data and sentiment analysis data, and the output is the storage of the final diagnosis data and notification to the doctor.

[1802] (Application example 2)

[1803] 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."

[1804] Current factory environments lack systems that can properly recognize workers' emotions and stress levels and provide feedback and relaxation suggestions based on that information. This can have a negative impact on work efficiency and workers' mental health. It is necessary to accurately grasp workers' emotional states and provide appropriate follow-up when checking the progress of work and adjusting tasks on-site. Currently, there are no means to solve these issues, and improvements to the work environment are stalled.

[1805] 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.

[1806] In this invention, the server includes means for recognizing the user's emotions using an emotion engine, means for dynamically generating the next question data based on the emotion and sending it to the terminal, and means for the emotion engine to monitor the user's stress level and suggest relaxation methods as necessary. This makes it possible to accurately grasp the emotions and stress levels of workers and provide appropriate feedback and suggestions in real time.

[1807] "User" refers to a person who uses the system.

[1808] "Medical interview" refers to the process of gathering information by asking questions about a user's health status and symptoms.

[1809] A "request" refers to data or a request that a user sends to a server.

[1810] "Server" means a computer system that processes user requests and generates and transmits query data and other information.

[1811] "Initial question data" refers to information about the first question that the server presents to the user at the start of the medical interview.

[1812] "Terminal" means a device operated by a user to exchange information with a server.

[1813] An "emotion engine" refers to a system that analyzes a user's emotional state from their responses, voice, facial expressions, etc.

[1814] "Emotion" indicates the user's psychological and sensory state and is recognized by the system.

[1815] The "stress level" is an index that indicates the degree of stress that the user is feeling.

[1816] "Relaxation methods" refer to methods and suggestions for reducing stress and relaxing the user.

[1817] "Dynamic generation" means that new questions are generated in real time based on the user's answers and emotional state.

[1818] "Feedback" refers to the information or suggestions that the system returns in response to the user's answers.

[1819] "Diagnostic data" refers to data including the results of a user's medical interview and emotion analysis.

[1820] The system for realizing this invention is a combination of a server, a terminal, an emotion engine, and a relaxation suggestion engine. A specific description of this system is given below.

[1821] System Overview

[1822] The system works in a factory environment by connecting with devices used by workers to recognize their emotions and stress levels and provide feedback in real time.

[1823] Hardware and software used

[1824] Terminal: A device operated by a worker, such as a smartphone, tablet, or smart glasses.

[1825] Server: A computer system that processes various requests and analyzes and stores data. Often uses cloud services such as Amazon Web Services (AWS).

[1826] Emotion engine: Software that analyzes emotional states. Examples include Google Cloud's Emotion Analysis API and Microsoft Azure's Emotion Recognition API.

[1827] Relaxation suggestion engine: A software module that suggests relaxation methods based on stress levels.

[1828] Processing flow

[1829] 1. The user operates the terminal and starts a medical interview session with this system.

[1830] 2. The device receives the user's input and sends the request to the server.

[1831] 3. The server generates the initial question data and sends it to the terminal.

[1832] 4. The device displays the question to the user, and the user enters the answer.

[1833] 5. The device sends the user's answer to the server.

[1834] 6. The server analyzes the user's answers and uses an emotion engine to recognize the user's emotions.

[1835] 7. The server dynamically generates the next question data based on the recognized emotion and sends it to the device.

[1836] 8. The terminal displays the next question to the user, and the user enters the answer. This process is repeated until all necessary questions have been answered.

[1837] 9. The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[1838] 10. After all questions are completed, the device will display a message indicating the session is over and all data will be saved on the server.

[1839] Specific use cases

[1840] For example, if a worker answers, "I'm working long hours today," the emotion engine will interpret the answer as "stress." The next question will then be, "That's tough. Shall we take a short break? Take a deep breath and relax," and the relaxation suggestion engine will be activated.

[1841] Prompt Sentence Examples

[1842] "You've been working long hours today. It's tough. Let's take a break. Take a deep breath and relax."

[1843] This system makes it possible to accurately grasp the emotional state of workers and provide appropriate feedback and suggestions for stress reduction.

[1844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1845] Step 1:

[1846] The user operates the terminal and presses the inquiry start button to start the inquiry session.

[1847] Input: User initiates interview.

[1848] Output: The terminal generates a request to start an interview and sends it to the server.

[1849] Step 2:

[1850] The terminal receives the user's request to start the medical interview and transmits this information to the server.

[1851] Input: The request to start the interview sent by the user using the terminal.

[1852] Output: Received by the server as a trigger to generate the initial question data.

[1853] Step 3:

[1854] The server generates the initial question data and sends it to the terminal.

[1855] Input: A request to start an interview from the terminal.

[1856] Data processing: The server selects the first question of the medical interview based on the request to start the medical interview.

[1857] Output: Sends the initial question data to the terminal.

[1858] Step 4:

[1859] The terminal displays the question received from the server to the user.

[1860] Input: The initial question data sent by the server.

[1861] Output: The initial question is displayed on the terminal screen.

[1862] Step 5:

[1863] The user enters an answer to the question.

[1864] Input: The user's answer to the question displayed on the terminal.

[1865] Output: The device prepares the response data to send to the server.

[1866] Step 6:

[1867] The terminal sends the user's answer to the server.

[1868] Input: The answer data entered by the user.

[1869] Output: Send the answer data to the server.

[1870] Step 7:

[1871] The server analyzes the user's responses and recognizes the user's emotions using an emotion engine.

[1872] Input: User response data sent from the device.

[1873] Data calculation: The emotion engine analyzes voice tone and facial expressions based on response data to determine emotional state.

[1874] Output: Recognized emotion data.

[1875] Step 8:

[1876] The server dynamically generates the next question data based on the recognized emotion and sends it to the terminal.

[1877] Input: Recognized emotion data and previous response data.

[1878] Data processing: Dynamically generate new question content and expressions taking into account emotional data.

[1879] Output: Send the next question data to the terminal.

[1880] Step 9:

[1881] The terminal displays the next question to the user, and the user enters an answer to the next question. This process is repeated until all necessary questions have been answered.

[1882] Input: Next question data sent from the server.

[1883] Output: The following question will be displayed on the terminal screen:

[1884] Step 10:

[1885] The server monitors the user's stress level, and if it recognizes high stress, the relaxation suggestion engine suggests relaxation methods to the user.

[1886] Input: User response data and sentiment data.

[1887] Data calculation: Evaluate stress levels and recommend relaxation methods if necessary.

[1888] Output: Send relaxation suggestion data to device.

[1889] Step 11:

[1890] After all questions are completed, the terminal will display a message stating the end of the session and all data will be saved on the server.

[1891] Input: Completed response data and sentiment analysis data.

[1892] Data processing: Organize and store data on the server.

[1893] Output: Session termination message and saved data.

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] 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.

[1899] 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.

[1900] 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).

[1901] 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.

[1902] 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."

[1903] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1904] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1905] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1906] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1907] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1908] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1909] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1910] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1911] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1912] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1913] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1914] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1915] The following is further disclosed regarding the above embodiment.

[1916] (Claim 1)

[1917] means for a user to initiate a questionnaire;

[1918] means for transmitting a user request to a server;

[1919] A means for the server to generate initial question data and transmit it to the terminal;

[1920] means for displaying to the user the question received by the terminal from the server;

[1921] a means for the user to input answers to the questions;

[1922] means for transmitting the user's answers to a server;

[1923] A means for the server to analyze the user's answer and generate next question data;

[1924] means for displaying to the user the next question received by the terminal from the server;

[1925] a means for generating and displaying the next question through an iterative process;

[1926] a means for finally transmitting answer data of all questions to a server when the medical interview is completed;

[1927] a means for the server to store the final diagnosis data and notify the physician if necessary;

[1928] A system including:

[1929] (Claim 2)

[1930] 10. The system of claim 1, further comprising a server that dynamically generates subsequent questions based on user responses at each stage of the interview.

[1931] (Claim 3)

[1932] 10. The system of claim 1, further comprising means for storing user response data and notifying a doctor to respond.

[1933] "Example 1"

[1934] (Claim 1)

[1935] means for a user to initiate a questionnaire;

[1936] means for transmitting a user request to an information processing device;

[1937] a means for generating initial question data by an information processing device and transmitting the data to a terminal device;

[1938] means for displaying to a user a question received by the terminal device from the information processing device;

[1939] a means for the user to input answers to the questions;

[1940] means for transmitting the user's answer to the information processing device;

[1941] A means for an information processing device to analyze the user's answer and dynamically generate next question data using a generation AI model;

[1942] means for displaying the next question received by the terminal device from the information processing device to the user;

[1943] a means for generating and displaying the next question through an iterative process;

[1944] a means for finally transmitting answer data of all questions to an information processing device when the medical interview is completed;

[1945] a means for the information processing device to store final diagnostic data and notify a doctor as necessary;

[1946] A system including:

[1947] (Claim 2)

[1948] 10. The system of claim 1, further comprising an information processing device that dynamically generates the next question based on the user's answers at each stage of the interview.

[1949] (Claim 3)

[1950] 10. The system of claim 1, further comprising means for storing user response data and notifying a doctor to respond.

[1951] "Application Example 1"

[1952] (Claim 1)

[1953] means for a user to initiate an order;

[1954] means for transmitting a user request to a server;

[1955] A means for the server to generate initial question data and transmit it to the terminal;

[1956] means for displaying to the user the question received by the terminal from the server;

[1957] a means for the user to input answers to the questions;

[1958] means for transmitting the user's answers to a server;

[1959] A means for the server to analyze the user's answer and generate next question data;

[1960] means for displaying to the user the next question received by the terminal from the server;

[1961] a means for generating and displaying the next question through an iterative process;

[1962] a means for finally transmitting answer data of all questions to a server when an order is completed;

[1963] a means for the server to store the final order data and notify the service provider if necessary;

[1964] A system including:

[1965] (Claim 2)

[1966] 10. The system of claim 1, further comprising a server that dynamically generates the next question at each stage of an order based on the user's answers.

[1967] (Claim 3)

[1968] 2. The system according to claim 1, further comprising a means for storing user response data and for notifying the service provider to respond.

[1969] "Example 2: Combining Emotion Engines"

[1970] (Claim 1)

[1971] means for a user to initiate a questionnaire;

[1972] means for transmitting a user request to a server;

[1973] A means for the server to generate initial question data and transmit it to the terminal;

[1974] means for displaying to the user the question received by the terminal from the server;

[1975] a means for the user to input answers to the questions;

[1976] means for transmitting the user's answers to a server;

[1977] A means for the server to analyze the user's answer, recognize the emotion using a sentiment analysis engine, and generate the next question data;

[1978] means for displaying to the user the next question received by the terminal from the server;

[1979] a means for generating and displaying the next question through an iterative process;

[1980] means for providing relaxation content according to the emotional state of the user;

[1981] a means for finally transmitting answer data and emotion analysis data to a server when the interview is completed;

[1982] a means for the server to store the final diagnosis data and notify the physician if necessary;

[1983] A system including:

[1984] (Claim 2)

[1985] 10. The system of claim 1, further comprising a server that dynamically generates next questions at each stage of the interview based on the user's answers and emotional state.

[1986] (Claim 3)

[1987] 10. The system of claim 1, further comprising means for storing user response data and sentiment analysis data and for notifying a physician for response.

[1988] "Application example 2 when combining emotion engines"

[1989] (Claim 1)

[1990] means for a user to initiate a questionnaire;

[1991] means for transmitting a user request to a server;

[1992] A means for the server to generate initial question data and transmit it to the terminal;

[1993] means for displaying to the user the question received by the terminal from the server;

[1994] a means for the user to input answers to the questions;

[1995] means for transmitting the user's answers to a server;

[1996] A means for the server to analyze the user's response and recognize the user's emotion using an emotion engine;

[1997] A means for dynamically generating next question data based on the emotion recognized by the server and transmitting the next question data to the terminal;

[1998] means for displaying to the user the next question received by the terminal from the server;

[1999] a means for the emotion engine to monitor the user's stress level and suggest relaxation techniques as needed;

[2000] a means for generating and displaying the next question through an iterative process;

[2001] a means for finally transmitting answer data of all questions to a server when the medical interview is completed;

[2002] a means for the server to store the final diagnosis data and notify the physician if necessary;

[2003] A system including:

[2004] (Claim 2)

[2005] 10. The system of claim 1, further comprising a server that dynamically generates subsequent questions based on user responses at each stage of the interview.

[2006] (Claim 3)

[2007] 10. The system of claim 1, further comprising means for storing user response data and sentiment analysis data and for notifying a physician for response. [Explanation of symbols]

[2008] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to initiate a questionnaire; means for transmitting a user request to a server; A means for the server to generate initial question data and transmit it to the terminal; means for displaying to the user the question received by the terminal from the server; a means for the user to input answers to the questions; means for transmitting the user's answers to a server; A means for the server to analyze the user's answer and generate next question data; means for displaying to the user the next question received by the terminal from the server; a means for generating and displaying the next question through an iterative process; a means for finally transmitting answer data of all questions to a server when the medical interview is completed; a means for the server to store the final diagnosis data and notify the physician if necessary; A system including:

2. 10. The system of claim 1, further comprising a server that dynamically generates subsequent questions based on the user's answers at each stage of the interview.

3. The system according to claim 1, further comprising a means for storing user response data and notifying a doctor so that the doctor can respond.

Images