System

Abstract

A system is provided.SOLUTION: A system comprising: means for extracting patient information from an electronic medical record; means for inputting the extracted patient information into a generative AI model; means for generating information summarized by the generative AI model as a draft document; means for presenting the draft document to a user for review and editing; and means for storing and publishing the finally reviewed document.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the medical field, excessive work loads for doctors working in hospitals have become a social problem, and much of the cause is due to paperwork. In particular, creating medical information forms and discharge summaries is a simple text summarization task, but it requires a lot of time and effort. This prevents doctors from concentrating on their essential work, and is one of the reasons for the increase in overtime work. Furthermore, the increased burden of administrative work may have a negative impact on the quality of medical care. This invention aims to solve these problems and reduce the workload of doctors. [Means for solving the problem]

[0005] This invention provides a system that includes a means for extracting patient data from electronic medical records, a means for inputting the extracted patient data into a generative AI model, a means for generating a draft document based on information summarized by the generative AI model, a means for presenting the draft document to the user for review and editing, and a means for saving and publishing the final, reviewed document. This automates the process of extracting and summarizing data from electronic medical records, enabling the efficient creation of medical information reports and discharge summaries. This system is designed to allow users to create the necessary documents with simple operations, reducing doctors' overtime work and administrative burdens.

[0006] An "electronic medical record" is a medical information system that records and stores a patient's medical information in digital format and makes it accessible when needed.

[0007] "Patient data" refers to information such as a patient's medical history, prescribed medications, and test results recorded in electronic medical records.

[0008] A "generative AI model" is an artificial intelligence system that includes algorithms that learn from large amounts of medical data and summarize necessary information from input patient data.

[0009] "Summary" refers to information that summarizes patient data in a concise form extracted by a generative AI model.

[0010] A "Draft Document" is a document created by a generative AI model that contains information that is a draft of the final document.

[0011] "User" refers to a medical professional such as a doctor who uses this system to perform document preparation work.

[0012] "Final Document" means the completed document that has been officially saved and published after user review and any necessary edits.

[0013] "Preservation" refers to the act of recording a completed document in digital form and making it accessible at a later date.

[0014] "Issuance" refers to the act of certifying the final document as official and providing it to the parties involved. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system that uses a generative AI model to support document creation in medical settings. Specific embodiments of this system are described below.

[0037] 1. User login

[0038] To access the system, a user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates it by checking it against information in a database. If authentication is successful, the server starts the user's session and displays the dashboard on the terminal.

[0039] 2. Extraction of electronic medical record information

[0040] The user selects "Create a medical information report" from the dashboard and enters the target patient's ID. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[0041] 3. Information Summarization Using Generative AI Models

[0042] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[0043] 4. Review and edit your draft

[0044] The server sends the generated draft document to the user's device. The device displays the draft document to the user, who checks the contents and makes edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The device then sends this request to the server.

[0045] 5. Publication of the Final Document

[0046] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0047] Specific examples

[0048] Take the example of a scenario in which a doctor is creating a medical information report for a patient. The doctor logs into the system on a terminal and selects to create a medical information report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is input into a generative AI model, which then summarizes it. The generated draft document is displayed on the doctor's terminal, where the doctor can review and edit the contents. It is then issued as the final document and saved in the system.

[0049] In this way, the system significantly reduces doctors' overtime work and enables efficient document preparation.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0053] Step 2:

[0054] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[0055] Step 3:

[0056] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[0057] Step 4:

[0058] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0059] Step 5:

[0060] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[0061] Step 6:

[0062] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[0063] Step 7:

[0064] The server sends the generated draft document to the user's terminal, and the terminal displays the draft document to the user.

[0065] Step 8:

[0066] The user checks the draft document and makes corrections and edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The terminal sends this request to the server.

[0067] Step 9:

[0068] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[0069] Step 10:

[0070] The terminal notifies the user that the final document has been successfully published.

[0071] Example 1

[0072] 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."

[0073] Traditional document creation processes in medical settings require time and effort from medical professionals, especially when creating documents such as medical information reports. Manual input and verification can lead to human error. There is a need for a system that can use generative AI models to summarize information from electronic medical records and create documents efficiently. Furthermore, it is necessary to reduce the burden on medical professionals by automating the processes of user authentication and data extraction.

[0074] 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.

[0075] In this invention, the server includes a means for a user to input authentication information and send it to the server, a means for the server to compare the authentication information with a database and perform authentication, a means for extracting patient data from the electronic medical record, a means for inputting the extracted patient data into a generative AI model, a means for generating information summarized by the generative AI model as a draft document, a means for presenting the draft document to the user for confirmation and editing, and a means for saving and issuing the final confirmed document. This enables medical professionals to create documents easily and quickly, reducing human error and improving work efficiency.

[0076] "User" refers to a healthcare professional who accesses and operates the system.

[0077] "Authentication information" refers to information such as the user ID and password that a user enters when logging in to a system.

[0078] "Server" refers to a computer device that processes data and performs authentication for the entire system.

[0079] "Database" refers to the data storage system where patient medical information and user authentication information is stored.

[0080] An "electronic medical record" refers to a digital system that manages medical information such as a patient's medical history, prescription medications, and test results.

[0081] "Patient data" refers to information stored in electronic medical records, such as each patient's medical history, prescribed medications, and test results.

[0082] A "generative AI model" refers to an artificial intelligence model that analyzes input data and performs summaries and text generation.

[0083] "Draft Document" refers to a draft document generated based on information summarized by a generative AI model.

[0084] "Terminal" means the computer or mobile device used by a User to access the System.

[0085] A "user session" refers to a series of communication states for operating a system after a user has been authenticated.

[0086] "Dashboard" refers to the interface through which users access the main functions of the system.

[0087] "Issuance" refers to the formal storage and recording of the final verified document in the system.

[0088] A "prompt" is an instructional sentence containing necessary information that is used as input to a generative AI model.

[0089] This invention relates to a system that uses generative AI models to support document creation in medical settings, including a series of processes for efficiently performing user authentication, data extraction, information summarization, document generation, and final document issuance.

[0090] System configuration and operation

[0091] This system is configured using the following hardware and software:

[0092] Hardware

[0093] Server: Manages the system's data processing, authentication, database access, and communication with the generative AI model.

[0094] Terminal: A computer or mobile device through which a user accesses the system.

[0095] software

[0096] Electronic medical record system: A digital system that manages information such as a patient's medical history, prescription medications, and test results (e.g., a general-purpose electronic medical record system).

[0097] Generative AI model: An artificial intelligence model that analyzes input data and performs summarization or text generation (e.g., GPT-3).

[0098] Program processing

[0099] 1. User Authentication

[0100] First, the user enters authentication information (user ID and password) on the login screen of the device. The device sends this authentication information to the server, which checks it against the database. If authentication is successful, the user session begins and the dashboard screen is displayed on the device.

[0101] 2. Data extraction

[0102] The user selects to create a medical information report from the dashboard and enters the target patient's ID. This request is sent from the device to the server. The server accesses the electronic medical record system, searches and extracts the specified patient's data (medical history, prescription medications, test results, etc.), and temporarily stores it on the server.

[0103] 3. Information Summary

[0104] The server generates a prompt sentence to be input to the generative AI model based on the extracted patient data. This prompt sentence is sent to the generative AI model, which analyzes and summarizes the data and generates a draft document of the medical information report. This draft document is then sent back to the server.

[0105] Prompt Sentence Examples

[0106] Patient ID: patient001

[0107] Medical History: Diagnosis on January 1, 2023

[0108] Prescription medication list: Aspirin, Metoprolol

[0109] Test results: Blood test normal

[0110] Generate a medical information form from this information.

[0111] 4. Review and edit the draft document

[0112] The server sends the generated draft document to the user's device. The device displays the draft document, and the user checks the contents and makes edits as necessary. When the user has completed editing, they click the "Publish as final document" button. This request is sent from the device to the server.

[0113] 5. Publication of the Final Document

[0114] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been published.

[0115] This system allows medical professionals to easily and quickly create documents such as medical information reports, and by using a generative AI model, it automates information summarization, which is expected to reduce human error and improve work efficiency.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1: User authentication

[0118] ---

[0119] Input: The user enters authentication information (user ID and password) on the device's login screen.

[0120] How it works: When the user clicks the "Login" button, the device sends these credentials to the server in real time.

[0121] Specific operation: The user enters the user ID "doctor123" and the password "password123" and presses the "Login" button.

[0122] Data processing: The server encrypts the received user ID and password and checks them against the database.

[0123] Output: If authentication is successful, the server starts a user session and sends the dashboard screen to the terminal. If authentication fails, it sends an error message.

[0124] Specific operation: The server searches the authentication information in the database, and if it matches, displays a message such as "Welcome, doctor123" on the user's terminal.

[0125] Step 2: Data extraction

[0126] ---

[0127] Input: The user selects "Create medical information report" on the dashboard and enters the ID of the target patient.

[0128] Specific operation: The user clicks the "Create medical information report" button, enters the patient ID "patient001", and presses the "Search" button.

[0129] Operation: The terminal sends the entered patient ID to the server.

[0130] Data processing: The server accesses the electronic medical record database and searches and extracts data on the target patient, such as medical history, prescription medications, and test results.

[0131] Output: The server temporarily stores the extracted patient data within the server and continues processing.

[0132] Specific operation: The server sends a query to the electronic medical record system, retrieves all information about the patient, and temporarily stores it in memory.

[0133] Step 3: Information Summary

[0134] ---

[0135] Input: Patient data stored in the server.

[0136] Specific operation: The server generates a prompt sentence to send to the generative AI model.

[0137] How it works: The server sends the generated prompt sentence to the generative AI model.

[0138] Data processing: The generative AI model analyzes the prompt text, summarizes information such as medical history, prescription medications, and test results, and generates a draft document.

[0139] Output: The generative AI model returns the generated draft document to the server.

[0140] Example prompt sentence:

[0141] Patient ID: patient001

[0142] Medical History: Diagnosis on January 1, 2023

[0143] Prescription medication list: Aspirin, Metoprolol

[0144] Test results: Blood test normal

[0145] Generate a medical information form from this information.

[0146] Step 4: Review and edit the draft document

[0147] ---

[0148] Input: The draft document returned from the generative AI model.

[0149] Specific operation: The server sends the generated draft document to the user's terminal.

[0150] How it works: The device displays the draft document to the user, who can review and edit it.

[0151] Data processing: After the user has completed editing, they click the "Publish as final document" button to send the final version to the server.

[0152] Output: Edited final draft document.

[0153] Specific actions: The user views the draft document, makes corrections such as adding additional information to the inspection results section, and clicks the "Publish as final document" button.

[0154] Step 5: Issuance of final document

[0155] ---

[0156] Input: The final draft document as edited by the user.

[0157] Specific operation: The terminal sends the finalized document to the server.

[0158] Actions: The server formally stores the final document and records its publication.

[0159] Data processing: After the server has completed saving, it will send a notification to the device.

[0160] Output: Save completion notification and final document.

[0161] Specific operation: The server saves the final document in the database and displays a notification on the terminal stating "Medical information report has been issued successfully."

[0162] In this way, the system reduces the burden on the user and enables efficient document creation.

[0163] (Application example 1)

[0164] 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."

[0165] In modern factories, the creation of manufacturing process and quality control reports still relies heavily on manual labor. This reduces efficiency and increases the risk of human error. It also makes it difficult to quickly share and confirm information, potentially leading to problems in product quality control. To solve this issue and improve overall factory productivity, a system is needed that can automatically summarize manufacturing data and quickly create reports.

[0166] 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.

[0167] In this invention, the server includes means for extracting target data from an electronic database, means for inputting the extracted target data into a generative AI model, means for generating a draft document from the information summarized by the generative AI model, means for presenting the draft document to a user for confirmation and editing, and means for saving and publishing the final confirmed document, thereby enabling the automatic generation and editing of manufacturing data summaries and reports.

[0168] An "electronic database" is a process of systematically storing and managing information in digital form, and is a database system that allows quick access to specific data.

[0169] "Target data" refers to information relating to a specific ID extracted from an electronic database, and is a group of data containing the necessary content depending on the purpose.

[0170] A "generative AI model" is an algorithm or software system that uses artificial intelligence technology to analyze input data and automatically generate summaries and documents.

[0171] A "draft document" is an intermediate document automatically generated by a generative AI model that is later reviewed and edited.

[0172] "Historical data" is information that contains past performance or records of a particular process or operation.

[0173] "Process data" refers to data that includes detailed information and execution details when a specific action or operation is performed.

[0174] "Outcome data" is information that describes the results or outputs achieved as a result of a particular procedure or process.

[0175] This invention proposes a system for automatically generating reports on manufacturing processes and quality control within factories. The system uses a generative AI model to summarize work data and efficiently generate reports.

[0176] First, a user (factory operator) logs in to the system. The user enters their authentication information (user ID and password) and sends it from the terminal to the server. The server compares this authentication information with the information in the database, and if authentication is successful, the user's session is started and a dashboard is displayed on the terminal.

[0177] Next, the user selects data for a specific production line from the dashboard. After the user enters the production line ID, the terminal sends this request to the server. The server accesses an electronic database to search and extract data for the specified production line. This data includes production history, quality data, and maintenance records. This extracted data is temporarily stored on the server.

[0178] The server then inputs the extracted data into a generative AI model, which analyzes the received data, summarizes manufacturing history, quality control data, and maintenance records, and generates a draft report document, which is returned to the server.

[0179] The server then sends the generated draft document to the user's device. The device displays the draft document to the user, who can review the content and make edits as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device then sends this request to the server.

[0180] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0181] The system can efficiently summarize manufacturing data and automatically generate and edit reports, allowing factory operators to reduce the risk of human error and share information quickly.

[0182] As a concrete example, consider a scenario in which a mechanical engineer operator creates a quality control report for a specific production line. The operator logs into the system and selects data for the specific production line. The production history, quality data, and maintenance records for that line are extracted from the database. This data is then input into a generative AI model, which then summarizes it. The generated draft document is displayed on the operator's device, where the operator can review and edit the contents. It is then published as a final document and saved in the system.

[0183] An example prompt for a generative AI model is:

[0184] "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating hours: 8 hours, Maintenance records: normal"

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] A user logs in to the system using their own terminal. The user enters authentication information (user ID and password) into the terminal's login screen and sends this information to the server. The server performs authentication by comparing it with information in the database, and if authentication is successful, starts a session and displays a dashboard on the terminal. The input is authentication information, and the output is the authentication result and the dashboard screen. The server compares the authentication information with the database and generates session information.

[0188] Step 2:

[0189] The user selects the relevant production line data from the dashboard. The user enters the production line ID and sends the request to the server via the terminal. The server accesses the electronic database to search and extract data for the specified production line. The input is the production line ID and the output is the extracted production data. The server retrieves historical data, quality data, and maintenance records from the database.

[0190] Step 3:

[0191] The server sends the extracted data to the generative AI model. The server passes the specified manufacturing data to the generative AI model and provides a prompt to the model. The generative AI model analyzes the data and generates summarized information as a draft document. An example of this prompt is "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating time: 8 hours, Maintenance record: Normal." The input is the manufacturing data, and the output is the summarized draft document.

[0192] Step 4:

[0193] The server sends the generated draft document to the user's terminal. The user's terminal displays the draft document, allowing the user to check and edit the contents. The terminal displays the draft document in the user's interface, allowing the user to manually edit and add comments. The input is the draft document, and the output is the edited document.

[0194] Step 5:

[0195] The user finishes editing the draft document and clicks the "Publish as final document" button. The terminal sends this request to the server. The server formally saves the edited document and records that it has been published. The server sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published. The input is the edited document and the publishing request, and the output is the final saved document and the notification.

[0196] At each step, the server or device processes and calculates the data to generate the required output. By utilizing a "generative AI model," we have created a system that can efficiently summarize data and generate documents.

[0197] 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.

[0198] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0199] 1. User login

[0200] To access the system, the user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates the user by comparing it with information in a database. If authentication is successful, the server starts a user session and sends a request to display the dashboard on the terminal. The terminal then displays the dashboard screen to the user.

[0201] 2. Extraction of electronic medical record information

[0202] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[0203] 3. Information Summarization Using Generative AI Models

[0204] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[0205] 4. Review and edit your draft

[0206] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[0207] 5. Emotion-Based Regulation

[0208] The emotion engine recognizes the user's emotions and feeds that information back to the generative AI model, which then adjusts the tone and expression of the document appropriately based on the user's emotions. For example, if the user is feeling stressed, the tone of the document can be softened.

[0209] 6. Final confirmation and issuance

[0210] The user reviews the draft document and makes corrections and edits as necessary. The emotion engine continues to monitor the user's emotions during this process and makes readjustments as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device sends this request to the server.

[0211] 7. Publication of the Final Document

[0212] The server officially saves the final document and records that it has been published. The server sends a notification to the terminal that the final document has been saved. The terminal notifies the user that the final document has been successfully published.

[0213] Specific examples

[0214] Consider a scenario in which a doctor is creating a medical report for a patient. The doctor logs into the system on their device and selects to create a medical report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress or fatigue and adjusts the tone and expression of the document appropriately. The final document is then published and saved in the system.

[0215] In this way, the system can significantly reduce doctors' overtime work and efficiently prepare documents. Also, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0219] Step 2:

[0220] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[0221] Step 3:

[0222] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[0223] Step 4:

[0224] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0225] Step 5:

[0226] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[0227] Step 6:

[0228] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[0229] Step 7:

[0230] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[0231] Step 8:

[0232] The emotion engine recognizes the user's emotions and feeds them back to the generative AI model, which then adjusts the tone and expression of the draft document based on the user's emotions.

[0233] Step 9:

[0234] The user checks the draft document and makes corrections or edits as necessary. The device temporarily saves the user's corrections.

[0235] Step 10:

[0236] The user completes the edits and clicks the "Publish as final document" button. The device sends this request to the server.

[0237] Step 11:

[0238] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[0239] Step 12:

[0240] The terminal notifies the user that the final document has been successfully published.

[0241] Example 2

[0242] 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."

[0243] In the medical field, efficient and accurate preparation of medical information reports is required, but conventional systems require doctors to spend a huge amount of time manually preparing documents. This increases doctors' overtime work and stress. Furthermore, the tone and expression of documents must also be adjusted manually, placing a burden on doctors. Furthermore, conventional systems do not take into account the doctor's emotional state when preparing documents, resulting in the problem of document quality being affected by the doctor's emotional state.

[0244] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for extracting patient data from the electronic medical record, means for inputting the extracted patient data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user and analyzing the user's emotions using an emotion recognition engine, means for adjusting the tone and expression of the draft document based on the analysis results, means for user confirmation and editing, and means for saving and publishing the final confirmed document. This reduces the burden on doctors and enables efficient and accurate creation of medical information reports. Furthermore, document creation that takes the doctor's emotional state into consideration is realized, improving the quality of the document.

[0245] An "electronic medical record" is a system that digitally records and manages patient medical information, prescription medications, test results, etc.

[0246] "Patient data" refers to information such as medical history, prescribed medications, and test results recorded in electronic medical records.

[0247] A "generative AI model" is an artificial intelligence model that analyzes input data, summarizes information, and generates text.

[0248] A "draft document" is an unfinalized document in which information summarized by a generative AI model is organized into sentence form.

[0249] An "emotion recognition engine" is an engine that has the ability to analyze data such as a user's facial expressions, voice tone, and keystroke patterns to identify the user's emotions.

[0250] "Tone and voice adjustment" is the process of changing the tone and language of a document depending on the user's emotional state.

[0251] A "session" is a unit in which the server maintains the user's logged-in status and manages the entire process of the user's use of the system.

[0252] A "dashboard" is a screen that aggregates the information and functions necessary for system users to operate the system.

[0253] "Storage and publication" refers to the process of formally recording the final reviewed document in a database and sharing it with other systems and users as needed.

[0254] MODE FOR CARRYING OUT THE INVENTION

[0255] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0256] User login

[0257] First, a user (doctor) logs in to the system using a terminal. The terminal displays a login screen, and the user enters their user ID and password. The terminal sends this authentication information to the server, which then authenticates the user by checking it against the user information in its database. If authentication is successful, the server starts a session and sends a request to the terminal to display the dashboard. The terminal renders the dashboard screen and displays it to the user.

[0258] Extraction of electronic medical record information

[0259] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0260] Information summarization using generative AI models

[0261] The server formats the extracted patient data and generates a prompt to send to the generative AI model, which analyzes the received patient data and summarizes the medical history, prescribed medications, test results, etc. to generate a draft medical information report document. The generated draft document is returned to the server.

[0262] Draft review and emotion recognition

[0263] The server then sends the generated draft document to the user's device, which then renders and displays it to the user. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, keystroke patterns, etc. to recognize the user's emotions.

[0264] Emotion-Based Adjustment

[0265] The emotion recognition engine feeds the analysis results back to the generative AI model, which then uses the feedback to adjust the tone and expression of the draft document appropriately. For example, if the user is feeling stressed, the tone of the document can be softened.

[0266] Final confirmation and issuance

[0267] The user reviews the draft document and manually corrects and edits it as needed. The emotion recognition engine continues to monitor the user's emotions during this process and readjusts the document as needed. Once editing is complete, the user clicks the "Publish as Final Document" button. The device sends this request to the server.

[0268] Final document retention and notification

[0269] The server officially saves the final document and records that it has been published. The server then sends a notification of the completion of saving to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0270] Specific examples

[0271] Consider a scenario in which a doctor is creating a medical record for a patient. The doctor logs in to the system on a device and selects to create a medical record for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress and fatigue and adjusts the tone and expression appropriately. The document is then published as a final document and saved in the system. In this way, this system significantly reduces overtime work for doctors and enables more efficient document creation. Furthermore, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[0272] Prompt Sentence Examples

[0273] Please draft a medical information form using the following patient data: Medical history: ____, Prescription medications: ____, Test results: ____.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] User login

[0277] The user enters their user ID and password, and the device sends this authentication information to the server. The input is the user ID and password, and the output is the authentication result. The server compares the authentication information with the user information in the database, and if authentication is successful, the session begins. Specifically, the server sends a successful authentication response to the device, and the device displays the dashboard.

[0278] Step 2:

[0279] Extraction of electronic medical record information

[0280] The user selects "Create a medical information report" on the dashboard, enters the patient ID, and performs a search. The terminal sends this request to the server. The input is the patient ID, and the output is the patient's medical record information. The server accesses the electronic medical record database, searches and extracts the medical record information of the specified patient, and temporarily stores this information. Specifically, it executes the request "GET / patient-info?patient_id=patient456" and retrieves the search results.

[0281] Step 3:

[0282] Information summarization using generative AI models

[0283] The server sends the extracted patient data to the generative AI model as a prompt. The input is the patient data, and the output is a summarized draft document. The generative AI model analyzes the received data and generates a draft document by summarizing information such as medical history, prescribed medications, and test results. Specifically, the prompt "Please create a draft medical information report using the following patient data. Medical history: XX, prescribed medications: △△, test results: □□" is input into the generative AI model, and the summary result is obtained.

[0284] Step 4:

[0285] Draft document review and emotion recognition

[0286] The server sends the generated draft document to the terminal, which then displays it to the user. The input is the draft document, and the output is the user's emotional data. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize their emotions. Specifically, it analyzes input data from the webcam and microphone to obtain emotion recognition results.

[0287] Step 5:

[0288] Emotion-Based Adjustment

[0289] The emotion recognition engine feeds the analysis results back to the generative AI model. The input is emotional data, and the output is an adjusted draft document. The generative AI model uses this feedback to appropriately adjust the tone and expression of the draft document. Specifically, for users who are feeling stressed, the model will soften the tone of the document.

[0290] Step 6:

[0291] Final confirmation and issuance

[0292] The user reviews the draft document and makes corrections as necessary. The input is the draft document and the user's corrections, and the output is the final document. The emotion recognition engine monitors the user's emotions during the final confirmation and readjusts them as necessary. When the user clicks the "Publish as Final Document" button, the terminal sends the request to the server. Specifically, after editing, it sends a "POST / finalize-document" request.

[0293] Step 7:

[0294] Final document retention and notification

[0295] The server officially saves the final document and records that publication is complete. The input is the final document, and the output is a notification that saving is complete. The server sends a notification of saving completion to the terminal, and the terminal notifies the user. Specifically, it executes a database query called "INSERT INTO final_documents (final document data)" and displays a message to the user that saving is complete.

[0296] (Application example 2)

[0297] 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."

[0298] In traditional medical settings and manufacturing plants, generative AI models are being used to improve the efficiency of document creation and robot operation, but no systems exist that take user emotions into account. As a result, if a user is stressed or fatigued, the quality and safety of the output may decline. In manufacturing plants in particular, where the emotions of operators are directly linked to work safety, a system that recognizes and adapts to their emotions is needed.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from the electronic medical record, means for inputting the extracted data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user for confirmation and editing, means for recognizing the user's emotions using emotion recognition technology, means for providing feedback to the generative AI model based on the recognized emotions and adjusting the tone and expression of the document, and means for saving and publishing the final confirmed document. This enables efficient document creation and safe operation that reflects the user's emotional state.

[0300] An "electronic medical record" is a system that electronically manages a patient's medical information.

[0301] "Data identification information" is information for uniquely identifying specific data.

[0302] An "information management system" is a system for storing, managing, retrieving, and processing data.

[0303] A "generative AI model" is an artificial intelligence model that generates or summarizes information based on given data.

[0304] A "draft document" is a temporary document intended for editing by users before final review.

[0305] "Emotion recognition technology" is a technology that detects emotions by analyzing a user's facial expressions, voice, keystroke patterns, etc.

[0306] "Feedback" is the action of making corrections to models and processes based on information obtained by the system.

[0307] "Tone" refers to the overall impression or mood of a document or statement.

[0308] A "representation" is a method or format for conveying data or information.

[0309] As an embodiment of the present invention, the following system can be constructed.

[0310] Overall system overview

[0311] The system includes the following main elements:

[0312] Server: A central system that stores, processes, and manages data.

[0313] Device: The device that a user accesses and operates (e.g., computer, smartphone, smart glasses, head-mounted display, etc.).

[0314] Robot: A piece of equipment on a manufacturing line that performs tasks according to control instructions.

[0315] Program Description

[0316] 1. Extract data from electronic medical records

[0317] The server accesses the electronic medical record database and extracts patient data, which is processed based on the data identification information.

[0318] 2. Input the extracted data into a generative AI model

[0319] The server sends the extracted patient data to a generative AI model, which then issues instructions for generating summaries and optimized information. The generative AI model summarizes the patient's medical history, prescription medications, test results, etc., and generates a draft document.

[0320] 3. Present the draft document to the user

[0321] The terminal presents the generated draft document to the user and provides an interface for reviewing and editing.

[0322] 4. Recognize user emotions using emotion recognition technology

[0323] The device's built-in emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions in real time.

[0324] 5. Feedback to generative AI models based on recognized emotions

[0325] The server then feeds the recognized user emotion back into the regenerative AI model, adjusting the tone and expression of the document. For example, if the user is feeling stressed, the document's expression will be softened.

[0326] 6. Save and publish the finalized document

[0327] The server officially stores the final document that has been reviewed and edited by the user and issues it as necessary. The user can confirm through their terminal that the final document has been successfully issued.

[0328] Hardware and software used

[0329] Server: Database management systems (e.g., MySQL, PostgreSQL) and web servers (e.g., Apache, NGINX).

[0330] Terminal: Facial recognition software (e.g., OpenCV), voice analysis software (e.g., TensorFlow).

[0331] Robot: Robot control system (e.g. ROS - Robot Operating System).

[0332] Specific examples

[0333] As a concrete example, consider the following scenario:

[0334] 1. An operator logs in to the system and instructs the robot to perform packaging with task ID "task_123." The server inputs the corresponding task information into the generative AI model and generates the optimal operation sequence.

[0335] 2. The generated operation sequence is displayed on the terminal, and the operator's emotions are detected by an emotion recognition engine. If the operator is feeling stressed, the system reconsiders the operation sequence to prioritize safety.

[0336] 3. The adjusted operation sequence is finally confirmed, and the robot begins its work. The operator checks the results via a terminal and confirms that the work has been completed safely.

[0337] Prompt Sentence Examples

[0338] prompt:

[0339] "Generate the optimal operation sequence for the robot packaging task with task ID 'task_123'."

[0340] Input data:

[0341] "Task: Packaging, Operational Steps: Step 1: Collect items, Step 2: Place items, Step 3: Package items, Step 4: Inspect packaging, Step 5: Remove finished product."

[0342] This system enables efficient document creation and safe operation that reflects the user's emotional state.

[0343] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0344] Specific processing steps of the program

[0345] Step 1:

[0346] User login

[0347] The user logs into the system using a terminal. The terminal displays a login screen and asks the user to enter a user ID and password. The entered authentication information is sent from the terminal to the server. The server verifies the information against the database and, if successful, starts a user session. A session ID is generated and a request to display the dashboard is sent to the terminal.

[0348] Input: User ID, Password

[0349] Output: Session ID, Dashboard display

[0350] Step 2:

[0351] Get task information

[0352] The user selects a specific task (e.g., packaging) from the dashboard and searches by entering the task ID. The device sends this request to the server, which accesses the database to retrieve the task information, including the operation steps and required resources.

[0353] Input: Task ID

[0354] Output: Task information

[0355] Step 3:

[0356] Optimizing task information

[0357] The server inputs the acquired task information into the generative AI model. At this time, the AI ​​model is also provided with a prompt. The generative AI model generates an optimal operation sequence based on the task information. The generated operation sequence is returned to the server.

[0358] Input: Task information, prompt

[0359] Output: Optimized operation sequence

[0360] Step 4:

[0361] Optimized operation sequence presentation

[0362] The server sends the generated optimized operation sequence to the user's terminal, which displays it to the user, who can then review the operation sequence and make any necessary corrections.

[0363] Input: Optimized operation sequence

[0364] Output: what is displayed to the user

[0365] Step 5:

[0366] emotion recognition

[0367] The emotion engine on the device analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotional state in real time. The recognized emotion information is then sent to the server.

[0368] Input: facial expression data, voice data, keystroke data

[0369] Output: Emotional information

[0370] Step 6:

[0371] Emotion-based feedback

[0372] The server then feeds the recognized emotion information back to the generative AI model and adjusts the tone and expression of the document. For example, if the user is feeling stressed, the tone of the document will be softened. The adjusted document is then sent back to the server.

[0373] Input: Emotion information

[0374] Output: Adjusted document

[0375] Step 7:

[0376] Final confirmation and document storage

[0377] The user finalizes the adjusted document and makes corrections as necessary. When the user clicks the final confirmation button, the terminal sends this request to the server. The server officially saves and publishes the final document. A notification that the final document has been saved is sent to the terminal and displayed to the user.

[0378] Input: Final confirmation request

[0379] Output: Save final document, display notification

[0380] This series of processing steps enables efficient document creation and safe operation that reflects the user's feelings.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Second embodiment]

[0385] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0396] 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."

[0397] This invention is a system that uses a generative AI model to support document creation in medical settings. Specific embodiments of this system are described below.

[0398] 1. User login

[0399] To access the system, a user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates it by checking it against information in a database. If authentication is successful, the server starts the user's session and displays the dashboard on the terminal.

[0400] 2. Extraction of electronic medical record information

[0401] The user selects "Create a medical information report" from the dashboard and enters the target patient's ID. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[0402] 3. Information Summarization Using Generative AI Models

[0403] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[0404] 4. Review and edit your draft

[0405] The server sends the generated draft document to the user's device. The device displays the draft document to the user, who checks the contents and makes edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The device then sends this request to the server.

[0406] 5. Publication of the Final Document

[0407] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0408] Specific examples

[0409] Take the example of a scenario in which a doctor is creating a medical information report for a patient. The doctor logs into the system on a terminal and selects to create a medical information report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is input into a generative AI model, which then summarizes it. The generated draft document is displayed on the doctor's terminal, where the doctor can review and edit the contents. It is then issued as the final document and saved in the system.

[0410] In this way, the system significantly reduces doctors' overtime work and enables efficient document preparation.

[0411] The processing flow will be explained below.

[0412] Step 1:

[0413] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0414] Step 2:

[0415] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[0416] Step 3:

[0417] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[0418] Step 4:

[0419] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0420] Step 5:

[0421] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[0422] Step 6:

[0423] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[0424] Step 7:

[0425] The server sends the generated draft document to the user's terminal, and the terminal displays the draft document to the user.

[0426] Step 8:

[0427] The user checks the draft document and makes corrections and edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The terminal sends this request to the server.

[0428] Step 9:

[0429] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[0430] Step 10:

[0431] The terminal notifies the user that the final document has been successfully published.

[0432] Example 1

[0433] 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."

[0434] Traditional document creation processes in medical settings require time and effort from medical professionals, especially when creating documents such as medical information reports. Manual input and verification can lead to human error. There is a need for a system that can use generative AI models to summarize information from electronic medical records and create documents efficiently. Furthermore, it is necessary to reduce the burden on medical professionals by automating the processes of user authentication and data extraction.

[0435] 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.

[0436] In this invention, the server includes a means for a user to input authentication information and send it to the server, a means for the server to compare the authentication information with a database and perform authentication, a means for extracting patient data from the electronic medical record, a means for inputting the extracted patient data into a generative AI model, a means for generating information summarized by the generative AI model as a draft document, a means for presenting the draft document to the user for confirmation and editing, and a means for saving and issuing the final confirmed document. This enables medical professionals to create documents easily and quickly, reducing human error and improving work efficiency.

[0437] "User" refers to a healthcare professional who accesses and operates the system.

[0438] "Authentication information" refers to information such as the user ID and password that a user enters when logging in to a system.

[0439] "Server" refers to a computer device that processes data and performs authentication for the entire system.

[0440] "Database" refers to the data storage system where patient medical information and user authentication information is stored.

[0441] An "electronic medical record" refers to a digital system that manages medical information such as a patient's medical history, prescription medications, and test results.

[0442] "Patient data" refers to information stored in electronic medical records, such as each patient's medical history, prescribed medications, and test results.

[0443] A "generative AI model" refers to an artificial intelligence model that analyzes input data and performs summaries and text generation.

[0444] "Draft Document" refers to a draft document generated based on information summarized by a generative AI model.

[0445] "Terminal" means the computer or mobile device used by a User to access the System.

[0446] A "user session" refers to a series of communication states for operating a system after a user has been authenticated.

[0447] "Dashboard" refers to the interface through which users access the main functions of the system.

[0448] "Issuance" refers to the formal storage and recording of the final verified document in the system.

[0449] A "prompt" is an instructional sentence containing necessary information that is used as input to a generative AI model.

[0450] This invention relates to a system that uses generative AI models to support document creation in medical settings, including a series of processes for efficiently performing user authentication, data extraction, information summarization, document generation, and final document issuance.

[0451] System configuration and operation

[0452] This system is configured using the following hardware and software:

[0453] Hardware

[0454] Server: Manages the system's data processing, authentication, database access, and communication with the generative AI model.

[0455] Terminal: A computer or mobile device through which a user accesses the system.

[0456] software

[0457] Electronic medical record system: A digital system that manages information such as a patient's medical history, prescription medications, and test results (e.g., a general-purpose electronic medical record system).

[0458] Generative AI model: An artificial intelligence model that analyzes input data and performs summarization or text generation (e.g., GPT-3).

[0459] Program processing

[0460] 1. User Authentication

[0461] First, the user enters authentication information (user ID and password) on the login screen of the device. The device sends this authentication information to the server, which checks it against the database. If authentication is successful, the user session begins and the dashboard screen is displayed on the device.

[0462] 2. Data extraction

[0463] The user selects to create a medical information report from the dashboard and enters the target patient's ID. This request is sent from the device to the server. The server accesses the electronic medical record system, searches and extracts the specified patient's data (medical history, prescription medications, test results, etc.), and temporarily stores it on the server.

[0464] 3. Information Summary

[0465] The server generates a prompt sentence to be input to the generative AI model based on the extracted patient data. This prompt sentence is sent to the generative AI model, which analyzes and summarizes the data and generates a draft document of the medical information report. This draft document is then sent back to the server.

[0466] Prompt Sentence Examples

[0467] Patient ID: patient001

[0468] Medical History: Diagnosis on January 1, 2023

[0469] Prescription medication list: Aspirin, Metoprolol

[0470] Test results: Blood test normal

[0471] Generate a medical information form from this information.

[0472] 4. Review and edit the draft document

[0473] The server sends the generated draft document to the user's device. The device displays the draft document, and the user checks the contents and makes edits as necessary. When the user has completed editing, they click the "Publish as final document" button. This request is sent from the device to the server.

[0474] 5. Publication of the Final Document

[0475] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been published.

[0476] This system allows medical professionals to easily and quickly create documents such as medical information reports, and by using a generative AI model, it automates information summarization, which is expected to reduce human error and improve work efficiency.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1: User authentication

[0479] ---

[0480] Input: The user enters authentication information (user ID and password) on the device's login screen.

[0481] How it works: When the user clicks the "Login" button, the device sends these credentials to the server in real time.

[0482] Specific operation: The user enters the user ID "doctor123" and the password "password123" and presses the "Login" button.

[0483] Data processing: The server encrypts the received user ID and password and checks them against the database.

[0484] Output: If authentication is successful, the server starts a user session and sends the dashboard screen to the terminal. If authentication fails, it sends an error message.

[0485] Specific operation: The server searches the authentication information in the database, and if it matches, displays a message such as "Welcome, doctor123" on the user's terminal.

[0486] Step 2: Data extraction

[0487] ---

[0488] Input: The user selects "Create medical information report" on the dashboard and enters the ID of the target patient.

[0489] Specific operation: The user clicks the "Create medical information report" button, enters the patient ID "patient001", and presses the "Search" button.

[0490] Operation: The terminal sends the entered patient ID to the server.

[0491] Data processing: The server accesses the electronic medical record database and searches and extracts data on the target patient, such as medical history, prescription medications, and test results.

[0492] Output: The server temporarily stores the extracted patient data within the server and continues processing.

[0493] Specific operation: The server sends a query to the electronic medical record system, retrieves all information about the patient, and temporarily stores it in memory.

[0494] Step 3: Information Summary

[0495] ---

[0496] Input: Patient data stored in the server.

[0497] Specific operation: The server generates a prompt sentence to send to the generative AI model.

[0498] How it works: The server sends the generated prompt sentence to the generative AI model.

[0499] Data processing: The generative AI model analyzes the prompt text, summarizes information such as medical history, prescription medications, and test results, and generates a draft document.

[0500] Output: The generative AI model returns the generated draft document to the server.

[0501] Example prompt sentence:

[0502] Patient ID: patient001

[0503] Medical History: Diagnosis on January 1, 2023

[0504] Prescription medication list: Aspirin, Metoprolol

[0505] Test results: Blood test normal

[0506] Generate a medical information form from this information.

[0507] Step 4: Review and edit the draft document

[0508] ---

[0509] Input: The draft document returned from the generative AI model.

[0510] Specific operation: The server sends the generated draft document to the user's terminal.

[0511] How it works: The device displays the draft document to the user, who can review and edit it.

[0512] Data processing: After the user has completed editing, they click the "Publish as final document" button to send the final version to the server.

[0513] Output: Edited final draft document.

[0514] Specific actions: The user views the draft document, makes corrections such as adding additional information to the inspection results section, and clicks the "Publish as final document" button.

[0515] Step 5: Issuance of final document

[0516] ---

[0517] Input: The final draft document as edited by the user.

[0518] Specific operation: The terminal sends the finalized document to the server.

[0519] Actions: The server formally stores the final document and records its publication.

[0520] Data processing: After the server has completed saving, it will send a notification to the device.

[0521] Output: Save completion notification and final document.

[0522] Specific operation: The server saves the final document in the database and displays a notification on the terminal stating "Medical information report has been issued successfully."

[0523] In this way, the system reduces the burden on the user and enables efficient document creation.

[0524] (Application example 1)

[0525] 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."

[0526] In modern factories, the creation of manufacturing process and quality control reports still relies heavily on manual labor. This reduces efficiency and increases the risk of human error. It also makes it difficult to quickly share and confirm information, potentially leading to problems in product quality control. To solve this issue and improve overall factory productivity, a system is needed that can automatically summarize manufacturing data and quickly create reports.

[0527] 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.

[0528] In this invention, the server includes means for extracting target data from an electronic database, means for inputting the extracted target data into a generative AI model, means for generating a draft document from the information summarized by the generative AI model, means for presenting the draft document to a user for confirmation and editing, and means for saving and publishing the final confirmed document, thereby enabling the automatic generation and editing of manufacturing data summaries and reports.

[0529] An "electronic database" is a process of systematically storing and managing information in digital form, and is a database system that allows quick access to specific data.

[0530] "Target data" refers to information relating to a specific ID extracted from an electronic database, and is a group of data containing the necessary content depending on the purpose.

[0531] A "generative AI model" is an algorithm or software system that uses artificial intelligence technology to analyze input data and automatically generate summaries and documents.

[0532] A "draft document" is an intermediate document automatically generated by a generative AI model that is later reviewed and edited.

[0533] "Historical data" is information that contains past performance or records of a particular process or operation.

[0534] "Process data" refers to data that includes detailed information and execution details when a specific action or operation is performed.

[0535] "Outcome data" is information that describes the results or outputs achieved as a result of a particular procedure or process.

[0536] This invention proposes a system for automatically generating reports on manufacturing processes and quality control within factories. The system uses a generative AI model to summarize work data and efficiently generate reports.

[0537] First, a user (factory operator) logs in to the system. The user enters their authentication information (user ID and password) and sends it from the terminal to the server. The server compares this authentication information with the information in the database, and if authentication is successful, the user's session is started and a dashboard is displayed on the terminal.

[0538] Next, the user selects data for a specific production line from the dashboard. After the user enters the production line ID, the terminal sends this request to the server. The server accesses an electronic database to search and extract data for the specified production line. This data includes production history, quality data, and maintenance records. This extracted data is temporarily stored on the server.

[0539] The server then inputs the extracted data into a generative AI model, which analyzes the received data, summarizes manufacturing history, quality control data, and maintenance records, and generates a draft report document, which is returned to the server.

[0540] The server then sends the generated draft document to the user's device. The device displays the draft document to the user, who can review the content and make edits as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device then sends this request to the server.

[0541] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0542] The system can efficiently summarize manufacturing data and automatically generate and edit reports, allowing factory operators to reduce the risk of human error and share information quickly.

[0543] As a concrete example, consider a scenario in which a mechanical engineer operator creates a quality control report for a specific production line. The operator logs into the system and selects data for the specific production line. The production history, quality data, and maintenance records for that line are extracted from the database. This data is then input into a generative AI model, which then summarizes it. The generated draft document is displayed on the operator's device, where the operator can review and edit the contents. It is then published as a final document and saved in the system.

[0544] An example prompt for a generative AI model is:

[0545] "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating hours: 8 hours, Maintenance records: normal"

[0546] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0547] Step 1:

[0548] A user logs in to the system using their own terminal. The user enters authentication information (user ID and password) into the terminal's login screen and sends this information to the server. The server performs authentication by comparing it with information in the database, and if authentication is successful, starts a session and displays a dashboard on the terminal. The input is authentication information, and the output is the authentication result and the dashboard screen. The server compares the authentication information with the database and generates session information.

[0549] Step 2:

[0550] The user selects the relevant production line data from the dashboard. The user enters the production line ID and sends the request to the server via the terminal. The server accesses the electronic database to search and extract data for the specified production line. The input is the production line ID and the output is the extracted production data. The server retrieves historical data, quality data, and maintenance records from the database.

[0551] Step 3:

[0552] The server sends the extracted data to the generative AI model. The server passes the specified manufacturing data to the generative AI model and provides a prompt to the model. The generative AI model analyzes the data and generates summarized information as a draft document. An example of this prompt is "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating time: 8 hours, Maintenance record: Normal." The input is the manufacturing data, and the output is the summarized draft document.

[0553] Step 4:

[0554] The server sends the generated draft document to the user's terminal. The user's terminal displays the draft document, allowing the user to check and edit the contents. The terminal displays the draft document in the user's interface, allowing the user to manually edit and add comments. The input is the draft document, and the output is the edited document.

[0555] Step 5:

[0556] The user finishes editing the draft document and clicks the "Publish as final document" button. The terminal sends this request to the server. The server formally saves the edited document and records that it has been published. The server sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published. The input is the edited document and the publishing request, and the output is the final saved document and the notification.

[0557] At each step, the server or device processes and calculates the data to generate the required output. By utilizing a "generative AI model," we have created a system that can efficiently summarize data and generate documents.

[0558] 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.

[0559] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0560] 1. User login

[0561] To access the system, the user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates the user by comparing it with information in a database. If authentication is successful, the server starts a user session and sends a request to display the dashboard on the terminal. The terminal then displays the dashboard screen to the user.

[0562] 2. Extraction of electronic medical record information

[0563] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[0564] 3. Information Summarization Using Generative AI Models

[0565] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[0566] 4. Review and edit your draft

[0567] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[0568] 5. Emotion-Based Regulation

[0569] The emotion engine recognizes the user's emotions and feeds that information back to the generative AI model, which then adjusts the tone and expression of the document appropriately based on the user's emotions. For example, if the user is feeling stressed, the tone of the document can be softened.

[0570] 6. Final confirmation and issuance

[0571] The user reviews the draft document and makes corrections and edits as necessary. The emotion engine continues to monitor the user's emotions during this process and makes readjustments as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device sends this request to the server.

[0572] 7. Publication of the Final Document

[0573] The server officially saves the final document and records that it has been published. The server sends a notification to the terminal that the final document has been saved. The terminal notifies the user that the final document has been successfully published.

[0574] Specific examples

[0575] Consider a scenario in which a doctor is creating a medical report for a patient. The doctor logs into the system on their device and selects to create a medical report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress or fatigue and adjusts the tone and expression of the document appropriately. The final document is then published and saved in the system.

[0576] In this way, the system can significantly reduce doctors' overtime work and efficiently prepare documents. Also, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[0577] The processing flow will be explained below.

[0578] Step 1:

[0579] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0580] Step 2:

[0581] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[0582] Step 3:

[0583] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[0584] Step 4:

[0585] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0586] Step 5:

[0587] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[0588] Step 6:

[0589] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[0590] Step 7:

[0591] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[0592] Step 8:

[0593] The emotion engine recognizes the user's emotions and feeds them back to the generative AI model, which then adjusts the tone and expression of the draft document based on the user's emotions.

[0594] Step 9:

[0595] The user checks the draft document and makes corrections or edits as necessary. The device temporarily saves the user's corrections.

[0596] Step 10:

[0597] The user completes the edits and clicks the "Publish as final document" button. The device sends this request to the server.

[0598] Step 11:

[0599] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[0600] Step 12:

[0601] The terminal notifies the user that the final document has been successfully published.

[0602] Example 2

[0603] 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."

[0604] In the medical field, efficient and accurate preparation of medical information reports is required, but conventional systems require doctors to spend a huge amount of time manually preparing documents. This increases doctors' overtime work and stress. Furthermore, the tone and expression of documents must also be adjusted manually, placing a burden on doctors. Furthermore, conventional systems do not take into account the doctor's emotional state when preparing documents, resulting in the problem of document quality being affected by the doctor's emotional state.

[0605] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for extracting patient data from the electronic medical record, means for inputting the extracted patient data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user and analyzing the user's emotions using an emotion recognition engine, means for adjusting the tone and expression of the draft document based on the analysis results, means for user confirmation and editing, and means for saving and publishing the final confirmed document. This reduces the burden on doctors and enables efficient and accurate creation of medical information reports. Furthermore, document creation that takes the doctor's emotional state into consideration is realized, improving the quality of the document.

[0606] An "electronic medical record" is a system that digitally records and manages patient medical information, prescription medications, test results, etc.

[0607] "Patient data" refers to information such as medical history, prescribed medications, and test results recorded in electronic medical records.

[0608] A "generative AI model" is an artificial intelligence model that analyzes input data, summarizes information, and generates text.

[0609] A "draft document" is an unfinalized document in which information summarized by a generative AI model is organized into sentence form.

[0610] An "emotion recognition engine" is an engine that has the ability to analyze data such as a user's facial expressions, voice tone, and keystroke patterns to identify the user's emotions.

[0611] "Tone and voice adjustment" is the process of changing the tone and language of a document depending on the user's emotional state.

[0612] A "session" is a unit in which the server maintains the user's logged-in status and manages the entire process of the user's use of the system.

[0613] A "dashboard" is a screen that aggregates the information and functions necessary for system users to operate the system.

[0614] "Storage and publication" refers to the process of formally recording the final reviewed document in a database and sharing it with other systems and users as needed.

[0615] MODE FOR CARRYING OUT THE INVENTION

[0616] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0617] User login

[0618] First, a user (doctor) logs in to the system using a terminal. The terminal displays a login screen, and the user enters their user ID and password. The terminal sends this authentication information to the server, which then authenticates the user by checking it against the user information in its database. If authentication is successful, the server starts a session and sends a request to the terminal to display the dashboard. The terminal renders the dashboard screen and displays it to the user.

[0619] Extraction of electronic medical record information

[0620] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0621] Information summarization using generative AI models

[0622] The server formats the extracted patient data and generates a prompt to send to the generative AI model, which analyzes the received patient data and summarizes the medical history, prescribed medications, test results, etc. to generate a draft medical information report document. The generated draft document is returned to the server.

[0623] Draft review and emotion recognition

[0624] The server then sends the generated draft document to the user's device, which then renders and displays it to the user. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, keystroke patterns, etc. to recognize the user's emotions.

[0625] Emotion-Based Adjustment

[0626] The emotion recognition engine feeds the analysis results back to the generative AI model, which then uses the feedback to adjust the tone and expression of the draft document appropriately. For example, if the user is feeling stressed, the tone of the document can be softened.

[0627] Final confirmation and issuance

[0628] The user reviews the draft document and manually corrects and edits it as needed. The emotion recognition engine continues to monitor the user's emotions during this process and readjusts the document as needed. Once editing is complete, the user clicks the "Publish as Final Document" button. The device sends this request to the server.

[0629] Final document retention and notification

[0630] The server officially saves the final document and records that it has been published. The server then sends a notification of the completion of saving to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0631] Specific examples

[0632] Consider a scenario in which a doctor is creating a medical record for a patient. The doctor logs in to the system on a device and selects to create a medical record for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress and fatigue and adjusts the tone and expression appropriately. The document is then published as a final document and saved in the system. In this way, this system significantly reduces overtime work for doctors and enables more efficient document creation. Furthermore, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[0633] Prompt Sentence Examples

[0634] Please draft a medical information form using the following patient data: Medical history: ____, Prescription medications: ____, Test results: ____.

[0635] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0636] Step 1:

[0637] User login

[0638] The user enters their user ID and password, and the device sends this authentication information to the server. The input is the user ID and password, and the output is the authentication result. The server compares the authentication information with the user information in the database, and if authentication is successful, the session begins. Specifically, the server sends a successful authentication response to the device, and the device displays the dashboard.

[0639] Step 2:

[0640] Extraction of electronic medical record information

[0641] The user selects "Create a medical information report" on the dashboard, enters the patient ID, and performs a search. The terminal sends this request to the server. The input is the patient ID, and the output is the patient's medical record information. The server accesses the electronic medical record database, searches and extracts the medical record information of the specified patient, and temporarily stores this information. Specifically, it executes the request "GET / patient-info?patient_id=patient456" and retrieves the search results.

[0642] Step 3:

[0643] Information summarization using generative AI models

[0644] The server sends the extracted patient data to the generative AI model as a prompt. The input is the patient data, and the output is a summarized draft document. The generative AI model analyzes the received data and generates a draft document by summarizing information such as medical history, prescribed medications, and test results. Specifically, the prompt "Please create a draft medical information report using the following patient data. Medical history: XX, prescribed medications: △△, test results: □□" is input into the generative AI model, and the summary result is obtained.

[0645] Step 4:

[0646] Draft document review and emotion recognition

[0647] The server sends the generated draft document to the terminal, which then displays it to the user. The input is the draft document, and the output is the user's emotional data. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize their emotions. Specifically, it analyzes input data from the webcam and microphone to obtain emotion recognition results.

[0648] Step 5:

[0649] Emotion-Based Adjustment

[0650] The emotion recognition engine feeds the analysis results back to the generative AI model. The input is emotional data, and the output is an adjusted draft document. The generative AI model uses this feedback to appropriately adjust the tone and expression of the draft document. Specifically, for users who are feeling stressed, the model will soften the tone of the document.

[0651] Step 6:

[0652] Final confirmation and issuance

[0653] The user reviews the draft document and makes corrections as necessary. The input is the draft document and the user's corrections, and the output is the final document. The emotion recognition engine monitors the user's emotions during the final confirmation and readjusts them as necessary. When the user clicks the "Publish as Final Document" button, the terminal sends the request to the server. Specifically, after editing, it sends a "POST / finalize-document" request.

[0654] Step 7:

[0655] Final document retention and notification

[0656] The server officially saves the final document and records that publication is complete. The input is the final document, and the output is a notification that saving is complete. The server sends a notification of saving completion to the terminal, and the terminal notifies the user. Specifically, it executes a database query called "INSERT INTO final_documents (final document data)" and displays a message to the user that saving is complete.

[0657] (Application example 2)

[0658] 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."

[0659] In traditional medical settings and manufacturing plants, generative AI models are being used to improve the efficiency of document creation and robot operation, but no systems exist that take user emotions into account. As a result, if a user is stressed or fatigued, the quality and safety of the output may decline. In manufacturing plants in particular, where the emotions of operators are directly linked to work safety, a system that recognizes and adapts to their emotions is needed.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from the electronic medical record, means for inputting the extracted data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user for confirmation and editing, means for recognizing the user's emotions using emotion recognition technology, means for providing feedback to the generative AI model based on the recognized emotions and adjusting the tone and expression of the document, and means for saving and publishing the final confirmed document. This enables efficient document creation and safe operation that reflects the user's emotional state.

[0661] An "electronic medical record" is a system that electronically manages a patient's medical information.

[0662] "Data identification information" is information for uniquely identifying specific data.

[0663] An "information management system" is a system for storing, managing, retrieving, and processing data.

[0664] A "generative AI model" is an artificial intelligence model that generates or summarizes information based on given data.

[0665] A "draft document" is a temporary document intended for editing by users before final review.

[0666] "Emotion recognition technology" is a technology that detects emotions by analyzing a user's facial expressions, voice, keystroke patterns, etc.

[0667] "Feedback" is the action of making corrections to models and processes based on information obtained by the system.

[0668] "Tone" refers to the overall impression or mood of a document or statement.

[0669] A "representation" is a method or format for conveying data or information.

[0670] As an embodiment of the present invention, the following system can be constructed.

[0671] Overall system overview

[0672] The system includes the following main elements:

[0673] Server: A central system that stores, processes, and manages data.

[0674] Device: The device that a user accesses and operates (e.g., computer, smartphone, smart glasses, head-mounted display, etc.).

[0675] Robot: A piece of equipment on a manufacturing line that performs tasks according to control instructions.

[0676] Program Description

[0677] 1. Extract data from electronic medical records

[0678] The server accesses the electronic medical record database and extracts patient data, which is processed based on the data identification information.

[0679] 2. Input the extracted data into a generative AI model

[0680] The server sends the extracted patient data to a generative AI model, which then issues instructions for generating summaries and optimized information. The generative AI model summarizes the patient's medical history, prescription medications, test results, etc., and generates a draft document.

[0681] 3. Present the draft document to the user

[0682] The terminal presents the generated draft document to the user and provides an interface for reviewing and editing.

[0683] 4. Recognize user emotions using emotion recognition technology

[0684] The device's built-in emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions in real time.

[0685] 5. Feedback to generative AI models based on recognized emotions

[0686] The server then feeds the recognized user emotion back into the regenerative AI model, adjusting the tone and expression of the document. For example, if the user is feeling stressed, the document's expression will be softened.

[0687] 6. Save and publish the finalized document

[0688] The server officially stores the final document that has been reviewed and edited by the user and issues it as necessary. The user can confirm through their terminal that the final document has been successfully issued.

[0689] Hardware and software used

[0690] Server: Database management systems (e.g., MySQL, PostgreSQL) and web servers (e.g., Apache, NGINX).

[0691] Terminal: Facial recognition software (e.g., OpenCV), voice analysis software (e.g., TensorFlow).

[0692] Robot: Robot control system (e.g. ROS - Robot Operating System).

[0693] Specific examples

[0694] As a concrete example, consider the following scenario:

[0695] 1. An operator logs in to the system and instructs the robot to perform packaging with task ID "task_123." The server inputs the corresponding task information into the generative AI model and generates the optimal operation sequence.

[0696] 2. The generated operation sequence is displayed on the terminal, and the operator's emotions are detected by an emotion recognition engine. If the operator is feeling stressed, the system reconsiders the operation sequence to prioritize safety.

[0697] 3. The adjusted operation sequence is finally confirmed, and the robot begins its work. The operator checks the results via a terminal and confirms that the work has been completed safely.

[0698] Prompt Sentence Examples

[0699] prompt:

[0700] "Generate the optimal operation sequence for the robot packaging task with task ID 'task_123'."

[0701] Input data:

[0702] "Task: Packaging, Operational Steps: Step 1: Collect items, Step 2: Place items, Step 3: Package items, Step 4: Inspect packaging, Step 5: Remove finished product."

[0703] This system enables efficient document creation and safe operation that reflects the user's emotional state.

[0704] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0705] Specific processing steps of the program

[0706] Step 1:

[0707] User login

[0708] The user logs into the system using a terminal. The terminal displays a login screen and asks the user to enter a user ID and password. The entered authentication information is sent from the terminal to the server. The server verifies the information against the database and, if successful, starts a user session. A session ID is generated and a request to display the dashboard is sent to the terminal.

[0709] Input: User ID, Password

[0710] Output: Session ID, Dashboard display

[0711] Step 2:

[0712] Get task information

[0713] The user selects a specific task (e.g., packaging) from the dashboard and searches by entering the task ID. The device sends this request to the server, which accesses the database to retrieve the task information, including the operation steps and required resources.

[0714] Input: Task ID

[0715] Output: Task information

[0716] Step 3:

[0717] Optimizing task information

[0718] The server inputs the acquired task information into the generative AI model. At this time, the AI ​​model is also provided with a prompt. The generative AI model generates an optimal operation sequence based on the task information. The generated operation sequence is returned to the server.

[0719] Input: Task information, prompt

[0720] Output: Optimized operation sequence

[0721] Step 4:

[0722] Optimized operation sequence presentation

[0723] The server sends the generated optimized operation sequence to the user's terminal, which displays it to the user, who can then review the operation sequence and make any necessary corrections.

[0724] Input: Optimized operation sequence

[0725] Output: what is displayed to the user

[0726] Step 5:

[0727] emotion recognition

[0728] The emotion engine on the device analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotional state in real time. The recognized emotion information is then sent to the server.

[0729] Input: facial expression data, voice data, keystroke data

[0730] Output: Emotional information

[0731] Step 6:

[0732] Emotion-based feedback

[0733] The server then feeds the recognized emotion information back to the generative AI model and adjusts the tone and expression of the document. For example, if the user is feeling stressed, the tone of the document will be softened. The adjusted document is then sent back to the server.

[0734] Input: Emotion information

[0735] Output: Adjusted document

[0736] Step 7:

[0737] Final confirmation and document storage

[0738] The user finalizes the adjusted document and makes corrections as necessary. When the user clicks the final confirmation button, the terminal sends this request to the server. The server officially saves and publishes the final document. A notification that the final document has been saved is sent to the terminal and displayed to the user.

[0739] Input: Final confirmation request

[0740] Output: Save final document, display notification

[0741] This series of processing steps enables efficient document creation and safe operation that reflects the user's feelings.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] [Third embodiment]

[0746] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0747] 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.

[0748] 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).

[0749] 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.

[0750] 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.

[0751] 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).

[0752] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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."

[0758] This invention is a system that uses a generative AI model to support document creation in medical settings. Specific embodiments of this system are described below.

[0759] 1. User login

[0760] To access the system, a user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates it by checking it against information in a database. If authentication is successful, the server starts the user's session and displays the dashboard on the terminal.

[0761] 2. Extraction of electronic medical record information

[0762] The user selects "Create a medical information report" from the dashboard and enters the target patient's ID. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[0763] 3. Information Summarization Using Generative AI Models

[0764] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[0765] 4. Review and edit your draft

[0766] The server sends the generated draft document to the user's device. The device displays the draft document to the user, who checks the contents and makes edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The device then sends this request to the server.

[0767] 5. Publication of the Final Document

[0768] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0769] Specific examples

[0770] Take the example of a scenario in which a doctor is creating a medical information report for a patient. The doctor logs into the system on a terminal and selects to create a medical information report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is input into a generative AI model, which then summarizes it. The generated draft document is displayed on the doctor's terminal, where the doctor can review and edit the contents. It is then issued as the final document and saved in the system.

[0771] In this way, the system significantly reduces doctors' overtime work and enables efficient document preparation.

[0772] The processing flow will be explained below.

[0773] Step 1:

[0774] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0775] Step 2:

[0776] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[0777] Step 3:

[0778] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[0779] Step 4:

[0780] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0781] Step 5:

[0782] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[0783] Step 6:

[0784] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[0785] Step 7:

[0786] The server sends the generated draft document to the user's terminal, and the terminal displays the draft document to the user.

[0787] Step 8:

[0788] The user checks the draft document and makes corrections and edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The terminal sends this request to the server.

[0789] Step 9:

[0790] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[0791] Step 10:

[0792] The terminal notifies the user that the final document has been successfully published.

[0793] Example 1

[0794] 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."

[0795] Traditional document creation processes in medical settings require time and effort from medical professionals, especially when creating documents such as medical information reports. Manual input and verification can lead to human error. There is a need for a system that can use generative AI models to summarize information from electronic medical records and create documents efficiently. Furthermore, it is necessary to reduce the burden on medical professionals by automating the processes of user authentication and data extraction.

[0796] 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.

[0797] In this invention, the server includes a means for a user to input authentication information and send it to the server, a means for the server to compare the authentication information with a database and perform authentication, a means for extracting patient data from the electronic medical record, a means for inputting the extracted patient data into a generative AI model, a means for generating information summarized by the generative AI model as a draft document, a means for presenting the draft document to the user for confirmation and editing, and a means for saving and issuing the final confirmed document. This enables medical professionals to create documents easily and quickly, reducing human error and improving work efficiency.

[0798] "User" refers to a healthcare professional who accesses and operates the system.

[0799] "Authentication information" refers to information such as the user ID and password that a user enters when logging in to a system.

[0800] "Server" refers to a computer device that processes data and performs authentication for the entire system.

[0801] "Database" refers to the data storage system where patient medical information and user authentication information is stored.

[0802] An "electronic medical record" refers to a digital system that manages medical information such as a patient's medical history, prescription medications, and test results.

[0803] "Patient data" refers to information stored in electronic medical records, such as each patient's medical history, prescribed medications, and test results.

[0804] A "generative AI model" refers to an artificial intelligence model that analyzes input data and performs summaries and text generation.

[0805] "Draft Document" refers to a draft document generated based on information summarized by a generative AI model.

[0806] "Terminal" means the computer or mobile device used by a User to access the System.

[0807] A "user session" refers to a series of communication states for operating a system after a user has been authenticated.

[0808] "Dashboard" refers to the interface through which users access the main functions of the system.

[0809] "Issuance" refers to the formal storage and recording of the final verified document in the system.

[0810] A "prompt" is an instructional sentence containing necessary information that is used as input to a generative AI model.

[0811] This invention relates to a system that uses generative AI models to support document creation in medical settings, including a series of processes for efficiently performing user authentication, data extraction, information summarization, document generation, and final document issuance.

[0812] System configuration and operation

[0813] This system is configured using the following hardware and software:

[0814] Hardware

[0815] Server: Manages the system's data processing, authentication, database access, and communication with the generative AI model.

[0816] Terminal: A computer or mobile device through which a user accesses the system.

[0817] software

[0818] Electronic medical record system: A digital system that manages information such as a patient's medical history, prescription medications, and test results (e.g., a general-purpose electronic medical record system).

[0819] Generative AI model: An artificial intelligence model that analyzes input data and performs summarization or text generation (e.g., GPT-3).

[0820] Program processing

[0821] 1. User Authentication

[0822] First, the user enters authentication information (user ID and password) on the login screen of the device. The device sends this authentication information to the server, which checks it against the database. If authentication is successful, the user session begins and the dashboard screen is displayed on the device.

[0823] 2. Data extraction

[0824] The user selects to create a medical information report from the dashboard and enters the target patient's ID. This request is sent from the device to the server. The server accesses the electronic medical record system, searches and extracts the specified patient's data (medical history, prescription medications, test results, etc.), and temporarily stores it on the server.

[0825] 3. Information Summary

[0826] The server generates a prompt sentence to be input to the generative AI model based on the extracted patient data. This prompt sentence is sent to the generative AI model, which analyzes and summarizes the data and generates a draft document of the medical information report. This draft document is then sent back to the server.

[0827] Prompt Sentence Examples

[0828] Patient ID: patient001

[0829] Medical History: Diagnosis on January 1, 2023

[0830] Prescription medication list: Aspirin, Metoprolol

[0831] Test results: Blood test normal

[0832] Generate a medical information form from this information.

[0833] 4. Review and edit the draft document

[0834] The server sends the generated draft document to the user's device. The device displays the draft document, and the user checks the contents and makes edits as necessary. When the user has completed editing, they click the "Publish as final document" button. This request is sent from the device to the server.

[0835] 5. Publication of the Final Document

[0836] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been published.

[0837] This system allows medical professionals to easily and quickly create documents such as medical information reports, and by using a generative AI model, it automates information summarization, which is expected to reduce human error and improve work efficiency.

[0838] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0839] Step 1: User authentication

[0840] ---

[0841] Input: The user enters authentication information (user ID and password) on the device's login screen.

[0842] How it works: When the user clicks the "Login" button, the device sends these credentials to the server in real time.

[0843] Specific operation: The user enters the user ID "doctor123" and the password "password123" and presses the "Login" button.

[0844] Data processing: The server encrypts the received user ID and password and checks them against the database.

[0845] Output: If authentication is successful, the server starts a user session and sends the dashboard screen to the terminal. If authentication fails, it sends an error message.

[0846] Specific operation: The server searches the authentication information in the database, and if it matches, displays a message such as "Welcome, doctor123" on the user's terminal.

[0847] Step 2: Data extraction

[0848] ---

[0849] Input: The user selects "Create medical information report" on the dashboard and enters the ID of the target patient.

[0850] Specific operation: The user clicks the "Create medical information report" button, enters the patient ID "patient001", and presses the "Search" button.

[0851] Operation: The terminal sends the entered patient ID to the server.

[0852] Data processing: The server accesses the electronic medical record database and searches and extracts data on the target patient, such as medical history, prescription medications, and test results.

[0853] Output: The server temporarily stores the extracted patient data within the server and continues processing.

[0854] Specific operation: The server sends a query to the electronic medical record system, retrieves all information about the patient, and temporarily stores it in memory.

[0855] Step 3: Information Summary

[0856] ---

[0857] Input: Patient data stored in the server.

[0858] Specific operation: The server generates a prompt sentence to send to the generative AI model.

[0859] How it works: The server sends the generated prompt sentence to the generative AI model.

[0860] Data processing: The generative AI model analyzes the prompt text, summarizes information such as medical history, prescription medications, and test results, and generates a draft document.

[0861] Output: The generative AI model returns the generated draft document to the server.

[0862] Example prompt sentence:

[0863] Patient ID: patient001

[0864] Medical History: Diagnosis on January 1, 2023

[0865] Prescription medication list: Aspirin, Metoprolol

[0866] Test results: Blood test normal

[0867] Generate a medical information form from this information.

[0868] Step 4: Review and edit the draft document

[0869] ---

[0870] Input: The draft document returned from the generative AI model.

[0871] Specific operation: The server sends the generated draft document to the user's terminal.

[0872] How it works: The device displays the draft document to the user, who can review and edit it.

[0873] Data processing: After the user has completed editing, they click the "Publish as final document" button to send the final version to the server.

[0874] Output: Edited final draft document.

[0875] Specific actions: The user views the draft document, makes corrections such as adding additional information to the inspection results section, and clicks the "Publish as final document" button.

[0876] Step 5: Issuance of final document

[0877] ---

[0878] Input: The final draft document as edited by the user.

[0879] Specific operation: The terminal sends the finalized document to the server.

[0880] Actions: The server formally stores the final document and records its publication.

[0881] Data processing: After the server has completed saving, it will send a notification to the device.

[0882] Output: Save completion notification and final document.

[0883] Specific operation: The server saves the final document in the database and displays a notification on the terminal stating "Medical information report has been issued successfully."

[0884] In this way, the system reduces the burden on the user and enables efficient document creation.

[0885] (Application example 1)

[0886] 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."

[0887] In modern factories, the creation of manufacturing process and quality control reports still relies heavily on manual labor. This reduces efficiency and increases the risk of human error. It also makes it difficult to quickly share and confirm information, potentially leading to problems in product quality control. To solve this issue and improve overall factory productivity, a system is needed that can automatically summarize manufacturing data and quickly create reports.

[0888] 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.

[0889] In this invention, the server includes means for extracting target data from an electronic database, means for inputting the extracted target data into a generative AI model, means for generating a draft document from the information summarized by the generative AI model, means for presenting the draft document to a user for confirmation and editing, and means for saving and publishing the final confirmed document, thereby enabling the automatic generation and editing of manufacturing data summaries and reports.

[0890] An "electronic database" is a process of systematically storing and managing information in digital form, and is a database system that allows quick access to specific data.

[0891] "Target data" refers to information relating to a specific ID extracted from an electronic database, and is a group of data containing the necessary content depending on the purpose.

[0892] A "generative AI model" is an algorithm or software system that uses artificial intelligence technology to analyze input data and automatically generate summaries and documents.

[0893] A "draft document" is an intermediate document automatically generated by a generative AI model that is later reviewed and edited.

[0894] "Historical data" is information that contains past performance or records of a particular process or operation.

[0895] "Process data" refers to data that includes detailed information and execution details when a specific action or operation is performed.

[0896] "Outcome data" is information that describes the results or outputs achieved as a result of a particular procedure or process.

[0897] This invention proposes a system for automatically generating reports on manufacturing processes and quality control within factories. The system uses a generative AI model to summarize work data and efficiently generate reports.

[0898] First, a user (factory operator) logs in to the system. The user enters their authentication information (user ID and password) and sends it from the terminal to the server. The server compares this authentication information with the information in the database, and if authentication is successful, the user's session is started and a dashboard is displayed on the terminal.

[0899] Next, the user selects data for a specific production line from the dashboard. After the user enters the production line ID, the terminal sends this request to the server. The server accesses an electronic database to search and extract data for the specified production line. This data includes production history, quality data, and maintenance records. This extracted data is temporarily stored on the server.

[0900] The server then inputs the extracted data into a generative AI model, which analyzes the received data, summarizes manufacturing history, quality control data, and maintenance records, and generates a draft report document, which is returned to the server.

[0901] The server then sends the generated draft document to the user's device. The device displays the draft document to the user, who can review the content and make edits as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device then sends this request to the server.

[0902] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0903] The system can efficiently summarize manufacturing data and automatically generate and edit reports, allowing factory operators to reduce the risk of human error and share information quickly.

[0904] As a concrete example, consider a scenario in which a mechanical engineer operator creates a quality control report for a specific production line. The operator logs into the system and selects data for the specific production line. The production history, quality data, and maintenance records for that line are extracted from the database. This data is then input into a generative AI model, which then summarizes it. The generated draft document is displayed on the operator's device, where the operator can review and edit the contents. It is then published as a final document and saved in the system.

[0905] An example prompt for a generative AI model is:

[0906] "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating hours: 8 hours, Maintenance records: normal"

[0907] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0908] Step 1:

[0909] A user logs in to the system using their own terminal. The user enters authentication information (user ID and password) into the terminal's login screen and sends this information to the server. The server performs authentication by comparing it with information in the database, and if authentication is successful, starts a session and displays a dashboard on the terminal. The input is authentication information, and the output is the authentication result and the dashboard screen. The server compares the authentication information with the database and generates session information.

[0910] Step 2:

[0911] The user selects the relevant production line data from the dashboard. The user enters the production line ID and sends the request to the server via the terminal. The server accesses the electronic database to search and extract data for the specified production line. The input is the production line ID and the output is the extracted production data. The server retrieves historical data, quality data, and maintenance records from the database.

[0912] Step 3:

[0913] The server sends the extracted data to the generative AI model. The server passes the specified manufacturing data to the generative AI model and provides a prompt to the model. The generative AI model analyzes the data and generates summarized information as a draft document. An example of this prompt is "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating time: 8 hours, Maintenance record: Normal." The input is the manufacturing data, and the output is the summarized draft document.

[0914] Step 4:

[0915] The server sends the generated draft document to the user's terminal. The user's terminal displays the draft document, allowing the user to check and edit the contents. The terminal displays the draft document in the user's interface, allowing the user to manually edit and add comments. The input is the draft document, and the output is the edited document.

[0916] Step 5:

[0917] The user finishes editing the draft document and clicks the "Publish as final document" button. The terminal sends this request to the server. The server formally saves the edited document and records that it has been published. The server sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published. The input is the edited document and the publishing request, and the output is the final saved document and the notification.

[0918] At each step, the server or device processes and calculates the data to generate the required output. By utilizing a "generative AI model," we have created a system that can efficiently summarize data and generate documents.

[0919] 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.

[0920] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0921] 1. User login

[0922] To access the system, the user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates the user by comparing it with information in a database. If authentication is successful, the server starts a user session and sends a request to display the dashboard on the terminal. The terminal then displays the dashboard screen to the user.

[0923] 2. Extraction of electronic medical record information

[0924] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[0925] 3. Information Summarization Using Generative AI Models

[0926] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[0927] 4. Review and edit your draft

[0928] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[0929] 5. Emotion-Based Regulation

[0930] The emotion engine recognizes the user's emotions and feeds that information back to the generative AI model, which then adjusts the tone and expression of the document appropriately based on the user's emotions. For example, if the user is feeling stressed, the tone of the document can be softened.

[0931] 6. Final confirmation and issuance

[0932] The user reviews the draft document and makes corrections and edits as necessary. The emotion engine continues to monitor the user's emotions during this process and makes readjustments as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device sends this request to the server.

[0933] 7. Publication of the Final Document

[0934] The server officially saves the final document and records that it has been published. The server sends a notification to the terminal that the final document has been saved. The terminal notifies the user that the final document has been successfully published.

[0935] Specific examples

[0936] Consider a scenario in which a doctor is creating a medical report for a patient. The doctor logs into the system on their device and selects to create a medical report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress or fatigue and adjusts the tone and expression of the document appropriately. The final document is then published and saved in the system.

[0937] In this way, the system can significantly reduce doctors' overtime work and efficiently prepare documents. Also, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[0938] The processing flow will be explained below.

[0939] Step 1:

[0940] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0941] Step 2:

[0942] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[0943] Step 3:

[0944] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[0945] Step 4:

[0946] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0947] Step 5:

[0948] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[0949] Step 6:

[0950] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[0951] Step 7:

[0952] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[0953] Step 8:

[0954] The emotion engine recognizes the user's emotions and feeds them back to the generative AI model, which then adjusts the tone and expression of the draft document based on the user's emotions.

[0955] Step 9:

[0956] The user checks the draft document and makes corrections or edits as necessary. The device temporarily saves the user's corrections.

[0957] Step 10:

[0958] The user completes the edits and clicks the "Publish as final document" button. The device sends this request to the server.

[0959] Step 11:

[0960] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[0961] Step 12:

[0962] The terminal notifies the user that the final document has been successfully published.

[0963] Example 2

[0964] 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."

[0965] In the medical field, efficient and accurate preparation of medical information reports is required, but conventional systems require doctors to spend a huge amount of time manually preparing documents. This increases doctors' overtime work and stress. Furthermore, the tone and expression of documents must also be adjusted manually, placing a burden on doctors. Furthermore, conventional systems do not take into account the doctor's emotional state when preparing documents, resulting in the problem of document quality being affected by the doctor's emotional state.

[0966] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for extracting patient data from the electronic medical record, means for inputting the extracted patient data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user and analyzing the user's emotions using an emotion recognition engine, means for adjusting the tone and expression of the draft document based on the analysis results, means for user confirmation and editing, and means for saving and publishing the final confirmed document. This reduces the burden on doctors and enables efficient and accurate creation of medical information reports. Furthermore, document creation that takes the doctor's emotional state into consideration is realized, improving the quality of the document.

[0967] An "electronic medical record" is a system that digitally records and manages patient medical information, prescription medications, test results, etc.

[0968] "Patient data" refers to information such as medical history, prescribed medications, and test results recorded in electronic medical records.

[0969] A "generative AI model" is an artificial intelligence model that analyzes input data, summarizes information, and generates text.

[0970] A "draft document" is an unfinalized document in which information summarized by a generative AI model is organized into sentence form.

[0971] An "emotion recognition engine" is an engine that has the ability to analyze data such as a user's facial expressions, voice tone, and keystroke patterns to identify the user's emotions.

[0972] "Tone and voice adjustment" is the process of changing the tone and language of a document depending on the user's emotional state.

[0973] A "session" is a unit in which the server maintains the user's logged-in status and manages the entire process of the user's use of the system.

[0974] A "dashboard" is a screen that aggregates the information and functions necessary for system users to operate the system.

[0975] "Storage and publication" refers to the process of formally recording the final reviewed document in a database and sharing it with other systems and users as needed.

[0976] MODE FOR CARRYING OUT THE INVENTION

[0977] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0978] User login

[0979] First, a user (doctor) logs in to the system using a terminal. The terminal displays a login screen, and the user enters their user ID and password. The terminal sends this authentication information to the server, which then authenticates the user by checking it against the user information in its database. If authentication is successful, the server starts a session and sends a request to the terminal to display the dashboard. The terminal renders the dashboard screen and displays it to the user.

[0980] Extraction of electronic medical record information

[0981] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[0982] Information summarization using generative AI models

[0983] The server formats the extracted patient data and generates a prompt to send to the generative AI model, which analyzes the received patient data and summarizes the medical history, prescribed medications, test results, etc. to generate a draft medical information report document. The generated draft document is returned to the server.

[0984] Draft review and emotion recognition

[0985] The server then sends the generated draft document to the user's device, which then renders and displays it to the user. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, keystroke patterns, etc. to recognize the user's emotions.

[0986] Emotion-Based Adjustment

[0987] The emotion recognition engine feeds the analysis results back to the generative AI model, which then uses the feedback to adjust the tone and expression of the draft document appropriately. For example, if the user is feeling stressed, the tone of the document can be softened.

[0988] Final confirmation and issuance

[0989] The user reviews the draft document and manually corrects and edits it as needed. The emotion recognition engine continues to monitor the user's emotions during this process and readjusts the document as needed. Once editing is complete, the user clicks the "Publish as Final Document" button. The device sends this request to the server.

[0990] Final document retention and notification

[0991] The server officially saves the final document and records that it has been published. The server then sends a notification of the completion of saving to the terminal, and the terminal notifies the user that the final document has been successfully published.

[0992] Specific examples

[0993] Consider a scenario in which a doctor is creating a medical record for a patient. The doctor logs in to the system on a device and selects to create a medical record for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress and fatigue and adjusts the tone and expression appropriately. The document is then published as a final document and saved in the system. In this way, this system significantly reduces overtime work for doctors and enables more efficient document creation. Furthermore, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[0994] Prompt Sentence Examples

[0995] Please draft a medical information form using the following patient data: Medical history: ____, Prescription medications: ____, Test results: ____.

[0996] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0997] Step 1:

[0998] User login

[0999] The user enters their user ID and password, and the device sends this authentication information to the server. The input is the user ID and password, and the output is the authentication result. The server compares the authentication information with the user information in the database, and if authentication is successful, the session begins. Specifically, the server sends a successful authentication response to the device, and the device displays the dashboard.

[1000] Step 2:

[1001] Extraction of electronic medical record information

[1002] The user selects "Create a medical information report" on the dashboard, enters the patient ID, and performs a search. The terminal sends this request to the server. The input is the patient ID, and the output is the patient's medical record information. The server accesses the electronic medical record database, searches and extracts the medical record information of the specified patient, and temporarily stores this information. Specifically, it executes the request "GET / patient-info?patient_id=patient456" and retrieves the search results.

[1003] Step 3:

[1004] Information summarization using generative AI models

[1005] The server sends the extracted patient data to the generative AI model as a prompt. The input is the patient data, and the output is a summarized draft document. The generative AI model analyzes the received data and generates a draft document by summarizing information such as medical history, prescribed medications, and test results. Specifically, the prompt "Please create a draft medical information report using the following patient data. Medical history: XX, prescribed medications: △△, test results: □□" is input into the generative AI model, and the summary result is obtained.

[1006] Step 4:

[1007] Draft document review and emotion recognition

[1008] The server sends the generated draft document to the terminal, which then displays it to the user. The input is the draft document, and the output is the user's emotional data. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize their emotions. Specifically, it analyzes input data from the webcam and microphone to obtain emotion recognition results.

[1009] Step 5:

[1010] Emotion-Based Adjustment

[1011] The emotion recognition engine feeds the analysis results back to the generative AI model. The input is emotional data, and the output is an adjusted draft document. The generative AI model uses this feedback to appropriately adjust the tone and expression of the draft document. Specifically, for users who are feeling stressed, the model will soften the tone of the document.

[1012] Step 6:

[1013] Final confirmation and issuance

[1014] The user reviews the draft document and makes corrections as necessary. The input is the draft document and the user's corrections, and the output is the final document. The emotion recognition engine monitors the user's emotions during the final confirmation and readjusts them as necessary. When the user clicks the "Publish as Final Document" button, the terminal sends the request to the server. Specifically, after editing, it sends a "POST / finalize-document" request.

[1015] Step 7:

[1016] Final document retention and notification

[1017] The server officially saves the final document and records that publication is complete. The input is the final document, and the output is a notification that saving is complete. The server sends a notification of saving completion to the terminal, and the terminal notifies the user. Specifically, it executes a database query called "INSERT INTO final_documents (final document data)" and displays a message to the user that saving is complete.

[1018] (Application example 2)

[1019] 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."

[1020] In traditional medical settings and manufacturing plants, generative AI models are being used to improve the efficiency of document creation and robot operation, but no systems exist that take user emotions into account. As a result, if a user is stressed or fatigued, the quality and safety of the output may decline. In manufacturing plants in particular, where the emotions of operators are directly linked to work safety, a system that recognizes and adapts to their emotions is needed.

[1021] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from the electronic medical record, means for inputting the extracted data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user for confirmation and editing, means for recognizing the user's emotions using emotion recognition technology, means for providing feedback to the generative AI model based on the recognized emotions and adjusting the tone and expression of the document, and means for saving and publishing the final confirmed document. This enables efficient document creation and safe operation that reflects the user's emotional state.

[1022] An "electronic medical record" is a system that electronically manages a patient's medical information.

[1023] "Data identification information" is information for uniquely identifying specific data.

[1024] An "information management system" is a system for storing, managing, retrieving, and processing data.

[1025] A "generative AI model" is an artificial intelligence model that generates or summarizes information based on given data.

[1026] A "draft document" is a temporary document intended for editing by users before final review.

[1027] "Emotion recognition technology" is a technology that detects emotions by analyzing a user's facial expressions, voice, keystroke patterns, etc.

[1028] "Feedback" is the action of making corrections to models and processes based on information obtained by the system.

[1029] "Tone" refers to the overall impression or mood of a document or statement.

[1030] A "representation" is a method or format for conveying data or information.

[1031] As an embodiment of the present invention, the following system can be constructed.

[1032] Overall system overview

[1033] The system includes the following main elements:

[1034] Server: A central system that stores, processes, and manages data.

[1035] Device: The device that a user accesses and operates (e.g., computer, smartphone, smart glasses, head-mounted display, etc.).

[1036] Robot: A piece of equipment on a manufacturing line that performs tasks according to control instructions.

[1037] Program Description

[1038] 1. Extract data from electronic medical records

[1039] The server accesses the electronic medical record database and extracts patient data, which is processed based on the data identification information.

[1040] 2. Input the extracted data into a generative AI model

[1041] The server sends the extracted patient data to a generative AI model, which then issues instructions for generating summaries and optimized information. The generative AI model summarizes the patient's medical history, prescription medications, test results, etc., and generates a draft document.

[1042] 3. Present the draft document to the user

[1043] The terminal presents the generated draft document to the user and provides an interface for reviewing and editing.

[1044] 4. Recognize user emotions using emotion recognition technology

[1045] The device's built-in emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions in real time.

[1046] 5. Feedback to generative AI models based on recognized emotions

[1047] The server then feeds the recognized user emotion back into the regenerative AI model, adjusting the tone and expression of the document. For example, if the user is feeling stressed, the document's expression will be softened.

[1048] 6. Save and publish the finalized document

[1049] The server officially stores the final document that has been reviewed and edited by the user and issues it as necessary. The user can confirm through their terminal that the final document has been successfully issued.

[1050] Hardware and software used

[1051] Server: Database management systems (e.g., MySQL, PostgreSQL) and web servers (e.g., Apache, NGINX).

[1052] Terminal: Facial recognition software (e.g., OpenCV), voice analysis software (e.g., TensorFlow).

[1053] Robot: Robot control system (e.g. ROS - Robot Operating System).

[1054] Specific examples

[1055] As a concrete example, consider the following scenario:

[1056] 1. An operator logs in to the system and instructs the robot to perform packaging with task ID "task_123." The server inputs the corresponding task information into the generative AI model and generates the optimal operation sequence.

[1057] 2. The generated operation sequence is displayed on the terminal, and the operator's emotions are detected by an emotion recognition engine. If the operator is feeling stressed, the system reconsiders the operation sequence to prioritize safety.

[1058] 3. The adjusted operation sequence is finally confirmed, and the robot begins its work. The operator checks the results via a terminal and confirms that the work has been completed safely.

[1059] Prompt Sentence Examples

[1060] prompt:

[1061] "Generate the optimal operation sequence for the robot packaging task with task ID 'task_123'."

[1062] Input data:

[1063] "Task: Packaging, Operational Steps: Step 1: Collect items, Step 2: Place items, Step 3: Package items, Step 4: Inspect packaging, Step 5: Remove finished product."

[1064] This system enables efficient document creation and safe operation that reflects the user's emotional state.

[1065] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1066] Specific processing steps of the program

[1067] Step 1:

[1068] User login

[1069] The user logs into the system using a terminal. The terminal displays a login screen and asks the user to enter a user ID and password. The entered authentication information is sent from the terminal to the server. The server verifies the information against the database and, if successful, starts a user session. A session ID is generated and a request to display the dashboard is sent to the terminal.

[1070] Input: User ID, Password

[1071] Output: Session ID, Dashboard display

[1072] Step 2:

[1073] Get task information

[1074] The user selects a specific task (e.g., packaging) from the dashboard and searches by entering the task ID. The device sends this request to the server, which accesses the database to retrieve the task information, including the operation steps and required resources.

[1075] Input: Task ID

[1076] Output: Task information

[1077] Step 3:

[1078] Optimizing task information

[1079] The server inputs the acquired task information into the generative AI model. At this time, the AI ​​model is also provided with a prompt. The generative AI model generates an optimal operation sequence based on the task information. The generated operation sequence is returned to the server.

[1080] Input: Task information, prompt

[1081] Output: Optimized operation sequence

[1082] Step 4:

[1083] Optimized operation sequence presentation

[1084] The server sends the generated optimized operation sequence to the user's terminal, which displays it to the user, who can then review the operation sequence and make any necessary corrections.

[1085] Input: Optimized operation sequence

[1086] Output: what is displayed to the user

[1087] Step 5:

[1088] emotion recognition

[1089] The emotion engine on the device analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotional state in real time. The recognized emotion information is then sent to the server.

[1090] Input: facial expression data, voice data, keystroke data

[1091] Output: Emotional information

[1092] Step 6:

[1093] Emotion-based feedback

[1094] The server then feeds the recognized emotion information back to the generative AI model and adjusts the tone and expression of the document. For example, if the user is feeling stressed, the tone of the document will be softened. The adjusted document is then sent back to the server.

[1095] Input: Emotion information

[1096] Output: Adjusted document

[1097] Step 7:

[1098] Final confirmation and document storage

[1099] The user finalizes the adjusted document and makes corrections as necessary. When the user clicks the final confirmation button, the terminal sends this request to the server. The server officially saves and publishes the final document. A notification that the final document has been saved is sent to the terminal and displayed to the user.

[1100] Input: Final confirmation request

[1101] Output: Save final document, display notification

[1102] This series of processing steps enables efficient document creation and safe operation that reflects the user's feelings.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] [Fourth embodiment]

[1107] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1108] 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.

[1109] 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).

[1110] 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.

[1111] 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.

[1112] 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).

[1113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1114] 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.

[1115] 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.

[1116] 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.

[1117] 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.

[1118] 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.

[1119] 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."

[1120] This invention is a system that uses a generative AI model to support document creation in medical settings. Specific embodiments of this system are described below.

[1121] 1. User login

[1122] To access the system, a user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates it by checking it against information in a database. If authentication is successful, the server starts the user's session and displays the dashboard on the terminal.

[1123] 2. Extraction of electronic medical record information

[1124] The user selects "Create a medical information report" from the dashboard and enters the target patient's ID. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[1125] 3. Information Summarization Using Generative AI Models

[1126] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[1127] 4. Review and edit your draft

[1128] The server sends the generated draft document to the user's device. The device displays the draft document to the user, who checks the contents and makes edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The device then sends this request to the server.

[1129] 5. Publication of the Final Document

[1130] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[1131] Specific examples

[1132] Take the example of a scenario in which a doctor is creating a medical information report for a patient. The doctor logs into the system on a terminal and selects to create a medical information report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is input into a generative AI model, which then summarizes it. The generated draft document is displayed on the doctor's terminal, where the doctor can review and edit the contents. It is then issued as the final document and saved in the system.

[1133] In this way, the system significantly reduces doctors' overtime work and enables efficient document preparation.

[1134] The processing flow will be explained below.

[1135] Step 1:

[1136] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[1137] Step 2:

[1138] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[1139] Step 3:

[1140] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[1141] Step 4:

[1142] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[1143] Step 5:

[1144] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[1145] Step 6:

[1146] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[1147] Step 7:

[1148] The server sends the generated draft document to the user's terminal, and the terminal displays the draft document to the user.

[1149] Step 8:

[1150] The user checks the draft document and makes corrections and edits as necessary. When the user has completed editing, he clicks the "Publish as final document" button. The terminal sends this request to the server.

[1151] Step 9:

[1152] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[1153] Step 10:

[1154] The terminal notifies the user that the final document has been successfully published.

[1155] Example 1

[1156] 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."

[1157] Traditional document creation processes in medical settings require time and effort from medical professionals, especially when creating documents such as medical information reports. Manual input and verification can lead to human error. There is a need for a system that can use generative AI models to summarize information from electronic medical records and create documents efficiently. Furthermore, it is necessary to reduce the burden on medical professionals by automating the processes of user authentication and data extraction.

[1158] 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.

[1159] In this invention, the server includes a means for a user to input authentication information and send it to the server, a means for the server to compare the authentication information with a database and perform authentication, a means for extracting patient data from the electronic medical record, a means for inputting the extracted patient data into a generative AI model, a means for generating information summarized by the generative AI model as a draft document, a means for presenting the draft document to the user for confirmation and editing, and a means for saving and issuing the final confirmed document. This enables medical professionals to create documents easily and quickly, reducing human error and improving work efficiency.

[1160] "User" refers to a healthcare professional who accesses and operates the system.

[1161] "Authentication information" refers to information such as the user ID and password that a user enters when logging in to a system.

[1162] "Server" refers to a computer device that processes data and performs authentication for the entire system.

[1163] "Database" refers to the data storage system where patient medical information and user authentication information is stored.

[1164] An "electronic medical record" refers to a digital system that manages medical information such as a patient's medical history, prescription medications, and test results.

[1165] "Patient data" refers to information stored in electronic medical records, such as each patient's medical history, prescribed medications, and test results.

[1166] A "generative AI model" refers to an artificial intelligence model that analyzes input data and performs summaries and text generation.

[1167] "Draft Document" refers to a draft document generated based on information summarized by a generative AI model.

[1168] "Terminal" means the computer or mobile device used by a User to access the System.

[1169] A "user session" refers to a series of communication states for operating a system after a user has been authenticated.

[1170] "Dashboard" refers to the interface through which users access the main functions of the system.

[1171] "Issuance" refers to the formal storage and recording of the final verified document in the system.

[1172] A "prompt" is an instructional sentence containing necessary information that is used as input to a generative AI model.

[1173] This invention relates to a system that uses generative AI models to support document creation in medical settings, including a series of processes for efficiently performing user authentication, data extraction, information summarization, document generation, and final document issuance.

[1174] System configuration and operation

[1175] This system is configured using the following hardware and software:

[1176] Hardware

[1177] Server: Manages the system's data processing, authentication, database access, and communication with the generative AI model.

[1178] Terminal: A computer or mobile device through which a user accesses the system.

[1179] software

[1180] Electronic medical record system: A digital system that manages information such as a patient's medical history, prescription medications, and test results (e.g., a general-purpose electronic medical record system).

[1181] Generative AI model: An artificial intelligence model that analyzes input data and performs summarization or text generation (e.g., GPT-3).

[1182] Program processing

[1183] 1. User Authentication

[1184] First, the user enters authentication information (user ID and password) on the login screen of the device. The device sends this authentication information to the server, which checks it against the database. If authentication is successful, the user session begins and the dashboard screen is displayed on the device.

[1185] 2. Data extraction

[1186] The user selects to create a medical information report from the dashboard and enters the target patient's ID. This request is sent from the device to the server. The server accesses the electronic medical record system, searches and extracts the specified patient's data (medical history, prescription medications, test results, etc.), and temporarily stores it on the server.

[1187] 3. Information Summary

[1188] The server generates a prompt sentence to be input to the generative AI model based on the extracted patient data. This prompt sentence is sent to the generative AI model, which analyzes and summarizes the data and generates a draft document of the medical information report. This draft document is then sent back to the server.

[1189] Prompt Sentence Examples

[1190] Patient ID: patient001

[1191] Medical History: Diagnosis on January 1, 2023

[1192] Prescription medication list: Aspirin, Metoprolol

[1193] Test results: Blood test normal

[1194] Generate a medical information form from this information.

[1195] 4. Review and edit the draft document

[1196] The server sends the generated draft document to the user's device. The device displays the draft document, and the user checks the contents and makes edits as necessary. When the user has completed editing, they click the "Publish as final document" button. This request is sent from the device to the server.

[1197] 5. Publication of the Final Document

[1198] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been published.

[1199] This system allows medical professionals to easily and quickly create documents such as medical information reports, and by using a generative AI model, it automates information summarization, which is expected to reduce human error and improve work efficiency.

[1200] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1201] Step 1: User authentication

[1202] ---

[1203] Input: The user enters authentication information (user ID and password) on the device's login screen.

[1204] How it works: When the user clicks the "Login" button, the device sends these credentials to the server in real time.

[1205] Specific operation: The user enters the user ID "doctor123" and the password "password123" and presses the "Login" button.

[1206] Data processing: The server encrypts the received user ID and password and checks them against the database.

[1207] Output: If authentication is successful, the server starts a user session and sends the dashboard screen to the terminal. If authentication fails, it sends an error message.

[1208] Specific operation: The server searches the authentication information in the database, and if it matches, displays a message such as "Welcome, doctor123" on the user's terminal.

[1209] Step 2: Data extraction

[1210] ---

[1211] Input: The user selects "Create medical information report" on the dashboard and enters the ID of the target patient.

[1212] Specific operation: The user clicks the "Create medical information report" button, enters the patient ID "patient001", and presses the "Search" button.

[1213] Operation: The terminal sends the entered patient ID to the server.

[1214] Data processing: The server accesses the electronic medical record database and searches and extracts data on the target patient, such as medical history, prescription medications, and test results.

[1215] Output: The server temporarily stores the extracted patient data within the server and continues processing.

[1216] Specific operation: The server sends a query to the electronic medical record system, retrieves all information about the patient, and temporarily stores it in memory.

[1217] Step 3: Information Summary

[1218] ---

[1219] Input: Patient data stored in the server.

[1220] Specific operation: The server generates a prompt sentence to send to the generative AI model.

[1221] How it works: The server sends the generated prompt sentence to the generative AI model.

[1222] Data processing: The generative AI model analyzes the prompt text, summarizes information such as medical history, prescription medications, and test results, and generates a draft document.

[1223] Output: The generative AI model returns the generated draft document to the server.

[1224] Example prompt sentence:

[1225] Patient ID: patient001

[1226] Medical History: Diagnosis on January 1, 2023

[1227] Prescription medication list: Aspirin, Metoprolol

[1228] Test results: Blood test normal

[1229] Generate a medical information form from this information.

[1230] Step 4: Review and edit the draft document

[1231] ---

[1232] Input: The draft document returned from the generative AI model.

[1233] Specific operation: The server sends the generated draft document to the user's terminal.

[1234] How it works: The device displays the draft document to the user, who can review and edit it.

[1235] Data processing: After the user has completed editing, they click the "Publish as final document" button to send the final version to the server.

[1236] Output: Edited final draft document.

[1237] Specific actions: The user views the draft document, makes corrections such as adding additional information to the inspection results section, and clicks the "Publish as final document" button.

[1238] Step 5: Issuance of final document

[1239] ---

[1240] Input: The final draft document as edited by the user.

[1241] Specific operation: The terminal sends the finalized document to the server.

[1242] Actions: The server formally stores the final document and records its publication.

[1243] Data processing: After the server has completed saving, it will send a notification to the device.

[1244] Output: Save completion notification and final document.

[1245] Specific operation: The server saves the final document in the database and displays a notification on the terminal stating "Medical information report has been issued successfully."

[1246] In this way, the system reduces the burden on the user and enables efficient document creation.

[1247] (Application example 1)

[1248] 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."

[1249] In modern factories, the creation of manufacturing process and quality control reports still relies heavily on manual labor. This reduces efficiency and increases the risk of human error. It also makes it difficult to quickly share and confirm information, potentially leading to problems in product quality control. To solve this issue and improve overall factory productivity, a system is needed that can automatically summarize manufacturing data and quickly create reports.

[1250] 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.

[1251] In this invention, the server includes means for extracting target data from an electronic database, means for inputting the extracted target data into a generative AI model, means for generating a draft document from the information summarized by the generative AI model, means for presenting the draft document to a user for confirmation and editing, and means for saving and publishing the final confirmed document, thereby enabling the automatic generation and editing of manufacturing data summaries and reports.

[1252] An "electronic database" is a process of systematically storing and managing information in digital form, and is a database system that allows quick access to specific data.

[1253] "Target data" refers to information relating to a specific ID extracted from an electronic database, and is a group of data containing the necessary content depending on the purpose.

[1254] A "generative AI model" is an algorithm or software system that uses artificial intelligence technology to analyze input data and automatically generate summaries and documents.

[1255] A "draft document" is an intermediate document automatically generated by a generative AI model that is later reviewed and edited.

[1256] "Historical data" is information that contains past performance or records of a particular process or operation.

[1257] "Process data" refers to data that includes detailed information and execution details when a specific action or operation is performed.

[1258] "Outcome data" is information that describes the results or outputs achieved as a result of a particular procedure or process.

[1259] This invention proposes a system for automatically generating reports on manufacturing processes and quality control within factories. The system uses a generative AI model to summarize work data and efficiently generate reports.

[1260] First, a user (factory operator) logs in to the system. The user enters their authentication information (user ID and password) and sends it from the terminal to the server. The server compares this authentication information with the information in the database, and if authentication is successful, the user's session is started and a dashboard is displayed on the terminal.

[1261] Next, the user selects data for a specific production line from the dashboard. After the user enters the production line ID, the terminal sends this request to the server. The server accesses an electronic database to search and extract data for the specified production line. This data includes production history, quality data, and maintenance records. This extracted data is temporarily stored on the server.

[1262] The server then inputs the extracted data into a generative AI model, which analyzes the received data, summarizes manufacturing history, quality control data, and maintenance records, and generates a draft report document, which is returned to the server.

[1263] The server then sends the generated draft document to the user's device. The device displays the draft document to the user, who can review the content and make edits as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device then sends this request to the server.

[1264] The server officially saves the final document and records that it has been published. The server then sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published.

[1265] The system can efficiently summarize manufacturing data and automatically generate and edit reports, allowing factory operators to reduce the risk of human error and share information quickly.

[1266] As a concrete example, consider a scenario in which a mechanical engineer operator creates a quality control report for a specific production line. The operator logs into the system and selects data for the specific production line. The production history, quality data, and maintenance records for that line are extracted from the database. This data is then input into a generative AI model, which then summarizes it. The generated draft document is displayed on the operator's device, where the operator can review and edit the contents. It is then published as a final document and saved in the system.

[1267] An example prompt for a generative AI model is:

[1268] "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating hours: 8 hours, Maintenance records: normal"

[1269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1270] Step 1:

[1271] A user logs in to the system using their own terminal. The user enters authentication information (user ID and password) into the terminal's login screen and sends this information to the server. The server performs authentication by comparing it with information in the database, and if authentication is successful, starts a session and displays a dashboard on the terminal. The input is authentication information, and the output is the authentication result and the dashboard screen. The server compares the authentication information with the database and generates session information.

[1272] Step 2:

[1273] The user selects the relevant production line data from the dashboard. The user enters the production line ID and sends the request to the server via the terminal. The server accesses the electronic database to search and extract data for the specified production line. The input is the production line ID and the output is the extracted production data. The server retrieves historical data, quality data, and maintenance records from the database.

[1274] Step 3:

[1275] The server sends the extracted data to the generative AI model. The server passes the specified manufacturing data to the generative AI model and provides a prompt to the model. The generative AI model analyzes the data and generates summarized information as a draft document. An example of this prompt is "Please summarize the following manufacturing data: Production line ID: line_10, Number of products: 1000, Number of defective products: 5, Operating time: 8 hours, Maintenance record: Normal." The input is the manufacturing data, and the output is the summarized draft document.

[1276] Step 4:

[1277] The server sends the generated draft document to the user's terminal. The user's terminal displays the draft document, allowing the user to check and edit the contents. The terminal displays the draft document in the user's interface, allowing the user to manually edit and add comments. The input is the draft document, and the output is the edited document.

[1278] Step 5:

[1279] The user finishes editing the draft document and clicks the "Publish as final document" button. The terminal sends this request to the server. The server formally saves the edited document and records that it has been published. The server sends a save completion notification to the terminal, and the terminal notifies the user that the final document has been successfully published. The input is the edited document and the publishing request, and the output is the final saved document and the notification.

[1280] At each step, the server or device processes and calculates the data to generate the required output. By utilizing a "generative AI model," we have created a system that can efficiently summarize data and generate documents.

[1281] 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.

[1282] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1283] 1. User login

[1284] To access the system, the user (doctor) uses a terminal to enter authentication information (user ID and password) into the login screen. The terminal sends this authentication information to the server, which then authenticates the user by comparing it with information in a database. If authentication is successful, the server starts a user session and sends a request to display the dashboard on the terminal. The terminal then displays the dashboard screen to the user.

[1285] 2. Extraction of electronic medical record information

[1286] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. This extracted patient data is temporarily stored on the server.

[1287] 3. Information Summarization Using Generative AI Models

[1288] The server generates a request to input the extracted patient data into the generative AI model and sends it to the model. The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft document of the medical information report. This draft document is returned to the server.

[1289] 4. Review and edit your draft

[1290] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[1291] 5. Emotion-Based Regulation

[1292] The emotion engine recognizes the user's emotions and feeds that information back to the generative AI model, which then adjusts the tone and expression of the document appropriately based on the user's emotions. For example, if the user is feeling stressed, the tone of the document can be softened.

[1293] 6. Final confirmation and issuance

[1294] The user reviews the draft document and makes corrections and edits as necessary. The emotion engine continues to monitor the user's emotions during this process and makes readjustments as necessary. When the user has completed editing, they click the "Publish as Final Document" button. The device sends this request to the server.

[1295] 7. Publication of the Final Document

[1296] The server officially saves the final document and records that it has been published. The server sends a notification to the terminal that the final document has been saved. The terminal notifies the user that the final document has been successfully published.

[1297] Specific examples

[1298] Consider a scenario in which a doctor is creating a medical report for a patient. The doctor logs into the system on their device and selects to create a medical report for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress or fatigue and adjusts the tone and expression of the document appropriately. The final document is then published and saved in the system.

[1299] In this way, the system can significantly reduce doctors' overtime work and efficiently prepare documents. Also, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[1300] The processing flow will be explained below.

[1301] Step 1:

[1302] A user accesses the system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[1303] Step 2:

[1304] The server checks the received authentication information against the information in its database. If authentication is successful, the server starts a session and sends a request to display the user's dashboard on the device. The device displays the dashboard screen to the user.

[1305] Step 3:

[1306] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device then sends this request to the server.

[1307] Step 4:

[1308] The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[1309] Step 5:

[1310] The server generates a request to input the extracted patient data into the generative AI model and sends it to the generative AI model.

[1311] Step 6:

[1312] The generative AI model analyzes the received patient data, summarizes medical history, prescribed medications, test results, etc., and generates a draft medical information report document. This draft document is returned to the server.

[1313] Step 7:

[1314] The server sends the generated draft document to the user's device, which then displays it to the user. At this time, the emotion engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions.

[1315] Step 8:

[1316] The emotion engine recognizes the user's emotions and feeds them back to the generative AI model, which then adjusts the tone and expression of the draft document based on the user's emotions.

[1317] Step 9:

[1318] The user checks the draft document and makes corrections or edits as necessary. The device temporarily saves the user's corrections.

[1319] Step 10:

[1320] The user completes the edits and clicks the "Publish as final document" button. The device sends this request to the server.

[1321] Step 11:

[1322] The server officially saves the final document and records that it has been published. The server then sends a notification to the terminal that the final document has been saved.

[1323] Step 12:

[1324] The terminal notifies the user that the final document has been successfully published.

[1325] Example 2

[1326] 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."

[1327] In the medical field, efficient and accurate preparation of medical information reports is required, but conventional systems require doctors to spend a huge amount of time manually preparing documents. This increases doctors' overtime work and stress. Furthermore, the tone and expression of documents must also be adjusted manually, placing a burden on doctors. Furthermore, conventional systems do not take into account the doctor's emotional state when preparing documents, resulting in the problem of document quality being affected by the doctor's emotional state.

[1328] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for extracting patient data from the electronic medical record, means for inputting the extracted patient data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user and analyzing the user's emotions using an emotion recognition engine, means for adjusting the tone and expression of the draft document based on the analysis results, means for user confirmation and editing, and means for saving and publishing the final confirmed document. This reduces the burden on doctors and enables efficient and accurate creation of medical information reports. Furthermore, document creation that takes the doctor's emotional state into consideration is realized, improving the quality of the document.

[1329] An "electronic medical record" is a system that digitally records and manages patient medical information, prescription medications, test results, etc.

[1330] "Patient data" refers to information such as medical history, prescribed medications, and test results recorded in electronic medical records.

[1331] A "generative AI model" is an artificial intelligence model that analyzes input data, summarizes information, and generates text.

[1332] A "draft document" is an unfinalized document in which information summarized by a generative AI model is organized into sentence form.

[1333] An "emotion recognition engine" is an engine that has the ability to analyze data such as a user's facial expressions, voice tone, and keystroke patterns to identify the user's emotions.

[1334] "Tone and voice adjustment" is the process of changing the tone and language of a document depending on the user's emotional state.

[1335] A "session" is a unit in which the server maintains the user's logged-in status and manages the entire process of the user's use of the system.

[1336] A "dashboard" is a screen that aggregates the information and functions necessary for system users to operate the system.

[1337] "Storage and publication" refers to the process of formally recording the final reviewed document in a database and sharing it with other systems and users as needed.

[1338] MODE FOR CARRYING OUT THE INVENTION

[1339] This invention combines a system that uses a generative AI model to support document creation in medical settings with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1340] User login

[1341] First, a user (doctor) logs in to the system using a terminal. The terminal displays a login screen, and the user enters their user ID and password. The terminal sends this authentication information to the server, which then authenticates the user by checking it against the user information in its database. If authentication is successful, the server starts a session and sends a request to the terminal to display the dashboard. The terminal renders the dashboard screen and displays it to the user.

[1342] Extraction of electronic medical record information

[1343] The user selects "Create a medical information report" from the dashboard, enters the target patient's ID, and clicks the search button. The device sends this request to the server. The server accesses the electronic medical record database and searches and extracts the medical record information of the specified patient. The extracted patient data is temporarily stored on the server.

[1344] Information summarization using generative AI models

[1345] The server formats the extracted patient data and generates a prompt to send to the generative AI model, which analyzes the received patient data and summarizes the medical history, prescribed medications, test results, etc. to generate a draft medical information report document. The generated draft document is returned to the server.

[1346] Draft review and emotion recognition

[1347] The server then sends the generated draft document to the user's device, which then renders and displays it to the user. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, keystroke patterns, etc. to recognize the user's emotions.

[1348] Emotion-Based Adjustment

[1349] The emotion recognition engine feeds the analysis results back to the generative AI model, which then uses the feedback to adjust the tone and expression of the draft document appropriately. For example, if the user is feeling stressed, the tone of the document can be softened.

[1350] Final confirmation and issuance

[1351] The user reviews the draft document and manually corrects and edits it as needed. The emotion recognition engine continues to monitor the user's emotions during this process and readjusts the document as needed. Once editing is complete, the user clicks the "Publish as Final Document" button. The device sends this request to the server.

[1352] Final document retention and notification

[1353] The server officially saves the final document and records that it has been published. The server then sends a notification of the completion of saving to the terminal, and the terminal notifies the user that the final document has been successfully published.

[1354] Specific examples

[1355] Consider a scenario in which a doctor is creating a medical record for a patient. The doctor logs in to the system on a device and selects to create a medical record for a specific patient. Information such as the patient's medical history, prescribed medications, and test results is extracted from the electronic medical record. This information is then input into the generative AI model, which then summarizes it. As the draft document is displayed on the doctor's device, the emotion engine recognizes the doctor's emotions and feeds back the analysis results to the generative AI model. As the doctor reviews and edits the content, the emotion engine detects the doctor's stress and fatigue and adjusts the tone and expression appropriately. The document is then published as a final document and saved in the system. In this way, this system significantly reduces overtime work for doctors and enables more efficient document creation. Furthermore, by taking doctors' emotions into consideration, it can reduce stress and provide a better working environment.

[1356] Prompt Sentence Examples

[1357] Please draft a medical information form using the following patient data: Medical history: ____, Prescription medications: ____, Test results: ____.

[1358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1359] Step 1:

[1360] User login

[1361] The user enters their user ID and password, and the device sends this authentication information to the server. The input is the user ID and password, and the output is the authentication result. The server compares the authentication information with the user information in the database, and if authentication is successful, the session begins. Specifically, the server sends a successful authentication response to the device, and the device displays the dashboard.

[1362] Step 2:

[1363] Extraction of electronic medical record information

[1364] The user selects "Create a medical information report" on the dashboard, enters the patient ID, and performs a search. The terminal sends this request to the server. The input is the patient ID, and the output is the patient's medical record information. The server accesses the electronic medical record database, searches and extracts the medical record information of the specified patient, and temporarily stores this information. Specifically, it executes the request "GET / patient-info?patient_id=patient456" and retrieves the search results.

[1365] Step 3:

[1366] Information summarization using generative AI models

[1367] The server sends the extracted patient data to the generative AI model as a prompt. The input is the patient data, and the output is a summarized draft document. The generative AI model analyzes the received data and generates a draft document by summarizing information such as medical history, prescribed medications, and test results. Specifically, the prompt "Please create a draft medical information report using the following patient data. Medical history: XX, prescribed medications: △△, test results: □□" is input into the generative AI model, and the summary result is obtained.

[1368] Step 4:

[1369] Draft document review and emotion recognition

[1370] The server sends the generated draft document to the terminal, which then displays it to the user. The input is the draft document, and the output is the user's emotional data. At the same time, the emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize their emotions. Specifically, it analyzes input data from the webcam and microphone to obtain emotion recognition results.

[1371] Step 5:

[1372] Emotion-Based Adjustment

[1373] The emotion recognition engine feeds the analysis results back to the generative AI model. The input is emotional data, and the output is an adjusted draft document. The generative AI model uses this feedback to appropriately adjust the tone and expression of the draft document. Specifically, for users who are feeling stressed, the model will soften the tone of the document.

[1374] Step 6:

[1375] Final confirmation and issuance

[1376] The user reviews the draft document and makes corrections as necessary. The input is the draft document and the user's corrections, and the output is the final document. The emotion recognition engine monitors the user's emotions during the final confirmation and readjusts them as necessary. When the user clicks the "Publish as Final Document" button, the terminal sends the request to the server. Specifically, after editing, it sends a "POST / finalize-document" request.

[1377] Step 7:

[1378] Final document retention and notification

[1379] The server officially saves the final document and records that publication is complete. The input is the final document, and the output is a notification that saving is complete. The server sends a notification of saving completion to the terminal, and the terminal notifies the user. Specifically, it executes a database query called "INSERT INTO final_documents (final document data)" and displays a message to the user that saving is complete.

[1380] (Application example 2)

[1381] 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."

[1382] In traditional medical settings and manufacturing plants, generative AI models are being used to improve the efficiency of document creation and robot operation, but no systems exist that take user emotions into account. As a result, if a user is stressed or fatigued, the quality and safety of the output may decline. In manufacturing plants in particular, where the emotions of operators are directly linked to work safety, a system that recognizes and adapts to their emotions is needed.

[1383] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for extracting data from the electronic medical record, means for inputting the extracted data into the generative AI model, means for generating information summarized by the generative AI model as a draft document, means for presenting the draft document to the user for confirmation and editing, means for recognizing the user's emotions using emotion recognition technology, means for providing feedback to the generative AI model based on the recognized emotions and adjusting the tone and expression of the document, and means for saving and publishing the final confirmed document. This enables efficient document creation and safe operation that reflects the user's emotional state.

[1384] An "electronic medical record" is a system that electronically manages a patient's medical information.

[1385] "Data identification information" is information for uniquely identifying specific data.

[1386] An "information management system" is a system for storing, managing, retrieving, and processing data.

[1387] A "generative AI model" is an artificial intelligence model that generates or summarizes information based on given data.

[1388] A "draft document" is a temporary document intended for editing by users before final review.

[1389] "Emotion recognition technology" is a technology that detects emotions by analyzing a user's facial expressions, voice, keystroke patterns, etc.

[1390] "Feedback" is the action of making corrections to models and processes based on information obtained by the system.

[1391] "Tone" refers to the overall impression or mood of a document or statement.

[1392] A "representation" is a method or format for conveying data or information.

[1393] As an embodiment of the present invention, the following system can be constructed.

[1394] Overall system overview

[1395] The system includes the following main elements:

[1396] Server: A central system that stores, processes, and manages data.

[1397] Device: The device that a user accesses and operates (e.g., computer, smartphone, smart glasses, head-mounted display, etc.).

[1398] Robot: A piece of equipment on a manufacturing line that performs tasks according to control instructions.

[1399] Program Description

[1400] 1. Extract data from electronic medical records

[1401] The server accesses the electronic medical record database and extracts patient data, which is processed based on the data identification information.

[1402] 2. Input the extracted data into a generative AI model

[1403] The server sends the extracted patient data to a generative AI model, which then issues instructions for generating summaries and optimized information. The generative AI model summarizes the patient's medical history, prescription medications, test results, etc., and generates a draft document.

[1404] 3. Present the draft document to the user

[1405] The terminal presents the generated draft document to the user and provides an interface for reviewing and editing.

[1406] 4. Recognize user emotions using emotion recognition technology

[1407] The device's built-in emotion recognition engine analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotions in real time.

[1408] 5. Feedback to generative AI models based on recognized emotions

[1409] The server then feeds the recognized user emotion back into the regenerative AI model, adjusting the tone and expression of the document. For example, if the user is feeling stressed, the document's expression will be softened.

[1410] 6. Save and publish the finalized document

[1411] The server officially stores the final document that has been reviewed and edited by the user and issues it as necessary. The user can confirm through their terminal that the final document has been successfully issued.

[1412] Hardware and software used

[1413] Server: Database management systems (e.g., MySQL, PostgreSQL) and web servers (e.g., Apache, NGINX).

[1414] Terminal: Facial recognition software (e.g., OpenCV), voice analysis software (e.g., TensorFlow).

[1415] Robot: Robot control system (e.g. ROS - Robot Operating System).

[1416] Specific examples

[1417] As a concrete example, consider the following scenario:

[1418] 1. An operator logs in to the system and instructs the robot to perform packaging with task ID "task_123." The server inputs the corresponding task information into the generative AI model and generates the optimal operation sequence.

[1419] 2. The generated operation sequence is displayed on the terminal, and the operator's emotions are detected by an emotion recognition engine. If the operator is feeling stressed, the system reconsiders the operation sequence to prioritize safety.

[1420] 3. The adjusted operation sequence is finally confirmed, and the robot begins its work. The operator checks the results via a terminal and confirms that the work has been completed safely.

[1421] Prompt Sentence Examples

[1422] prompt:

[1423] "Generate the optimal operation sequence for the robot packaging task with task ID 'task_123'."

[1424] Input data:

[1425] "Task: Packaging, Operational Steps: Step 1: Collect items, Step 2: Place items, Step 3: Package items, Step 4: Inspect packaging, Step 5: Remove finished product."

[1426] This system enables efficient document creation and safe operation that reflects the user's emotional state.

[1427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1428] Specific processing steps of the program

[1429] Step 1:

[1430] User login

[1431] The user logs into the system using a terminal. The terminal displays a login screen and asks the user to enter a user ID and password. The entered authentication information is sent from the terminal to the server. The server verifies the information against the database and, if successful, starts a user session. A session ID is generated and a request to display the dashboard is sent to the terminal.

[1432] Input: User ID, Password

[1433] Output: Session ID, Dashboard display

[1434] Step 2:

[1435] Get task information

[1436] The user selects a specific task (e.g., packaging) from the dashboard and searches by entering the task ID. The device sends this request to the server, which accesses the database to retrieve the task information, including the operation steps and required resources.

[1437] Input: Task ID

[1438] Output: Task information

[1439] Step 3:

[1440] Optimizing task information

[1441] The server inputs the acquired task information into the generative AI model. At this time, the AI ​​model is also provided with a prompt. The generative AI model generates an optimal operation sequence based on the task information. The generated operation sequence is returned to the server.

[1442] Input: Task information, prompt

[1443] Output: Optimized operation sequence

[1444] Step 4:

[1445] Optimized operation sequence presentation

[1446] The server sends the generated optimized operation sequence to the user's terminal, which displays it to the user, who can then review the operation sequence and make any necessary corrections.

[1447] Input: Optimized operation sequence

[1448] Output: what is displayed to the user

[1449] Step 5:

[1450] emotion recognition

[1451] The emotion engine on the device analyzes the user's facial expressions, voice tone, and keystroke patterns to recognize the user's emotional state in real time. The recognized emotion information is then sent to the server.

[1452] Input: facial expression data, voice data, keystroke data

[1453] Output: Emotional information

[1454] Step 6:

[1455] Emotion-based feedback

[1456] The server then feeds the recognized emotion information back to the generative AI model and adjusts the tone and expression of the document. For example, if the user is feeling stressed, the tone of the document will be softened. The adjusted document is then sent back to the server.

[1457] Input: Emotion information

[1458] Output: Adjusted document

[1459] Step 7:

[1460] Final confirmation and document storage

[1461] The user finalizes the adjusted document and makes corrections as necessary. When the user clicks the final confirmation button, the terminal sends this request to the server. The server officially saves and publishes the final document. A notification that the final document has been saved is sent to the terminal and displayed to the user.

[1462] Input: Final confirmation request

[1463] Output: Save final document, display notification

[1464] This series of processing steps enables efficient document creation and safe operation that reflects the user's feelings.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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).

[1472] 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.

[1473] 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."

[1474] 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.

[1475] 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).

[1476] 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.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] The following is further disclosed regarding the above embodiment.

[1487] (Claim 1)

[1488] means for extracting patient data from an electronic medical record;

[1489] a means for inputting the extracted patient data into a generative AI model;

[1490] A means for generating the information summarized by the generative AI model as a draft document;

[1491] a means for presenting the draft document to the user for review and editing;

[1492] A system that includes a means for storing and publishing finalized documents.

[1493] (Claim 2)

[1494] 2. The system of claim 1, wherein the means for extracting patient data from the electronic medical record accesses the database using a patient ID.

[1495] (Claim 3)

[1496] 10. The system of claim 1, wherein the information summarized by the generative AI model includes medical history, prescription medications, and test results.

[1497] "Example 1"

[1498] (Claim 1)

[1499] A means for the user to enter authentication information and transmit it to the server;

[1500] a means for the server to verify the authentication information against a database and perform authentication;

[1501] means for extracting patient data from an electronic medical record;

[1502] a means for inputting the extracted patient data into a generative AI model;

[1503] A means for generating the information summarized by the generative AI model as a draft document;

[1504] a means for presenting the draft document to the user for review and editing;

[1505] A system that includes a means for storing and publishing finalized documents.

[1506] (Claim 2)

[1507] 2. The system of claim 1, wherein the means for extracting patient data from the electronic medical record accesses the database using a patient ID.

[1508] (Claim 3)

[1509] 10. The system of claim 1, wherein the information summarized by the generative AI model includes medical history, prescription medications, and test results.

[1510] "Application Example 1"

[1511] (Claim 1)

[1512] means for extracting target data from an electronic database;

[1513] a means for inputting the extracted target data into a generative AI model;

[1514] A means for generating the information summarized by the generative AI model as a draft document;

[1515] a means for presenting the draft document to the user for review and editing;

[1516] A system that includes a means for storing and publishing finalized documents.

[1517] (Claim 2)

[1518] 10. The system of claim 1, wherein the means for extracting subject data from the electronic database accesses the database using a subject ID.

[1519] (Claim 3)

[1520] 10. The system of claim 1, wherein the information summarized by the generative AI model includes historical data, treatment data, and outcome data.

[1521] "Example 2: Combining Emotion Engines"

[1522] (Claim 1)

[1523] means for extracting patient data from an electronic medical record;

[1524] a means for inputting the extracted patient data into a generative AI model;

[1525] A means for generating the information summarized by the generative AI model as a draft document;

[1526] means for presenting the draft document to a user and analyzing the user's emotions using an emotion recognition engine;

[1527] a means of adjusting the tone and language of the draft document based on the analysis results; and

[1528] A means for user review and editing;

[1529] A system that includes a means for storing and publishing finalized documents.

[1530] (Claim 2)

[1531] 2. The system of claim 1, wherein the means for extracting patient data from the electronic medical record accesses the database using a patient ID.

[1532] (Claim 3)

[1533] 10. The system of claim 1, wherein the information summarized by the generative AI model includes medical history, prescription medications, and test results.

[1534] "Application example 2 when combining emotion engines"

[1535] (Claim 1)

[1536] a means for extracting data from an electronic medical record;

[1537] a means for inputting the extracted data into a generative AI model;

[1538] A means for generating the information summarized by the generative AI model as a draft document;

[1539] a means for presenting the draft document to the user for review and editing;

[1540] A means for recognizing a user's emotion using emotion recognition technology;

[1541] A means to adjust the tone and expression of a document by providing feedback to a generative AI model based on the perceived sentiment; and

[1542] A system that includes a means for storing and publishing finalized documents.

[1543] (Claim 2)

[1544] 2. The system of claim 1, wherein the means for extracting data from the electronic medical record accesses the information management system using the data identification information.

[1545] (Claim 3)

[1546] 10. The system of claim 1, wherein the information summarized by the generative AI model includes historical data, prescription information, and test results. [Explanation of symbols]

[1547] 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 extracting patient data from an electronic medical record; a means for inputting the extracted patient data into a generative AI model; A means for generating the information summarized by the generative AI model as a draft document; a means for presenting the draft document to the user for review and editing; A system that includes a means for storing and publishing finalized documents.

2. 2. The system according to claim 1, wherein the means for extracting patient data from the electronic medical record accesses the database using a patient ID.

3. 10. The system of claim 1, wherein the information summarized by the generative AI model includes medical history, prescription medications, and test results.

Images