System

Abstract

A system is provided.SOLUTION: A server configured to receive the request and record the request in a database, a generative AI model configured to analyze request content received from the server and generate and transmit an automatic response, and a processor configured to display the automatic response generated by the generative AI model to the patient to determine a degree of urgency based on the request content and vital information of the patient to be diagnosed, A system comprising: triage means for transmitting an emergency notification as necessary; a server for receiving the emergency notification from the triage means and transmitting the notification to a tablet terminal of a nurse; means for transmitting the notification to the tablet terminal of the nurse; and video call means for realizing remote communication between the patient and the nurse.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] With conventional nurse call systems, responding to calls and questions from patients required physical intervention by nurses and a large amount of communication. This placed a significant burden on nurses' time and effort. Furthermore, nurse call systems were used for even minor questions and to provide information, creating the problem of inefficient responses. This made it difficult for nurses to focus on important tasks, potentially reducing the quality of patient care. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following solutions. A terminal is installed that sends requests when a patient presses a nurse call button, and this request is received and managed via a server that records the request in a database. Furthermore, by introducing a generative AI model that analyzes the received request content and generates an automatic response, it is possible to provide quick answers to common patient questions. Furthermore, a triage system is provided that determines the level of urgency based on the request content and the patient's vital signs, and if the urgency is high, a notification is sent to the nurse's tablet device. This allows nurses to respond quickly to emergencies. Additionally, a video call system is provided that enables remote communication between patients and nurses, allowing nurses to provide necessary instructions and advice remotely. This reduces the workload of nurses and improves the quality and efficiency of patient care.

[0006] A "terminal" is an electronic device operated by patients and nurses, and is used to send and receive nurse call messages and for remote communication.

[0007] The "server" is a central computing device that receives nurse call requests, records them in a database, and processes them, working in conjunction with the generative AI model and triage tools.

[0008] A "generative AI model" refers to an artificial intelligence algorithm or program that analyzes requests from patients and automatically generates appropriate responses.

[0009] "Triage measures" refers to an analysis and notification system that determines the level of urgency based on the content of the nurse call request and the patient's vital signs, and issues an emergency notification if necessary.

[0010] "Database" refers to an information storage device or system for recording and managing information such as nurse call request content, time, and patient ID.

[0011] "Vital information" refers to data related to a patient's body, such as temperature, pulse, blood pressure, and respiratory rate, and is used to determine the level of urgency through triage measures.

[0012] "Remote communication" refers to a method in which patients and nurses communicate through non-face-to-face means such as video calls, and is a system that enables instructions and advice to be given remotely.

[0013] "Notification" refers to important information or alerts sent from the server or triage tool to the nurse's tablet device, prompting the nurse to take immediate action. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[0036] System configuration

[0037] 1. Nurse call button and terminal

[0038] - Device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is made.

[0039] 2. Server

[0040] - Server: Receives nurse call requests, records them in a database, analyzes the request content, and sends it to the generative AI model for processing.

[0041] 3. Generative AI Models

[0042] - Generative AI model: Analyzes requests from patients and automatically generates answers. For example, in response to a request such as "What time is my medicine?", it generates an answer such as "The next medicine is due at 2:00 PM."

[0043] 4. Triage Measures

[0044] - Triage method: Determine the level of urgency based on the content of the nurse call and the patient's vital signs. If the level of urgency is high, a notification is sent to the nurse's tablet.

[0045] 5. Remote communication

[0046] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[0047] Program processing

[0048] Automated responses to general questions

[0049] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[0050] Device: Sends this request to the server.

[0051] Server: Receives requests and sends them to the generative AI model for processing.

[0052] Generative AI model (on the server): Analyzes the request and generates an appropriate answer, such as "The next medication time is at 2 p.m."

[0053] Server: Sends the generated answers to the patient's tablet device.

[0054] Terminal: Display the answers to the patient.

[0055] Triage

[0056] User (patient): Presses the nurse call button and enters an emergency request such as "I suddenly have chest pain."

[0057] Device: Sends this request to the server.

[0058] Server: Receives the request, obtains vital signs, and asks the generative AI model to determine the level of urgency.

[0059] Generative AI model (on the server): Integrates the request content and vital signs to calculate an urgency score. If "chest pain" is determined to be a serious symptom, a high urgency score is assigned.

[0060] Server: If the urgency score exceeds the threshold, a notification is sent to the nurse's tablet.

[0061] Terminal (Nurse): Receives notification and prepares to go to the patient's room immediately.

[0062] Remote Communication

[0063] User (patient): If the patient wants to contact a nurse via video call, he or she sends a request from the device.

[0064] Device: Sends a video call request to the server.

[0065] Server: Relays the request to the nurse's tablet.

[0066] Terminal (nurse): Receives requests and answers video calls.

[0067] Terminal (Patient): A video call is initiated and the patient explains their condition to the nurse.

[0068] Terminal (Nurse): Checks the situation and provides instructions and advice as needed.

[0069] Specific examples

[0070] Example 1: Common patient questions

[0071] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[0072] Terminal: Sends a question to the server.

[0073] Server: Requests processing from the generative AI model and obtains the answer.

[0074] Generative AI model (on the server): Generates the answer, "The next medication time is at 2:00 p.m."

[0075] Server: Sends the answer to the patient's device.

[0076] Terminal: Display answers to patient.

[0077] Example 2: Emergency response

[0078] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[0079] Device: Sends a request to the server.

[0080] Server: Determines the urgency based on the request and vital signs.

[0081] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[0082] Server: Sends emergency notifications to nurses' tablets.

[0083] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[0084] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. Each component works together to enable efficient nurse call response.

[0085] The processing flow will be explained below.

[0086] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[0087] Program processing

[0088] Automated responses to general questions

[0089] Step 1:

[0090] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[0091] Step 2:

[0092] The terminal converts this request into a digital signal and sends it to the server.

[0093] Step 3:

[0094] The server receives the request, analyzes the request content, and starts the process of requesting processing from the generative AI model.

[0095] Step 4:

[0096] The generative AI model (on the server) analyzes the request and generates an appropriate answer, such as "The next medication time is 2:00 PM."

[0097] Step 5:

[0098] The server sends the generated response data to the patient's tablet device.

[0099] Step 6:

[0100] The terminal displays the received data in text format to the patient.

[0101] Triage

[0102] Step 1:

[0103] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[0104] Step 2:

[0105] The terminal sends this emergency request to the server.

[0106] Step 3:

[0107] The server receives the request and retrieves and consolidates the patient's vital information from the database.

[0108] Step 4:

[0109] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[0110] Step 5:

[0111] The generative AI model (on the server) calculates an urgency score based on the request content and vital signs. In this case, "chest pain" is determined to be a serious symptom and a high urgency score is assigned.

[0112] Step 6:

[0113] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[0114] Step 7:

[0115] The terminal (nurse) receives the emergency notification, checks the details, and immediately prepares to go to the patient's room.

[0116] Remote Communication

[0117] Step 1:

[0118] The user (patient) sends a video call request from a tablet device to contact a nurse remotely.

[0119] Step 2:

[0120] The terminal sends a video call request to the server.

[0121] Step 3:

[0122] The server relays the received request to the nurse's tablet device.

[0123] Step 4:

[0124] The terminal (nurse) receives the video call request and responds.

[0125] Step 5:

[0126] A video call is initiated on the terminal (patient), and the patient explains their current condition to the nurse.

[0127] Step 6:

[0128] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[0129] Through these processing steps, this system reduces the workload of nurses and enables prompt and appropriate care for patients. Each component works together to enable efficient nurse call responses and the provision of high-quality services.

[0130] Example 1

[0131] 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."

[0132] Conventional nurse call systems can be slow to respond to patient requests, and rapid response is especially required in emergencies. This can also increase the workload of nurses, making it difficult to provide efficient medical care. To address these issues, a system that can respond quickly and appropriately to patient needs is needed.

[0133] 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.

[0134] In this invention, the server includes an electronic device that sends a request when a patient operates the nurse call button, an electronic computer that receives the request and records it in an information recording device, an AI generation means that analyzes the request content and generates and sends an automatic response, a priority determination means that determines the urgency based on the request content and biometric information and issues an emergency notification as necessary, and a video communication means that enables remote communication between the patient and nursing professionals. This reduces the workload of nurses and enables prompt and appropriate care for patients.

[0135] An "electronic device" is a device that allows a patient to operate a nurse call button to send a request.

[0136] An "electronic computer" is a computing device that has the function of receiving requests and recording them in an information recording device.

[0137] The "generative AI means" is an AI model that analyzes the request content received from the server and generates and sends an automatic response.

[0138] "Biometric information" is data that indicates the patient's health condition, such as heart rate, blood pressure, and respiratory rate.

[0139] The "priority determination means" is a device that determines the level of urgency based on the request content and biometric information, and issues an emergency notification as necessary.

[0140] A "nursing professional" is a health care worker trained to provide medical care to patients.

[0141] A "mobile terminal" is an electronic terminal device that can be carried by a nursing professional.

[0142] "Video communication means" refers to a communication means that enables video communication between a patient and a nursing professional.

[0143] This invention aims to improve the efficiency and quality of a nurse call system by using a generative AI model. This system consists of an electronic device used by the patient, a server, a generative AI means, a priority determination means, a mobile terminal for nursing professionals, and a video communication means.

[0144] System configuration

[0145] 1. Patient's electronic device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is sent from the device.

[0146] 2. Server: Receives requests sent from the patient's electronic device, records them in the information recording device, and sends the request content to the AI ​​generation means to request it to generate a response.

[0147] 3. Generative AI means: The generative AI means analyzes the request content and generates an appropriate automated response. For example, in response to the request "What time is my next medicine?", it generates the answer "My next medicine is due at 2:00 PM."

[0148] 4. Priority determination means: The priority determination means determines the urgency level based on the request content and the patient's biological information. For example, if a request is made such as "I suddenly have chest pain," this means calculates an urgency score, and if a high urgency score is assigned, a notification is sent to the nursing professional's mobile device.

[0149] 5. Mobile terminal of nursing specialist: The nursing specialist uses this terminal to receive emergency notifications, and upon receiving the notification, the nursing specialist immediately begins to respond.

[0150] 6. Video Calling: This has the function to conduct video calls between the patient and the nursing professional. The communication is carried out between the patient's electronic device, the server, and the nursing professional's mobile device.

[0151] Specific examples

[0152] Example 1: Common patient questions

[0153] The user (patient) presses the nurse call button and asks, "When is my next medication due?" The terminal sends this request to the server, which then asks the generation AI means to process it. The generation AI means generates the answer, "The next medication is due at 2:00 PM," and this answer is sent via the server to the patient's electronic device. Finally, the terminal displays the answer to the patient.

[0154] Example 2: Emergency response

[0155] The user (patient) presses the nurse call button to send a request saying, "I suddenly have chest pain." This request is sent from the device to the server, which acquires the biometric information and asks the AI ​​generation means to determine the level of urgency. The AI ​​generation means calculates a high urgency score, and the server notifies the nursing professional of this information on their mobile device. The nursing professional receives the emergency notification and immediately begins responding.

[0156] Prompt Sentence Examples

[0157] "When is my next dose?"

[0158] "I suddenly had a pain in my chest"

[0159] The system uses generative AI models and prompts to enable efficient and rapid nurse call responses, reducing the workload for nurses and improving the quality of patient care.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] Step 1:

[0162] The user (patient) operates the nurse call button to input a request.

[0163] Input: Patient question or request text (e.g., "When is my next medication?", "I suddenly have chest pain," etc.)

[0164] Output: Request data to be sent to the device

[0165] Specific operation: The patient touches the nurse call button on the tablet device and enters a question or request in the input field that appears. The input content is a specific question such as "When is my next medication due?"

[0166] Step 2:

[0167] The device sends a request to the server.

[0168] Input: Request data entered by the patient

[0169] Output: Request data sent to the server

[0170] Specific operation: The device sends a request to the server via Wi-Fi or wired LAN. The transmitted data includes the patient ID and the request content.

[0171] Step 3:

[0172] The server analyzes the received request and sends it to the generative AI model.

[0173] Input: Request data sent from the terminal

[0174] Output: Prompt sentence to be passed to the generative AI model

[0175] What it does: The server parses the request data and sends the appropriate prompt (e.g., "When is my next medicine due?") to the generative AI model.

[0176] Step 4:

[0177] A generative AI model analyzes the request and generates an answer.

[0178] Input: Prompt sent from the server

[0179] Output: Generated answer text

[0180] What it does: The generative AI model uses natural language processing algorithms to analyze the prompt and generate an appropriate response (e.g., "Your next medication is due at 2 p.m.").

[0181] Step 5:

[0182] The server sends the generated response to the patient's terminal.

[0183] Input: Answer text obtained from the generative AI model

[0184] Output: Response data sent to the patient's device

[0185] What it does: The server receives the answer from the generative AI model and sends this data to the patient's electronic device in the appropriate format.

[0186] Step 6:

[0187] The device displays the answers to the patient.

[0188] Input: Response data sent from the server

[0189] Output: Answer text displayed on the screen

[0190] Specific operation: The device receives the answer text and displays it on the screen in a popup or dedicated window. The user checks the display on the screen.

[0191] Step 7:

[0192] In an emergency, the server acquires vital information and asks the generative AI model to determine the level of urgency.

[0193] Input: Emergency request details and patient vitals

[0194] Output: Urgency score

[0195] Specific operation: The server obtains the patient's heart rate and blood pressure information from a medical database, sends it to the generative AI model, and performs an urgency assessment that integrates the request content and vital information.

[0196] Step 8:

[0197] A generative AI model calculates an urgency score.

[0198] Input: Request details and vital information sent from the server

[0199] Output: Urgency score

[0200] Specific operation: The generative AI model calculates an urgency score based on the request content and vital information, and returns a high urgency score to the server.

[0201] Step 9:

[0202] The server sends a notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[0203] Input: Urgency score and threshold

[0204] Output: Emergency notification to nursing professional's mobile device

[0205] Specific operation: The server evaluates the urgency score and sends a push notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[0206] Step 10:

[0207] The terminal (nursing professional) receives the emergency notification and immediately begins responding.

[0208] Input: Urgent notification sent from the server

[0209] Output: Emergency response by nursing professionals initiated

[0210] Specific actions: The nursing professional checks the notification on the mobile device and immediately initiates the necessary action (e.g., rushing to the scene).

[0211] Step 11:

[0212] The user (patient) makes a video call request.

[0213] Input: Video call request (e.g., "I'd like to video call with a nurse")

[0214] Output: Video call request data from the device to the server

[0215] Specific actions: The patient activates the video call function on the tablet device and presses the call button.

[0216] Step 12:

[0217] The terminal sends a video call request to the server.

[0218] Input: Patient video call request data

[0219] Output: Data sent to the server

[0220] Specific operation: The device performs the communication processing necessary to send a video call request to the server.

[0221] Step 13:

[0222] The server relays the video call request to the nursing professional's mobile terminal.

[0223] Input: Patient video call request data

[0224] Output: Video call request data to the nursing professional's mobile device

[0225] Specific operation: The server receives the patient's video call request and relays it to the nursing professional's mobile device.

[0226] Step 14:

[0227] The terminal (nursing professional) answers the video call and communicates with the patient via the screen.

[0228] Input: Video call request from server

[0229] Output: Start a video call with the patient

[0230] What it does: A nursing professional answers a video call on a mobile device, checks on the patient's condition, and provides necessary instructions and advice.

[0231] This program utilizes a generative AI model and prompts to efficiently perform a series of tasks, including analyzing requests, generating automatic responses, determining urgency, and relaying video calls, thereby enabling prompt and appropriate responses to patients.

[0232] (Application example 1)

[0233] 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."

[0234] Modern nurse call systems are important for reducing the workload of nurses and providing prompt and appropriate care to patients. However, similar challenges exist in manufacturing. Robot operators in manufacturing must be able to quickly respond to problems and questions, and when errors occur, they must be able to immediately assess the urgency and take appropriate action. Technical means for facilitating communication between workers and management are also important. The present invention provides a system that solves these challenges.

[0235] 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.

[0236] In this invention, the server includes a terminal that sends a request when a patient operates a nurse call button, a means for receiving the request and recording it in a database, a means for displaying an automated response generated by the generative AI model to the patient, a means for determining the level of urgency based on the request content and the patient's vital signs and sending a notification to the nurse's tablet device, a video call means for enabling remote communication between the patient and the nurse, a means for generating a response when a robot operator inputs a question in a factory and displaying it on a robot operation panel, a means for integrating error messages and sensor data based on the robot operator's input and determining the level of urgency, a means for sending a notification to a manager's terminal when the level of urgency exceeds a threshold, and a means for enabling video calls between the robot operator and the manager. This enables prompt responses to questions from robot operators and appropriate responses to emergencies even at manufacturing sites.

[0237] The "terminal that sends a request when a patient presses the nurse call button" is a device that sends a request when a patient presses the nurse call button in an emergency or when they have a question.

[0238] The "server that receives requests and records them in a database" is a computer that receives requests from patients and stores the contents of those requests in a database.

[0239] A "generative AI model that analyzes request content and generates and sends an automatic response" is an artificial intelligence system that automatically analyzes the content of a received request and generates and sends an appropriate automatic response.

[0240] A "terminal that displays the generated automated response to the patient" is a device that displays the automated response generated by the generative AI model so that the patient can check it.

[0241] "Triage method that determines the level of urgency based on the request content and the patient's vital signs, and issues an emergency notification if necessary" is a function that integrates the request content and the patient's vital signs to evaluate the level of urgency, and issues an emergency notification if the level of urgency is high.

[0242] The "server that receives emergency notifications from the triage means and sends notifications to the tablet devices of nurses" is a computer that receives emergency notifications sent by the triage means and sends the notifications to the tablet devices held by nurses.

[0243] The "means for sending a notification to the tablet terminal of the nurse" is a function for sending an emergency notification from the server to the tablet terminal of the nurse.

[0244] "Video calling means enabling remote communication between patients and nurses" is a video calling function that allows patients and nurses to communicate directly from a distance.

[0245] "A means of using a generative AI model to generate a response when a robot operator in a factory inputs a question and displays it on the robot operation panel" is a function that analyzes a question input by a robot operator in a factory, generates an automatic response, and displays it on the robot operation panel.

[0246] "Means for integrating error messages and sensor data based on input from the robot operator and determining the level of urgency" is a function that analyzes the error messages input by the robot operator and the robot's sensor data and evaluates the level of urgency.

[0247] The "means for sending a notification to the administrator's terminal when the urgency exceeds a threshold" is a function for sending a notification to the terminal held by the administrator when the urgency exceeds a set threshold.

[0248] "Means for realizing video calls between a robot operator and an administrator" is a function that enables a robot operator and an administrator to communicate via video calls.

[0249] This invention utilizes generative AI models to improve the efficiency and quality of nurse call systems. We also describe a system that can support robot operators and respond to emergencies in the manufacturing industry.

[0250] The basic configuration of the system is as follows:

[0251] Hardware and Software

[0252] Terminal: A tablet device used by the patient and robot operator, which displays a nurse call button and a question input interface.

[0253] Server: Receives requests, submits them to the generative AI model, and records the results.

[0254] Generative AI model: An artificial intelligence system that analyzes requests and generates automated responses.

[0255] Triage measures: Evaluate requests by combining vital signs and sensor data to determine urgency.

[0256] Remote communication means: The ability to conduct video calls between patients and nurses, and between robot operators and administrators.

[0257] Software Configuration

[0258] The system includes the following major software components:

[0259] Flask: A web framework for building API servers and accepting requests.

[0260] HuggingFace's transformers library: Generative AI models for question-answering.

[0261] Automated Response and Triage

[0262] Automated responses to general questions

[0263] The patient presses the nurse call button on the tablet device and enters a question.

[0264] The server receives the request and asks the generative AI model to process it.

[0265] The generative AI model analyzes the question and generates an appropriate answer.

[0266] The server sends the generated answer to the patient's tablet device and displays it to the patient.

[0267] Urgency assessment and notification

[0268] When a patient inputs an emergency request, the server receives the request and obtains vital information.

[0269] The triage tool integrates the request details with vital information and calculates an urgency score.

[0270] If the urgency score exceeds the threshold, the server sends an emergency notification to the nurse's tablet device.

[0271] Factory robot applications

[0272] The robot operator inputs questions from the operation panel.

[0273] The server receives the request and asks the generative AI model to process it.

[0274] The generative AI model generates an appropriate response and displays it on the robot's control panel.

[0275] If the robot operator inputs an error, the server integrates the sensor data and the error message to determine the urgency.

[0276] If the urgency exceeds the threshold, an emergency notification is sent to the administrator terminal.

[0277] Remote Communication

[0278] If a patient or robot operator wishes to have a video call, they send a request to the server.

[0279] The server relays the video call request to the nurse or administrator's device.

[0280] Video calls are initiated on the nurses' and administrators' devices, enabling direct communication.

[0281] Specific examples

[0282] Question-answering prompt examples

[0283] "When is my next dose?"

[0284] "An error suddenly occurred"

[0285] This allows the system of the present invention to apply the functions of a nurse call system to manufacturing sites, enabling quick and accurate responses to different requests.

[0286] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0287] Step 1:

[0288] A user (patient or robot operator) presses the nurse call button or inputs a question from a terminal, and the input request is sent to the server by the terminal.

[0289] Input: User question or request

[0290] Output: Request data sent to the server

[0291] Step 2:

[0292] The server analyzes the received request and requests the generative AI model to process it. The request content is converted into an appropriate prompt sentence and passed to the generative AI model.

[0293] Input: Request data received by the server

[0294] Output: The prompt sent to the generative AI model

[0295] Step 3:

[0296] The generative AI model analyzes the question based on the prompt and generates an appropriate answer, which is then returned to the server.

[0297] Input: Prompt sentence for the generative AI model

[0298] Output: The generated answer

[0299] Step 4:

[0300] The server receives the answer from the generative AI model and sends it to the patient or robot operator's device, which displays the answer to the user.

[0301] Input: Answer generated by the generative AI model

[0302] Output: The answer displayed on the user's terminal

[0303] Step 5:

[0304] When a patient or a robot operator inputs an urgent request, vital information or sensor data is sent to the server at the same time as the request.

[0305] Input: Emergency request and vital signs or sensor data

[0306] Output: Urgent request data sent to the server

[0307] Step 6:

[0308] The server integrates the emergency request with vital signs or sensor data, calculates an urgency score using triage methods, and sends an emergency notification if the urgency score exceeds a threshold.

[0309] Input: Emergency request data and vital signs or sensor data

[0310] Output: Urgency score and emergency notification

[0311] Step 7:

[0312] An emergency notification is sent from the server to the tablet device of the nurse or administrator, who then takes immediate action.

[0313] Input: Urgent notification from the server

[0314] Output: Emergency notification displayed on the nurse or manager's terminal

[0315] Step 8:

[0316] When a user (patient or robot operator) requests a video call, the request is sent from the terminal to the server, which relays the request to the other terminal and the video call begins.

[0317] Input: A video call request from a user

[0318] Output: Video call request relayed to the other device and video call initiated

[0319] 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.

[0320] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[0321] System configuration

[0322] 1. Nurse call button and terminal

[0323] - Device: A tablet device used by patients. It has a touch interface with a nurse call button. When a patient presses this button, a request is sent. The device also has an emotion engine to recognize the patient's emotions.

[0324] 2. Server

[0325] - Server: Receives nurse call requests, records them in a database, analyzes the request content and emotional state, and sends them to the generative AI model for processing.

[0326] 3. Generative AI Models

[0327] - Generative AI model: Analyzes the patient's request and emotional state and automatically generates a response. For example, in response to the request "What time is my medicine?", it generates a response such as "The next medicine is due at 2:00 PM."

[0328] 4. Triage Measures

[0329] - Triage method: Determines the level of urgency based on the content of the nurse call, the patient's vital signs, and their emotional state. If the level of urgency is high, a notification is sent to the nurse's tablet.

[0330] 5. Remote communication

[0331] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[0332] Program processing

[0333] Automated responses to general questions

[0334] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[0335] Terminal: Sends this request and the emotional state generated by the emotion engine to the server.

[0336] Server: Receives the request, analyzes the request content and emotional state, and initiates the process to request processing from the generative AI model.

[0337] Generative AI model (on the server): Analyzes the request and emotional state and generates an appropriate answer, for example, "The next medication time is 2:00 PM."

[0338] Server: Sends the generated response data to the patient's tablet device.

[0339] Terminal: Displays the received data to the patient in text format.

[0340] Triage

[0341] User (patient): Presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[0342] Device: Sends this urgent request and the emotional state generated by the emotion engine to the server.

[0343] Server: Receives the request and retrieves and integrates the patient's vital signs and emotional state from the database.

[0344] Server: Sends the integrated information to the generative AI model and requests it to determine the urgency of the situation.

[0345] Generative AI model (on the server): Calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[0346] Server: If the urgency score exceeds the set threshold, an emergency notification is immediately sent to the nurse's tablet device.

[0347] Terminal (Nurse): Receives notification, checks details, and prepares to go to the patient's room immediately.

[0348] Remote Communication

[0349] User (patient): If the patient wants to contact a nurse remotely, they can make a video call request from their tablet device.

[0350] Device: Sends a video call request and the emotional state generated by the emotion engine to the server.

[0351] Server: Relays the received request to the nurse's tablet device.

[0352] Terminal (nurse): Receives and responds to video call requests.

[0353] Terminal (Patient): A video call is initiated and the patient explains their current condition to the nurse.

[0354] Terminal (nurse): Checks on the patient's condition via video call and provides instructions and advice as needed.

[0355] Specific examples

[0356] Example 1: Common patient questions

[0357] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[0358] Terminal: Sends the question and emotional state to the server.

[0359] Server: Sends the request content and emotional state to the generation AI model for processing and obtains the answer.

[0360] Generative AI model (on the server): Generates the answer, "The next medicine time is 2:00 p.m."

[0361] Server: Sends the answer to the patient's device.

[0362] Terminal: Display the answers to the patient.

[0363] Example 2: Emergency response

[0364] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[0365] Terminal: Sends the request and emotional state to the server.

[0366] Server: Determines the urgency based on the request, vital information, and emotional state.

[0367] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[0368] Server: Sends emergency notifications to nurses' tablets.

[0369] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[0370] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[0371] The processing flow will be explained below.

[0372] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[0373] Program processing

[0374] Automated responses to general questions

[0375] Step 1:

[0376] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[0377] Step 2:

[0378] The terminal converts the request and the patient's emotional state analyzed by the emotion engine into a digital signal and sends it to the server.

[0379] Step 3:

[0380] The server receives the request, analyzes the request content and emotional state, and initiates the process of requesting processing from the generative AI model.

[0381] Step 4:

[0382] A generative AI model (on the server) analyzes the request and emotional state and generates an appropriate answer, such as "Your next medication is due at 2 p.m."

[0383] Step 5:

[0384] The server sends the generated response data to the patient's tablet device.

[0385] Step 6:

[0386] The terminal displays the received data in text format to the patient.

[0387] Triage

[0388] Step 1:

[0389] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[0390] Step 2:

[0391] The terminal sends this emergency request and the patient's emotional state analyzed by the emotion engine to the server.

[0392] Step 3:

[0393] The server receives the request and retrieves and integrates the patient's vital information and emotional state from the database.

[0394] Step 4:

[0395] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[0396] Step 5:

[0397] The generative AI model (on the server) calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[0398] Step 6:

[0399] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[0400] Step 7:

[0401] The terminal (nurse) receives the notification, checks the details, and immediately prepares to head to the patient's room.

[0402] Remote Communication

[0403] Step 1:

[0404] When a user (patient) wants to contact a nurse remotely, they send a video call request from their tablet device.

[0405] Step 2:

[0406] The device sends a video call request and the patient's emotional state analyzed by the emotion engine to the server.

[0407] Step 3:

[0408] The server relays the received request to the nurse's tablet device.

[0409] Step 4:

[0410] The terminal (nurse) receives the video call request and responds.

[0411] Step 5:

[0412] A video call is initiated from the terminal (patient), and the patient explains their current condition to the nurse.

[0413] Step 6:

[0414] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[0415] Specific examples

[0416] Example 1: Common patient questions

[0417] Step 1:

[0418] The user (patient) presses the nurse call button and asks, "When is my next medication due?"

[0419] Step 2:

[0420] The device sends the question and emotional state to the server.

[0421] Step 3:

[0422] The server requests the request content and emotional state to be processed by a generative AI model and obtains a response.

[0423] Step 4:

[0424] The generative AI model (in the server) generates the answer, "The next medication time is 2:00 p.m."

[0425] Step 5:

[0426] The server sends the response to the patient's terminal.

[0427] Step 6:

[0428] The device displays the answers to the patient.

[0429] Example 2: Emergency response

[0430] Step 1:

[0431] The user (patient) presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[0432] Step 2:

[0433] The device sends the request and emotional state to the server.

[0434] Step 3:

[0435] The server determines the urgency based on the request, vital information, and emotional state.

[0436] Step 4:

[0437] The generative AI model (within the server) calculates a high urgency score and notifies the server.

[0438] Step 5:

[0439] The server sends an emergency notification to the nurse's tablet device.

[0440] Step 6:

[0441] The terminal (nurse) receives the emergency notification and immediately performs on-site intervention.

[0442] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[0443] Example 2

[0444] 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."

[0445] When patients face an emergency situation in the hospital, or when they have everyday questions, it is difficult to get a quick and accurate answer. Another problem is that the workload of nurses increases, making it difficult to respond quickly. In particular, there is a lack of response that takes into account the emotional state of patients, and psychological care for patients is not being provided adequately. This can lead to a decrease in patient satisfaction and a sense of security.

[0446] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0447] In this invention, the server includes a terminal that transmits the request and emotional state when the patient operates the nurse call button, a server that receives the request and emotional state, records it in a database, and begins analysis, a generative AI model that analyzes the request content and emotional state received from the server and generates and transmits an automatic response, a terminal that displays the automatic response generated by the generative AI model to the patient, triage means that determines the urgency based on the request content, the patient's vital signs, and the patient's emotional state and sends an emergency notification as necessary, a server that receives the emergency notification from the triage means and sends the notification to the nurse's tablet device, means for sending the notification to the nurse's tablet device, and video call means that enables remote communication between the patient and the nurse. This enables a quick and accurate response to the patient's request and realizes a comprehensive response that also includes psychological care for the patient.

[0448] A "terminal" is a device that allows a patient to operate a nurse call button and has the function of transmitting requests and emotional states.

[0449] The "server" is a central control unit that receives requests and emotional states sent from the terminals, records them in a database and initiates the analysis.

[0450] A "generative AI model" is an artificial intelligence model that analyzes the request content and emotional state received from the server and generates and sends an automatic response.

[0451] The "triage method" is a system that determines the level of urgency based on the request content, the patient's vital signs, and their emotional state, and has the ability to send emergency notifications if necessary.

[0452] "Vital information" refers to key physiological data related to maintaining a patient's life, such as blood pressure, heart rate, and body temperature.

[0453] An "emergency notification" is alert information that is sent based on the level of urgency determined by the triage means and prompts nurses to take prompt action.

[0454] "Remote communication" refers to a means for patients and nurses to communicate remotely, including systems such as video calls.

[0455] "Emotional state" is information that indicates the psychological state of the patient analyzed by the emotion engine, and includes anxiety, relief, excitement, etc.

[0456] The present invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. The system of the present invention is configured as follows.

[0457] System Components

[0458] Nurse call button and terminal

[0459] The terminal is a tablet device that allows patients to operate the nurse call button. This terminal has the function of transmitting requests and emotional states. It also has an emotion engine that analyzes the patient's emotional state.

[0460] server

[0461] The server receives requests and emotional states sent from the devices, records them in a database, and then analyzes the request content and emotional state and requests processing from the generative AI model.

[0462] Generative AI Models

[0463] The generative AI model analyzes the request content and emotional state received from the server and generates an automatic response. For example, the model uses natural language processing technology to generate an appropriate response such as "The next medicine time is 2:00 PM" in response to a request such as "When is the next medicine time?"

[0464] Triage Measures

[0465] The triage system determines the level of urgency based on the request, the patient's vital signs, and their emotional state. If the urgency is high, the system sends an emergency notification to the nurse's tablet.

[0466] Remote Communication

[0467] To realize remote communication between patients and nurses, the video call function of the device is used. A video call request is sent from the device to a server, which then relays the request to the nurse's tablet device, and the video call begins.

[0468] Specific examples

[0469] Automated responses to general questions

[0470] 1. User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[0471] 2. Terminal: Sends the question and the emotional state determined by the emotion engine to the server.

[0472] 3. Server: Sends the request to the AI ​​model for processing and obtains the answer.

[0473] 4. Generative AI model: Generates the answer, "The next medication time is at 2:00 PM."

[0474] 5. Server: Sends the answer to the patient's device.

[0475] 6. Terminal: Displays the answers to the patient.

[0476] Emergency response

[0477] 1. User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[0478] 2. Terminal: Sends the request content and the emotional state determined by the emotion engine to the server.

[0479] 3. Server: Determines the urgency of the request by integrating the request content, vital signs, and emotional state.

[0480] 4. Generative AI model: Calculates a high urgency score and notifies the server.

[0481] 5. Server: Sends emergency notifications to the nurses' tablets.

[0482] 6. Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[0483] Prompt Sentence Examples

[0484] "When is my next dose?"

[0485] "I suddenly had a pain in my chest"

[0486] Using the above components and processes, the system of the present invention responds quickly and appropriately to patient requests, reducing the workload of nurses while providing comprehensive care, including psychological care for patients.

[0487] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0488] Step 1:

[0489] User (patient): Presses the nurse call button to input a request. For example, the user might ask, "When is my next medication due?" This input is the starting point for the entire system process.

[0490] Step 2:

[0491] Terminal: Collects requests entered by the patient and the corresponding emotional state (e.g., "anxiety") calculated by the emotion engine. Sends this data to the server. The input is the patient's question and emotional data, and the output is sending this data to the server.

[0492] Step 3:

[0493] Server: Receives the sent request and emotional state. Records the received data in a database and starts the analysis process. The input is the request and emotional data sent from the device, and the output is a processing request to the generative AI model.

[0494] Step 4:

[0495] Generative AI model (in the server): Analyzes the request content and emotional state received from the server. Generates an automatic response using natural language processing technology. The input is the request and emotional data sent from the server, and the output is the generated answer (e.g., "The next medication time is 2 p.m.").

[0496] Step 5:

[0497] Server: Receives the answers generated by the generative AI model and sends them to the patient's tablet device. The input is the answer data from the generative AI model, and the output is the sending of the answer data to the device.

[0498] Step 6:

[0499] Terminal: Receives the answer sent from the server and displays it on the screen. The patient confirms it. The input is the answer data from the server, and the output is the answer displayed on the screen.

[0500] Step 7:

[0501] User (Patient): If they have any further questions or concerns, they press the nurse call button again to enter their request. This cycle provides continuous support.

[0502] Triage

[0503] Step 1:

[0504] User (patient): Presses the nurse call button and inputs a request saying, "I suddenly have chest pain." This is an emergency request.

[0505] Step 2:

[0506] Terminal: Collects requests and emotional states (e.g., "fear") from the emotion engine and sends them to the server. The input is the patient's urgent request and emotional data, and the output is the data sent to the server.

[0507] Step 3:

[0508] Server: Receives emergency requests and emotional states, and retrieves and integrates the patient's vital information from the database. The input is data from the device and vital information from the database, and the output is the integrated data.

[0509] Step 4:

[0510] Generative AI model (on the server): Analyzes the integrated data and calculates the urgency score. The input is the integrated request, emotional state, and vital information, and the output is the urgency score.

[0511] Step 5:

[0512] Server: If the urgency score exceeds the threshold, it sends an emergency notification to the nurse's tablet. The input is the urgency score, and the output is the emergency notification to the nurse's device.

[0513] Step 6:

[0514] Terminal (nurse): Receives emergency notification, checks detailed information, and immediately prepares to go to the patient's room. The input is the emergency notification, and the output is the nurse's actions.

[0515] Remote Communication

[0516] Step 1:

[0517] User (patient): Sends a video call request from a tablet device. The input is a video call request.

[0518] Step 2:

[0519] Terminal: Sends a video call request and the emotional state (e.g., "anxiety") generated by the emotion engine to the server. The input is the video call request and emotion data, and the output is the data sent to the server.

[0520] Step 3:

[0521] Server: Relays video call requests to the nurse's tablet. The input is the video call request from the device, and the output is the relayed data to the nurse's device.

[0522] Step 4:

[0523] Terminal (nurse): Receives and responds to video call requests. The input is a video call request, and the output is the start of a video call.

[0524] Step 5:

[0525] User (patient): A video call is initiated with a nurse, describing the current state. The input is the initiation of the video call, and the output is the patient description.

[0526] Step 6:

[0527] Terminal (nurse): Checks the patient's condition via video call and provides instructions and advice as needed. The input is the patient's explanation, and the output is the nurse's instructions and advice.

[0528] (Application example 2)

[0529] 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."

[0530] Conventional nurse call systems have difficulty responding quickly and appropriately to requests from patients, placing a heavy burden on nurses. They also struggle to take into account the patient's emotional state, which can lead to poor communication quality. Similarly, in brick-and-mortar stores, it's difficult to respond quickly and appropriately to customer requests, often resulting in poor customer satisfaction.

[0531] 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 receiving and processing requests operated by patients and customers, generation AI model means for analyzing the request content and emotional state and generating an automatic response, means for displaying the generated automatic response and realizing remote communication, and triage means. This enables quick and appropriate responses to requests from patients and customers, reduces the burden on nurses and staff, and improves patient and customer satisfaction.

[0532] A "patient" is a person who receives treatment or care at a medical institution or hospital.

[0533] A "nurse call button" is an interface device that patients use to make requests or contact nurses in an emergency.

[0534] A "terminal" is an electronic device used to send and receive requests at a medical institution or physical store.

[0535] A "server" is a device that provides the computing resources to receive and analyze requests, and generate and send automated responses.

[0536] A "generative AI model" is a system equipped with artificial intelligence technology that analyzes the request content and emotional state and automatically generates an appropriate response.

[0537] An "automated response" is an answer or response automatically provided in response to a request by a generative AI model.

[0538] "Triage measures" is a function that determines the urgency of a request based on its content and emotional state, and sends an emergency notification if necessary.

[0539] "Remote communication" is a means by which people in distant locations communicate with each other via electronic devices.

[0540] "Video calling means" is a function that enables real-time communication by sending and receiving audio and video through a terminal.

[0541] An "emergency notification" is a notification message sent to nurses and staff when a high level of urgency is determined.

[0542] A "customer support button" is an interface device that a customer uses to request support within a store.

[0543] The "urgency score" is a numerical assessment of the urgency calculated based on the request content, emotional state, vital information, etc.

[0544] This invention utilizes generative AI models and emotion engines to improve the efficiency and quality of responses in nurse call systems and brick-and-mortar customer support systems.

[0545] System configuration

[0546] 1. Nurse call button and customer support button and terminal

[0547] The terminal is an electronic device used by patients and customers in medical institutions and brick-and-mortar stores, and displays a nurse call button or customer support button on the touch interface. When a patient or customer presses the button, a request is sent. The terminal also has an emotion engine for recognizing emotions.

[0548] 2. Server

[0549] The server receives nurse call and customer support requests, records them in a database, analyzes the request content and emotional state, requests a generative AI model to process them, records the generated automated response, and sends it back to the device.

[0550] 3. Generative AI Models

[0551] The generative AI model analyzes the request and the patient's emotional state and automatically generates a response. For example, in response to a patient's request, "When is my medicine due?", the model might respond, "The next medicine is due at 2 p.m."

[0552] 4. Triage Measures

[0553] The triage system determines the level of urgency based on the content of nurse call and customer support requests, the patient's vital signs, and the customer's emotional state. If the level of urgency is high, an emergency notification is sent to the staff member's tablet device.

[0554] 5. Remote communication

[0555] The remote communication function allows video calls between patients / customers and nurses / staff via terminals. This function is realized by communication between the server and terminals.

[0556] What the program does

[0557] The server performs the following process.

[0558] 1. Sentiment analysis:

[0559] Send the patient or customer request text to an emotion engine API (e.g., EmotionAPI) to analyze the emotional state.

[0560] 2. Response generation:

[0561] Have a generative AI model API (e.g., AIModelAPI) generate an appropriate response using the request text and the analyzed emotional state.

[0562] 3. Staff Notification:

[0563] The level of urgency is determined based on the emotional state and the generated response, and if the level of urgency is high, an emergency notification is sent to a nurse or staff member via a triage means.

[0564] Specific examples

[0565] Example 1: Common patient questions

[0566] Patient: "When is my next dose?"

[0567] Terminal: Sends questions and emotional states to the server.

[0568] Server: Sends the request to the generative AI model and generates an answer such as "The next medicine time is at 2:00 p.m."

[0569] Terminal: Displays the generated answers to the patient.

[0570] Example 2: Urgent customer request

[0571] Customer: "What items are in stock?"

[0572] Terminal: Sends questions and emotional states to the server.

[0573] Server: Sends the request content to the generative AI model and generates a response.

[0574] High stress levels are identified using the emotion engine.

[0575] Server: Sends emergency notifications to staff.

[0576] Terminal: Display the answer to the customer.

[0577] Prompt Sentence Examples

[0578] "What products are in stock?"

[0579] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0580] Step 1:

[0581] The patient or customer (user) operates the nurse call button or customer support button on the terminal. They input the request details as text. This operation causes the terminal to send the request details and the emotional state analyzed by the emotion engine to the server. The input is the request text and emotional data, and the output is data sent to the server.

[0582] Step 2:

[0583] The server stores the received request content and emotional state. Then, it converts the request content and emotional state into JSON format to send to the generative AI model. The input is the request text and emotional data, and the output is the input data to the generative AI model.

[0584] Step 3:

[0585] The generative AI model receives the request content and emotional state from the server, performs text analysis, and generates an appropriate response based on the analyzed results. The input is the request text and emotional data, and the output is the response text.

[0586] Step 4:

[0587] The server analyzes the response text received from the generative AI model and, if necessary, determines the level of urgency using triage methods. If the level of urgency is determined to be high, an emergency notification is sent to the terminals of staff and nurses. The input is the response text and emotion data, and the output is the emergency notification data or response data.

[0588] Step 5:

[0589] The terminal displays the response text received from the server to the user. If the urgency is high, a notification by the triage means is also displayed. The input is the response text from the server, and the output is the display to the user.

[0590] Step 6:

[0591] The nurse or staff member (user) who receives the emergency notification checks the content of the notification and takes on-site action as necessary. This process ensures a prompt response to the user. The input is the emergency notification data, and the output is the on-site response action.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] [Second embodiment]

[0596] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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."

[0608] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[0609] System configuration

[0610] 1. Nurse call button and terminal

[0611] - Device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is made.

[0612] 2. Server

[0613] - Server: Receives nurse call requests, records them in a database, analyzes the request content, and sends it to the generative AI model for processing.

[0614] 3. Generative AI Models

[0615] - Generative AI model: Analyzes requests from patients and automatically generates answers. For example, in response to a request such as "What time is my medicine?", it generates an answer such as "The next medicine is due at 2:00 PM."

[0616] 4. Triage Measures

[0617] - Triage method: Determine the level of urgency based on the content of the nurse call and the patient's vital signs. If the level of urgency is high, a notification is sent to the nurse's tablet.

[0618] 5. Remote communication

[0619] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[0620] Program processing

[0621] Automated responses to general questions

[0622] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[0623] Device: Sends this request to the server.

[0624] Server: Receives requests and sends them to the generative AI model for processing.

[0625] Generative AI model (on the server): Analyzes the request and generates an appropriate answer, such as "The next medication time is at 2 p.m."

[0626] Server: Sends the generated answers to the patient's tablet device.

[0627] Terminal: Display the answers to the patient.

[0628] Triage

[0629] User (patient): Presses the nurse call button and enters an emergency request such as "I suddenly have chest pain."

[0630] Device: Sends this request to the server.

[0631] Server: Receives the request, obtains vital signs, and asks the generative AI model to determine the level of urgency.

[0632] Generative AI model (on the server): Integrates the request content and vital signs to calculate an urgency score. If "chest pain" is determined to be a serious symptom, a high urgency score is assigned.

[0633] Server: If the urgency score exceeds the threshold, a notification is sent to the nurse's tablet.

[0634] Terminal (Nurse): Receives notification and prepares to go to the patient's room immediately.

[0635] Remote Communication

[0636] User (patient): If the patient wants to contact a nurse via video call, he or she sends a request from the device.

[0637] Device: Sends a video call request to the server.

[0638] Server: Relays the request to the nurse's tablet.

[0639] Terminal (nurse): Receives requests and answers video calls.

[0640] Terminal (Patient): A video call is initiated and the patient explains their condition to the nurse.

[0641] Terminal (Nurse): Checks the situation and provides instructions and advice as needed.

[0642] Specific examples

[0643] Example 1: Common patient questions

[0644] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[0645] Terminal: Sends a question to the server.

[0646] Server: Requests processing from the generative AI model and obtains the answer.

[0647] Generative AI model (on the server): Generates the answer, "The next medication time is at 2:00 p.m."

[0648] Server: Sends the answer to the patient's device.

[0649] Terminal: Display answers to patient.

[0650] Example 2: Emergency response

[0651] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[0652] Device: Sends a request to the server.

[0653] Server: Determines the urgency based on the request and vital signs.

[0654] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[0655] Server: Sends emergency notifications to nurses' tablets.

[0656] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[0657] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. Each component works together to enable efficient nurse call response.

[0658] The processing flow will be explained below.

[0659] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[0660] Program processing

[0661] Automated responses to general questions

[0662] Step 1:

[0663] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[0664] Step 2:

[0665] The terminal converts this request into a digital signal and sends it to the server.

[0666] Step 3:

[0667] The server receives the request, analyzes the request content, and starts the process of requesting processing from the generative AI model.

[0668] Step 4:

[0669] The generative AI model (on the server) analyzes the request and generates an appropriate answer, such as "The next medication time is 2:00 PM."

[0670] Step 5:

[0671] The server sends the generated response data to the patient's tablet device.

[0672] Step 6:

[0673] The terminal displays the received data in text format to the patient.

[0674] Triage

[0675] Step 1:

[0676] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[0677] Step 2:

[0678] The terminal sends this emergency request to the server.

[0679] Step 3:

[0680] The server receives the request and retrieves and consolidates the patient's vital information from the database.

[0681] Step 4:

[0682] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[0683] Step 5:

[0684] The generative AI model (on the server) calculates an urgency score based on the request content and vital signs. In this case, "chest pain" is determined to be a serious symptom and a high urgency score is assigned.

[0685] Step 6:

[0686] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[0687] Step 7:

[0688] The terminal (nurse) receives the emergency notification, checks the details, and immediately prepares to go to the patient's room.

[0689] Remote Communication

[0690] Step 1:

[0691] The user (patient) sends a video call request from a tablet device to contact a nurse remotely.

[0692] Step 2:

[0693] The terminal sends a video call request to the server.

[0694] Step 3:

[0695] The server relays the received request to the nurse's tablet device.

[0696] Step 4:

[0697] The terminal (nurse) receives the video call request and responds.

[0698] Step 5:

[0699] A video call is initiated on the terminal (patient), and the patient explains their current condition to the nurse.

[0700] Step 6:

[0701] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[0702] Through these processing steps, this system reduces the workload of nurses and enables prompt and appropriate care for patients. Each component works together to enable efficient nurse call responses and the provision of high-quality services.

[0703] Example 1

[0704] 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."

[0705] Conventional nurse call systems can be slow to respond to patient requests, and rapid response is especially required in emergencies. This can also increase the workload of nurses, making it difficult to provide efficient medical care. To address these issues, a system that can respond quickly and appropriately to patient needs is needed.

[0706] 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.

[0707] In this invention, the server includes an electronic device that sends a request when a patient operates the nurse call button, an electronic computer that receives the request and records it in an information recording device, an AI generation means that analyzes the request content and generates and sends an automatic response, a priority determination means that determines the urgency based on the request content and biometric information and issues an emergency notification as necessary, and a video communication means that enables remote communication between the patient and nursing professionals. This reduces the workload of nurses and enables prompt and appropriate care for patients.

[0708] An "electronic device" is a device that allows a patient to operate a nurse call button to send a request.

[0709] An "electronic computer" is a computing device that has the function of receiving requests and recording them in an information recording device.

[0710] The "generative AI means" is an AI model that analyzes the request content received from the server and generates and sends an automatic response.

[0711] "Biometric information" is data that indicates the patient's health condition, such as heart rate, blood pressure, and respiratory rate.

[0712] The "priority determination means" is a device that determines the level of urgency based on the request content and biometric information, and issues an emergency notification as necessary.

[0713] A "nursing professional" is a health care worker trained to provide medical care to patients.

[0714] A "mobile terminal" is an electronic terminal device that can be carried by a nursing professional.

[0715] "Video communication means" refers to a communication means that enables video communication between a patient and a nursing professional.

[0716] This invention aims to improve the efficiency and quality of a nurse call system by using a generative AI model. This system consists of an electronic device used by the patient, a server, a generative AI means, a priority determination means, a mobile terminal for nursing professionals, and a video communication means.

[0717] System configuration

[0718] 1. Patient's electronic device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is sent from the device.

[0719] 2. Server: Receives requests sent from the patient's electronic device, records them in the information recording device, and sends the request content to the AI ​​generation means to request it to generate a response.

[0720] 3. Generative AI means: The generative AI means analyzes the request content and generates an appropriate automated response. For example, in response to the request "What time is my next medicine?", it generates the answer "My next medicine is due at 2:00 PM."

[0721] 4. Priority determination means: The priority determination means determines the urgency level based on the request content and the patient's biological information. For example, if a request is made such as "I suddenly have chest pain," this means calculates an urgency score, and if a high urgency score is assigned, a notification is sent to the nursing professional's mobile device.

[0722] 5. Mobile terminal of nursing specialist: The nursing specialist uses this terminal to receive emergency notifications, and upon receiving the notification, the nursing specialist immediately begins to respond.

[0723] 6. Video Calling: This has the function to conduct video calls between the patient and the nursing professional. The communication is carried out between the patient's electronic device, the server, and the nursing professional's mobile device.

[0724] Specific examples

[0725] Example 1: Common patient questions

[0726] The user (patient) presses the nurse call button and asks, "When is my next medication due?" The terminal sends this request to the server, which then asks the generation AI means to process it. The generation AI means generates the answer, "The next medication is due at 2:00 PM," and this answer is sent via the server to the patient's electronic device. Finally, the terminal displays the answer to the patient.

[0727] Example 2: Emergency response

[0728] The user (patient) presses the nurse call button to send a request saying, "I suddenly have chest pain." This request is sent from the device to the server, which acquires the biometric information and asks the AI ​​generation means to determine the level of urgency. The AI ​​generation means calculates a high urgency score, and the server notifies the nursing professional of this information on their mobile device. The nursing professional receives the emergency notification and immediately begins responding.

[0729] Prompt Sentence Examples

[0730] "When is my next dose?"

[0731] "I suddenly had a pain in my chest"

[0732] The system uses generative AI models and prompts to enable efficient and rapid nurse call responses, reducing the workload for nurses and improving the quality of patient care.

[0733] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0734] Step 1:

[0735] The user (patient) operates the nurse call button to input a request.

[0736] Input: Patient question or request text (e.g., "When is my next medication?", "I suddenly have chest pain," etc.)

[0737] Output: Request data to be sent to the device

[0738] Specific operation: The patient touches the nurse call button on the tablet device and enters a question or request in the input field that appears. The input content is a specific question such as "When is my next medication due?"

[0739] Step 2:

[0740] The device sends a request to the server.

[0741] Input: Request data entered by the patient

[0742] Output: Request data sent to the server

[0743] Specific operation: The device sends a request to the server via Wi-Fi or wired LAN. The transmitted data includes the patient ID and the request content.

[0744] Step 3:

[0745] The server analyzes the received request and sends it to the generative AI model.

[0746] Input: Request data sent from the terminal

[0747] Output: Prompt sentence to be passed to the generative AI model

[0748] What it does: The server parses the request data and sends the appropriate prompt (e.g., "When is my next medicine due?") to the generative AI model.

[0749] Step 4:

[0750] A generative AI model analyzes the request and generates an answer.

[0751] Input: Prompt sent from the server

[0752] Output: Generated answer text

[0753] What it does: The generative AI model uses natural language processing algorithms to analyze the prompt and generate an appropriate response (e.g., "Your next medication is due at 2 p.m.").

[0754] Step 5:

[0755] The server sends the generated response to the patient's terminal.

[0756] Input: Answer text obtained from the generative AI model

[0757] Output: Response data sent to the patient's device

[0758] What it does: The server receives the answer from the generative AI model and sends this data to the patient's electronic device in the appropriate format.

[0759] Step 6:

[0760] The device displays the answers to the patient.

[0761] Input: Response data sent from the server

[0762] Output: Answer text displayed on the screen

[0763] Specific operation: The device receives the answer text and displays it on the screen in a popup or dedicated window. The user checks the display on the screen.

[0764] Step 7:

[0765] In an emergency, the server acquires vital information and asks the generative AI model to determine the level of urgency.

[0766] Input: Emergency request details and patient vitals

[0767] Output: Urgency score

[0768] Specific operation: The server obtains the patient's heart rate and blood pressure information from a medical database, sends it to the generative AI model, and performs an urgency assessment that integrates the request content and vital information.

[0769] Step 8:

[0770] A generative AI model calculates an urgency score.

[0771] Input: Request details and vital information sent from the server

[0772] Output: Urgency score

[0773] Specific operation: The generative AI model calculates an urgency score based on the request content and vital information, and returns a high urgency score to the server.

[0774] Step 9:

[0775] The server sends a notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[0776] Input: Urgency score and threshold

[0777] Output: Emergency notification to nursing professional's mobile device

[0778] Specific operation: The server evaluates the urgency score and sends a push notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[0779] Step 10:

[0780] The terminal (nursing professional) receives the emergency notification and immediately begins responding.

[0781] Input: Urgent notification sent from the server

[0782] Output: Emergency response by nursing professionals initiated

[0783] Specific actions: The nursing professional checks the notification on the mobile device and immediately initiates the necessary action (e.g., rushing to the scene).

[0784] Step 11:

[0785] The user (patient) makes a video call request.

[0786] Input: Video call request (e.g., "I'd like to video call with a nurse")

[0787] Output: Video call request data from the device to the server

[0788] Specific actions: The patient activates the video call function on the tablet device and presses the call button.

[0789] Step 12:

[0790] The terminal sends a video call request to the server.

[0791] Input: Patient video call request data

[0792] Output: Data sent to the server

[0793] Specific operation: The device performs the communication processing necessary to send a video call request to the server.

[0794] Step 13:

[0795] The server relays the video call request to the nursing professional's mobile terminal.

[0796] Input: Patient video call request data

[0797] Output: Video call request data to the nursing professional's mobile device

[0798] Specific operation: The server receives the patient's video call request and relays it to the nursing professional's mobile device.

[0799] Step 14:

[0800] The terminal (nursing professional) answers the video call and communicates with the patient via the screen.

[0801] Input: Video call request from server

[0802] Output: Start a video call with the patient

[0803] What it does: A nursing professional answers a video call on a mobile device, checks on the patient's condition, and provides necessary instructions and advice.

[0804] This program utilizes a generative AI model and prompts to efficiently perform a series of tasks, including analyzing requests, generating automatic responses, determining urgency, and relaying video calls, thereby enabling prompt and appropriate responses to patients.

[0805] (Application example 1)

[0806] 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."

[0807] Modern nurse call systems are important for reducing the workload of nurses and providing prompt and appropriate care to patients. However, similar challenges exist in manufacturing. Robot operators in manufacturing must be able to quickly respond to problems and questions, and when errors occur, they must be able to immediately assess the urgency and take appropriate action. Technical means for facilitating communication between workers and management are also important. The present invention provides a system that solves these challenges.

[0808] 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.

[0809] In this invention, the server includes a terminal that sends a request when a patient operates a nurse call button, a means for receiving the request and recording it in a database, a means for displaying an automated response generated by the generative AI model to the patient, a means for determining the level of urgency based on the request content and the patient's vital signs and sending a notification to the nurse's tablet device, a video call means for enabling remote communication between the patient and the nurse, a means for generating a response when a robot operator inputs a question in a factory and displaying it on a robot operation panel, a means for integrating error messages and sensor data based on the robot operator's input and determining the level of urgency, a means for sending a notification to a manager's terminal when the level of urgency exceeds a threshold, and a means for enabling video calls between the robot operator and the manager. This enables prompt responses to questions from robot operators and appropriate responses to emergencies even at manufacturing sites.

[0810] The "terminal that sends a request when a patient presses the nurse call button" is a device that sends a request when a patient presses the nurse call button in an emergency or when they have a question.

[0811] The "server that receives requests and records them in a database" is a computer that receives requests from patients and stores the contents of those requests in a database.

[0812] A "generative AI model that analyzes request content and generates and sends an automatic response" is an artificial intelligence system that automatically analyzes the content of a received request and generates and sends an appropriate automatic response.

[0813] A "terminal that displays the generated automated response to the patient" is a device that displays the automated response generated by the generative AI model so that the patient can check it.

[0814] "Triage method that determines the level of urgency based on the request content and the patient's vital signs, and issues an emergency notification if necessary" is a function that integrates the request content and the patient's vital signs to evaluate the level of urgency, and issues an emergency notification if the level of urgency is high.

[0815] The "server that receives emergency notifications from the triage means and sends notifications to the tablet devices of nurses" is a computer that receives emergency notifications sent by the triage means and sends the notifications to the tablet devices held by nurses.

[0816] The "means for sending a notification to the tablet terminal of the nurse" is a function for sending an emergency notification from the server to the tablet terminal of the nurse.

[0817] "Video calling means enabling remote communication between patients and nurses" is a video calling function that allows patients and nurses to communicate directly from a distance.

[0818] "A means of using a generative AI model to generate a response when a robot operator in a factory inputs a question and displays it on the robot operation panel" is a function that analyzes a question input by a robot operator in a factory, generates an automatic response, and displays it on the robot operation panel.

[0819] "Means for integrating error messages and sensor data based on input from the robot operator and determining the level of urgency" is a function that analyzes the error messages input by the robot operator and the robot's sensor data and evaluates the level of urgency.

[0820] The "means for sending a notification to the administrator's terminal when the urgency exceeds a threshold" is a function for sending a notification to the terminal held by the administrator when the urgency exceeds a set threshold.

[0821] "Means for realizing video calls between a robot operator and an administrator" is a function that enables a robot operator and an administrator to communicate via video calls.

[0822] This invention utilizes generative AI models to improve the efficiency and quality of nurse call systems. We also describe a system that can support robot operators and respond to emergencies in the manufacturing industry.

[0823] The basic configuration of the system is as follows:

[0824] Hardware and Software

[0825] Terminal: A tablet device used by the patient and robot operator, which displays a nurse call button and a question input interface.

[0826] Server: Receives requests, submits them to the generative AI model, and records the results.

[0827] Generative AI model: An artificial intelligence system that analyzes requests and generates automated responses.

[0828] Triage measures: Evaluate requests by combining vital signs and sensor data to determine urgency.

[0829] Remote communication means: The ability to conduct video calls between patients and nurses, and between robot operators and administrators.

[0830] Software Configuration

[0831] The system includes the following major software components:

[0832] Flask: A web framework for building API servers and accepting requests.

[0833] HuggingFace's transformers library: Generative AI models for question-answering.

[0834] Automated Response and Triage

[0835] Automated responses to general questions

[0836] The patient presses the nurse call button on the tablet device and enters a question.

[0837] The server receives the request and asks the generative AI model to process it.

[0838] The generative AI model analyzes the question and generates an appropriate answer.

[0839] The server sends the generated answer to the patient's tablet device and displays it to the patient.

[0840] Urgency assessment and notification

[0841] When a patient inputs an emergency request, the server receives the request and obtains vital information.

[0842] The triage tool integrates the request details with vital information and calculates an urgency score.

[0843] If the urgency score exceeds the threshold, the server sends an emergency notification to the nurse's tablet device.

[0844] Factory robot applications

[0845] The robot operator inputs questions from the operation panel.

[0846] The server receives the request and asks the generative AI model to process it.

[0847] The generative AI model generates an appropriate response and displays it on the robot's control panel.

[0848] If the robot operator inputs an error, the server integrates the sensor data and the error message to determine the urgency.

[0849] If the urgency exceeds the threshold, an emergency notification is sent to the administrator terminal.

[0850] Remote Communication

[0851] If a patient or robot operator wishes to have a video call, they send a request to the server.

[0852] The server relays the video call request to the nurse or administrator's device.

[0853] Video calls are initiated on the nurses' and administrators' devices, enabling direct communication.

[0854] Specific examples

[0855] Question-answering prompt examples

[0856] "When is my next dose?"

[0857] "An error suddenly occurred"

[0858] This allows the system of the present invention to apply the functions of a nurse call system to manufacturing sites, enabling quick and accurate responses to different requests.

[0859] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0860] Step 1:

[0861] A user (patient or robot operator) presses the nurse call button or inputs a question from a terminal, and the input request is sent to the server by the terminal.

[0862] Input: User question or request

[0863] Output: Request data sent to the server

[0864] Step 2:

[0865] The server analyzes the received request and requests the generative AI model to process it. The request content is converted into an appropriate prompt sentence and passed to the generative AI model.

[0866] Input: Request data received by the server

[0867] Output: The prompt sent to the generative AI model

[0868] Step 3:

[0869] The generative AI model analyzes the question based on the prompt and generates an appropriate answer, which is then returned to the server.

[0870] Input: Prompt sentence for the generative AI model

[0871] Output: The generated answer

[0872] Step 4:

[0873] The server receives the answer from the generative AI model and sends it to the patient or robot operator's device, which displays the answer to the user.

[0874] Input: Answer generated by the generative AI model

[0875] Output: The answer displayed on the user's terminal

[0876] Step 5:

[0877] When a patient or a robot operator inputs an urgent request, vital information or sensor data is sent to the server at the same time as the request.

[0878] Input: Emergency request and vital signs or sensor data

[0879] Output: Urgent request data sent to the server

[0880] Step 6:

[0881] The server integrates the emergency request with vital signs or sensor data, calculates an urgency score using triage methods, and sends an emergency notification if the urgency score exceeds a threshold.

[0882] Input: Emergency request data and vital signs or sensor data

[0883] Output: Urgency score and emergency notification

[0884] Step 7:

[0885] An emergency notification is sent from the server to the tablet device of the nurse or administrator, who then takes immediate action.

[0886] Input: Urgent notification from the server

[0887] Output: Emergency notification displayed on the nurse or manager's terminal

[0888] Step 8:

[0889] When a user (patient or robot operator) requests a video call, the request is sent from the terminal to the server, which relays the request to the other terminal and the video call begins.

[0890] Input: A video call request from a user

[0891] Output: Video call request relayed to the other device and video call initiated

[0892] 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.

[0893] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[0894] System configuration

[0895] 1. Nurse call button and terminal

[0896] - Device: A tablet device used by patients. It has a touch interface with a nurse call button. When a patient presses this button, a request is sent. The device also has an emotion engine to recognize the patient's emotions.

[0897] 2. Server

[0898] - Server: Receives nurse call requests, records them in a database, analyzes the request content and emotional state, and sends them to the generative AI model for processing.

[0899] 3. Generative AI Models

[0900] - Generative AI model: Analyzes the patient's request and emotional state and automatically generates a response. For example, in response to the request "What time is my medicine?", it generates a response such as "The next medicine is due at 2:00 PM."

[0901] 4. Triage Measures

[0902] - Triage method: Determines the level of urgency based on the content of the nurse call, the patient's vital signs, and their emotional state. If the level of urgency is high, a notification is sent to the nurse's tablet.

[0903] 5. Remote communication

[0904] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[0905] Program processing

[0906] Automated responses to general questions

[0907] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[0908] Terminal: Sends this request and the emotional state generated by the emotion engine to the server.

[0909] Server: Receives the request, analyzes the request content and emotional state, and initiates the process to request processing from the generative AI model.

[0910] Generative AI model (on the server): Analyzes the request and emotional state and generates an appropriate answer, for example, "The next medication time is 2:00 PM."

[0911] Server: Sends the generated response data to the patient's tablet device.

[0912] Terminal: Displays the received data to the patient in text format.

[0913] Triage

[0914] User (patient): Presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[0915] Device: Sends this urgent request and the emotional state generated by the emotion engine to the server.

[0916] Server: Receives the request and retrieves and integrates the patient's vital signs and emotional state from the database.

[0917] Server: Sends the integrated information to the generative AI model and requests it to determine the urgency of the situation.

[0918] Generative AI model (on the server): Calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[0919] Server: If the urgency score exceeds the set threshold, an emergency notification is immediately sent to the nurse's tablet device.

[0920] Terminal (Nurse): Receives notification, checks details, and prepares to go to the patient's room immediately.

[0921] Remote Communication

[0922] User (patient): If the patient wants to contact a nurse remotely, they can make a video call request from their tablet device.

[0923] Device: Sends a video call request and the emotional state generated by the emotion engine to the server.

[0924] Server: Relays the received request to the nurse's tablet device.

[0925] Terminal (nurse): Receives and responds to video call requests.

[0926] Terminal (Patient): A video call is initiated and the patient explains their current condition to the nurse.

[0927] Terminal (nurse): Checks on the patient's condition via video call and provides instructions and advice as needed.

[0928] Specific examples

[0929] Example 1: Common patient questions

[0930] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[0931] Terminal: Sends the question and emotional state to the server.

[0932] Server: Sends the request content and emotional state to the generation AI model for processing and obtains the answer.

[0933] Generative AI model (on the server): Generates the answer, "The next medicine time is 2:00 p.m."

[0934] Server: Sends the answer to the patient's device.

[0935] Terminal: Display the answers to the patient.

[0936] Example 2: Emergency response

[0937] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[0938] Terminal: Sends the request and emotional state to the server.

[0939] Server: Determines the urgency based on the request, vital information, and emotional state.

[0940] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[0941] Server: Sends emergency notifications to nurses' tablets.

[0942] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[0943] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[0944] The processing flow will be explained below.

[0945] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[0946] Program processing

[0947] Automated responses to general questions

[0948] Step 1:

[0949] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[0950] Step 2:

[0951] The terminal converts the request and the patient's emotional state analyzed by the emotion engine into a digital signal and sends it to the server.

[0952] Step 3:

[0953] The server receives the request, analyzes the request content and emotional state, and initiates the process of requesting processing from the generative AI model.

[0954] Step 4:

[0955] A generative AI model (on the server) analyzes the request and emotional state and generates an appropriate answer, such as "Your next medication is due at 2 p.m."

[0956] Step 5:

[0957] The server sends the generated response data to the patient's tablet device.

[0958] Step 6:

[0959] The terminal displays the received data in text format to the patient.

[0960] Triage

[0961] Step 1:

[0962] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[0963] Step 2:

[0964] The terminal sends this emergency request and the patient's emotional state analyzed by the emotion engine to the server.

[0965] Step 3:

[0966] The server receives the request and retrieves and integrates the patient's vital information and emotional state from the database.

[0967] Step 4:

[0968] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[0969] Step 5:

[0970] The generative AI model (on the server) calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[0971] Step 6:

[0972] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[0973] Step 7:

[0974] The terminal (nurse) receives the notification, checks the details, and immediately prepares to head to the patient's room.

[0975] Remote Communication

[0976] Step 1:

[0977] When a user (patient) wants to contact a nurse remotely, they send a video call request from their tablet device.

[0978] Step 2:

[0979] The device sends a video call request and the patient's emotional state analyzed by the emotion engine to the server.

[0980] Step 3:

[0981] The server relays the received request to the nurse's tablet device.

[0982] Step 4:

[0983] The terminal (nurse) receives the video call request and responds.

[0984] Step 5:

[0985] A video call is initiated from the terminal (patient), and the patient explains their current condition to the nurse.

[0986] Step 6:

[0987] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[0988] Specific examples

[0989] Example 1: Common patient questions

[0990] Step 1:

[0991] The user (patient) presses the nurse call button and asks, "When is my next medication due?"

[0992] Step 2:

[0993] The device sends the question and emotional state to the server.

[0994] Step 3:

[0995] The server requests the request content and emotional state to be processed by a generative AI model and obtains a response.

[0996] Step 4:

[0997] The generative AI model (in the server) generates the answer, "The next medication time is 2:00 p.m."

[0998] Step 5:

[0999] The server sends the response to the patient's terminal.

[1000] Step 6:

[1001] The device displays the answers to the patient.

[1002] Example 2: Emergency response

[1003] Step 1:

[1004] The user (patient) presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1005] Step 2:

[1006] The device sends the request and emotional state to the server.

[1007] Step 3:

[1008] The server determines the urgency based on the request, vital information, and emotional state.

[1009] Step 4:

[1010] The generative AI model (within the server) calculates a high urgency score and notifies the server.

[1011] Step 5:

[1012] The server sends an emergency notification to the nurse's tablet device.

[1013] Step 6:

[1014] The terminal (nurse) receives the emergency notification and immediately performs on-site intervention.

[1015] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[1016] Example 2

[1017] 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."

[1018] When patients face an emergency situation in the hospital, or when they have everyday questions, it is difficult to get a quick and accurate answer. Another problem is that the workload of nurses increases, making it difficult to respond quickly. In particular, there is a lack of response that takes into account the emotional state of patients, and psychological care for patients is not being provided adequately. This can lead to a decrease in patient satisfaction and a sense of security.

[1019] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1020] In this invention, the server includes a terminal that transmits the request and emotional state when the patient operates the nurse call button, a server that receives the request and emotional state, records it in a database, and begins analysis, a generative AI model that analyzes the request content and emotional state received from the server and generates and transmits an automatic response, a terminal that displays the automatic response generated by the generative AI model to the patient, triage means that determines the urgency based on the request content, the patient's vital signs, and the patient's emotional state and sends an emergency notification as necessary, a server that receives the emergency notification from the triage means and sends the notification to the nurse's tablet device, means for sending the notification to the nurse's tablet device, and video call means that enables remote communication between the patient and the nurse. This enables a quick and accurate response to the patient's request and realizes a comprehensive response that also includes psychological care for the patient.

[1021] A "terminal" is a device that allows a patient to operate a nurse call button and has the function of transmitting requests and emotional states.

[1022] The "server" is a central control unit that receives requests and emotional states sent from the terminals, records them in a database and initiates the analysis.

[1023] A "generative AI model" is an artificial intelligence model that analyzes the request content and emotional state received from the server and generates and sends an automatic response.

[1024] The "triage method" is a system that determines the level of urgency based on the request content, the patient's vital signs, and their emotional state, and has the ability to send emergency notifications if necessary.

[1025] "Vital information" refers to key physiological data related to maintaining a patient's life, such as blood pressure, heart rate, and body temperature.

[1026] An "emergency notification" is alert information that is sent based on the level of urgency determined by the triage means and prompts nurses to take prompt action.

[1027] "Remote communication" refers to a means for patients and nurses to communicate remotely, including systems such as video calls.

[1028] "Emotional state" is information that indicates the psychological state of the patient analyzed by the emotion engine, and includes anxiety, relief, excitement, etc.

[1029] The present invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. The system of the present invention is configured as follows.

[1030] System Components

[1031] Nurse call button and terminal

[1032] The terminal is a tablet device that allows patients to operate the nurse call button. This terminal has the function of transmitting requests and emotional states. It also has an emotion engine that analyzes the patient's emotional state.

[1033] server

[1034] The server receives requests and emotional states sent from the devices, records them in a database, and then analyzes the request content and emotional state and requests processing from the generative AI model.

[1035] Generative AI Models

[1036] The generative AI model analyzes the request content and emotional state received from the server and generates an automatic response. For example, the model uses natural language processing technology to generate an appropriate response such as "The next medicine time is 2:00 PM" in response to a request such as "When is the next medicine time?"

[1037] Triage Measures

[1038] The triage system determines the level of urgency based on the request, the patient's vital signs, and their emotional state. If the urgency is high, the system sends an emergency notification to the nurse's tablet.

[1039] Remote Communication

[1040] To realize remote communication between patients and nurses, the video call function of the device is used. A video call request is sent from the device to a server, which then relays the request to the nurse's tablet device, and the video call begins.

[1041] Specific examples

[1042] Automated responses to general questions

[1043] 1. User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[1044] 2. Terminal: Sends the question and the emotional state determined by the emotion engine to the server.

[1045] 3. Server: Sends the request to the AI ​​model for processing and obtains the answer.

[1046] 4. Generative AI model: Generates the answer, "The next medication time is at 2:00 PM."

[1047] 5. Server: Sends the answer to the patient's device.

[1048] 6. Terminal: Displays the answers to the patient.

[1049] Emergency response

[1050] 1. User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1051] 2. Terminal: Sends the request content and the emotional state determined by the emotion engine to the server.

[1052] 3. Server: Determines the urgency of the request by integrating the request content, vital signs, and emotional state.

[1053] 4. Generative AI model: Calculates a high urgency score and notifies the server.

[1054] 5. Server: Sends emergency notifications to the nurses' tablets.

[1055] 6. Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[1056] Prompt Sentence Examples

[1057] "When is my next dose?"

[1058] "I suddenly had a pain in my chest"

[1059] Using the above components and processes, the system of the present invention responds quickly and appropriately to patient requests, reducing the workload of nurses while providing comprehensive care, including psychological care for patients.

[1060] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1061] Step 1:

[1062] User (patient): Presses the nurse call button to input a request. For example, the user might ask, "When is my next medication due?" This input is the starting point for the entire system process.

[1063] Step 2:

[1064] Terminal: Collects requests entered by the patient and the corresponding emotional state (e.g., "anxiety") calculated by the emotion engine. Sends this data to the server. The input is the patient's question and emotional data, and the output is sending this data to the server.

[1065] Step 3:

[1066] Server: Receives the sent request and emotional state. Records the received data in a database and starts the analysis process. The input is the request and emotional data sent from the device, and the output is a processing request to the generative AI model.

[1067] Step 4:

[1068] Generative AI model (in the server): Analyzes the request content and emotional state received from the server. Generates an automatic response using natural language processing technology. The input is the request and emotional data sent from the server, and the output is the generated answer (e.g., "The next medication time is 2 p.m.").

[1069] Step 5:

[1070] Server: Receives the answers generated by the generative AI model and sends them to the patient's tablet device. The input is the answer data from the generative AI model, and the output is the sending of the answer data to the device.

[1071] Step 6:

[1072] Terminal: Receives the answer sent from the server and displays it on the screen. The patient confirms it. The input is the answer data from the server, and the output is the answer displayed on the screen.

[1073] Step 7:

[1074] User (Patient): If they have any further questions or concerns, they press the nurse call button again to enter their request. This cycle provides continuous support.

[1075] Triage

[1076] Step 1:

[1077] User (patient): Presses the nurse call button and inputs a request saying, "I suddenly have chest pain." This is an emergency request.

[1078] Step 2:

[1079] Terminal: Collects requests and emotional states (e.g., "fear") from the emotion engine and sends them to the server. The input is the patient's urgent request and emotional data, and the output is the data sent to the server.

[1080] Step 3:

[1081] Server: Receives emergency requests and emotional states, and retrieves and integrates the patient's vital information from the database. The input is data from the device and vital information from the database, and the output is the integrated data.

[1082] Step 4:

[1083] Generative AI model (on the server): Analyzes the integrated data and calculates the urgency score. The input is the integrated request, emotional state, and vital information, and the output is the urgency score.

[1084] Step 5:

[1085] Server: If the urgency score exceeds the threshold, it sends an emergency notification to the nurse's tablet. The input is the urgency score, and the output is the emergency notification to the nurse's device.

[1086] Step 6:

[1087] Terminal (nurse): Receives emergency notification, checks detailed information, and immediately prepares to go to the patient's room. The input is the emergency notification, and the output is the nurse's actions.

[1088] Remote Communication

[1089] Step 1:

[1090] User (patient): Sends a video call request from a tablet device. The input is a video call request.

[1091] Step 2:

[1092] Terminal: Sends a video call request and the emotional state (e.g., "anxiety") generated by the emotion engine to the server. The input is the video call request and emotion data, and the output is the data sent to the server.

[1093] Step 3:

[1094] Server: Relays video call requests to the nurse's tablet. The input is the video call request from the device, and the output is the relayed data to the nurse's device.

[1095] Step 4:

[1096] Terminal (nurse): Receives and responds to video call requests. The input is a video call request, and the output is the start of a video call.

[1097] Step 5:

[1098] User (patient): A video call is initiated with a nurse, describing the current state. The input is the initiation of the video call, and the output is the patient description.

[1099] Step 6:

[1100] Terminal (nurse): Checks the patient's condition via video call and provides instructions and advice as needed. The input is the patient's explanation, and the output is the nurse's instructions and advice.

[1101] (Application example 2)

[1102] 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."

[1103] Conventional nurse call systems have difficulty responding quickly and appropriately to requests from patients, placing a heavy burden on nurses. They also struggle to take into account the patient's emotional state, which can lead to poor communication quality. Similarly, in brick-and-mortar stores, it's difficult to respond quickly and appropriately to customer requests, often resulting in poor customer satisfaction.

[1104] 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 receiving and processing requests operated by patients and customers, generation AI model means for analyzing the request content and emotional state and generating an automatic response, means for displaying the generated automatic response and realizing remote communication, and triage means. This enables quick and appropriate responses to requests from patients and customers, reduces the burden on nurses and staff, and improves patient and customer satisfaction.

[1105] A "patient" is a person who receives treatment or care at a medical institution or hospital.

[1106] A "nurse call button" is an interface device that patients use to make requests or contact nurses in an emergency.

[1107] A "terminal" is an electronic device used to send and receive requests at a medical institution or physical store.

[1108] A "server" is a device that provides the computing resources to receive and analyze requests, and generate and send automated responses.

[1109] A "generative AI model" is a system equipped with artificial intelligence technology that analyzes the request content and emotional state and automatically generates an appropriate response.

[1110] An "automated response" is an answer or response automatically provided in response to a request by a generative AI model.

[1111] "Triage measures" is a function that determines the urgency of a request based on its content and emotional state, and sends an emergency notification if necessary.

[1112] "Remote communication" is a means by which people in distant locations communicate with each other via electronic devices.

[1113] "Video calling means" is a function that enables real-time communication by sending and receiving audio and video through a terminal.

[1114] An "emergency notification" is a notification message sent to nurses and staff when a high level of urgency is determined.

[1115] A "customer support button" is an interface device that a customer uses to request support within a store.

[1116] The "urgency score" is a numerical assessment of the urgency calculated based on the request content, emotional state, vital information, etc.

[1117] This invention utilizes generative AI models and emotion engines to improve the efficiency and quality of responses in nurse call systems and brick-and-mortar customer support systems.

[1118] System configuration

[1119] 1. Nurse call button and customer support button and terminal

[1120] The terminal is an electronic device used by patients and customers in medical institutions and brick-and-mortar stores, and displays a nurse call button or customer support button on the touch interface. When a patient or customer presses the button, a request is sent. The terminal also has an emotion engine for recognizing emotions.

[1121] 2. Server

[1122] The server receives nurse call and customer support requests, records them in a database, analyzes the request content and emotional state, requests a generative AI model to process them, records the generated automated response, and sends it back to the device.

[1123] 3. Generative AI Models

[1124] The generative AI model analyzes the request and the patient's emotional state and automatically generates a response. For example, in response to a patient's request, "When is my medicine due?", the model might respond, "The next medicine is due at 2 p.m."

[1125] 4. Triage Measures

[1126] The triage system determines the level of urgency based on the content of nurse call and customer support requests, the patient's vital signs, and the customer's emotional state. If the level of urgency is high, an emergency notification is sent to the staff member's tablet device.

[1127] 5. Remote communication

[1128] The remote communication function allows video calls between patients / customers and nurses / staff via terminals. This function is realized by communication between the server and terminals.

[1129] What the program does

[1130] The server performs the following process.

[1131] 1. Sentiment analysis:

[1132] Send the patient or customer request text to an emotion engine API (e.g., EmotionAPI) to analyze the emotional state.

[1133] 2. Response generation:

[1134] Have a generative AI model API (e.g., AIModelAPI) generate an appropriate response using the request text and the analyzed emotional state.

[1135] 3. Staff Notification:

[1136] The level of urgency is determined based on the emotional state and the generated response, and if the level of urgency is high, an emergency notification is sent to a nurse or staff member via a triage means.

[1137] Specific examples

[1138] Example 1: Common patient questions

[1139] Patient: "When is my next dose?"

[1140] Terminal: Sends questions and emotional states to the server.

[1141] Server: Sends the request to the generative AI model and generates an answer such as "The next medicine time is at 2:00 p.m."

[1142] Terminal: Displays the generated answers to the patient.

[1143] Example 2: Urgent customer request

[1144] Customer: "What items are in stock?"

[1145] Terminal: Sends questions and emotional states to the server.

[1146] Server: Sends the request content to the generative AI model and generates a response.

[1147] High stress levels are identified using the emotion engine.

[1148] Server: Sends emergency notifications to staff.

[1149] Terminal: Display the answer to the customer.

[1150] Prompt Sentence Examples

[1151] "What products are in stock?"

[1152] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1153] Step 1:

[1154] The patient or customer (user) operates the nurse call button or customer support button on the terminal. They input the request details as text. This operation causes the terminal to send the request details and the emotional state analyzed by the emotion engine to the server. The input is the request text and emotional data, and the output is data sent to the server.

[1155] Step 2:

[1156] The server stores the received request content and emotional state. Then, it converts the request content and emotional state into JSON format to send to the generative AI model. The input is the request text and emotional data, and the output is the input data to the generative AI model.

[1157] Step 3:

[1158] The generative AI model receives the request content and emotional state from the server, performs text analysis, and generates an appropriate response based on the analyzed results. The input is the request text and emotional data, and the output is the response text.

[1159] Step 4:

[1160] The server analyzes the response text received from the generative AI model and, if necessary, determines the level of urgency using triage methods. If the level of urgency is determined to be high, an emergency notification is sent to the terminals of staff and nurses. The input is the response text and emotion data, and the output is the emergency notification data or response data.

[1161] Step 5:

[1162] The terminal displays the response text received from the server to the user. If the urgency is high, a notification by the triage means is also displayed. The input is the response text from the server, and the output is the display to the user.

[1163] Step 6:

[1164] The nurse or staff member (user) who receives the emergency notification checks the content of the notification and takes on-site action as necessary. This process ensures a prompt response to the user. The input is the emergency notification data, and the output is the on-site response action.

[1165] 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.

[1166] 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.

[1167] 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.

[1168] [Third embodiment]

[1169] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1170] 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.

[1171] 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).

[1172] 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.

[1173] 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.

[1174] 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).

[1175] 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.

[1176] 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.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] 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."

[1181] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[1182] System configuration

[1183] 1. Nurse call button and terminal

[1184] - Device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is made.

[1185] 2. Server

[1186] - Server: Receives nurse call requests, records them in a database, analyzes the request content, and sends it to the generative AI model for processing.

[1187] 3. Generative AI Models

[1188] - Generative AI model: Analyzes requests from patients and automatically generates answers. For example, in response to a request such as "What time is my medicine?", it generates an answer such as "The next medicine is due at 2:00 PM."

[1189] 4. Triage Measures

[1190] - Triage method: Determine the level of urgency based on the content of the nurse call and the patient's vital signs. If the level of urgency is high, a notification is sent to the nurse's tablet.

[1191] 5. Remote communication

[1192] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[1193] Program processing

[1194] Automated responses to general questions

[1195] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[1196] Device: Sends this request to the server.

[1197] Server: Receives requests and sends them to the generative AI model for processing.

[1198] Generative AI model (on the server): Analyzes the request and generates an appropriate answer, such as "The next medication time is at 2 p.m."

[1199] Server: Sends the generated answers to the patient's tablet device.

[1200] Terminal: Display the answers to the patient.

[1201] Triage

[1202] User (patient): Presses the nurse call button and enters an emergency request such as "I suddenly have chest pain."

[1203] Device: Sends this request to the server.

[1204] Server: Receives the request, obtains vital signs, and asks the generative AI model to determine the level of urgency.

[1205] Generative AI model (on the server): Integrates the request content and vital signs to calculate an urgency score. If "chest pain" is determined to be a serious symptom, a high urgency score is assigned.

[1206] Server: If the urgency score exceeds the threshold, a notification is sent to the nurse's tablet.

[1207] Terminal (Nurse): Receives notification and prepares to go to the patient's room immediately.

[1208] Remote Communication

[1209] User (patient): If the patient wants to contact a nurse via video call, he or she sends a request from the device.

[1210] Device: Sends a video call request to the server.

[1211] Server: Relays the request to the nurse's tablet.

[1212] Terminal (nurse): Receives requests and answers video calls.

[1213] Terminal (Patient): A video call is initiated and the patient explains their condition to the nurse.

[1214] Terminal (Nurse): Checks the situation and provides instructions and advice as needed.

[1215] Specific examples

[1216] Example 1: Common patient questions

[1217] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[1218] Terminal: Sends a question to the server.

[1219] Server: Requests processing from the generative AI model and obtains the answer.

[1220] Generative AI model (on the server): Generates the answer, "The next medication time is at 2:00 p.m."

[1221] Server: Sends the answer to the patient's device.

[1222] Terminal: Display answers to patient.

[1223] Example 2: Emergency response

[1224] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1225] Device: Sends a request to the server.

[1226] Server: Determines the urgency based on the request and vital signs.

[1227] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[1228] Server: Sends emergency notifications to nurses' tablets.

[1229] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[1230] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. Each component works together to enable efficient nurse call response.

[1231] The processing flow will be explained below.

[1232] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[1233] Program processing

[1234] Automated responses to general questions

[1235] Step 1:

[1236] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[1237] Step 2:

[1238] The terminal converts this request into a digital signal and sends it to the server.

[1239] Step 3:

[1240] The server receives the request, analyzes the request content, and starts the process of requesting processing from the generative AI model.

[1241] Step 4:

[1242] The generative AI model (on the server) analyzes the request and generates an appropriate answer, such as "The next medication time is 2:00 PM."

[1243] Step 5:

[1244] The server sends the generated response data to the patient's tablet device.

[1245] Step 6:

[1246] The terminal displays the received data in text format to the patient.

[1247] Triage

[1248] Step 1:

[1249] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[1250] Step 2:

[1251] The terminal sends this emergency request to the server.

[1252] Step 3:

[1253] The server receives the request and retrieves and consolidates the patient's vital information from the database.

[1254] Step 4:

[1255] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[1256] Step 5:

[1257] The generative AI model (on the server) calculates an urgency score based on the request content and vital signs. In this case, "chest pain" is determined to be a serious symptom and a high urgency score is assigned.

[1258] Step 6:

[1259] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[1260] Step 7:

[1261] The terminal (nurse) receives the emergency notification, checks the details, and immediately prepares to go to the patient's room.

[1262] Remote Communication

[1263] Step 1:

[1264] The user (patient) sends a video call request from a tablet device to contact a nurse remotely.

[1265] Step 2:

[1266] The terminal sends a video call request to the server.

[1267] Step 3:

[1268] The server relays the received request to the nurse's tablet device.

[1269] Step 4:

[1270] The terminal (nurse) receives the video call request and responds.

[1271] Step 5:

[1272] A video call is initiated on the terminal (patient), and the patient explains their current condition to the nurse.

[1273] Step 6:

[1274] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[1275] Through these processing steps, this system reduces the workload of nurses and enables prompt and appropriate care for patients. Each component works together to enable efficient nurse call responses and the provision of high-quality services.

[1276] Example 1

[1277] 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."

[1278] Conventional nurse call systems can be slow to respond to patient requests, and rapid response is especially required in emergencies. This can also increase the workload of nurses, making it difficult to provide efficient medical care. To address these issues, a system that can respond quickly and appropriately to patient needs is needed.

[1279] 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.

[1280] In this invention, the server includes an electronic device that sends a request when a patient operates the nurse call button, an electronic computer that receives the request and records it in an information recording device, an AI generation means that analyzes the request content and generates and sends an automatic response, a priority determination means that determines the urgency based on the request content and biometric information and issues an emergency notification as necessary, and a video communication means that enables remote communication between the patient and nursing professionals. This reduces the workload of nurses and enables prompt and appropriate care for patients.

[1281] An "electronic device" is a device that allows a patient to operate a nurse call button to send a request.

[1282] An "electronic computer" is a computing device that has the function of receiving requests and recording them in an information recording device.

[1283] The "generative AI means" is an AI model that analyzes the request content received from the server and generates and sends an automatic response.

[1284] "Biometric information" is data that indicates the patient's health condition, such as heart rate, blood pressure, and respiratory rate.

[1285] The "priority determination means" is a device that determines the level of urgency based on the request content and biometric information, and issues an emergency notification as necessary.

[1286] A "nursing professional" is a health care worker trained to provide medical care to patients.

[1287] A "mobile terminal" is an electronic terminal device that can be carried by a nursing professional.

[1288] "Video communication means" refers to a communication means that enables video communication between a patient and a nursing professional.

[1289] This invention aims to improve the efficiency and quality of a nurse call system by using a generative AI model. This system consists of an electronic device used by the patient, a server, a generative AI means, a priority determination means, a mobile terminal for nursing professionals, and a video communication means.

[1290] System configuration

[1291] 1. Patient's electronic device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is sent from the device.

[1292] 2. Server: Receives requests sent from the patient's electronic device, records them in the information recording device, and sends the request content to the AI ​​generation means to request it to generate a response.

[1293] 3. Generative AI means: The generative AI means analyzes the request content and generates an appropriate automated response. For example, in response to the request "What time is my next medicine?", it generates the answer "My next medicine is due at 2:00 PM."

[1294] 4. Priority determination means: The priority determination means determines the urgency level based on the request content and the patient's biological information. For example, if a request is made such as "I suddenly have chest pain," this means calculates an urgency score, and if a high urgency score is assigned, a notification is sent to the nursing professional's mobile device.

[1295] 5. Mobile terminal of nursing specialist: The nursing specialist uses this terminal to receive emergency notifications, and upon receiving the notification, the nursing specialist immediately begins to respond.

[1296] 6. Video Calling: This has the function to conduct video calls between the patient and the nursing professional. The communication is carried out between the patient's electronic device, the server, and the nursing professional's mobile device.

[1297] Specific examples

[1298] Example 1: Common patient questions

[1299] The user (patient) presses the nurse call button and asks, "When is my next medication due?" The terminal sends this request to the server, which then asks the generation AI means to process it. The generation AI means generates the answer, "The next medication is due at 2:00 PM," and this answer is sent via the server to the patient's electronic device. Finally, the terminal displays the answer to the patient.

[1300] Example 2: Emergency response

[1301] The user (patient) presses the nurse call button to send a request saying, "I suddenly have chest pain." This request is sent from the device to the server, which acquires the biometric information and asks the AI ​​generation means to determine the level of urgency. The AI ​​generation means calculates a high urgency score, and the server notifies the nursing professional of this information on their mobile device. The nursing professional receives the emergency notification and immediately begins responding.

[1302] Prompt Sentence Examples

[1303] "When is my next dose?"

[1304] "I suddenly had a pain in my chest"

[1305] The system uses generative AI models and prompts to enable efficient and rapid nurse call responses, reducing the workload for nurses and improving the quality of patient care.

[1306] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1307] Step 1:

[1308] The user (patient) operates the nurse call button to input a request.

[1309] Input: Patient question or request text (e.g., "When is my next medication?", "I suddenly have chest pain," etc.)

[1310] Output: Request data to be sent to the device

[1311] Specific operation: The patient touches the nurse call button on the tablet device and enters a question or request in the input field that appears. The input content is a specific question such as "When is my next medication due?"

[1312] Step 2:

[1313] The device sends a request to the server.

[1314] Input: Request data entered by the patient

[1315] Output: Request data sent to the server

[1316] Specific operation: The device sends a request to the server via Wi-Fi or wired LAN. The transmitted data includes the patient ID and the request content.

[1317] Step 3:

[1318] The server analyzes the received request and sends it to the generative AI model.

[1319] Input: Request data sent from the terminal

[1320] Output: Prompt sentence to be passed to the generative AI model

[1321] What it does: The server parses the request data and sends the appropriate prompt (e.g., "When is my next medicine due?") to the generative AI model.

[1322] Step 4:

[1323] A generative AI model analyzes the request and generates an answer.

[1324] Input: Prompt sent from the server

[1325] Output: Generated answer text

[1326] What it does: The generative AI model uses natural language processing algorithms to analyze the prompt and generate an appropriate response (e.g., "Your next medication is due at 2 p.m.").

[1327] Step 5:

[1328] The server sends the generated response to the patient's terminal.

[1329] Input: Answer text obtained from the generative AI model

[1330] Output: Response data sent to the patient's device

[1331] What it does: The server receives the answer from the generative AI model and sends this data to the patient's electronic device in the appropriate format.

[1332] Step 6:

[1333] The device displays the answers to the patient.

[1334] Input: Response data sent from the server

[1335] Output: Answer text displayed on the screen

[1336] Specific operation: The device receives the answer text and displays it on the screen in a popup or dedicated window. The user checks the display on the screen.

[1337] Step 7:

[1338] In an emergency, the server acquires vital information and asks the generative AI model to determine the level of urgency.

[1339] Input: Emergency request details and patient vitals

[1340] Output: Urgency score

[1341] Specific operation: The server obtains the patient's heart rate and blood pressure information from a medical database, sends it to the generative AI model, and performs an urgency assessment that integrates the request content and vital information.

[1342] Step 8:

[1343] A generative AI model calculates an urgency score.

[1344] Input: Request details and vital information sent from the server

[1345] Output: Urgency score

[1346] Specific operation: The generative AI model calculates an urgency score based on the request content and vital information, and returns a high urgency score to the server.

[1347] Step 9:

[1348] The server sends a notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[1349] Input: Urgency score and threshold

[1350] Output: Emergency notification to nursing professional's mobile device

[1351] Specific operation: The server evaluates the urgency score and sends a push notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[1352] Step 10:

[1353] The terminal (nursing professional) receives the emergency notification and immediately begins responding.

[1354] Input: Urgent notification sent from the server

[1355] Output: Emergency response by nursing professionals initiated

[1356] Specific actions: The nursing professional checks the notification on the mobile device and immediately initiates the necessary action (e.g., rushing to the scene).

[1357] Step 11:

[1358] The user (patient) makes a video call request.

[1359] Input: Video call request (e.g., "I'd like to video call with a nurse")

[1360] Output: Video call request data from the device to the server

[1361] Specific actions: The patient activates the video call function on the tablet device and presses the call button.

[1362] Step 12:

[1363] The terminal sends a video call request to the server.

[1364] Input: Patient video call request data

[1365] Output: Data sent to the server

[1366] Specific operation: The device performs the communication processing necessary to send a video call request to the server.

[1367] Step 13:

[1368] The server relays the video call request to the nursing professional's mobile terminal.

[1369] Input: Patient video call request data

[1370] Output: Video call request data to the nursing professional's mobile device

[1371] Specific operation: The server receives the patient's video call request and relays it to the nursing professional's mobile device.

[1372] Step 14:

[1373] The terminal (nursing professional) answers the video call and communicates with the patient via the screen.

[1374] Input: Video call request from server

[1375] Output: Start a video call with the patient

[1376] What it does: A nursing professional answers a video call on a mobile device, checks on the patient's condition, and provides necessary instructions and advice.

[1377] This program utilizes a generative AI model and prompts to efficiently perform a series of tasks, including analyzing requests, generating automatic responses, determining urgency, and relaying video calls, thereby enabling prompt and appropriate responses to patients.

[1378] (Application example 1)

[1379] 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."

[1380] Modern nurse call systems are important for reducing the workload of nurses and providing prompt and appropriate care to patients. However, similar challenges exist in manufacturing. Robot operators in manufacturing must be able to quickly respond to problems and questions, and when errors occur, they must be able to immediately assess the urgency and take appropriate action. Technical means for facilitating communication between workers and management are also important. The present invention provides a system that solves these challenges.

[1381] 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.

[1382] In this invention, the server includes a terminal that sends a request when a patient operates a nurse call button, a means for receiving the request and recording it in a database, a means for displaying an automated response generated by the generative AI model to the patient, a means for determining the level of urgency based on the request content and the patient's vital signs and sending a notification to the nurse's tablet device, a video call means for enabling remote communication between the patient and the nurse, a means for generating a response when a robot operator inputs a question in a factory and displaying it on a robot operation panel, a means for integrating error messages and sensor data based on the robot operator's input and determining the level of urgency, a means for sending a notification to a manager's terminal when the level of urgency exceeds a threshold, and a means for enabling video calls between the robot operator and the manager. This enables prompt responses to questions from robot operators and appropriate responses to emergencies even at manufacturing sites.

[1383] The "terminal that sends a request when a patient presses the nurse call button" is a device that sends a request when a patient presses the nurse call button in an emergency or when they have a question.

[1384] The "server that receives requests and records them in a database" is a computer that receives requests from patients and stores the contents of those requests in a database.

[1385] A "generative AI model that analyzes request content and generates and sends an automatic response" is an artificial intelligence system that automatically analyzes the content of a received request and generates and sends an appropriate automatic response.

[1386] A "terminal that displays the generated automated response to the patient" is a device that displays the automated response generated by the generative AI model so that the patient can check it.

[1387] "Triage method that determines the level of urgency based on the request content and the patient's vital signs, and issues an emergency notification if necessary" is a function that integrates the request content and the patient's vital signs to evaluate the level of urgency, and issues an emergency notification if the level of urgency is high.

[1388] The "server that receives emergency notifications from the triage means and sends notifications to the tablet devices of nurses" is a computer that receives emergency notifications sent by the triage means and sends the notifications to the tablet devices held by nurses.

[1389] The "means for sending a notification to the tablet terminal of the nurse" is a function for sending an emergency notification from the server to the tablet terminal of the nurse.

[1390] "Video calling means enabling remote communication between patients and nurses" is a video calling function that allows patients and nurses to communicate directly from a distance.

[1391] "A means of using a generative AI model to generate a response when a robot operator in a factory inputs a question and displays it on the robot operation panel" is a function that analyzes a question input by a robot operator in a factory, generates an automatic response, and displays it on the robot operation panel.

[1392] "Means for integrating error messages and sensor data based on input from the robot operator and determining the level of urgency" is a function that analyzes the error messages input by the robot operator and the robot's sensor data and evaluates the level of urgency.

[1393] The "means for sending a notification to the administrator's terminal when the urgency exceeds a threshold" is a function for sending a notification to the terminal held by the administrator when the urgency exceeds a set threshold.

[1394] "Means for realizing video calls between a robot operator and an administrator" is a function that enables a robot operator and an administrator to communicate via video calls.

[1395] This invention utilizes generative AI models to improve the efficiency and quality of nurse call systems. We also describe a system that can support robot operators and respond to emergencies in the manufacturing industry.

[1396] The basic configuration of the system is as follows:

[1397] Hardware and Software

[1398] Terminal: A tablet device used by the patient and robot operator, which displays a nurse call button and a question input interface.

[1399] Server: Receives requests, submits them to the generative AI model, and records the results.

[1400] Generative AI model: An artificial intelligence system that analyzes requests and generates automated responses.

[1401] Triage measures: Evaluate requests by combining vital signs and sensor data to determine urgency.

[1402] Remote communication means: The ability to conduct video calls between patients and nurses, and between robot operators and administrators.

[1403] Software Configuration

[1404] The system includes the following major software components:

[1405] Flask: A web framework for building API servers and accepting requests.

[1406] HuggingFace's transformers library: Generative AI models for question-answering.

[1407] Automated Response and Triage

[1408] Automated responses to general questions

[1409] The patient presses the nurse call button on the tablet device and enters a question.

[1410] The server receives the request and asks the generative AI model to process it.

[1411] The generative AI model analyzes the question and generates an appropriate answer.

[1412] The server sends the generated answer to the patient's tablet device and displays it to the patient.

[1413] Urgency assessment and notification

[1414] When a patient inputs an emergency request, the server receives the request and obtains vital information.

[1415] The triage tool integrates the request details with vital information and calculates an urgency score.

[1416] If the urgency score exceeds the threshold, the server sends an emergency notification to the nurse's tablet device.

[1417] Factory robot applications

[1418] The robot operator inputs questions from the operation panel.

[1419] The server receives the request and asks the generative AI model to process it.

[1420] The generative AI model generates an appropriate response and displays it on the robot's control panel.

[1421] If the robot operator inputs an error, the server integrates the sensor data and the error message to determine the urgency.

[1422] If the urgency exceeds the threshold, an emergency notification is sent to the administrator terminal.

[1423] Remote Communication

[1424] If a patient or robot operator wishes to have a video call, they send a request to the server.

[1425] The server relays the video call request to the nurse or administrator's device.

[1426] Video calls are initiated on the nurses' and administrators' devices, enabling direct communication.

[1427] Specific examples

[1428] Question-answering prompt examples

[1429] "When is my next dose?"

[1430] "An error suddenly occurred"

[1431] This allows the system of the present invention to apply the functions of a nurse call system to manufacturing sites, enabling quick and accurate responses to different requests.

[1432] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1433] Step 1:

[1434] A user (patient or robot operator) presses the nurse call button or inputs a question from a terminal, and the input request is sent to the server by the terminal.

[1435] Input: User question or request

[1436] Output: Request data sent to the server

[1437] Step 2:

[1438] The server analyzes the received request and requests the generative AI model to process it. The request content is converted into an appropriate prompt sentence and passed to the generative AI model.

[1439] Input: Request data received by the server

[1440] Output: The prompt sent to the generative AI model

[1441] Step 3:

[1442] The generative AI model analyzes the question based on the prompt and generates an appropriate answer, which is then returned to the server.

[1443] Input: Prompt sentence for the generative AI model

[1444] Output: The generated answer

[1445] Step 4:

[1446] The server receives the answer from the generative AI model and sends it to the patient or robot operator's device, which displays the answer to the user.

[1447] Input: Answer generated by the generative AI model

[1448] Output: The answer displayed on the user's terminal

[1449] Step 5:

[1450] When a patient or a robot operator inputs an urgent request, vital information or sensor data is sent to the server at the same time as the request.

[1451] Input: Emergency request and vital signs or sensor data

[1452] Output: Urgent request data sent to the server

[1453] Step 6:

[1454] The server integrates the emergency request with vital signs or sensor data, calculates an urgency score using triage methods, and sends an emergency notification if the urgency score exceeds a threshold.

[1455] Input: Emergency request data and vital signs or sensor data

[1456] Output: Urgency score and emergency notification

[1457] Step 7:

[1458] An emergency notification is sent from the server to the tablet device of the nurse or administrator, who then takes immediate action.

[1459] Input: Urgent notification from the server

[1460] Output: Emergency notification displayed on the nurse or manager's terminal

[1461] Step 8:

[1462] When a user (patient or robot operator) requests a video call, the request is sent from the terminal to the server, which relays the request to the other terminal and the video call begins.

[1463] Input: A video call request from a user

[1464] Output: Video call request relayed to the other device and video call initiated

[1465] 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.

[1466] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[1467] System configuration

[1468] 1. Nurse call button and terminal

[1469] - Device: A tablet device used by patients. It has a touch interface with a nurse call button. When a patient presses this button, a request is sent. The device also has an emotion engine to recognize the patient's emotions.

[1470] 2. Server

[1471] - Server: Receives nurse call requests, records them in a database, analyzes the request content and emotional state, and sends them to the generative AI model for processing.

[1472] 3. Generative AI Models

[1473] - Generative AI model: Analyzes the patient's request and emotional state and automatically generates a response. For example, in response to the request "What time is my medicine?", it generates a response such as "The next medicine is due at 2:00 PM."

[1474] 4. Triage Measures

[1475] - Triage method: Determines the level of urgency based on the content of the nurse call, the patient's vital signs, and their emotional state. If the level of urgency is high, a notification is sent to the nurse's tablet.

[1476] 5. Remote communication

[1477] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[1478] Program processing

[1479] Automated responses to general questions

[1480] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[1481] Terminal: Sends this request and the emotional state generated by the emotion engine to the server.

[1482] Server: Receives the request, analyzes the request content and emotional state, and initiates the process to request processing from the generative AI model.

[1483] Generative AI model (on the server): Analyzes the request and emotional state and generates an appropriate answer, for example, "The next medication time is 2:00 PM."

[1484] Server: Sends the generated response data to the patient's tablet device.

[1485] Terminal: Displays the received data to the patient in text format.

[1486] Triage

[1487] User (patient): Presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[1488] Device: Sends this urgent request and the emotional state generated by the emotion engine to the server.

[1489] Server: Receives the request and retrieves and integrates the patient's vital signs and emotional state from the database.

[1490] Server: Sends the integrated information to the generative AI model and requests it to determine the urgency of the situation.

[1491] Generative AI model (on the server): Calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[1492] Server: If the urgency score exceeds the set threshold, an emergency notification is immediately sent to the nurse's tablet device.

[1493] Terminal (Nurse): Receives notification, checks details, and prepares to go to the patient's room immediately.

[1494] Remote Communication

[1495] User (patient): If the patient wants to contact a nurse remotely, they can make a video call request from their tablet device.

[1496] Device: Sends a video call request and the emotional state generated by the emotion engine to the server.

[1497] Server: Relays the received request to the nurse's tablet device.

[1498] Terminal (nurse): Receives and responds to video call requests.

[1499] Terminal (Patient): A video call is initiated and the patient explains their current condition to the nurse.

[1500] Terminal (nurse): Checks on the patient's condition via video call and provides instructions and advice as needed.

[1501] Specific examples

[1502] Example 1: Common patient questions

[1503] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[1504] Terminal: Sends the question and emotional state to the server.

[1505] Server: Sends the request content and emotional state to the generation AI model for processing and obtains the answer.

[1506] Generative AI model (on the server): Generates the answer, "The next medicine time is 2:00 p.m."

[1507] Server: Sends the answer to the patient's device.

[1508] Terminal: Display the answers to the patient.

[1509] Example 2: Emergency response

[1510] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1511] Terminal: Sends the request and emotional state to the server.

[1512] Server: Determines the urgency based on the request, vital information, and emotional state.

[1513] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[1514] Server: Sends emergency notifications to nurses' tablets.

[1515] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[1516] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[1517] The processing flow will be explained below.

[1518] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[1519] Program processing

[1520] Automated responses to general questions

[1521] Step 1:

[1522] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[1523] Step 2:

[1524] The terminal converts the request and the patient's emotional state analyzed by the emotion engine into a digital signal and sends it to the server.

[1525] Step 3:

[1526] The server receives the request, analyzes the request content and emotional state, and initiates the process of requesting processing from the generative AI model.

[1527] Step 4:

[1528] A generative AI model (on the server) analyzes the request and emotional state and generates an appropriate answer, such as "Your next medication is due at 2 p.m."

[1529] Step 5:

[1530] The server sends the generated response data to the patient's tablet device.

[1531] Step 6:

[1532] The terminal displays the received data in text format to the patient.

[1533] Triage

[1534] Step 1:

[1535] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[1536] Step 2:

[1537] The terminal sends this emergency request and the patient's emotional state analyzed by the emotion engine to the server.

[1538] Step 3:

[1539] The server receives the request and retrieves and integrates the patient's vital information and emotional state from the database.

[1540] Step 4:

[1541] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[1542] Step 5:

[1543] The generative AI model (on the server) calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[1544] Step 6:

[1545] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[1546] Step 7:

[1547] The terminal (nurse) receives the notification, checks the details, and immediately prepares to head to the patient's room.

[1548] Remote Communication

[1549] Step 1:

[1550] When a user (patient) wants to contact a nurse remotely, they send a video call request from their tablet device.

[1551] Step 2:

[1552] The device sends a video call request and the patient's emotional state analyzed by the emotion engine to the server.

[1553] Step 3:

[1554] The server relays the received request to the nurse's tablet device.

[1555] Step 4:

[1556] The terminal (nurse) receives the video call request and responds.

[1557] Step 5:

[1558] A video call is initiated from the terminal (patient), and the patient explains their current condition to the nurse.

[1559] Step 6:

[1560] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[1561] Specific examples

[1562] Example 1: Common patient questions

[1563] Step 1:

[1564] The user (patient) presses the nurse call button and asks, "When is my next medication due?"

[1565] Step 2:

[1566] The device sends the question and emotional state to the server.

[1567] Step 3:

[1568] The server requests the request content and emotional state to be processed by a generative AI model and obtains a response.

[1569] Step 4:

[1570] The generative AI model (in the server) generates the answer, "The next medication time is 2:00 p.m."

[1571] Step 5:

[1572] The server sends the response to the patient's terminal.

[1573] Step 6:

[1574] The device displays the answers to the patient.

[1575] Example 2: Emergency response

[1576] Step 1:

[1577] The user (patient) presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1578] Step 2:

[1579] The device sends the request and emotional state to the server.

[1580] Step 3:

[1581] The server determines the urgency based on the request, vital information, and emotional state.

[1582] Step 4:

[1583] The generative AI model (within the server) calculates a high urgency score and notifies the server.

[1584] Step 5:

[1585] The server sends an emergency notification to the nurse's tablet device.

[1586] Step 6:

[1587] The terminal (nurse) receives the emergency notification and immediately performs on-site intervention.

[1588] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[1589] Example 2

[1590] 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."

[1591] When patients face an emergency situation in the hospital, or when they have everyday questions, it is difficult to get a quick and accurate answer. Another problem is that the workload of nurses increases, making it difficult to respond quickly. In particular, there is a lack of response that takes into account the emotional state of patients, and psychological care for patients is not being provided adequately. This can lead to a decrease in patient satisfaction and a sense of security.

[1592] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1593] In this invention, the server includes a terminal that transmits the request and emotional state when the patient operates the nurse call button, a server that receives the request and emotional state, records it in a database, and begins analysis, a generative AI model that analyzes the request content and emotional state received from the server and generates and transmits an automatic response, a terminal that displays the automatic response generated by the generative AI model to the patient, triage means that determines the urgency based on the request content, the patient's vital signs, and the patient's emotional state and sends an emergency notification as necessary, a server that receives the emergency notification from the triage means and sends the notification to the nurse's tablet device, means for sending the notification to the nurse's tablet device, and video call means that enables remote communication between the patient and the nurse. This enables a quick and accurate response to the patient's request and realizes a comprehensive response that also includes psychological care for the patient.

[1594] A "terminal" is a device that allows a patient to operate a nurse call button and has the function of transmitting requests and emotional states.

[1595] The "server" is a central control unit that receives requests and emotional states sent from the terminals, records them in a database and initiates the analysis.

[1596] A "generative AI model" is an artificial intelligence model that analyzes the request content and emotional state received from the server and generates and sends an automatic response.

[1597] The "triage method" is a system that determines the level of urgency based on the request content, the patient's vital signs, and their emotional state, and has the ability to send emergency notifications if necessary.

[1598] "Vital information" refers to key physiological data related to maintaining a patient's life, such as blood pressure, heart rate, and body temperature.

[1599] An "emergency notification" is alert information that is sent based on the level of urgency determined by the triage means and prompts nurses to take prompt action.

[1600] "Remote communication" refers to a means for patients and nurses to communicate remotely, including systems such as video calls.

[1601] "Emotional state" is information that indicates the psychological state of the patient analyzed by the emotion engine, and includes anxiety, relief, excitement, etc.

[1602] The present invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. The system of the present invention is configured as follows.

[1603] System Components

[1604] Nurse call button and terminal

[1605] The terminal is a tablet device that allows patients to operate the nurse call button. This terminal has the function of transmitting requests and emotional states. It also has an emotion engine that analyzes the patient's emotional state.

[1606] server

[1607] The server receives requests and emotional states sent from the devices, records them in a database, and then analyzes the request content and emotional state and requests processing from the generative AI model.

[1608] Generative AI Models

[1609] The generative AI model analyzes the request content and emotional state received from the server and generates an automatic response. For example, the model uses natural language processing technology to generate an appropriate response such as "The next medicine time is 2:00 PM" in response to a request such as "When is the next medicine time?"

[1610] Triage Measures

[1611] The triage system determines the level of urgency based on the request, the patient's vital signs, and their emotional state. If the urgency is high, the system sends an emergency notification to the nurse's tablet.

[1612] Remote Communication

[1613] To realize remote communication between patients and nurses, the video call function of the device is used. A video call request is sent from the device to a server, which then relays the request to the nurse's tablet device, and the video call begins.

[1614] Specific examples

[1615] Automated responses to general questions

[1616] 1. User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[1617] 2. Terminal: Sends the question and the emotional state determined by the emotion engine to the server.

[1618] 3. Server: Sends the request to the AI ​​model for processing and obtains the answer.

[1619] 4. Generative AI model: Generates the answer, "The next medication time is at 2:00 PM."

[1620] 5. Server: Sends the answer to the patient's device.

[1621] 6. Terminal: Displays the answers to the patient.

[1622] Emergency response

[1623] 1. User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1624] 2. Terminal: Sends the request content and the emotional state determined by the emotion engine to the server.

[1625] 3. Server: Determines the urgency of the request by integrating the request content, vital signs, and emotional state.

[1626] 4. Generative AI model: Calculates a high urgency score and notifies the server.

[1627] 5. Server: Sends emergency notifications to the nurses' tablets.

[1628] 6. Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[1629] Prompt Sentence Examples

[1630] "When is my next dose?"

[1631] "I suddenly had a pain in my chest"

[1632] Using the above components and processes, the system of the present invention responds quickly and appropriately to patient requests, reducing the workload of nurses while providing comprehensive care, including psychological care for patients.

[1633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1634] Step 1:

[1635] User (patient): Presses the nurse call button to input a request. For example, the user might ask, "When is my next medication due?" This input is the starting point for the entire system process.

[1636] Step 2:

[1637] Terminal: Collects requests entered by the patient and the corresponding emotional state (e.g., "anxiety") calculated by the emotion engine. Sends this data to the server. The input is the patient's question and emotional data, and the output is sending this data to the server.

[1638] Step 3:

[1639] Server: Receives the sent request and emotional state. Records the received data in a database and starts the analysis process. The input is the request and emotional data sent from the device, and the output is a processing request to the generative AI model.

[1640] Step 4:

[1641] Generative AI model (in the server): Analyzes the request content and emotional state received from the server. Generates an automatic response using natural language processing technology. The input is the request and emotional data sent from the server, and the output is the generated answer (e.g., "The next medication time is 2 p.m.").

[1642] Step 5:

[1643] Server: Receives the answers generated by the generative AI model and sends them to the patient's tablet device. The input is the answer data from the generative AI model, and the output is the sending of the answer data to the device.

[1644] Step 6:

[1645] Terminal: Receives the answer sent from the server and displays it on the screen. The patient confirms it. The input is the answer data from the server, and the output is the answer displayed on the screen.

[1646] Step 7:

[1647] User (Patient): If they have any further questions or concerns, they press the nurse call button again to enter their request. This cycle provides continuous support.

[1648] Triage

[1649] Step 1:

[1650] User (patient): Presses the nurse call button and inputs a request saying, "I suddenly have chest pain." This is an emergency request.

[1651] Step 2:

[1652] Terminal: Collects requests and emotional states (e.g., "fear") from the emotion engine and sends them to the server. The input is the patient's urgent request and emotional data, and the output is the data sent to the server.

[1653] Step 3:

[1654] Server: Receives emergency requests and emotional states, and retrieves and integrates the patient's vital information from the database. The input is data from the device and vital information from the database, and the output is the integrated data.

[1655] Step 4:

[1656] Generative AI model (on the server): Analyzes the integrated data and calculates the urgency score. The input is the integrated request, emotional state, and vital information, and the output is the urgency score.

[1657] Step 5:

[1658] Server: If the urgency score exceeds the threshold, it sends an emergency notification to the nurse's tablet. The input is the urgency score, and the output is the emergency notification to the nurse's device.

[1659] Step 6:

[1660] Terminal (nurse): Receives emergency notification, checks detailed information, and immediately prepares to go to the patient's room. The input is the emergency notification, and the output is the nurse's actions.

[1661] Remote Communication

[1662] Step 1:

[1663] User (patient): Sends a video call request from a tablet device. The input is a video call request.

[1664] Step 2:

[1665] Terminal: Sends a video call request and the emotional state (e.g., "anxiety") generated by the emotion engine to the server. The input is the video call request and emotion data, and the output is the data sent to the server.

[1666] Step 3:

[1667] Server: Relays video call requests to the nurse's tablet. The input is the video call request from the device, and the output is the relayed data to the nurse's device.

[1668] Step 4:

[1669] Terminal (nurse): Receives and responds to video call requests. The input is a video call request, and the output is the start of a video call.

[1670] Step 5:

[1671] User (patient): A video call is initiated with a nurse, describing the current state. The input is the initiation of the video call, and the output is the patient description.

[1672] Step 6:

[1673] Terminal (nurse): Checks the patient's condition via video call and provides instructions and advice as needed. The input is the patient's explanation, and the output is the nurse's instructions and advice.

[1674] (Application example 2)

[1675] 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."

[1676] Conventional nurse call systems have difficulty responding quickly and appropriately to requests from patients, placing a heavy burden on nurses. They also struggle to take into account the patient's emotional state, which can lead to poor communication quality. Similarly, in brick-and-mortar stores, it's difficult to respond quickly and appropriately to customer requests, often resulting in poor customer satisfaction.

[1677] 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 receiving and processing requests operated by patients and customers, generation AI model means for analyzing the request content and emotional state and generating an automatic response, means for displaying the generated automatic response and realizing remote communication, and triage means. This enables quick and appropriate responses to requests from patients and customers, reduces the burden on nurses and staff, and improves patient and customer satisfaction.

[1678] A "patient" is a person who receives treatment or care at a medical institution or hospital.

[1679] A "nurse call button" is an interface device that patients use to make requests or contact nurses in an emergency.

[1680] A "terminal" is an electronic device used to send and receive requests at a medical institution or physical store.

[1681] A "server" is a device that provides the computing resources to receive and analyze requests, and generate and send automated responses.

[1682] A "generative AI model" is a system equipped with artificial intelligence technology that analyzes the request content and emotional state and automatically generates an appropriate response.

[1683] An "automated response" is an answer or response automatically provided in response to a request by a generative AI model.

[1684] "Triage measures" is a function that determines the urgency of a request based on its content and emotional state, and sends an emergency notification if necessary.

[1685] "Remote communication" is a means by which people in distant locations communicate with each other via electronic devices.

[1686] "Video calling means" is a function that enables real-time communication by sending and receiving audio and video through a terminal.

[1687] An "emergency notification" is a notification message sent to nurses and staff when a high level of urgency is determined.

[1688] A "customer support button" is an interface device that a customer uses to request support within a store.

[1689] The "urgency score" is a numerical assessment of the urgency calculated based on the request content, emotional state, vital information, etc.

[1690] This invention utilizes generative AI models and emotion engines to improve the efficiency and quality of responses in nurse call systems and brick-and-mortar customer support systems.

[1691] System configuration

[1692] 1. Nurse call button and customer support button and terminal

[1693] The terminal is an electronic device used by patients and customers in medical institutions and brick-and-mortar stores, and displays a nurse call button or customer support button on the touch interface. When a patient or customer presses the button, a request is sent. The terminal also has an emotion engine for recognizing emotions.

[1694] 2. Server

[1695] The server receives nurse call and customer support requests, records them in a database, analyzes the request content and emotional state, requests a generative AI model to process them, records the generated automated response, and sends it back to the device.

[1696] 3. Generative AI Models

[1697] The generative AI model analyzes the request and the patient's emotional state and automatically generates a response. For example, in response to a patient's request, "When is my medicine due?", the model might respond, "The next medicine is due at 2 p.m."

[1698] 4. Triage Measures

[1699] The triage system determines the level of urgency based on the content of nurse call and customer support requests, the patient's vital signs, and the customer's emotional state. If the level of urgency is high, an emergency notification is sent to the staff member's tablet device.

[1700] 5. Remote communication

[1701] The remote communication function allows video calls between patients / customers and nurses / staff via terminals. This function is realized by communication between the server and terminals.

[1702] What the program does

[1703] The server performs the following process.

[1704] 1. Sentiment analysis:

[1705] Send the patient or customer request text to an emotion engine API (e.g., EmotionAPI) to analyze the emotional state.

[1706] 2. Response generation:

[1707] Have a generative AI model API (e.g., AIModelAPI) generate an appropriate response using the request text and the analyzed emotional state.

[1708] 3. Staff Notification:

[1709] The level of urgency is determined based on the emotional state and the generated response, and if the level of urgency is high, an emergency notification is sent to a nurse or staff member via a triage means.

[1710] Specific examples

[1711] Example 1: Common patient questions

[1712] Patient: "When is my next dose?"

[1713] Terminal: Sends questions and emotional states to the server.

[1714] Server: Sends the request to the generative AI model and generates an answer such as "The next medicine time is at 2:00 p.m."

[1715] Terminal: Displays the generated answers to the patient.

[1716] Example 2: Urgent customer request

[1717] Customer: "What items are in stock?"

[1718] Terminal: Sends questions and emotional states to the server.

[1719] Server: Sends the request content to the generative AI model and generates a response.

[1720] High stress levels are identified using the emotion engine.

[1721] Server: Sends emergency notifications to staff.

[1722] Terminal: Display the answer to the customer.

[1723] Prompt Sentence Examples

[1724] "What products are in stock?"

[1725] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1726] Step 1:

[1727] The patient or customer (user) operates the nurse call button or customer support button on the terminal. They input the request details as text. This operation causes the terminal to send the request details and the emotional state analyzed by the emotion engine to the server. The input is the request text and emotional data, and the output is data sent to the server.

[1728] Step 2:

[1729] The server stores the received request content and emotional state. Then, it converts the request content and emotional state into JSON format to send to the generative AI model. The input is the request text and emotional data, and the output is the input data to the generative AI model.

[1730] Step 3:

[1731] The generative AI model receives the request content and emotional state from the server, performs text analysis, and generates an appropriate response based on the analyzed results. The input is the request text and emotional data, and the output is the response text.

[1732] Step 4:

[1733] The server analyzes the response text received from the generative AI model and, if necessary, determines the level of urgency using triage methods. If the level of urgency is determined to be high, an emergency notification is sent to the terminals of staff and nurses. The input is the response text and emotion data, and the output is the emergency notification data or response data.

[1734] Step 5:

[1735] The terminal displays the response text received from the server to the user. If the urgency is high, a notification by the triage means is also displayed. The input is the response text from the server, and the output is the display to the user.

[1736] Step 6:

[1737] The nurse or staff member (user) who receives the emergency notification checks the content of the notification and takes on-site action as necessary. This process ensures a prompt response to the user. The input is the emergency notification data, and the output is the on-site response action.

[1738] 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.

[1739] 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.

[1740] 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.

[1741] [Fourth embodiment]

[1742] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1743] 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.

[1744] 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).

[1745] 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.

[1746] 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.

[1747] 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).

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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.

[1753] 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.

[1754] 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."

[1755] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[1756] System configuration

[1757] 1. Nurse call button and terminal

[1758] - Device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is made.

[1759] 2. Server

[1760] - Server: Receives nurse call requests, records them in a database, analyzes the request content, and sends it to the generative AI model for processing.

[1761] 3. Generative AI Models

[1762] - Generative AI model: Analyzes requests from patients and automatically generates answers. For example, in response to a request such as "What time is my medicine?", it generates an answer such as "The next medicine is due at 2:00 PM."

[1763] 4. Triage Measures

[1764] - Triage method: Determine the level of urgency based on the content of the nurse call and the patient's vital signs. If the level of urgency is high, a notification is sent to the nurse's tablet.

[1765] 5. Remote communication

[1766] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[1767] Program processing

[1768] Automated responses to general questions

[1769] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[1770] Device: Sends this request to the server.

[1771] Server: Receives requests and sends them to the generative AI model for processing.

[1772] Generative AI model (on the server): Analyzes the request and generates an appropriate answer, such as "The next medication time is at 2 p.m."

[1773] Server: Sends the generated answers to the patient's tablet device.

[1774] Terminal: Display the answers to the patient.

[1775] Triage

[1776] User (patient): Presses the nurse call button and enters an emergency request such as "I suddenly have chest pain."

[1777] Device: Sends this request to the server.

[1778] Server: Receives the request, obtains vital signs, and asks the generative AI model to determine the level of urgency.

[1779] Generative AI model (on the server): Integrates the request content and vital signs to calculate an urgency score. If "chest pain" is determined to be a serious symptom, a high urgency score is assigned.

[1780] Server: If the urgency score exceeds the threshold, a notification is sent to the nurse's tablet.

[1781] Terminal (Nurse): Receives notification and prepares to go to the patient's room immediately.

[1782] Remote Communication

[1783] User (patient): If the patient wants to contact a nurse via video call, he or she sends a request from the device.

[1784] Device: Sends a video call request to the server.

[1785] Server: Relays the request to the nurse's tablet.

[1786] Terminal (nurse): Receives requests and answers video calls.

[1787] Terminal (Patient): A video call is initiated and the patient explains their condition to the nurse.

[1788] Terminal (Nurse): Checks the situation and provides instructions and advice as needed.

[1789] Specific examples

[1790] Example 1: Common patient questions

[1791] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[1792] Terminal: Sends a question to the server.

[1793] Server: Requests processing from the generative AI model and obtains the answer.

[1794] Generative AI model (on the server): Generates the answer, "The next medication time is at 2:00 p.m."

[1795] Server: Sends the answer to the patient's device.

[1796] Terminal: Display answers to patient.

[1797] Example 2: Emergency response

[1798] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[1799] Device: Sends a request to the server.

[1800] Server: Determines the urgency based on the request and vital signs.

[1801] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[1802] Server: Sends emergency notifications to nurses' tablets.

[1803] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[1804] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. Each component works together to enable efficient nurse call response.

[1805] The processing flow will be explained below.

[1806] This invention aims to improve the efficiency and quality of nurse call systems by using generative AI models. This system is implemented with the following configuration.

[1807] Program processing

[1808] Automated responses to general questions

[1809] Step 1:

[1810] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[1811] Step 2:

[1812] The terminal converts this request into a digital signal and sends it to the server.

[1813] Step 3:

[1814] The server receives the request, analyzes the request content, and starts the process of requesting processing from the generative AI model.

[1815] Step 4:

[1816] The generative AI model (on the server) analyzes the request and generates an appropriate answer, such as "The next medication time is 2:00 PM."

[1817] Step 5:

[1818] The server sends the generated response data to the patient's tablet device.

[1819] Step 6:

[1820] The terminal displays the received data in text format to the patient.

[1821] Triage

[1822] Step 1:

[1823] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[1824] Step 2:

[1825] The terminal sends this emergency request to the server.

[1826] Step 3:

[1827] The server receives the request and retrieves and consolidates the patient's vital information from the database.

[1828] Step 4:

[1829] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[1830] Step 5:

[1831] The generative AI model (on the server) calculates an urgency score based on the request content and vital signs. In this case, "chest pain" is determined to be a serious symptom and a high urgency score is assigned.

[1832] Step 6:

[1833] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[1834] Step 7:

[1835] The terminal (nurse) receives the emergency notification, checks the details, and immediately prepares to go to the patient's room.

[1836] Remote Communication

[1837] Step 1:

[1838] The user (patient) sends a video call request from a tablet device to contact a nurse remotely.

[1839] Step 2:

[1840] The terminal sends a video call request to the server.

[1841] Step 3:

[1842] The server relays the received request to the nurse's tablet device.

[1843] Step 4:

[1844] The terminal (nurse) receives the video call request and responds.

[1845] Step 5:

[1846] A video call is initiated on the terminal (patient), and the patient explains their current condition to the nurse.

[1847] Step 6:

[1848] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[1849] Through these processing steps, this system reduces the workload of nurses and enables prompt and appropriate care for patients. Each component works together to enable efficient nurse call responses and the provision of high-quality services.

[1850] Example 1

[1851] 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."

[1852] Conventional nurse call systems can be slow to respond to patient requests, and rapid response is especially required in emergencies. This can also increase the workload of nurses, making it difficult to provide efficient medical care. To address these issues, a system that can respond quickly and appropriately to patient needs is needed.

[1853] 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.

[1854] In this invention, the server includes an electronic device that sends a request when a patient operates the nurse call button, an electronic computer that receives the request and records it in an information recording device, an AI generation means that analyzes the request content and generates and sends an automatic response, a priority determination means that determines the urgency based on the request content and biometric information and issues an emergency notification as necessary, and a video communication means that enables remote communication between the patient and nursing professionals. This reduces the workload of nurses and enables prompt and appropriate care for patients.

[1855] An "electronic device" is a device that allows a patient to operate a nurse call button to send a request.

[1856] An "electronic computer" is a computing device that has the function of receiving requests and recording them in an information recording device.

[1857] The "generative AI means" is an AI model that analyzes the request content received from the server and generates and sends an automatic response.

[1858] "Biometric information" is data that indicates the patient's health condition, such as heart rate, blood pressure, and respiratory rate.

[1859] The "priority determination means" is a device that determines the level of urgency based on the request content and biometric information, and issues an emergency notification as necessary.

[1860] A "nursing professional" is a health care worker trained to provide medical care to patients.

[1861] A "mobile terminal" is an electronic terminal device that can be carried by a nursing professional.

[1862] "Video communication means" refers to a communication means that enables video communication between a patient and a nursing professional.

[1863] This invention aims to improve the efficiency and quality of a nurse call system by using a generative AI model. This system consists of an electronic device used by the patient, a server, a generative AI means, a priority determination means, a mobile terminal for nursing professionals, and a video communication means.

[1864] System configuration

[1865] 1. Patient's electronic device: A tablet device used by the patient, with a nurse call button displayed on the touch interface. When the patient presses this button, a request is sent from the device.

[1866] 2. Server: Receives requests sent from the patient's electronic device, records them in the information recording device, and sends the request content to the AI ​​generation means to request it to generate a response.

[1867] 3. Generative AI means: The generative AI means analyzes the request content and generates an appropriate automated response. For example, in response to the request "What time is my next medicine?", it generates the answer "My next medicine is due at 2:00 PM."

[1868] 4. Priority determination means: The priority determination means determines the urgency level based on the request content and the patient's biological information. For example, if a request is made such as "I suddenly have chest pain," this means calculates an urgency score, and if a high urgency score is assigned, a notification is sent to the nursing professional's mobile device.

[1869] 5. Mobile terminal of nursing specialist: The nursing specialist uses this terminal to receive emergency notifications, and upon receiving the notification, the nursing specialist immediately begins to respond.

[1870] 6. Video Calling: This has the function to conduct video calls between the patient and the nursing professional. The communication is carried out between the patient's electronic device, the server, and the nursing professional's mobile device.

[1871] Specific examples

[1872] Example 1: Common patient questions

[1873] The user (patient) presses the nurse call button and asks, "When is my next medication due?" The terminal sends this request to the server, which then asks the generation AI means to process it. The generation AI means generates the answer, "The next medication is due at 2:00 PM," and this answer is sent via the server to the patient's electronic device. Finally, the terminal displays the answer to the patient.

[1874] Example 2: Emergency response

[1875] The user (patient) presses the nurse call button to send a request saying, "I suddenly have chest pain." This request is sent from the device to the server, which acquires the biometric information and asks the AI ​​generation means to determine the level of urgency. The AI ​​generation means calculates a high urgency score, and the server notifies the nursing professional of this information on their mobile device. The nursing professional receives the emergency notification and immediately begins responding.

[1876] Prompt Sentence Examples

[1877] "When is my next dose?"

[1878] "I suddenly had a pain in my chest"

[1879] The system uses generative AI models and prompts to enable efficient and rapid nurse call responses, reducing the workload for nurses and improving the quality of patient care.

[1880] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1881] Step 1:

[1882] The user (patient) operates the nurse call button to input a request.

[1883] Input: Patient question or request text (e.g., "When is my next medication?", "I suddenly have chest pain," etc.)

[1884] Output: Request data to be sent to the device

[1885] Specific operation: The patient touches the nurse call button on the tablet device and enters a question or request in the input field that appears. The input content is a specific question such as "When is my next medication due?"

[1886] Step 2:

[1887] The device sends a request to the server.

[1888] Input: Request data entered by the patient

[1889] Output: Request data sent to the server

[1890] Specific operation: The device sends a request to the server via Wi-Fi or wired LAN. The transmitted data includes the patient ID and the request content.

[1891] Step 3:

[1892] The server analyzes the received request and sends it to the generative AI model.

[1893] Input: Request data sent from the terminal

[1894] Output: Prompt sentence to be passed to the generative AI model

[1895] What it does: The server parses the request data and sends the appropriate prompt (e.g., "When is my next medicine due?") to the generative AI model.

[1896] Step 4:

[1897] A generative AI model analyzes the request and generates an answer.

[1898] Input: Prompt sent from the server

[1899] Output: Generated answer text

[1900] What it does: The generative AI model uses natural language processing algorithms to analyze the prompt and generate an appropriate response (e.g., "Your next medication is due at 2 p.m.").

[1901] Step 5:

[1902] The server sends the generated response to the patient's terminal.

[1903] Input: Answer text obtained from the generative AI model

[1904] Output: Response data sent to the patient's device

[1905] What it does: The server receives the answer from the generative AI model and sends this data to the patient's electronic device in the appropriate format.

[1906] Step 6:

[1907] The device displays the answers to the patient.

[1908] Input: Response data sent from the server

[1909] Output: Answer text displayed on the screen

[1910] Specific operation: The device receives the answer text and displays it on the screen in a popup or dedicated window. The user checks the display on the screen.

[1911] Step 7:

[1912] In an emergency, the server acquires vital information and asks the generative AI model to determine the level of urgency.

[1913] Input: Emergency request details and patient vitals

[1914] Output: Urgency score

[1915] Specific operation: The server obtains the patient's heart rate and blood pressure information from a medical database, sends it to the generative AI model, and performs an urgency assessment that integrates the request content and vital information.

[1916] Step 8:

[1917] A generative AI model calculates an urgency score.

[1918] Input: Request details and vital information sent from the server

[1919] Output: Urgency score

[1920] Specific operation: The generative AI model calculates an urgency score based on the request content and vital information, and returns a high urgency score to the server.

[1921] Step 9:

[1922] The server sends a notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[1923] Input: Urgency score and threshold

[1924] Output: Emergency notification to nursing professional's mobile device

[1925] Specific operation: The server evaluates the urgency score and sends a push notification to the nursing professional's mobile device if the urgency score exceeds a threshold.

[1926] Step 10:

[1927] The terminal (nursing professional) receives the emergency notification and immediately begins responding.

[1928] Input: Urgent notification sent from the server

[1929] Output: Emergency response by nursing professionals initiated

[1930] Specific actions: The nursing professional checks the notification on the mobile device and immediately initiates the necessary action (e.g., rushing to the scene).

[1931] Step 11:

[1932] The user (patient) makes a video call request.

[1933] Input: Video call request (e.g., "I'd like to video call with a nurse")

[1934] Output: Video call request data from the device to the server

[1935] Specific actions: The patient activates the video call function on the tablet device and presses the call button.

[1936] Step 12:

[1937] The terminal sends a video call request to the server.

[1938] Input: Patient video call request data

[1939] Output: Data sent to the server

[1940] Specific operation: The device performs the communication processing necessary to send a video call request to the server.

[1941] Step 13:

[1942] The server relays the video call request to the nursing professional's mobile terminal.

[1943] Input: Patient video call request data

[1944] Output: Video call request data to the nursing professional's mobile device

[1945] Specific operation: The server receives the patient's video call request and relays it to the nursing professional's mobile device.

[1946] Step 14:

[1947] The terminal (nursing professional) answers the video call and communicates with the patient via the screen.

[1948] Input: Video call request from server

[1949] Output: Start a video call with the patient

[1950] What it does: A nursing professional answers a video call on a mobile device, checks on the patient's condition, and provides necessary instructions and advice.

[1951] This program utilizes a generative AI model and prompts to efficiently perform a series of tasks, including analyzing requests, generating automatic responses, determining urgency, and relaying video calls, thereby enabling prompt and appropriate responses to patients.

[1952] (Application example 1)

[1953] 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."

[1954] Modern nurse call systems are important for reducing the workload of nurses and providing prompt and appropriate care to patients. However, similar challenges exist in manufacturing. Robot operators in manufacturing must be able to quickly respond to problems and questions, and when errors occur, they must be able to immediately assess the urgency and take appropriate action. Technical means for facilitating communication between workers and management are also important. The present invention provides a system that solves these challenges.

[1955] 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.

[1956] In this invention, the server includes a terminal that sends a request when a patient operates a nurse call button, a means for receiving the request and recording it in a database, a means for displaying an automated response generated by the generative AI model to the patient, a means for determining the level of urgency based on the request content and the patient's vital signs and sending a notification to the nurse's tablet device, a video call means for enabling remote communication between the patient and the nurse, a means for generating a response when a robot operator inputs a question in a factory and displaying it on a robot operation panel, a means for integrating error messages and sensor data based on the robot operator's input and determining the level of urgency, a means for sending a notification to a manager's terminal when the level of urgency exceeds a threshold, and a means for enabling video calls between the robot operator and the manager. This enables prompt responses to questions from robot operators and appropriate responses to emergencies even at manufacturing sites.

[1957] The "terminal that sends a request when a patient presses the nurse call button" is a device that sends a request when a patient presses the nurse call button in an emergency or when they have a question.

[1958] The "server that receives requests and records them in a database" is a computer that receives requests from patients and stores the contents of those requests in a database.

[1959] A "generative AI model that analyzes request content and generates and sends an automatic response" is an artificial intelligence system that automatically analyzes the content of a received request and generates and sends an appropriate automatic response.

[1960] A "terminal that displays the generated automated response to the patient" is a device that displays the automated response generated by the generative AI model so that the patient can check it.

[1961] "Triage method that determines the level of urgency based on the request content and the patient's vital signs, and issues an emergency notification if necessary" is a function that integrates the request content and the patient's vital signs to evaluate the level of urgency, and issues an emergency notification if the level of urgency is high.

[1962] The "server that receives emergency notifications from the triage means and sends notifications to the tablet devices of nurses" is a computer that receives emergency notifications sent by the triage means and sends the notifications to the tablet devices held by nurses.

[1963] The "means for sending a notification to the tablet terminal of the nurse" is a function for sending an emergency notification from the server to the tablet terminal of the nurse.

[1964] "Video calling means enabling remote communication between patients and nurses" is a video calling function that allows patients and nurses to communicate directly from a distance.

[1965] "A means of using a generative AI model to generate a response when a robot operator in a factory inputs a question and displays it on the robot operation panel" is a function that analyzes a question input by a robot operator in a factory, generates an automatic response, and displays it on the robot operation panel.

[1966] "Means for integrating error messages and sensor data based on input from the robot operator and determining the level of urgency" is a function that analyzes the error messages input by the robot operator and the robot's sensor data and evaluates the level of urgency.

[1967] The "means for sending a notification to the administrator's terminal when the urgency exceeds a threshold" is a function for sending a notification to the terminal held by the administrator when the urgency exceeds a set threshold.

[1968] "Means for realizing video calls between a robot operator and an administrator" is a function that enables a robot operator and an administrator to communicate via video calls.

[1969] This invention utilizes generative AI models to improve the efficiency and quality of nurse call systems. We also describe a system that can support robot operators and respond to emergencies in the manufacturing industry.

[1970] The basic configuration of the system is as follows:

[1971] Hardware and Software

[1972] Terminal: A tablet device used by the patient and robot operator, which displays a nurse call button and a question input interface.

[1973] Server: Receives requests, submits them to the generative AI model, and records the results.

[1974] Generative AI model: An artificial intelligence system that analyzes requests and generates automated responses.

[1975] Triage measures: Evaluate requests by combining vital signs and sensor data to determine urgency.

[1976] Remote communication means: The ability to conduct video calls between patients and nurses, and between robot operators and administrators.

[1977] Software Configuration

[1978] The system includes the following major software components:

[1979] Flask: A web framework for building API servers and accepting requests.

[1980] HuggingFace's transformers library: Generative AI models for question-answering.

[1981] Automated Response and Triage

[1982] Automated responses to general questions

[1983] The patient presses the nurse call button on the tablet device and enters a question.

[1984] The server receives the request and asks the generative AI model to process it.

[1985] The generative AI model analyzes the question and generates an appropriate answer.

[1986] The server sends the generated answer to the patient's tablet device and displays it to the patient.

[1987] Urgency assessment and notification

[1988] When a patient inputs an emergency request, the server receives the request and obtains vital information.

[1989] The triage tool integrates the request details with vital information and calculates an urgency score.

[1990] If the urgency score exceeds the threshold, the server sends an emergency notification to the nurse's tablet device.

[1991] Factory robot applications

[1992] The robot operator inputs questions from the operation panel.

[1993] The server receives the request and asks the generative AI model to process it.

[1994] The generative AI model generates an appropriate response and displays it on the robot's control panel.

[1995] If the robot operator inputs an error, the server integrates the sensor data and the error message to determine the urgency.

[1996] If the urgency exceeds the threshold, an emergency notification is sent to the administrator terminal.

[1997] Remote Communication

[1998] If a patient or robot operator wishes to have a video call, they send a request to the server.

[1999] The server relays the video call request to the nurse or administrator's device.

[2000] Video calls are initiated on the nurses' and administrators' devices, enabling direct communication.

[2001] Specific examples

[2002] Question-answering prompt examples

[2003] "When is my next dose?"

[2004] "An error suddenly occurred"

[2005] This allows the system of the present invention to apply the functions of a nurse call system to manufacturing sites, enabling quick and accurate responses to different requests.

[2006] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2007] Step 1:

[2008] A user (patient or robot operator) presses the nurse call button or inputs a question from a terminal, and the input request is sent to the server by the terminal.

[2009] Input: User question or request

[2010] Output: Request data sent to the server

[2011] Step 2:

[2012] The server analyzes the received request and requests the generative AI model to process it. The request content is converted into an appropriate prompt sentence and passed to the generative AI model.

[2013] Input: Request data received by the server

[2014] Output: The prompt sent to the generative AI model

[2015] Step 3:

[2016] The generative AI model analyzes the question based on the prompt and generates an appropriate answer, which is then returned to the server.

[2017] Input: Prompt sentence for the generative AI model

[2018] Output: The generated answer

[2019] Step 4:

[2020] The server receives the answer from the generative AI model and sends it to the patient or robot operator's device, which displays the answer to the user.

[2021] Input: Answer generated by the generative AI model

[2022] Output: The answer displayed on the user's terminal

[2023] Step 5:

[2024] When a patient or a robot operator inputs an urgent request, vital information or sensor data is sent to the server at the same time as the request.

[2025] Input: Emergency request and vital signs or sensor data

[2026] Output: Urgent request data sent to the server

[2027] Step 6:

[2028] The server integrates the emergency request with vital signs or sensor data, calculates an urgency score using triage methods, and sends an emergency notification if the urgency score exceeds a threshold.

[2029] Input: Emergency request data and vital signs or sensor data

[2030] Output: Urgency score and emergency notification

[2031] Step 7:

[2032] An emergency notification is sent from the server to the tablet device of the nurse or administrator, who then takes immediate action.

[2033] Input: Urgent notification from the server

[2034] Output: Emergency notification displayed on the nurse or manager's terminal

[2035] Step 8:

[2036] When a user (patient or robot operator) requests a video call, the request is sent from the terminal to the server, which relays the request to the other terminal and the video call begins.

[2037] Input: A video call request from a user

[2038] Output: Video call request relayed to the other device and video call initiated

[2039] 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.

[2040] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[2041] System configuration

[2042] 1. Nurse call button and terminal

[2043] - Device: A tablet device used by patients. It has a touch interface with a nurse call button. When a patient presses this button, a request is sent. The device also has an emotion engine to recognize the patient's emotions.

[2044] 2. Server

[2045] - Server: Receives nurse call requests, records them in a database, analyzes the request content and emotional state, and sends them to the generative AI model for processing.

[2046] 3. Generative AI Models

[2047] - Generative AI model: Analyzes the patient's request and emotional state and automatically generates a response. For example, in response to the request "What time is my medicine?", it generates a response such as "The next medicine is due at 2:00 PM."

[2048] 4. Triage Measures

[2049] - Triage method: Determines the level of urgency based on the content of the nurse call, the patient's vital signs, and their emotional state. If the level of urgency is high, a notification is sent to the nurse's tablet.

[2050] 5. Remote communication

[2051] - Terminal: A terminal that has the function to conduct video calls between patients and nurses. This is realized through communication between the terminal and the server.

[2052] Program processing

[2053] Automated responses to general questions

[2054] User (Patient): Presses the nurse call button and enters a question, such as "When is my next medication due?"

[2055] Terminal: Sends this request and the emotional state generated by the emotion engine to the server.

[2056] Server: Receives the request, analyzes the request content and emotional state, and initiates the process to request processing from the generative AI model.

[2057] Generative AI model (on the server): Analyzes the request and emotional state and generates an appropriate answer, for example, "The next medication time is 2:00 PM."

[2058] Server: Sends the generated response data to the patient's tablet device.

[2059] Terminal: Displays the received data to the patient in text format.

[2060] Triage

[2061] User (patient): Presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[2062] Device: Sends this urgent request and the emotional state generated by the emotion engine to the server.

[2063] Server: Receives the request and retrieves and integrates the patient's vital signs and emotional state from the database.

[2064] Server: Sends the integrated information to the generative AI model and requests it to determine the urgency of the situation.

[2065] Generative AI model (on the server): Calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[2066] Server: If the urgency score exceeds the set threshold, an emergency notification is immediately sent to the nurse's tablet device.

[2067] Terminal (Nurse): Receives notification, checks details, and prepares to go to the patient's room immediately.

[2068] Remote Communication

[2069] User (patient): If the patient wants to contact a nurse remotely, they can make a video call request from their tablet device.

[2070] Device: Sends a video call request and the emotional state generated by the emotion engine to the server.

[2071] Server: Relays the received request to the nurse's tablet device.

[2072] Terminal (nurse): Receives and responds to video call requests.

[2073] Terminal (Patient): A video call is initiated and the patient explains their current condition to the nurse.

[2074] Terminal (nurse): Checks on the patient's condition via video call and provides instructions and advice as needed.

[2075] Specific examples

[2076] Example 1: Common patient questions

[2077] User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[2078] Terminal: Sends the question and emotional state to the server.

[2079] Server: Sends the request content and emotional state to the generation AI model for processing and obtains the answer.

[2080] Generative AI model (on the server): Generates the answer, "The next medicine time is 2:00 p.m."

[2081] Server: Sends the answer to the patient's device.

[2082] Terminal: Display the answers to the patient.

[2083] Example 2: Emergency response

[2084] User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[2085] Terminal: Sends the request and emotional state to the server.

[2086] Server: Determines the urgency based on the request, vital information, and emotional state.

[2087] Generative AI model (in the server): Calculates a high urgency score and notifies the server.

[2088] Server: Sends emergency notifications to nurses' tablets.

[2089] Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[2090] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[2091] The processing flow will be explained below.

[2092] This invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. This system is implemented in the following configuration.

[2093] Program processing

[2094] Automated responses to general questions

[2095] Step 1:

[2096] The user (patient) presses the nurse call button on a tablet device and enters a question such as, "When is my next medication due?"

[2097] Step 2:

[2098] The terminal converts the request and the patient's emotional state analyzed by the emotion engine into a digital signal and sends it to the server.

[2099] Step 3:

[2100] The server receives the request, analyzes the request content and emotional state, and initiates the process of requesting processing from the generative AI model.

[2101] Step 4:

[2102] A generative AI model (on the server) analyzes the request and emotional state and generates an appropriate answer, such as "Your next medication is due at 2 p.m."

[2103] Step 5:

[2104] The server sends the generated response data to the patient's tablet device.

[2105] Step 6:

[2106] The terminal displays the received data in text format to the patient.

[2107] Triage

[2108] Step 1:

[2109] The user (patient) presses the nurse call button and enters the request, saying, "I suddenly have chest pain."

[2110] Step 2:

[2111] The terminal sends this emergency request and the patient's emotional state analyzed by the emotion engine to the server.

[2112] Step 3:

[2113] The server receives the request and retrieves and integrates the patient's vital information and emotional state from the database.

[2114] Step 4:

[2115] The server sends the integrated information to the generative AI model and requests it to determine the level of urgency.

[2116] Step 5:

[2117] The generative AI model (on the server) calculates an urgency score based on the request, vital signs, and emotional state. In this case, it assigns a high urgency score of "chest pain."

[2118] Step 6:

[2119] If the urgency score exceeds a set threshold, the server immediately sends an emergency notification to the nurse's tablet device.

[2120] Step 7:

[2121] The terminal (nurse) receives the notification, checks the details, and immediately prepares to head to the patient's room.

[2122] Remote Communication

[2123] Step 1:

[2124] When a user (patient) wants to contact a nurse remotely, they send a video call request from their tablet device.

[2125] Step 2:

[2126] The device sends a video call request and the patient's emotional state analyzed by the emotion engine to the server.

[2127] Step 3:

[2128] The server relays the received request to the nurse's tablet device.

[2129] Step 4:

[2130] The terminal (nurse) receives the video call request and responds.

[2131] Step 5:

[2132] A video call is initiated from the terminal (patient), and the patient explains their current condition to the nurse.

[2133] Step 6:

[2134] The terminal (nurse) checks the patient's condition via video call and provides instructions and advice as needed.

[2135] Specific examples

[2136] Example 1: Common patient questions

[2137] Step 1:

[2138] The user (patient) presses the nurse call button and asks, "When is my next medication due?"

[2139] Step 2:

[2140] The device sends the question and emotional state to the server.

[2141] Step 3:

[2142] The server requests the request content and emotional state to be processed by a generative AI model and obtains a response.

[2143] Step 4:

[2144] The generative AI model (in the server) generates the answer, "The next medication time is 2:00 p.m."

[2145] Step 5:

[2146] The server sends the response to the patient's terminal.

[2147] Step 6:

[2148] The device displays the answers to the patient.

[2149] Example 2: Emergency response

[2150] Step 1:

[2151] The user (patient) presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[2152] Step 2:

[2153] The device sends the request and emotional state to the server.

[2154] Step 3:

[2155] The server determines the urgency based on the request, vital information, and emotional state.

[2156] Step 4:

[2157] The generative AI model (within the server) calculates a high urgency score and notifies the server.

[2158] Step 5:

[2159] The server sends an emergency notification to the nurse's tablet device.

[2160] Step 6:

[2161] The terminal (nurse) receives the emergency notification and immediately performs on-site intervention.

[2162] This system is designed to reduce the workload of nurses and ensure prompt and appropriate care for patients. The introduction of an emotion engine enables advanced responses that take into account the emotional state of the patient, resulting in the provision of higher quality services.

[2163] Example 2

[2164] 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."

[2165] When patients face an emergency situation in the hospital, or when they have everyday questions, it is difficult to get a quick and accurate answer. Another problem is that the workload of nurses increases, making it difficult to respond quickly. In particular, there is a lack of response that takes into account the emotional state of patients, and psychological care for patients is not being provided adequately. This can lead to a decrease in patient satisfaction and a sense of security.

[2166] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2167] In this invention, the server includes a terminal that transmits the request and emotional state when the patient operates the nurse call button, a server that receives the request and emotional state, records it in a database, and begins analysis, a generative AI model that analyzes the request content and emotional state received from the server and generates and transmits an automatic response, a terminal that displays the automatic response generated by the generative AI model to the patient, triage means that determines the urgency based on the request content, the patient's vital signs, and the patient's emotional state and sends an emergency notification as necessary, a server that receives the emergency notification from the triage means and sends the notification to the nurse's tablet device, means for sending the notification to the nurse's tablet device, and video call means that enables remote communication between the patient and the nurse. This enables a quick and accurate response to the patient's request and realizes a comprehensive response that also includes psychological care for the patient.

[2168] A "terminal" is a device that allows a patient to operate a nurse call button and has the function of transmitting requests and emotional states.

[2169] The "server" is a central control unit that receives requests and emotional states sent from the terminals, records them in a database and initiates the analysis.

[2170] A "generative AI model" is an artificial intelligence model that analyzes the request content and emotional state received from the server and generates and sends an automatic response.

[2171] The "triage method" is a system that determines the level of urgency based on the request content, the patient's vital signs, and their emotional state, and has the ability to send emergency notifications if necessary.

[2172] "Vital information" refers to key physiological data related to maintaining a patient's life, such as blood pressure, heart rate, and body temperature.

[2173] An "emergency notification" is alert information that is sent based on the level of urgency determined by the triage means and prompts nurses to take prompt action.

[2174] "Remote communication" refers to a means for patients and nurses to communicate remotely, including systems such as video calls.

[2175] "Emotional state" is information that indicates the psychological state of the patient analyzed by the emotion engine, and includes anxiety, relief, excitement, etc.

[2176] The present invention utilizes a generative AI model and an emotion engine to improve the efficiency of nurse call systems and the quality of patient care. The system of the present invention is configured as follows.

[2177] System Components

[2178] Nurse call button and terminal

[2179] The terminal is a tablet device that allows patients to operate the nurse call button. This terminal has the function of transmitting requests and emotional states. It also has an emotion engine that analyzes the patient's emotional state.

[2180] server

[2181] The server receives requests and emotional states sent from the devices, records them in a database, and then analyzes the request content and emotional state and requests processing from the generative AI model.

[2182] Generative AI Models

[2183] The generative AI model analyzes the request content and emotional state received from the server and generates an automatic response. For example, the model uses natural language processing technology to generate an appropriate response such as "The next medicine time is 2:00 PM" in response to a request such as "When is the next medicine time?"

[2184] Triage Measures

[2185] The triage system determines the level of urgency based on the request, the patient's vital signs, and their emotional state. If the urgency is high, the system sends an emergency notification to the nurse's tablet.

[2186] Remote Communication

[2187] To realize remote communication between patients and nurses, the video call function of the device is used. A video call request is sent from the device to a server, which then relays the request to the nurse's tablet device, and the video call begins.

[2188] Specific examples

[2189] Automated responses to general questions

[2190] 1. User (patient): Presses the nurse call button and asks, "When is my next medication due?"

[2191] 2. Terminal: Sends the question and the emotional state determined by the emotion engine to the server.

[2192] 3. Server: Sends the request to the AI ​​model for processing and obtains the answer.

[2193] 4. Generative AI model: Generates the answer, "The next medication time is at 2:00 PM."

[2194] 5. Server: Sends the answer to the patient's device.

[2195] 6. Terminal: Displays the answers to the patient.

[2196] Emergency response

[2197] 1. User (patient): Presses the nurse call button and sends a message saying, "I suddenly have chest pain."

[2198] 2. Terminal: Sends the request content and the emotional state determined by the emotion engine to the server.

[2199] 3. Server: Determines the urgency of the request by integrating the request content, vital signs, and emotional state.

[2200] 4. Generative AI model: Calculates a high urgency score and notifies the server.

[2201] 5. Server: Sends emergency notifications to the nurses' tablets.

[2202] 6. Terminal (Nurse): Receives emergency notifications and provides immediate on-site intervention.

[2203] Prompt Sentence Examples

[2204] "When is my next dose?"

[2205] "I suddenly had a pain in my chest"

[2206] Using the above components and processes, the system of the present invention responds quickly and appropriately to patient requests, reducing the workload of nurses while providing comprehensive care, including psychological care for patients.

[2207] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2208] Step 1:

[2209] User (patient): Presses the nurse call button to input a request. For example, the user might ask, "When is my next medication due?" This input is the starting point for the entire system process.

[2210] Step 2:

[2211] Terminal: Collects requests entered by the patient and the corresponding emotional state (e.g., "anxiety") calculated by the emotion engine. Sends this data to the server. The input is the patient's question and emotional data, and the output is sending this data to the server.

[2212] Step 3:

[2213] Server: Receives the sent request and emotional state. Records the received data in a database and starts the analysis process. The input is the request and emotional data sent from the device, and the output is a processing request to the generative AI model.

[2214] Step 4:

[2215] Generative AI model (in the server): Analyzes the request content and emotional state received from the server. Generates an automatic response using natural language processing technology. The input is the request and emotional data sent from the server, and the output is the generated answer (e.g., "The next medication time is 2 p.m.").

[2216] Step 5:

[2217] Server: Receives the answers generated by the generative AI model and sends them to the patient's tablet device. The input is the answer data from the generative AI model, and the output is the sending of the answer data to the device.

[2218] Step 6:

[2219] Terminal: Receives the answer sent from the server and displays it on the screen. The patient confirms it. The input is the answer data from the server, and the output is the answer displayed on the screen.

[2220] Step 7:

[2221] User (Patient): If they have any further questions or concerns, they press the nurse call button again to enter their request. This cycle provides continuous support.

[2222] Triage

[2223] Step 1:

[2224] User (patient): Presses the nurse call button and inputs a request saying, "I suddenly have chest pain." This is an emergency request.

[2225] Step 2:

[2226] Terminal: Collects requests and emotional states (e.g., "fear") from the emotion engine and sends them to the server. The input is the patient's urgent request and emotional data, and the output is the data sent to the server.

[2227] Step 3:

[2228] Server: Receives emergency requests and emotional states, and retrieves and integrates the patient's vital information from the database. The input is data from the device and vital information from the database, and the output is the integrated data.

[2229] Step 4:

[2230] Generative AI model (on the server): Analyzes the integrated data and calculates the urgency score. The input is the integrated request, emotional state, and vital information, and the output is the urgency score.

[2231] Step 5:

[2232] Server: If the urgency score exceeds the threshold, it sends an emergency notification to the nurse's tablet. The input is the urgency score, and the output is the emergency notification to the nurse's device.

[2233] Step 6:

[2234] Terminal (nurse): Receives emergency notification, checks detailed information, and immediately prepares to go to the patient's room. The input is the emergency notification, and the output is the nurse's actions.

[2235] Remote Communication

[2236] Step 1:

[2237] User (patient): Sends a video call request from a tablet device. The input is a video call request.

[2238] Step 2:

[2239] Terminal: Sends a video call request and the emotional state (e.g., "anxiety") generated by the emotion engine to the server. The input is the video call request and emotion data, and the output is the data sent to the server.

[2240] Step 3:

[2241] Server: Relays video call requests to the nurse's tablet. The input is the video call request from the device, and the output is the relayed data to the nurse's device.

[2242] Step 4:

[2243] Terminal (nurse): Receives and responds to video call requests. The input is a video call request, and the output is the start of a video call.

[2244] Step 5:

[2245] User (patient): A video call is initiated with a nurse, describing the current state. The input is the initiation of the video call, and the output is the patient description.

[2246] Step 6:

[2247] Terminal (nurse): Checks the patient's condition via video call and provides instructions and advice as needed. The input is the patient's explanation, and the output is the nurse's instructions and advice.

[2248] (Application example 2)

[2249] 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."

[2250] Conventional nurse call systems have difficulty responding quickly and appropriately to requests from patients, placing a heavy burden on nurses. They also struggle to take into account the patient's emotional state, which can lead to poor communication quality. Similarly, in brick-and-mortar stores, it's difficult to respond quickly and appropriately to customer requests, often resulting in poor customer satisfaction.

[2251] 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 receiving and processing requests operated by patients and customers, generation AI model means for analyzing the request content and emotional state and generating an automatic response, means for displaying the generated automatic response and realizing remote communication, and triage means. This enables quick and appropriate responses to requests from patients and customers, reduces the burden on nurses and staff, and improves patient and customer satisfaction.

[2252] A "patient" is a person who receives treatment or care at a medical institution or hospital.

[2253] A "nurse call button" is an interface device that patients use to make requests or contact nurses in an emergency.

[2254] A "terminal" is an electronic device used to send and receive requests at a medical institution or physical store.

[2255] A "server" is a device that provides the computing resources to receive and analyze requests, and generate and send automated responses.

[2256] A "generative AI model" is a system equipped with artificial intelligence technology that analyzes the request content and emotional state and automatically generates an appropriate response.

[2257] An "automated response" is an answer or response automatically provided in response to a request by a generative AI model.

[2258] "Triage measures" is a function that determines the urgency of a request based on its content and emotional state, and sends an emergency notification if necessary.

[2259] "Remote communication" is a means by which people in distant locations communicate with each other via electronic devices.

[2260] "Video calling means" is a function that enables real-time communication by sending and receiving audio and video through a terminal.

[2261] An "emergency notification" is a notification message sent to nurses and staff when a high level of urgency is determined.

[2262] A "customer support button" is an interface device that a customer uses to request support within a store.

[2263] The "urgency score" is a numerical assessment of the urgency calculated based on the request content, emotional state, vital information, etc.

[2264] This invention utilizes generative AI models and emotion engines to improve the efficiency and quality of responses in nurse call systems and brick-and-mortar customer support systems.

[2265] System configuration

[2266] 1. Nurse call button and customer support button and terminal

[2267] The terminal is an electronic device used by patients and customers in medical institutions and brick-and-mortar stores, and displays a nurse call button or customer support button on the touch interface. When a patient or customer presses the button, a request is sent. The terminal also has an emotion engine for recognizing emotions.

[2268] 2. Server

[2269] The server receives nurse call and customer support requests, records them in a database, analyzes the request content and emotional state, requests a generative AI model to process them, records the generated automated response, and sends it back to the device.

[2270] 3. Generative AI Models

[2271] The generative AI model analyzes the request and the patient's emotional state and automatically generates a response. For example, in response to a patient's request, "When is my medicine due?", the model might respond, "The next medicine is due at 2 p.m."

[2272] 4. Triage Measures

[2273] The triage system determines the level of urgency based on the content of nurse call and customer support requests, the patient's vital signs, and the customer's emotional state. If the level of urgency is high, an emergency notification is sent to the staff member's tablet device.

[2274] 5. Remote communication

[2275] The remote communication function allows video calls between patients / customers and nurses / staff via terminals. This function is realized by communication between the server and terminals.

[2276] What the program does

[2277] The server performs the following process.

[2278] 1. Sentiment analysis:

[2279] Send the patient or customer request text to an emotion engine API (e.g., EmotionAPI) to analyze the emotional state.

[2280] 2. Response generation:

[2281] Have a generative AI model API (e.g., AIModelAPI) generate an appropriate response using the request text and the analyzed emotional state.

[2282] 3. Staff Notification:

[2283] The level of urgency is determined based on the emotional state and the generated response, and if the level of urgency is high, an emergency notification is sent to a nurse or staff member via a triage means.

[2284] Specific examples

[2285] Example 1: Common patient questions

[2286] Patient: "When is my next dose?"

[2287] Terminal: Sends questions and emotional states to the server.

[2288] Server: Sends the request to the generative AI model and generates an answer such as "The next medicine time is at 2:00 p.m."

[2289] Terminal: Displays the generated answers to the patient.

[2290] Example 2: Urgent customer request

[2291] Customer: "What items are in stock?"

[2292] Terminal: Sends questions and emotional states to the server.

[2293] Server: Sends the request content to the generative AI model and generates a response.

[2294] High stress levels are identified using the emotion engine.

[2295] Server: Sends emergency notifications to staff.

[2296] Terminal: Display the answer to the customer.

[2297] Prompt Sentence Examples

[2298] "What products are in stock?"

[2299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2300] Step 1:

[2301] The patient or customer (user) operates the nurse call button or customer support button on the terminal. They input the request details as text. This operation causes the terminal to send the request details and the emotional state analyzed by the emotion engine to the server. The input is the request text and emotional data, and the output is data sent to the server.

[2302] Step 2:

[2303] The server stores the received request content and emotional state. Then, it converts the request content and emotional state into JSON format to send to the generative AI model. The input is the request text and emotional data, and the output is the input data to the generative AI model.

[2304] Step 3:

[2305] The generative AI model receives the request content and emotional state from the server, performs text analysis, and generates an appropriate response based on the analyzed results. The input is the request text and emotional data, and the output is the response text.

[2306] Step 4:

[2307] The server analyzes the response text received from the generative AI model and, if necessary, determines the level of urgency using triage methods. If the level of urgency is determined to be high, an emergency notification is sent to the terminals of staff and nurses. The input is the response text and emotion data, and the output is the emergency notification data or response data.

[2308] Step 5:

[2309] The terminal displays the response text received from the server to the user. If the urgency is high, a notification by the triage means is also displayed. The input is the response text from the server, and the output is the display to the user.

[2310] Step 6:

[2311] The nurse or staff member (user) who receives the emergency notification checks the content of the notification and takes on-site action as necessary. This process ensures a prompt response to the user. The input is the emergency notification data, and the output is the on-site response action.

[2312] 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.

[2313] 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.

[2314] 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.

[2315] 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.

[2316] 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.

[2317] 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.

[2318] 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).

[2319] 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.

[2320] 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."

[2321] 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.

[2322] 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).

[2323] 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.

[2324] 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.

[2325] 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.

[2326] 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.

[2327] 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.

[2328] 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.

[2329] 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.

[2330] 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.

[2331] 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.

[2332] 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.

[2333] The following is further disclosed regarding the above embodiment.

[2334] (Claim 1)

[2335] a terminal that transmits a request when a patient operates a nurse call button;

[2336] a server that receives the request and records it in a database;

[2337] a generative AI model that analyzes the request content received from the server and generates and transmits an automatic response;

[2338] a terminal that displays the automated response generated by the generative AI model to the patient;

[2339] a triage means for determining the degree of urgency based on the request content and the patient's vital signs, and issuing...

Claims

1. a terminal that transmits a request when a patient operates a nurse call button; a server that receives the request and records it in a database; a generative AI model that analyzes the request content received from the server and generates and transmits an automatic response; a terminal that displays the automated response generated by the generative AI model to the patient; a triage means for determining the degree of urgency based on the request content and the patient's vital signs, and issuing an emergency notification as necessary; a server that receives an emergency notification from the triage means and sends the notification to a tablet terminal of a nurse; a means for sending a notification to the tablet terminal of the nurse; The system includes a video call means for enabling remote communication between the patient and the nurse.

2. The system according to claim 1 , wherein the server calculates an urgency score by integrating the request content and the vital information, and sends a notification to a nurse when the urgency score exceeds a threshold.

3. The system of claim 1, wherein the terminal is equipped with a generative AI model for generating an automatic response in accordance with the patient's request, and the generative AI model analyzes the request content and generates an appropriate response.

Images