System

Abstract

A system is provided.SOLUTION: The system includes terminals for inputting questions by patients with cancer and their families, a server for receiving the questions transmitted from the terminals and analyzing the questions by using a natural language process, a generation AI for generating answers to the analyzed questions based on the latest research and guidelines, and a means for transmitting and displaying the generated answers to the terminals.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] Cancer patients and their families often have many anxieties and questions about treatment options, side effects, prognosis, and more. In these situations, a lack of appropriate information and support not only makes necessary decision-making difficult, but also increases the mental burden. In the current healthcare system, direct contact with healthcare professionals is often difficult due to time and location constraints, making it difficult to receive ongoing support. Furthermore, while the reliability and timeliness of information are important, there are insufficient means in place to ensure this. The present invention aims to address these issues. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a terminal for cancer patients and their families to input questions, a server that receives the questions sent from the terminal and analyzes the questions using natural language processing, a generation AI that generates answers to the analyzed questions based on the latest research and guidelines, and means for transmitting the generated answers to the terminal and displaying them. The system also includes means for receiving a user's online consultation request and coordinating the schedules of specialists and nurses to determine the date and time of the online consultation, means for notifying the terminal of the determined date and time and receiving the user's confirmation, and means for notifying the specialists and nurses of the confirmation results and re-notifying the terminal of details of the online consultation. The system also includes means for converting the user's natural language questions into an appropriate format and means for transmitting the converted questions to the server, making it easy to input questions and enabling smooth information provision.

[0006] A "terminal" is a physical or virtual device through which a user enters questions and sends and receives information to the system.

[0007] A "server" is a centralized computer system that analyzes questions received from terminals and performs appropriate processing.

[0008] "Natural language processing (NLP)" is a technical field that uses computers to understand, analyze, and generate human language.

[0009] "Question analysis" is the process of identifying the subject and intent of an incoming question.

[0010] "Generative AI" is an artificial intelligence technology that automatically generates answers to analyzed questions based on the latest research and guidelines.

[0011] "Answer generation" is the process by which AI constructs an answer to provide appropriate information to a user's question.

[0012] "Online consultation" is a system that allows users to directly interact with specialist doctors and nurses via the Internet to obtain medical advice and information.

[0013] "Schedule adjustment" refers to the process of checking the schedules of specialists and nurses and deciding on dates and times when online consultations can be conducted.

[0014] "Notification" is the act of the system sending information or instructions to a user or medical professional.

[0015] "Confirmation" is the process by which a user responds to information and suggestions provided by the system and indicates their intention.

[0016] A "natural language question" is a question that a user enters into the system using everyday language.

[0017] "Reforming" is the process by which the user's input is reconstructed into a form that can be processed by the system. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] overview

[0040] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is composed mainly of terminals, servers, and generation AI, provides answers to users' questions based on the latest research and guidelines, and also allows online consultations with specialized doctors and nurses as needed.

[0041] System Configuration

[0042] Terminal: A device on which users can input questions and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[0043] Server: Receives questions sent from the device, analyzes the questions, and generates answers in cooperation with the generation AI. It is also responsible for scheduling and notifying online consultations.

[0044] Generative AI: Based on analyzed questions received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[0045] Program processing

[0046] 1. Enter and submit your question

[0047] The user types their question (e.g., "What are the side effects of chemotherapy?") into the terminal.

[0048] The terminal converts the entered question into an appropriate format and sends it to the server.

[0049] 2. Receiving and analyzing questions

[0050] The server receives the query sent from the terminal.

[0051] The server uses natural language processing (NLP) techniques to analyze the question and identify the subject matter (e.g., "chemotherapy" and "side effects").

[0052] 3. Generate answers

[0053] The server sends the parsed question to the generation AI.

[0054] The generative AI generates answers to questions based on the latest research databases and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.") and sends them to a server.

[0055] 4. Providing answers

[0056] The server sends the generated response to the terminal.

[0057] The terminal displays the answer to the user.

[0058] 5. Request an online consultation

[0059] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[0060] The terminal converts the request into an appropriate format and sends it to the server.

[0061] 6. Scheduling online consultations

[0062] The server accesses a database of specialist and nurse schedules to select possible dates and times.

[0063] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[0064] 7. Confirmation and Final Notice

[0065] The user confirms the date and time of the online consultation from their device and approves it.

[0066] The terminal sends the confirmation results to the server, which then notifies the specialist or nurse.

[0067] The server sends a final confirmation to the terminal and notifies the user again.

[0068] Specific examples

[0069] Basic Questions and Answers

[0070] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0071] 2. The device converts the question into a format and sends it to the server.

[0072] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[0073] 4. The generative AI generates answers based on the latest side effects information for chemotherapy.

[0074] 5. The server sends the generated answer to the terminal and displays it to the user.

[0075] Request an online consultation

[0076] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[0077] 2. The device converts the request into a format and sends it to the server.

[0078] 3. The server checks the specialist's schedule and selects an available date and time.

[0079] 4. The server sends the selection results to the terminal and notifies the user.

[0080] 5. Once the user confirms and approves the date and time, it is sent from the device to the server.

[0081] 6. The server notifies the specialist of the results of the check and resends the final details to the terminal.

[0082] Through this series of processes, we can provide support to cancer patients and their families so that they can approach treatment with peace of mind.

[0083] The processing flow will be explained below.

[0084] Basic question and answer process flow

[0085] Step 1:

[0086] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0087] Step 2:

[0088] The terminal converts the entered question into text format and sends it to the server.

[0089] Step 3:

[0090] The server receives a query from the terminal.

[0091] Step 4:

[0092] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[0093] Step 5:

[0094] Based on the analysis results, the server generates a request to the generation AI.

[0095] Step 6:

[0096] The generative AI references the latest research databases and guidelines to generate appropriate answers to questions (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.").

[0097] Step 7:

[0098] The generation AI sends the generated answer to the server.

[0099] Step 8:

[0100] The server sends the generated response to the terminal.

[0101] Step 9:

[0102] The terminal displays the received response to the user.

[0103] Online consultation request processing flow

[0104] Step 1:

[0105] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[0106] Step 2:

[0107] The terminal converts the input request into text format and sends it to the server.

[0108] Step 3:

[0109] The server receives a request for online consultation from the terminal.

[0110] Step 4:

[0111] The server accesses a database of specialist and nurse schedules to check available time slots.

[0112] Step 5:

[0113] The server selects candidate dates and times and determines the date and time for the online consultation.

[0114] Step 6:

[0115] The server notifies the terminal of the determined online consultation date and time.

[0116] Step 7:

[0117] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[0118] Step 8:

[0119] The user confirms the date and time of the online consultation through the terminal and approves it.

[0120] Step 9:

[0121] The terminal transmits the user's confirmation result to the server.

[0122] Step 10:

[0123] The server notifies the specialist or nurse of the approval result.

[0124] Step 11:

[0125] The server sends a final confirmation to the terminal and notifies the user again.

[0126] In this way, the system as a whole executes each processing step in detail to facilitate two-way communication between the user and the medical professional.

[0127] Example 1

[0128] 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."

[0129] There is a need for an environment where cancer patients and their families can quickly and appropriately obtain reliable medical information. However, currently, providing appropriate information requires referencing numerous specialized materials, which places a significant burden on patients. Furthermore, there is a lack of efficient scheduling methods for patients who wish to consult online with specialists or nurses. To solve these problems, it is necessary to use advanced technology to automate the information and consultation procedures and provide them quickly and accurately.

[0130] 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.

[0131] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal and analyzing the question using natural language processing, artificial intelligence for generating an answer to the analyzed question based on the latest research and guidelines, means for transmitting the generated answer to the terminal and displaying it, means for receiving the user's request for online consultation and adjusting the specialist's schedule to determine the date and time of the online consultation, means for notifying the terminal of the determined date and time and receiving confirmation from the user, and means for notifying the specialist of the confirmation result and re-notifying the terminal of details of the online consultation. This enables cancer patients and their families to quickly and accurately obtain the medical information they need and to have efficient online consultations with specialists and nurses.

[0132] "Users" refer to cancer patients and their families who use the system.

[0133] "Device" refers to the device used by a user to enter questions and receive responses and notifications from the system, such as a smartphone, tablet, or PC.

[0134] The "server" refers to a computer system that receives and analyzes questions sent from the device, works with the generation AI to generate answers, and is also responsible for scheduling and notifying online consultations.

[0135] "Natural language processing" refers to computer techniques for analyzing natural language questions entered by users to identify their subject matter and intent. Examples include tokenization, part-of-speech tagging, and named entity recognition.

[0136] "Artificial intelligence" refers to technology that generates answers based on the latest research and guidelines, based on analyzed questions received from a server. In a broad sense, it includes machine learning and deep learning.

[0137] "Online consultation" refers to a consultation a user has with a specialist or nurse via the internet, including requests, scheduling, and notifications.

[0138] "Generative AI" is a form of artificial intelligence, specifically referring to algorithms and models that automatically generate appropriate answers to user questions.

[0139] "Schedule adjustment" refers to the process of receiving a user's request for online consultation and determining the date and time of the consultation according to the availability of the expert.

[0140] "Notification" refers to the system's act of conveying information or confirmation to users or experts, such as informing them of the date and time of an online consultation or the content of the response.

[0141] overview

[0142] This invention is an online consulting system that enables cancer patients and their families to quickly and appropriately obtain reliable medical information. The system uses terminals, a server, and a generative AI to automatically generate answers to users' questions and support online consultations with specialist doctors and nurses.

[0143] System Configuration

[0144] Terminal

[0145] This is a device that allows users to input questions and receive answers and notifications from the system. A variety of devices, including smartphones, tablets, and PCs, can be used as terminals. The system can be accessed through a dedicated application or a web browser.

[0146] server

[0147] The server has the following main functions:

[0148] 1. Receiving and parsing questions: Receive questions sent from the device and parse them using natural language processing (NLP) techniques. NLP libraries used include NLTK and spaCy.

[0149] 2. Collaboration with Generative AI: The analyzed question is sent to Generative AI, which then generates an appropriate answer. Generative AI then refers to the latest research databases and guidelines (e.g., PubMed, NCCN guidelines).

[0150] 3. Online consultation scheduling: Upon receiving a user request for an online consultation, the system accesses the specialist or nurse's schedule database (e.g., Google Calendar API) to determine the consultation date and time, and notifies the user or specialist.

[0151] Generation AI

[0152] Generative AI automatically generates answers based on the latest research and guidelines, based on analyzed questions received from the server, using trained machine learning models to extract information from relevant databases to create answers.

[0153] Specific operation example

[0154] User-entered questions

[0155] The user opens a dedicated application or web browser and enters their question (e.g., "What are the side effects of chemotherapy?"). The entered question is converted into an appropriate format (e.g., JSON format) and sent to the server.

[0156] Server parsing of the question

[0157] The server receives the question sent from the device and analyzes it using NLP technology to identify the topic of the question (e.g., "chemotherapy" or "side effects").

[0158] Generative AI generates answers

[0159] The server sends the analyzed question to the generation AI, which generates an appropriate answer based on the latest research database and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections."). The generated answer is then sent back to the server.

[0160] Show Answers

[0161] The server sends the generated answer to the terminal, which displays the answer to the user and notifies them using a notification function if necessary.

[0162] Request an online consultation

[0163] When a user wishes to have an online consultation with a specialist, they input a request from their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist.") The request is converted into an appropriate format and sent to the server.

[0164] Server-based scheduling

[0165] The server accesses the schedule database of specialists and nurses to select available dates and times. The selection results are sent to the terminal and the user is asked to confirm. Once the user confirms and agrees with the date and time, the confirmation results are sent to the server, which notifies the specialist and resends the final schedule to the terminal.

[0166] In this way, cancer patients and their families can quickly and accurately obtain the medical information they need, enabling efficient online consultations.

[0167] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0168] Step 1:

[0169] User-entered questions

[0170] Users open a dedicated application or web browser and enter their question (e.g., "What are the side effects of chemotherapy?").

[0171] The terminal converts the entered question into an appropriate format (e.g., JSON format).

[0172] Input: A text question entered by the user

[0173] Data processing: Convert text data into JSON format

[0174] Output: Converted JSON format question data

[0175] The device sends the generated question data in JSON format to the server.

[0176] Step 2:

[0177] The server receives and analyzes the query

[0178] The server receives the query sent from the terminal.

[0179] Input: JSON-formatted question data sent from the terminal

[0180] Data processing: JSON data analysis, data consistency check

[0181] Output: Parsed question data

[0182] The server uses natural language processing (NLP) techniques to analyze the question.

[0183] NLP libraries used include NLTK and spaCy.

[0184] Input: Question data in JSON format

[0185] Data operations: tokenization, part-of-speech tagging, named entity recognition

[0186] Output: The subject and keywords of the parsed question (e.g., "chemotherapy" and "side effects")

[0187] Step 3:

[0188] Generative AI generates answers

[0189] The server sends the parsed question to the generation AI.

[0190] Input: Parsed question data

[0191] Data processing: Converting data into a format that can be understood by generative AI

[0192] Output: Data sent to the generative AI

[0193] Generative AI generates appropriate answers based on the latest research databases and guidelines.

[0194] Databases used include PubMed and NCCN guidelines.

[0195] Input: Parsed question data

[0196] Data Computing: Find the latest research information for your questions and generate answers, including citations

[0197] Output: Generated answer (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection.")

[0198] The generated answer is sent back to the server.

[0199] Step 4:

[0200] Server provides answer

[0201] The server sends the generated response to the terminal.

[0202] Input: Answer data sent from the generation AI

[0203] Data processing: Convert response data into JSON format

[0204] Output: Converted JSON format response data

[0205] The terminal displays the answer to the user and notifies the user using a notification function if necessary.

[0206] Input: JSON format response data sent from the server

[0207] Data processing: Parsing JSON data and converting it into a format suitable for the user interface

[0208] Output: The answer displayed in the user interface

[0209] Step 5:

[0210] User requests for online consultation

[0211] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[0212] The device converts the request into an appropriate format (e.g., JSON).

[0213] Input: A textual request entered by the user.

[0214] Data processing: Convert text data into JSON format

[0215] Output: The converted JSON format request data

[0216] The terminal sends the generated request data in JSON format to the server.

[0217] Step 6:

[0218] Server-based scheduling of online consultations

[0219] The server accesses a database of specialist and nurse schedules to select available dates and times.

[0220] The schedule database used is the Google Calendar API.

[0221] Input: Request data sent from the terminal

[0222] Data calculation: Access to schedule database, search and obtain available time slots

[0223] Output: A list of candidate dates and times

[0224] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[0225] Input: A list of possible dates and times

[0226] Data Processing: Generate a confirmation request

[0227] Output: Verification request sent to the terminal

[0228] Step 7:

[0229] User confirmation and final notification

[0230] The user confirms the date and time of the online consultation from their device and approves it.

[0231] Input: Verification request sent by the server

[0232] Data manipulation: Get user selection

[0233] Output: User verification data

[0234] The terminal transmits the confirmation result to the server.

[0235] Input: User verification data

[0236] Data processing: Check data integrity and convert to JSON format

[0237] Output: Converted JSON format confirmation data

[0238] The server notifies the specialist or nurse of the results of the confirmation and confirms the final schedule.

[0239] Input: Verification data sent from the terminal

[0240] Data processing: Generate data to inform experts

[0241] Output: Final schedule sent to the expert

[0242] The server transmits the final schedule information to the terminal and notifies the user again.

[0243] Input: Final schedule data

[0244] Data processing: Generate notification data for users

[0245] Output: Final schedule notification sent to device

[0246] (Application example 1)

[0247] 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."

[0248] Cancer patients and their families often find it difficult to obtain reliable medical information quickly and appropriately. Even when they need to consult with a specialist doctor or nurse, scheduling an appointment is often difficult. Furthermore, it is necessary to establish a method for providing similar support in brick-and-mortar stores.

[0249] 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.

[0250] In this invention, the server includes a terminal for cancer patients and their families to input questions, a means for receiving questions sent from the terminal and analyzing the questions using natural language processing, a generation AI means for generating answers to the analyzed questions based on the latest research and guidelines, a means for sending the generated answers to the terminal and displaying them, a means for accepting requests from users seeking specialist consultations, a means for checking the schedules of specialists and nurses and arranging consultation dates and times, a means for notifying the terminal of the arranged date and time, receiving confirmation from the user, and again notifying the specialist or nurse, a means for installing a terminal for accepting questions in a physical store, and a means for appropriately processing questions and requests from the terminal installed in the physical store. This allows patients and their families to instantly obtain reliable medical information and smoothly conduct online consultations with specialists. Similar services can also be provided in physical stores to improve convenience.

[0251] "Cancer patients and their families" refers to patients who have currently been diagnosed with cancer and their families who need information and care to support them.

[0252] "Terminal" refers to a device through which a user can enter questions and receive answers and notifications from the system, including smartphones, tablets, and PCs.

[0253] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0254] A "server" refers to a device that receives questions sent from a terminal, analyzes the questions using natural language processing, and works with a generation AI to generate answers.

[0255] "Generative AI" refers to artificial intelligence technology that automatically generates appropriate answers based on analyzed questions, citing the latest research and guidelines.

[0256] "Display means" refers to a method or technology for transmitting the generated answer to a terminal and displaying it in a format that is easy for the user to view.

[0257] The "means for accepting a request" refers to a method or device for allowing a user who desires professional consultation to input a request into the system.

[0258] "Means for checking schedules and arranging consultation dates and times" refers to methods and technologies for managing the schedule data of specialists and nurses, and selecting and arranging appropriate dates and times for online consultations.

[0259] "Means for receiving confirmation and notifying again" refers to the method or technology for receiving final confirmation from the user and notifying the specialist or nurse of the confirmation content.

[0260] "Store-based terminal" refers to a device located within a physical store that a customer uses to input a question or request a consultation with a specialist.

[0261] "Means for appropriately processing questions and requests" refers to the methods and technologies for receiving user input from terminals installed in physical stores and analyzing and processing it on the server.

[0262] "Medical information" refers to reliable information in the medical field based on the latest research data and guidelines.

[0263] A "specialist" refers to a medical professional with advanced knowledge and experience in a particular medical field.

[0264] "Online consultation" refers to real-time health consultation with a specialist doctor or nurse via the Internet.

[0265] This invention is a system that allows cancer patients and their families to quickly and appropriately obtain reliable medical information and smoothly conduct online consultations with specialized doctors and nurses. Similar services can also be provided in physical stores. A specific embodiment of this system is described below.

[0266] System Configuration

[0267] 1. Terminal

[0268] A device that allows users to input questions and receive answers from generative AI. Specifically, it includes smartphones, tablets, PCs, and kiosks installed in physical stores.

[0269] 2. Server

[0270] The server receives questions sent from the device and analyzes them using natural language processing, which then sends the analyzed questions to a generative AI that generates answers based on the latest research and guidelines.

[0271] 3. Generation AI

[0272] The generative AI automatically generates appropriate answers based on the analyzed questions received from the server, citing the latest research data and guidelines, using natural language generation models (e.g., the GPT series).

[0273] Hardware and Software

[0274] Natural Language Processing (NLP) toolkits: We use NLP tools such as spaCy and NLTK to analyze questions, which helps us identify the subject of the question and access the appropriate information.

[0275] Generative AI models: Use natural language generation models like the OpenAI GPT series to generate answers based on the latest research data.

[0276] RESTful API: To ensure that each component of the entire system works together, data is communicated between the server and the terminal via a RESTful API using Flask or Django REST framework.

[0277] Explanation with concrete examples

[0278] Here is a specific example of a "health consultation kiosk" installed in a physical drugstore. When a customer using this kiosk asks, "Which supplements are effective for diabetes?", the following actions are taken:

[0279] 1. The user enters a question into the kiosk terminal's touch panel.

[0280] 2. The terminal converts the entered question into an appropriate format and sends it to the server.

[0281] 3. The server uses natural language processing to analyze the question and identify keywords such as "diabetes" and "supplements."

[0282] 4. Based on the analysis results, the AI ​​generates an answer citing the latest research data and guidelines. In this case, the generated answer would be "Vitamin D and magnesium are effective in managing diabetes."

[0283] 5. The server sends the generated answer to the terminal and displays it to the user.

[0284] Examples of prompt statements

[0285] Below are some specific examples of prompt sentences to input into the generative AI model.

[0286] Prompt: "Which supplements are effective for diabetes?"

[0287] Generative AI model: “Certain vitamins and minerals have been shown to be effective in managing diabetes. Examples include vitamin D and magnesium.”

[0288] In this way, users can instantly obtain reliable medical information and smoothly consult with specialists online. Similar services can also be provided in physical stores, improving convenience.

[0289] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0290] Step 1:

[0291] The user enters a question into the device's input screen, for example, "Which supplements are effective for diabetes?" The entered question is converted into an appropriate format for subsequent processing.

[0292] Step 2:

[0293] The device converts the question into a format and sends it to the server. This process uses an HTTP request, and the question is sent to the server in JSON format.

[0294] Step 3:

[0295] The server receives the question sent from the terminal. This input is a natural language question entered by the user. The received question is analyzed using a natural language processing (NLP) engine. Specifically, keywords (e.g., "diabetes" and "supplements") are extracted.

[0296] Step 4:

[0297] The server sends the analyzed results to a generative AI model, which uses this input to refer to the latest research data and guidelines to generate an appropriate answer to the question. For example, it may generate an answer such as, "Vitamin D and magnesium are effective in managing diabetes."

[0298] Step 5:

[0299] The server then sends the answer received from the generative AI model back to the device. At this stage, the generated answer is returned from the server to the device in JSON format.

[0300] Step 6:

[0301] The device displays the answer received from the server to the user. Specifically, the device screen displays the message, "Vitamin D and magnesium are effective in managing diabetes."

[0302] Step 7:

[0303] If the user wishes to further consult with a specialist online, he or she inputs a request from the terminal, for example, "I would like to speak to a specialist." This request is also sent to the server.

[0304] Step 8:

[0305] The server queries the schedule data of specialists and nurses to determine possible dates and times for online consultations. This coordination involves database access.

[0306] Step 9:

[0307] The server notifies the terminal of the arranged date and time of the online consultation, and this information is sent to the terminal in a format that can be confirmed by the user.

[0308] Step 10:

[0309] If the user confirms the presented date and time and approves it, the confirmation result is transmitted from the terminal to the server.

[0310] Step 11:

[0311] The server notifies the specialist or nurse of the user's confirmation results, including the arranged consultation date and time.

[0312] Step 12:

[0313] The server retransmits the final details of the online consultation to the terminal and prompts the user for final confirmation, after which the online consultation is officially scheduled.

[0314] The above are the specific processing steps of the system according to the present invention, which allows patients and their families to quickly obtain reliable medical information and smoothly consult with specialists online.

[0315] 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.

[0316] overview

[0317] This invention combines an emotion engine with an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is centered around a terminal, server, generative AI, and emotion engine, provides answers to users' questions based on the latest research and guidelines, and allows online consultations with specialized doctors and nurses as needed. It can also recognize users' emotions and provide tailored answers and support.

[0318] System Configuration

[0319] Terminal: A device on which users can input questions or requests for online consultations and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[0320] Server: Receives questions and requests sent from the device and analyzes the questions using natural language processing. It then passes the analyzed questions to a generation AI to generate answers. It also analyzes the user's emotions using an emotion engine.

[0321] Generative AI: Based on analyzed questions and requests received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[0322] Emotion Engine: Recognizes emotions from questions and requests entered by users and adjusts responses and notifications accordingly.

[0323] Program processing

[0324] 1. Enter and submit your question

[0325] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0326] The terminal converts the entered question into text format and sends it to the server.

[0327] 2. Receiving and analyzing questions

[0328] The server receives the query sent from the terminal.

[0329] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[0330] The server passes the analyzed question to the emotion engine to recognize the user's emotion.

[0331] 3. Emotional awareness and adaptation

[0332] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and tone of the question.

[0333] The server adjusts the content of the response and notification based on the results of the emotion engine.

[0334] 4. Answer Generation

[0335] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and an increased risk of infection. We understand your concerns, so please feel free to contact us.").

[0336] 5. Submitting and Viewing Your Answers

[0337] The server sends the generated response to the terminal.

[0338] The terminal displays the received response to the user.

[0339] 6. Online consultation requests and processing

[0340] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[0341] The terminal converts the request into text format and sends it to the server.

[0342] The server receives the request for online consultation and analyzes the user's urgency and emotions using an emotion engine.

[0343] The server accesses a database of specialists' and nurses' schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the request is given higher priority.

[0344] The server will notify the user of the suggested dates and times and ask for confirmation.

[0345] The user checks the date and time, and after approval, transmits it from the terminal to the server.

[0346] The server receives the confirmation and notifies the specialist or nurse.

[0347] The server sends the final details to the terminal and re-informs the user.

[0348] Specific examples

[0349] Basic Questions and Answers

[0350] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0351] 2. The device converts the question into a format and sends it to the server.

[0352] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[0353] 4. The emotion engine recognizes the emotion "anxiety" from the context of the question.

[0354] 5. The generative AI generates emotionally sensitive answers based on the latest side effects information about chemotherapy.

[0355] 6. The server sends the generated answer to the terminal and displays it to the user.

[0356] Request an online consultation

[0357] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[0358] 2. The device converts the request into a format and sends it to the server.

[0359] 3. The server receives the request and analyzes the user's urgency and emotion using the emotion engine.

[0360] 4. The server checks the specialist's schedule and prioritizes the date and time if the appointment is highly urgent.

[0361] 5. The server notifies the user of the date and time and asks for confirmation.

[0362] 6. Once the user confirms and approves the date and time, it is sent from the device to the server.

[0363] 7. The server notifies the specialist of the confirmation and resends the final details to the terminal.

[0364] This system allows cancer patients and their families to receive appropriate information and support that is sensitive to their emotions, allowing them to approach treatment with peace of mind.

[0365] The processing flow will be explained below.

[0366] Basic question and answer process flow

[0367] Step 1:

[0368] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0369] Step 2:

[0370] The terminal converts the entered question into text format and sends it to the server in the appropriate format.

[0371] Step 3:

[0372] The server receives the query sent from the terminal.

[0373] Step 4:

[0374] The server uses a natural language processing (NLP) module to analyze the received question and identify key keywords (e.g., "chemotherapy" and "side effects").

[0375] Step 5:

[0376] The server passes the analysis results to the emotion engine, which recognizes the user's emotions.

[0377] Step 6:

[0378] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and wording of the question.

[0379] Step 7:

[0380] The server receives the results of the emotion engine and includes the emotion information in the request to the generation AI.

[0381] Step 8:

[0382] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection. We understand that you are concerned, but these symptoms are common. Please let us know if there are any other concerns you have.").

[0383] Step 9:

[0384] The generation AI sends the generated answer to the server.

[0385] Step 10:

[0386] The server sends the generated response to the terminal.

[0387] Step 11:

[0388] The terminal displays the answer to the user.

[0389] Online consultation request processing flow

[0390] Step 1:

[0391] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[0392] Step 2:

[0393] The terminal converts the input request into text format and transmits it to the server in the appropriate format.

[0394] Step 3:

[0395] The server receives a request for online consultation sent from the terminal.

[0396] Step 4:

[0397] The server uses an emotion engine to recognize the emotion contained in the user's request (e.g., anxiety with high urgency).

[0398] Step 5:

[0399] The server accesses a database of specialist and nurse schedules to check available time slots.

[0400] Step 6:

[0401] Based on the analysis results of the emotion engine, the server determines the urgency of the online consultation and changes the priority of schedule adjustments as necessary.

[0402] Step 7:

[0403] The server selects candidate dates and times and determines the date and time for the online consultation.

[0404] Step 8:

[0405] The server notifies the terminal of the determined date and time of the online consultation.

[0406] Step 9:

[0407] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[0408] Step 10:

[0409] The user confirms the date and time of the online consultation through the terminal and approves it.

[0410] Step 11:

[0411] The terminal transmits the confirmation result to the server.

[0412] Step 12:

[0413] The server notifies the specialist or nurse of the confirmation results.

[0414] Step 13:

[0415] The server sends a final confirmation to the terminal and notifies the user again.

[0416] In this way, the system can provide appropriate information and support in response to users' questions and requests while taking their emotions into consideration, enabling smooth two-way communication.

[0417] Example 2

[0418] 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."

[0419] Currently, it is not easy for cancer patients and their families to obtain reliable medical information. While online consultation systems exist, they often do not provide appropriate responses that take into consideration the patient's feelings. As a result, patients often undergo treatment while feeling anxious and worried, placing a heavy psychological burden on them. Furthermore, there is a problem in that they are unable to respond appropriately to urgent consultation requests, making it difficult to fully meet the needs of patients.

[0420] 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.

[0421] In this invention, the server includes a means for receiving questions sent from a terminal and analyzing the questions using natural language processing; an automatic response generation device for generating answers to the analyzed questions based on the latest research and guidelines; and an emotion analysis device for recognizing the user's emotions and adapting the answers and notification content based on the recognized emotions. This not only enables patients and their families to obtain reliable medical information, but also enables responses that take emotions into consideration. Furthermore, since highly urgent requests can be responded to quickly and appropriately, the psychological burden on patients is reduced, allowing them to receive treatment with peace of mind.

[0422] A "terminal" is a device through which a user inputs questions or requests for online consultations and receives responses or notifications from the system.

[0423] An "information processing device" is a device that receives a question sent from a terminal and analyzes the question using natural language processing.

[0424] An "automatic response generator" is a device that generates answers to analyzed questions based on the latest research and guidelines.

[0425] An "emotion analysis device" is a device that recognizes a user's emotions and adjusts responses and notification content based on the recognized emotions.

[0426] "Online consultation request" is a request input by the user to request an online consultation with a specialist doctor or nurse.

[0427] The "schedule adjustment method" is a system that checks the schedules of specialists and nurses and determines the date and time of online consultations.

[0428] "Urgency" is an index that indicates the importance or urgency of a user's request.

[0429] "Natural language processing" is a technology for analyzing user questions and understanding important keywords and context.

[0430] A "generative AI model" is an artificial intelligence that generates appropriate answers from analyzed questions and sentiment analysis results based on the latest research and guidelines.

[0431] A "prompt" is a textual representation of a question or request that is input to a generative AI model.

[0432] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information, and also combines it with emotion analysis functions. The system is mainly composed of a terminal, an information processing device, an automatic response generation device, and an emotion analysis device, and provides users with prompt and appropriate information.

[0433] overview

[0434] The basic configuration of the invention is as follows:

[0435] 1. Terminal: A device on which users can enter questions or requests for online consultations and receive answers and notifications from the system. It can be a smartphone, tablet, or PC.

[0436] 2. Information processing device: Receives questions sent from the device and analyzes them using natural language processing (NLP), for example, using libraries such as spaCy or NLTK.

[0437] 3. Automatic response generator: Receives analyzed questions from an information processing device and uses a generative AI model to generate answers based on the latest research and guidelines. Databases such as PubMed can be used for reference.

[0438] 4. Emotion analyzer: This function analyzes the user's input and recognizes emotions (e.g., anxiety, worry). Emotion analysis is performed using IBM Watson Tone Analyzer, etc.

[0439] The main features of the system are:

[0440] 1. Enter and submit your question

[0441] Users use a terminal to enter a question in text format, such as "What are the side effects of chemotherapy?"

[0442] The terminal converts the entered question into an appropriate format and sends it to the server.

[0443] 2. Receiving and analyzing questions

[0444] The server receives the query sent from the terminal.

[0445] The server uses a natural language processing module to analyze the question and identify important keywords.

[0446] After analysis, the question data is passed to an emotion analyzer to recognize the user's emotion.

[0447] 3. Emotional awareness and adaptation

[0448] The emotion analyzer recognizes the user's emotions and returns the results to the server.

[0449] The server adjusts the response content based on the results of the emotion analysis.

[0450] 4. Answer Generation

[0451] The generative AI model uses the parsed question and sentiment analysis results to generate appropriate answers.

[0452] The generated answer is sent to the terminal via the server.

[0453] 5. View Answers

[0454] The terminal displays the received response to the user.

[0455] 6. Online consultation requests and processing

[0456] If the user wishes to have an online consultation with a specialist, they enter a request.

[0457] The device sends a request to the server, which checks the specialist's schedule and adjusts the priority according to the urgency.

[0458] The confirmed consultation date and time is notified to the user and the specialist.

[0459] Specific examples

[0460] When a user types a question such as "I'm anxious about the treatment I'm currently receiving," the device converts it into text format and sends it to the server. The server uses natural language processing to identify keywords such as "treatment" and "anxiety," and passes these to the emotion analyzer. The emotion analyzer recognizes the emotion "anxiety" and passes the results to the generative AI model. The generative AI model generates an answer based on the latest research data, such as "It's common to feel anxious about treatment. If you could tell us your story, we'll respond appropriately."

[0461] Prompt Sentence Examples

[0462] "Tell us about common side effects of chemotherapy and be mindful of any concerns users may have."

[0463] This system not only allows cancer patients and their families to obtain reliable medical information, but also provides emotionally sensitive care, allowing them to undergo treatment with peace of mind.

[0464] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0465] Step 1:

[0466] The user types a question into the terminal.

[0467] Input: The user types the question, "What are the side effects of chemotherapy?"

[0468] Action: The action of entering text into a device input field.

[0469] Output: The input text data.

[0470] Step 2:

[0471] The terminal converts the entered question into the appropriate format.

[0472] Input: The text data entered in step 1.

[0473] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[0474] Output: Formatted text data.

[0475] Step 3:

[0476] The device sends a formatted text question to the server.

[0477] Input: The formatted text data from step 2.

[0478] What it does: Sends data to a server via an HTTP request.

[0479] Output: Request data to the server.

[0480] Step 4:

[0481] The server receives the question sent from the terminal.

[0482] Input: The request data sent in step 3.

[0483] How it works: The API endpoint receives request data.

[0484] Output: The received query data.

[0485] Step 5:

[0486] The server parses the question using a natural language processing (NLP) module.

[0487] Input: The question data received in step 4.

[0488] How it works: Analyzes text using NLP techniques (e.g. spaCy) to extract important keywords.

[0489] Output: Extracted keyword data (e.g., "chemotherapy" and "side effects").

[0490] Step 6:

[0491] The server passes the analysis results to the emotion analysis device.

[0492] Input: Keyword data extracted in step 5.

[0493] What it does: Converts NLP results into JSON format and sends them to the sentiment analyzer.

[0494] Output: Request data to the sentiment analyzer.

[0495] Step 7:

[0496] The emotion analyzer recognizes the user's emotions from the context and tone of the question.

[0497] Input: The request data sent in step 6.

[0498] How it works: Identifies emotions using emotion analysis technology (e.g., IBM Watson Tone Analyzer).

[0499] Output: Recognized emotion data (e.g., "anxiety").

[0500] Step 8:

[0501] The server receives the sentiment analysis results.

[0502] Input: Emotion data obtained in step 7.

[0503] What it does: Receives emotion data and prepares it for use in adjusting responses.

[0504] Output: Emotion data ready for conditioning.

[0505] Step 9:

[0506] The server passes the analyzed question and sentiment analysis results to the generated AI model.

[0507] Input: Keyword data extracted in step 5 and sentiment data obtained in step 8.

[0508] How it works: The question and emotion data are input as prompts to the generative AI.

[0509] Output: Prompt data to the generative AI model.

[0510] Step 10:

[0511] The generative AI model generates answers by referencing the latest research databases and guidelines.

[0512] Input: Prompt data from step 9.

[0513] What it does: Consults up-to-date research databases (e.g., PubMed) and generates relevant answers.

[0514] Output: The generated response data.

[0515] Step 11:

[0516] The server sends the answer received from the generation AI to the terminal.

[0517] Input: The response data generated in step 10.

[0518] What it does: Sends data to the device via an HTTP response.

[0519] Output: Response data to the device.

[0520] Step 12:

[0521] The terminal displays the received answer to the user.

[0522] Input: The response data sent in step 11.

[0523] What it does: Displays textual responses via a GUI.

[0524] Output: The answer data displayed to the user.

[0525] Step 13:

[0526] If the user wishes to have an online consultation with a specialist, they enter a request.

[0527] Input: User types "I would like to speak to a specialist."

[0528] Action: The action of entering text into a device input field.

[0529] Output: The input request data.

[0530] Step 14:

[0531] The device converts the request into an appropriate format and sends it to the server.

[0532] Input: The request data entered in step 13.

[0533] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[0534] Output: The formatted request data.

[0535] Step 15:

[0536] The server receives the online consultation request and analyzes the urgency and emotion of the user with an emotion analyzer.

[0537] Input: The request data sent in step 14.

[0538] How it works: It uses NLP techniques and sentiment analyzers to analyze text and identify sentiment and urgency.

[0539] Output: Extracted urgency and sentiment data.

[0540] Step 16:

[0541] The server accesses a database of specialist and nurse schedules to check available time slots.

[0542] Input: Urgency data identified in Step 15.

[0543] What it does: Runs a database query to find and identify free time.

[0544] Output: Data on available time slots.

[0545] Step 17:

[0546] If the server is in a high emergency state, the date and time are set with priority.

[0547] Input: The open time slot data identified in step 16.

[0548] What it does: Prioritize and optimize dates and times based on urgency.

[0549] Output: Date and time data of the online consultation that was set.

[0550] Step 18:

[0551] The server notifies the user of the set date and time and asks for confirmation.

[0552] Input: Date and time data set in step 17.

[0553] Behavior: Generates a confirmation message and sends it to the device as an HTTP response.

[0554] Output: Acknowledgement data to the user.

[0555] Step 19:

[0556] Once the user confirms and approves the date and time, it is sent from the device to the server.

[0557] Input: Acknowledgment data sent in step 18.

[0558] Action: The user sees the notification and clicks the confirm / agree button.

[0559] Output: Confirmation and acceptance data.

[0560] Step 20:

[0561] The server notifies the specialist or nurse of the confirmation.

[0562] Input: Confirmation and acknowledgement data sent in step 19.

[0563] What it does: Generates and sends a message to notify specialists and nurses of the results of the check.

[0564] Output: Data for notifying specialists and nurses.

[0565] Step 21:

[0566] The server sends the final details to the terminal and re-informs the user.

[0567] Input: Specialist and nurse notification data sent in step 20.

[0568] Behavior: A message containing the confirmed date and time and details is generated and sent to the device as an HTTP response.

[0569] Output: Final notification data to the user.

[0570] (Application example 2)

[0571] 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."

[0572] Currently, cancer patients and their families have limited access to reliable medical information, and there is a particular lack of information provision that takes into consideration the user's emotions. For example, there is a lack of means to provide appropriate information and support to users who are feeling anxious or worried. Furthermore, there is a lack of mechanisms for appropriately adjusting online consultations with specialists based on the level of urgency and emotions. This presents a challenge for users, making it difficult to receive the information and support they need in a timely manner.

[0573] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0574] In this invention, the server includes means for receiving questions or requests entered by users and analyzing them using natural language processing, means for using generative artificial intelligence to generate answers based on the analyzed questions and the latest research and guidelines, and means for using an emotion engine to analyze the user's emotions and adjust the content of the answers based on the analysis results, thereby making it possible to provide answers and support that take into consideration the user's emotions as well as reliable medical information.

[0575] A "terminal" is a device through which a user can input questions or requests for online consultations and receive responses and notifications from the system.

[0576] The "server" is a central computer system that receives questions and requests sent from devices, analyzes them using natural language processing, and works with generative AI and emotion engines to generate answers and support.

[0577] "Natural language processing" is a computer science technique for analyzing text data and understanding its meaning.

[0578] "Generative AI" is an AI technology that automatically generates appropriate answers based on the latest research and guidelines, based on analyzed questions and requests.

[0579] The "emotion engine" is a technology that recognizes emotions from the text entered by the user and appropriately adjusts the response content and notifications based on the analysis results.

[0580] "Online consultation" is a consultation format that allows users to directly interact with experts via the Internet.

[0581] "Schedule adjustment" refers to the process of checking the specialist's schedule, selecting an available time slot, and deciding on the date and time of the consultation.

[0582] A "generative AI model" is a type of artificial intelligence used to analyze questions or requests and generate new answers.

[0583] A "prompt" is textual data that is input to a generative AI model and contains hints and instructions that help the model generate an answer.

[0584] This invention combines an emotion engine with an online consulting system that provides reliable medical information for cancer patients and their families. Each component is described in detail below.

[0585] System Configuration

[0586] 1. Terminal

[0587] The terminal is a device that allows users to input questions or requests for online consultations and receive replies and notifications from the system. Terminals can be smartphones, tablets, PCs, etc.

[0588] 2. Server

[0589] The server receives questions and requests sent from the device and analyzes the questions using natural language processing (NLP). The analyzed questions are used to generate answers through generative AI and an emotion engine. The server then sends the answers generated based on the analysis results to the device and displays them.

[0590] 3. Natural Language Processing

[0591] Natural language processing is a computer science technique used to analyze text data and understand its meaning. Specifically, it extracts important keywords from input questions and matches them with relevant medical databases and guidelines.

[0592] 4. Generative Artificial Intelligence

[0593] Generative AI (generative AI) generates appropriate answers based on analyzed questions received from the server, citing the latest research and guidelines. For example, OpenAI's GPT-4 is used as a generative AI.

[0594] 5. Emotion Engine

[0595] The emotion engine recognizes emotions from questions and requests entered by users and adjusts responses and notification content appropriately based on the recognized emotions. The emotion engine uses emotion analysis tools such as AWS Comprehend.

[0596] Program processing

[0597] The server receives questions sent from the device and analyzes them using natural language processing. The analyzed questions are then analyzed for user emotion through an emotion engine, and the results are passed on to a generation AI to generate an answer. The generated answer is then returned to the server and sent to the device.

[0598] This process involves the following hardware and software:

[0599] Hardware: smartphones, tablets, PCs, servers

[0600] Software: Natural language processing libraries (e.g., spaCy, NLTK), sentiment analysis tools (e.g., AWS Comprehend, TextBlob), generative AI (e.g., OpenAI GPT-4)

[0601] Specific examples

[0602] Specific examples of questions and answers

[0603] The user types the question "What are the side effects of chemotherapy?" into their smartphone. This question is sent to the server and analyzed through a natural language processing module and an emotion engine. Based on the analysis results, the generative AI generates the following answer: "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us." This answer is then sent back to the server and displayed on the device.

[0604] Specific examples of online consultation requests

[0605] The user inputs a request saying, "I want to talk to a specialist." This request is sent to the server, where the emotion engine analyzes the urgency and emotion. Based on the analysis results, the specialist's schedule is checked, and if the urgency is high, a date and time is set as a priority. The date and time are then notified to the user, and once the user confirms and agrees, the specialist is notified.

[0606] Prompt Sentence Examples

[0607] "Tell me about the side effects of chemotherapy. I'm worried."

[0608] This will ensure that cancer patients and their families receive timely, appropriate, and emotionally sensitive information and support.

[0609] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0610] Step 1: User enters question

[0611] The user inputs a question into a device (smartphone, tablet, PC, etc.) such as "What are the side effects of chemotherapy?" The input question is converted into text format on the device.

[0612] Step 2: The device sends the question to the server

[0613] The device sends the converted question to the server via an HTTP POST request, using JSON as the data format.

[0614] Step 3: The server receives and parses the query

[0615] The server receives the question sent from the device and uses a natural language processing (NLP) module (e.g., spaCy) to analyze the question and identify important keywords (e.g., "chemotherapy" and "side effects").

[0616] Step 4: The server analyzes the emotion using the emotion engine

[0617] The server passes the parsed question to an emotion engine (e.g., AWS Comprehend) to recognize the user's emotion (e.g., anxiety, worry). The emotion analysis results are returned in JSON format and stored on the server.

[0618] Step 5: The server passes the question and emotion data to the generation AI.

[0619] The server passes the analysis results and emotion data to a generative AI (e.g., OpenAI GPT-4), which then inputs a prompt into the generative AI model that generates an answer to the question. Example prompt: "Tell me about the side effects of chemotherapy. I'm feeling anxious."

[0620] Step 6: Generative AI generates an answer

[0621] Based on the given prompt, the generative AI refers to the latest research databases and guidelines to generate an appropriate answer. For example, it might generate an answer such as, "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us."

[0622] Step 7: The server sends the response to the device

[0623] The generated answer is sent back to the server, which then sends it to the device in JSON format. The answer data may also include the results of sentiment analysis.

[0624] Step 8: The device displays the answer to the user

[0625] The device analyzes the received responses and displays them to the user, allowing the user to obtain appropriate information about chemotherapy side effects.

[0626] Step 9: User requests an online consultation

[0627] If the user wishes to further consult with a specialist, the user inputs a request "I would like to speak to a specialist" from the terminal.

[0628] Step 10: The device sends a request to the server

[0629] The terminal converts the request into text format and sends it to the server as an HTTP POST request.

[0630] Step 11: The server receives and parses the request

[0631] The server receives the request and again analyzes the user's urgency and emotion using natural language processing and an emotion engine. Based on the analysis results, it determines the priority of the user's request.

[0632] Step 12: The server checks the specialist's schedule and sets the date and time.

[0633] The server accesses a database of specialist schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the call is prioritized.

[0634] Step 13: The server notifies the user of the candidate dates and times and asks for confirmation.

[0635] The server sends the proposed date and time in JSON format to the device and asks for confirmation from the user. The user checks the displayed date and time and selects the desired time slot.

[0636] Step 14: User checks the date and time and sends it to the server

[0637] Once the user confirms and approves the date and time, the information is sent to the server in JSON format.

[0638] Step 15: Server notifies specialist and resends final details to terminal

[0639] The server receives confirmation and notifies the specialist, and the final details are sent back to the terminal and notified to the user.

[0640] This series of processes enables cancer patients and their families to obtain reliable medical information in real time and smoothly consult with specialists online.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] [Second embodiment]

[0645] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0646] 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.

[0647] 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).

[0648] 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.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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."

[0657] overview

[0658] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is composed mainly of terminals, servers, and generation AI, provides answers to users' questions based on the latest research and guidelines, and also allows online consultations with specialized doctors and nurses as needed.

[0659] System Configuration

[0660] Terminal: A device on which users can input questions and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[0661] Server: Receives questions sent from the device, analyzes the questions, and generates answers in cooperation with the generation AI. It is also responsible for scheduling and notifying online consultations.

[0662] Generative AI: Based on analyzed questions received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[0663] Program processing

[0664] 1. Enter and submit your question

[0665] The user types their question (e.g., "What are the side effects of chemotherapy?") into the terminal.

[0666] The terminal converts the entered question into an appropriate format and sends it to the server.

[0667] 2. Receiving and analyzing questions

[0668] The server receives the query sent from the terminal.

[0669] The server uses natural language processing (NLP) techniques to analyze the question and identify the subject matter (e.g., "chemotherapy" and "side effects").

[0670] 3. Generate answers

[0671] The server sends the parsed question to the generation AI.

[0672] The generative AI generates answers to questions based on the latest research databases and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.") and sends them to a server.

[0673] 4. Providing answers

[0674] The server sends the generated response to the terminal.

[0675] The terminal displays the answer to the user.

[0676] 5. Request an online consultation

[0677] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[0678] The terminal converts the request into an appropriate format and sends it to the server.

[0679] 6. Scheduling online consultations

[0680] The server accesses a database of specialist and nurse schedules to select possible dates and times.

[0681] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[0682] 7. Confirmation and Final Notice

[0683] The user confirms the date and time of the online consultation from their device and approves it.

[0684] The terminal sends the confirmation results to the server, which then notifies the specialist or nurse.

[0685] The server sends a final confirmation to the terminal and notifies the user again.

[0686] Specific examples

[0687] Basic Questions and Answers

[0688] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0689] 2. The device converts the question into a format and sends it to the server.

[0690] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[0691] 4. The generative AI generates answers based on the latest side effects information for chemotherapy.

[0692] 5. The server sends the generated answer to the terminal and displays it to the user.

[0693] Request an online consultation

[0694] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[0695] 2. The device converts the request into a format and sends it to the server.

[0696] 3. The server checks the specialist's schedule and selects an available date and time.

[0697] 4. The server sends the selection results to the terminal and notifies the user.

[0698] 5. Once the user confirms and approves the date and time, it is sent from the device to the server.

[0699] 6. The server notifies the specialist of the results of the check and resends the final details to the terminal.

[0700] Through this series of processes, we can provide support to cancer patients and their families so that they can approach treatment with peace of mind.

[0701] The processing flow will be explained below.

[0702] Basic question and answer process flow

[0703] Step 1:

[0704] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0705] Step 2:

[0706] The terminal converts the entered question into text format and sends it to the server.

[0707] Step 3:

[0708] The server receives a query from the terminal.

[0709] Step 4:

[0710] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[0711] Step 5:

[0712] Based on the analysis results, the server generates a request to the generation AI.

[0713] Step 6:

[0714] The generative AI references the latest research databases and guidelines to generate appropriate answers to questions (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.").

[0715] Step 7:

[0716] The generation AI sends the generated answer to the server.

[0717] Step 8:

[0718] The server sends the generated response to the terminal.

[0719] Step 9:

[0720] The terminal displays the received response to the user.

[0721] Online consultation request processing flow

[0722] Step 1:

[0723] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[0724] Step 2:

[0725] The terminal converts the input request into text format and sends it to the server.

[0726] Step 3:

[0727] The server receives a request for online consultation from the terminal.

[0728] Step 4:

[0729] The server accesses a database of specialist and nurse schedules to check available time slots.

[0730] Step 5:

[0731] The server selects candidate dates and times and determines the date and time for the online consultation.

[0732] Step 6:

[0733] The server notifies the terminal of the determined online consultation date and time.

[0734] Step 7:

[0735] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[0736] Step 8:

[0737] The user confirms the date and time of the online consultation through the terminal and approves it.

[0738] Step 9:

[0739] The terminal transmits the user's confirmation result to the server.

[0740] Step 10:

[0741] The server notifies the specialist or nurse of the approval result.

[0742] Step 11:

[0743] The server sends a final confirmation to the terminal and notifies the user again.

[0744] In this way, the system as a whole executes each processing step in detail to facilitate two-way communication between the user and the medical professional.

[0745] Example 1

[0746] 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."

[0747] There is a need for an environment where cancer patients and their families can quickly and appropriately obtain reliable medical information. However, currently, providing appropriate information requires referencing numerous specialized materials, which places a significant burden on patients. Furthermore, there is a lack of efficient scheduling methods for patients who wish to consult online with specialists or nurses. To solve these problems, it is necessary to use advanced technology to automate the information and consultation procedures and provide them quickly and accurately.

[0748] 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.

[0749] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal and analyzing the question using natural language processing, artificial intelligence for generating an answer to the analyzed question based on the latest research and guidelines, means for transmitting the generated answer to the terminal and displaying it, means for receiving the user's request for online consultation and adjusting the specialist's schedule to determine the date and time of the online consultation, means for notifying the terminal of the determined date and time and receiving confirmation from the user, and means for notifying the specialist of the confirmation result and re-notifying the terminal of details of the online consultation. This enables cancer patients and their families to quickly and accurately obtain the medical information they need and to have efficient online consultations with specialists and nurses.

[0750] "Users" refer to cancer patients and their families who use the system.

[0751] "Device" refers to the device used by a user to enter questions and receive responses and notifications from the system, such as a smartphone, tablet, or PC.

[0752] The "server" refers to a computer system that receives and analyzes questions sent from the device, works with the generation AI to generate answers, and is also responsible for scheduling and notifying online consultations.

[0753] "Natural language processing" refers to computer techniques for analyzing natural language questions entered by users to identify their subject matter and intent. Examples include tokenization, part-of-speech tagging, and named entity recognition.

[0754] "Artificial intelligence" refers to technology that generates answers based on the latest research and guidelines, based on analyzed questions received from a server. In a broad sense, it includes machine learning and deep learning.

[0755] "Online consultation" refers to a consultation a user has with a specialist or nurse via the internet, including requests, scheduling, and notifications.

[0756] "Generative AI" is a form of artificial intelligence, specifically referring to algorithms and models that automatically generate appropriate answers to user questions.

[0757] "Schedule adjustment" refers to the process of receiving a user's request for online consultation and determining the date and time of the consultation according to the availability of the expert.

[0758] "Notification" refers to the system's act of conveying information or confirmation to users or experts, such as informing them of the date and time of an online consultation or the content of the response.

[0759] overview

[0760] This invention is an online consulting system that enables cancer patients and their families to quickly and appropriately obtain reliable medical information. The system uses terminals, a server, and a generative AI to automatically generate answers to users' questions and support online consultations with specialist doctors and nurses.

[0761] System Configuration

[0762] Terminal

[0763] This is a device that allows users to input questions and receive answers and notifications from the system. A variety of devices, including smartphones, tablets, and PCs, can be used as terminals. The system can be accessed through a dedicated application or a web browser.

[0764] server

[0765] The server has the following main functions:

[0766] 1. Receiving and parsing questions: Receive questions sent from the device and parse them using natural language processing (NLP) techniques. NLP libraries used include NLTK and spaCy.

[0767] 2. Collaboration with Generative AI: The analyzed question is sent to Generative AI, which then generates an appropriate answer. Generative AI then refers to the latest research databases and guidelines (e.g., PubMed, NCCN guidelines).

[0768] 3. Online consultation scheduling: Upon receiving a user request for an online consultation, the system accesses the specialist or nurse's schedule database (e.g., Google Calendar API) to determine the consultation date and time, and notifies the user or specialist.

[0769] Generation AI

[0770] Generative AI automatically generates answers based on the latest research and guidelines, based on analyzed questions received from the server, using trained machine learning models to extract information from relevant databases to create answers.

[0771] Specific operation example

[0772] User-entered questions

[0773] The user opens a dedicated application or web browser and enters their question (e.g., "What are the side effects of chemotherapy?"). The entered question is converted into an appropriate format (e.g., JSON format) and sent to the server.

[0774] Server parsing of the question

[0775] The server receives the question sent from the device and analyzes it using NLP technology to identify the topic of the question (e.g., "chemotherapy" or "side effects").

[0776] Generative AI generates answers

[0777] The server sends the analyzed question to the generation AI, which generates an appropriate answer based on the latest research database and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections."). The generated answer is then sent back to the server.

[0778] Show Answers

[0779] The server sends the generated answer to the terminal, which displays the answer to the user and notifies them using a notification function if necessary.

[0780] Request an online consultation

[0781] When a user wishes to have an online consultation with a specialist, they input a request from their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist.") The request is converted into an appropriate format and sent to the server.

[0782] Server-based scheduling

[0783] The server accesses the schedule database of specialists and nurses to select available dates and times. The selection results are sent to the terminal and the user is asked to confirm. Once the user confirms and agrees with the date and time, the confirmation results are sent to the server, which notifies the specialist and resends the final schedule to the terminal.

[0784] In this way, cancer patients and their families can quickly and accurately obtain the medical information they need, enabling efficient online consultations.

[0785] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0786] Step 1:

[0787] User-entered questions

[0788] Users open a dedicated application or web browser and enter their question (e.g., "What are the side effects of chemotherapy?").

[0789] The terminal converts the entered question into an appropriate format (e.g., JSON format).

[0790] Input: A text question entered by the user

[0791] Data processing: Convert text data into JSON format

[0792] Output: Converted JSON format question data

[0793] The device sends the generated question data in JSON format to the server.

[0794] Step 2:

[0795] The server receives and analyzes the query

[0796] The server receives the query sent from the terminal.

[0797] Input: JSON-formatted question data sent from the terminal

[0798] Data processing: JSON data analysis, data consistency check

[0799] Output: Parsed question data

[0800] The server uses natural language processing (NLP) techniques to analyze the question.

[0801] NLP libraries used include NLTK and spaCy.

[0802] Input: Question data in JSON format

[0803] Data operations: tokenization, part-of-speech tagging, named entity recognition

[0804] Output: The subject and keywords of the parsed question (e.g., "chemotherapy" and "side effects")

[0805] Step 3:

[0806] Generative AI generates answers

[0807] The server sends the parsed question to the generation AI.

[0808] Input: Parsed question data

[0809] Data processing: Converting data into a format that can be understood by generative AI

[0810] Output: Data sent to the generative AI

[0811] Generative AI generates appropriate answers based on the latest research databases and guidelines.

[0812] Databases used include PubMed and NCCN guidelines.

[0813] Input: Parsed question data

[0814] Data Computing: Find the latest research information for your questions and generate answers, including citations

[0815] Output: Generated answer (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection.")

[0816] The generated answer is sent back to the server.

[0817] Step 4:

[0818] Server provides answer

[0819] The server sends the generated response to the terminal.

[0820] Input: Answer data sent from the generation AI

[0821] Data processing: Convert response data into JSON format

[0822] Output: Converted JSON format response data

[0823] The terminal displays the answer to the user and notifies the user using a notification function if necessary.

[0824] Input: JSON format response data sent from the server

[0825] Data processing: Parsing JSON data and converting it into a format suitable for the user interface

[0826] Output: The answer displayed in the user interface

[0827] Step 5:

[0828] User requests for online consultation

[0829] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[0830] The device converts the request into an appropriate format (e.g., JSON).

[0831] Input: A textual request entered by the user.

[0832] Data processing: Convert text data into JSON format

[0833] Output: The converted JSON format request data

[0834] The terminal sends the generated request data in JSON format to the server.

[0835] Step 6:

[0836] Server-based scheduling of online consultations

[0837] The server accesses a database of specialist and nurse schedules to select available dates and times.

[0838] The schedule database used is the Google Calendar API.

[0839] Input: Request data sent from the terminal

[0840] Data calculation: Access to schedule database, search and obtain available time slots

[0841] Output: A list of candidate dates and times

[0842] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[0843] Input: A list of possible dates and times

[0844] Data Processing: Generate a confirmation request

[0845] Output: Verification request sent to the terminal

[0846] Step 7:

[0847] User confirmation and final notification

[0848] The user confirms the date and time of the online consultation from their device and approves it.

[0849] Input: Verification request sent by the server

[0850] Data manipulation: Get user selection

[0851] Output: User verification data

[0852] The terminal transmits the confirmation result to the server.

[0853] Input: User verification data

[0854] Data processing: Check data integrity and convert to JSON format

[0855] Output: Converted JSON format confirmation data

[0856] The server notifies the specialist or nurse of the results of the confirmation and confirms the final schedule.

[0857] Input: Verification data sent from the terminal

[0858] Data processing: Generate data to inform experts

[0859] Output: Final schedule sent to the expert

[0860] The server transmits the final schedule information to the terminal and notifies the user again.

[0861] Input: Final schedule data

[0862] Data processing: Generate notification data for users

[0863] Output: Final schedule notification sent to device

[0864] (Application example 1)

[0865] 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."

[0866] Cancer patients and their families often find it difficult to obtain reliable medical information quickly and appropriately. Even when they need to consult with a specialist doctor or nurse, scheduling an appointment is often difficult. Furthermore, it is necessary to establish a method for providing similar support in brick-and-mortar stores.

[0867] 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.

[0868] In this invention, the server includes a terminal for cancer patients and their families to input questions, a means for receiving questions sent from the terminal and analyzing the questions using natural language processing, a generation AI means for generating answers to the analyzed questions based on the latest research and guidelines, a means for sending the generated answers to the terminal and displaying them, a means for accepting requests from users seeking specialist consultations, a means for checking the schedules of specialists and nurses and arranging consultation dates and times, a means for notifying the terminal of the arranged date and time, receiving confirmation from the user, and again notifying the specialist or nurse, a means for installing a terminal for accepting questions in a physical store, and a means for appropriately processing questions and requests from the terminal installed in the physical store. This allows patients and their families to instantly obtain reliable medical information and smoothly conduct online consultations with specialists. Similar services can also be provided in physical stores to improve convenience.

[0869] "Cancer patients and their families" refers to patients who have currently been diagnosed with cancer and their families who need information and care to support them.

[0870] "Terminal" refers to a device through which a user can enter questions and receive answers and notifications from the system, including smartphones, tablets, and PCs.

[0871] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0872] A "server" refers to a device that receives questions sent from a terminal, analyzes the questions using natural language processing, and works with a generation AI to generate answers.

[0873] "Generative AI" refers to artificial intelligence technology that automatically generates appropriate answers based on analyzed questions, citing the latest research and guidelines.

[0874] "Display means" refers to a method or technology for transmitting the generated answer to a terminal and displaying it in a format that is easy for the user to view.

[0875] The "means for accepting a request" refers to a method or device for allowing a user who desires professional consultation to input a request into the system.

[0876] "Means for checking schedules and arranging consultation dates and times" refers to methods and technologies for managing the schedule data of specialists and nurses, and selecting and arranging appropriate dates and times for online consultations.

[0877] "Means for receiving confirmation and notifying again" refers to the method or technology for receiving final confirmation from the user and notifying the specialist or nurse of the confirmation content.

[0878] "Store-based terminal" refers to a device located within a physical store that a customer uses to input a question or request a consultation with a specialist.

[0879] "Means for appropriately processing questions and requests" refers to the methods and technologies for receiving user input from terminals installed in physical stores and analyzing and processing it on the server.

[0880] "Medical information" refers to reliable information in the medical field based on the latest research data and guidelines.

[0881] A "specialist" refers to a medical professional with advanced knowledge and experience in a particular medical field.

[0882] "Online consultation" refers to real-time health consultation with a specialist doctor or nurse via the Internet.

[0883] This invention is a system that allows cancer patients and their families to quickly and appropriately obtain reliable medical information and smoothly conduct online consultations with specialized doctors and nurses. Similar services can also be provided in physical stores. A specific embodiment of this system is described below.

[0884] System Configuration

[0885] 1. Terminal

[0886] A device that allows users to input questions and receive answers from generative AI. Specifically, it includes smartphones, tablets, PCs, and kiosks installed in physical stores.

[0887] 2. Server

[0888] The server receives questions sent from the device and analyzes them using natural language processing, which then sends the analyzed questions to a generative AI that generates answers based on the latest research and guidelines.

[0889] 3. Generation AI

[0890] The generative AI automatically generates appropriate answers based on the analyzed questions received from the server, citing the latest research data and guidelines, using natural language generation models (e.g., the GPT series).

[0891] Hardware and Software

[0892] Natural Language Processing (NLP) toolkits: We use NLP tools such as spaCy and NLTK to analyze questions, which helps us identify the subject of the question and access the appropriate information.

[0893] Generative AI models: Use natural language generation models like the OpenAI GPT series to generate answers based on the latest research data.

[0894] RESTful API: To ensure that each component of the entire system works together, data is communicated between the server and the terminal via a RESTful API using Flask or Django REST framework.

[0895] Explanation with concrete examples

[0896] Here is a specific example of a "health consultation kiosk" installed in a physical drugstore. When a customer using this kiosk asks, "Which supplements are effective for diabetes?", the following actions are taken:

[0897] 1. The user enters a question into the kiosk terminal's touch panel.

[0898] 2. The terminal converts the entered question into an appropriate format and sends it to the server.

[0899] 3. The server uses natural language processing to analyze the question and identify keywords such as "diabetes" and "supplements."

[0900] 4. Based on the analysis results, the AI ​​generates an answer citing the latest research data and guidelines. In this case, the generated answer would be "Vitamin D and magnesium are effective in managing diabetes."

[0901] 5. The server sends the generated answer to the terminal and displays it to the user.

[0902] Examples of prompt statements

[0903] Below are some specific examples of prompt sentences to input into the generative AI model.

[0904] Prompt: "Which supplements are effective for diabetes?"

[0905] Generative AI model: “Certain vitamins and minerals have been shown to be effective in managing diabetes. Examples include vitamin D and magnesium.”

[0906] In this way, users can instantly obtain reliable medical information and smoothly consult with specialists online. Similar services can also be provided in physical stores, improving convenience.

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

[0908] Step 1:

[0909] The user enters a question into the device's input screen, for example, "Which supplements are effective for diabetes?" The entered question is converted into an appropriate format for subsequent processing.

[0910] Step 2:

[0911] The device converts the question into a format and sends it to the server. This process uses an HTTP request, and the question is sent to the server in JSON format.

[0912] Step 3:

[0913] The server receives the question sent from the terminal. This input is a natural language question entered by the user. The received question is analyzed using a natural language processing (NLP) engine. Specifically, keywords (e.g., "diabetes" and "supplements") are extracted.

[0914] Step 4:

[0915] The server sends the analyzed results to a generative AI model, which uses this input to refer to the latest research data and guidelines to generate an appropriate answer to the question. For example, it may generate an answer such as, "Vitamin D and magnesium are effective in managing diabetes."

[0916] Step 5:

[0917] The server then sends the answer received from the generative AI model back to the device. At this stage, the generated answer is returned from the server to the device in JSON format.

[0918] Step 6:

[0919] The device displays the answer received from the server to the user. Specifically, the device screen displays the message, "Vitamin D and magnesium are effective in managing diabetes."

[0920] Step 7:

[0921] If the user wishes to further consult with a specialist online, he or she inputs a request from the terminal, for example, "I would like to speak to a specialist." This request is also sent to the server.

[0922] Step 8:

[0923] The server queries the schedule data of specialists and nurses to determine possible dates and times for online consultations. This coordination involves database access.

[0924] Step 9:

[0925] The server notifies the terminal of the arranged date and time of the online consultation, and this information is sent to the terminal in a format that can be confirmed by the user.

[0926] Step 10:

[0927] If the user confirms the presented date and time and approves it, the confirmation result is transmitted from the terminal to the server.

[0928] Step 11:

[0929] The server notifies the specialist or nurse of the user's confirmation results, including the arranged consultation date and time.

[0930] Step 12:

[0931] The server retransmits the final details of the online consultation to the terminal and prompts the user for final confirmation, after which the online consultation is officially scheduled.

[0932] The above are the specific processing steps of the system according to the present invention, which allows patients and their families to quickly obtain reliable medical information and smoothly consult with specialists online.

[0933] 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.

[0934] overview

[0935] This invention combines an emotion engine with an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is centered around a terminal, server, generative AI, and emotion engine, provides answers to users' questions based on the latest research and guidelines, and allows online consultations with specialized doctors and nurses as needed. It can also recognize users' emotions and provide tailored answers and support.

[0936] System Configuration

[0937] Terminal: A device on which users can input questions or requests for online consultations and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[0938] Server: Receives questions and requests sent from the device and analyzes the questions using natural language processing. It then passes the analyzed questions to a generation AI to generate answers. It also analyzes the user's emotions using an emotion engine.

[0939] Generative AI: Based on analyzed questions and requests received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[0940] Emotion Engine: Recognizes emotions from questions and requests entered by users and adjusts responses and notifications accordingly.

[0941] Program processing

[0942] 1. Enter and submit your question

[0943] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0944] The terminal converts the entered question into text format and sends it to the server.

[0945] 2. Receiving and analyzing questions

[0946] The server receives the query sent from the terminal.

[0947] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[0948] The server passes the analyzed question to the emotion engine to recognize the user's emotion.

[0949] 3. Emotional awareness and adaptation

[0950] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and tone of the question.

[0951] The server adjusts the content of the response and notification based on the results of the emotion engine.

[0952] 4. Answer Generation

[0953] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and an increased risk of infection. We understand your concerns, so please feel free to contact us.").

[0954] 5. Submitting and Viewing Your Answers

[0955] The server sends the generated response to the terminal.

[0956] The terminal displays the received response to the user.

[0957] 6. Online consultation requests and processing

[0958] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[0959] The terminal converts the request into text format and sends it to the server.

[0960] The server receives the request for online consultation and analyzes the user's urgency and emotions using an emotion engine.

[0961] The server accesses a database of specialists' and nurses' schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the request is given higher priority.

[0962] The server will notify the user of the suggested dates and times and ask for confirmation.

[0963] The user checks the date and time, and after approval, transmits it from the terminal to the server.

[0964] The server receives the confirmation and notifies the specialist or nurse.

[0965] The server sends the final details to the terminal and re-informs the user.

[0966] Specific examples

[0967] Basic Questions and Answers

[0968] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0969] 2. The device converts the question into a format and sends it to the server.

[0970] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[0971] 4. The emotion engine recognizes the emotion "anxiety" from the context of the question.

[0972] 5. The generative AI generates emotionally sensitive answers based on the latest side effects information about chemotherapy.

[0973] 6. The server sends the generated answer to the terminal and displays it to the user.

[0974] Request an online consultation

[0975] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[0976] 2. The device converts the request into a format and sends it to the server.

[0977] 3. The server receives the request and analyzes the user's urgency and emotion using the emotion engine.

[0978] 4. The server checks the specialist's schedule and prioritizes the date and time if the appointment is highly urgent.

[0979] 5. The server notifies the user of the date and time and asks for confirmation.

[0980] 6. Once the user confirms and approves the date and time, it is sent from the device to the server.

[0981] 7. The server notifies the specialist of the confirmation and resends the final details to the terminal.

[0982] This system allows cancer patients and their families to receive appropriate information and support that is sensitive to their emotions, allowing them to approach treatment with peace of mind.

[0983] The processing flow will be explained below.

[0984] Basic question and answer process flow

[0985] Step 1:

[0986] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[0987] Step 2:

[0988] The terminal converts the entered question into text format and sends it to the server in the appropriate format.

[0989] Step 3:

[0990] The server receives the query sent from the terminal.

[0991] Step 4:

[0992] The server uses a natural language processing (NLP) module to analyze the received question and identify key keywords (e.g., "chemotherapy" and "side effects").

[0993] Step 5:

[0994] The server passes the analysis results to the emotion engine, which recognizes the user's emotions.

[0995] Step 6:

[0996] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and wording of the question.

[0997] Step 7:

[0998] The server receives the results of the emotion engine and includes the emotion information in the request to the generation AI.

[0999] Step 8:

[1000] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection. We understand that you are concerned, but these symptoms are common. Please let us know if there are any other concerns you have.").

[1001] Step 9:

[1002] The generation AI sends the generated answer to the server.

[1003] Step 10:

[1004] The server sends the generated response to the terminal.

[1005] Step 11:

[1006] The terminal displays the answer to the user.

[1007] Online consultation request processing flow

[1008] Step 1:

[1009] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[1010] Step 2:

[1011] The terminal converts the input request into text format and transmits it to the server in the appropriate format.

[1012] Step 3:

[1013] The server receives a request for online consultation sent from the terminal.

[1014] Step 4:

[1015] The server uses an emotion engine to recognize the emotion contained in the user's request (e.g., anxiety with high urgency).

[1016] Step 5:

[1017] The server accesses a database of specialist and nurse schedules to check available time slots.

[1018] Step 6:

[1019] Based on the analysis results of the emotion engine, the server determines the urgency of the online consultation and changes the priority of schedule adjustments as necessary.

[1020] Step 7:

[1021] The server selects candidate dates and times and determines the date and time for the online consultation.

[1022] Step 8:

[1023] The server notifies the terminal of the determined date and time of the online consultation.

[1024] Step 9:

[1025] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[1026] Step 10:

[1027] The user confirms the date and time of the online consultation through the terminal and approves it.

[1028] Step 11:

[1029] The terminal transmits the confirmation result to the server.

[1030] Step 12:

[1031] The server notifies the specialist or nurse of the confirmation results.

[1032] Step 13:

[1033] The server sends a final confirmation to the terminal and notifies the user again.

[1034] In this way, the system can provide appropriate information and support in response to users' questions and requests while taking their emotions into consideration, enabling smooth two-way communication.

[1035] Example 2

[1036] 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."

[1037] Currently, it is not easy for cancer patients and their families to obtain reliable medical information. While online consultation systems exist, they often do not provide appropriate responses that take into consideration the patient's feelings. As a result, patients often undergo treatment while feeling anxious and worried, placing a heavy psychological burden on them. Furthermore, there is a problem in that they are unable to respond appropriately to urgent consultation requests, making it difficult to fully meet the needs of patients.

[1038] 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.

[1039] In this invention, the server includes a means for receiving questions sent from a terminal and analyzing the questions using natural language processing; an automatic response generation device for generating answers to the analyzed questions based on the latest research and guidelines; and an emotion analysis device for recognizing the user's emotions and adapting the answers and notification content based on the recognized emotions. This not only enables patients and their families to obtain reliable medical information, but also enables responses that take emotions into consideration. Furthermore, since highly urgent requests can be responded to quickly and appropriately, the psychological burden on patients is reduced, allowing them to receive treatment with peace of mind.

[1040] A "terminal" is a device through which a user inputs questions or requests for online consultations and receives responses or notifications from the system.

[1041] An "information processing device" is a device that receives a question sent from a terminal and analyzes the question using natural language processing.

[1042] An "automatic response generator" is a device that generates answers to analyzed questions based on the latest research and guidelines.

[1043] An "emotion analysis device" is a device that recognizes a user's emotions and adjusts responses and notification content based on the recognized emotions.

[1044] "Online consultation request" is a request input by the user to request an online consultation with a specialist doctor or nurse.

[1045] The "schedule adjustment method" is a system that checks the schedules of specialists and nurses and determines the date and time of online consultations.

[1046] "Urgency" is an index that indicates the importance or urgency of a user's request.

[1047] "Natural language processing" is a technology for analyzing user questions and understanding important keywords and context.

[1048] A "generative AI model" is an artificial intelligence that generates appropriate answers from analyzed questions and sentiment analysis results based on the latest research and guidelines.

[1049] A "prompt" is a textual representation of a question or request that is input to a generative AI model.

[1050] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information, and also combines it with emotion analysis functions. The system is mainly composed of a terminal, an information processing device, an automatic response generation device, and an emotion analysis device, and provides users with prompt and appropriate information.

[1051] overview

[1052] The basic configuration of the invention is as follows:

[1053] 1. Terminal: A device on which users can enter questions or requests for online consultations and receive answers and notifications from the system. It can be a smartphone, tablet, or PC.

[1054] 2. Information processing device: Receives questions sent from the device and analyzes them using natural language processing (NLP), for example, using libraries such as spaCy or NLTK.

[1055] 3. Automatic response generator: Receives analyzed questions from an information processing device and uses a generative AI model to generate answers based on the latest research and guidelines. Databases such as PubMed can be used for reference.

[1056] 4. Emotion analyzer: This function analyzes the user's input and recognizes emotions (e.g., anxiety, worry). Emotion analysis is performed using IBM Watson Tone Analyzer, etc.

[1057] The main features of the system are:

[1058] 1. Enter and submit your question

[1059] Users use a terminal to enter a question in text format, such as "What are the side effects of chemotherapy?"

[1060] The terminal converts the entered question into an appropriate format and sends it to the server.

[1061] 2. Receiving and analyzing questions

[1062] The server receives the query sent from the terminal.

[1063] The server uses a natural language processing module to analyze the question and identify important keywords.

[1064] After analysis, the question data is passed to an emotion analyzer to recognize the user's emotion.

[1065] 3. Emotional awareness and adaptation

[1066] The emotion analyzer recognizes the user's emotions and returns the results to the server.

[1067] The server adjusts the response content based on the results of the emotion analysis.

[1068] 4. Answer Generation

[1069] The generative AI model uses the parsed question and sentiment analysis results to generate appropriate answers.

[1070] The generated answer is sent to the terminal via the server.

[1071] 5. View Answers

[1072] The terminal displays the received response to the user.

[1073] 6. Online consultation requests and processing

[1074] If the user wishes to have an online consultation with a specialist, they enter a request.

[1075] The device sends a request to the server, which checks the specialist's schedule and adjusts the priority according to the urgency.

[1076] The confirmed consultation date and time is notified to the user and the specialist.

[1077] Specific examples

[1078] When a user types a question such as "I'm anxious about the treatment I'm currently receiving," the device converts it into text format and sends it to the server. The server uses natural language processing to identify keywords such as "treatment" and "anxiety," and passes these to the emotion analyzer. The emotion analyzer recognizes the emotion "anxiety" and passes the results to the generative AI model. The generative AI model generates an answer based on the latest research data, such as "It's common to feel anxious about treatment. If you could tell us your story, we'll respond appropriately."

[1079] Prompt Sentence Examples

[1080] "Tell us about common side effects of chemotherapy and be mindful of any concerns users may have."

[1081] This system not only allows cancer patients and their families to obtain reliable medical information, but also provides emotionally sensitive care, allowing them to undergo treatment with peace of mind.

[1082] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1083] Step 1:

[1084] The user types a question into the terminal.

[1085] Input: The user types the question, "What are the side effects of chemotherapy?"

[1086] Action: The action of entering text into a device input field.

[1087] Output: The input text data.

[1088] Step 2:

[1089] The terminal converts the entered question into the appropriate format.

[1090] Input: The text data entered in step 1.

[1091] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[1092] Output: Formatted text data.

[1093] Step 3:

[1094] The device sends a formatted text question to the server.

[1095] Input: The formatted text data from step 2.

[1096] What it does: Sends data to a server via an HTTP request.

[1097] Output: Request data to the server.

[1098] Step 4:

[1099] The server receives the question sent from the terminal.

[1100] Input: The request data sent in step 3.

[1101] How it works: The API endpoint receives request data.

[1102] Output: The received query data.

[1103] Step 5:

[1104] The server parses the question using a natural language processing (NLP) module.

[1105] Input: The question data received in step 4.

[1106] How it works: Analyzes text using NLP techniques (e.g. spaCy) to extract important keywords.

[1107] Output: Extracted keyword data (e.g., "chemotherapy" and "side effects").

[1108] Step 6:

[1109] The server passes the analysis results to the emotion analysis device.

[1110] Input: Keyword data extracted in step 5.

[1111] What it does: Converts NLP results into JSON format and sends them to the sentiment analyzer.

[1112] Output: Request data to the sentiment analyzer.

[1113] Step 7:

[1114] The emotion analyzer recognizes the user's emotions from the context and tone of the question.

[1115] Input: The request data sent in step 6.

[1116] How it works: Identifies emotions using emotion analysis technology (e.g., IBM Watson Tone Analyzer).

[1117] Output: Recognized emotion data (e.g., "anxiety").

[1118] Step 8:

[1119] The server receives the sentiment analysis results.

[1120] Input: Emotion data obtained in step 7.

[1121] What it does: Receives emotion data and prepares it for use in adjusting responses.

[1122] Output: Emotion data ready for conditioning.

[1123] Step 9:

[1124] The server passes the analyzed question and sentiment analysis results to the generated AI model.

[1125] Input: Keyword data extracted in step 5 and sentiment data obtained in step 8.

[1126] How it works: The question and emotion data are input as prompts to the generative AI.

[1127] Output: Prompt data to the generative AI model.

[1128] Step 10:

[1129] The generative AI model generates answers by referencing the latest research databases and guidelines.

[1130] Input: Prompt data from step 9.

[1131] What it does: Consults up-to-date research databases (e.g., PubMed) and generates relevant answers.

[1132] Output: The generated response data.

[1133] Step 11:

[1134] The server sends the answer received from the generation AI to the terminal.

[1135] Input: The response data generated in step 10.

[1136] What it does: Sends data to the device via an HTTP response.

[1137] Output: Response data to the device.

[1138] Step 12:

[1139] The terminal displays the received answer to the user.

[1140] Input: The response data sent in step 11.

[1141] What it does: Displays textual responses via a GUI.

[1142] Output: The answer data displayed to the user.

[1143] Step 13:

[1144] If the user wishes to have an online consultation with a specialist, they enter a request.

[1145] Input: User types "I would like to speak to a specialist."

[1146] Action: The action of entering text into a device input field.

[1147] Output: The input request data.

[1148] Step 14:

[1149] The device converts the request into an appropriate format and sends it to the server.

[1150] Input: The request data entered in step 13.

[1151] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[1152] Output: The formatted request data.

[1153] Step 15:

[1154] The server receives the online consultation request and analyzes the urgency and emotion of the user with an emotion analyzer.

[1155] Input: The request data sent in step 14.

[1156] How it works: It uses NLP techniques and sentiment analyzers to analyze text and identify sentiment and urgency.

[1157] Output: Extracted urgency and sentiment data.

[1158] Step 16:

[1159] The server accesses a database of specialist and nurse schedules to check available time slots.

[1160] Input: Urgency data identified in Step 15.

[1161] What it does: Runs a database query to find and identify free time.

[1162] Output: Data on available time slots.

[1163] Step 17:

[1164] If the server is in a high emergency state, the date and time are set with priority.

[1165] Input: The open time slot data identified in step 16.

[1166] What it does: Prioritize and optimize dates and times based on urgency.

[1167] Output: Date and time data of the online consultation that was set.

[1168] Step 18:

[1169] The server notifies the user of the set date and time and asks for confirmation.

[1170] Input: Date and time data set in step 17.

[1171] Behavior: Generates a confirmation message and sends it to the device as an HTTP response.

[1172] Output: Acknowledgement data to the user.

[1173] Step 19:

[1174] Once the user confirms and approves the date and time, it is sent from the device to the server.

[1175] Input: Acknowledgment data sent in step 18.

[1176] Action: The user sees the notification and clicks the confirm / agree button.

[1177] Output: Confirmation and acceptance data.

[1178] Step 20:

[1179] The server notifies the specialist or nurse of the confirmation.

[1180] Input: Confirmation and acknowledgement data sent in step 19.

[1181] What it does: Generates and sends a message to notify specialists and nurses of the results of the check.

[1182] Output: Data for notifying specialists and nurses.

[1183] Step 21:

[1184] The server sends the final details to the terminal and re-informs the user.

[1185] Input: Specialist and nurse notification data sent in step 20.

[1186] Behavior: A message containing the confirmed date and time and details is generated and sent to the device as an HTTP response.

[1187] Output: Final notification data to the user.

[1188] (Application example 2)

[1189] 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."

[1190] Currently, cancer patients and their families have limited access to reliable medical information, and there is a particular lack of information provision that takes into consideration the user's emotions. For example, there is a lack of means to provide appropriate information and support to users who are feeling anxious or worried. Furthermore, there is a lack of mechanisms for appropriately adjusting online consultations with specialists based on the level of urgency and emotions. This presents a challenge for users, making it difficult to receive the information and support they need in a timely manner.

[1191] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1192] In this invention, the server includes means for receiving questions or requests entered by users and analyzing them using natural language processing, means for using generative artificial intelligence to generate answers based on the analyzed questions and the latest research and guidelines, and means for using an emotion engine to analyze the user's emotions and adjust the content of the answers based on the analysis results, thereby making it possible to provide answers and support that take into consideration the user's emotions as well as reliable medical information.

[1193] A "terminal" is a device through which a user can input questions or requests for online consultations and receive responses and notifications from the system.

[1194] The "server" is a central computer system that receives questions and requests sent from devices, analyzes them using natural language processing, and works with generative AI and emotion engines to generate answers and support.

[1195] "Natural language processing" is a computer science technique for analyzing text data and understanding its meaning.

[1196] "Generative AI" is an AI technology that automatically generates appropriate answers based on the latest research and guidelines, based on analyzed questions and requests.

[1197] The "emotion engine" is a technology that recognizes emotions from the text entered by the user and appropriately adjusts the response content and notifications based on the analysis results.

[1198] "Online consultation" is a consultation format that allows users to directly interact with experts via the Internet.

[1199] "Schedule adjustment" refers to the process of checking the specialist's schedule, selecting an available time slot, and deciding on the date and time of the consultation.

[1200] A "generative AI model" is a type of artificial intelligence used to analyze questions or requests and generate new answers.

[1201] A "prompt" is textual data that is input to a generative AI model and contains hints and instructions that help the model generate an answer.

[1202] This invention combines an emotion engine with an online consulting system that provides reliable medical information for cancer patients and their families. Each component is described in detail below.

[1203] System Configuration

[1204] 1. Terminal

[1205] The terminal is a device that allows users to input questions or requests for online consultations and receive replies and notifications from the system. Terminals can be smartphones, tablets, PCs, etc.

[1206] 2. Server

[1207] The server receives questions and requests sent from the device and analyzes the questions using natural language processing (NLP). The analyzed questions are used to generate answers through generative AI and an emotion engine. The server then sends the answers generated based on the analysis results to the device and displays them.

[1208] 3. Natural Language Processing

[1209] Natural language processing is a computer science technique used to analyze text data and understand its meaning. Specifically, it extracts important keywords from input questions and matches them with relevant medical databases and guidelines.

[1210] 4. Generative Artificial Intelligence

[1211] Generative AI (generative AI) generates appropriate answers based on analyzed questions received from the server, citing the latest research and guidelines. For example, OpenAI's GPT-4 is used as a generative AI.

[1212] 5. Emotion Engine

[1213] The emotion engine recognizes emotions from questions and requests entered by users and adjusts responses and notification content appropriately based on the recognized emotions. The emotion engine uses emotion analysis tools such as AWS Comprehend.

[1214] Program processing

[1215] The server receives questions sent from the device and analyzes them using natural language processing. The analyzed questions are then analyzed for user emotion through an emotion engine, and the results are passed on to a generation AI to generate an answer. The generated answer is then returned to the server and sent to the device.

[1216] This process involves the following hardware and software:

[1217] Hardware: smartphones, tablets, PCs, servers

[1218] Software: Natural language processing libraries (e.g., spaCy, NLTK), sentiment analysis tools (e.g., AWS Comprehend, TextBlob), generative AI (e.g., OpenAI GPT-4)

[1219] Specific examples

[1220] Specific examples of questions and answers

[1221] The user types the question "What are the side effects of chemotherapy?" into their smartphone. This question is sent to the server and analyzed through a natural language processing module and an emotion engine. Based on the analysis results, the generative AI generates the following answer: "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us." This answer is then sent back to the server and displayed on the device.

[1222] Specific examples of online consultation requests

[1223] The user inputs a request saying, "I want to talk to a specialist." This request is sent to the server, where the emotion engine analyzes the urgency and emotion. Based on the analysis results, the specialist's schedule is checked, and if the urgency is high, a date and time is set as a priority. The date and time are then notified to the user, and once the user confirms and agrees, the specialist is notified.

[1224] Prompt Sentence Examples

[1225] "Tell me about the side effects of chemotherapy. I'm worried."

[1226] This will ensure that cancer patients and their families receive timely, appropriate, and emotionally sensitive information and support.

[1227] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1228] Step 1: User enters question

[1229] The user inputs a question into a device (smartphone, tablet, PC, etc.) such as "What are the side effects of chemotherapy?" The input question is converted into text format on the device.

[1230] Step 2: The device sends the question to the server

[1231] The device sends the converted question to the server via an HTTP POST request, using JSON as the data format.

[1232] Step 3: The server receives and parses the query

[1233] The server receives the question sent from the device and uses a natural language processing (NLP) module (e.g., spaCy) to analyze the question and identify important keywords (e.g., "chemotherapy" and "side effects").

[1234] Step 4: The server analyzes the emotion using the emotion engine

[1235] The server passes the parsed question to an emotion engine (e.g., AWS Comprehend) to recognize the user's emotion (e.g., anxiety, worry). The emotion analysis results are returned in JSON format and stored on the server.

[1236] Step 5: The server passes the question and emotion data to the generation AI.

[1237] The server passes the analysis results and emotion data to a generative AI (e.g., OpenAI GPT-4), which then inputs a prompt into the generative AI model that generates an answer to the question. Example prompt: "Tell me about the side effects of chemotherapy. I'm feeling anxious."

[1238] Step 6: Generative AI generates an answer

[1239] Based on the given prompt, the generative AI refers to the latest research databases and guidelines to generate an appropriate answer. For example, it might generate an answer such as, "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us."

[1240] Step 7: The server sends the response to the device

[1241] The generated answer is sent back to the server, which then sends it to the device in JSON format. The answer data may also include the results of sentiment analysis.

[1242] Step 8: The device displays the answer to the user

[1243] The device analyzes the received responses and displays them to the user, allowing the user to obtain appropriate information about chemotherapy side effects.

[1244] Step 9: User requests an online consultation

[1245] If the user wishes to further consult with a specialist, the user inputs a request "I would like to speak to a specialist" from the terminal.

[1246] Step 10: The device sends a request to the server

[1247] The terminal converts the request into text format and sends it to the server as an HTTP POST request.

[1248] Step 11: The server receives and parses the request

[1249] The server receives the request and again analyzes the user's urgency and emotion using natural language processing and an emotion engine. Based on the analysis results, it determines the priority of the user's request.

[1250] Step 12: The server checks the specialist's schedule and sets the date and time.

[1251] The server accesses a database of specialist schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the call is prioritized.

[1252] Step 13: The server notifies the user of the candidate dates and times and asks for confirmation.

[1253] The server sends the proposed date and time in JSON format to the device and asks for confirmation from the user. The user checks the displayed date and time and selects the desired time slot.

[1254] Step 14: User checks the date and time and sends it to the server

[1255] Once the user confirms and approves the date and time, the information is sent to the server in JSON format.

[1256] Step 15: Server notifies specialist and resends final details to terminal

[1257] The server receives confirmation and notifies the specialist, and the final details are sent back to the terminal and notified to the user.

[1258] This series of processes enables cancer patients and their families to obtain reliable medical information in real time and smoothly consult with specialists online.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] [Third embodiment]

[1263] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1264] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1265] 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).

[1266] 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.

[1267] 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.

[1268] 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).

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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."

[1275] overview

[1276] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is composed mainly of terminals, servers, and generation AI, provides answers to users' questions based on the latest research and guidelines, and also allows online consultations with specialized doctors and nurses as needed.

[1277] System Configuration

[1278] Terminal: A device on which users can input questions and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[1279] Server: Receives questions sent from the device, analyzes the questions, and generates answers in cooperation with the generation AI. It is also responsible for scheduling and notifying online consultations.

[1280] Generative AI: Based on analyzed questions received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[1281] Program processing

[1282] 1. Enter and submit your question

[1283] The user types their question (e.g., "What are the side effects of chemotherapy?") into the terminal.

[1284] The terminal converts the entered question into an appropriate format and sends it to the server.

[1285] 2. Receiving and analyzing questions

[1286] The server receives the query sent from the terminal.

[1287] The server uses natural language processing (NLP) techniques to analyze the question and identify the subject matter (e.g., "chemotherapy" and "side effects").

[1288] 3. Generate answers

[1289] The server sends the parsed question to the generation AI.

[1290] The generative AI generates answers to questions based on the latest research databases and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.") and sends them to a server.

[1291] 4. Providing answers

[1292] The server sends the generated response to the terminal.

[1293] The terminal displays the answer to the user.

[1294] 5. Request an online consultation

[1295] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[1296] The terminal converts the request into an appropriate format and sends it to the server.

[1297] 6. Scheduling online consultations

[1298] The server accesses a database of specialist and nurse schedules to select possible dates and times.

[1299] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[1300] 7. Confirmation and Final Notice

[1301] The user confirms the date and time of the online consultation from their device and approves it.

[1302] The terminal sends the confirmation results to the server, which then notifies the specialist or nurse.

[1303] The server sends a final confirmation to the terminal and notifies the user again.

[1304] Specific examples

[1305] Basic Questions and Answers

[1306] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1307] 2. The device converts the question into a format and sends it to the server.

[1308] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[1309] 4. The generative AI generates answers based on the latest side effects information for chemotherapy.

[1310] 5. The server sends the generated answer to the terminal and displays it to the user.

[1311] Request an online consultation

[1312] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[1313] 2. The device converts the request into a format and sends it to the server.

[1314] 3. The server checks the specialist's schedule and selects an available date and time.

[1315] 4. The server sends the selection results to the terminal and notifies the user.

[1316] 5. Once the user confirms and approves the date and time, it is sent from the device to the server.

[1317] 6. The server notifies the specialist of the results of the check and resends the final details to the terminal.

[1318] Through this series of processes, we can provide support to cancer patients and their families so that they can approach treatment with peace of mind.

[1319] The processing flow will be explained below.

[1320] Basic question and answer process flow

[1321] Step 1:

[1322] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1323] Step 2:

[1324] The terminal converts the entered question into text format and sends it to the server.

[1325] Step 3:

[1326] The server receives a query from the terminal.

[1327] Step 4:

[1328] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[1329] Step 5:

[1330] Based on the analysis results, the server generates a request to the generation AI.

[1331] Step 6:

[1332] The generative AI references the latest research databases and guidelines to generate appropriate answers to questions (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.").

[1333] Step 7:

[1334] The generation AI sends the generated answer to the server.

[1335] Step 8:

[1336] The server sends the generated response to the terminal.

[1337] Step 9:

[1338] The terminal displays the received response to the user.

[1339] Online consultation request processing flow

[1340] Step 1:

[1341] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[1342] Step 2:

[1343] The terminal converts the input request into text format and sends it to the server.

[1344] Step 3:

[1345] The server receives a request for online consultation from the terminal.

[1346] Step 4:

[1347] The server accesses a database of specialist and nurse schedules to check available time slots.

[1348] Step 5:

[1349] The server selects candidate dates and times and determines the date and time for the online consultation.

[1350] Step 6:

[1351] The server notifies the terminal of the determined online consultation date and time.

[1352] Step 7:

[1353] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[1354] Step 8:

[1355] The user confirms the date and time of the online consultation through the terminal and approves it.

[1356] Step 9:

[1357] The terminal transmits the user's confirmation result to the server.

[1358] Step 10:

[1359] The server notifies the specialist or nurse of the approval result.

[1360] Step 11:

[1361] The server sends a final confirmation to the terminal and notifies the user again.

[1362] In this way, the system as a whole executes each processing step in detail to facilitate two-way communication between the user and the medical professional.

[1363] Example 1

[1364] 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."

[1365] There is a need for an environment where cancer patients and their families can quickly and appropriately obtain reliable medical information. However, currently, providing appropriate information requires referencing numerous specialized materials, which places a significant burden on patients. Furthermore, there is a lack of efficient scheduling methods for patients who wish to consult online with specialists or nurses. To solve these problems, it is necessary to use advanced technology to automate the information and consultation procedures and provide them quickly and accurately.

[1366] 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.

[1367] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal and analyzing the question using natural language processing, artificial intelligence for generating an answer to the analyzed question based on the latest research and guidelines, means for transmitting the generated answer to the terminal and displaying it, means for receiving the user's request for online consultation and adjusting the specialist's schedule to determine the date and time of the online consultation, means for notifying the terminal of the determined date and time and receiving confirmation from the user, and means for notifying the specialist of the confirmation result and re-notifying the terminal of details of the online consultation. This enables cancer patients and their families to quickly and accurately obtain the medical information they need and to have efficient online consultations with specialists and nurses.

[1368] "Users" refer to cancer patients and their families who use the system.

[1369] "Device" refers to the device used by a user to enter questions and receive responses and notifications from the system, such as a smartphone, tablet, or PC.

[1370] The "server" refers to a computer system that receives and analyzes questions sent from the device, works with the generation AI to generate answers, and is also responsible for scheduling and notifying online consultations.

[1371] "Natural language processing" refers to computer techniques for analyzing natural language questions entered by users to identify their subject matter and intent. Examples include tokenization, part-of-speech tagging, and named entity recognition.

[1372] "Artificial intelligence" refers to technology that generates answers based on the latest research and guidelines, based on analyzed questions received from a server. In a broad sense, it includes machine learning and deep learning.

[1373] "Online consultation" refers to a consultation a user has with a specialist or nurse via the internet, including requests, scheduling, and notifications.

[1374] "Generative AI" is a form of artificial intelligence, specifically referring to algorithms and models that automatically generate appropriate answers to user questions.

[1375] "Schedule adjustment" refers to the process of receiving a user's request for online consultation and determining the date and time of the consultation according to the availability of the expert.

[1376] "Notification" refers to the system's act of conveying information or confirmation to users or experts, such as informing them of the date and time of an online consultation or the content of the response.

[1377] overview

[1378] This invention is an online consulting system that enables cancer patients and their families to quickly and appropriately obtain reliable medical information. The system uses terminals, a server, and a generative AI to automatically generate answers to users' questions and support online consultations with specialist doctors and nurses.

[1379] System Configuration

[1380] Terminal

[1381] This is a device that allows users to input questions and receive answers and notifications from the system. A variety of devices, including smartphones, tablets, and PCs, can be used as terminals. The system can be accessed through a dedicated application or a web browser.

[1382] server

[1383] The server has the following main functions:

[1384] 1. Receiving and parsing questions: Receive questions sent from the device and parse them using natural language processing (NLP) techniques. NLP libraries used include NLTK and spaCy.

[1385] 2. Collaboration with Generative AI: The analyzed question is sent to Generative AI, which then generates an appropriate answer. Generative AI then refers to the latest research databases and guidelines (e.g., PubMed, NCCN guidelines).

[1386] 3. Online consultation scheduling: Upon receiving a user request for an online consultation, the system accesses the specialist or nurse's schedule database (e.g., Google Calendar API) to determine the consultation date and time, and notifies the user or specialist.

[1387] Generation AI

[1388] Generative AI automatically generates answers based on the latest research and guidelines, based on analyzed questions received from the server, using trained machine learning models to extract information from relevant databases to create answers.

[1389] Specific operation example

[1390] User-entered questions

[1391] The user opens a dedicated application or web browser and enters their question (e.g., "What are the side effects of chemotherapy?"). The entered question is converted into an appropriate format (e.g., JSON format) and sent to the server.

[1392] Server parsing of the question

[1393] The server receives the question sent from the device and analyzes it using NLP technology to identify the topic of the question (e.g., "chemotherapy" or "side effects").

[1394] Generative AI generates answers

[1395] The server sends the analyzed question to the generation AI, which generates an appropriate answer based on the latest research database and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections."). The generated answer is then sent back to the server.

[1396] Show Answers

[1397] The server sends the generated answer to the terminal, which displays the answer to the user and notifies them using a notification function if necessary.

[1398] Request an online consultation

[1399] When a user wishes to have an online consultation with a specialist, they input a request from their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist.") The request is converted into an appropriate format and sent to the server.

[1400] Server-based scheduling

[1401] The server accesses the schedule database of specialists and nurses to select available dates and times. The selection results are sent to the terminal and the user is asked to confirm. Once the user confirms and agrees with the date and time, the confirmation results are sent to the server, which notifies the specialist and resends the final schedule to the terminal.

[1402] In this way, cancer patients and their families can quickly and accurately obtain the medical information they need, enabling efficient online consultations.

[1403] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1404] Step 1:

[1405] User-entered questions

[1406] Users open a dedicated application or web browser and enter their question (e.g., "What are the side effects of chemotherapy?").

[1407] The terminal converts the entered question into an appropriate format (e.g., JSON format).

[1408] Input: A text question entered by the user

[1409] Data processing: Convert text data into JSON format

[1410] Output: Converted JSON format question data

[1411] The device sends the generated question data in JSON format to the server.

[1412] Step 2:

[1413] The server receives and analyzes the query

[1414] The server receives the query sent from the terminal.

[1415] Input: JSON-formatted question data sent from the terminal

[1416] Data processing: JSON data analysis, data consistency check

[1417] Output: Parsed question data

[1418] The server uses natural language processing (NLP) techniques to analyze the question.

[1419] NLP libraries used include NLTK and spaCy.

[1420] Input: Question data in JSON format

[1421] Data operations: tokenization, part-of-speech tagging, named entity recognition

[1422] Output: The subject and keywords of the parsed question (e.g., "chemotherapy" and "side effects")

[1423] Step 3:

[1424] Generative AI generates answers

[1425] The server sends the parsed question to the generation AI.

[1426] Input: Parsed question data

[1427] Data processing: Converting data into a format that can be understood by generative AI

[1428] Output: Data sent to the generative AI

[1429] Generative AI generates appropriate answers based on the latest research databases and guidelines.

[1430] Databases used include PubMed and NCCN guidelines.

[1431] Input: Parsed question data

[1432] Data Computing: Find the latest research information for your questions and generate answers, including citations

[1433] Output: Generated answer (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection.")

[1434] The generated answer is sent back to the server.

[1435] Step 4:

[1436] Server provides answer

[1437] The server sends the generated response to the terminal.

[1438] Input: Answer data sent from the generation AI

[1439] Data processing: Convert response data into JSON format

[1440] Output: Converted JSON format response data

[1441] The terminal displays the answer to the user and notifies the user using a notification function if necessary.

[1442] Input: JSON format response data sent from the server

[1443] Data processing: Parsing JSON data and converting it into a format suitable for the user interface

[1444] Output: The answer displayed in the user interface

[1445] Step 5:

[1446] User requests for online consultation

[1447] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[1448] The device converts the request into an appropriate format (e.g., JSON).

[1449] Input: A textual request entered by the user.

[1450] Data processing: Convert text data into JSON format

[1451] Output: The converted JSON format request data

[1452] The terminal sends the generated request data in JSON format to the server.

[1453] Step 6:

[1454] Server-based scheduling of online consultations

[1455] The server accesses a database of specialist and nurse schedules to select available dates and times.

[1456] The schedule database used is the Google Calendar API.

[1457] Input: Request data sent from the terminal

[1458] Data calculation: Access to schedule database, search and obtain available time slots

[1459] Output: A list of candidate dates and times

[1460] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[1461] Input: A list of possible dates and times

[1462] Data Processing: Generate a confirmation request

[1463] Output: Verification request sent to the terminal

[1464] Step 7:

[1465] User confirmation and final notification

[1466] The user confirms the date and time of the online consultation from their device and approves it.

[1467] Input: Verification request sent by the server

[1468] Data manipulation: Get user selection

[1469] Output: User verification data

[1470] The terminal transmits the confirmation result to the server.

[1471] Input: User verification data

[1472] Data processing: Check data integrity and convert to JSON format

[1473] Output: Converted JSON format confirmation data

[1474] The server notifies the specialist or nurse of the results of the confirmation and confirms the final schedule.

[1475] Input: Verification data sent from the terminal

[1476] Data processing: Generate data to inform experts

[1477] Output: Final schedule sent to the expert

[1478] The server transmits the final schedule information to the terminal and notifies the user again.

[1479] Input: Final schedule data

[1480] Data processing: Generate notification data for users

[1481] Output: Final schedule notification sent to device

[1482] (Application example 1)

[1483] 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."

[1484] Cancer patients and their families often find it difficult to obtain reliable medical information quickly and appropriately. Even when they need to consult with a specialist doctor or nurse, scheduling an appointment is often difficult. Furthermore, it is necessary to establish a method for providing similar support in brick-and-mortar stores.

[1485] 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.

[1486] In this invention, the server includes a terminal for cancer patients and their families to input questions, a means for receiving questions sent from the terminal and analyzing the questions using natural language processing, a generation AI means for generating answers to the analyzed questions based on the latest research and guidelines, a means for sending the generated answers to the terminal and displaying them, a means for accepting requests from users seeking specialist consultations, a means for checking the schedules of specialists and nurses and arranging consultation dates and times, a means for notifying the terminal of the arranged date and time, receiving confirmation from the user, and again notifying the specialist or nurse, a means for installing a terminal for accepting questions in a physical store, and a means for appropriately processing questions and requests from the terminal installed in the physical store. This allows patients and their families to instantly obtain reliable medical information and smoothly conduct online consultations with specialists. Similar services can also be provided in physical stores to improve convenience.

[1487] "Cancer patients and their families" refers to patients who have currently been diagnosed with cancer and their families who need information and care to support them.

[1488] "Terminal" refers to a device through which a user can enter questions and receive answers and notifications from the system, including smartphones, tablets, and PCs.

[1489] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1490] A "server" refers to a device that receives questions sent from a terminal, analyzes the questions using natural language processing, and works with a generation AI to generate answers.

[1491] "Generative AI" refers to artificial intelligence technology that automatically generates appropriate answers based on analyzed questions, citing the latest research and guidelines.

[1492] "Display means" refers to a method or technology for transmitting the generated answer to a terminal and displaying it in a format that is easy for the user to view.

[1493] The "means for accepting a request" refers to a method or device for allowing a user who desires professional consultation to input a request into the system.

[1494] "Means for checking schedules and arranging consultation dates and times" refers to methods and technologies for managing the schedule data of specialists and nurses, and selecting and arranging appropriate dates and times for online consultations.

[1495] "Means for receiving confirmation and notifying again" refers to the method or technology for receiving final confirmation from the user and notifying the specialist or nurse of the confirmation content.

[1496] "Store-based terminal" refers to a device located within a physical store that a customer uses to input a question or request a consultation with a specialist.

[1497] "Means for appropriately processing questions and requests" refers to the methods and technologies for receiving user input from terminals installed in physical stores and analyzing and processing it on the server.

[1498] "Medical information" refers to reliable information in the medical field based on the latest research data and guidelines.

[1499] A "specialist" refers to a medical professional with advanced knowledge and experience in a particular medical field.

[1500] "Online consultation" refers to real-time health consultation with a specialist doctor or nurse via the Internet.

[1501] This invention is a system that allows cancer patients and their families to quickly and appropriately obtain reliable medical information and smoothly conduct online consultations with specialized doctors and nurses. Similar services can also be provided in physical stores. A specific embodiment of this system is described below.

[1502] System Configuration

[1503] 1. Terminal

[1504] A device that allows users to input questions and receive answers from generative AI. Specifically, it includes smartphones, tablets, PCs, and kiosks installed in physical stores.

[1505] 2. Server

[1506] The server receives questions sent from the device and analyzes them using natural language processing, which then sends the analyzed questions to a generative AI that generates answers based on the latest research and guidelines.

[1507] 3. Generation AI

[1508] The generative AI automatically generates appropriate answers based on the analyzed questions received from the server, citing the latest research data and guidelines, using natural language generation models (e.g., the GPT series).

[1509] Hardware and Software

[1510] Natural Language Processing (NLP) toolkits: We use NLP tools such as spaCy and NLTK to analyze questions, which helps us identify the subject of the question and access the appropriate information.

[1511] Generative AI models: Use natural language generation models like the OpenAI GPT series to generate answers based on the latest research data.

[1512] RESTful API: To ensure that each component of the entire system works together, data is communicated between the server and the terminal via a RESTful API using Flask or Django REST framework.

[1513] Explanation with concrete examples

[1514] Here is a specific example of a "health consultation kiosk" installed in a physical drugstore. When a customer using this kiosk asks, "Which supplements are effective for diabetes?", the following actions are taken:

[1515] 1. The user enters a question into the kiosk terminal's touch panel.

[1516] 2. The terminal converts the entered question into an appropriate format and sends it to the server.

[1517] 3. The server uses natural language processing to analyze the question and identify keywords such as "diabetes" and "supplements."

[1518] 4. Based on the analysis results, the AI ​​generates an answer citing the latest research data and guidelines. In this case, the generated answer would be "Vitamin D and magnesium are effective in managing diabetes."

[1519] 5. The server sends the generated answer to the terminal and displays it to the user.

[1520] Examples of prompt statements

[1521] Below are some specific examples of prompt sentences to input into the generative AI model.

[1522] Prompt: "Which supplements are effective for diabetes?"

[1523] Generative AI model: “Certain vitamins and minerals have been shown to be effective in managing diabetes. Examples include vitamin D and magnesium.”

[1524] In this way, users can instantly obtain reliable medical information and smoothly consult with specialists online. Similar services can also be provided in physical stores, improving convenience.

[1525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1526] Step 1:

[1527] The user enters a question into the device's input screen, for example, "Which supplements are effective for diabetes?" The entered question is converted into an appropriate format for subsequent processing.

[1528] Step 2:

[1529] The device converts the question into a format and sends it to the server. This process uses an HTTP request, and the question is sent to the server in JSON format.

[1530] Step 3:

[1531] The server receives the question sent from the terminal. This input is a natural language question entered by the user. The received question is analyzed using a natural language processing (NLP) engine. Specifically, keywords (e.g., "diabetes" and "supplements") are extracted.

[1532] Step 4:

[1533] The server sends the analyzed results to a generative AI model, which uses this input to refer to the latest research data and guidelines to generate an appropriate answer to the question. For example, it may generate an answer such as, "Vitamin D and magnesium are effective in managing diabetes."

[1534] Step 5:

[1535] The server then sends the answer received from the generative AI model back to the device. At this stage, the generated answer is returned from the server to the device in JSON format.

[1536] Step 6:

[1537] The device displays the answer received from the server to the user. Specifically, the device screen displays the message, "Vitamin D and magnesium are effective in managing diabetes."

[1538] Step 7:

[1539] If the user wishes to further consult with a specialist online, he or she inputs a request from the terminal, for example, "I would like to speak to a specialist." This request is also sent to the server.

[1540] Step 8:

[1541] The server queries the schedule data of specialists and nurses to determine possible dates and times for online consultations. This coordination involves database access.

[1542] Step 9:

[1543] The server notifies the terminal of the arranged date and time of the online consultation, and this information is sent to the terminal in a format that can be confirmed by the user.

[1544] Step 10:

[1545] If the user confirms the presented date and time and approves it, the confirmation result is transmitted from the terminal to the server.

[1546] Step 11:

[1547] The server notifies the specialist or nurse of the user's confirmation results, including the arranged consultation date and time.

[1548] Step 12:

[1549] The server retransmits the final details of the online consultation to the terminal and prompts the user for final confirmation, after which the online consultation is officially scheduled.

[1550] The above are the specific processing steps of the system according to the present invention, which allows patients and their families to quickly obtain reliable medical information and smoothly consult with specialists online.

[1551] 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.

[1552] overview

[1553] This invention combines an emotion engine with an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is centered around a terminal, server, generative AI, and emotion engine, provides answers to users' questions based on the latest research and guidelines, and allows online consultations with specialized doctors and nurses as needed. It can also recognize users' emotions and provide tailored answers and support.

[1554] System Configuration

[1555] Terminal: A device on which users can input questions or requests for online consultations and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[1556] Server: Receives questions and requests sent from the device and analyzes the questions using natural language processing. It then passes the analyzed questions to a generation AI to generate answers. It also analyzes the user's emotions using an emotion engine.

[1557] Generative AI: Based on analyzed questions and requests received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[1558] Emotion Engine: Recognizes emotions from questions and requests entered by users and adjusts responses and notifications accordingly.

[1559] Program processing

[1560] 1. Enter and submit your question

[1561] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1562] The terminal converts the entered question into text format and sends it to the server.

[1563] 2. Receiving and analyzing questions

[1564] The server receives the query sent from the terminal.

[1565] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[1566] The server passes the analyzed question to the emotion engine to recognize the user's emotion.

[1567] 3. Emotional awareness and adaptation

[1568] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and tone of the question.

[1569] The server adjusts the content of the response and notification based on the results of the emotion engine.

[1570] 4. Answer Generation

[1571] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and an increased risk of infection. We understand your concerns, so please feel free to contact us.").

[1572] 5. Submitting and Viewing Your Answers

[1573] The server sends the generated response to the terminal.

[1574] The terminal displays the received response to the user.

[1575] 6. Online consultation requests and processing

[1576] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[1577] The terminal converts the request into text format and sends it to the server.

[1578] The server receives the request for online consultation and analyzes the user's urgency and emotions using an emotion engine.

[1579] The server accesses a database of specialists' and nurses' schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the request is given higher priority.

[1580] The server will notify the user of the suggested dates and times and ask for confirmation.

[1581] The user checks the date and time, and after approval, transmits it from the terminal to the server.

[1582] The server receives the confirmation and notifies the specialist or nurse.

[1583] The server sends the final details to the terminal and re-informs the user.

[1584] Specific examples

[1585] Basic Questions and Answers

[1586] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1587] 2. The device converts the question into a format and sends it to the server.

[1588] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[1589] 4. The emotion engine recognizes the emotion "anxiety" from the context of the question.

[1590] 5. The generative AI generates emotionally sensitive answers based on the latest side effects information about chemotherapy.

[1591] 6. The server sends the generated answer to the terminal and displays it to the user.

[1592] Request an online consultation

[1593] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[1594] 2. The device converts the request into a format and sends it to the server.

[1595] 3. The server receives the request and analyzes the user's urgency and emotion using the emotion engine.

[1596] 4. The server checks the specialist's schedule and prioritizes the date and time if the appointment is highly urgent.

[1597] 5. The server notifies the user of the date and time and asks for confirmation.

[1598] 6. Once the user confirms and approves the date and time, it is sent from the device to the server.

[1599] 7. The server notifies the specialist of the confirmation and resends the final details to the terminal.

[1600] This system allows cancer patients and their families to receive appropriate information and support that is sensitive to their emotions, allowing them to approach treatment with peace of mind.

[1601] The processing flow will be explained below.

[1602] Basic question and answer process flow

[1603] Step 1:

[1604] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1605] Step 2:

[1606] The terminal converts the entered question into text format and sends it to the server in the appropriate format.

[1607] Step 3:

[1608] The server receives the query sent from the terminal.

[1609] Step 4:

[1610] The server uses a natural language processing (NLP) module to analyze the received question and identify key keywords (e.g., "chemotherapy" and "side effects").

[1611] Step 5:

[1612] The server passes the analysis results to the emotion engine, which recognizes the user's emotions.

[1613] Step 6:

[1614] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and wording of the question.

[1615] Step 7:

[1616] The server receives the results of the emotion engine and includes the emotion information in the request to the generation AI.

[1617] Step 8:

[1618] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection. We understand that you are concerned, but these symptoms are common. Please let us know if there are any other concerns you have.").

[1619] Step 9:

[1620] The generation AI sends the generated answer to the server.

[1621] Step 10:

[1622] The server sends the generated response to the terminal.

[1623] Step 11:

[1624] The terminal displays the answer to the user.

[1625] Online consultation request processing flow

[1626] Step 1:

[1627] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[1628] Step 2:

[1629] The terminal converts the input request into text format and transmits it to the server in the appropriate format.

[1630] Step 3:

[1631] The server receives a request for online consultation sent from the terminal.

[1632] Step 4:

[1633] The server uses an emotion engine to recognize the emotion contained in the user's request (e.g., anxiety with high urgency).

[1634] Step 5:

[1635] The server accesses a database of specialist and nurse schedules to check available time slots.

[1636] Step 6:

[1637] Based on the analysis results of the emotion engine, the server determines the urgency of the online consultation and changes the priority of schedule adjustments as necessary.

[1638] Step 7:

[1639] The server selects candidate dates and times and determines the date and time for the online consultation.

[1640] Step 8:

[1641] The server notifies the terminal of the determined date and time of the online consultation.

[1642] Step 9:

[1643] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[1644] Step 10:

[1645] The user confirms the date and time of the online consultation through the terminal and approves it.

[1646] Step 11:

[1647] The terminal transmits the confirmation result to the server.

[1648] Step 12:

[1649] The server notifies the specialist or nurse of the confirmation results.

[1650] Step 13:

[1651] The server sends a final confirmation to the terminal and notifies the user again.

[1652] In this way, the system can provide appropriate information and support in response to users' questions and requests while taking their emotions into consideration, enabling smooth two-way communication.

[1653] Example 2

[1654] 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."

[1655] Currently, it is not easy for cancer patients and their families to obtain reliable medical information. While online consultation systems exist, they often do not provide appropriate responses that take into consideration the patient's feelings. As a result, patients often undergo treatment while feeling anxious and worried, placing a heavy psychological burden on them. Furthermore, there is a problem in that they are unable to respond appropriately to urgent consultation requests, making it difficult to fully meet the needs of patients.

[1656] 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.

[1657] In this invention, the server includes a means for receiving questions sent from a terminal and analyzing the questions using natural language processing; an automatic response generation device for generating answers to the analyzed questions based on the latest research and guidelines; and an emotion analysis device for recognizing the user's emotions and adapting the answers and notification content based on the recognized emotions. This not only enables patients and their families to obtain reliable medical information, but also enables responses that take emotions into consideration. Furthermore, since highly urgent requests can be responded to quickly and appropriately, the psychological burden on patients is reduced, allowing them to receive treatment with peace of mind.

[1658] A "terminal" is a device through which a user inputs questions or requests for online consultations and receives responses or notifications from the system.

[1659] An "information processing device" is a device that receives a question sent from a terminal and analyzes the question using natural language processing.

[1660] An "automatic response generator" is a device that generates answers to analyzed questions based on the latest research and guidelines.

[1661] An "emotion analysis device" is a device that recognizes a user's emotions and adjusts responses and notification content based on the recognized emotions.

[1662] "Online consultation request" is a request input by the user to request an online consultation with a specialist doctor or nurse.

[1663] The "schedule adjustment method" is a system that checks the schedules of specialists and nurses and determines the date and time of online consultations.

[1664] "Urgency" is an index that indicates the importance or urgency of a user's request.

[1665] "Natural language processing" is a technology for analyzing user questions and understanding important keywords and context.

[1666] A "generative AI model" is an artificial intelligence that generates appropriate answers from analyzed questions and sentiment analysis results based on the latest research and guidelines.

[1667] A "prompt" is a textual representation of a question or request that is input to a generative AI model.

[1668] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information, and also combines it with emotion analysis functions. The system is mainly composed of a terminal, an information processing device, an automatic response generation device, and an emotion analysis device, and provides users with prompt and appropriate information.

[1669] overview

[1670] The basic configuration of the invention is as follows:

[1671] 1. Terminal: A device on which users can enter questions or requests for online consultations and receive answers and notifications from the system. It can be a smartphone, tablet, or PC.

[1672] 2. Information processing device: Receives questions sent from the device and analyzes them using natural language processing (NLP), for example, using libraries such as spaCy or NLTK.

[1673] 3. Automatic response generator: Receives analyzed questions from an information processing device and uses a generative AI model to generate answers based on the latest research and guidelines. Databases such as PubMed can be used for reference.

[1674] 4. Emotion analyzer: This function analyzes the user's input and recognizes emotions (e.g., anxiety, worry). Emotion analysis is performed using IBM Watson Tone Analyzer, etc.

[1675] The main features of the system are:

[1676] 1. Enter and submit your question

[1677] Users use a terminal to enter a question in text format, such as "What are the side effects of chemotherapy?"

[1678] The terminal converts the entered question into an appropriate format and sends it to the server.

[1679] 2. Receiving and analyzing questions

[1680] The server receives the query sent from the terminal.

[1681] The server uses a natural language processing module to analyze the question and identify important keywords.

[1682] After analysis, the question data is passed to an emotion analyzer to recognize the user's emotion.

[1683] 3. Emotional awareness and adaptation

[1684] The emotion analyzer recognizes the user's emotions and returns the results to the server.

[1685] The server adjusts the response content based on the results of the emotion analysis.

[1686] 4. Answer Generation

[1687] The generative AI model uses the parsed question and sentiment analysis results to generate appropriate answers.

[1688] The generated answer is sent to the terminal via the server.

[1689] 5. View Answers

[1690] The terminal displays the received response to the user.

[1691] 6. Online consultation requests and processing

[1692] If the user wishes to have an online consultation with a specialist, they enter a request.

[1693] The device sends a request to the server, which checks the specialist's schedule and adjusts the priority according to the urgency.

[1694] The confirmed consultation date and time is notified to the user and the specialist.

[1695] Specific examples

[1696] When a user types a question such as "I'm anxious about the treatment I'm currently receiving," the device converts it into text format and sends it to the server. The server uses natural language processing to identify keywords such as "treatment" and "anxiety," and passes these to the emotion analyzer. The emotion analyzer recognizes the emotion "anxiety" and passes the results to the generative AI model. The generative AI model generates an answer based on the latest research data, such as "It's common to feel anxious about treatment. If you could tell us your story, we'll respond appropriately."

[1697] Prompt Sentence Examples

[1698] "Tell us about common side effects of chemotherapy and be mindful of any concerns users may have."

[1699] This system not only allows cancer patients and their families to obtain reliable medical information, but also provides emotionally sensitive care, allowing them to undergo treatment with peace of mind.

[1700] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1701] Step 1:

[1702] The user types a question into the terminal.

[1703] Input: The user types the question, "What are the side effects of chemotherapy?"

[1704] Action: The action of entering text into a device input field.

[1705] Output: The input text data.

[1706] Step 2:

[1707] The terminal converts the entered question into the appropriate format.

[1708] Input: The text data entered in step 1.

[1709] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[1710] Output: Formatted text data.

[1711] Step 3:

[1712] The device sends a formatted text question to the server.

[1713] Input: The formatted text data from step 2.

[1714] What it does: Sends data to a server via an HTTP request.

[1715] Output: Request data to the server.

[1716] Step 4:

[1717] The server receives the question sent from the terminal.

[1718] Input: The request data sent in step 3.

[1719] How it works: The API endpoint receives request data.

[1720] Output: The received query data.

[1721] Step 5:

[1722] The server parses the question using a natural language processing (NLP) module.

[1723] Input: The question data received in step 4.

[1724] How it works: Analyzes text using NLP techniques (e.g. spaCy) to extract important keywords.

[1725] Output: Extracted keyword data (e.g., "chemotherapy" and "side effects").

[1726] Step 6:

[1727] The server passes the analysis results to the emotion analysis device.

[1728] Input: Keyword data extracted in step 5.

[1729] What it does: Converts NLP results into JSON format and sends them to the sentiment analyzer.

[1730] Output: Request data to the sentiment analyzer.

[1731] Step 7:

[1732] The emotion analyzer recognizes the user's emotions from the context and tone of the question.

[1733] Input: The request data sent in step 6.

[1734] How it works: Identifies emotions using emotion analysis technology (e.g., IBM Watson Tone Analyzer).

[1735] Output: Recognized emotion data (e.g., "anxiety").

[1736] Step 8:

[1737] The server receives the sentiment analysis results.

[1738] Input: Emotion data obtained in step 7.

[1739] What it does: Receives emotion data and prepares it for use in adjusting responses.

[1740] Output: Emotion data ready for conditioning.

[1741] Step 9:

[1742] The server passes the analyzed question and sentiment analysis results to the generated AI model.

[1743] Input: Keyword data extracted in step 5 and sentiment data obtained in step 8.

[1744] How it works: The question and emotion data are input as prompts to the generative AI.

[1745] Output: Prompt data to the generative AI model.

[1746] Step 10:

[1747] The generative AI model generates answers by referencing the latest research databases and guidelines.

[1748] Input: Prompt data from step 9.

[1749] What it does: Consults up-to-date research databases (e.g., PubMed) and generates relevant answers.

[1750] Output: The generated response data.

[1751] Step 11:

[1752] The server sends the answer received from the generation AI to the terminal.

[1753] Input: The response data generated in step 10.

[1754] What it does: Sends data to the device via an HTTP response.

[1755] Output: Response data to the device.

[1756] Step 12:

[1757] The terminal displays the received answer to the user.

[1758] Input: The response data sent in step 11.

[1759] What it does: Displays textual responses via a GUI.

[1760] Output: The answer data displayed to the user.

[1761] Step 13:

[1762] If the user wishes to have an online consultation with a specialist, they enter a request.

[1763] Input: User types "I would like to speak to a specialist."

[1764] Action: The action of entering text into a device input field.

[1765] Output: The input request data.

[1766] Step 14:

[1767] The device converts the request into an appropriate format and sends it to the server.

[1768] Input: The request data entered in step 13.

[1769] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[1770] Output: The formatted request data.

[1771] Step 15:

[1772] The server receives the online consultation request and analyzes the urgency and emotion of the user with an emotion analyzer.

[1773] Input: The request data sent in step 14.

[1774] How it works: It uses NLP techniques and sentiment analyzers to analyze text and identify sentiment and urgency.

[1775] Output: Extracted urgency and sentiment data.

[1776] Step 16:

[1777] The server accesses a database of specialist and nurse schedules to check available time slots.

[1778] Input: Urgency data identified in Step 15.

[1779] What it does: Runs a database query to find and identify free time.

[1780] Output: Data on available time slots.

[1781] Step 17:

[1782] If the server is in a high emergency state, the date and time are set with priority.

[1783] Input: The open time slot data identified in step 16.

[1784] What it does: Prioritize and optimize dates and times based on urgency.

[1785] Output: Date and time data of the online consultation that was set.

[1786] Step 18:

[1787] The server notifies the user of the set date and time and asks for confirmation.

[1788] Input: Date and time data set in step 17.

[1789] Behavior: Generates a confirmation message and sends it to the device as an HTTP response.

[1790] Output: Acknowledgement data to the user.

[1791] Step 19:

[1792] Once the user confirms and approves the date and time, it is sent from the device to the server.

[1793] Input: Acknowledgment data sent in step 18.

[1794] Action: The user sees the notification and clicks the confirm / agree button.

[1795] Output: Confirmation and acceptance data.

[1796] Step 20:

[1797] The server notifies the specialist or nurse of the confirmation.

[1798] Input: Confirmation and acknowledgement data sent in step 19.

[1799] What it does: Generates and sends a message to notify specialists and nurses of the results of the check.

[1800] Output: Data for notifying specialists and nurses.

[1801] Step 21:

[1802] The server sends the final details to the terminal and re-informs the user.

[1803] Input: Specialist and nurse notification data sent in step 20.

[1804] Behavior: A message containing the confirmed date and time and details is generated and sent to the device as an HTTP response.

[1805] Output: Final notification data to the user.

[1806] (Application example 2)

[1807] 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."

[1808] Currently, cancer patients and their families have limited access to reliable medical information, and there is a particular lack of information provision that takes into consideration the user's emotions. For example, there is a lack of means to provide appropriate information and support to users who are feeling anxious or worried. Furthermore, there is a lack of mechanisms for appropriately adjusting online consultations with specialists based on the level of urgency and emotions. This presents a challenge for users, making it difficult to receive the information and support they need in a timely manner.

[1809] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1810] In this invention, the server includes means for receiving questions or requests entered by users and analyzing them using natural language processing, means for using generative artificial intelligence to generate answers based on the analyzed questions and the latest research and guidelines, and means for using an emotion engine to analyze the user's emotions and adjust the content of the answers based on the analysis results, thereby making it possible to provide answers and support that take into consideration the user's emotions as well as reliable medical information.

[1811] A "terminal" is a device through which a user can input questions or requests for online consultations and receive responses and notifications from the system.

[1812] The "server" is a central computer system that receives questions and requests sent from devices, analyzes them using natural language processing, and works with generative AI and emotion engines to generate answers and support.

[1813] "Natural language processing" is a computer science technique for analyzing text data and understanding its meaning.

[1814] "Generative AI" is an AI technology that automatically generates appropriate answers based on the latest research and guidelines, based on analyzed questions and requests.

[1815] The "emotion engine" is a technology that recognizes emotions from the text entered by the user and appropriately adjusts the response content and notifications based on the analysis results.

[1816] "Online consultation" is a consultation format that allows users to directly interact with experts via the Internet.

[1817] "Schedule adjustment" refers to the process of checking the specialist's schedule, selecting an available time slot, and deciding on the date and time of the consultation.

[1818] A "generative AI model" is a type of artificial intelligence used to analyze questions or requests and generate new answers.

[1819] A "prompt" is textual data that is input to a generative AI model and contains hints and instructions that help the model generate an answer.

[1820] This invention combines an emotion engine with an online consulting system that provides reliable medical information for cancer patients and their families. Each component is described in detail below.

[1821] System Configuration

[1822] 1. Terminal

[1823] The terminal is a device that allows users to input questions or requests for online consultations and receive replies and notifications from the system. Terminals can be smartphones, tablets, PCs, etc.

[1824] 2. Server

[1825] The server receives questions and requests sent from the device and analyzes the questions using natural language processing (NLP). The analyzed questions are used to generate answers through generative AI and an emotion engine. The server then sends the answers generated based on the analysis results to the device and displays them.

[1826] 3. Natural Language Processing

[1827] Natural language processing is a computer science technique used to analyze text data and understand its meaning. Specifically, it extracts important keywords from input questions and matches them with relevant medical databases and guidelines.

[1828] 4. Generative Artificial Intelligence

[1829] Generative AI (generative AI) generates appropriate answers based on analyzed questions received from the server, citing the latest research and guidelines. For example, OpenAI's GPT-4 is used as a generative AI.

[1830] 5. Emotion Engine

[1831] The emotion engine recognizes emotions from questions and requests entered by users and adjusts responses and notification content appropriately based on the recognized emotions. The emotion engine uses emotion analysis tools such as AWS Comprehend.

[1832] Program processing

[1833] The server receives questions sent from the device and analyzes them using natural language processing. The analyzed questions are then analyzed for user emotion through an emotion engine, and the results are passed on to a generation AI to generate an answer. The generated answer is then returned to the server and sent to the device.

[1834] This process involves the following hardware and software:

[1835] Hardware: smartphones, tablets, PCs, servers

[1836] Software: Natural language processing libraries (e.g., spaCy, NLTK), sentiment analysis tools (e.g., AWS Comprehend, TextBlob), generative AI (e.g., OpenAI GPT-4)

[1837] Specific examples

[1838] Specific examples of questions and answers

[1839] The user types the question "What are the side effects of chemotherapy?" into their smartphone. This question is sent to the server and analyzed through a natural language processing module and an emotion engine. Based on the analysis results, the generative AI generates the following answer: "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us." This answer is then sent back to the server and displayed on the device.

[1840] Specific examples of online consultation requests

[1841] The user inputs a request saying, "I want to talk to a specialist." This request is sent to the server, where the emotion engine analyzes the urgency and emotion. Based on the analysis results, the specialist's schedule is checked, and if the urgency is high, a date and time is set as a priority. The date and time are then notified to the user, and once the user confirms and agrees, the specialist is notified.

[1842] Prompt Sentence Examples

[1843] "Tell me about the side effects of chemotherapy. I'm worried."

[1844] This will ensure that cancer patients and their families receive timely, appropriate, and emotionally sensitive information and support.

[1845] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1846] Step 1: User enters question

[1847] The user inputs a question into a device (smartphone, tablet, PC, etc.) such as "What are the side effects of chemotherapy?" The input question is converted into text format on the device.

[1848] Step 2: The device sends the question to the server

[1849] The device sends the converted question to the server via an HTTP POST request, using JSON as the data format.

[1850] Step 3: The server receives and parses the query

[1851] The server receives the question sent from the device and uses a natural language processing (NLP) module (e.g., spaCy) to analyze the question and identify important keywords (e.g., "chemotherapy" and "side effects").

[1852] Step 4: The server analyzes the emotion using the emotion engine

[1853] The server passes the parsed question to an emotion engine (e.g., AWS Comprehend) to recognize the user's emotion (e.g., anxiety, worry). The emotion analysis results are returned in JSON format and stored on the server.

[1854] Step 5: The server passes the question and emotion data to the generation AI.

[1855] The server passes the analysis results and emotion data to a generative AI (e.g., OpenAI GPT-4), which then inputs a prompt into the generative AI model that generates an answer to the question. Example prompt: "Tell me about the side effects of chemotherapy. I'm feeling anxious."

[1856] Step 6: Generative AI generates an answer

[1857] Based on the given prompt, the generative AI refers to the latest research databases and guidelines to generate an appropriate answer. For example, it might generate an answer such as, "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us."

[1858] Step 7: The server sends the response to the device

[1859] The generated answer is sent back to the server, which then sends it to the device in JSON format. The answer data may also include the results of sentiment analysis.

[1860] Step 8: The device displays the answer to the user

[1861] The device analyzes the received responses and displays them to the user, allowing the user to obtain appropriate information about chemotherapy side effects.

[1862] Step 9: User requests an online consultation

[1863] If the user wishes to further consult with a specialist, the user inputs a request "I would like to speak to a specialist" from the terminal.

[1864] Step 10: The device sends a request to the server

[1865] The terminal converts the request into text format and sends it to the server as an HTTP POST request.

[1866] Step 11: The server receives and parses the request

[1867] The server receives the request and again analyzes the user's urgency and emotion using natural language processing and an emotion engine. Based on the analysis results, it determines the priority of the user's request.

[1868] Step 12: The server checks the specialist's schedule and sets the date and time.

[1869] The server accesses a database of specialist schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the call is prioritized.

[1870] Step 13: The server notifies the user of the candidate dates and times and asks for confirmation.

[1871] The server sends the proposed date and time in JSON format to the device and asks for confirmation from the user. The user checks the displayed date and time and selects the desired time slot.

[1872] Step 14: User checks the date and time and sends it to the server

[1873] Once the user confirms and approves the date and time, the information is sent to the server in JSON format.

[1874] Step 15: Server notifies specialist and resends final details to terminal

[1875] The server receives confirmation and notifies the specialist, and the final details are sent back to the terminal and notified to the user.

[1876] This series of processes enables cancer patients and their families to obtain reliable medical information in real time and smoothly consult with specialists online.

[1877] 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.

[1878] 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.

[1879] 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.

[1880] [Fourth embodiment]

[1881] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1882] 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.

[1883] 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).

[1884] 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.

[1885] 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.

[1886] 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).

[1887] 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.

[1888] 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.

[1889] 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.

[1890] 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.

[1891] 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.

[1892] 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.

[1893] 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."

[1894] overview

[1895] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is composed mainly of terminals, servers, and generation AI, provides answers to users' questions based on the latest research and guidelines, and also allows online consultations with specialized doctors and nurses as needed.

[1896] System Configuration

[1897] Terminal: A device on which users can input questions and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[1898] Server: Receives questions sent from the device, analyzes the questions, and generates answers in cooperation with the generation AI. It is also responsible for scheduling and notifying online consultations.

[1899] Generative AI: Based on analyzed questions received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[1900] Program processing

[1901] 1. Enter and submit your question

[1902] The user types their question (e.g., "What are the side effects of chemotherapy?") into the terminal.

[1903] The terminal converts the entered question into an appropriate format and sends it to the server.

[1904] 2. Receiving and analyzing questions

[1905] The server receives the query sent from the terminal.

[1906] The server uses natural language processing (NLP) techniques to analyze the question and identify the subject matter (e.g., "chemotherapy" and "side effects").

[1907] 3. Generate answers

[1908] The server sends the parsed question to the generation AI.

[1909] The generative AI generates answers to questions based on the latest research databases and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.") and sends them to a server.

[1910] 4. Providing answers

[1911] The server sends the generated response to the terminal.

[1912] The terminal displays the answer to the user.

[1913] 5. Request an online consultation

[1914] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[1915] The terminal converts the request into an appropriate format and sends it to the server.

[1916] 6. Scheduling online consultations

[1917] The server accesses a database of specialist and nurse schedules to select possible dates and times.

[1918] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[1919] 7. Confirmation and Final Notice

[1920] The user confirms the date and time of the online consultation from their device and approves it.

[1921] The terminal sends the confirmation results to the server, which then notifies the specialist or nurse.

[1922] The server sends a final confirmation to the terminal and notifies the user again.

[1923] Specific examples

[1924] Basic Questions and Answers

[1925] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1926] 2. The device converts the question into a format and sends it to the server.

[1927] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[1928] 4. The generative AI generates answers based on the latest side effects information for chemotherapy.

[1929] 5. The server sends the generated answer to the terminal and displays it to the user.

[1930] Request an online consultation

[1931] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[1932] 2. The device converts the request into a format and sends it to the server.

[1933] 3. The server checks the specialist's schedule and selects an available date and time.

[1934] 4. The server sends the selection results to the terminal and notifies the user.

[1935] 5. Once the user confirms and approves the date and time, it is sent from the device to the server.

[1936] 6. The server notifies the specialist of the results of the check and resends the final details to the terminal.

[1937] Through this series of processes, we can provide support to cancer patients and their families so that they can approach treatment with peace of mind.

[1938] The processing flow will be explained below.

[1939] Basic question and answer process flow

[1940] Step 1:

[1941] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[1942] Step 2:

[1943] The terminal converts the entered question into text format and sends it to the server.

[1944] Step 3:

[1945] The server receives a query from the terminal.

[1946] Step 4:

[1947] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[1948] Step 5:

[1949] Based on the analysis results, the server generates a request to the generation AI.

[1950] Step 6:

[1951] The generative AI references the latest research databases and guidelines to generate appropriate answers to questions (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections.").

[1952] Step 7:

[1953] The generation AI sends the generated answer to the server.

[1954] Step 8:

[1955] The server sends the generated response to the terminal.

[1956] Step 9:

[1957] The terminal displays the received response to the user.

[1958] Online consultation request processing flow

[1959] Step 1:

[1960] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[1961] Step 2:

[1962] The terminal converts the input request into text format and sends it to the server.

[1963] Step 3:

[1964] The server receives a request for online consultation from the terminal.

[1965] Step 4:

[1966] The server accesses a database of specialist and nurse schedules to check available time slots.

[1967] Step 5:

[1968] The server selects candidate dates and times and determines the date and time for the online consultation.

[1969] Step 6:

[1970] The server notifies the terminal of the determined online consultation date and time.

[1971] Step 7:

[1972] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[1973] Step 8:

[1974] The user confirms the date and time of the online consultation through the terminal and approves it.

[1975] Step 9:

[1976] The terminal transmits the user's confirmation result to the server.

[1977] Step 10:

[1978] The server notifies the specialist or nurse of the approval result.

[1979] Step 11:

[1980] The server sends a final confirmation to the terminal and notifies the user again.

[1981] In this way, the system as a whole executes each processing step in detail to facilitate two-way communication between the user and the medical professional.

[1982] Example 1

[1983] 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."

[1984] There is a need for an environment where cancer patients and their families can quickly and appropriately obtain reliable medical information. However, currently, providing appropriate information requires referencing numerous specialized materials, which places a significant burden on patients. Furthermore, there is a lack of efficient scheduling methods for patients who wish to consult online with specialists or nurses. To solve these problems, it is necessary to use advanced technology to automate the information and consultation procedures and provide them quickly and accurately.

[1985] 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.

[1986] In this invention, the server includes a terminal for a user to input a question, means for receiving the question sent from the terminal and analyzing the question using natural language processing, artificial intelligence for generating an answer to the analyzed question based on the latest research and guidelines, means for transmitting the generated answer to the terminal and displaying it, means for receiving the user's request for online consultation and adjusting the specialist's schedule to determine the date and time of the online consultation, means for notifying the terminal of the determined date and time and receiving confirmation from the user, and means for notifying the specialist of the confirmation result and re-notifying the terminal of details of the online consultation. This enables cancer patients and their families to quickly and accurately obtain the medical information they need and to have efficient online consultations with specialists and nurses.

[1987] "Users" refer to cancer patients and their families who use the system.

[1988] "Device" refers to the device used by a user to enter questions and receive responses and notifications from the system, such as a smartphone, tablet, or PC.

[1989] The "server" refers to a computer system that receives and analyzes questions sent from the device, works with the generation AI to generate answers, and is also responsible for scheduling and notifying online consultations.

[1990] "Natural language processing" refers to computer techniques for analyzing natural language questions entered by users to identify their subject matter and intent. Examples include tokenization, part-of-speech tagging, and named entity recognition.

[1991] "Artificial intelligence" refers to technology that generates answers based on the latest research and guidelines, based on analyzed questions received from a server. In a broad sense, it includes machine learning and deep learning.

[1992] "Online consultation" refers to a consultation a user has with a specialist or nurse via the internet, including requests, scheduling, and notifications.

[1993] "Generative AI" is a form of artificial intelligence, specifically referring to algorithms and models that automatically generate appropriate answers to user questions.

[1994] "Schedule adjustment" refers to the process of receiving a user's request for online consultation and determining the date and time of the consultation according to the availability of the expert.

[1995] "Notification" refers to the system's act of conveying information or confirmation to users or experts, such as informing them of the date and time of an online consultation or the content of the response.

[1996] overview

[1997] This invention is an online consulting system that enables cancer patients and their families to quickly and appropriately obtain reliable medical information. The system uses terminals, a server, and a generative AI to automatically generate answers to users' questions and support online consultations with specialist doctors and nurses.

[1998] System Configuration

[1999] Terminal

[2000] This is a device that allows users to input questions and receive answers and notifications from the system. A variety of devices, including smartphones, tablets, and PCs, can be used as terminals. The system can be accessed through a dedicated application or a web browser.

[2001] server

[2002] The server has the following main functions:

[2003] 1. Receiving and parsing questions: Receive questions sent from the device and parse them using natural language processing (NLP) techniques. NLP libraries used include NLTK and spaCy.

[2004] 2. Collaboration with Generative AI: The analyzed question is sent to Generative AI, which then generates an appropriate answer. Generative AI then refers to the latest research databases and guidelines (e.g., PubMed, NCCN guidelines).

[2005] 3. Online consultation scheduling: Upon receiving a user request for an online consultation, the system accesses the specialist or nurse's schedule database (e.g., Google Calendar API) to determine the consultation date and time, and notifies the user or specialist.

[2006] Generation AI

[2007] Generative AI automatically generates answers based on the latest research and guidelines, based on analyzed questions received from the server, using trained machine learning models to extract information from relevant databases to create answers.

[2008] Specific operation example

[2009] User-entered questions

[2010] The user opens a dedicated application or web browser and enters their question (e.g., "What are the side effects of chemotherapy?"). The entered question is converted into an appropriate format (e.g., JSON format) and sent to the server.

[2011] Server parsing of the question

[2012] The server receives the question sent from the device and analyzes it using NLP technology to identify the topic of the question (e.g., "chemotherapy" or "side effects").

[2013] Generative AI generates answers

[2014] The server sends the analyzed question to the generation AI, which generates an appropriate answer based on the latest research database and guidelines (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infections."). The generated answer is then sent back to the server.

[2015] Show Answers

[2016] The server sends the generated answer to the terminal, which displays the answer to the user and notifies them using a notification function if necessary.

[2017] Request an online consultation

[2018] When a user wishes to have an online consultation with a specialist, they input a request from their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist.") The request is converted into an appropriate format and sent to the server.

[2019] Server-based scheduling

[2020] The server accesses the schedule database of specialists and nurses to select available dates and times. The selection results are sent to the terminal and the user is asked to confirm. Once the user confirms and agrees with the date and time, the confirmation results are sent to the server, which notifies the specialist and resends the final schedule to the terminal.

[2021] In this way, cancer patients and their families can quickly and accurately obtain the medical information they need, enabling efficient online consultations.

[2022] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2023] Step 1:

[2024] User-entered questions

[2025] Users open a dedicated application or web browser and enter their question (e.g., "What are the side effects of chemotherapy?").

[2026] The terminal converts the entered question into an appropriate format (e.g., JSON format).

[2027] Input: A text question entered by the user

[2028] Data processing: Convert text data into JSON format

[2029] Output: Converted JSON format question data

[2030] The device sends the generated question data in JSON format to the server.

[2031] Step 2:

[2032] The server receives and analyzes the query

[2033] The server receives the query sent from the terminal.

[2034] Input: JSON-formatted question data sent from the terminal

[2035] Data processing: JSON data analysis, data consistency check

[2036] Output: Parsed question data

[2037] The server uses natural language processing (NLP) techniques to analyze the question.

[2038] NLP libraries used include NLTK and spaCy.

[2039] Input: Question data in JSON format

[2040] Data operations: tokenization, part-of-speech tagging, named entity recognition

[2041] Output: The subject and keywords of the parsed question (e.g., "chemotherapy" and "side effects")

[2042] Step 3:

[2043] Generative AI generates answers

[2044] The server sends the parsed question to the generation AI.

[2045] Input: Parsed question data

[2046] Data processing: Converting data into a format that can be understood by generative AI

[2047] Output: Data sent to the generative AI

[2048] Generative AI generates appropriate answers based on the latest research databases and guidelines.

[2049] Databases used include PubMed and NCCN guidelines.

[2050] Input: Parsed question data

[2051] Data Computing: Find the latest research information for your questions and generate answers, including citations

[2052] Output: Generated answer (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection.")

[2053] The generated answer is sent back to the server.

[2054] Step 4:

[2055] Server provides answer

[2056] The server sends the generated response to the terminal.

[2057] Input: Answer data sent from the generation AI

[2058] Data processing: Convert response data into JSON format

[2059] Output: Converted JSON format response data

[2060] The terminal displays the answer to the user and notifies the user using a notification function if necessary.

[2061] Input: JSON format response data sent from the server

[2062] Data processing: Parsing JSON data and converting it into a format suitable for the user interface

[2063] Output: The answer displayed in the user interface

[2064] Step 5:

[2065] User requests for online consultation

[2066] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[2067] The device converts the request into an appropriate format (e.g., JSON).

[2068] Input: A textual request entered by the user.

[2069] Data processing: Convert text data into JSON format

[2070] Output: The converted JSON format request data

[2071] The terminal sends the generated request data in JSON format to the server.

[2072] Step 6:

[2073] Server-based scheduling of online consultations

[2074] The server accesses a database of specialist and nurse schedules to select available dates and times.

[2075] The schedule database used is the Google Calendar API.

[2076] Input: Request data sent from the terminal

[2077] Data calculation: Access to schedule database, search and obtain available time slots

[2078] Output: A list of candidate dates and times

[2079] The server notifies the terminal of the date and time of the online consultation and requests the user's confirmation.

[2080] Input: A list of possible dates and times

[2081] Data Processing: Generate a confirmation request

[2082] Output: Verification request sent to the terminal

[2083] Step 7:

[2084] User confirmation and final notification

[2085] The user confirms the date and time of the online consultation from their device and approves it.

[2086] Input: Verification request sent by the server

[2087] Data manipulation: Get user selection

[2088] Output: User verification data

[2089] The terminal transmits the confirmation result to the server.

[2090] Input: User verification data

[2091] Data processing: Check data integrity and convert to JSON format

[2092] Output: Converted JSON format confirmation data

[2093] The server notifies the specialist or nurse of the results of the confirmation and confirms the final schedule.

[2094] Input: Verification data sent from the terminal

[2095] Data processing: Generate data to inform experts

[2096] Output: Final schedule sent to the expert

[2097] The server transmits the final schedule information to the terminal and notifies the user again.

[2098] Input: Final schedule data

[2099] Data processing: Generate notification data for users

[2100] Output: Final schedule notification sent to device

[2101] (Application example 1)

[2102] 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."

[2103] Cancer patients and their families often find it difficult to obtain reliable medical information quickly and appropriately. Even when they need to consult with a specialist doctor or nurse, scheduling an appointment is often difficult. Furthermore, it is necessary to establish a method for providing similar support in brick-and-mortar stores.

[2104] 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.

[2105] In this invention, the server includes a terminal for cancer patients and their families to input questions, a means for receiving questions sent from the terminal and analyzing the questions using natural language processing, a generation AI means for generating answers to the analyzed questions based on the latest research and guidelines, a means for sending the generated answers to the terminal and displaying them, a means for accepting requests from users seeking specialist consultations, a means for checking the schedules of specialists and nurses and arranging consultation dates and times, a means for notifying the terminal of the arranged date and time, receiving confirmation from the user, and again notifying the specialist or nurse, a means for installing a terminal for accepting questions in a physical store, and a means for appropriately processing questions and requests from the terminal installed in the physical store. This allows patients and their families to instantly obtain reliable medical information and smoothly conduct online consultations with specialists. Similar services can also be provided in physical stores to improve convenience.

[2106] "Cancer patients and their families" refers to patients who have currently been diagnosed with cancer and their families who need information and care to support them.

[2107] "Terminal" refers to a device through which a user can enter questions and receive answers and notifications from the system, including smartphones, tablets, and PCs.

[2108] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[2109] A "server" refers to a device that receives questions sent from a terminal, analyzes the questions using natural language processing, and works with a generation AI to generate answers.

[2110] "Generative AI" refers to artificial intelligence technology that automatically generates appropriate answers based on analyzed questions, citing the latest research and guidelines.

[2111] "Display means" refers to a method or technology for transmitting the generated answer to a terminal and displaying it in a format that is easy for the user to view.

[2112] The "means for accepting a request" refers to a method or device for allowing a user who desires professional consultation to input a request into the system.

[2113] "Means for checking schedules and arranging consultation dates and times" refers to methods and technologies for managing the schedule data of specialists and nurses, and selecting and arranging appropriate dates and times for online consultations.

[2114] "Means for receiving confirmation and notifying again" refers to the method or technology for receiving final confirmation from the user and notifying the specialist or nurse of the confirmation content.

[2115] "Store-based terminal" refers to a device located within a physical store that a customer uses to input a question or request a consultation with a specialist.

[2116] "Means for appropriately processing questions and requests" refers to the methods and technologies for receiving user input from terminals installed in physical stores and analyzing and processing it on the server.

[2117] "Medical information" refers to reliable information in the medical field based on the latest research data and guidelines.

[2118] A "specialist" refers to a medical professional with advanced knowledge and experience in a particular medical field.

[2119] "Online consultation" refers to real-time health consultation with a specialist doctor or nurse via the Internet.

[2120] This invention is a system that allows cancer patients and their families to quickly and appropriately obtain reliable medical information and smoothly conduct online consultations with specialized doctors and nurses. Similar services can also be provided in physical stores. A specific embodiment of this system is described below.

[2121] System Configuration

[2122] 1. Terminal

[2123] A device that allows users to input questions and receive answers from generative AI. Specifically, it includes smartphones, tablets, PCs, and kiosks installed in physical stores.

[2124] 2. Server

[2125] The server receives questions sent from the device and analyzes them using natural language processing, which then sends the analyzed questions to a generative AI that generates answers based on the latest research and guidelines.

[2126] 3. Generation AI

[2127] The generative AI automatically generates appropriate answers based on the analyzed questions received from the server, citing the latest research data and guidelines, using natural language generation models (e.g., the GPT series).

[2128] Hardware and Software

[2129] Natural Language Processing (NLP) toolkits: We use NLP tools such as spaCy and NLTK to analyze questions, which helps us identify the subject of the question and access the appropriate information.

[2130] Generative AI models: Use natural language generation models like the OpenAI GPT series to generate answers based on the latest research data.

[2131] RESTful API: To ensure that each component of the entire system works together, data is communicated between the server and the terminal via a RESTful API using Flask or Django REST framework.

[2132] Explanation with concrete examples

[2133] Here is a specific example of a "health consultation kiosk" installed in a physical drugstore. When a customer using this kiosk asks, "Which supplements are effective for diabetes?", the following actions are taken:

[2134] 1. The user enters a question into the kiosk terminal's touch panel.

[2135] 2. The terminal converts the entered question into an appropriate format and sends it to the server.

[2136] 3. The server uses natural language processing to analyze the question and identify keywords such as "diabetes" and "supplements."

[2137] 4. Based on the analysis results, the AI ​​generates an answer citing the latest research data and guidelines. In this case, the generated answer would be "Vitamin D and magnesium are effective in managing diabetes."

[2138] 5. The server sends the generated answer to the terminal and displays it to the user.

[2139] Examples of prompt statements

[2140] Below are some specific examples of prompt sentences to input into the generative AI model.

[2141] Prompt: "Which supplements are effective for diabetes?"

[2142] Generative AI model: “Certain vitamins and minerals have been shown to be effective in managing diabetes. Examples include vitamin D and magnesium.”

[2143] In this way, users can instantly obtain reliable medical information and smoothly consult with specialists online. Similar services can also be provided in physical stores, improving convenience.

[2144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2145] Step 1:

[2146] The user enters a question into the device's input screen, for example, "Which supplements are effective for diabetes?" The entered question is converted into an appropriate format for subsequent processing.

[2147] Step 2:

[2148] The device converts the question into a format and sends it to the server. This process uses an HTTP request, and the question is sent to the server in JSON format.

[2149] Step 3:

[2150] The server receives the question sent from the terminal. This input is a natural language question entered by the user. The received question is analyzed using a natural language processing (NLP) engine. Specifically, keywords (e.g., "diabetes" and "supplements") are extracted.

[2151] Step 4:

[2152] The server sends the analyzed results to a generative AI model, which uses this input to refer to the latest research data and guidelines to generate an appropriate answer to the question. For example, it may generate an answer such as, "Vitamin D and magnesium are effective in managing diabetes."

[2153] Step 5:

[2154] The server then sends the answer received from the generative AI model back to the device. At this stage, the generated answer is returned from the server to the device in JSON format.

[2155] Step 6:

[2156] The device displays the answer received from the server to the user. Specifically, the device screen displays the message, "Vitamin D and magnesium are effective in managing diabetes."

[2157] Step 7:

[2158] If the user wishes to further consult with a specialist online, he or she inputs a request from the terminal, for example, "I would like to speak to a specialist." This request is also sent to the server.

[2159] Step 8:

[2160] The server queries the schedule data of specialists and nurses to determine possible dates and times for online consultations. This coordination involves database access.

[2161] Step 9:

[2162] The server notifies the terminal of the arranged date and time of the online consultation, and this information is sent to the terminal in a format that can be confirmed by the user.

[2163] Step 10:

[2164] If the user confirms the presented date and time and approves it, the confirmation result is transmitted from the terminal to the server.

[2165] Step 11:

[2166] The server notifies the specialist or nurse of the user's confirmation results, including the arranged consultation date and time.

[2167] Step 12:

[2168] The server retransmits the final details of the online consultation to the terminal and prompts the user for final confirmation, after which the online consultation is officially scheduled.

[2169] The above are the specific processing steps of the system according to the present invention, which allows patients and their families to quickly obtain reliable medical information and smoothly consult with specialists online.

[2170] 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.

[2171] overview

[2172] This invention combines an emotion engine with an online consulting system that allows cancer patients and their families to obtain reliable medical information. The system, which is centered around a terminal, server, generative AI, and emotion engine, provides answers to users' questions based on the latest research and guidelines, and allows online consultations with specialized doctors and nurses as needed. It can also recognize users' emotions and provide tailored answers and support.

[2173] System Configuration

[2174] Terminal: A device on which users can input questions or requests for online consultations and receive answers and notifications from the system. A variety of devices can be used as terminals, including smartphones, tablets, and PCs.

[2175] Server: Receives questions and requests sent from the device and analyzes the questions using natural language processing. It then passes the analyzed questions to a generation AI to generate answers. It also analyzes the user's emotions using an emotion engine.

[2176] Generative AI: Based on analyzed questions and requests received from the server, it automatically generates appropriate answers, citing the latest research and guidelines.

[2177] Emotion Engine: Recognizes emotions from questions and requests entered by users and adjusts responses and notifications accordingly.

[2178] Program processing

[2179] 1. Enter and submit your question

[2180] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[2181] The terminal converts the entered question into text format and sends it to the server.

[2182] 2. Receiving and analyzing questions

[2183] The server receives the query sent from the terminal.

[2184] The server uses a natural language processing (NLP) module to analyze the received question and identify important keywords (e.g., "chemotherapy" and "side effects").

[2185] The server passes the analyzed question to the emotion engine to recognize the user's emotion.

[2186] 3. Emotional awareness and adaptation

[2187] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and tone of the question.

[2188] The server adjusts the content of the response and notification based on the results of the emotion engine.

[2189] 4. Answer Generation

[2190] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and an increased risk of infection. We understand your concerns, so please feel free to contact us.").

[2191] 5. Submitting and Viewing Your Answers

[2192] The server sends the generated response to the terminal.

[2193] The terminal displays the received response to the user.

[2194] 6. Online consultation requests and processing

[2195] If a user wishes to have an online consultation with a specialist, they input a request on their device (e.g., "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist").

[2196] The terminal converts the request into text format and sends it to the server.

[2197] The server receives the request for online consultation and analyzes the user's urgency and emotions using an emotion engine.

[2198] The server accesses a database of specialists' and nurses' schedules to check available time slots, and if a high level of urgency or strong emotion is detected, the request is given higher priority.

[2199] The server will notify the user of the suggested dates and times and ask for confirmation.

[2200] The user checks the date and time, and after approval, transmits it from the terminal to the server.

[2201] The server receives the confirmation and notifies the specialist or nurse.

[2202] The server sends the final details to the terminal and re-informs the user.

[2203] Specific examples

[2204] Basic Questions and Answers

[2205] 1. The user types the question into the terminal: "What are the side effects of chemotherapy?"

[2206] 2. The device converts the question into a format and sends it to the server.

[2207] 3. The server receives the question and uses NLP technology to identify the keywords "chemotherapy" and "side effects."

[2208] 4. The emotion engine recognizes the emotion "anxiety" from the context of the question.

[2209] 5. The generative AI generates emotionally sensitive answers based on the latest side effects information about chemotherapy.

[2210] 6. The server sends the generated answer to the terminal and displays it to the user.

[2211] Request an online consultation

[2212] 1. The user inputs a request on the terminal saying, "I would like to speak to a specialist."

[2213] 2. The device converts the request into a format and sends it to the server.

[2214] 3. The server receives the request and analyzes the user's urgency and emotion using the emotion engine.

[2215] 4. The server checks the specialist's schedule and prioritizes the date and time if the appointment is highly urgent.

[2216] 5. The server notifies the user of the date and time and asks for confirmation.

[2217] 6. Once the user confirms and approves the date and time, it is sent from the device to the server.

[2218] 7. The server notifies the specialist of the confirmation and resends the final details to the terminal.

[2219] This system allows cancer patients and their families to receive appropriate information and support that is sensitive to their emotions, allowing them to approach treatment with peace of mind.

[2220] The processing flow will be explained below.

[2221] Basic question and answer process flow

[2222] Step 1:

[2223] The user types the question into the terminal: "What are the side effects of chemotherapy?"

[2224] Step 2:

[2225] The terminal converts the entered question into text format and sends it to the server in the appropriate format.

[2226] Step 3:

[2227] The server receives the query sent from the terminal.

[2228] Step 4:

[2229] The server uses a natural language processing (NLP) module to analyze the received question and identify key keywords (e.g., "chemotherapy" and "side effects").

[2230] Step 5:

[2231] The server passes the analysis results to the emotion engine, which recognizes the user's emotions.

[2232] Step 6:

[2233] The emotion engine recognizes the user's emotion (e.g., anxiety, worry) from the context and wording of the question.

[2234] Step 7:

[2235] The server receives the results of the emotion engine and includes the emotion information in the request to the generation AI.

[2236] Step 8:

[2237] Based on the questions received from the server and the results of sentiment analysis, the generative AI refers to the latest research databases and guidelines to generate appropriate answers (e.g., "Common side effects of chemotherapy include nausea, hair loss, fatigue, and increased risk of infection. We understand that you are concerned, but these symptoms are common. Please let us know if there are any other concerns you have.").

[2238] Step 9:

[2239] The generation AI sends the generated answer to the server.

[2240] Step 10:

[2241] The server sends the generated response to the terminal.

[2242] Step 11:

[2243] The terminal displays the answer to the user.

[2244] Online consultation request processing flow

[2245] Step 1:

[2246] The user inputs a request for an online consultation on their device, stating, "I'm worried about the treatment I'm currently receiving, so I'd like to speak to a specialist."

[2247] Step 2:

[2248] The terminal converts the input request into text format and transmits it to the server in the appropriate format.

[2249] Step 3:

[2250] The server receives a request for online consultation sent from the terminal.

[2251] Step 4:

[2252] The server uses an emotion engine to recognize the emotion contained in the user's request (e.g., anxiety with high urgency).

[2253] Step 5:

[2254] The server accesses a database of specialist and nurse schedules to check available time slots.

[2255] Step 6:

[2256] Based on the analysis results of the emotion engine, the server determines the urgency of the online consultation and changes the priority of schedule adjustments as necessary.

[2257] Step 7:

[2258] The server selects candidate dates and times and determines the date and time for the online consultation.

[2259] Step 8:

[2260] The server notifies the terminal of the determined date and time of the online consultation.

[2261] Step 9:

[2262] The terminal notifies the user of the date and time of the online consultation and asks for confirmation.

[2263] Step 10:

[2264] The user confirms the date and time of the online consultation through the terminal and approves it.

[2265] Step 11:

[2266] The terminal transmits the confirmation result to the server.

[2267] Step 12:

[2268] The server notifies the specialist or nurse of the confirmation results.

[2269] Step 13:

[2270] The server sends a final confirmation to the terminal and notifies the user again.

[2271] In this way, the system can provide appropriate information and support in response to users' questions and requests while taking their emotions into consideration, enabling smooth two-way communication.

[2272] Example 2

[2273] 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."

[2274] Currently, it is not easy for cancer patients and their families to obtain reliable medical information. While online consultation systems exist, they often do not provide appropriate responses that take into consideration the patient's feelings. As a result, patients often undergo treatment while feeling anxious and worried, placing a heavy psychological burden on them. Furthermore, there is a problem in that they are unable to respond appropriately to urgent consultation requests, making it difficult to fully meet the needs of patients.

[2275] 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.

[2276] In this invention, the server includes a means for receiving questions sent from a terminal and analyzing the questions using natural language processing; an automatic response generation device for generating answers to the analyzed questions based on the latest research and guidelines; and an emotion analysis device for recognizing the user's emotions and adapting the answers and notification content based on the recognized emotions. This not only enables patients and their families to obtain reliable medical information, but also enables responses that take emotions into consideration. Furthermore, since highly urgent requests can be responded to quickly and appropriately, the psychological burden on patients is reduced, allowing them to receive treatment with peace of mind.

[2277] A "terminal" is a device through which a user inputs questions or requests for online consultations and receives responses or notifications from the system.

[2278] An "information processing device" is a device that receives a question sent from a terminal and analyzes the question using natural language processing.

[2279] An "automatic response generator" is a device that generates answers to analyzed questions based on the latest research and guidelines.

[2280] An "emotion analysis device" is a device that recognizes a user's emotions and adjusts responses and notification content based on the recognized emotions.

[2281] "Online consultation request" is a request input by the user to request an online consultation with a specialist doctor or nurse.

[2282] The "schedule adjustment method" is a system that checks the schedules of specialists and nurses and determines the date and time of online consultations.

[2283] "Urgency" is an index that indicates the importance or urgency of a user's request.

[2284] "Natural language processing" is a technology for analyzing user questions and understanding important keywords and context.

[2285] A "generative AI model" is an artificial intelligence that generates appropriate answers from analyzed questions and sentiment analysis results based on the latest research and guidelines.

[2286] A "prompt" is a textual representation of a question or request that is input to a generative AI model.

[2287] This invention is an online consulting system that allows cancer patients and their families to obtain reliable medical information, and also combines it with emotion analysis functions. The system is mainly composed of a terminal, an information processing device, an automatic response generation device, and an emotion analysis device, and provides users with prompt and appropriate information.

[2288] overview

[2289] The basic configuration of the invention is as follows:

[2290] 1. Terminal: A device on which users can enter questions or requests for online consultations and receive answers and notifications from the system. It can be a smartphone, tablet, or PC.

[2291] 2. Information processing device: Receives questions sent from the device and analyzes them using natural language processing (NLP), for example, using libraries such as spaCy or NLTK.

[2292] 3. Automatic response generator: Receives analyzed questions from an information processing device and uses a generative AI model to generate answers based on the latest research and guidelines. Databases such as PubMed can be used for reference.

[2293] 4. Emotion analyzer: This function analyzes the user's input and recognizes emotions (e.g., anxiety, worry). Emotion analysis is performed using IBM Watson Tone Analyzer, etc.

[2294] The main features of the system are:

[2295] 1. Enter and submit your question

[2296] Users use a terminal to enter a question in text format, such as "What are the side effects of chemotherapy?"

[2297] The terminal converts the entered question into an appropriate format and sends it to the server.

[2298] 2. Receiving and analyzing questions

[2299] The server receives the query sent from the terminal.

[2300] The server uses a natural language processing module to analyze the question and identify important keywords.

[2301] After analysis, the question data is passed to an emotion analyzer to recognize the user's emotion.

[2302] 3. Emotional awareness and adaptation

[2303] The emotion analyzer recognizes the user's emotions and returns the results to the server.

[2304] The server adjusts the response content based on the results of the emotion analysis.

[2305] 4. Answer Generation

[2306] The generative AI model uses the parsed question and sentiment analysis results to generate appropriate answers.

[2307] The generated answer is sent to the terminal via the server.

[2308] 5. View Answers

[2309] The terminal displays the received response to the user.

[2310] 6. Online consultation requests and processing

[2311] If the user wishes to have an online consultation with a specialist, they enter a request.

[2312] The device sends a request to the server, which checks the specialist's schedule and adjusts the priority according to the urgency.

[2313] The confirmed consultation date and time is notified to the user and the specialist.

[2314] Specific examples

[2315] When a user types a question such as "I'm anxious about the treatment I'm currently receiving," the device converts it into text format and sends it to the server. The server uses natural language processing to identify keywords such as "treatment" and "anxiety," and passes these to the emotion analyzer. The emotion analyzer recognizes the emotion "anxiety" and passes the results to the generative AI model. The generative AI model generates an answer based on the latest research data, such as "It's common to feel anxious about treatment. If you could tell us your story, we'll respond appropriately."

[2316] Prompt Sentence Examples

[2317] "Tell us about common side effects of chemotherapy and be mindful of any concerns users may have."

[2318] This system not only allows cancer patients and their families to obtain reliable medical information, but also provides emotionally sensitive care, allowing them to undergo treatment with peace of mind.

[2319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2320] Step 1:

[2321] The user types a question into the terminal.

[2322] Input: The user types the question, "What are the side effects of chemotherapy?"

[2323] Action: The action of entering text into a device input field.

[2324] Output: The input text data.

[2325] Step 2:

[2326] The terminal converts the entered question into the appropriate format.

[2327] Input: The text data entered in step 1.

[2328] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[2329] Output: Formatted text data.

[2330] Step 3:

[2331] The device sends a formatted text question to the server.

[2332] Input: The formatted text data from step 2.

[2333] What it does: Sends data to a server via an HTTP request.

[2334] Output: Request data to the server.

[2335] Step 4:

[2336] The server receives the question sent from the terminal.

[2337] Input: The request data sent in step 3.

[2338] How it works: The API endpoint receives request data.

[2339] Output: The received query data.

[2340] Step 5:

[2341] The server parses the question using a natural language processing (NLP) module.

[2342] Input: The question data received in step 4.

[2343] How it works: Analyzes text using NLP techniques (e.g. spaCy) to extract important keywords.

[2344] Output: Extracted keyword data (e.g., "chemotherapy" and "side effects").

[2345] Step 6:

[2346] The server passes the analysis results to the emotion analysis device.

[2347] Input: Keyword data extracted in step 5.

[2348] What it does: Converts NLP results into JSON format and sends them to the sentiment analyzer.

[2349] Output: Request data to the sentiment analyzer.

[2350] Step 7:

[2351] The emotion analyzer recognizes the user's emotions from the context and tone of the question.

[2352] Input: The request data sent in step 6.

[2353] How it works: Identifies emotions using emotion analysis technology (e.g., IBM Watson Tone Analyzer).

[2354] Output: Recognized emotion data (e.g., "anxiety").

[2355] Step 8:

[2356] The server receives the sentiment analysis results.

[2357] Input: Emotion data obtained in step 7.

[2358] What it does: Receives emotion data and prepares it for use in adjusting responses.

[2359] Output: Emotion data ready for conditioning.

[2360] Step 9:

[2361] The server passes the analyzed question and sentiment analysis results to the generated AI model.

[2362] Input: Keyword data extracted in step 5 and sentiment data obtained in step 8.

[2363] How it works: The question and emotion data are input as prompts to the generative AI.

[2364] Output: Prompt data to the generative AI model.

[2365] Step 10:

[2366] The generative AI model generates answers by referencing the latest research databases and guidelines.

[2367] Input: Prompt data from step 9.

[2368] What it does: Consults up-to-date research databases (e.g., PubMed) and generates relevant answers.

[2369] Output: The generated response data.

[2370] Step 11:

[2371] The server sends the answer received from the generation AI to the terminal.

[2372] Input: The response data generated in step 10.

[2373] What it does: Sends data to the device via an HTTP response.

[2374] Output: Response data to the device.

[2375] Step 12:

[2376] The terminal displays the received answer to the user.

[2377] Input: The response data sent in step 11.

[2378] What it does: Displays textual responses via a GUI.

[2379] Output: The answer data displayed to the user.

[2380] Step 13:

[2381] If the user wishes to have an online consultation with a specialist, they enter a request.

[2382] Input: User types "I would like to speak to a specialist."

[2383] Action: The action of entering text into a device input field.

[2384] Output: The input request data.

[2385] Step 14:

[2386] The device converts the request into an appropriate format and sends it to the server.

[2387] Input: The request data entered in step 13.

[2388] What it does: Text formatting (e.g. removing unnecessary whitespace, encoding).

[2389] Output: The formatted request data.

[2390] Step 15:

[2391] The server receives the online consultation request and analyzes the urgency and emotion of the user with an emotion analyzer.

[2392] Input: The request data sent in step 14.

[2393] How it works: It uses NLP techniques and sentiment analyzers to analyze text and identify sentiment and urgency.

[2394] Output: Extracted urgency and sentiment data.

[2395] Step 16:

[2396] The server accesses a database of specialist and nurse schedules to check available time slots.

[2397] Input: Urgency data identified in Step 15.

[2398] What it does: Runs a database query to find and identify free time.

[2399] Output: Data on available time slots.

[2400] Step 17:

[2401] If the server is in a high emergency state, the date and time are set with priority.

[2402] Input: The open time slot data identified in step 16.

[2403] What it does: Prioritize and optimize dates and times based on urgency.

[2404] Output: Date and time data of the online consultation that was set.

[2405] Step 18:

[2406] The server notifies the user of the set date and time and asks for confirmation.

[2407] Input: Date and time data set in step 17.

[2408] Behavior: Generates a confirmation message and sends it to the device as an HTTP response.

[2409] Output: Acknowledgement data to the user.

[2410] Step 19:

[2411] Once the user confirms and approves the date and time, it is sent from the device to the server.

[2412] Input: Acknowledgment data sent in step 18.

[2413] Action: The user sees the notification and clicks the confirm / agree button.

[2414] Output: Confirmation and acceptance data.

[2415] Step 20:

[2416] The server notifies the specialist or nurse of the confirmation.

[2417] Input: Confirmation and acknowledgement data sent in step 19.

[2418] What it does: Generates and sends a message to notify specialists and nurses of the results of the check.

[2419] Output: Data for notifying specialists and nurses.

[2420] Step 21:

[2421] The server sends the final details to the terminal and re-informs the user.

[2422] Input: Specialist and nurse notification data sent in step 20.

[2423] Behavior: A message containing the confirmed date and time and details is generated and sent to the device as an HTTP response.

[2424] Output: Final notification data to the user.

[2425] (Application example 2)

[2426] 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."

[2427] Currently, cancer patients and their families have limited access to reliable medical information, and there is a particular lack of information provision that takes into consideration the user's emotions. For example, there is a lack of means to provide appropriate information and support to users who are feeling anxious or worried. Furthermore, there is a lack of mechanisms for appropriately adjusting online consultations with specialists based on the level of urgency and emotions. This presents a challenge for users, making it difficult to receive the information and support they need in a timely manner.

[2428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2429] In this invention, the server includes means for receiving questions or requests entered by users and analyzing them using natural language processing, means for using generative artificial intelligence to generate answers based on the analyzed questions and the latest research and guidelines, and means for using an emotion engine to analyze the user's emotions and adjust the content of the answers based on the analysis results, thereby making it possible to provide answers and support that take into consideration the user's emotions as well as reliable medical information.

[2430] A "terminal" is a device through which a user can input questions or requests for online consultations and receive responses and notifications from the system.

[2431] The "server" is a central computer system that receives questions and requests sent from devices, analyzes them using natural language processing, and works with generative AI and emotion engines to generate answers and support.

[2432] "Natural language processing" is a computer science technique for analyzing text data and understanding its meaning.

[2433] "Generative AI" is an AI technology that automatically generates appropriate answers based on the latest research and guidelines, based on analyzed questions and requests.

[2434] The "emotion engine" is a technology that recognizes emotions from the text entered by the user and appropriately adjusts the response content and notifications based on the analysis results.

[2435] "Online consultation" is a consultation format that allows users to directly interact with experts via the Internet.

[2436] "Schedule adjustment" refers to the process of checking the specialist's schedule, selecting an available time slot, and deciding on the date and time of the consultation.

[2437] A "generative AI model" is a type of artificial intelligence used to analyze questions or requests and generate new answers.

[2438] A "prompt" is textual data that is input to a generative AI model and contains hints and instructions that help the model generate an answer.

[2439] This invention combines an emotion engine with an online consulting system that provides reliable medical information for cancer patients and their families. Each component is described in detail below.

[2440] System Configuration

[2441] 1. Terminal

[2442] The terminal is a device that allows users to input questions or requests for online consultations and receive replies and notifications from the system. Terminals can be smartphones, tablets, PCs, etc.

[2443] 2. Server

[2444] The server receives questions and requests sent from the device and analyzes the questions using natural language processing (NLP). The analyzed questions are used to generate answers through generative AI and an emotion engine. The server then sends the answers generated based on the analysis results to the device and displays them.

[2445] 3. Natural Language Processing

[2446] Natural language processing is a computer science technique used to analyze text data and understand its meaning. Specifically, it extracts important keywords from input questions and matches them with relevant medical databases and guidelines.

[2447] 4. Generative Artificial Intelligence

[2448] Generative AI (generative AI) generates appropriate answers based on analyzed questions received from the server, citing the latest research and guidelines. For example, OpenAI's GPT-4 is used as a generative AI.

[2449] 5. Emotion Engine

[2450] The emotion engine recognizes emotions from questions and requests entered by users and adjusts responses and notification content appropriately based on the recognized emotions. The emotion engine uses emotion analysis tools such as AWS Comprehend.

[2451] Program processing

[2452] The server receives questions sent from the device and analyzes them using natural language processing. The analyzed questions are then analyzed for user emotion through an emotion engine, and the results are passed on to a generation AI to generate an answer. The generated answer is then returned to the server and sent to the device.

[2453] This process involves the following hardware and software:

[2454] Hardware: smartphones, tablets, PCs, servers

[2455] Software: Natural language processing libraries (e.g., spaCy, NLTK), sentiment analysis tools (e.g., AWS Comprehend, TextBlob), generative AI (e.g., OpenAI GPT-4)

[2456] Specific examples

[2457] Specific examples of questions and answers

[2458] The user types the question "What are the side effects of chemotherapy?" into their smartphone. This question is sent to the server and analyzed through a natural language processing module and an emotion engine. Based on the analysis results, the generative AI generates the following answer: "Common side effects of chemotherapy include nausea, hair loss, fatigue, and the risk of infection. We understand your concerns, so please feel free to contact us." This a...

Claims

1. A terminal for cancer patients and their families to input questions, a server that receives a question sent from a terminal and analyzes the question using natural language processing; Generative AI generates answers based on the latest research and guidelines for analyzed questions, and means for transmitting the generated answer to a terminal and displaying it; A system including:

2. A means for receiving a request for an online consultation from a user and arranging the schedule of a specialist or nurse to determine the date and time of the online consultation; means for notifying the terminal of the determined date and time and receiving confirmation from the user; A method to notify specialists and nurses of the confirmation results and re-notify the details of the online consultation to the terminal, The system of claim 1 further comprising:

3. a means for converting a user's natural language query into an appropriate format; means for transmitting the properly formatted question to a server; The system of claim 1 further comprising:

Images