System

Abstract

A system is provided.SOLUTION: A system including means for inputting a medical question or medical condition from a user, means for transmitting the input medical question or medical condition to a server, means for analyzing the received medical question or medical condition in the server, means for generating an appropriate answer by a generative AI model based on an analysis result, means for transmitting the generated answer to the user, and means for receiving feedback from the user and updating training data of the generative AI model.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] The present invention aims to reduce the risk of patients and their families making medical decisions based on inaccurate information, as information on the Internet is not always reliable. There is also a need to reduce the burden on medical professionals before medical treatment and to resolve medical-related questions and concerns that patients and their families have in a timely manner. This will enable access to high-quality medical information and improve health awareness. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means: a system including a means for inputting medical questions and symptoms from a user, a means for transmitting the input questions and symptoms to a server, a means for analyzing the received questions and symptoms at the server, a means for generating appropriate answers using a generative AI model based on the analysis results, a means for transmitting the generated answers to the user, and a means for receiving feedback from the user and updating the learning data of the generative AI model. The system may also include a means for registering basic user information and storing it on the server, a means for authenticating the user based on the registered user information, a means for analyzing the user's questions and symptoms using a natural language processing module, and a means for generating answers from a curated medical knowledge base. In this way, it is possible to simultaneously provide reliable medical information and reduce the burden on medical professionals.

[0006] "User" refers to an individual who uses the system to input medical questions or symptoms.

[0007] "Questions and symptoms" refers to specific questions and physical conditions entered by users when requesting medical information.

[0008] "Server" refers to a computer system that receives user-entered information, analyzes it, and generates and transmits an appropriate response.

[0009] A "natural language processing module" refers to a software component that analyzes questions and symptoms entered by users and identifies their intent and keywords.

[0010] "Generative AI model" refers to an artificial intelligence model that generates answers to user questions from a curated medical knowledge base.

[0011] A "medical knowledge base" refers to a database that is supervised by medical specialists and contains reliable medical information.

[0012] "Feedback" refers to information that a user inputs in response to a provided answer, such as an opinion or evaluation.

[0013] "Training data" refers to the collection of data used to improve the accuracy of a generative AI model.

[0014] "Authentication" refers to the process by which the server verifies the user's registration information and verifies its legitimacy.

[0015] "Answer" refers to the solution or information generated by the generative AI model in response to a user's question or symptom.

[0016] "Transmission means" refers to the infrastructure and protocols used to send and receive user-entered information and generated responses to the server. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[0039] System Configuration

[0040] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0041] User terminal

[0042] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[0043] server

[0044] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[0045] Natural Language Processing Module

[0046] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0047] Generative AI Models

[0048] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[0049] Medical Knowledge Base

[0050] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[0051] Program processing

[0052] The program of this system is processed as follows.

[0053] User Registration and Login

[0054] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0055] Enter and submit your question

[0056] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[0057] Parsing questions and generating answers

[0058] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[0059] Collecting user feedback

[0060] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0061] Through the above process, this system provides users with reliable medical information and reduces the burden on medical professionals.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user downloads the application and installs it on the device.

[0065] Step 2:

[0066] The user opens the account creation screen on their device and enters their name, age, and email address.

[0067] Step 3:

[0068] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[0069] Step 4:

[0070] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[0071] Step 5:

[0072] The server will send a confirmation email containing an authentication code to the user's email address.

[0073] Step 6:

[0074] The user enters the authentication code received via email into the authentication screen within the application.

[0075] Step 7:

[0076] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[0077] Step 8:

[0078] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[0079] Step 9:

[0080] The terminal receives the token and sets the user to a logged-in state.

[0081] Step 10:

[0082] The user uses the terminal to input medical questions and symptoms and send the question.

[0083] Step 11:

[0084] The terminal generates a request to transmit the input question information to the server, and transmits the request to the server.

[0085] Step 12:

[0086] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question.

[0087] Step 13:

[0088] The natural language processing module returns the analysis results to the server.

[0089] Step 14:

[0090] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[0091] Step 15:

[0092] The generative AI model references a curated medical knowledge base to generate appropriate answers.

[0093] Step 16:

[0094] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[0095] Step 17:

[0096] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[0097] Step 18:

[0098] The user inputs feedback on the provided answers and transmits it from the terminal to the server.

[0099] Step 19:

[0100] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[0101] Step 20:

[0102] The server stores the received feedback in a database and updates the training data for the generative AI model.

[0103] The above is a specific processing flow of the entire system.

[0104] Example 1

[0105] 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."

[0106] Many users today require fast and reliable answers to their medical questions and symptoms. However, current systems require users to search for medical information on their own, and the information they receive is often inaccurate and unreliable. Furthermore, the burden on medical professionals is increasing, requiring more efficient responses. An effective system is needed to address these issues.

[0107] 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.

[0108] In this invention, the server includes means for accepting medical input from a user, means for transmitting the input information to a central processing unit via a communication network, means for analyzing the information received by the central processing unit using a natural language processing module, means for generating an answer based on the analysis result using a generative AI model, means for transmitting the generated answer to the user's terminal, and means for receiving feedback from the user and updating the learning data of the generative AI model. This allows users to obtain reliable medical information quickly and reduces the burden on medical professionals.

[0109] "User" refers to an individual who utilizes the system to provide medical input.

[0110] "Input" refers to the act of a user providing information such as medical questions or symptoms to the system.

[0111] "Communications network" refers to a digital network for transmitting information from user terminals to a central processing unit (server).

[0112] "Central Processing Unit" refers to the server that analyzes and processes information received from the user and generates a response.

[0113] A "natural language processing module" refers to a software component that analyzes user input and extracts its intent and keywords.

[0114] "Generative AI model" refers to an artificial intelligence model that generates appropriate answers based on the analysis results of a natural language processing module.

[0115] "Answer" refers to medical information or advice generated by a generative AI model.

[0116] "Terminal" refers to the device (e.g., smartphone, tablet, computer, etc.) used by a user to provide input and receive responses from the system.

[0117] "Feedback" refers to the evaluation or opinion a user gives on a provided answer.

[0118] "Training data" refers to data used to improve the performance and accuracy of generative AI models.

[0119] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[0120] System Configuration

[0121] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0122] User terminal

[0123] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[0124] server

[0125] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[0126] Natural Language Processing Module

[0127] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0128] Generative AI Models

[0129] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[0130] Medical Knowledge Base

[0131] A medical knowledge base is a database of reliable medical information curated by experts, which serves as a source of information for generative AI models to generate appropriate answers.

[0132] Program processing explanation

[0133] User Registration and Login

[0134] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0135] Enter and submit your question

[0136] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[0137] Parsing questions and generating answers

[0138] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[0139] Collecting user feedback

[0140] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0141] Examples of specific examples and prompts

[0142] Specific examples

[0143] If a user asks, "I have a persistent headache, but medicine isn't helping," the question is sent from the device to the server and analyzed by a natural language processing module. Based on the analysis results, the generative AI model considers various possibilities regarding the headache and generates an appropriate answer. This answer is then sent to the user's device.

[0144] Prompt Sentence Examples

[0145] 1. "When a user submits a headache question, please describe how it is parsed and an answer generated."

[0146] 2. "Please specifically show how your generative AI model would respond if the headache had lasted for several weeks."

[0147] In this way, this system provides users with reliable medical information and reduces the burden on medical professionals.

[0148] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0149] Step 1: User Registration and Login

[0150] What happens: A user downloads an application and enters basic information such as name, age, and email address.

[0151] Input: Basic information (name, age, email address, etc.)

[0152] Output: The user information is saved in the database and a confirmation email is sent.

[0153] Detailed description: The device generates an API request to send the entered basic information to the server. The server receives this information and stores it in a database. The server then sends a confirmation email to the user's email address. The user enters the authentication code received in the email into the application, and the server verifies the information and sets the user to logged in.

[0154] Step 2: Enter and submit your question

[0155] What it does: A user enters a medical question or symptom through the application.

[0156] Input: User's question or symptom

[0157] Output: The question is sent to the server.

[0158] Detailed description: The device generates an API request to send the entered medical question or symptoms to the server. The generated API request is sent to the server via a communication network. The server stores the received question in a database.

[0159] Step 3: Parsing the Question

[0160] Specific operation: The server forwards the received question to the natural language processing module.

[0161] Input: Question (question or symptom submitted by the user)

[0162] Output: Analysis results (intention and keywords)

[0163] Detailed explanation: The natural language processing module analyzes the question and identifies its intent and keywords. For example, if the question is "I've had a headache for several weeks, and it hasn't gone away even after taking medicine," the NLP module extracts keywords such as "headache," "several weeks," and "medicine isn't working." The analysis results are then sent to the generative AI model.

[0164] Step 4: Generate an answer

[0165] Specific operation: The generative AI model generates an answer based on the analysis results.

[0166] Input: Analysis results (intention and keywords)

[0167] Output: Medical answers

[0168] Detailed description: The generative AI model generates appropriate answers from a medically supervised medical knowledge base. Based on the analysis results, the model generates a specific answer such as "You may have a chronic headache and we recommend that you consult a doctor." This answer is sent to the server.

[0169] Step 5: Submit your response

[0170] Specific operation: The server sends the generated answer to the user's device.

[0171] Input: Answer (medical information provided by the generative AI model)

[0172] Output: Send the answer to the user's terminal

[0173] Detailed description: The server checks the generated answer and sends it to the user's device, where the user receives the answer on the application screen.

[0174] Step 6: Gather feedback

[0175] Specific Actions: The user enters feedback on the answers provided.

[0176] Input: Feedback (user ratings and opinions)

[0177] Output: Save the feedback to a database and use it to update the generative AI model

[0178] Detailed description: The user inputs feedback about the provided answer, such as "It was very easy to understand." The device generates an API request to send this feedback to the server, and sends it to the server. The server receives the feedback and stores it in a database. This feedback is also used as training data for the generative AI model, contributing to improving the model's performance.

[0179] The above is a detailed description of the specific processing flow of this system and the inputs and outputs at each step.

[0180] (Application example 1)

[0181] 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."

[0182] When users have medical questions or symptoms, it is difficult to easily obtain reliable medical information. Furthermore, the inability to obtain medical information immediately when shopping in physical stores or using services reduces user satisfaction. Furthermore, the inability to efficiently recommend health products and services in physical stores makes it difficult to increase sales or meet customer needs.

[0183] 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.

[0184] In this invention, the server includes means for registering and storing basic user information, means for authenticating based on the registered user information, means for inputting medical questions and symptoms from the user, means for transmitting the input questions and symptoms to the server, means for analyzing the questions and symptoms received by the server, means for generating appropriate answers using a generative AI model based on the analysis results, means for transmitting the generated answers to the user, means for receiving feedback from the user and updating the learning data of the generative AI model, means for the user to input questions and symptoms using a robot in a physical store, means for displaying the answers generated by the robot by voice and on a screen, means for recommending products and services in the physical store, means for analyzing the questions and symptoms from the user using a natural language processing module, and means for generating answers from a curated medical knowledge base. This allows users to instantly obtain reliable medical information in a physical store, and enables accurate recommendations of health products and services.

[0185] The "means for users to input medical questions and symptoms" refers to a device that provides an interface for users to input questions about their own health condition and symptoms using the robot's touch screen, etc.

[0186] The "means for transmitting input questions and symptoms to a server" is a communication device for transmitting information input by a user to a remote server via the Internet or the like.

[0187] The "means for analyzing questions and symptoms received at the server" is a software module for analyzing user questions and symptoms sent to the server and extracting their intent and key keywords.

[0188] "Means for generating appropriate answers using a generative AI model based on the analysis results" refers to a device that uses a generative AI model to generate appropriate answers based on data analyzed through natural language processing.

[0189] The "means for transmitting the generated answer to the user" is a communication device that transmits the generated answer back to the robot or touch screen used by the user by displaying or audibly transmitting the answer.

[0190] The "means for receiving feedback from users and updating the learning data of the generative AI model" refers to a database and update function for collecting feedback provided by users and using it as training data for the generative AI model.

[0191] "A means for users to input questions and symptoms using a robot within a physical store" refers to a device that allows users to input medical questions and symptoms using a touch screen or the like on a robot placed within a physical store.

[0192] "Means for the robot to display the generated answers by voice and on a screen" is a function that enables the robot to explain the generated medical information and product recommendations by voice and simultaneously display them on a touch screen.

[0193] "Means for recommending products and services in physical stores" is a function that allows the robot to recommend related health products and services based on the user's questions and symptoms.

[0194] A "natural language processing module" is a software module that analyzes text data of questions and symptoms received from users, extracts intent and keywords, and passes them on to the next process.

[0195] A "supervised medical knowledge base" is a database that stores reliable medical information that has been verified by medical specialists.

[0196] This invention relates to a system that allows users to input medical questions and symptoms in a physical store and obtain reliable medical information in real time. This system is broadly composed of a user terminal (a robot touch screen), a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0197] User terminal

[0198] A robot placed in a physical store is used as a means for users to input their questions and symptoms. The robot is equipped with a touchscreen, providing an interface for users to input directly. The robot then provides the generated answers to the user via voice and on the screen, and also recommends related health products and services.

[0199] server

[0200] The server receives questions and symptoms sent by users and analyzes them. The server works as follows:

[0201] 1. The user uses the robot in a physical store to input their questions or symptoms, and the input information is sent to the server.

[0202] 2. The server forwards the received questions and symptoms to the natural language processing module, which analyzes the intent and keywords.

[0203] 3. Based on the analysis results, a generative AI model is used to generate an appropriate answer.

[0204] 4. The generated answer is sent back to the robot via the server and provided to the user.

[0205] 5. The user enters feedback on the provided answer, and the server uses that feedback as training data for the generative AI model.

[0206] Natural Language Processing Module

[0207] The natural language processing module (NLP module) analyzes the user's inputted question or symptom to identify their intent and key keywords. This provides the basis for the generative AI model to generate appropriate answers. Specifically, NLP libraries such as SpaCy and NLTK are used.

[0208] Generative AI Models

[0209] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module. Generative models such as GPT-3 and OpenAI are used to provide users with reliable medical information.

[0210] Medical Knowledge Base

[0211] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[0212] Specific examples

[0213] The user types a question into the robot's touchscreen: "I have a persistent cough. What product do you recommend?" This information is sent to the server, which uses a natural language processing module to extract keywords such as "cough," "product," and "recommendation." The generative AI model then uses this information to create a prompt and generate an appropriate answer. For example, the generated answer might be, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The robot provides this answer to the user both aloud and on the screen, and also guides them to products in specific locations in the store.

[0214] Prompt Sentence Examples

[0215] I have a persistent cough. Which product would you recommend?

[0216] The above is a specific embodiment for carrying out the present invention. This system allows users to instantly obtain reliable medical information even in physical stores, making it easy to select health products and services. Furthermore, by collecting feedback, the accuracy of the entire system can be improved.

[0217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0218] Step 1:

[0219] A user uses the robot's touchscreen in a brick-and-mortar store to input their medical question or symptoms, such as "I have a persistent cough. What product would you recommend?" This input data is stored in the robot's internal system.

[0220] Step 2:

[0221] The device sends the entered question or symptom to the server. At this time, an API request including the input data is generated and sent to the server via the Internet. The input data (user question) is received at the server's API endpoint.

[0222] Step 3:

[0223] The server passes the received question to a natural language processing module, which first analyzes the text data and extracts key keywords such as "cough," "product," and "recommendation." The input data is then processed based on this, and keywords are generated as the analysis results.

[0224] Step 4:

[0225] Based on the analysis results, the server creates and sends a prompt to the generative AI model. This prompt is formatted as "I have a persistent cough. What products do you recommend?" The prompt is then input to the generative AI model (such as GPT-3).

[0226] Step 5:

[0227] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The answer text is returned to the server as output data from the generative AI model.

[0228] Step 6:

[0229] The server forwards the generated answer to the robot. This answer data is again sent as an API request and received by the robot. The robot then tells the user by voice and on the screen, "As a product that is effective for coughs, we recommend cough syrup sold at pharmacies."

[0230] Step 7:

[0231] The user inputs feedback on the provided answer into the robot's touchscreen, for example, "This answer was helpful."

[0232] Step 8:

[0233] The device sends the user's feedback to the server, and an API request containing the feedback data is generated again and sent to the server.

[0234] Step 9:

[0235] The server stores the received feedback in a database and uses this data as training data for the generative AI model, which improves the accuracy of the generative AI model and the quality of answers from the next time onwards.

[0236] 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.

[0237] This invention relates to a system that allows users to input medical questions and symptoms and generates appropriate answers. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond according to the user's emotional state. This system provides reliable medical information, alleviating user anxiety and reducing the burden on medical professionals.

[0238] System Configuration

[0239] The system consists of the following main components: a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[0240] User terminal

[0241] The user terminal provides an interface for users to input medical questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or personal computer. In addition, the user terminal is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice, and also has the function of sending this information to the server.

[0242] server

[0243] The server receives questions, symptoms, and emotional data sent by users and performs analysis and answer generation. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The generative AI model generates appropriate answers from a medical knowledge base and sends them to the user's device. It also adjusts the tone of the answers based on the emotional data and collects feedback.

[0244] Natural Language Processing Module

[0245] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0246] Generative AI Models

[0247] The generative AI model generates answers from a curated medical knowledge base based on the analysis results and emotion data received from the natural language processing module, and also has the ability to adjust the tone of the answer based on data from the emotion engine.

[0248] Medical Knowledge Base

[0249] A medical knowledge base is a database of reliable medical information curated by medical experts, which serves as the primary source of information for generative AI models to generate appropriate answers.

[0250] Emotion Engine

[0251] The emotion engine is a module that recognizes emotions from the user's facial expressions and voice when they input their questions or symptoms. The emotion data recognized by the emotion engine is sent to the server and used for subsequent interviews and answer generation.

[0252] Program processing

[0253] The program of this system is processed in the following manner.

[0254] 1. User Registration and Login

[0255] The user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0256] 2. Enter and submit your question

[0257] The user inputs medical questions and symptoms using the device and sends the question. The emotion engine recognizes the user's emotions and sends the emotion data to the server. The device then generates a request to send this information to the server and sends it to the server.

[0258] 3. Question Analysis and Answer Generation

[0259] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results and emotional data are passed to a generative AI model, which then generates an appropriate answer from a medical knowledge base. The tone of the generated answer is adjusted based on the emotional data, and the answer is sent to the user's device via the server.

[0260] 4. Collecting User Feedback

[0261] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0262] Specific examples

[0263] For example, suppose a user inputs a question such as "I've been having headaches lately due to work stress," and the emotion engine detects anxiety and stress. The server receives this, and the natural language processing module extracts keywords such as "stress" and "headache," and passes the analysis results to the generative AI model. The generative AI model then generates an answer on "how to deal with stress-related headaches" from a medical knowledge base, such as "Relaxation techniques and lifestyle changes are effective for headaches caused by stress. We recommend that you see a doctor for a detailed diagnosis." Based on the emotion engine's data, the tone of the answer is adjusted to be calming. The user confirms this and enters feedback such as "This was helpful," and the system collects this feedback to improve the AI ​​model's performance.

[0264] The above is an embodiment of the present invention. In this way, the system can provide the user with prompt and appropriate medical information, while also responding appropriately to the user's emotions.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] The user downloads the application and installs it on the device.

[0268] Step 2:

[0269] The user opens the account creation screen on their device and enters their name, age, and email address.

[0270] Step 3:

[0271] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[0272] Step 4:

[0273] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[0274] Step 5:

[0275] The server will send a confirmation email containing an authentication code to the user's email address.

[0276] Step 6:

[0277] The user enters the authentication code received via email into the authentication screen within the application.

[0278] Step 7:

[0279] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[0280] Step 8:

[0281] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[0282] Step 9:

[0283] The terminal receives the token and sets the user to a logged-in state.

[0284] Step 10:

[0285] Users use the terminal to input medical questions and symptoms.

[0286] Step 11:

[0287] The emotion engine recognizes emotions from the user's facial expressions and voice and acquires emotion data.

[0288] Step 12:

[0289] The device generates a request to send information about the question or symptom and emotional data to the server, and sends it to the server.

[0290] Step 13:

[0291] The server transfers the received information to a natural language processing module, which analyzes the intent and keywords of the question.

[0292] Step 14:

[0293] The natural language processing module returns the analysis results to the server.

[0294] Step 15:

[0295] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[0296] Step 16:

[0297] The generative AI model references a medical knowledge base to generate appropriate answers and adjusts the tone of the answer based on emotional data.

[0298] Step 17:

[0299] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[0300] Step 18:

[0301] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[0302] Step 19:

[0303] The user enters feedback on the answers provided, and the feedback is also transmitted from the terminal to the server.

[0304] Step 20:

[0305] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[0306] Step 21:

[0307] The server stores the received feedback in a database and uses it as training data for the generative AI model.

[0308] Step 22:

[0309] The server uses emotional data and past feedback to improve the accuracy and personalization of future question answers.

[0310] Example 2

[0311] 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."

[0312] In today's medical field, there is a demand for fast and appropriate medical information, but the burden on medical professionals is becoming a problem. In particular, when users input medical questions or symptoms, it is difficult to provide appropriate answers to those questions or symptoms, and responses that are not adequately responsive to the user's emotions are not being provided. Therefore, it is important to alleviate users' anxiety and reduce the burden on medical professionals.

[0313] 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.

[0314] In this invention, the server includes means for inputting medical questions and symptoms from a user, means for transmitting the input questions and symptoms, means for analyzing the questions and symptoms, means for generating appropriate answers using a generative AI model, means for transmitting the generated answers to the user, means for recognizing the user's emotions and acquiring emotional data, means for adjusting the tone of the answers based on the emotional data, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to quickly provide appropriate answers to the questions and symptoms input by users and responses tailored to each individual's emotions.

[0315] "User" refers to a person who enters a medical question or symptom or provides feedback in response to a question.

[0316] "Terminal" refers to a device that allows users to input medical questions and symptoms and send them to a server. Examples of such devices include smartphones, tablets, and personal computers.

[0317] "Server" refers to a central computer system that receives questions and symptoms sent by users, analyzes them, generates appropriate answers, and sends them to the users.

[0318] A "natural language processing module" refers to a software module that analyzes questions and symptoms entered by users and extracts their intent and keywords.

[0319] A "generative AI model" refers to an artificial intelligence model that generates appropriate answers from a medical knowledge base based on the results analyzed by a natural language processing module.

[0320] A "medical knowledge base" refers to a database that accumulates medical information supervised by specialist doctors and medical institutions.

[0321] An "emotion engine" refers to a module that recognizes emotions from the user's facial expressions and voice and acquires that emotion data.

[0322] "Emotion data" refers to information about a user's emotions recognized by the emotion engine.

[0323] "Answer tone adjustment" refers to the process of ensuring that generated answers are delivered in an appropriate tone depending on the user's emotions.

[0324] "Feedback" refers to the act of a user inputting their opinion on the usefulness and satisfaction of a provided answer.

[0325] The present invention is a system that allows users to input medical questions and symptoms and provides appropriate answers to those questions. The system includes a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[0326] System Configuration

[0327] User terminal

[0328] The user terminal is a device that allows users to input medical questions and symptoms. Users use a smartphone, tablet, or personal computer to create an account, log in, enter questions, and provide feedback. The user terminal also incorporates an emotion engine that uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This emotion data is sent to the server in real time.

[0329] server

[0330] The server is a central computer system that receives questions and emotional data sent by users, analyzes them, and generates answers. The server sends the received questions to a natural language processing module and obtains analysis results. The analysis results and emotional data are then passed to a generative AI model, which generates an appropriate answer. The tone of the generated answer is adjusted based on the emotional data and sent to the user's device.

[0331] Natural Language Processing Module

[0332] The natural language processing module (NLP module) is software that analyzes user-entered questions and symptoms. This module extracts intent and keywords from the input text and provides the basis for answer generation by generative AI models.

[0333] Generative AI Models

[0334] The generative AI model is an artificial intelligence model that generates appropriate answers from a curated medical knowledge base based on the analysis results and emotional data received from the natural language processing module, and also has the ability to adjust the tone of the answer taking into account the emotional data.

[0335] Medical Knowledge Base

[0336] A medical knowledge base is a database of reliable medical information supervised by specialist doctors and medical institutions. A generative AI model references this database to generate appropriate answers to user questions.

[0337] Emotion Engine

[0338] The emotion engine is a module that recognizes emotions from facial expressions and voice when a user inputs a question or symptom. This engine sends the recognized emotion data to the server in real time and reflects it in generating an answer.

[0339] Specific examples

[0340] For example, consider the case where a user enters the question, "I've been having headaches lately due to work stress." When this question is entered, the emotion engine recognizes the user's anxiety and stress. The server sends the received question to a natural language processing module, which extracts keywords such as "stress" and "headache." The analysis results are passed to a generative AI model, which generates an answer on "how to deal with stress-related headaches" from a medical knowledge base. This answer might be something like, "For headaches caused by stress, relaxation techniques and lifestyle changes are effective. I recommend seeing a doctor for a detailed diagnosis." Furthermore, based on the emotion data, the tone of the answer is adjusted to be calmer.

[0341] An example prompt might look like this:

[0342] "I've been having headaches lately because of work stress. What should I do?"

[0343] In this way, the system provides users with prompt and appropriate medical information and responds to their emotions, thereby reducing user anxiety and the burden on medical professionals.

[0344] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0345] Program processing flow

[0346] Step 1: User Registration and Login

[0347] The user creates an account using the device. The user's input information (name, age, email address) is sent from the device to the server. The server stores this information in a database and generates a confirmation email that is sent to the user's email address. The user then enters the authentication code they received, and the device sends the code to the server. Once authentication is complete, the user is logged in.

[0348] Input: User's name, age, email address, verification code

[0349] Processing: Sending and storing information, generating and verifying authentication codes

[0350] Output:Login status

[0351] Step 2: Enter your question

[0352] Users input their medical questions and symptoms using a device. The emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The acquired emotional data and information about the questions and symptoms are then sent from the device to the server.

[0353] Input: User's questions, symptoms, facial expressions, and voice

[0354] Processing: Entering questions and symptoms, acquiring and sending emotional data

[0355] Output: Question, symptom, and emotion data sent to the server

[0356] Step 3: Parsing the Question

[0357] The server transfers the received question and emotion data to the natural language processing module, which analyzes the text of the question or symptom to extract the intent and important keywords. The extracted analysis results are returned to the server.

[0358] Input: Question, Symptoms, and Emotional Data

[0359] Processing: Text analysis and keyword extraction using natural language processing modules

[0360] Output: Extracted intent and important keywords

[0361] Step 4: Generate an answer

[0362] The server passes the analysis results and emotional data to the generative AI model, which then generates an appropriate answer from a medical knowledge base based on the analysis results, adjusts the tone of the answer based on the emotional data, and returns the generated answer to the server.

[0363] Input: Analysis results, emotion data

[0364] Processing: Answer generation using generative AI model, tone adjustment

[0365] Output: The generated answer

[0366] Step 5: Submit your response

[0367] The server sends the generated answer to the user's terminal, which displays the answer to the user.

[0368] Input: Generated Answer

[0369] Action: Send response

[0370] Output: Answer displayed on the user's device

[0371] Step 6: Gather feedback

[0372] The user enters feedback on the provided answers, and the device sends the feedback to the server, which stores it in a database and uses it as training data for the generative AI model.

[0373] Input: User feedback

[0374] Action: Send and save feedback

[0375] Output: Saved feedback data

[0376] Specific examples of processing

[0377] Step 1: The user downloads the application and enters their name, age, and email address. The server then sends a confirmation email, confirming the entry of a verification code.

[0378] Step 2: The user enters "I've been having headaches lately because of work stress," and the emotion engine recognizes anxiety and stress. The data is sent to the server.

[0379] Step 3: The natural language processing module extracts keywords such as "stress" and "headache" and returns the analysis results to the server.

[0380] Step 4: The generative AI model consults a medical knowledge base and generates an answer about "how to deal with stress-related headaches," adjusting the tone to be calming.

[0381] Step 5: The server sends the answer to the user's terminal, and the user confirms the answer.

[0382] Step 6: The user enters feedback such as "It was helpful" and the server stores it in the database.

[0383] In this way, the system provides the user with appropriate medical information and responds according to the user's emotions.

[0384] (Application example 2)

[0385] 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."

[0386] In recent years, many companies and facilities have been required to monitor the health status of their employees in real time and take appropriate measures. Especially in large-scale facilities, it is difficult to monitor the health status of many employees individually, making an effective health management system necessary. Furthermore, taking into account employees' emotional state and stress level would enable more accurate responses. However, conventional health monitoring systems lack the ability to analyze emotional states or adjust tone in real time, making it difficult to take prompt and appropriate action.

[0387] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting questions and symptoms related to health status from a user, means for transmitting the input questions, symptoms, and emotional data to the server, means for analyzing the questions, symptoms, and emotional data received in the server, means for generating appropriate advice using a generative AI model based on the analysis results, means for adjusting the tone of the generated advice and transmitting it to the user, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to monitor the health status of employees in real time and quickly take appropriate measures that take their emotional state into consideration.

[0388] "Health status" refers to the physical and mental condition of the user, and refers to questions and symptoms input by the user.

[0389] "Emotion data" refers to data that indicates the emotional state of the user analyzed from their facial expressions and voice.

[0390] "Server" refers to a computer system that analyzes received data and generates and sends appropriate advice.

[0391] "Analysis means" refers to methods and technologies for understanding the input question, symptoms, and emotion data and extracting appropriate information.

[0392] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates appropriate advice based on input data.

[0393] "Tone adjustment" refers to adjusting the tone and expression of generated advice to match the user's emotional state.

[0394] "Feedback" refers to the user's reaction and evaluation of the advice provided, and is information used to improve the system.

[0395] "Training data" refers to the data, including feedback, that a generative AI model uses to generate more accurate advice.

[0396] This invention relates to a system that analyzes a user's health-related questions and symptoms in real time and provides appropriate advice based on emotional data. The system mainly consists of the following components: a user terminal, a server, a natural language processing module, a generative AI model, a knowledge base, and an emotional engine.

[0397] User terminal

[0398] The user device is provided as a smartphone app. This app has a means for the user to input their health status and acquire emotional data from facial expressions and voice in real time. For example, if a user inputs "Recently, my work environment has been causing me stress," the device analyzes it and captures emotional data such as anxiety from facial expressions.

[0399] server

[0400] The server receives and analyzes health and emotion data sent from the user's device. The analyzed data is processed by a natural language processing module and passed to the generative AI model. The server is built using cloud services such as AWS and Microsoft Azure.

[0401] Natural Language Processing Module

[0402] The natural language processing module analyzes text data entered by the user and extracts its intent and keywords. For example, an input sentence such as "Recently, the environment at work has been causing me stress" is parsed into the keywords "stress" and "work environment." This module uses Google's BERT model and OpenAI's GPT series.

[0403] Generative AI Models

[0404] The generative AI model generates appropriate advice based on the analysis results and emotion data received from the natural language processing module. For example, advice such as "For stress-related issues, we recommend taking regular breaks or consulting with a manager" is automatically generated. This is done using TensorFlow or PyTorch.

[0405] Knowledge Base

[0406] A knowledge base is a database curated by trusted experts. Generative AI models refer to this database and use it to provide optimal advice. Databases such as MongoDB and PostgreSQL are commonly used.

[0407] Emotion Engine

[0408] The emotion engine analyzes the user's facial expressions and voice to generate emotion data, which then adjusts the tone of the generated advice appropriately. The emotion engine uses AWS Rekognition and the Microsoft Azure Emotion API.

[0409] Specific examples

[0410] 1. The user enters into the app, "Recently, my work environment has been causing me stress."

[0411] 2. The emotion engine analyzes the user's facial expressions and voice to detect anxiety.

[0412] 3. The natural language processing module extracts the keywords "stress" and "work environment."

[0413] 4. The generative AI model references the knowledge base and generates appropriate advice.

[0414] 5. Adjust the tone of your advice based on emotional data.

[0415] 6. The adjusted advice is sent to the user terminal.

[0416] Prompt Sentence Examples

[0417] Employee A enters his recent health condition into the app: "Recently, my work environment has been causing me stress." The emotion engine detects A's anxiety and generates appropriate advice based on the analysis results and emotional data.

[0418] This allows the system to monitor the user's health status in real time and provide appropriate advice quickly, taking into account their emotional state.

[0419] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0420] Step 1:

[0421] A user uses a smartphone app to input questions or symptoms about their health. For example, they input text such as, "Recently, my work environment has been causing me stress." The input data also includes emotional data obtained from the user's facial expressions and voice. This captures emotional data (e.g., anxiety, stress level).

[0422] Step 2:

[0423] The device sends the entered health question, symptoms, and emotional data to a server. The sent data includes text data and emotional data (obtained through facial recognition and voice analysis). This data is stored on the server and used for analysis.

[0424] Step 3:

[0425] The server passes the received questions, symptoms, and emotional data to a natural language processing module. This module analyzes the input text data and extracts key keywords (e.g., "stress" and "work environment"). It also analyzes the emotional data to clarify the user's emotional state.

[0426] Step 4:

[0427] The analysis results and emotion data obtained from the natural language processing module are passed to a generative AI model. The generative AI model generates appropriate advice based on the input data. At this time, the model references its knowledge base and generates the advice it deems most appropriate. For example, the generated advice might be, "Regarding the cause of stress, we recommend taking regular breaks and consulting with your manager."

[0428] Step 5:

[0429] The generated advice is tone-adjusted based on the emotional data. For example, if the user is feeling anxious, the generated advice will be delivered in a gentle tone. The tone adjustment is performed by a special module in the server.

[0430] Step 6:

[0431] The server sends the tone-adjusted advice to the user's device, where the user can review the advice through a smartphone app. The advice is optimized based on the user's questions, symptoms, and emotional state.

[0432] Step 7:

[0433] Users can provide feedback on the advice provided to the app, which then sends the feedback data back to the server and uses it as training data for the generative AI model, allowing the system to improve the accuracy of future responses.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] [Second embodiment]

[0438] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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."

[0450] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[0451] System Configuration

[0452] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0453] User terminal

[0454] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[0455] server

[0456] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[0457] Natural Language Processing Module

[0458] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0459] Generative AI Models

[0460] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[0461] Medical Knowledge Base

[0462] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[0463] Program processing

[0464] The program of this system is processed as follows.

[0465] User Registration and Login

[0466] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0467] Enter and submit your question

[0468] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[0469] Parsing questions and generating answers

[0470] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[0471] Collecting user feedback

[0472] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0473] Through the above process, this system provides users with reliable medical information and reduces the burden on medical professionals.

[0474] The processing flow will be explained below.

[0475] Step 1:

[0476] The user downloads the application and installs it on the device.

[0477] Step 2:

[0478] The user opens the account creation screen on their device and enters their name, age, and email address.

[0479] Step 3:

[0480] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[0481] Step 4:

[0482] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[0483] Step 5:

[0484] The server will send a confirmation email containing an authentication code to the user's email address.

[0485] Step 6:

[0486] The user enters the authentication code received via email into the authentication screen within the application.

[0487] Step 7:

[0488] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[0489] Step 8:

[0490] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[0491] Step 9:

[0492] The terminal receives the token and sets the user to a logged-in state.

[0493] Step 10:

[0494] The user uses the terminal to input medical questions and symptoms and send the question.

[0495] Step 11:

[0496] The terminal generates a request to transmit the input question information to the server, and transmits the request to the server.

[0497] Step 12:

[0498] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question.

[0499] Step 13:

[0500] The natural language processing module returns the analysis results to the server.

[0501] Step 14:

[0502] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[0503] Step 15:

[0504] The generative AI model references a curated medical knowledge base to generate appropriate answers.

[0505] Step 16:

[0506] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[0507] Step 17:

[0508] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[0509] Step 18:

[0510] The user inputs feedback on the provided answers and transmits it from the terminal to the server.

[0511] Step 19:

[0512] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[0513] Step 20:

[0514] The server stores the received feedback in a database and updates the training data for the generative AI model.

[0515] The above is a specific processing flow of the entire system.

[0516] Example 1

[0517] 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."

[0518] Many users today require fast and reliable answers to their medical questions and symptoms. However, current systems require users to search for medical information on their own, and the information they receive is often inaccurate and unreliable. Furthermore, the burden on medical professionals is increasing, requiring more efficient responses. An effective system is needed to address these issues.

[0519] 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.

[0520] In this invention, the server includes means for accepting medical input from a user, means for transmitting the input information to a central processing unit via a communication network, means for analyzing the information received by the central processing unit using a natural language processing module, means for generating an answer based on the analysis result using a generative AI model, means for transmitting the generated answer to the user's terminal, and means for receiving feedback from the user and updating the learning data of the generative AI model. This allows users to obtain reliable medical information quickly and reduces the burden on medical professionals.

[0521] "User" refers to an individual who utilizes the system to provide medical input.

[0522] "Input" refers to the act of a user providing information such as medical questions or symptoms to the system.

[0523] "Communications network" refers to a digital network for transmitting information from user terminals to a central processing unit (server).

[0524] "Central Processing Unit" refers to the server that analyzes and processes information received from the user and generates a response.

[0525] A "natural language processing module" refers to a software component that analyzes user input and extracts its intent and keywords.

[0526] "Generative AI model" refers to an artificial intelligence model that generates appropriate answers based on the analysis results of a natural language processing module.

[0527] "Answer" refers to medical information or advice generated by a generative AI model.

[0528] "Terminal" refers to the device (e.g., smartphone, tablet, computer, etc.) used by a user to provide input and receive responses from the system.

[0529] "Feedback" refers to the evaluation or opinion a user gives on a provided answer.

[0530] "Training data" refers to data used to improve the performance and accuracy of generative AI models.

[0531] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[0532] System Configuration

[0533] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0534] User terminal

[0535] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[0536] server

[0537] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[0538] Natural Language Processing Module

[0539] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0540] Generative AI Models

[0541] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[0542] Medical Knowledge Base

[0543] A medical knowledge base is a database of reliable medical information curated by experts, which serves as a source of information for generative AI models to generate appropriate answers.

[0544] Program processing explanation

[0545] User Registration and Login

[0546] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0547] Enter and submit your question

[0548] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[0549] Parsing questions and generating answers

[0550] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[0551] Collecting user feedback

[0552] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0553] Examples of specific examples and prompts

[0554] Specific examples

[0555] If a user asks, "I have a persistent headache, but medicine isn't helping," the question is sent from the device to the server and analyzed by a natural language processing module. Based on the analysis results, the generative AI model considers various possibilities regarding the headache and generates an appropriate answer. This answer is then sent to the user's device.

[0556] Prompt Sentence Examples

[0557] 1. "When a user submits a headache question, please describe how it is parsed and an answer generated."

[0558] 2. "Please specifically show how your generative AI model would respond if the headache had lasted for several weeks."

[0559] In this way, this system provides users with reliable medical information and reduces the burden on medical professionals.

[0560] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0561] Step 1: User Registration and Login

[0562] What happens: A user downloads an application and enters basic information such as name, age, and email address.

[0563] Input: Basic information (name, age, email address, etc.)

[0564] Output: The user information is saved in the database and a confirmation email is sent.

[0565] Detailed description: The device generates an API request to send the entered basic information to the server. The server receives this information and stores it in a database. The server then sends a confirmation email to the user's email address. The user enters the authentication code received in the email into the application, and the server verifies the information and sets the user to logged in.

[0566] Step 2: Enter and submit your question

[0567] What it does: A user enters a medical question or symptom through the application.

[0568] Input: User's question or symptom

[0569] Output: The question is sent to the server.

[0570] Detailed description: The device generates an API request to send the entered medical question or symptoms to the server. The generated API request is sent to the server via a communication network. The server stores the received question in a database.

[0571] Step 3: Parsing the Question

[0572] Specific operation: The server forwards the received question to the natural language processing module.

[0573] Input: Question (question or symptom submitted by the user)

[0574] Output: Analysis results (intention and keywords)

[0575] Detailed explanation: The natural language processing module analyzes the question and identifies its intent and keywords. For example, if the question is "I've had a headache for several weeks, and it hasn't gone away even after taking medicine," the NLP module extracts keywords such as "headache," "several weeks," and "medicine isn't working." The analysis results are then sent to the generative AI model.

[0576] Step 4: Generate an answer

[0577] Specific operation: The generative AI model generates an answer based on the analysis results.

[0578] Input: Analysis results (intention and keywords)

[0579] Output: Medical answers

[0580] Detailed description: The generative AI model generates appropriate answers from a medically supervised medical knowledge base. Based on the analysis results, the model generates a specific answer such as "You may have a chronic headache and we recommend that you consult a doctor." This answer is sent to the server.

[0581] Step 5: Submit your response

[0582] Specific operation: The server sends the generated answer to the user's device.

[0583] Input: Answer (medical information provided by the generative AI model)

[0584] Output: Send the answer to the user's terminal

[0585] Detailed description: The server checks the generated answer and sends it to the user's device, where the user receives the answer on the application screen.

[0586] Step 6: Gather feedback

[0587] Specific Actions: The user enters feedback on the answers provided.

[0588] Input: Feedback (user ratings and opinions)

[0589] Output: Save the feedback to a database and use it to update the generative AI model

[0590] Detailed description: The user inputs feedback about the provided answer, such as "It was very easy to understand." The device generates an API request to send this feedback to the server, and sends it to the server. The server receives the feedback and stores it in a database. This feedback is also used as training data for the generative AI model, contributing to improving the model's performance.

[0591] The above is a detailed description of the specific processing flow of this system and the inputs and outputs at each step.

[0592] (Application example 1)

[0593] 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."

[0594] When users have medical questions or symptoms, it is difficult to easily obtain reliable medical information. Furthermore, the inability to obtain medical information immediately when shopping in physical stores or using services reduces user satisfaction. Furthermore, the inability to efficiently recommend health products and services in physical stores makes it difficult to increase sales or meet customer needs.

[0595] 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.

[0596] In this invention, the server includes means for registering and storing basic user information, means for authenticating based on the registered user information, means for inputting medical questions and symptoms from the user, means for transmitting the input questions and symptoms to the server, means for analyzing the questions and symptoms received by the server, means for generating appropriate answers using a generative AI model based on the analysis results, means for transmitting the generated answers to the user, means for receiving feedback from the user and updating the learning data of the generative AI model, means for the user to input questions and symptoms using a robot in a physical store, means for displaying the answers generated by the robot by voice and on a screen, means for recommending products and services in the physical store, means for analyzing the questions and symptoms from the user using a natural language processing module, and means for generating answers from a curated medical knowledge base. This allows users to instantly obtain reliable medical information in a physical store, and enables accurate recommendations of health products and services.

[0597] The "means for users to input medical questions and symptoms" refers to a device that provides an interface for users to input questions about their own health condition and symptoms using the robot's touch screen, etc.

[0598] The "means for transmitting input questions and symptoms to a server" is a communication device for transmitting information input by a user to a remote server via the Internet or the like.

[0599] The "means for analyzing questions and symptoms received at the server" is a software module for analyzing user questions and symptoms sent to the server and extracting their intent and key keywords.

[0600] "Means for generating appropriate answers using a generative AI model based on the analysis results" refers to a device that uses a generative AI model to generate appropriate answers based on data analyzed through natural language processing.

[0601] The "means for transmitting the generated answer to the user" is a communication device that transmits the generated answer back to the robot or touch screen used by the user by displaying or audibly transmitting the answer.

[0602] The "means for receiving feedback from users and updating the learning data of the generative AI model" refers to a database and update function for collecting feedback provided by users and using it as training data for the generative AI model.

[0603] "A means for users to input questions and symptoms using a robot within a physical store" refers to a device that allows users to input medical questions and symptoms using a touch screen or the like on a robot placed within a physical store.

[0604] "Means for the robot to display the generated answers by voice and on a screen" is a function that enables the robot to explain the generated medical information and product recommendations by voice and simultaneously display them on a touch screen.

[0605] "Means for recommending products and services in physical stores" is a function that allows the robot to recommend related health products and services based on the user's questions and symptoms.

[0606] A "natural language processing module" is a software module that analyzes text data of questions and symptoms received from users, extracts intent and keywords, and passes them on to the next process.

[0607] A "supervised medical knowledge base" is a database that stores reliable medical information that has been verified by medical specialists.

[0608] This invention relates to a system that allows users to input medical questions and symptoms in a physical store and obtain reliable medical information in real time. This system is broadly composed of a user terminal (a robot touch screen), a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0609] User terminal

[0610] A robot placed in a physical store is used as a means for users to input their questions and symptoms. The robot is equipped with a touchscreen, providing an interface for users to input directly. The robot then provides the generated answers to the user via voice and on the screen, and also recommends related health products and services.

[0611] server

[0612] The server receives questions and symptoms sent by users and analyzes them. The server works as follows:

[0613] 1. The user uses the robot in a physical store to input their questions or symptoms, and the input information is sent to the server.

[0614] 2. The server forwards the received questions and symptoms to the natural language processing module, which analyzes the intent and keywords.

[0615] 3. Based on the analysis results, a generative AI model is used to generate an appropriate answer.

[0616] 4. The generated answer is sent back to the robot via the server and provided to the user.

[0617] 5. The user enters feedback on the provided answer, and the server uses that feedback as training data for the generative AI model.

[0618] Natural Language Processing Module

[0619] The natural language processing module (NLP module) analyzes the user's inputted question or symptom to identify their intent and key keywords. This provides the basis for the generative AI model to generate appropriate answers. Specifically, NLP libraries such as SpaCy and NLTK are used.

[0620] Generative AI Models

[0621] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module. Generative models such as GPT-3 and OpenAI are used to provide users with reliable medical information.

[0622] Medical Knowledge Base

[0623] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[0624] Specific examples

[0625] The user types a question into the robot's touchscreen: "I have a persistent cough. What product do you recommend?" This information is sent to the server, which uses a natural language processing module to extract keywords such as "cough," "product," and "recommendation." The generative AI model then uses this information to create a prompt and generate an appropriate answer. For example, the generated answer might be, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The robot provides this answer to the user both aloud and on the screen, and also guides them to products in specific locations in the store.

[0626] Prompt Sentence Examples

[0627] I have a persistent cough. Which product would you recommend?

[0628] The above is a specific embodiment for carrying out the present invention. This system allows users to instantly obtain reliable medical information even in physical stores, making it easy to select health products and services. Furthermore, by collecting feedback, the accuracy of the entire system can be improved.

[0629] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0630] Step 1:

[0631] A user uses the robot's touchscreen in a brick-and-mortar store to input their medical question or symptoms, such as "I have a persistent cough. What product would you recommend?" This input data is stored in the robot's internal system.

[0632] Step 2:

[0633] The device sends the entered question or symptom to the server. At this time, an API request including the input data is generated and sent to the server via the Internet. The input data (user question) is received at the server's API endpoint.

[0634] Step 3:

[0635] The server passes the received question to a natural language processing module, which first analyzes the text data and extracts key keywords such as "cough," "product," and "recommendation." The input data is then processed based on this, and keywords are generated as the analysis results.

[0636] Step 4:

[0637] Based on the analysis results, the server creates and sends a prompt to the generative AI model. This prompt is formatted as "I have a persistent cough. What products do you recommend?" The prompt is then input to the generative AI model (such as GPT-3).

[0638] Step 5:

[0639] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The answer text is returned to the server as output data from the generative AI model.

[0640] Step 6:

[0641] The server forwards the generated answer to the robot. This answer data is again sent as an API request and received by the robot. The robot then tells the user by voice and on the screen, "As a product that is effective for coughs, we recommend cough syrup sold at pharmacies."

[0642] Step 7:

[0643] The user inputs feedback on the provided answer into the robot's touchscreen, for example, "This answer was helpful."

[0644] Step 8:

[0645] The device sends the user's feedback to the server, and an API request containing the feedback data is generated again and sent to the server.

[0646] Step 9:

[0647] The server stores the received feedback in a database and uses this data as training data for the generative AI model, which improves the accuracy of the generative AI model and the quality of answers from the next time onwards.

[0648] 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.

[0649] This invention relates to a system that allows users to input medical questions and symptoms and generates appropriate answers. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond according to the user's emotional state. This system provides reliable medical information, alleviating user anxiety and reducing the burden on medical professionals.

[0650] System Configuration

[0651] The system consists of the following main components: a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[0652] User terminal

[0653] The user terminal provides an interface for users to input medical questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or personal computer. In addition, the user terminal is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice, and also has the function of sending this information to the server.

[0654] server

[0655] The server receives questions, symptoms, and emotional data sent by users and performs analysis and answer generation. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The generative AI model generates appropriate answers from a medical knowledge base and sends them to the user's device. It also adjusts the tone of the answers based on the emotional data and collects feedback.

[0656] Natural Language Processing Module

[0657] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0658] Generative AI Models

[0659] The generative AI model generates answers from a curated medical knowledge base based on the analysis results and emotion data received from the natural language processing module, and also has the ability to adjust the tone of the answer based on data from the emotion engine.

[0660] Medical Knowledge Base

[0661] A medical knowledge base is a database of reliable medical information curated by medical experts, which serves as the primary source of information for generative AI models to generate appropriate answers.

[0662] Emotion Engine

[0663] The emotion engine is a module that recognizes emotions from the user's facial expressions and voice when they input their questions or symptoms. The emotion data recognized by the emotion engine is sent to the server and used for subsequent interviews and answer generation.

[0664] Program processing

[0665] The program of this system is processed in the following manner.

[0666] 1. User Registration and Login

[0667] The user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0668] 2. Enter and submit your question

[0669] The user inputs medical questions and symptoms using the device and sends the question. The emotion engine recognizes the user's emotions and sends the emotion data to the server. The device then generates a request to send this information to the server and sends it to the server.

[0670] 3. Question Analysis and Answer Generation

[0671] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results and emotional data are passed to a generative AI model, which then generates an appropriate answer from a medical knowledge base. The tone of the generated answer is adjusted based on the emotional data, and the answer is sent to the user's device via the server.

[0672] 4. Collecting User Feedback

[0673] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0674] Specific examples

[0675] For example, suppose a user inputs a question such as "I've been having headaches lately due to work stress," and the emotion engine detects anxiety and stress. The server receives this, and the natural language processing module extracts keywords such as "stress" and "headache," and passes the analysis results to the generative AI model. The generative AI model then generates an answer on "how to deal with stress-related headaches" from a medical knowledge base, such as "Relaxation techniques and lifestyle changes are effective for headaches caused by stress. We recommend that you see a doctor for a detailed diagnosis." Based on the emotion engine's data, the tone of the answer is adjusted to be calming. The user confirms this and enters feedback such as "This was helpful," and the system collects this feedback to improve the AI ​​model's performance.

[0676] The above is an embodiment of the present invention. In this way, the system can provide the user with prompt and appropriate medical information, while also responding appropriately to the user's emotions.

[0677] The processing flow will be explained below.

[0678] Step 1:

[0679] The user downloads the application and installs it on the device.

[0680] Step 2:

[0681] The user opens the account creation screen on their device and enters their name, age, and email address.

[0682] Step 3:

[0683] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[0684] Step 4:

[0685] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[0686] Step 5:

[0687] The server will send a confirmation email containing an authentication code to the user's email address.

[0688] Step 6:

[0689] The user enters the authentication code received via email into the authentication screen within the application.

[0690] Step 7:

[0691] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[0692] Step 8:

[0693] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[0694] Step 9:

[0695] The terminal receives the token and sets the user to a logged-in state.

[0696] Step 10:

[0697] Users use the terminal to input medical questions and symptoms.

[0698] Step 11:

[0699] The emotion engine recognizes emotions from the user's facial expressions and voice and acquires emotion data.

[0700] Step 12:

[0701] The device generates a request to send information about the question or symptom and emotional data to the server, and sends it to the server.

[0702] Step 13:

[0703] The server transfers the received information to a natural language processing module, which analyzes the intent and keywords of the question.

[0704] Step 14:

[0705] The natural language processing module returns the analysis results to the server.

[0706] Step 15:

[0707] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[0708] Step 16:

[0709] The generative AI model references a medical knowledge base to generate appropriate answers and adjusts the tone of the answer based on emotional data.

[0710] Step 17:

[0711] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[0712] Step 18:

[0713] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[0714] Step 19:

[0715] The user enters feedback on the answers provided, and the feedback is also transmitted from the terminal to the server.

[0716] Step 20:

[0717] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[0718] Step 21:

[0719] The server stores the received feedback in a database and uses it as training data for the generative AI model.

[0720] Step 22:

[0721] The server uses emotional data and past feedback to improve the accuracy and personalization of future question answers.

[0722] Example 2

[0723] 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."

[0724] In today's medical field, there is a demand for fast and appropriate medical information, but the burden on medical professionals is becoming a problem. In particular, when users input medical questions or symptoms, it is difficult to provide appropriate answers to those questions or symptoms, and responses that are not adequately responsive to the user's emotions are not being provided. Therefore, it is important to alleviate users' anxiety and reduce the burden on medical professionals.

[0725] 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.

[0726] In this invention, the server includes means for inputting medical questions and symptoms from a user, means for transmitting the input questions and symptoms, means for analyzing the questions and symptoms, means for generating appropriate answers using a generative AI model, means for transmitting the generated answers to the user, means for recognizing the user's emotions and acquiring emotional data, means for adjusting the tone of the answers based on the emotional data, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to quickly provide appropriate answers to the questions and symptoms input by users and responses tailored to each individual's emotions.

[0727] "User" refers to a person who enters a medical question or symptom or provides feedback in response to a question.

[0728] "Terminal" refers to a device that allows users to input medical questions and symptoms and send them to a server. Examples of such devices include smartphones, tablets, and personal computers.

[0729] "Server" refers to a central computer system that receives questions and symptoms sent by users, analyzes them, generates appropriate answers, and sends them to the users.

[0730] A "natural language processing module" refers to a software module that analyzes questions and symptoms entered by users and extracts their intent and keywords.

[0731] A "generative AI model" refers to an artificial intelligence model that generates appropriate answers from a medical knowledge base based on the results analyzed by a natural language processing module.

[0732] A "medical knowledge base" refers to a database that accumulates medical information supervised by specialist doctors and medical institutions.

[0733] An "emotion engine" refers to a module that recognizes emotions from the user's facial expressions and voice and acquires that emotion data.

[0734] "Emotion data" refers to information about a user's emotions recognized by the emotion engine.

[0735] "Answer tone adjustment" refers to the process of ensuring that generated answers are delivered in an appropriate tone depending on the user's emotions.

[0736] "Feedback" refers to the act of a user inputting their opinion on the usefulness and satisfaction of a provided answer.

[0737] The present invention is a system that allows users to input medical questions and symptoms and provides appropriate answers to those questions. The system includes a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[0738] System Configuration

[0739] User terminal

[0740] The user terminal is a device that allows users to input medical questions and symptoms. Users use a smartphone, tablet, or personal computer to create an account, log in, enter questions, and provide feedback. The user terminal also incorporates an emotion engine that uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This emotion data is sent to the server in real time.

[0741] server

[0742] The server is a central computer system that receives questions and emotional data sent by users, analyzes them, and generates answers. The server sends the received questions to a natural language processing module and obtains analysis results. The analysis results and emotional data are then passed to a generative AI model, which generates an appropriate answer. The tone of the generated answer is adjusted based on the emotional data and sent to the user's device.

[0743] Natural Language Processing Module

[0744] The natural language processing module (NLP module) is software that analyzes user-entered questions and symptoms. This module extracts intent and keywords from the input text and provides the basis for answer generation by generative AI models.

[0745] Generative AI Models

[0746] The generative AI model is an artificial intelligence model that generates appropriate answers from a curated medical knowledge base based on the analysis results and emotional data received from the natural language processing module, and also has the ability to adjust the tone of the answer taking into account the emotional data.

[0747] Medical Knowledge Base

[0748] A medical knowledge base is a database of reliable medical information supervised by specialist doctors and medical institutions. A generative AI model references this database to generate appropriate answers to user questions.

[0749] Emotion Engine

[0750] The emotion engine is a module that recognizes emotions from facial expressions and voice when a user inputs a question or symptom. This engine sends the recognized emotion data to the server in real time and reflects it in generating an answer.

[0751] Specific examples

[0752] For example, consider the case where a user enters the question, "I've been having headaches lately due to work stress." When this question is entered, the emotion engine recognizes the user's anxiety and stress. The server sends the received question to a natural language processing module, which extracts keywords such as "stress" and "headache." The analysis results are passed to a generative AI model, which generates an answer on "how to deal with stress-related headaches" from a medical knowledge base. This answer might be something like, "For headaches caused by stress, relaxation techniques and lifestyle changes are effective. I recommend seeing a doctor for a detailed diagnosis." Furthermore, based on the emotion data, the tone of the answer is adjusted to be calmer.

[0753] An example prompt might look like this:

[0754] "I've been having headaches lately because of work stress. What should I do?"

[0755] In this way, the system provides users with prompt and appropriate medical information and responds to their emotions, thereby reducing user anxiety and the burden on medical professionals.

[0756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0757] Program processing flow

[0758] Step 1: User Registration and Login

[0759] The user creates an account using the device. The user's input information (name, age, email address) is sent from the device to the server. The server stores this information in a database and generates a confirmation email that is sent to the user's email address. The user then enters the authentication code they received, and the device sends the code to the server. Once authentication is complete, the user is logged in.

[0760] Input: User's name, age, email address, verification code

[0761] Processing: Sending and storing information, generating and verifying authentication codes

[0762] Output:Login status

[0763] Step 2: Enter your question

[0764] Users input their medical questions and symptoms using a device. The emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The acquired emotional data and information about the questions and symptoms are then sent from the device to the server.

[0765] Input: User's questions, symptoms, facial expressions, and voice

[0766] Processing: Entering questions and symptoms, acquiring and sending emotional data

[0767] Output: Question, symptom, and emotion data sent to the server

[0768] Step 3: Parsing the Question

[0769] The server transfers the received question and emotion data to the natural language processing module, which analyzes the text of the question or symptom to extract the intent and important keywords. The extracted analysis results are returned to the server.

[0770] Input: Question, Symptoms, and Emotional Data

[0771] Processing: Text analysis and keyword extraction using natural language processing modules

[0772] Output: Extracted intent and important keywords

[0773] Step 4: Generate an answer

[0774] The server passes the analysis results and emotional data to the generative AI model, which then generates an appropriate answer from a medical knowledge base based on the analysis results, adjusts the tone of the answer based on the emotional data, and returns the generated answer to the server.

[0775] Input: Analysis results, emotion data

[0776] Processing: Answer generation using generative AI model, tone adjustment

[0777] Output: The generated answer

[0778] Step 5: Submit your response

[0779] The server sends the generated answer to the user's terminal, which displays the answer to the user.

[0780] Input: Generated Answer

[0781] Action: Send response

[0782] Output: Answer displayed on the user's device

[0783] Step 6: Gather feedback

[0784] The user enters feedback on the provided answers, and the device sends the feedback to the server, which stores it in a database and uses it as training data for the generative AI model.

[0785] Input: User feedback

[0786] Action: Send and save feedback

[0787] Output: Saved feedback data

[0788] Specific examples of processing

[0789] Step 1: The user downloads the application and enters their name, age, and email address. The server then sends a confirmation email, confirming the entry of a verification code.

[0790] Step 2: The user enters "I've been having headaches lately because of work stress," and the emotion engine recognizes anxiety and stress. The data is sent to the server.

[0791] Step 3: The natural language processing module extracts keywords such as "stress" and "headache" and returns the analysis results to the server.

[0792] Step 4: The generative AI model consults a medical knowledge base and generates an answer about "how to deal with stress-related headaches," adjusting the tone to be calming.

[0793] Step 5: The server sends the answer to the user's terminal, and the user confirms the answer.

[0794] Step 6: The user enters feedback such as "It was helpful" and the server stores it in the database.

[0795] In this way, the system provides the user with appropriate medical information and responds according to the user's emotions.

[0796] (Application example 2)

[0797] 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."

[0798] In recent years, many companies and facilities have been required to monitor the health status of their employees in real time and take appropriate measures. Especially in large-scale facilities, it is difficult to monitor the health status of many employees individually, making an effective health management system necessary. Furthermore, taking into account employees' emotional state and stress level would enable more accurate responses. However, conventional health monitoring systems lack the ability to analyze emotional states or adjust tone in real time, making it difficult to take prompt and appropriate action.

[0799] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting questions and symptoms related to health status from a user, means for transmitting the input questions, symptoms, and emotional data to the server, means for analyzing the questions, symptoms, and emotional data received in the server, means for generating appropriate advice using a generative AI model based on the analysis results, means for adjusting the tone of the generated advice and transmitting it to the user, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to monitor the health status of employees in real time and quickly take appropriate measures that take their emotional state into consideration.

[0800] "Health status" refers to the physical and mental condition of the user, and refers to questions and symptoms input by the user.

[0801] "Emotion data" refers to data that indicates the emotional state of the user analyzed from their facial expressions and voice.

[0802] "Server" refers to a computer system that analyzes received data and generates and sends appropriate advice.

[0803] "Analysis means" refers to methods and technologies for understanding the input question, symptoms, and emotion data and extracting appropriate information.

[0804] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates appropriate advice based on input data.

[0805] "Tone adjustment" refers to adjusting the tone and expression of generated advice to match the user's emotional state.

[0806] "Feedback" refers to the user's reaction and evaluation of the advice provided, and is information used to improve the system.

[0807] "Training data" refers to the data, including feedback, that a generative AI model uses to generate more accurate advice.

[0808] This invention relates to a system that analyzes a user's health-related questions and symptoms in real time and provides appropriate advice based on emotional data. The system mainly consists of the following components: a user terminal, a server, a natural language processing module, a generative AI model, a knowledge base, and an emotional engine.

[0809] User terminal

[0810] The user device is provided as a smartphone app. This app has a means for the user to input their health status and acquire emotional data from facial expressions and voice in real time. For example, if a user inputs "Recently, my work environment has been causing me stress," the device analyzes it and captures emotional data such as anxiety from facial expressions.

[0811] server

[0812] The server receives and analyzes health and emotion data sent from the user's device. The analyzed data is processed by a natural language processing module and passed to the generative AI model. The server is built using cloud services such as AWS and Microsoft Azure.

[0813] Natural Language Processing Module

[0814] The natural language processing module analyzes text data entered by the user and extracts its intent and keywords. For example, an input sentence such as "Recently, the environment at work has been causing me stress" is parsed into the keywords "stress" and "work environment." This module uses Google's BERT model and OpenAI's GPT series.

[0815] Generative AI Models

[0816] The generative AI model generates appropriate advice based on the analysis results and emotion data received from the natural language processing module. For example, advice such as "For stress-related issues, we recommend taking regular breaks or consulting with a manager" is automatically generated. This is done using TensorFlow or PyTorch.

[0817] Knowledge Base

[0818] A knowledge base is a database curated by trusted experts. Generative AI models refer to this database and use it to provide optimal advice. Databases such as MongoDB and PostgreSQL are commonly used.

[0819] Emotion Engine

[0820] The emotion engine analyzes the user's facial expressions and voice to generate emotion data, which then adjusts the tone of the generated advice appropriately. The emotion engine uses AWS Rekognition and the Microsoft Azure Emotion API.

[0821] Specific examples

[0822] 1. The user enters into the app, "Recently, my work environment has been causing me stress."

[0823] 2. The emotion engine analyzes the user's facial expressions and voice to detect anxiety.

[0824] 3. The natural language processing module extracts the keywords "stress" and "work environment."

[0825] 4. The generative AI model references the knowledge base and generates appropriate advice.

[0826] 5. Adjust the tone of your advice based on emotional data.

[0827] 6. The adjusted advice is sent to the user terminal.

[0828] Prompt Sentence Examples

[0829] Employee A enters his recent health condition into the app: "Recently, my work environment has been causing me stress." The emotion engine detects A's anxiety and generates appropriate advice based on the analysis results and emotional data.

[0830] This allows the system to monitor the user's health status in real time and provide appropriate advice quickly, taking into account their emotional state.

[0831] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0832] Step 1:

[0833] A user uses a smartphone app to input questions or symptoms about their health. For example, they input text such as, "Recently, my work environment has been causing me stress." The input data also includes emotional data obtained from the user's facial expressions and voice. This captures emotional data (e.g., anxiety, stress level).

[0834] Step 2:

[0835] The device sends the entered health question, symptoms, and emotional data to a server. The sent data includes text data and emotional data (obtained through facial recognition and voice analysis). This data is stored on the server and used for analysis.

[0836] Step 3:

[0837] The server passes the received questions, symptoms, and emotional data to a natural language processing module. This module analyzes the input text data and extracts key keywords (e.g., "stress" and "work environment"). It also analyzes the emotional data to clarify the user's emotional state.

[0838] Step 4:

[0839] The analysis results and emotion data obtained from the natural language processing module are passed to a generative AI model. The generative AI model generates appropriate advice based on the input data. At this time, the model references its knowledge base and generates the advice it deems most appropriate. For example, the generated advice might be, "Regarding the cause of stress, we recommend taking regular breaks and consulting with your manager."

[0840] Step 5:

[0841] The generated advice is tone-adjusted based on the emotional data. For example, if the user is feeling anxious, the generated advice will be delivered in a gentle tone. The tone adjustment is performed by a special module in the server.

[0842] Step 6:

[0843] The server sends the tone-adjusted advice to the user's device, where the user can review the advice through a smartphone app. The advice is optimized based on the user's questions, symptoms, and emotional state.

[0844] Step 7:

[0845] Users can provide feedback on the advice provided to the app, which then sends the feedback data back to the server and uses it as training data for the generative AI model, allowing the system to improve the accuracy of future responses.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] [Third embodiment]

[0850] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0851] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0852] 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).

[0853] 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.

[0854] 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.

[0855] 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).

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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."

[0862] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[0863] System Configuration

[0864] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0865] User terminal

[0866] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[0867] server

[0868] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[0869] Natural Language Processing Module

[0870] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0871] Generative AI Models

[0872] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[0873] Medical Knowledge Base

[0874] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[0875] Program processing

[0876] The program of this system is processed as follows.

[0877] User Registration and Login

[0878] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0879] Enter and submit your question

[0880] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[0881] Parsing questions and generating answers

[0882] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[0883] Collecting user feedback

[0884] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0885] Through the above process, this system provides users with reliable medical information and reduces the burden on medical professionals.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] The user downloads the application and installs it on the device.

[0889] Step 2:

[0890] The user opens the account creation screen on their device and enters their name, age, and email address.

[0891] Step 3:

[0892] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[0893] Step 4:

[0894] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[0895] Step 5:

[0896] The server will send a confirmation email containing an authentication code to the user's email address.

[0897] Step 6:

[0898] The user enters the authentication code received via email into the authentication screen within the application.

[0899] Step 7:

[0900] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[0901] Step 8:

[0902] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[0903] Step 9:

[0904] The terminal receives the token and sets the user to a logged-in state.

[0905] Step 10:

[0906] The user uses the terminal to input medical questions and symptoms and send the question.

[0907] Step 11:

[0908] The terminal generates a request to transmit the input question information to the server, and transmits the request to the server.

[0909] Step 12:

[0910] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question.

[0911] Step 13:

[0912] The natural language processing module returns the analysis results to the server.

[0913] Step 14:

[0914] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[0915] Step 15:

[0916] The generative AI model references a curated medical knowledge base to generate appropriate answers.

[0917] Step 16:

[0918] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[0919] Step 17:

[0920] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[0921] Step 18:

[0922] The user inputs feedback on the provided answers and transmits it from the terminal to the server.

[0923] Step 19:

[0924] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[0925] Step 20:

[0926] The server stores the received feedback in a database and updates the training data for the generative AI model.

[0927] The above is a specific processing flow of the entire system.

[0928] Example 1

[0929] 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."

[0930] Many users today require fast and reliable answers to their medical questions and symptoms. However, current systems require users to search for medical information on their own, and the information they receive is often inaccurate and unreliable. Furthermore, the burden on medical professionals is increasing, requiring more efficient responses. An effective system is needed to address these issues.

[0931] 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.

[0932] In this invention, the server includes means for accepting medical input from a user, means for transmitting the input information to a central processing unit via a communication network, means for analyzing the information received by the central processing unit using a natural language processing module, means for generating an answer based on the analysis result using a generative AI model, means for transmitting the generated answer to the user's terminal, and means for receiving feedback from the user and updating the learning data of the generative AI model. This allows users to obtain reliable medical information quickly and reduces the burden on medical professionals.

[0933] "User" refers to an individual who utilizes the system to provide medical input.

[0934] "Input" refers to the act of a user providing information such as medical questions or symptoms to the system.

[0935] "Communications network" refers to a digital network for transmitting information from user terminals to a central processing unit (server).

[0936] "Central Processing Unit" refers to the server that analyzes and processes information received from the user and generates a response.

[0937] A "natural language processing module" refers to a software component that analyzes user input and extracts its intent and keywords.

[0938] "Generative AI model" refers to an artificial intelligence model that generates appropriate answers based on the analysis results of a natural language processing module.

[0939] "Answer" refers to medical information or advice generated by a generative AI model.

[0940] "Terminal" refers to the device (e.g., smartphone, tablet, computer, etc.) used by a user to provide input and receive responses from the system.

[0941] "Feedback" refers to the evaluation or opinion a user gives on a provided answer.

[0942] "Training data" refers to data used to improve the performance and accuracy of generative AI models.

[0943] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[0944] System Configuration

[0945] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[0946] User terminal

[0947] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[0948] server

[0949] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[0950] Natural Language Processing Module

[0951] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[0952] Generative AI Models

[0953] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[0954] Medical Knowledge Base

[0955] A medical knowledge base is a database of reliable medical information curated by experts, which serves as a source of information for generative AI models to generate appropriate answers.

[0956] Program processing explanation

[0957] User Registration and Login

[0958] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[0959] Enter and submit your question

[0960] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[0961] Parsing questions and generating answers

[0962] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[0963] Collecting user feedback

[0964] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[0965] Examples of specific examples and prompts

[0966] Specific examples

[0967] If a user asks, "I have a persistent headache, but medicine isn't helping," the question is sent from the device to the server and analyzed by a natural language processing module. Based on the analysis results, the generative AI model considers various possibilities regarding the headache and generates an appropriate answer. This answer is then sent to the user's device.

[0968] Prompt Sentence Examples

[0969] 1. "When a user submits a headache question, please describe how it is parsed and an answer generated."

[0970] 2. "Please specifically show how your generative AI model would respond if the headache had lasted for several weeks."

[0971] In this way, this system provides users with reliable medical information and reduces the burden on medical professionals.

[0972] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0973] Step 1: User Registration and Login

[0974] What happens: A user downloads an application and enters basic information such as name, age, and email address.

[0975] Input: Basic information (name, age, email address, etc.)

[0976] Output: The user information is saved in the database and a confirmation email is sent.

[0977] Detailed description: The device generates an API request to send the entered basic information to the server. The server receives this information and stores it in a database. The server then sends a confirmation email to the user's email address. The user enters the authentication code received in the email into the application, and the server verifies the information and sets the user to logged in.

[0978] Step 2: Enter and submit your question

[0979] What it does: A user enters a medical question or symptom through the application.

[0980] Input: User's question or symptom

[0981] Output: The question is sent to the server.

[0982] Detailed description: The device generates an API request to send the entered medical question or symptoms to the server. The generated API request is sent to the server via a communication network. The server stores the received question in a database.

[0983] Step 3: Parsing the Question

[0984] Specific operation: The server forwards the received question to the natural language processing module.

[0985] Input: Question (question or symptom submitted by the user)

[0986] Output: Analysis results (intention and keywords)

[0987] Detailed explanation: The natural language processing module analyzes the question and identifies its intent and keywords. For example, if the question is "I've had a headache for several weeks, and it hasn't gone away even after taking medicine," the NLP module extracts keywords such as "headache," "several weeks," and "medicine isn't working." The analysis results are then sent to the generative AI model.

[0988] Step 4: Generate an answer

[0989] Specific operation: The generative AI model generates an answer based on the analysis results.

[0990] Input: Analysis results (intention and keywords)

[0991] Output: Medical answers

[0992] Detailed description: The generative AI model generates appropriate answers from a medically supervised medical knowledge base. Based on the analysis results, the model generates a specific answer such as "You may have a chronic headache and we recommend that you consult a doctor." This answer is sent to the server.

[0993] Step 5: Submit your response

[0994] Specific operation: The server sends the generated answer to the user's device.

[0995] Input: Answer (medical information provided by the generative AI model)

[0996] Output: Send the answer to the user's terminal

[0997] Detailed description: The server checks the generated answer and sends it to the user's device, where the user receives the answer on the application screen.

[0998] Step 6: Gather feedback

[0999] Specific Actions: The user enters feedback on the answers provided.

[1000] Input: Feedback (user ratings and opinions)

[1001] Output: Save the feedback to a database and use it to update the generative AI model

[1002] Detailed description: The user inputs feedback about the provided answer, such as "It was very easy to understand." The device generates an API request to send this feedback to the server, and sends it to the server. The server receives the feedback and stores it in a database. This feedback is also used as training data for the generative AI model, contributing to improving the model's performance.

[1003] The above is a detailed description of the specific processing flow of this system and the inputs and outputs at each step.

[1004] (Application example 1)

[1005] 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."

[1006] When users have medical questions or symptoms, it is difficult to easily obtain reliable medical information. Furthermore, the inability to obtain medical information immediately when shopping in physical stores or using services reduces user satisfaction. Furthermore, the inability to efficiently recommend health products and services in physical stores makes it difficult to increase sales or meet customer needs.

[1007] 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.

[1008] In this invention, the server includes means for registering and storing basic user information, means for authenticating based on the registered user information, means for inputting medical questions and symptoms from the user, means for transmitting the input questions and symptoms to the server, means for analyzing the questions and symptoms received by the server, means for generating appropriate answers using a generative AI model based on the analysis results, means for transmitting the generated answers to the user, means for receiving feedback from the user and updating the learning data of the generative AI model, means for the user to input questions and symptoms using a robot in a physical store, means for displaying the answers generated by the robot by voice and on a screen, means for recommending products and services in the physical store, means for analyzing the questions and symptoms from the user using a natural language processing module, and means for generating answers from a curated medical knowledge base. This allows users to instantly obtain reliable medical information in a physical store, and enables accurate recommendations of health products and services.

[1009] The "means for users to input medical questions and symptoms" refers to a device that provides an interface for users to input questions about their own health condition and symptoms using the robot's touch screen, etc.

[1010] The "means for transmitting input questions and symptoms to a server" is a communication device for transmitting information input by a user to a remote server via the Internet or the like.

[1011] The "means for analyzing questions and symptoms received at the server" is a software module for analyzing user questions and symptoms sent to the server and extracting their intent and key keywords.

[1012] "Means for generating appropriate answers using a generative AI model based on the analysis results" refers to a device that uses a generative AI model to generate appropriate answers based on data analyzed through natural language processing.

[1013] The "means for transmitting the generated answer to the user" is a communication device that transmits the generated answer back to the robot or touch screen used by the user by displaying or audibly transmitting the answer.

[1014] The "means for receiving feedback from users and updating the learning data of the generative AI model" refers to a database and update function for collecting feedback provided by users and using it as training data for the generative AI model.

[1015] "A means for users to input questions and symptoms using a robot within a physical store" refers to a device that allows users to input medical questions and symptoms using a touch screen or the like on a robot placed within a physical store.

[1016] "Means for the robot to display the generated answers by voice and on a screen" is a function that enables the robot to explain the generated medical information and product recommendations by voice and simultaneously display them on a touch screen.

[1017] "Means for recommending products and services in physical stores" is a function that allows the robot to recommend related health products and services based on the user's questions and symptoms.

[1018] A "natural language processing module" is a software module that analyzes text data of questions and symptoms received from users, extracts intent and keywords, and passes them on to the next process.

[1019] A "supervised medical knowledge base" is a database that stores reliable medical information that has been verified by medical specialists.

[1020] This invention relates to a system that allows users to input medical questions and symptoms in a physical store and obtain reliable medical information in real time. This system is broadly composed of a user terminal (a robot touch screen), a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[1021] User terminal

[1022] A robot placed in a physical store is used as a means for users to input their questions and symptoms. The robot is equipped with a touchscreen, providing an interface for users to input directly. The robot then provides the generated answers to the user via voice and on the screen, and also recommends related health products and services.

[1023] server

[1024] The server receives questions and symptoms sent by users and analyzes them. The server works as follows:

[1025] 1. The user uses the robot in a physical store to input their questions or symptoms, and the input information is sent to the server.

[1026] 2. The server forwards the received questions and symptoms to the natural language processing module, which analyzes the intent and keywords.

[1027] 3. Based on the analysis results, a generative AI model is used to generate an appropriate answer.

[1028] 4. The generated answer is sent back to the robot via the server and provided to the user.

[1029] 5. The user enters feedback on the provided answer, and the server uses that feedback as training data for the generative AI model.

[1030] Natural Language Processing Module

[1031] The natural language processing module (NLP module) analyzes the user's inputted question or symptom to identify their intent and key keywords. This provides the basis for the generative AI model to generate appropriate answers. Specifically, NLP libraries such as SpaCy and NLTK are used.

[1032] Generative AI Models

[1033] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module. Generative models such as GPT-3 and OpenAI are used to provide users with reliable medical information.

[1034] Medical Knowledge Base

[1035] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[1036] Specific examples

[1037] The user types a question into the robot's touchscreen: "I have a persistent cough. What product do you recommend?" This information is sent to the server, which uses a natural language processing module to extract keywords such as "cough," "product," and "recommendation." The generative AI model then uses this information to create a prompt and generate an appropriate answer. For example, the generated answer might be, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The robot provides this answer to the user both aloud and on the screen, and also guides them to products in specific locations in the store.

[1038] Prompt Sentence Examples

[1039] I have a persistent cough. Which product would you recommend?

[1040] The above is a specific embodiment for carrying out the present invention. This system allows users to instantly obtain reliable medical information even in physical stores, making it easy to select health products and services. Furthermore, by collecting feedback, the accuracy of the entire system can be improved.

[1041] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1042] Step 1:

[1043] A user uses the robot's touchscreen in a brick-and-mortar store to input their medical question or symptoms, such as "I have a persistent cough. What product would you recommend?" This input data is stored in the robot's internal system.

[1044] Step 2:

[1045] The device sends the entered question or symptom to the server. At this time, an API request including the input data is generated and sent to the server via the Internet. The input data (user question) is received at the server's API endpoint.

[1046] Step 3:

[1047] The server passes the received question to a natural language processing module, which first analyzes the text data and extracts key keywords such as "cough," "product," and "recommendation." The input data is then processed based on this, and keywords are generated as the analysis results.

[1048] Step 4:

[1049] Based on the analysis results, the server creates and sends a prompt to the generative AI model. This prompt is formatted as "I have a persistent cough. What products do you recommend?" The prompt is then input to the generative AI model (such as GPT-3).

[1050] Step 5:

[1051] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The answer text is returned to the server as output data from the generative AI model.

[1052] Step 6:

[1053] The server forwards the generated answer to the robot. This answer data is again sent as an API request and received by the robot. The robot then tells the user by voice and on the screen, "As a product that is effective for coughs, we recommend cough syrup sold at pharmacies."

[1054] Step 7:

[1055] The user inputs feedback on the provided answer into the robot's touchscreen, for example, "This answer was helpful."

[1056] Step 8:

[1057] The device sends the user's feedback to the server, and an API request containing the feedback data is generated again and sent to the server.

[1058] Step 9:

[1059] The server stores the received feedback in a database and uses this data as training data for the generative AI model, which improves the accuracy of the generative AI model and the quality of answers from the next time onwards.

[1060] 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.

[1061] This invention relates to a system that allows users to input medical questions and symptoms and generates appropriate answers. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond according to the user's emotional state. This system provides reliable medical information, alleviating user anxiety and reducing the burden on medical professionals.

[1062] System Configuration

[1063] The system consists of the following main components: a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[1064] User terminal

[1065] The user terminal provides an interface for users to input medical questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or personal computer. In addition, the user terminal is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice, and also has the function of sending this information to the server.

[1066] server

[1067] The server receives questions, symptoms, and emotional data sent by users and performs analysis and answer generation. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The generative AI model generates appropriate answers from a medical knowledge base and sends them to the user's device. It also adjusts the tone of the answers based on the emotional data and collects feedback.

[1068] Natural Language Processing Module

[1069] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[1070] Generative AI Models

[1071] The generative AI model generates answers from a curated medical knowledge base based on the analysis results and emotion data received from the natural language processing module, and also has the ability to adjust the tone of the answer based on data from the emotion engine.

[1072] Medical Knowledge Base

[1073] A medical knowledge base is a database of reliable medical information curated by medical experts, which serves as the primary source of information for generative AI models to generate appropriate answers.

[1074] Emotion Engine

[1075] The emotion engine is a module that recognizes emotions from the user's facial expressions and voice when they input their questions or symptoms. The emotion data recognized by the emotion engine is sent to the server and used for subsequent interviews and answer generation.

[1076] Program processing

[1077] The program of this system is processed in the following manner.

[1078] 1. User Registration and Login

[1079] The user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[1080] 2. Enter and submit your question

[1081] The user inputs medical questions and symptoms using the device and sends the question. The emotion engine recognizes the user's emotions and sends the emotion data to the server. The device then generates a request to send this information to the server and sends it to the server.

[1082] 3. Question Analysis and Answer Generation

[1083] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results and emotional data are passed to a generative AI model, which then generates an appropriate answer from a medical knowledge base. The tone of the generated answer is adjusted based on the emotional data, and the answer is sent to the user's device via the server.

[1084] 4. Collecting User Feedback

[1085] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[1086] Specific examples

[1087] For example, suppose a user inputs a question such as "I've been having headaches lately due to work stress," and the emotion engine detects anxiety and stress. The server receives this, and the natural language processing module extracts keywords such as "stress" and "headache," and passes the analysis results to the generative AI model. The generative AI model then generates an answer on "how to deal with stress-related headaches" from a medical knowledge base, such as "Relaxation techniques and lifestyle changes are effective for headaches caused by stress. We recommend that you see a doctor for a detailed diagnosis." Based on the emotion engine's data, the tone of the answer is adjusted to be calming. The user confirms this and enters feedback such as "This was helpful," and the system collects this feedback to improve the AI ​​model's performance.

[1088] The above is an embodiment of the present invention. In this way, the system can provide the user with prompt and appropriate medical information, while also responding appropriately to the user's emotions.

[1089] The processing flow will be explained below.

[1090] Step 1:

[1091] The user downloads the application and installs it on the device.

[1092] Step 2:

[1093] The user opens the account creation screen on their device and enters their name, age, and email address.

[1094] Step 3:

[1095] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[1096] Step 4:

[1097] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[1098] Step 5:

[1099] The server will send a confirmation email containing an authentication code to the user's email address.

[1100] Step 6:

[1101] The user enters the authentication code received via email into the authentication screen within the application.

[1102] Step 7:

[1103] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[1104] Step 8:

[1105] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[1106] Step 9:

[1107] The terminal receives the token and sets the user to a logged-in state.

[1108] Step 10:

[1109] Users use the terminal to input medical questions and symptoms.

[1110] Step 11:

[1111] The emotion engine recognizes emotions from the user's facial expressions and voice and acquires emotion data.

[1112] Step 12:

[1113] The device generates a request to send information about the question or symptom and emotional data to the server, and sends it to the server.

[1114] Step 13:

[1115] The server transfers the received information to a natural language processing module, which analyzes the intent and keywords of the question.

[1116] Step 14:

[1117] The natural language processing module returns the analysis results to the server.

[1118] Step 15:

[1119] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[1120] Step 16:

[1121] The generative AI model references a medical knowledge base to generate appropriate answers and adjusts the tone of the answer based on emotional data.

[1122] Step 17:

[1123] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[1124] Step 18:

[1125] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[1126] Step 19:

[1127] The user enters feedback on the answers provided, and the feedback is also transmitted from the terminal to the server.

[1128] Step 20:

[1129] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[1130] Step 21:

[1131] The server stores the received feedback in a database and uses it as training data for the generative AI model.

[1132] Step 22:

[1133] The server uses emotional data and past feedback to improve the accuracy and personalization of future question answers.

[1134] Example 2

[1135] 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."

[1136] In today's medical field, there is a demand for fast and appropriate medical information, but the burden on medical professionals is becoming a problem. In particular, when users input medical questions or symptoms, it is difficult to provide appropriate answers to those questions or symptoms, and responses that are not adequately responsive to the user's emotions are not being provided. Therefore, it is important to alleviate users' anxiety and reduce the burden on medical professionals.

[1137] 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.

[1138] In this invention, the server includes means for inputting medical questions and symptoms from a user, means for transmitting the input questions and symptoms, means for analyzing the questions and symptoms, means for generating appropriate answers using a generative AI model, means for transmitting the generated answers to the user, means for recognizing the user's emotions and acquiring emotional data, means for adjusting the tone of the answers based on the emotional data, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to quickly provide appropriate answers to the questions and symptoms input by users and responses tailored to each individual's emotions.

[1139] "User" refers to a person who enters a medical question or symptom or provides feedback in response to a question.

[1140] "Terminal" refers to a device that allows users to input medical questions and symptoms and send them to a server. Examples of such devices include smartphones, tablets, and personal computers.

[1141] "Server" refers to a central computer system that receives questions and symptoms sent by users, analyzes them, generates appropriate answers, and sends them to the users.

[1142] A "natural language processing module" refers to a software module that analyzes questions and symptoms entered by users and extracts their intent and keywords.

[1143] A "generative AI model" refers to an artificial intelligence model that generates appropriate answers from a medical knowledge base based on the results analyzed by a natural language processing module.

[1144] A "medical knowledge base" refers to a database that accumulates medical information supervised by specialist doctors and medical institutions.

[1145] An "emotion engine" refers to a module that recognizes emotions from the user's facial expressions and voice and acquires that emotion data.

[1146] "Emotion data" refers to information about a user's emotions recognized by the emotion engine.

[1147] "Answer tone adjustment" refers to the process of ensuring that generated answers are delivered in an appropriate tone depending on the user's emotions.

[1148] "Feedback" refers to the act of a user inputting their opinion on the usefulness and satisfaction of a provided answer.

[1149] The present invention is a system that allows users to input medical questions and symptoms and provides appropriate answers to those questions. The system includes a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[1150] System Configuration

[1151] User terminal

[1152] The user terminal is a device that allows users to input medical questions and symptoms. Users use a smartphone, tablet, or personal computer to create an account, log in, enter questions, and provide feedback. The user terminal also incorporates an emotion engine that uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This emotion data is sent to the server in real time.

[1153] server

[1154] The server is a central computer system that receives questions and emotional data sent by users, analyzes them, and generates answers. The server sends the received questions to a natural language processing module and obtains analysis results. The analysis results and emotional data are then passed to a generative AI model, which generates an appropriate answer. The tone of the generated answer is adjusted based on the emotional data and sent to the user's device.

[1155] Natural Language Processing Module

[1156] The natural language processing module (NLP module) is software that analyzes user-entered questions and symptoms. This module extracts intent and keywords from the input text and provides the basis for answer generation by generative AI models.

[1157] Generative AI Models

[1158] The generative AI model is an artificial intelligence model that generates appropriate answers from a curated medical knowledge base based on the analysis results and emotional data received from the natural language processing module, and also has the ability to adjust the tone of the answer taking into account the emotional data.

[1159] Medical Knowledge Base

[1160] A medical knowledge base is a database of reliable medical information supervised by specialist doctors and medical institutions. A generative AI model references this database to generate appropriate answers to user questions.

[1161] Emotion Engine

[1162] The emotion engine is a module that recognizes emotions from facial expressions and voice when a user inputs a question or symptom. This engine sends the recognized emotion data to the server in real time and reflects it in generating an answer.

[1163] Specific examples

[1164] For example, consider the case where a user enters the question, "I've been having headaches lately due to work stress." When this question is entered, the emotion engine recognizes the user's anxiety and stress. The server sends the received question to a natural language processing module, which extracts keywords such as "stress" and "headache." The analysis results are passed to a generative AI model, which generates an answer on "how to deal with stress-related headaches" from a medical knowledge base. This answer might be something like, "For headaches caused by stress, relaxation techniques and lifestyle changes are effective. I recommend seeing a doctor for a detailed diagnosis." Furthermore, based on the emotion data, the tone of the answer is adjusted to be calmer.

[1165] An example prompt might look like this:

[1166] "I've been having headaches lately because of work stress. What should I do?"

[1167] In this way, the system provides users with prompt and appropriate medical information and responds to their emotions, thereby reducing user anxiety and the burden on medical professionals.

[1168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1169] Program processing flow

[1170] Step 1: User Registration and Login

[1171] The user creates an account using the device. The user's input information (name, age, email address) is sent from the device to the server. The server stores this information in a database and generates a confirmation email that is sent to the user's email address. The user then enters the authentication code they received, and the device sends the code to the server. Once authentication is complete, the user is logged in.

[1172] Input: User's name, age, email address, verification code

[1173] Processing: Sending and storing information, generating and verifying authentication codes

[1174] Output:Login status

[1175] Step 2: Enter your question

[1176] Users input their medical questions and symptoms using a device. The emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The acquired emotional data and information about the questions and symptoms are then sent from the device to the server.

[1177] Input: User's questions, symptoms, facial expressions, and voice

[1178] Processing: Entering questions and symptoms, acquiring and sending emotional data

[1179] Output: Question, symptom, and emotion data sent to the server

[1180] Step 3: Parsing the Question

[1181] The server transfers the received question and emotion data to the natural language processing module, which analyzes the text of the question or symptom to extract the intent and important keywords. The extracted analysis results are returned to the server.

[1182] Input: Question, Symptoms, and Emotional Data

[1183] Processing: Text analysis and keyword extraction using natural language processing modules

[1184] Output: Extracted intent and important keywords

[1185] Step 4: Generate an answer

[1186] The server passes the analysis results and emotional data to the generative AI model, which then generates an appropriate answer from a medical knowledge base based on the analysis results, adjusts the tone of the answer based on the emotional data, and returns the generated answer to the server.

[1187] Input: Analysis results, emotion data

[1188] Processing: Answer generation using generative AI model, tone adjustment

[1189] Output: The generated answer

[1190] Step 5: Submit your response

[1191] The server sends the generated answer to the user's terminal, which displays the answer to the user.

[1192] Input: Generated Answer

[1193] Action: Send response

[1194] Output: Answer displayed on the user's device

[1195] Step 6: Gather feedback

[1196] The user enters feedback on the provided answers, and the device sends the feedback to the server, which stores it in a database and uses it as training data for the generative AI model.

[1197] Input: User feedback

[1198] Action: Send and save feedback

[1199] Output: Saved feedback data

[1200] Specific examples of processing

[1201] Step 1: The user downloads the application and enters their name, age, and email address. The server then sends a confirmation email, confirming the entry of a verification code.

[1202] Step 2: The user enters "I've been having headaches lately because of work stress," and the emotion engine recognizes anxiety and stress. The data is sent to the server.

[1203] Step 3: The natural language processing module extracts keywords such as "stress" and "headache" and returns the analysis results to the server.

[1204] Step 4: The generative AI model consults a medical knowledge base and generates an answer about "how to deal with stress-related headaches," adjusting the tone to be calming.

[1205] Step 5: The server sends the answer to the user's terminal, and the user confirms the answer.

[1206] Step 6: The user enters feedback such as "It was helpful" and the server stores it in the database.

[1207] In this way, the system provides the user with appropriate medical information and responds according to the user's emotions.

[1208] (Application example 2)

[1209] 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."

[1210] In recent years, many companies and facilities have been required to monitor the health status of their employees in real time and take appropriate measures. Especially in large-scale facilities, it is difficult to monitor the health status of many employees individually, making an effective health management system necessary. Furthermore, taking into account employees' emotional state and stress level would enable more accurate responses. However, conventional health monitoring systems lack the ability to analyze emotional states or adjust tone in real time, making it difficult to take prompt and appropriate action.

[1211] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting questions and symptoms related to health status from a user, means for transmitting the input questions, symptoms, and emotional data to the server, means for analyzing the questions, symptoms, and emotional data received in the server, means for generating appropriate advice using a generative AI model based on the analysis results, means for adjusting the tone of the generated advice and transmitting it to the user, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to monitor the health status of employees in real time and quickly take appropriate measures that take their emotional state into consideration.

[1212] "Health status" refers to the physical and mental condition of the user, and refers to questions and symptoms input by the user.

[1213] "Emotion data" refers to data that indicates the emotional state of the user analyzed from their facial expressions and voice.

[1214] "Server" refers to a computer system that analyzes received data and generates and sends appropriate advice.

[1215] "Analysis means" refers to methods and technologies for understanding the input question, symptoms, and emotion data and extracting appropriate information.

[1216] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates appropriate advice based on input data.

[1217] "Tone adjustment" refers to adjusting the tone and expression of generated advice to match the user's emotional state.

[1218] "Feedback" refers to the user's reaction and evaluation of the advice provided, and is information used to improve the system.

[1219] "Training data" refers to the data, including feedback, that a generative AI model uses to generate more accurate advice.

[1220] This invention relates to a system that analyzes a user's health-related questions and symptoms in real time and provides appropriate advice based on emotional data. The system mainly consists of the following components: a user terminal, a server, a natural language processing module, a generative AI model, a knowledge base, and an emotional engine.

[1221] User terminal

[1222] The user device is provided as a smartphone app. This app has a means for the user to input their health status and acquire emotional data from facial expressions and voice in real time. For example, if a user inputs "Recently, my work environment has been causing me stress," the device analyzes it and captures emotional data such as anxiety from facial expressions.

[1223] server

[1224] The server receives and analyzes health and emotion data sent from the user's device. The analyzed data is processed by a natural language processing module and passed to the generative AI model. The server is built using cloud services such as AWS and Microsoft Azure.

[1225] Natural Language Processing Module

[1226] The natural language processing module analyzes text data entered by the user and extracts its intent and keywords. For example, an input sentence such as "Recently, the environment at work has been causing me stress" is parsed into the keywords "stress" and "work environment." This module uses Google's BERT model and OpenAI's GPT series.

[1227] Generative AI Models

[1228] The generative AI model generates appropriate advice based on the analysis results and emotion data received from the natural language processing module. For example, advice such as "For stress-related issues, we recommend taking regular breaks or consulting with a manager" is automatically generated. This is done using TensorFlow or PyTorch.

[1229] Knowledge Base

[1230] A knowledge base is a database curated by trusted experts. Generative AI models refer to this database and use it to provide optimal advice. Databases such as MongoDB and PostgreSQL are commonly used.

[1231] Emotion Engine

[1232] The emotion engine analyzes the user's facial expressions and voice to generate emotion data, which then adjusts the tone of the generated advice appropriately. The emotion engine uses AWS Rekognition and the Microsoft Azure Emotion API.

[1233] Specific examples

[1234] 1. The user enters into the app, "Recently, my work environment has been causing me stress."

[1235] 2. The emotion engine analyzes the user's facial expressions and voice to detect anxiety.

[1236] 3. The natural language processing module extracts the keywords "stress" and "work environment."

[1237] 4. The generative AI model references the knowledge base and generates appropriate advice.

[1238] 5. Adjust the tone of your advice based on emotional data.

[1239] 6. The adjusted advice is sent to the user terminal.

[1240] Prompt Sentence Examples

[1241] Employee A enters his recent health condition into the app: "Recently, my work environment has been causing me stress." The emotion engine detects A's anxiety and generates appropriate advice based on the analysis results and emotional data.

[1242] This allows the system to monitor the user's health status in real time and provide appropriate advice quickly, taking into account their emotional state.

[1243] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1244] Step 1:

[1245] A user uses a smartphone app to input questions or symptoms about their health. For example, they input text such as, "Recently, my work environment has been causing me stress." The input data also includes emotional data obtained from the user's facial expressions and voice. This captures emotional data (e.g., anxiety, stress level).

[1246] Step 2:

[1247] The device sends the entered health question, symptoms, and emotional data to a server. The sent data includes text data and emotional data (obtained through facial recognition and voice analysis). This data is stored on the server and used for analysis.

[1248] Step 3:

[1249] The server passes the received questions, symptoms, and emotional data to a natural language processing module. This module analyzes the input text data and extracts key keywords (e.g., "stress" and "work environment"). It also analyzes the emotional data to clarify the user's emotional state.

[1250] Step 4:

[1251] The analysis results and emotion data obtained from the natural language processing module are passed to a generative AI model. The generative AI model generates appropriate advice based on the input data. At this time, the model references its knowledge base and generates the advice it deems most appropriate. For example, the generated advice might be, "Regarding the cause of stress, we recommend taking regular breaks and consulting with your manager."

[1252] Step 5:

[1253] The generated advice is tone-adjusted based on the emotional data. For example, if the user is feeling anxious, the generated advice will be delivered in a gentle tone. The tone adjustment is performed by a special module in the server.

[1254] Step 6:

[1255] The server sends the tone-adjusted advice to the user's device, where the user can review the advice through a smartphone app. The advice is optimized based on the user's questions, symptoms, and emotional state.

[1256] Step 7:

[1257] Users can provide feedback on the advice provided to the app, which then sends the feedback data back to the server and uses it as training data for the generative AI model, allowing the system to improve the accuracy of future responses.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] [Fourth embodiment]

[1262] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1263] 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.

[1264] 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).

[1265] 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.

[1266] 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.

[1267] 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).

[1268] 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.

[1269] 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.

[1270] 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.

[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 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.

[1274] 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."

[1275] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[1276] System Configuration

[1277] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[1278] User terminal

[1279] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[1280] server

[1281] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[1282] Natural Language Processing Module

[1283] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[1284] Generative AI Models

[1285] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[1286] Medical Knowledge Base

[1287] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[1288] Program processing

[1289] The program of this system is processed as follows.

[1290] User Registration and Login

[1291] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[1292] Enter and submit your question

[1293] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[1294] Parsing questions and generating answers

[1295] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[1296] Collecting user feedback

[1297] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[1298] Through the above process, this system provides users with reliable medical information and reduces the burden on medical professionals.

[1299] The processing flow will be explained below.

[1300] Step 1:

[1301] The user downloads the application and installs it on the device.

[1302] Step 2:

[1303] The user opens the account creation screen on their device and enters their name, age, and email address.

[1304] Step 3:

[1305] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[1306] Step 4:

[1307] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[1308] Step 5:

[1309] The server will send a confirmation email containing an authentication code to the user's email address.

[1310] Step 6:

[1311] The user enters the authentication code received via email into the authentication screen within the application.

[1312] Step 7:

[1313] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[1314] Step 8:

[1315] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[1316] Step 9:

[1317] The terminal receives the token and sets the user to a logged-in state.

[1318] Step 10:

[1319] The user uses the terminal to input medical questions and symptoms and send the question.

[1320] Step 11:

[1321] The terminal generates a request to transmit the input question information to the server, and transmits the request to the server.

[1322] Step 12:

[1323] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question.

[1324] Step 13:

[1325] The natural language processing module returns the analysis results to the server.

[1326] Step 14:

[1327] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[1328] Step 15:

[1329] The generative AI model references a curated medical knowledge base to generate appropriate answers.

[1330] Step 16:

[1331] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[1332] Step 17:

[1333] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[1334] Step 18:

[1335] The user inputs feedback on the provided answers and transmits it from the terminal to the server.

[1336] Step 19:

[1337] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[1338] Step 20:

[1339] The server stores the received feedback in a database and updates the training data for the generative AI model.

[1340] The above is a specific processing flow of the entire system.

[1341] Example 1

[1342] 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."

[1343] Many users today require fast and reliable answers to their medical questions and symptoms. However, current systems require users to search for medical information on their own, and the information they receive is often inaccurate and unreliable. Furthermore, the burden on medical professionals is increasing, requiring more efficient responses. An effective system is needed to address these issues.

[1344] 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.

[1345] In this invention, the server includes means for accepting medical input from a user, means for transmitting the input information to a central processing unit via a communication network, means for analyzing the information received by the central processing unit using a natural language processing module, means for generating an answer based on the analysis result using a generative AI model, means for transmitting the generated answer to the user's terminal, and means for receiving feedback from the user and updating the learning data of the generative AI model. This allows users to obtain reliable medical information quickly and reduces the burden on medical professionals.

[1346] "User" refers to an individual who utilizes the system to provide medical input.

[1347] "Input" refers to the act of a user providing information such as medical questions or symptoms to the system.

[1348] "Communications network" refers to a digital network for transmitting information from user terminals to a central processing unit (server).

[1349] "Central Processing Unit" refers to the server that analyzes and processes information received from the user and generates a response.

[1350] A "natural language processing module" refers to a software component that analyzes user input and extracts its intent and keywords.

[1351] "Generative AI model" refers to an artificial intelligence model that generates appropriate answers based on the analysis results of a natural language processing module.

[1352] "Answer" refers to medical information or advice generated by a generative AI model.

[1353] "Terminal" refers to the device (e.g., smartphone, tablet, computer, etc.) used by a user to provide input and receive responses from the system.

[1354] "Feedback" refers to the evaluation or opinion a user gives on a provided answer.

[1355] "Training data" refers to data used to improve the performance and accuracy of generative AI models.

[1356] The present invention relates to a system that allows users to input medical questions and symptoms, and generates analysis and answers via a server. The system aims to alleviate users' anxiety and reduce the burden on medical professionals by providing reliable medical information.

[1357] System Configuration

[1358] This system is broadly composed of a user terminal, a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[1359] User terminal

[1360] The user terminal provides an interface for users to input questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or computer. The user terminal is equipped with a communication function for transmitting user-entered information to the server.

[1361] server

[1362] The server receives and analyzes questions and symptoms sent by users. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The server then sends the generated answers to the user's device and collects feedback.

[1363] Natural Language Processing Module

[1364] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[1365] Generative AI Models

[1366] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module, and the generated answers are provided to users as reliable medical information.

[1367] Medical Knowledge Base

[1368] A medical knowledge base is a database of reliable medical information curated by experts, which serves as a source of information for generative AI models to generate appropriate answers.

[1369] Program processing explanation

[1370] User Registration and Login

[1371] First, the user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[1372] Enter and submit your question

[1373] Users input their medical questions and symptoms using a device, which then generates an API request to send this information to the server.

[1374] Parsing questions and generating answers

[1375] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results are passed to a generative AI model, which generates an appropriate answer from a medical knowledge base. The generated answer is then sent to the user's device via the server.

[1376] Collecting user feedback

[1377] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[1378] Examples of specific examples and prompts

[1379] Specific examples

[1380] If a user asks, "I have a persistent headache, but medicine isn't helping," the question is sent from the device to the server and analyzed by a natural language processing module. Based on the analysis results, the generative AI model considers various possibilities regarding the headache and generates an appropriate answer. This answer is then sent to the user's device.

[1381] Prompt Sentence Examples

[1382] 1. "When a user submits a headache question, please describe how it is parsed and an answer generated."

[1383] 2. "Please specifically show how your generative AI model would respond if the headache had lasted for several weeks."

[1384] In this way, this system provides users with reliable medical information and reduces the burden on medical professionals.

[1385] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1386] Step 1: User Registration and Login

[1387] What happens: A user downloads an application and enters basic information such as name, age, and email address.

[1388] Input: Basic information (name, age, email address, etc.)

[1389] Output: The user information is saved in the database and a confirmation email is sent.

[1390] Detailed description: The device generates an API request to send the entered basic information to the server. The server receives this information and stores it in a database. The server then sends a confirmation email to the user's email address. The user enters the authentication code received in the email into the application, and the server verifies the information and sets the user to logged in.

[1391] Step 2: Enter and submit your question

[1392] What it does: A user enters a medical question or symptom through the application.

[1393] Input: User's question or symptom

[1394] Output: The question is sent to the server.

[1395] Detailed description: The device generates an API request to send the entered medical question or symptoms to the server. The generated API request is sent to the server via a communication network. The server stores the received question in a database.

[1396] Step 3: Parsing the Question

[1397] Specific operation: The server forwards the received question to the natural language processing module.

[1398] Input: Question (question or symptom submitted by the user)

[1399] Output: Analysis results (intention and keywords)

[1400] Detailed explanation: The natural language processing module analyzes the question and identifies its intent and keywords. For example, if the question is "I've had a headache for several weeks, and it hasn't gone away even after taking medicine," the NLP module extracts keywords such as "headache," "several weeks," and "medicine isn't working." The analysis results are then sent to the generative AI model.

[1401] Step 4: Generate an answer

[1402] Specific operation: The generative AI model generates an answer based on the analysis results.

[1403] Input: Analysis results (intention and keywords)

[1404] Output: Medical answers

[1405] Detailed description: The generative AI model generates appropriate answers from a medically supervised medical knowledge base. Based on the analysis results, the model generates a specific answer such as "You may have a chronic headache and we recommend that you consult a doctor." This answer is sent to the server.

[1406] Step 5: Submit your response

[1407] Specific operation: The server sends the generated answer to the user's device.

[1408] Input: Answer (medical information provided by the generative AI model)

[1409] Output: Send the answer to the user's terminal

[1410] Detailed description: The server checks the generated answer and sends it to the user's device, where the user receives the answer on the application screen.

[1411] Step 6: Gather feedback

[1412] Specific Actions: The user enters feedback on the answers provided.

[1413] Input: Feedback (user ratings and opinions)

[1414] Output: Save the feedback to a database and use it to update the generative AI model

[1415] Detailed description: The user inputs feedback about the provided answer, such as "It was very easy to understand." The device generates an API request to send this feedback to the server, and sends it to the server. The server receives the feedback and stores it in a database. This feedback is also used as training data for the generative AI model, contributing to improving the model's performance.

[1416] The above is a detailed description of the specific processing flow of this system and the inputs and outputs at each step.

[1417] (Application example 1)

[1418] 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."

[1419] When users have medical questions or symptoms, it is difficult to easily obtain reliable medical information. Furthermore, the inability to obtain medical information immediately when shopping in physical stores or using services reduces user satisfaction. Furthermore, the inability to efficiently recommend health products and services in physical stores makes it difficult to increase sales or meet customer needs.

[1420] 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.

[1421] In this invention, the server includes means for registering and storing basic user information, means for authenticating based on the registered user information, means for inputting medical questions and symptoms from the user, means for transmitting the input questions and symptoms to the server, means for analyzing the questions and symptoms received by the server, means for generating appropriate answers using a generative AI model based on the analysis results, means for transmitting the generated answers to the user, means for receiving feedback from the user and updating the learning data of the generative AI model, means for the user to input questions and symptoms using a robot in a physical store, means for displaying the answers generated by the robot by voice and on a screen, means for recommending products and services in the physical store, means for analyzing the questions and symptoms from the user using a natural language processing module, and means for generating answers from a curated medical knowledge base. This allows users to instantly obtain reliable medical information in a physical store, and enables accurate recommendations of health products and services.

[1422] The "means for users to input medical questions and symptoms" refers to a device that provides an interface for users to input questions about their own health condition and symptoms using the robot's touch screen, etc.

[1423] The "means for transmitting input questions and symptoms to a server" is a communication device for transmitting information input by a user to a remote server via the Internet or the like.

[1424] The "means for analyzing questions and symptoms received at the server" is a software module for analyzing user questions and symptoms sent to the server and extracting their intent and key keywords.

[1425] "Means for generating appropriate answers using a generative AI model based on the analysis results" refers to a device that uses a generative AI model to generate appropriate answers based on data analyzed through natural language processing.

[1426] The "means for transmitting the generated answer to the user" is a communication device that transmits the generated answer back to the robot or touch screen used by the user by displaying or audibly transmitting the answer.

[1427] The "means for receiving feedback from users and updating the learning data of the generative AI model" refers to a database and update function for collecting feedback provided by users and using it as training data for the generative AI model.

[1428] "A means for users to input questions and symptoms using a robot within a physical store" refers to a device that allows users to input medical questions and symptoms using a touch screen or the like on a robot placed within a physical store.

[1429] "Means for the robot to display the generated answers by voice and on a screen" is a function that enables the robot to explain the generated medical information and product recommendations by voice and simultaneously display them on a touch screen.

[1430] "Means for recommending products and services in physical stores" is a function that allows the robot to recommend related health products and services based on the user's questions and symptoms.

[1431] A "natural language processing module" is a software module that analyzes text data of questions and symptoms received from users, extracts intent and keywords, and passes them on to the next process.

[1432] A "supervised medical knowledge base" is a database that stores reliable medical information that has been verified by medical specialists.

[1433] This invention relates to a system that allows users to input medical questions and symptoms in a physical store and obtain reliable medical information in real time. This system is broadly composed of a user terminal (a robot touch screen), a server, a natural language processing module, a generative AI model, and a medical knowledge base.

[1434] User terminal

[1435] A robot placed in a physical store is used as a means for users to input their questions and symptoms. The robot is equipped with a touchscreen, providing an interface for users to input directly. The robot then provides the generated answers to the user via voice and on the screen, and also recommends related health products and services.

[1436] server

[1437] The server receives questions and symptoms sent by users and analyzes them. The server works as follows:

[1438] 1. The user uses the robot in a physical store to input their questions or symptoms, and the input information is sent to the server.

[1439] 2. The server forwards the received questions and symptoms to the natural language processing module, which analyzes the intent and keywords.

[1440] 3. Based on the analysis results, a generative AI model is used to generate an appropriate answer.

[1441] 4. The generated answer is sent back to the robot via the server and provided to the user.

[1442] 5. The user enters feedback on the provided answer, and the server uses that feedback as training data for the generative AI model.

[1443] Natural Language Processing Module

[1444] The natural language processing module (NLP module) analyzes the user's inputted question or symptom to identify their intent and key keywords. This provides the basis for the generative AI model to generate appropriate answers. Specifically, NLP libraries such as SpaCy and NLTK are used.

[1445] Generative AI Models

[1446] The generative AI model generates answers from a curated medical knowledge base based on the analysis results received from the natural language processing module. Generative models such as GPT-3 and OpenAI are used to provide users with reliable medical information.

[1447] Medical Knowledge Base

[1448] A medical knowledge base is a database of reliable medical information curated by medical specialists, which serves as a source of information for generative AI models to generate appropriate answers.

[1449] Specific examples

[1450] The user types a question into the robot's touchscreen: "I have a persistent cough. What product do you recommend?" This information is sent to the server, which uses a natural language processing module to extract keywords such as "cough," "product," and "recommendation." The generative AI model then uses this information to create a prompt and generate an appropriate answer. For example, the generated answer might be, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The robot provides this answer to the user both aloud and on the screen, and also guides them to products in specific locations in the store.

[1451] Prompt Sentence Examples

[1452] I have a persistent cough. Which product would you recommend?

[1453] The above is a specific embodiment for carrying out the present invention. This system allows users to instantly obtain reliable medical information even in physical stores, making it easy to select health products and services. Furthermore, by collecting feedback, the accuracy of the entire system can be improved.

[1454] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1455] Step 1:

[1456] A user uses the robot's touchscreen in a brick-and-mortar store to input their medical question or symptoms, such as "I have a persistent cough. What product would you recommend?" This input data is stored in the robot's internal system.

[1457] Step 2:

[1458] The device sends the entered question or symptom to the server. At this time, an API request including the input data is generated and sent to the server via the Internet. The input data (user question) is received at the server's API endpoint.

[1459] Step 3:

[1460] The server passes the received question to a natural language processing module, which first analyzes the text data and extracts key keywords such as "cough," "product," and "recommendation." The input data is then processed based on this, and keywords are generated as the analysis results.

[1461] Step 4:

[1462] Based on the analysis results, the server creates and sends a prompt to the generative AI model. This prompt is formatted as "I have a persistent cough. What products do you recommend?" The prompt is then input to the generative AI model (such as GPT-3).

[1463] Step 5:

[1464] The generative AI model generates an appropriate answer based on the prompt. For example, it might generate an answer such as, "As a product that is effective for coughs, I recommend cough syrup sold at pharmacies." The answer text is returned to the server as output data from the generative AI model.

[1465] Step 6:

[1466] The server forwards the generated answer to the robot. This answer data is again sent as an API request and received by the robot. The robot then tells the user by voice and on the screen, "As a product that is effective for coughs, we recommend cough syrup sold at pharmacies."

[1467] Step 7:

[1468] The user inputs feedback on the provided answer into the robot's touchscreen, for example, "This answer was helpful."

[1469] Step 8:

[1470] The device sends the user's feedback to the server, and an API request containing the feedback data is generated again and sent to the server.

[1471] Step 9:

[1472] The server stores the received feedback in a database and uses this data as training data for the generative AI model, which improves the accuracy of the generative AI model and the quality of answers from the next time onwards.

[1473] 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.

[1474] This invention relates to a system that allows users to input medical questions and symptoms and generates appropriate answers. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to respond according to the user's emotional state. This system provides reliable medical information, alleviating user anxiety and reducing the burden on medical professionals.

[1475] System Configuration

[1476] The system consists of the following main components: a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[1477] User terminal

[1478] The user terminal provides an interface for users to input medical questions and symptoms. Users can create an account, log in, input questions, and provide feedback using a smartphone, tablet, or personal computer. In addition, the user terminal is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice, and also has the function of sending this information to the server.

[1479] server

[1480] The server receives questions, symptoms, and emotional data sent by users and performs analysis and answer generation. The server sends the questions and symptoms to a natural language processing module and passes the analysis results to a generative AI model. The generative AI model generates appropriate answers from a medical knowledge base and sends them to the user's device. It also adjusts the tone of the answers based on the emotional data and collects feedback.

[1481] Natural Language Processing Module

[1482] The natural language processing module (NLP module) analyzes the questions and symptoms entered by the user and identifies their intent and keywords, providing the base information for the generative AI model to generate appropriate answers.

[1483] Generative AI Models

[1484] The generative AI model generates answers from a curated medical knowledge base based on the analysis results and emotion data received from the natural language processing module, and also has the ability to adjust the tone of the answer based on data from the emotion engine.

[1485] Medical Knowledge Base

[1486] A medical knowledge base is a database of reliable medical information curated by medical experts, which serves as the primary source of information for generative AI models to generate appropriate answers.

[1487] Emotion Engine

[1488] The emotion engine is a module that recognizes emotions from the user's facial expressions and voice when they input their questions or symptoms. The emotion data recognized by the emotion engine is sent to the server and used for subsequent interviews and answer generation.

[1489] Program processing

[1490] The program of this system is processed in the following manner.

[1491] 1. User Registration and Login

[1492] The user downloads the application and creates an account using their device. The user's basic information (name, age, email address, etc.) is entered and sent from the device to the server. The server stores this information in a database and sends a confirmation email. When the user enters the authentication code received by email, the server verifies the authentication information and logs the user in.

[1493] 2. Enter and submit your question

[1494] The user inputs medical questions and symptoms using the device and sends the question. The emotion engine recognizes the user's emotions and sends the emotion data to the server. The device then generates a request to send this information to the server and sends it to the server.

[1495] 3. Question Analysis and Answer Generation

[1496] The server forwards the received question to a natural language processing module, which analyzes the intent and keywords of the question. The analysis results and emotional data are passed to a generative AI model, which then generates an appropriate answer from a medical knowledge base. The tone of the generated answer is adjusted based on the emotional data, and the answer is sent to the user's device via the server.

[1497] 4. Collecting User Feedback

[1498] The user enters feedback on the provided answers and sends it from their device to the server, which stores the feedback in a database and uses it as training data for the generative AI model.

[1499] Specific examples

[1500] For example, suppose a user inputs a question such as "I've been having headaches lately due to work stress," and the emotion engine detects anxiety and stress. The server receives this, and the natural language processing module extracts keywords such as "stress" and "headache," and passes the analysis results to the generative AI model. The generative AI model then generates an answer on "how to deal with stress-related headaches" from a medical knowledge base, such as "Relaxation techniques and lifestyle changes are effective for headaches caused by stress. We recommend that you see a doctor for a detailed diagnosis." Based on the emotion engine's data, the tone of the answer is adjusted to be calming. The user confirms this and enters feedback such as "This was helpful," and the system collects this feedback to improve the AI ​​model's performance.

[1501] The above is an embodiment of the present invention. In this way, the system can provide the user with prompt and appropriate medical information, while also responding appropriately to the user's emotions.

[1502] The processing flow will be explained below.

[1503] Step 1:

[1504] The user downloads the application and installs it on the device.

[1505] Step 2:

[1506] The user opens the account creation screen on their device and enters their name, age, and email address.

[1507] Step 3:

[1508] The terminal generates a request to transmit the input information to the server and transmits it to the server.

[1509] Step 4:

[1510] The server stores the received user information in a database and generates an authentication code for sending a confirmation email.

[1511] Step 5:

[1512] The server will send a confirmation email containing an authentication code to the user's email address.

[1513] Step 6:

[1514] The user enters the authentication code received via email into the authentication screen within the application.

[1515] Step 7:

[1516] The terminal generates a request to send the input authentication code to the server and sends it to the server.

[1517] Step 8:

[1518] The server checks the authentication code and, if correct, generates a token that starts the user's login session and sends it to the terminal.

[1519] Step 9:

[1520] The terminal receives the token and sets the user to a logged-in state.

[1521] Step 10:

[1522] Users use the terminal to input medical questions and symptoms.

[1523] Step 11:

[1524] The emotion engine recognizes emotions from the user's facial expressions and voice and acquires emotion data.

[1525] Step 12:

[1526] The device generates a request to send information about the question or symptom and emotional data to the server, and sends it to the server.

[1527] Step 13:

[1528] The server transfers the received information to a natural language processing module, which analyzes the intent and keywords of the question.

[1529] Step 14:

[1530] The natural language processing module returns the analysis results to the server.

[1531] Step 15:

[1532] The server passes the analysis results to the generative AI model and instructs it to generate an appropriate answer.

[1533] Step 16:

[1534] The generative AI model references a medical knowledge base to generate appropriate answers and adjusts the tone of the answer based on emotional data.

[1535] Step 17:

[1536] The generated answer is returned to the server, which then transmits the answer to the user terminal.

[1537] Step 18:

[1538] The terminal receives the answer and displays it to the user, who then confirms the answer to their question.

[1539] Step 19:

[1540] The user enters feedback on the answers provided, and the feedback is also transmitted from the terminal to the server.

[1541] Step 20:

[1542] The terminal generates a request to transmit feedback information to the server and transmits it to the server.

[1543] Step 21:

[1544] The server stores the received feedback in a database and uses it as training data for the generative AI model.

[1545] Step 22:

[1546] The server uses emotional data and past feedback to improve the accuracy and personalization of future question answers.

[1547] Example 2

[1548] 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."

[1549] In today's medical field, there is a demand for fast and appropriate medical information, but the burden on medical professionals is becoming a problem. In particular, when users input medical questions or symptoms, it is difficult to provide appropriate answers to those questions or symptoms, and responses that are not adequately responsive to the user's emotions are not being provided. Therefore, it is important to alleviate users' anxiety and reduce the burden on medical professionals.

[1550] 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.

[1551] In this invention, the server includes means for inputting medical questions and symptoms from a user, means for transmitting the input questions and symptoms, means for analyzing the questions and symptoms, means for generating appropriate answers using a generative AI model, means for transmitting the generated answers to the user, means for recognizing the user's emotions and acquiring emotional data, means for adjusting the tone of the answers based on the emotional data, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to quickly provide appropriate answers to the questions and symptoms input by users and responses tailored to each individual's emotions.

[1552] "User" refers to a person who enters a medical question or symptom or provides feedback in response to a question.

[1553] "Terminal" refers to a device that allows users to input medical questions and symptoms and send them to a server. Examples of such devices include smartphones, tablets, and personal computers.

[1554] "Server" refers to a central computer system that receives questions and symptoms sent by users, analyzes them, generates appropriate answers, and sends them to the users.

[1555] A "natural language processing module" refers to a software module that analyzes questions and symptoms entered by users and extracts their intent and keywords.

[1556] A "generative AI model" refers to an artificial intelligence model that generates appropriate answers from a medical knowledge base based on the results analyzed by a natural language processing module.

[1557] A "medical knowledge base" refers to a database that accumulates medical information supervised by specialist doctors and medical institutions.

[1558] An "emotion engine" refers to a module that recognizes emotions from the user's facial expressions and voice and acquires that emotion data.

[1559] "Emotion data" refers to information about a user's emotions recognized by the emotion engine.

[1560] "Answer tone adjustment" refers to the process of ensuring that generated answers are delivered in an appropriate tone depending on the user's emotions.

[1561] "Feedback" refers to the act of a user inputting their opinion on the usefulness and satisfaction of a provided answer.

[1562] The present invention is a system that allows users to input medical questions and symptoms and provides appropriate answers to those questions. The system includes a user terminal, a server, a natural language processing module, a generative AI model, a medical knowledge base, and an emotion engine.

[1563] System Configuration

[1564] User terminal

[1565] The user terminal is a device that allows users to input medical questions and symptoms. Users use a smartphone, tablet, or personal computer to create an account, log in, enter questions, and provide feedback. The user terminal also incorporates an emotion engine that uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This emotion data is sent to the server in real time.

[1566] server

[1567] The server is a central computer system that receives questions and emotional data sent by users, analyzes them, and generates answers. The server sends the received questions to a natural language processing module and obtains analysis results. The analysis results and emotional data are then passed to a generative AI model, which generates an appropriate answer. The tone of the generated answer is adjusted based on the emotional data and sent to the user's device.

[1568] Natural Language Processing Module

[1569] The natural language processing module (NLP module) is software that analyzes user-entered questions and symptoms. This module extracts intent and keywords from the input text and provides the basis for answer generation by generative AI models.

[1570] Generative AI Models

[1571] The generative AI model is an artificial intelligence model that generates appropriate answers from a curated medical knowledge base based on the analysis results and emotional data received from the natural language processing module, and also has the ability to adjust the tone of the answer taking into account the emotional data.

[1572] Medical Knowledge Base

[1573] A medical knowledge base is a database of reliable medical information supervised by specialist doctors and medical institutions. A generative AI model references this database to generate appropriate answers to user questions.

[1574] Emotion Engine

[1575] The emotion engine is a module that recognizes emotions from facial expressions and voice when a user inputs a question or symptom. This engine sends the recognized emotion data to the server in real time and reflects it in generating an answer.

[1576] Specific examples

[1577] For example, consider the case where a user enters the question, "I've been having headaches lately due to work stress." When this question is entered, the emotion engine recognizes the user's anxiety and stress. The server sends the received question to a natural language processing module, which extracts keywords such as "stress" and "headache." The analysis results are passed to a generative AI model, which generates an answer on "how to deal with stress-related headaches" from a medical knowledge base. This answer might be something like, "For headaches caused by stress, relaxation techniques and lifestyle changes are effective. I recommend seeing a doctor for a detailed diagnosis." Furthermore, based on the emotion data, the tone of the answer is adjusted to be calmer.

[1578] An example prompt might look like this:

[1579] "I've been having headaches lately because of work stress. What should I do?"

[1580] In this way, the system provides users with prompt and appropriate medical information and responds to their emotions, thereby reducing user anxiety and the burden on medical professionals.

[1581] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1582] Program processing flow

[1583] Step 1: User Registration and Login

[1584] The user creates an account using the device. The user's input information (name, age, email address) is sent from the device to the server. The server stores this information in a database and generates a confirmation email that is sent to the user's email address. The user then enters the authentication code they received, and the device sends the code to the server. Once authentication is complete, the user is logged in.

[1585] Input: User's name, age, email address, verification code

[1586] Processing: Sending and storing information, generating and verifying authentication codes

[1587] Output:Login status

[1588] Step 2: Enter your question

[1589] Users input their medical questions and symptoms using a device. The emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The acquired emotional data and information about the questions and symptoms are then sent from the device to the server.

[1590] Input: User's questions, symptoms, facial expressions, and voice

[1591] Processing: Entering questions and symptoms, acquiring and sending emotional data

[1592] Output: Question, symptom, and emotion data sent to the server

[1593] Step 3: Parsing the Question

[1594] The server transfers the received question and emotion data to the natural language processing module, which analyzes the text of the question or symptom to extract the intent and important keywords. The extracted analysis results are returned to the server.

[1595] Input: Question, Symptoms, and Emotional Data

[1596] Processing: Text analysis and keyword extraction using natural language processing modules

[1597] Output: Extracted intent and important keywords

[1598] Step 4: Generate an answer

[1599] The server passes the analysis results and emotional data to the generative AI model, which then generates an appropriate answer from a medical knowledge base based on the analysis results, adjusts the tone of the answer based on the emotional data, and returns the generated answer to the server.

[1600] Input: Analysis results, emotion data

[1601] Processing: Answer generation using generative AI model, tone adjustment

[1602] Output: The generated answer

[1603] Step 5: Submit your response

[1604] The server sends the generated answer to the user's terminal, which displays the answer to the user.

[1605] Input: Generated Answer

[1606] Action: Send response

[1607] Output: Answer displayed on the user's device

[1608] Step 6: Gather feedback

[1609] The user enters feedback on the provided answers, and the device sends the feedback to the server, which stores it in a database and uses it as training data for the generative AI model.

[1610] Input: User feedback

[1611] Action: Send and save feedback

[1612] Output: Saved feedback data

[1613] Specific examples of processing

[1614] Step 1: The user downloads the application and enters their name, age, and email address. The server then sends a confirmation email, confirming the entry of a verification code.

[1615] Step 2: The user enters "I've been having headaches lately because of work stress," and the emotion engine recognizes anxiety and stress. The data is sent to the server.

[1616] Step 3: The natural language processing module extracts keywords such as "stress" and "headache" and returns the analysis results to the server.

[1617] Step 4: The generative AI model consults a medical knowledge base and generates an answer about "how to deal with stress-related headaches," adjusting the tone to be calming.

[1618] Step 5: The server sends the answer to the user's terminal, and the user confirms the answer.

[1619] Step 6: The user enters feedback such as "It was helpful" and the server stores it in the database.

[1620] In this way, the system provides the user with appropriate medical information and responds according to the user's emotions.

[1621] (Application example 2)

[1622] 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."

[1623] In recent years, many companies and facilities have been required to monitor the health status of their employees in real time and take appropriate measures. Especially in large-scale facilities, it is difficult to monitor the health status of many employees individually, making an effective health management system necessary. Furthermore, taking into account employees' emotional state and stress level would enable more accurate responses. However, conventional health monitoring systems lack the ability to analyze emotional states or adjust tone in real time, making it difficult to take prompt and appropriate action.

[1624] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting questions and symptoms related to health status from a user, means for transmitting the input questions, symptoms, and emotional data to the server, means for analyzing the questions, symptoms, and emotional data received in the server, means for generating appropriate advice using a generative AI model based on the analysis results, means for adjusting the tone of the generated advice and transmitting it to the user, and means for receiving feedback from the user and updating the learning data of the generative AI model. This makes it possible to monitor the health status of employees in real time and quickly take appropriate measures that take their emotional state into consideration.

[1625] "Health status" refers to the physical and mental condition of the user, and refers to questions and symptoms input by the user.

[1626] "Emotion data" refers to data that indicates the emotional state of the user analyzed from their facial expressions and voice.

[1627] "Server" refers to a computer system that analyzes received data and generates and sends appropriate advice.

[1628] "Analysis means" refers to methods and technologies for understanding the input question, symptoms, and emotion data and extracting appropriate information.

[1629] A "generative AI model" refers to an artificial intelligence algorithm or system that automatically generates appropriate advice based on input data.

[1630] "Tone adjustment" refers to adjusting the tone and expression of generated advice to match the user's emotional state.

[1631] "Feedback" refers to the user's reaction and evaluation of the advice provided, and is information used to improve the system.

[1632] "Training data" refers to the data, including feedback, that a generative AI model uses to generate more accurate advice.

[1633] This invention relates to a system that analyzes a user's health-related questions and symptoms in real time and provides appropriate advice based on emotional data. The system mainly consists of the following components: a user terminal, a server, a natural language processing module, a generative AI model, a knowledge base, and an emotional engine.

[1634] User terminal

[1635] The user device is provided as a smartphone app. This app has a means for the user to input their health status and acquire emotional data from facial expressions and voice in real time. For example, if a user inputs "Recently, my work environment has been causing me stress," the device analyzes it and captures emotional data such as anxiety from facial expressions.

[1636] server

[1637] The server receives and analyzes health and emotion data sent from the user's device. The analyzed data is processed by a natural language processing module and passed to the generative AI model. The server is built using cloud services such as AWS and Microsoft Azure.

[1638] Natural Language Processing Module

[1639] The natural language processing module analyzes text data entered by the user and extracts its intent and keywords. For example, an input sentence such as "Recently, the environment at work has been causing me stress" is parsed into the keywords "stress" and "work environment." This module uses Google's BERT model and OpenAI's GPT series.

[1640] Generative AI Models

[1641] The generative AI model generates appropriate advice based on the analysis results and emotion data received from the natural language processing module. For example, advice such as "For stress-related issues, we recommend taking regular breaks or consulting with a manager" is automatically generated. This is done using TensorFlow or PyTorch.

[1642] Knowledge Base

[1643] A knowledge base is a database curated by trusted experts. Generative AI models refer to this database and use it to provide optimal advice. Databases such as MongoDB and PostgreSQL are commonly used.

[1644] Emotion Engine

[1645] The emotion engine analyzes the user's facial expressions and voice to generate emotion data, which then adjusts the tone of the generated advice appropriately. The emotion engine uses AWS Rekognition and the Microsoft Azure Emotion API.

[1646] Specific examples

[1647] 1. The user enters into the app, "Recently, my work environment has been causing me stress."

[1648] 2. The emotion engine analyzes the user's facial expressions and voice to detect anxiety.

[1649] 3. The natural language processing module extracts the keywords "stress" and "work environment."

[1650] 4. The generative AI model references the knowledge base and generates appropriate advice.

[1651] 5. Adjust the tone of your advice based on emotional data.

[1652] 6. The adjusted advice is sent to the user terminal.

[1653] Prompt Sentence Examples

[1654] Employee A enters his recent health condition into the app: "Recently, my work environment has been causing me stress." The emotion engine detects A's anxiety and generates appropriate advice based on the analysis results and emotional data.

[1655] This allows the system to monitor the user's health status in real time and provide appropriate advice quickly, taking into account their emotional state.

[1656] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1657] Step 1:

[1658] A user uses a smartphone app to input questions or symptoms about their health. For example, they input text such as, "Recently, my work environment has been causing me stress." The input data also includes emotional data obtained from the user's facial expressions and voice. This captures emotional data (e.g., anxiety, stress level).

[1659] Step 2:

[1660] The device sends the entered health question, symptoms, and emotional data to a server. The sent data includes text data and emotional data (obtained through facial recognition and voice analysis). This data is stored on the server and used for analysis.

[1661] Step 3:

[1662] The server passes the received questions, symptoms, and emotional data to a natural language processing module. This module analyzes the input text data and extracts key keywords (e.g., "stress" and "work environment"). It also analyzes the emotional data to clarify the user's emotional state.

[1663] Step 4:

[1664] The analysis results and emotion data obtained from the natural language processing module are passed to a generative AI model. The generative AI model generates appropriate advice based on the input data. At this time, the model references its knowledge base and generates the advice it deems most appropriate. For example, the generated advice might be, "Regarding the cause of stress, we recommend taking regular breaks and consulting with your manager."

[1665] Step 5:

[1666] The generated advice is tone-adjusted based on the emotional data. For example, if the user is feeling anxious, the generated advice will be delivered in a gentle tone. The tone adjustment is performed by a special module in the server.

[1667] Step 6:

[1668] The server sends the tone-adjusted advice to the user's device, where the user can review the advice through a smartphone app. The advice is optimized based on the user's questions, symptoms, and emotional state.

[1669] Step 7:

[1670] Users can provide feedback on the advice provided to the app, which then sends the feedback data back to the server and uses it as training data for the generative AI model, allowing the system to improve the accuracy of future responses.

[1671] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1672] 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.

[1673] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1674] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1675] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1676] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1677] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1678] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1679] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1680] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1681] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1682] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1683] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1684] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1685] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1686] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1687] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1688] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1689] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1690] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1691] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1692] The following is further disclosed regarding the above embodiment.

[1693] (Claim 1)

[1694] a means for users to input medical questions and symptoms;

[1695] A means for sending the inputted question or symptom to a server;

[1696] A means for analyzing questions and symptoms received on the server;

[1697] A means for generating appropriate answers using an AI model based on the analysis results;

[1698] means for transmitting the generated answer to the user;

[1699] A means of receiving user feedback and updating the training data of the generative AI model;

[1700] A system including:

[1701] (Claim 2)

[1702] A means for registering basic information of users and storing it on a server;

[1703] means for performing authentication based on registered user information;

[1704] The system of claim 1 further comprising:

[1705] (Claim 3)

[1706] A means of analyzing user questions and symptoms using a natural language processing module;

[1707] a means of generating answers from a curated medical knowledge base;

[1708] 10. The system of claim 1, comprising:

[1709] "Example 1"

[1710] (Claim 1)

[1711] means for accepting medical input from a user;

[1712] means for transmitting the input information to a central processing unit through a communication network;

[1713] means for analyzing the information received by the central processing unit using a natural language processing module;

[1714] A means for generating an answer using a generative AI model based on the analysis results;

[1715] means for transmitting the generated answer to the user's terminal;

[1716] A means of receiving user feedback and updating the training data of the generative AI model;

[1717] A system including:

[1718] (Claim 2)

[1719] A means for registering basic information of a user and storing it in a central processing unit;

[1720] means for performing authentication based on registered user information;

[1721] The system of claim 1 further comprising:

[1722] (Claim 3)

[1723] means for analyzing input information from a user using a natural language processing module;

[1724] a means for generating answers from a curated knowledge database;

[1725] 10. The system of claim 1, comprising:

[1726] "Application Example 1"

[1727] (Claim 1)

[1728] a means for users to input medical questions and symptoms;

[1729] A means for sending the inputted question or symptom to a server;

[1730] A means for analyzing questions and symptoms received on the server;

[1731] A means for generating appropriate answers using an AI model based on the analysis results;

[1732] means for transmitting the generated answer to the user;

[1733] A means of receiving user feedback and updating the training data of the generative AI model;

[1734] A way for users to input questions or symptoms using the robot in a physical store,

[1735] a means for the robot to display the generated answer aloud and on a screen;

[1736] A means of recommending products and services in physical stores,

[1737] A system including:

[1738] (Claim 2)

[1739] A means for registering basic information of users and storing it on a server;

[1740] means for performing authentication based on registered user information;

[1741] The system of claim 1 further comprising:

[1742] (Claim 3)

[1743] A means of analyzing user questions and symptoms using a natural language processing module;

[1744] a means of generating answers from a curated medical knowledge base;

[1745] 10. The system of claim 1, comprising:

[1746] "Example 2: Combining Emotion Engines"

[1747] (Claim 1)

[1748] a means for users to input medical questions and symptoms;

[1749] A means for sending the inputted question or symptom to a server;

[1750] A means for analyzing questions and symptoms received on the server;

[1751] A means for generating appropriate answers using an AI model based on the analysis results;

[1752] means for transmitting the generated answer to the user;

[1753] means for recognizing a user's emotion and acquiring emotion data;

[1754] a means of adjusting the tone of responses based on emotional data;

[1755] A means of receiving user feedback and updating the training data of the generative AI model;

[1756] A system including:

[1757] (Claim 2)

[1758] A means for registering basic information of users and storing it on a server;

[1759] means for performing authentication based on registered user information;

[1760] The system of claim 1 further comprising:

[1761] (Claim 3)

[1762] A means of analyzing user questions and symptoms using a natural language processing module;

[1763] a means of generating answers from a curated medical knowledge base;

[1764] 10. The system of claim 1, comprising:

[1765] "Application example 2 when combining emotion engines"

[1766] (Claim 1)

[1767] a means for users to input health questions and symptoms;

[1768] means for transmitting the input question, symptom and emotion data to a server;

[1769] a means for analyzing the received question, symptom and emotion data in the server;

[1770] A means for generating appropriate advice based on the analysis results using an AI model;

[1771] means for adjusting the tone of the generated advice and transmitting it to the user;

[1772] A means of receiving user feedback and updating the training data of the generative AI model;

[1773] A system including:

[1774] (Claim 2)

[1775] A means for registering basic information of users and storing it on a server;

[1776] means for performing authentication based on registered user information;

[1777] The system of claim 1 further comprising:

[1778] (Claim 3)

[1779] A means of analyzing user questions and symptoms using a natural language processing module;

[1780] a means for generating advice from a curated knowledge base;

[1781] 10. The system of claim 1, comprising: [Explanation of symbols]

[1782] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for users to input medical questions and symptoms; A means for sending the inputted question or symptom to a server; A means for analyzing questions and symptoms received on the server; A means for generating appropriate answers using an AI model based on the analysis results; means for transmitting the generated answer to the user; A means of receiving user feedback and updating the training data of the generative AI model; A system including:

2. A means for registering basic information of users and storing it on a server; means for performing authentication based on registered user information; The system of claim 1 further comprising:

3. A means of analyzing user questions and symptoms using a natural language processing module; a means of generating answers from a curated medical knowledge base; The system of claim 1 , comprising:

Images