System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a question input by a user; means for analyzing the received question to extract a keyword; means for searching a health-knowledge database based on the keyword; means for searching a preventive database based on the keyword; means for providing a result of the searching to a generative AI model to generate a customized response to the user; and means for transmitting the generated response to the user device.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's world, users have access to a wealth of health-related information, but it is difficult to determine whether that information is appropriate for them. Furthermore, much of the health information is general and lacks customization to suit individual users' circumstances. As a result, users are unable to obtain appropriate health information and preventative measures, making it difficult to practice effective healthcare. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system that receives a question entered by a user in natural language, analyzes the question to extract keywords, searches a health knowledge database and a preventive measures database based on the extracted keywords, uses a generative AI model to generate a customized response for the user based on the search results, and transmits the response to the user's terminal, allowing the user to easily obtain appropriate health information and preventive measures tailored to their own situation.

[0006] "User" refers to an individual who uses the system to obtain health information.

[0007] "Natural language" refers to a language used in everyday life and expressed through speech and text.

[0008] "Question" refers to a health-related question or inquiry that a user inputs into the system.

[0009] "Receiving" refers to the act of a terminal or server receiving a question sent by a user.

[0010] "Analysis" refers to the process of linguistically analyzing the received question and extracting important elements and keywords from it.

[0011] "Keywords" refer to important words or phrases extracted through analysis that express the gist of the question.

[0012] A "health knowledge database" refers to a source of information that systematically registers and stores various types of health information.

[0013] "Preventive measures database" refers to a source of information that systematically registers and stores measures and information for preventing various diseases and health problems.

[0014] "Search" refers to the act of finding relevant information from a database based on keywords extracted through analysis.

[0015] A "generative AI model" is a type of artificial intelligence that refers to an algorithm that generates responses or sentences in natural language based on specified input.

[0016] "Customized response" refers to a personalized response generated based on the user's question and situation.

[0017] "Sending" refers to the act of sending the generated response to the user's terminal.

[0018] "User terminal" refers to an electronic device used by a user to access the system, enter questions, and receive responses.

[0019] "HTTP request" refers to a method of sending a data request to a server using the Hypertext Transfer Protocol.

[0020] An "HTTP response" refers to the data or information returned by a server in response to an HTTP request. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. To explain the present invention, a specific embodiment will be described below.

[0043] Users access this system using devices such as smartphones or PCs. They input a health-related question and press the send button to send the question to the system. For example, a user might input "I've been feeling tired a lot lately. What should I do?" and send it.

[0044] The terminal sends the question entered by the user to the server. Specifically, the terminal sends the user's question data to the server using a protocol such as an HTTP POST request. The server then analyzes the received user's question.

[0045] The server uses a natural language processing (NLP) engine to analyze the received question and extract keywords. For example, from the question "I've been feeling tired a lot lately, what should I do?", it extracts keywords such as "I get tired easily."

[0046] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. Specifically, it searches the database for health information and preventive measures related to the keyword "easily tired."

[0047] Based on the search results, the server uses a generative AI model to generate a customized response for the user, such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0048] The server sends the generated response to the user's terminal. Specifically, it returns the generated response data as an HTTP response to the terminal. The terminal then displays the received response to the user.

[0049] For example, if a user inputs "I've been feeling tired a lot lately. What should I do?", the server will generate a response saying, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective," and send it to the user's device. The device will then display the response to the user.

[0050] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures tailored to their own circumstances. Furthermore, by utilizing a generative AI model, responses to users can be customized, providing more specific and useful information.

[0051] The above is a specific embodiment of the present invention.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0055] Step 2:

[0056] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0057] Step 3:

[0058] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine.

[0059] Step 4:

[0060] The server analyzes the received question using an NLP engine and extracts keywords, for example, "getting tired easily."

[0061] Step 5:

[0062] The server searches a health knowledge database based on the extracted keywords and retrieves health information related to the keywords from the database.

[0063] Step 6:

[0064] The server searches the preventive measures database using the same keyword, and retrieves preventive measures information related to the keyword from the database.

[0065] Step 7:

[0066] The server integrates the health and prevention information obtained from the search results and provides it to a generative AI model, which then uses this information to generate a customized response.

[0067] Step 8:

[0068] The server then sends the generated response to the device as an HTTP response, which includes specific health advice and preventative measures.

[0069] Step 9:

[0070] The terminal analyzes the HTTP response received from the server, extracts the generated response, and displays the obtained response to the user.

[0071] Step 10:

[0072] Users can check and use customized health advice and preventative measures displayed on their device. For example, advice such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective."

[0073] Example 1

[0074] 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."

[0075] Many users today require fast and accurate access to health-related information. However, the Internet is overflowing with a wide variety of information, making it difficult to efficiently search for reliable information and to instantly obtain customized advice tailored to each user's situation and questions. The present invention aims to solve these problems by providing customized responses to questions entered by users in natural language.

[0076] 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.

[0077] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to the user terminal as an HTTP response, and means for displaying the generated response on the user terminal, thereby enabling users to efficiently obtain reliable health information and preventive measures.

[0078] A "user" is a person who uses the system to input questions in natural language and obtain information.

[0079] "Natural language" refers to words and sentences that humans use on a daily basis, and is not a specialized programming language.

[0080] The "means for receiving a question" refers to a function for receiving a question entered by a user in natural language and passing it to the system.

[0081] "Means for analyzing questions and extracting keywords" refers to a function for extracting key keywords from received questions using a natural language processing engine.

[0082] The "health knowledge database" is a database that organizes and stores health-related information, and allows users to search for information related to relevant keywords.

[0083] A "prevention measures database" is a database that describes methods and measures for preventing health problems.

[0084] A "generative AI model" refers to an artificial intelligence model that generates customized responses to users based on given input data.

[0085] An "HTTP response" refers to data that a server sends in response to an HTTP request from a client (user terminal).

[0086] "User terminal" refers to a device used by a user, such as a smartphone or PC.

[0087] "Means for displaying a response" refers to a function for visually displaying the generated response on the user terminal.

[0088] The present invention is a system that allows a user to input a health-related question in natural language and generates and provides a customized response to the question. Specific embodiments of the present invention are described below.

[0089] Users access the system using devices such as smartphones or PCs. Using a browser or a dedicated application, users input health-related questions in natural language and press the send button. For example, a user might input, "I've been feeling tired a lot lately. What should I do?"

[0090] The device sends the question entered by the user to the server using an HTTP POST request. Specifically, the device generates data containing the question text entered on the device and sends it to the specified API endpoint of the server.

[0091] The server receives the HTTP request, parses its contents, extracts the question text from the request body, and passes it to a backend application server, where a web server such as NGINX or Apache runs, and an application server such as Node.js or Django processes the request.

[0092] The server then uses a natural language processing (NLP) engine to analyze the received question and extract key keywords. For example, to extract the keyword "tired easily" from the question "I've been feeling tired a lot lately, what should I do?", it uses natural language processing tools such as spaCy and Google Cloud Natural Language API.

[0093] The server searches the health knowledge database and preventive measures database based on the extracted keywords. For the search, a database management system (e.g., MySQL or MongoDB) is used to retrieve health information and preventive measures related to "easily tired" through a database query.

[0094] The server uses a generative AI model to generate a response customized for the user based on the search results. As an example of a generative AI model, we use OpenAI GPT-3. For example, we send the following prompt to the generative AI model:

[0095] "If you're feeling tired recently, what measures would be effective?"

[0096] This allows the generative AI model to generate a specific response sentence and return it to the server.

[0097] The server sends the response to the user's device as an HTTP response, along with the appropriate HTTP status code and the generated response text.

[0098] Finally, the device analyzes the received response and displays it in a format that is easy for the user to see. For example, it could display a message on a web page or in an application that reads, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0099] In this way, users can easily obtain specific and relevant health advice and information to answer their questions. The system excels in that it utilizes generative AI models to customize responses to users and provide more useful information.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] Users access the system using a smartphone or PC. They launch a browser or a dedicated application and input health-related questions in natural language. For example, they might input, "I've been feeling tired a lot lately. What should I do?" The input data is stored in the device's memory.

[0103] Step 2:

[0104] The device sends the entered question to the server as an HTTP POST request. Specifically, the device generates data including the question text and sends it to the server's API endpoint. The input data is the question text to be sent, and the output data is the HTTP request to the server.

[0105] Step 3:

[0106] The server receives the HTTP request and parses its content. A web server (e.g., NGINX or Apache) receives the request, and an application server (e.g., Node.js or Django) extracts the question text from the request body. The input data is the received HTTP request, and the output data is the extracted question text.

[0107] Step 4:

[0108] The server uses a natural language processing (NLP) engine (e.g., spaCy or Google Cloud Natural Language API) to analyze the received question and extract key keywords. For example, the keyword "gets tired easily" is extracted from the question "I've been feeling tired a lot lately. What should I do?" The input data is the question text, and the output data is the extracted keywords.

[0109] Step 5:

[0110] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. It uses a database management system (e.g., MySQL or MongoDB) to retrieve information related to the corresponding keywords. The input data are the extracted keywords, and the output data are the search results.

[0111] Step 6:

[0112] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a personalized response for the user based on the search results. The server sends the following prompt to the generative AI model:

[0113] "If you're feeling tired recently, what measures would be effective?"

[0114] This allows the generative AI model to generate a specific response. The input data are the search results and the prompt, and the output data is the generated response.

[0115] Step 7:

[0116] The server sends the generated response to the user terminal as an HTTP response. The server creates response data and sends it to the terminal along with an appropriate HTTP status code. The input data is the generated response, and the output data is the HTTP response.

[0117] Step 8:

[0118] The terminal analyzes the HTTP response received from the server and displays its contents to the user. Specifically, the browser or application processes the response data and displays it on the screen in a form that the user can see. For example, a message such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective." is displayed. The input data is the received HTTP response, and the output data is the response message that is displayed.

[0119] (Application example 1)

[0120] 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."

[0121] Conventional health information systems lack the convenience of providing responses to user questions when the user is in a vehicle or using an autonomous vehicle. For example, when a passenger needs health advice while driving long distances, there are limited means to provide prompt and appropriate information. In such environments, providing prompt, appropriate, and customized responses to users is required, but this has been difficult with conventional systems.

[0122] 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.

[0123] In this invention, the server includes means for receiving a question input in natural language by a user, means for analyzing the received question to extract keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model to generate a customized response for the user, means for transmitting the generated response to a user terminal, and means for displaying the response on a display device used in the autonomous vehicle, thereby enabling passengers to instantly receive prompt and appropriate advice regarding their health condition while in the autonomous vehicle.

[0124] A "user" is an individual who utilizes the system to enter a question.

[0125] "Natural language" is a form of language expressed in words used by people in everyday life.

[0126] A "question" is a statement that a user enters into the system to request information or advice.

[0127] A "means" is a method or device designed to accomplish a particular purpose.

[0128] "Analysis" is the process of interpreting the input question and extracting the necessary information.

[0129] "Keywords" are words or phrases extracted from a question as important elements.

[0130] A "health knowledge database" is a database that compiles information and knowledge about health.

[0131] The "Preventive Measures Database" is a database that compiles information on preventive measures for health problems.

[0132] "Searching" is the process of finding information related to specific keywords within a database.

[0133] A "generative AI model" is a program that uses machine learning techniques to generate customized responses to users.

[0134] A "customized response" is a response that is individually generated in response to a user's specific question.

[0135] A "user terminal" is an electronic device that a user uses to enter questions and receive responses.

[0136] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without a driver.

[0137] A "display device" is a device for visually presenting the generated response to a user.

[0138] This invention is a system that processes questions entered by a user in natural language and provides customized health advice. This system is intended for use in autonomous vehicles and can use a display device such as smart glasses.

[0139] The server receives questions entered by the user in natural language. For example, if a user wears smart glasses and asks a question by voice, such as "I get tired easily when I sit for a long time. Is there anything I can do?", the voice recognition API of the smart glasses converts this into text and sends it to the server.

[0140] The server analyzes the received question using a natural language processing engine (such as Google Cloud NLP or spaCy) to extract keywords, such as "sitting for long periods of time" and "getting tired easily."

[0141] The server then searches the health knowledge database and the preventive measures database based on the extracted keywords, thereby obtaining relevant health information and preventive measures.

[0142] The server then provides the search results to a generative AI model (e.g., OpenAI's GPT-3) to generate a customized response for the user, such as "It's important to stretch regularly. Also, getting out of the car and taking breaks regularly can help reduce fatigue."

[0143] The generated response is sent as an HTTP response to the user's smart glasses, which then visually display the received response on their display, allowing the user to receive prompt and appropriate health advice within the autonomous vehicle.

[0144] For example, if a passenger on a long-distance drive asks, "I get tired when I sit for long periods of time. What should I do?", the following prompt sentence is input to the generative AI model:

[0145] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[0146] response:

[0147] Based on this prompt, the generative AI model generates an appropriate response and displays it on the passenger's smart glasses, providing specific advice such as, "It's important to stretch regularly. Staying hydrated and ventilating the car can also help reduce fatigue."

[0148] In this way, the present invention allows passengers to easily manage their health in autonomous vehicles through smart glasses.

[0149] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0150] Step 1:

[0151] The user inputs a question by voice through the smart glasses. For example, "I get tired easily when I sit for a long time. Is there anything I can do about it?" The input voice data is picked up by the microphone in the smart glasses.

[0152] Step 2:

[0153] The device (smart glasses) converts the acquired voice data into text data using a speech recognition API (e.g., Google Speech-to-Text API). The converted text data is generated.

[0154] Step 3:

[0155] The terminal sends the converted text data to the server using an HTTP POST request, and the sent data is received by the server.

[0156] Step 4:

[0157] The server analyzes the text data of the received question using a natural language processing engine (e.g., Google Cloud NLP, spaCy) and extracts keywords, such as "sitting for long periods of time" and "getting tired easily."

[0158] Step 5:

[0159] The server searches the health knowledge database and the preventive measures database based on the extracted keywords, and retrieves relevant information that matches the keywords.

[0160] Step 6:

[0161] The server inputs the search results into a generative AI model (e.g., OpenAI's GPT-3). For example, the following prompt is generated along with the search results:

[0162] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[0163] response:

[0164] The generative AI model uses this prompt to generate a customized response.

[0165] Step 7:

[0166] The server sends the generated response to the user's device (smart glasses) as an HTTP response. The sent response data is received by the device.

[0167] Step 8:

[0168] The device visually displays the received response data on the smart glasses display, providing advice to the user, such as, "It is important to stretch regularly. Also, staying hydrated and ventilating the car interior can help reduce fatigue."

[0169] 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.

[0170] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. By further combining the present invention with an emotion engine, the system can recognize the user's emotion and provide a customized response according to the emotion. Specific embodiments of the present invention are described below.

[0171] Users access this system using devices such as smartphones or PCs. The user inputs a health-related question and sends it to the system by pressing the send button. For example, consider the case where a user inputs and sends "I've been feeling tired a lot lately. What should I do?"

[0172] The device sends the question entered by the user to the server as an HTTP POST request. Specifically, the destination is the system's API endpoint. The server analyzes the HTTP request received from the device and extracts the question. The received question is then sent to a natural language processing (NLP) engine and an emotion engine.

[0173] The server uses an NLP engine to analyze the question and extract keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the user's emotions and obtains the results. For example, if the user enters the question "gets tired easily," emotions such as anxiety and fatigue are recognized.

[0174] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions. Specifically, it retrieves health information and preventive measures related to keywords such as "easily tired" and emotions such as anxiety and fatigue from the database.

[0175] The server uses a generative AI model to generate a customized response based on the search results. For example, it takes into account the user's emotions recognized by the emotion engine and generates a response such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[0176] The server sends the generated response to the terminal as an HTTP response. The terminal analyzes the HTTP response received from the server and extracts the generated response. The terminal displays the obtained response to the user. The user can check and practice the customized health advice and preventive measures displayed on the terminal.

[0177] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[0178] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures according to their own situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses to users become more specific and useful, enabling the provision of personalized healthcare support.

[0179] The above is a specific embodiment of the present invention.

[0180] The processing flow will be explained below.

[0181] Step 1:

[0182] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0183] Step 2:

[0184] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0185] Step 3:

[0186] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine and an emotion engine.

[0187] Step 4:

[0188] The server uses an NLP engine to analyze the question and extract keywords. For example, the server extracts the keyword "tired easily" from the question "I've been feeling tired a lot lately. What should I do?"

[0189] Step 5:

[0190] The server uses an emotion engine to recognize the emotion contained in the user's question. For example, it can recognize that the user is feeling tired or anxious based on keywords and context in the question.

[0191] Step 6:

[0192] The server searches a health knowledge database based on the extracted keywords and the recognized emotions. For example, based on the keywords "easily tired" and "anxiety," it retrieves related health information.

[0193] Step 7:

[0194] The server searches the preventive measures database using the same keywords and emotions, for example, to retrieve preventive measures related to fatigue recovery and mental stress reduction.

[0195] Step 8:

[0196] The server uses a generative AI model based on the acquired health and preventive measures information to generate a customized response, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. If you feel anxious, try relaxation techniques."

[0197] Step 9:

[0198] The server sends the generated response to the terminal as an HTTP response. Specifically, the server includes the generated response text in the HTTP response body and returns it to the terminal.

[0199] Step 10:

[0200] The terminal analyzes the HTTP response received from the server and extracts the generated response. Specifically, it obtains text data from the response body and displays it to the user.

[0201] Step 11:

[0202] Users can review and implement customized health advice and preventative measures displayed on their device, such as following suggested dietary changes and trying relaxation techniques.

[0203] The above is the flow of processing in a specific embodiment of the present invention.

[0204] Example 2

[0205] 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."

[0206] Conventional health information systems typically respond to users' questions in natural language and are often not customized to reflect the individual user's situation or emotions. This makes it difficult for users to obtain specific and useful advice. Furthermore, while taking the user's emotions into account would enable more appropriate and effective responses, conventional technologies lack such functionality.

[0207] 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.

[0208] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to a user terminal, means including an emotion engine for analyzing the user's emotions, and means for generating a customized response based on the emotions recognized by the emotion engine. This makes it possible to provide specific and useful advice in response to a user's health-related question, taking into account the user's individual situation and emotions.

[0209] "User" refers to a person who enters a health-related question into the system in natural language and intends to receive a response.

[0210] A "question" refers to a sentence in which a user expresses a question or concern about health in natural language, and this sentence is the subject of transmission to the system.

[0211] "Terminal" refers to the device used by the user to input questions and receive responses from the system, such as a smartphone or PC.

[0212] "Server" refers to a computing system that is responsible for receiving and analyzing a user's query, and generating and transmitting a response.

[0213] A "natural language processing engine" refers to software that analyzes natural language questions entered by users and extracts keywords and structures.

[0214] An "emotion engine" refers to software that analyzes and recognizes the emotions contained in a user's question.

[0215] A "health knowledge database" refers to a collection of data that systematically records health-related information and is used to generate answers to questions.

[0216] A "preventive measures database" refers to a collection of data containing specific measures for maintaining or improving health, and is used to generate answers to questions.

[0217] A "generative AI model" refers to an artificial intelligence that automatically generates natural language responses to users based on received data. Specifically, this includes deep learning models.

[0218] "Customized responses" refer to answers that are individually tailored based on the user's question and emotions, providing the user with the most relevant health advice and information.

[0219] The present invention provides a system that provides customized responses to health-related questions entered by a user in natural language, taking into account the user's individual circumstances and emotions. Specific embodiments of the system are described below.

[0220] A user accesses the system using a device such as a smartphone or PC. For example, they enter "I've been feeling tired a lot lately. What should I do?" into a text box displayed on a web browser and press the send button. The device then sends this question to the server as an HTTP POST request.

[0221] The server receives the HTTP POST request sent from the device and analyzes the request body to extract the question. This question is then sent to a natural language processing (NLP) engine and an emotion engine. The NLP engine analyzes the question and extracts key keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the emotions contained in the question and recognizes "anxiety" and "fatigue."

[0222] Next, the server searches the health knowledge database and preventive measures database based on the keywords from the NLP engine and the emotion information from the emotion engine. For example, it retrieves health information and preventive measures related to "easily tired," "anxiety," and "fatigue" from the database. The retrieved information is then provided to a generative AI model (e.g., GPT-4).

[0223] The generative AI model generates a customized response based on the information provided, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend making time to relax."

[0224] The generated response is sent from the server to the device as an HTTP response. The device analyzes the received HTTP response and displays the generated response to the user. The user can then review and implement specific, customized health advice and preventive measures.

[0225] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[0226] Examples of prompts:

[0227] If a user types, "I've been feeling tired lately, what should I do?", what response should the system generate? The user's emotions are anxiety and fatigue.

[0228] As described above, by implementing this invention, users can easily obtain specific and useful advice tailored to their health-related situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses can be personalized, providing more beneficial healthcare support.

[0229] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0230] System program processing flow:

[0231] Step 1:

[0232] User inputs and submits a question

[0233] The user uses the terminal to input a health-related question in natural language. For example, the user might input "I've been feeling tired a lot lately. What should I do?" and click the send button.

[0234] Input: A user-entered natural language question.

[0235] Output: HTTP POST request from the terminal to the server.

[0236] Step 2:

[0237] Sending an HTTP request from the device to the server

[0238] The device sends the question entered by the user to the server as an HTTP POST request, which includes the question in JSON format.

[0239] Specific request example:

[0240] POST / api / health_query HTTP / 1.1

[0241] Host: api.example.com

[0242] Content-Type: application / json

[0243] {

[0244] "question": "I've been feeling tired a lot lately. What should I do?"

[0245] }

[0246] Input: The user's question.

[0247] Output: HTTP POST request to the server.

[0248] Step 3:

[0249] The server receives and analyzes the HTTP request

[0250] The server receives the HTTP POST request sent from the device, extracts the question from the request body, and sends it to the natural language processing engine and emotion engine for analysis.

[0251] Input: HTTP POST request.

[0252] Output: The question.

[0253] Step 4:

[0254] Question analysis by NLP engine

[0255] The server sends the question to a natural language processing (NLP) engine, which analyzes the question and extracts keywords, such as "easily tired."

[0256] Input: Question.

[0257] Output: Extracted keywords.

[0258] Step 5:

[0259] Emotion analysis using an emotion engine

[0260] The server sends the question to the emotion engine, which analyzes the user's emotions. For example, "anxiety" or "fatigue" is recognized.

[0261] Input: Question.

[0262] Output: Recognized emotion.

[0263] Step 6:

[0264] Database search by server

[0265] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions to obtain relevant health information and preventive measures. For example, information related to "easily tired," "anxiety," and "fatigue" is obtained.

[0266] Input: Extracted keywords, recognized sentiment.

[0267] Output: Health information and preventive measures.

[0268] Step 7:

[0269] Generating a response

[0270] The server provides the acquired health information and preventive measures to a generative AI model (e.g., GPT-4) to generate a customized response for the user. For example, a response might be generated such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[0271] Enter: health information and precautions.

[0272] Output: The customized response.

[0273] Step 8:

[0274] Sending HTTP responses from the server to the device

[0275] The server sends the generated customization response to the device as an HTTP response. For example, the response is sent in the following format:

[0276] HTTP / 1.1 200 OK

[0277] Content-Type: application / json

[0278] {

[0279] "response": "To recover from fatigue, it is important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Taking care of your mind is also important, so I recommend making time to relax."

[0280] }

[0281] Input: Your customized response.

[0282] Output: HTTP response to the device.

[0283] Step 9:

[0284] Terminal receives and displays response

[0285] The device receives the HTTP response, parses it, extracts the generated response, and displays it to the user, who can then view and implement specific, customized health advice.

[0286] Input: HTTP response.

[0287] Output: The response displayed to the user.

[0288] The above are the specific processing steps of the program for this system. By following this flow, users can easily receive specific and useful advice tailored to their health condition.

[0289] (Application example 2)

[0290] 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."

[0291] In recent years, there has been an increasing demand for health consultations and advice via smart devices. However, conventional systems have difficulty providing customized responses that take the user's emotions into account in real time, resulting in a decline in user satisfaction. Furthermore, there is a demand for efficient information provision using wearable devices such as smart glasses, but the technology to achieve this is still in its infancy. Therefore, a system that analyzes the user's emotions and provides health advice accordingly is needed.

[0292] 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 receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, and means for searching a health knowledge database based on the keywords. This makes it possible to analyze the user's emotions and generate customized responses in real time to display on the smart glasses. This also improves user satisfaction and makes it possible to provide health advice more effectively.

[0293] "Means for receiving questions entered by a user in natural language" refers to the function of recognizing questions entered by a user in natural language such as voice or text and sending them to the system.

[0294] "Means for analyzing received questions and extracting keywords" refers to a function that analyzes received questions using natural language processing technology and extracts important keywords.

[0295] "Means for searching a health knowledge database based on keywords" refers to a function for searching a database for relevant health information using the extracted keywords.

[0296] "Means for searching the database of preventive measures based on keywords" refers to a function that uses the extracted keywords to search the database for relevant preventive measures and advice.

[0297] "Means for analyzing user emotions" refers to a function for recognizing the user's emotions from the received questions and identifying the appropriate emotional state.

[0298] "Means of providing search results and sentiment analysis results to a generative AI model to generate a customized response for the user" refers to the function of using generative AI to create a customized response for the user based on the searched information and the results of sentiment analysis.

[0299] "Means for transmitting the generated response to the user terminal and displaying it on the display of the smart glasses" refers to a function for transmitting the generated response to the user's smart device via the Internet and displaying it on the display of the smart glasses.

[0300] "Natural language processing engine" refers to a software engine that analyzes received natural language text and understands its meaning.

[0301] "Emotion engine" refers to a software engine for recognizing a user's emotional state from text or speech.

[0302] A "generative AI model" refers to an artificial intelligence model that generates appropriate responses based on input data (keywords and sentiment analysis results).

[0303] "Smart glasses" are a wearable eyeglass-type device with a built-in display that allows users to receive visual information in real time.

[0304] The present invention relates to a system that allows users to input health-related questions in natural language and generates and provides responses to those questions, and that can provide real-time health advice using smart glasses.

[0305] Users can input health-related questions by voice through the smart glasses. The voice-input information is converted into text using voice recognition software (e.g., Google Speech-to-Text API) within the smart glasses. The converted text is then sent to a server over the Internet.

[0306] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) to extract keywords from the question, and simultaneously analyzes the user's sentiment using an emotion engine (e.g., Microsoft Azure's Text Analytics API) to obtain the results.

[0307] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the results of emotion analysis. For example, if the keyword "easily tired" is extracted and "fatigue" and "anxiety" are recognized from the emotion analysis results, the server retrieves related health information and preventive measures from the database.

[0308] The server generates a customized response based on the search results and sentiment analysis results using a generative AI model (e.g., GPT-3), which is then sent over the internet to the user's smart glasses and displayed on their screen.

[0309] For example, if a user types, "I've been feeling tired a lot lately. What should I do?", the server will generate a response such as, "A balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so I recommend that you make time to relax," and display this on the smart glasses.

[0310] This invention allows users to receive customized health advice in real time and enjoy individual health support, thereby improving user satisfaction and realizing a system that effectively provides health advice.

[0311] An example of a prompt sentence is as follows:

[0312] "Generate customized health advice based on the following questions and emotions: Question: 'I've been feeling tired lately, what should I do?' Emotion: 'I feel anxious and tired.'"

[0313] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0314] Step 1:

[0315] The user inputs health-related questions by voice through the smart glasses. The voice data is captured by the microphone of the smart glasses. The input data is in voice format, and the final output is a question in text format.

[0316] Step 2:

[0317] The smart glasses' voice recognition software converts the input voice data into text. Specifically, the Google Speech-to-Text API receives the voice data, analyzes its content, and generates corresponding text. The input is voice data, and the output is text data.

[0318] Step 3:

[0319] The terminal sends text data to a server over the Internet. The text data is sent using an HTTP POST request. The input is the text data, and the output is an HTTP request to the server.

[0320] Step 4:

[0321] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) and extracts keywords. Specifically, it tokenizes the text and extracts important keywords. The input is text data, and the output is a list of keywords.

[0322] Step 5:

[0323] The server searches the health knowledge database based on the keywords, and uses SQL queries to retrieve relevant health information from the database. The input is the keywords, and the output is a list of health information.

[0324] Step 6:

[0325] At the same time, the server uses an emotion engine (e.g., Microsoft Azure's Text Analytics API) to analyze the user's emotions. Specifically, it analyzes the text data to detect patterns specific to emotions. The input is the text data, and the output is the emotion analysis results.

[0326] Step 7:

[0327] The server searches the preventive measures database based on the keywords and sentiment analysis results. It uses SQL queries to retrieve relevant information from the preventive measures database. The input is the keywords and sentiment analysis results, and the output is a list of preventive measures.

[0328] Step 8:

[0329] The server generates a customized response using a generative AI model (e.g., GPT-3) based on the search results and sentiment analysis results. A prompt is input to the generative AI model, which outputs a customized text response. The input is the prompt and search results, and the output is a customized response.

[0330] Step 9:

[0331] The server generates a response and sends it to the terminal as an HTTP response. The input is a customized response, and the output is an HTTP response.

[0332] Step 10:

[0333] The terminal parses the received HTTP response and extracts the generated response. The input is the HTTP response and the output is the text response.

[0334] Step 11:

[0335] The terminal displays the acquired text response on the display of the smart glasses. The input is the text response, and the output is the response displayed on the display.

[0336] 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.

[0337] 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.

[0338] 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.

[0339] [Second embodiment]

[0340] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0341] 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.

[0342] 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).

[0343] 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.

[0344] 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.

[0345] 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).

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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.

[0350] 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.

[0351] 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."

[0352] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. To explain the present invention, a specific embodiment will be described below.

[0353] Users access this system using devices such as smartphones or PCs. They input a health-related question and press the send button to send the question to the system. For example, a user might input "I've been feeling tired a lot lately. What should I do?" and send it.

[0354] The terminal sends the question entered by the user to the server. Specifically, the terminal sends the user's question data to the server using a protocol such as an HTTP POST request. The server then analyzes the received user's question.

[0355] The server uses a natural language processing (NLP) engine to analyze the received question and extract keywords. For example, from the question "I've been feeling tired a lot lately, what should I do?", it extracts keywords such as "I get tired easily."

[0356] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. Specifically, it searches the database for health information and preventive measures related to the keyword "easily tired."

[0357] Based on the search results, the server uses a generative AI model to generate a customized response for the user, such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0358] The server sends the generated response to the user's terminal. Specifically, it returns the generated response data as an HTTP response to the terminal. The terminal then displays the received response to the user.

[0359] For example, if a user inputs "I've been feeling tired a lot lately. What should I do?", the server will generate a response saying, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective," and send it to the user's device. The device will then display the response to the user.

[0360] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures tailored to their own circumstances. Furthermore, by utilizing a generative AI model, responses to users can be customized, providing more specific and useful information.

[0361] The above is a specific embodiment of the present invention.

[0362] The processing flow will be explained below.

[0363] Step 1:

[0364] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0365] Step 2:

[0366] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0367] Step 3:

[0368] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine.

[0369] Step 4:

[0370] The server analyzes the received question using an NLP engine and extracts keywords, for example, "getting tired easily."

[0371] Step 5:

[0372] The server searches a health knowledge database based on the extracted keywords and retrieves health information related to the keywords from the database.

[0373] Step 6:

[0374] The server searches the preventive measures database using the same keyword, and retrieves preventive measures information related to the keyword from the database.

[0375] Step 7:

[0376] The server integrates the health and prevention information obtained from the search results and provides it to a generative AI model, which then uses this information to generate a customized response.

[0377] Step 8:

[0378] The server then sends the generated response to the device as an HTTP response, which includes specific health advice and preventative measures.

[0379] Step 9:

[0380] The terminal analyzes the HTTP response received from the server, extracts the generated response, and displays the obtained response to the user.

[0381] Step 10:

[0382] Users can check and use customized health advice and preventative measures displayed on their device. For example, advice such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective."

[0383] Example 1

[0384] 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."

[0385] Many users today require fast and accurate access to health-related information. However, the Internet is overflowing with a wide variety of information, making it difficult to efficiently search for reliable information and to instantly obtain customized advice tailored to each user's situation and questions. The present invention aims to solve these problems by providing customized responses to questions entered by users in natural language.

[0386] 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.

[0387] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to the user terminal as an HTTP response, and means for displaying the generated response on the user terminal, thereby enabling users to efficiently obtain reliable health information and preventive measures.

[0388] A "user" is a person who uses the system to input questions in natural language and obtain information.

[0389] "Natural language" refers to words and sentences that humans use on a daily basis, and is not a specialized programming language.

[0390] The "means for receiving a question" refers to a function for receiving a question entered by a user in natural language and passing it to the system.

[0391] "Means for analyzing questions and extracting keywords" refers to a function for extracting key keywords from received questions using a natural language processing engine.

[0392] The "health knowledge database" is a database that organizes and stores health-related information, and allows users to search for information related to relevant keywords.

[0393] A "prevention measures database" is a database that describes methods and measures for preventing health problems.

[0394] A "generative AI model" refers to an artificial intelligence model that generates customized responses to users based on given input data.

[0395] An "HTTP response" refers to data that a server sends in response to an HTTP request from a client (user terminal).

[0396] "User terminal" refers to a device used by a user, such as a smartphone or PC.

[0397] "Means for displaying a response" refers to a function for visually displaying the generated response on the user terminal.

[0398] The present invention is a system that allows a user to input a health-related question in natural language and generates and provides a customized response to the question. Specific embodiments of the present invention are described below.

[0399] Users access the system using devices such as smartphones or PCs. Using a browser or a dedicated application, users input health-related questions in natural language and press the send button. For example, a user might input, "I've been feeling tired a lot lately. What should I do?"

[0400] The device sends the question entered by the user to the server using an HTTP POST request. Specifically, the device generates data containing the question text entered on the device and sends it to the specified API endpoint of the server.

[0401] The server receives the HTTP request, parses its contents, extracts the question text from the request body, and passes it to a backend application server, where a web server such as NGINX or Apache runs, and an application server such as Node.js or Django processes the request.

[0402] The server then uses a natural language processing (NLP) engine to analyze the received question and extract key keywords. For example, to extract the keyword "tired easily" from the question "I've been feeling tired a lot lately, what should I do?", it uses natural language processing tools such as spaCy and Google Cloud Natural Language API.

[0403] The server searches the health knowledge database and preventive measures database based on the extracted keywords. For the search, a database management system (e.g., MySQL or MongoDB) is used to retrieve health information and preventive measures related to "easily tired" through a database query.

[0404] The server uses a generative AI model to generate a response customized for the user based on the search results. As an example of a generative AI model, we use OpenAI GPT-3. For example, we send the following prompt to the generative AI model:

[0405] "If you're feeling tired recently, what measures would be effective?"

[0406] This allows the generative AI model to generate a specific response sentence and return it to the server.

[0407] The server sends the response to the user's device as an HTTP response, along with the appropriate HTTP status code and the generated response text.

[0408] Finally, the device analyzes the received response and displays it in a format that is easy for the user to see. For example, it could display a message on a web page or in an application that reads, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0409] In this way, users can easily obtain specific and relevant health advice and information to answer their questions. The system excels in that it utilizes generative AI models to customize responses to users and provide more useful information.

[0410] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0411] Step 1:

[0412] Users access the system using a smartphone or PC. They launch a browser or a dedicated application and input health-related questions in natural language. For example, they might input, "I've been feeling tired a lot lately. What should I do?" The input data is stored in the device's memory.

[0413] Step 2:

[0414] The device sends the entered question to the server as an HTTP POST request. Specifically, the device generates data including the question text and sends it to the server's API endpoint. The input data is the question text to be sent, and the output data is the HTTP request to the server.

[0415] Step 3:

[0416] The server receives the HTTP request and parses its content. A web server (e.g., NGINX or Apache) receives the request, and an application server (e.g., Node.js or Django) extracts the question text from the request body. The input data is the received HTTP request, and the output data is the extracted question text.

[0417] Step 4:

[0418] The server uses a natural language processing (NLP) engine (e.g., spaCy or Google Cloud Natural Language API) to analyze the received question and extract key keywords. For example, the keyword "gets tired easily" is extracted from the question "I've been feeling tired a lot lately. What should I do?" The input data is the question text, and the output data is the extracted keywords.

[0419] Step 5:

[0420] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. It uses a database management system (e.g., MySQL or MongoDB) to retrieve information related to the corresponding keywords. The input data are the extracted keywords, and the output data are the search results.

[0421] Step 6:

[0422] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a personalized response for the user based on the search results. The server sends the following prompt to the generative AI model:

[0423] "If you're feeling tired recently, what measures would be effective?"

[0424] This allows the generative AI model to generate a specific response. The input data are the search results and the prompt, and the output data is the generated response.

[0425] Step 7:

[0426] The server sends the generated response to the user terminal as an HTTP response. The server creates response data and sends it to the terminal along with an appropriate HTTP status code. The input data is the generated response, and the output data is the HTTP response.

[0427] Step 8:

[0428] The terminal analyzes the HTTP response received from the server and displays its contents to the user. Specifically, the browser or application processes the response data and displays it on the screen in a form that the user can see. For example, a message such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective." is displayed. The input data is the received HTTP response, and the output data is the response message that is displayed.

[0429] (Application example 1)

[0430] 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."

[0431] Conventional health information systems lack the convenience of providing responses to user questions when the user is in a vehicle or using an autonomous vehicle. For example, when a passenger needs health advice while driving long distances, there are limited means to provide prompt and appropriate information. In such environments, providing prompt, appropriate, and customized responses to users is required, but this has been difficult with conventional systems.

[0432] 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.

[0433] In this invention, the server includes means for receiving a question input in natural language by a user, means for analyzing the received question to extract keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model to generate a customized response for the user, means for transmitting the generated response to a user terminal, and means for displaying the response on a display device used in the autonomous vehicle, thereby enabling passengers to instantly receive prompt and appropriate advice regarding their health condition while in the autonomous vehicle.

[0434] A "user" is an individual who utilizes the system to enter a question.

[0435] "Natural language" is a form of language expressed in words used by people in everyday life.

[0436] A "question" is a statement that a user enters into the system to request information or advice.

[0437] A "means" is a method or device designed to accomplish a particular purpose.

[0438] "Analysis" is the process of interpreting the input question and extracting the necessary information.

[0439] "Keywords" are words or phrases extracted from a question as important elements.

[0440] A "health knowledge database" is a database that compiles information and knowledge about health.

[0441] The "Preventive Measures Database" is a database that compiles information on preventive measures for health problems.

[0442] "Searching" is the process of finding information related to specific keywords within a database.

[0443] A "generative AI model" is a program that uses machine learning techniques to generate customized responses to users.

[0444] A "customized response" is a response that is individually generated in response to a user's specific question.

[0445] A "user terminal" is an electronic device that a user uses to enter questions and receive responses.

[0446] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without a driver.

[0447] A "display device" is a device for visually presenting the generated response to a user.

[0448] This invention is a system that processes questions entered by a user in natural language and provides customized health advice. This system is intended for use in autonomous vehicles and can use a display device such as smart glasses.

[0449] The server receives questions entered by the user in natural language. For example, if a user wears smart glasses and asks a question by voice, such as "I get tired easily when I sit for a long time. Is there anything I can do?", the voice recognition API of the smart glasses converts this into text and sends it to the server.

[0450] The server analyzes the received question using a natural language processing engine (such as Google Cloud NLP or spaCy) to extract keywords, such as "sitting for long periods of time" and "getting tired easily."

[0451] The server then searches the health knowledge database and the preventive measures database based on the extracted keywords, thereby obtaining relevant health information and preventive measures.

[0452] The server then provides the search results to a generative AI model (e.g., OpenAI's GPT-3) to generate a customized response for the user, such as "It's important to stretch regularly. Also, getting out of the car and taking breaks regularly can help reduce fatigue."

[0453] The generated response is sent as an HTTP response to the user's smart glasses, which then visually display the received response on their display, allowing the user to receive prompt and appropriate health advice within the autonomous vehicle.

[0454] For example, if a passenger on a long-distance drive asks, "I get tired when I sit for long periods of time. What should I do?", the following prompt sentence is input to the generative AI model:

[0455] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[0456] response:

[0457] Based on this prompt, the generative AI model generates an appropriate response and displays it on the passenger's smart glasses, providing specific advice such as, "It's important to stretch regularly. Staying hydrated and ventilating the car can also help reduce fatigue."

[0458] In this way, the present invention allows passengers to easily manage their health in autonomous vehicles through smart glasses.

[0459] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0460] Step 1:

[0461] The user inputs a question by voice through the smart glasses. For example, "I get tired easily when I sit for a long time. Is there anything I can do about it?" The input voice data is picked up by the microphone in the smart glasses.

[0462] Step 2:

[0463] The device (smart glasses) converts the acquired voice data into text data using a speech recognition API (e.g., Google Speech-to-Text API). The converted text data is generated.

[0464] Step 3:

[0465] The terminal sends the converted text data to the server using an HTTP POST request, and the sent data is received by the server.

[0466] Step 4:

[0467] The server analyzes the text data of the received question using a natural language processing engine (e.g., Google Cloud NLP, spaCy) and extracts keywords, such as "sitting for long periods of time" and "getting tired easily."

[0468] Step 5:

[0469] The server searches the health knowledge database and the preventive measures database based on the extracted keywords, and retrieves relevant information that matches the keywords.

[0470] Step 6:

[0471] The server inputs the search results into a generative AI model (e.g., OpenAI's GPT-3). For example, the following prompt is generated along with the search results:

[0472] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[0473] response:

[0474] The generative AI model uses this prompt to generate a customized response.

[0475] Step 7:

[0476] The server sends the generated response to the user's device (smart glasses) as an HTTP response. The sent response data is received by the device.

[0477] Step 8:

[0478] The device visually displays the received response data on the smart glasses display, providing advice to the user, such as, "It is important to stretch regularly. Also, staying hydrated and ventilating the car interior can help reduce fatigue."

[0479] 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.

[0480] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. By further combining the present invention with an emotion engine, the system can recognize the user's emotion and provide a customized response according to the emotion. Specific embodiments of the present invention are described below.

[0481] Users access this system using devices such as smartphones or PCs. The user inputs a health-related question and sends it to the system by pressing the send button. For example, consider the case where a user inputs and sends "I've been feeling tired a lot lately. What should I do?"

[0482] The device sends the question entered by the user to the server as an HTTP POST request. Specifically, the destination is the system's API endpoint. The server analyzes the HTTP request received from the device and extracts the question. The received question is then sent to a natural language processing (NLP) engine and an emotion engine.

[0483] The server uses an NLP engine to analyze the question and extract keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the user's emotions and obtains the results. For example, if the user enters the question "gets tired easily," emotions such as anxiety and fatigue are recognized.

[0484] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions. Specifically, it retrieves health information and preventive measures related to keywords such as "easily tired" and emotions such as anxiety and fatigue from the database.

[0485] The server uses a generative AI model to generate a customized response based on the search results. For example, it takes into account the user's emotions recognized by the emotion engine and generates a response such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[0486] The server sends the generated response to the terminal as an HTTP response. The terminal analyzes the HTTP response received from the server and extracts the generated response. The terminal displays the obtained response to the user. The user can check and practice the customized health advice and preventive measures displayed on the terminal.

[0487] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[0488] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures according to their own situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses to users become more specific and useful, enabling the provision of personalized healthcare support.

[0489] The above is a specific embodiment of the present invention.

[0490] The processing flow will be explained below.

[0491] Step 1:

[0492] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0493] Step 2:

[0494] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0495] Step 3:

[0496] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine and an emotion engine.

[0497] Step 4:

[0498] The server uses an NLP engine to analyze the question and extract keywords. For example, the server extracts the keyword "tired easily" from the question "I've been feeling tired a lot lately. What should I do?"

[0499] Step 5:

[0500] The server uses an emotion engine to recognize the emotion contained in the user's question. For example, it can recognize that the user is feeling tired or anxious based on keywords and context in the question.

[0501] Step 6:

[0502] The server searches a health knowledge database based on the extracted keywords and the recognized emotions. For example, based on the keywords "easily tired" and "anxiety," it retrieves related health information.

[0503] Step 7:

[0504] The server searches the preventive measures database using the same keywords and emotions, for example, to retrieve preventive measures related to fatigue recovery and mental stress reduction.

[0505] Step 8:

[0506] The server uses a generative AI model based on the acquired health and preventive measures information to generate a customized response, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. If you feel anxious, try relaxation techniques."

[0507] Step 9:

[0508] The server sends the generated response to the terminal as an HTTP response. Specifically, the server includes the generated response text in the HTTP response body and returns it to the terminal.

[0509] Step 10:

[0510] The terminal analyzes the HTTP response received from the server and extracts the generated response. Specifically, it obtains text data from the response body and displays it to the user.

[0511] Step 11:

[0512] Users can review and implement customized health advice and preventative measures displayed on their device, such as following suggested dietary changes and trying relaxation techniques.

[0513] The above is the flow of processing in a specific embodiment of the present invention.

[0514] Example 2

[0515] 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."

[0516] Conventional health information systems typically respond to users' questions in natural language and are often not customized to reflect the individual user's situation or emotions. This makes it difficult for users to obtain specific and useful advice. Furthermore, while taking the user's emotions into account would enable more appropriate and effective responses, conventional technologies lack such functionality.

[0517] 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.

[0518] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to a user terminal, means including an emotion engine for analyzing the user's emotions, and means for generating a customized response based on the emotions recognized by the emotion engine. This makes it possible to provide specific and useful advice in response to a user's health-related question, taking into account the user's individual situation and emotions.

[0519] "User" refers to a person who enters a health-related question into the system in natural language and intends to receive a response.

[0520] A "question" refers to a sentence in which a user expresses a question or concern about health in natural language, and this sentence is the subject of transmission to the system.

[0521] "Terminal" refers to the device used by the user to input questions and receive responses from the system, such as a smartphone or PC.

[0522] "Server" refers to a computing system that is responsible for receiving and analyzing a user's query, and generating and transmitting a response.

[0523] A "natural language processing engine" refers to software that analyzes natural language questions entered by users and extracts keywords and structures.

[0524] An "emotion engine" refers to software that analyzes and recognizes the emotions contained in a user's question.

[0525] A "health knowledge database" refers to a collection of data that systematically records health-related information and is used to generate answers to questions.

[0526] A "preventive measures database" refers to a collection of data containing specific measures for maintaining or improving health, and is used to generate answers to questions.

[0527] A "generative AI model" refers to an artificial intelligence that automatically generates natural language responses to users based on received data. Specifically, this includes deep learning models.

[0528] "Customized responses" refer to answers that are individually tailored based on the user's question and emotions, providing the user with the most relevant health advice and information.

[0529] The present invention provides a system that provides customized responses to health-related questions entered by a user in natural language, taking into account the user's individual circumstances and emotions. Specific embodiments of the system are described below.

[0530] A user accesses the system using a device such as a smartphone or PC. For example, they enter "I've been feeling tired a lot lately. What should I do?" into a text box displayed on a web browser and press the send button. The device then sends this question to the server as an HTTP POST request.

[0531] The server receives the HTTP POST request sent from the device and analyzes the request body to extract the question. This question is then sent to a natural language processing (NLP) engine and an emotion engine. The NLP engine analyzes the question and extracts key keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the emotions contained in the question and recognizes "anxiety" and "fatigue."

[0532] Next, the server searches the health knowledge database and preventive measures database based on the keywords from the NLP engine and the emotion information from the emotion engine. For example, it retrieves health information and preventive measures related to "easily tired," "anxiety," and "fatigue" from the database. The retrieved information is then provided to a generative AI model (e.g., GPT-4).

[0533] The generative AI model generates a customized response based on the information provided, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend making time to relax."

[0534] The generated response is sent from the server to the device as an HTTP response. The device analyzes the received HTTP response and displays the generated response to the user. The user can then review and implement specific, customized health advice and preventive measures.

[0535] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[0536] Examples of prompts:

[0537] If a user types, "I've been feeling tired lately, what should I do?", what response should the system generate? The user's emotions are anxiety and fatigue.

[0538] As described above, by implementing this invention, users can easily obtain specific and useful advice tailored to their health-related situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses can be personalized, providing more beneficial healthcare support.

[0539] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0540] System program processing flow:

[0541] Step 1:

[0542] User inputs and submits a question

[0543] The user uses the terminal to input a health-related question in natural language. For example, the user might input "I've been feeling tired a lot lately. What should I do?" and click the send button.

[0544] Input: A user-entered natural language question.

[0545] Output: HTTP POST request from the terminal to the server.

[0546] Step 2:

[0547] Sending an HTTP request from the device to the server

[0548] The device sends the question entered by the user to the server as an HTTP POST request, which includes the question in JSON format.

[0549] Specific request example:

[0550] POST / api / health_query HTTP / 1.1

[0551] Host: api.example.com

[0552] Content-Type: application / json

[0553] {

[0554] "question": "I've been feeling tired a lot lately. What should I do?"

[0555] }

[0556] Input: The user's question.

[0557] Output: HTTP POST request to the server.

[0558] Step 3:

[0559] The server receives and analyzes the HTTP request

[0560] The server receives the HTTP POST request sent from the device, extracts the question from the request body, and sends it to the natural language processing engine and emotion engine for analysis.

[0561] Input: HTTP POST request.

[0562] Output: The question.

[0563] Step 4:

[0564] Question analysis by NLP engine

[0565] The server sends the question to a natural language processing (NLP) engine, which analyzes the question and extracts keywords, such as "easily tired."

[0566] Input: Question.

[0567] Output: Extracted keywords.

[0568] Step 5:

[0569] Emotion analysis using an emotion engine

[0570] The server sends the question to the emotion engine, which analyzes the user's emotions. For example, "anxiety" or "fatigue" is recognized.

[0571] Input: Question.

[0572] Output: Recognized emotion.

[0573] Step 6:

[0574] Database search by server

[0575] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions to obtain relevant health information and preventive measures. For example, information related to "easily tired," "anxiety," and "fatigue" is obtained.

[0576] Input: Extracted keywords, recognized sentiment.

[0577] Output: Health information and preventive measures.

[0578] Step 7:

[0579] Generating a response

[0580] The server provides the acquired health information and preventive measures to a generative AI model (e.g., GPT-4) to generate a customized response for the user. For example, a response might be generated such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[0581] Enter: health information and precautions.

[0582] Output: The customized response.

[0583] Step 8:

[0584] Sending HTTP responses from the server to the device

[0585] The server sends the generated customization response to the device as an HTTP response. For example, the response is sent in the following format:

[0586] HTTP / 1.1 200 OK

[0587] Content-Type: application / json

[0588] {

[0589] "response": "To recover from fatigue, it is important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Taking care of your mind is also important, so I recommend making time to relax."

[0590] }

[0591] Input: Your customized response.

[0592] Output: HTTP response to the device.

[0593] Step 9:

[0594] Terminal receives and displays response

[0595] The device receives the HTTP response, parses it, extracts the generated response, and displays it to the user, who can then view and implement specific, customized health advice.

[0596] Input: HTTP response.

[0597] Output: The response displayed to the user.

[0598] The above are the specific processing steps of the program for this system. By following this flow, users can easily receive specific and useful advice tailored to their health condition.

[0599] (Application example 2)

[0600] 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."

[0601] In recent years, there has been an increasing demand for health consultations and advice via smart devices. However, conventional systems have difficulty providing customized responses that take the user's emotions into account in real time, resulting in a decline in user satisfaction. Furthermore, there is a demand for efficient information provision using wearable devices such as smart glasses, but the technology to achieve this is still in its infancy. Therefore, a system that analyzes the user's emotions and provides health advice accordingly is needed.

[0602] 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 receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, and means for searching a health knowledge database based on the keywords. This makes it possible to analyze the user's emotions and generate customized responses in real time to display on the smart glasses. This also improves user satisfaction and makes it possible to provide health advice more effectively.

[0603] "Means for receiving questions entered by a user in natural language" refers to the function of recognizing questions entered by a user in natural language such as voice or text and sending them to the system.

[0604] "Means for analyzing received questions and extracting keywords" refers to a function that analyzes received questions using natural language processing technology and extracts important keywords.

[0605] "Means for searching a health knowledge database based on keywords" refers to a function for searching a database for relevant health information using the extracted keywords.

[0606] "Means for searching the database of preventive measures based on keywords" refers to a function that uses the extracted keywords to search the database for relevant preventive measures and advice.

[0607] "Means for analyzing user emotions" refers to a function for recognizing the user's emotions from the received questions and identifying the appropriate emotional state.

[0608] "Means of providing search results and sentiment analysis results to a generative AI model to generate a customized response for the user" refers to the function of using generative AI to create a customized response for the user based on the searched information and the results of sentiment analysis.

[0609] "Means for transmitting the generated response to the user terminal and displaying it on the display of the smart glasses" refers to a function for transmitting the generated response to the user's smart device via the Internet and displaying it on the display of the smart glasses.

[0610] "Natural language processing engine" refers to a software engine that analyzes received natural language text and understands its meaning.

[0611] "Emotion engine" refers to a software engine for recognizing a user's emotional state from text or speech.

[0612] A "generative AI model" refers to an artificial intelligence model that generates appropriate responses based on input data (keywords and sentiment analysis results).

[0613] "Smart glasses" are a wearable eyeglass-type device with a built-in display that allows users to receive visual information in real time.

[0614] The present invention relates to a system that allows users to input health-related questions in natural language and generates and provides responses to those questions, and that can provide real-time health advice using smart glasses.

[0615] Users can input health-related questions by voice through the smart glasses. The voice-input information is converted into text using voice recognition software (e.g., Google Speech-to-Text API) within the smart glasses. The converted text is then sent to a server over the Internet.

[0616] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) to extract keywords from the question, and simultaneously analyzes the user's sentiment using an emotion engine (e.g., Microsoft Azure's Text Analytics API) to obtain the results.

[0617] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the results of emotion analysis. For example, if the keyword "easily tired" is extracted and "fatigue" and "anxiety" are recognized from the emotion analysis results, the server retrieves related health information and preventive measures from the database.

[0618] The server generates a customized response based on the search results and sentiment analysis results using a generative AI model (e.g., GPT-3), which is then sent over the internet to the user's smart glasses and displayed on their screen.

[0619] For example, if a user types, "I've been feeling tired a lot lately. What should I do?", the server will generate a response such as, "A balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so I recommend that you make time to relax," and display this on the smart glasses.

[0620] This invention allows users to receive customized health advice in real time and enjoy individual health support, thereby improving user satisfaction and realizing a system that effectively provides health advice.

[0621] An example of a prompt sentence is as follows:

[0622] "Generate customized health advice based on the following questions and emotions: Question: 'I've been feeling tired lately, what should I do?' Emotion: 'I feel anxious and tired.'"

[0623] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0624] Step 1:

[0625] The user inputs health-related questions by voice through the smart glasses. The voice data is captured by the microphone of the smart glasses. The input data is in voice format, and the final output is a question in text format.

[0626] Step 2:

[0627] The smart glasses' voice recognition software converts the input voice data into text. Specifically, the Google Speech-to-Text API receives the voice data, analyzes its content, and generates corresponding text. The input is voice data, and the output is text data.

[0628] Step 3:

[0629] The terminal sends text data to a server over the Internet. The text data is sent using an HTTP POST request. The input is the text data, and the output is an HTTP request to the server.

[0630] Step 4:

[0631] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) and extracts keywords. Specifically, it tokenizes the text and extracts important keywords. The input is text data, and the output is a list of keywords.

[0632] Step 5:

[0633] The server searches the health knowledge database based on the keywords, and uses SQL queries to retrieve relevant health information from the database. The input is the keywords, and the output is a list of health information.

[0634] Step 6:

[0635] At the same time, the server uses an emotion engine (e.g., Microsoft Azure's Text Analytics API) to analyze the user's emotions. Specifically, it analyzes the text data to detect patterns specific to emotions. The input is the text data, and the output is the emotion analysis results.

[0636] Step 7:

[0637] The server searches the preventive measures database based on the keywords and sentiment analysis results. It uses SQL queries to retrieve relevant information from the preventive measures database. The input is the keywords and sentiment analysis results, and the output is a list of preventive measures.

[0638] Step 8:

[0639] The server generates a customized response using a generative AI model (e.g., GPT-3) based on the search results and sentiment analysis results. A prompt is input to the generative AI model, which outputs a customized text response. The input is the prompt and search results, and the output is a customized response.

[0640] Step 9:

[0641] The server generates a response and sends it to the terminal as an HTTP response. The input is a customized response, and the output is an HTTP response.

[0642] Step 10:

[0643] The terminal parses the received HTTP response and extracts the generated response. The input is the HTTP response and the output is the text response.

[0644] Step 11:

[0645] The terminal displays the acquired text response on the display of the smart glasses. The input is the text response, and the output is the response displayed on the display.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] [Third embodiment]

[0650] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0651] 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.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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."

[0662] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. To explain the present invention, a specific embodiment will be described below.

[0663] Users access this system using devices such as smartphones or PCs. They input a health-related question and press the send button to send the question to the system. For example, a user might input "I've been feeling tired a lot lately. What should I do?" and send it.

[0664] The terminal sends the question entered by the user to the server. Specifically, the terminal sends the user's question data to the server using a protocol such as an HTTP POST request. The server then analyzes the received user's question.

[0665] The server uses a natural language processing (NLP) engine to analyze the received question and extract keywords. For example, from the question "I've been feeling tired a lot lately, what should I do?", it extracts keywords such as "I get tired easily."

[0666] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. Specifically, it searches the database for health information and preventive measures related to the keyword "easily tired."

[0667] Based on the search results, the server uses a generative AI model to generate a customized response for the user, such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0668] The server sends the generated response to the user's terminal. Specifically, it returns the generated response data as an HTTP response to the terminal. The terminal then displays the received response to the user.

[0669] For example, if a user inputs "I've been feeling tired a lot lately. What should I do?", the server will generate a response saying, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective," and send it to the user's device. The device will then display the response to the user.

[0670] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures tailored to their own circumstances. Furthermore, by utilizing a generative AI model, responses to users can be customized, providing more specific and useful information.

[0671] The above is a specific embodiment of the present invention.

[0672] The processing flow will be explained below.

[0673] Step 1:

[0674] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0675] Step 2:

[0676] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0677] Step 3:

[0678] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine.

[0679] Step 4:

[0680] The server analyzes the received question using an NLP engine and extracts keywords, for example, "getting tired easily."

[0681] Step 5:

[0682] The server searches a health knowledge database based on the extracted keywords and retrieves health information related to the keywords from the database.

[0683] Step 6:

[0684] The server searches the preventive measures database using the same keyword, and retrieves preventive measures information related to the keyword from the database.

[0685] Step 7:

[0686] The server integrates the health and prevention information obtained from the search results and provides it to a generative AI model, which then uses this information to generate a customized response.

[0687] Step 8:

[0688] The server then sends the generated response to the device as an HTTP response, which includes specific health advice and preventative measures.

[0689] Step 9:

[0690] The terminal analyzes the HTTP response received from the server, extracts the generated response, and displays the obtained response to the user.

[0691] Step 10:

[0692] Users can check and use customized health advice and preventative measures displayed on their device. For example, advice such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective."

[0693] Example 1

[0694] 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."

[0695] Many users today require fast and accurate access to health-related information. However, the Internet is overflowing with a wide variety of information, making it difficult to efficiently search for reliable information and to instantly obtain customized advice tailored to each user's situation and questions. The present invention aims to solve these problems by providing customized responses to questions entered by users in natural language.

[0696] 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.

[0697] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to the user terminal as an HTTP response, and means for displaying the generated response on the user terminal, thereby enabling users to efficiently obtain reliable health information and preventive measures.

[0698] A "user" is a person who uses the system to input questions in natural language and obtain information.

[0699] "Natural language" refers to words and sentences that humans use on a daily basis, and is not a specialized programming language.

[0700] The "means for receiving a question" refers to a function for receiving a question entered by a user in natural language and passing it to the system.

[0701] "Means for analyzing questions and extracting keywords" refers to a function for extracting key keywords from received questions using a natural language processing engine.

[0702] The "health knowledge database" is a database that organizes and stores health-related information, and allows users to search for information related to relevant keywords.

[0703] A "prevention measures database" is a database that describes methods and measures for preventing health problems.

[0704] A "generative AI model" refers to an artificial intelligence model that generates customized responses to users based on given input data.

[0705] An "HTTP response" refers to data that a server sends in response to an HTTP request from a client (user terminal).

[0706] "User terminal" refers to a device used by a user, such as a smartphone or PC.

[0707] "Means for displaying a response" refers to a function for visually displaying the generated response on the user terminal.

[0708] The present invention is a system that allows a user to input a health-related question in natural language and generates and provides a customized response to the question. Specific embodiments of the present invention are described below.

[0709] Users access the system using devices such as smartphones or PCs. Using a browser or a dedicated application, users input health-related questions in natural language and press the send button. For example, a user might input, "I've been feeling tired a lot lately. What should I do?"

[0710] The device sends the question entered by the user to the server using an HTTP POST request. Specifically, the device generates data containing the question text entered on the device and sends it to the specified API endpoint of the server.

[0711] The server receives the HTTP request, parses its contents, extracts the question text from the request body, and passes it to a backend application server, where a web server such as NGINX or Apache runs, and an application server such as Node.js or Django processes the request.

[0712] The server then uses a natural language processing (NLP) engine to analyze the received question and extract key keywords. For example, to extract the keyword "tired easily" from the question "I've been feeling tired a lot lately, what should I do?", it uses natural language processing tools such as spaCy and Google Cloud Natural Language API.

[0713] The server searches the health knowledge database and preventive measures database based on the extracted keywords. For the search, a database management system (e.g., MySQL or MongoDB) is used to retrieve health information and preventive measures related to "easily tired" through a database query.

[0714] The server uses a generative AI model to generate a response customized for the user based on the search results. As an example of a generative AI model, we use OpenAI GPT-3. For example, we send the following prompt to the generative AI model:

[0715] "If you're feeling tired recently, what measures would be effective?"

[0716] This allows the generative AI model to generate a specific response sentence and return it to the server.

[0717] The server sends the response to the user's device as an HTTP response, along with the appropriate HTTP status code and the generated response text.

[0718] Finally, the device analyzes the received response and displays it in a format that is easy for the user to see. For example, it could display a message on a web page or in an application that reads, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0719] In this way, users can easily obtain specific and relevant health advice and information to answer their questions. The system excels in that it utilizes generative AI models to customize responses to users and provide more useful information.

[0720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] Users access the system using a smartphone or PC. They launch a browser or a dedicated application and input health-related questions in natural language. For example, they might input, "I've been feeling tired a lot lately. What should I do?" The input data is stored in the device's memory.

[0723] Step 2:

[0724] The device sends the entered question to the server as an HTTP POST request. Specifically, the device generates data including the question text and sends it to the server's API endpoint. The input data is the question text to be sent, and the output data is the HTTP request to the server.

[0725] Step 3:

[0726] The server receives the HTTP request and parses its content. A web server (e.g., NGINX or Apache) receives the request, and an application server (e.g., Node.js or Django) extracts the question text from the request body. The input data is the received HTTP request, and the output data is the extracted question text.

[0727] Step 4:

[0728] The server uses a natural language processing (NLP) engine (e.g., spaCy or Google Cloud Natural Language API) to analyze the received question and extract key keywords. For example, the keyword "gets tired easily" is extracted from the question "I've been feeling tired a lot lately. What should I do?" The input data is the question text, and the output data is the extracted keywords.

[0729] Step 5:

[0730] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. It uses a database management system (e.g., MySQL or MongoDB) to retrieve information related to the corresponding keywords. The input data are the extracted keywords, and the output data are the search results.

[0731] Step 6:

[0732] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a personalized response for the user based on the search results. The server sends the following prompt to the generative AI model:

[0733] "If you're feeling tired recently, what measures would be effective?"

[0734] This allows the generative AI model to generate a specific response. The input data are the search results and the prompt, and the output data is the generated response.

[0735] Step 7:

[0736] The server sends the generated response to the user terminal as an HTTP response. The server creates response data and sends it to the terminal along with an appropriate HTTP status code. The input data is the generated response, and the output data is the HTTP response.

[0737] Step 8:

[0738] The terminal analyzes the HTTP response received from the server and displays its contents to the user. Specifically, the browser or application processes the response data and displays it on the screen in a form that the user can see. For example, a message such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective." is displayed. The input data is the received HTTP response, and the output data is the response message that is displayed.

[0739] (Application example 1)

[0740] 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."

[0741] Conventional health information systems lack the convenience of providing responses to user questions when the user is in a vehicle or using an autonomous vehicle. For example, when a passenger needs health advice while driving long distances, there are limited means to provide prompt and appropriate information. In such environments, providing prompt, appropriate, and customized responses to users is required, but this has been difficult with conventional systems.

[0742] 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.

[0743] In this invention, the server includes means for receiving a question input in natural language by a user, means for analyzing the received question to extract keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model to generate a customized response for the user, means for transmitting the generated response to a user terminal, and means for displaying the response on a display device used in the autonomous vehicle, thereby enabling passengers to instantly receive prompt and appropriate advice regarding their health condition while in the autonomous vehicle.

[0744] A "user" is an individual who utilizes the system to enter a question.

[0745] "Natural language" is a form of language expressed in words used by people in everyday life.

[0746] A "question" is a statement that a user enters into the system to request information or advice.

[0747] A "means" is a method or device designed to accomplish a particular purpose.

[0748] "Analysis" is the process of interpreting the input question and extracting the necessary information.

[0749] "Keywords" are words or phrases extracted from a question as important elements.

[0750] A "health knowledge database" is a database that compiles information and knowledge about health.

[0751] The "Preventive Measures Database" is a database that compiles information on preventive measures for health problems.

[0752] "Searching" is the process of finding information related to specific keywords within a database.

[0753] A "generative AI model" is a program that uses machine learning techniques to generate customized responses to users.

[0754] A "customized response" is a response that is individually generated in response to a user's specific question.

[0755] A "user terminal" is an electronic device that a user uses to enter questions and receive responses.

[0756] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without a driver.

[0757] A "display device" is a device for visually presenting the generated response to a user.

[0758] This invention is a system that processes questions entered by a user in natural language and provides customized health advice. This system is intended for use in autonomous vehicles and can use a display device such as smart glasses.

[0759] The server receives questions entered by the user in natural language. For example, if a user wears smart glasses and asks a question by voice, such as "I get tired easily when I sit for a long time. Is there anything I can do?", the voice recognition API of the smart glasses converts this into text and sends it to the server.

[0760] The server analyzes the received question using a natural language processing engine (such as Google Cloud NLP or spaCy) to extract keywords, such as "sitting for long periods of time" and "getting tired easily."

[0761] The server then searches the health knowledge database and the preventive measures database based on the extracted keywords, thereby obtaining relevant health information and preventive measures.

[0762] The server then provides the search results to a generative AI model (e.g., OpenAI's GPT-3) to generate a customized response for the user, such as "It's important to stretch regularly. Also, getting out of the car and taking breaks regularly can help reduce fatigue."

[0763] The generated response is sent as an HTTP response to the user's smart glasses, which then visually display the received response on their display, allowing the user to receive prompt and appropriate health advice within the autonomous vehicle.

[0764] For example, if a passenger on a long-distance drive asks, "I get tired when I sit for long periods of time. What should I do?", the following prompt sentence is input to the generative AI model:

[0765] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[0766] response:

[0767] Based on this prompt, the generative AI model generates an appropriate response and displays it on the passenger's smart glasses, providing specific advice such as, "It's important to stretch regularly. Staying hydrated and ventilating the car can also help reduce fatigue."

[0768] In this way, the present invention allows passengers to easily manage their health in autonomous vehicles through smart glasses.

[0769] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0770] Step 1:

[0771] The user inputs a question by voice through the smart glasses. For example, "I get tired easily when I sit for a long time. Is there anything I can do about it?" The input voice data is picked up by the microphone in the smart glasses.

[0772] Step 2:

[0773] The device (smart glasses) converts the acquired voice data into text data using a speech recognition API (e.g., Google Speech-to-Text API). The converted text data is generated.

[0774] Step 3:

[0775] The terminal sends the converted text data to the server using an HTTP POST request, and the sent data is received by the server.

[0776] Step 4:

[0777] The server analyzes the text data of the received question using a natural language processing engine (e.g., Google Cloud NLP, spaCy) and extracts keywords, such as "sitting for long periods of time" and "getting tired easily."

[0778] Step 5:

[0779] The server searches the health knowledge database and the preventive measures database based on the extracted keywords, and retrieves relevant information that matches the keywords.

[0780] Step 6:

[0781] The server inputs the search results into a generative AI model (e.g., OpenAI's GPT-3). For example, the following prompt is generated along with the search results:

[0782] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[0783] response:

[0784] The generative AI model uses this prompt to generate a customized response.

[0785] Step 7:

[0786] The server sends the generated response to the user's device (smart glasses) as an HTTP response. The sent response data is received by the device.

[0787] Step 8:

[0788] The device visually displays the received response data on the smart glasses display, providing advice to the user, such as, "It is important to stretch regularly. Also, staying hydrated and ventilating the car interior can help reduce fatigue."

[0789] 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.

[0790] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. By further combining the present invention with an emotion engine, the system can recognize the user's emotion and provide a customized response according to the emotion. Specific embodiments of the present invention are described below.

[0791] Users access this system using devices such as smartphones or PCs. The user inputs a health-related question and sends it to the system by pressing the send button. For example, consider the case where a user inputs and sends "I've been feeling tired a lot lately. What should I do?"

[0792] The device sends the question entered by the user to the server as an HTTP POST request. Specifically, the destination is the system's API endpoint. The server analyzes the HTTP request received from the device and extracts the question. The received question is then sent to a natural language processing (NLP) engine and an emotion engine.

[0793] The server uses an NLP engine to analyze the question and extract keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the user's emotions and obtains the results. For example, if the user enters the question "gets tired easily," emotions such as anxiety and fatigue are recognized.

[0794] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions. Specifically, it retrieves health information and preventive measures related to keywords such as "easily tired" and emotions such as anxiety and fatigue from the database.

[0795] The server uses a generative AI model to generate a customized response based on the search results. For example, it takes into account the user's emotions recognized by the emotion engine and generates a response such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[0796] The server sends the generated response to the terminal as an HTTP response. The terminal analyzes the HTTP response received from the server and extracts the generated response. The terminal displays the obtained response to the user. The user can check and practice the customized health advice and preventive measures displayed on the terminal.

[0797] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[0798] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures according to their own situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses to users become more specific and useful, enabling the provision of personalized healthcare support.

[0799] The above is a specific embodiment of the present invention.

[0800] The processing flow will be explained below.

[0801] Step 1:

[0802] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0803] Step 2:

[0804] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0805] Step 3:

[0806] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine and an emotion engine.

[0807] Step 4:

[0808] The server uses an NLP engine to analyze the question and extract keywords. For example, the server extracts the keyword "tired easily" from the question "I've been feeling tired a lot lately. What should I do?"

[0809] Step 5:

[0810] The server uses an emotion engine to recognize the emotion contained in the user's question. For example, it can recognize that the user is feeling tired or anxious based on keywords and context in the question.

[0811] Step 6:

[0812] The server searches a health knowledge database based on the extracted keywords and the recognized emotions. For example, based on the keywords "easily tired" and "anxiety," it retrieves related health information.

[0813] Step 7:

[0814] The server searches the preventive measures database using the same keywords and emotions, for example, to retrieve preventive measures related to fatigue recovery and mental stress reduction.

[0815] Step 8:

[0816] The server uses a generative AI model based on the acquired health and preventive measures information to generate a customized response, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. If you feel anxious, try relaxation techniques."

[0817] Step 9:

[0818] The server sends the generated response to the terminal as an HTTP response. Specifically, the server includes the generated response text in the HTTP response body and returns it to the terminal.

[0819] Step 10:

[0820] The terminal analyzes the HTTP response received from the server and extracts the generated response. Specifically, it obtains text data from the response body and displays it to the user.

[0821] Step 11:

[0822] Users can review and implement customized health advice and preventative measures displayed on their device, such as following suggested dietary changes and trying relaxation techniques.

[0823] The above is the flow of processing in a specific embodiment of the present invention.

[0824] Example 2

[0825] 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."

[0826] Conventional health information systems typically respond to users' questions in natural language and are often not customized to reflect the individual user's situation or emotions. This makes it difficult for users to obtain specific and useful advice. Furthermore, while taking the user's emotions into account would enable more appropriate and effective responses, conventional technologies lack such functionality.

[0827] 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.

[0828] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to a user terminal, means including an emotion engine for analyzing the user's emotions, and means for generating a customized response based on the emotions recognized by the emotion engine. This makes it possible to provide specific and useful advice in response to a user's health-related question, taking into account the user's individual situation and emotions.

[0829] "User" refers to a person who enters a health-related question into the system in natural language and intends to receive a response.

[0830] A "question" refers to a sentence in which a user expresses a question or concern about health in natural language, and this sentence is the subject of transmission to the system.

[0831] "Terminal" refers to the device used by the user to input questions and receive responses from the system, such as a smartphone or PC.

[0832] "Server" refers to a computing system that is responsible for receiving and analyzing a user's query, and generating and transmitting a response.

[0833] A "natural language processing engine" refers to software that analyzes natural language questions entered by users and extracts keywords and structures.

[0834] An "emotion engine" refers to software that analyzes and recognizes the emotions contained in a user's question.

[0835] A "health knowledge database" refers to a collection of data that systematically records health-related information and is used to generate answers to questions.

[0836] A "preventive measures database" refers to a collection of data containing specific measures for maintaining or improving health, and is used to generate answers to questions.

[0837] A "generative AI model" refers to an artificial intelligence that automatically generates natural language responses to users based on received data. Specifically, this includes deep learning models.

[0838] "Customized responses" refer to answers that are individually tailored based on the user's question and emotions, providing the user with the most relevant health advice and information.

[0839] The present invention provides a system that provides customized responses to health-related questions entered by a user in natural language, taking into account the user's individual circumstances and emotions. Specific embodiments of the system are described below.

[0840] A user accesses the system using a device such as a smartphone or PC. For example, they enter "I've been feeling tired a lot lately. What should I do?" into a text box displayed on a web browser and press the send button. The device then sends this question to the server as an HTTP POST request.

[0841] The server receives the HTTP POST request sent from the device and analyzes the request body to extract the question. This question is then sent to a natural language processing (NLP) engine and an emotion engine. The NLP engine analyzes the question and extracts key keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the emotions contained in the question and recognizes "anxiety" and "fatigue."

[0842] Next, the server searches the health knowledge database and preventive measures database based on the keywords from the NLP engine and the emotion information from the emotion engine. For example, it retrieves health information and preventive measures related to "easily tired," "anxiety," and "fatigue" from the database. The retrieved information is then provided to a generative AI model (e.g., GPT-4).

[0843] The generative AI model generates a customized response based on the information provided, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend making time to relax."

[0844] The generated response is sent from the server to the device as an HTTP response. The device analyzes the received HTTP response and displays the generated response to the user. The user can then review and implement specific, customized health advice and preventive measures.

[0845] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[0846] Examples of prompts:

[0847] If a user types, "I've been feeling tired lately, what should I do?", what response should the system generate? The user's emotions are anxiety and fatigue.

[0848] As described above, by implementing this invention, users can easily obtain specific and useful advice tailored to their health-related situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses can be personalized, providing more beneficial healthcare support.

[0849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0850] System program processing flow:

[0851] Step 1:

[0852] User inputs and submits a question

[0853] The user uses the terminal to input a health-related question in natural language. For example, the user might input "I've been feeling tired a lot lately. What should I do?" and click the send button.

[0854] Input: A user-entered natural language question.

[0855] Output: HTTP POST request from the terminal to the server.

[0856] Step 2:

[0857] Sending an HTTP request from the device to the server

[0858] The device sends the question entered by the user to the server as an HTTP POST request, which includes the question in JSON format.

[0859] Specific request example:

[0860] POST / api / health_query HTTP / 1.1

[0861] Host: api.example.com

[0862] Content-Type: application / json

[0863] {

[0864] "question": "I've been feeling tired a lot lately. What should I do?"

[0865] }

[0866] Input: The user's question.

[0867] Output: HTTP POST request to the server.

[0868] Step 3:

[0869] The server receives and analyzes the HTTP request

[0870] The server receives the HTTP POST request sent from the device, extracts the question from the request body, and sends it to the natural language processing engine and emotion engine for analysis.

[0871] Input: HTTP POST request.

[0872] Output: The question.

[0873] Step 4:

[0874] Question analysis by NLP engine

[0875] The server sends the question to a natural language processing (NLP) engine, which analyzes the question and extracts keywords, such as "easily tired."

[0876] Input: Question.

[0877] Output: Extracted keywords.

[0878] Step 5:

[0879] Emotion analysis using an emotion engine

[0880] The server sends the question to the emotion engine, which analyzes the user's emotions. For example, "anxiety" or "fatigue" is recognized.

[0881] Input: Question.

[0882] Output: Recognized emotion.

[0883] Step 6:

[0884] Database search by server

[0885] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions to obtain relevant health information and preventive measures. For example, information related to "easily tired," "anxiety," and "fatigue" is obtained.

[0886] Input: Extracted keywords, recognized sentiment.

[0887] Output: Health information and preventive measures.

[0888] Step 7:

[0889] Generating a response

[0890] The server provides the acquired health information and preventive measures to a generative AI model (e.g., GPT-4) to generate a customized response for the user. For example, a response might be generated such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[0891] Enter: health information and precautions.

[0892] Output: The customized response.

[0893] Step 8:

[0894] Sending HTTP responses from the server to the device

[0895] The server sends the generated customization response to the device as an HTTP response. For example, the response is sent in the following format:

[0896] HTTP / 1.1 200 OK

[0897] Content-Type: application / json

[0898] {

[0899] "response": "To recover from fatigue, it is important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Taking care of your mind is also important, so I recommend making time to relax."

[0900] }

[0901] Input: Your customized response.

[0902] Output: HTTP response to the device.

[0903] Step 9:

[0904] Terminal receives and displays response

[0905] The device receives the HTTP response, parses it, extracts the generated response, and displays it to the user, who can then view and implement specific, customized health advice.

[0906] Input: HTTP response.

[0907] Output: The response displayed to the user.

[0908] The above are the specific processing steps of the program for this system. By following this flow, users can easily receive specific and useful advice tailored to their health condition.

[0909] (Application example 2)

[0910] 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."

[0911] In recent years, there has been an increasing demand for health consultations and advice via smart devices. However, conventional systems have difficulty providing customized responses that take the user's emotions into account in real time, resulting in a decline in user satisfaction. Furthermore, there is a demand for efficient information provision using wearable devices such as smart glasses, but the technology to achieve this is still in its infancy. Therefore, a system that analyzes the user's emotions and provides health advice accordingly is needed.

[0912] 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 receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, and means for searching a health knowledge database based on the keywords. This makes it possible to analyze the user's emotions and generate customized responses in real time to display on the smart glasses. This also improves user satisfaction and makes it possible to provide health advice more effectively.

[0913] "Means for receiving questions entered by a user in natural language" refers to the function of recognizing questions entered by a user in natural language such as voice or text and sending them to the system.

[0914] "Means for analyzing received questions and extracting keywords" refers to a function that analyzes received questions using natural language processing technology and extracts important keywords.

[0915] "Means for searching a health knowledge database based on keywords" refers to a function for searching a database for relevant health information using the extracted keywords.

[0916] "Means for searching the database of preventive measures based on keywords" refers to a function that uses the extracted keywords to search the database for relevant preventive measures and advice.

[0917] "Means for analyzing user emotions" refers to a function for recognizing the user's emotions from the received questions and identifying the appropriate emotional state.

[0918] "Means of providing search results and sentiment analysis results to a generative AI model to generate a customized response for the user" refers to the function of using generative AI to create a customized response for the user based on the searched information and the results of sentiment analysis.

[0919] "Means for transmitting the generated response to the user terminal and displaying it on the display of the smart glasses" refers to a function for transmitting the generated response to the user's smart device via the Internet and displaying it on the display of the smart glasses.

[0920] "Natural language processing engine" refers to a software engine that analyzes received natural language text and understands its meaning.

[0921] "Emotion engine" refers to a software engine for recognizing a user's emotional state from text or speech.

[0922] A "generative AI model" refers to an artificial intelligence model that generates appropriate responses based on input data (keywords and sentiment analysis results).

[0923] "Smart glasses" are a wearable eyeglass-type device with a built-in display that allows users to receive visual information in real time.

[0924] The present invention relates to a system that allows users to input health-related questions in natural language and generates and provides responses to those questions, and that can provide real-time health advice using smart glasses.

[0925] Users can input health-related questions by voice through the smart glasses. The voice-input information is converted into text using voice recognition software (e.g., Google Speech-to-Text API) within the smart glasses. The converted text is then sent to a server over the Internet.

[0926] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) to extract keywords from the question, and simultaneously analyzes the user's sentiment using an emotion engine (e.g., Microsoft Azure's Text Analytics API) to obtain the results.

[0927] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the results of emotion analysis. For example, if the keyword "easily tired" is extracted and "fatigue" and "anxiety" are recognized from the emotion analysis results, the server retrieves related health information and preventive measures from the database.

[0928] The server generates a customized response based on the search results and sentiment analysis results using a generative AI model (e.g., GPT-3), which is then sent over the internet to the user's smart glasses and displayed on their screen.

[0929] For example, if a user types, "I've been feeling tired a lot lately. What should I do?", the server will generate a response such as, "A balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so I recommend that you make time to relax," and display this on the smart glasses.

[0930] This invention allows users to receive customized health advice in real time and enjoy individual health support, thereby improving user satisfaction and realizing a system that effectively provides health advice.

[0931] An example of a prompt sentence is as follows:

[0932] "Generate customized health advice based on the following questions and emotions: Question: 'I've been feeling tired lately, what should I do?' Emotion: 'I feel anxious and tired.'"

[0933] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0934] Step 1:

[0935] The user inputs health-related questions by voice through the smart glasses. The voice data is captured by the microphone of the smart glasses. The input data is in voice format, and the final output is a question in text format.

[0936] Step 2:

[0937] The smart glasses' voice recognition software converts the input voice data into text. Specifically, the Google Speech-to-Text API receives the voice data, analyzes its content, and generates corresponding text. The input is voice data, and the output is text data.

[0938] Step 3:

[0939] The terminal sends text data to a server over the Internet. The text data is sent using an HTTP POST request. The input is the text data, and the output is an HTTP request to the server.

[0940] Step 4:

[0941] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) and extracts keywords. Specifically, it tokenizes the text and extracts important keywords. The input is text data, and the output is a list of keywords.

[0942] Step 5:

[0943] The server searches the health knowledge database based on the keywords, and uses SQL queries to retrieve relevant health information from the database. The input is the keywords, and the output is a list of health information.

[0944] Step 6:

[0945] At the same time, the server uses an emotion engine (e.g., Microsoft Azure's Text Analytics API) to analyze the user's emotions. Specifically, it analyzes the text data to detect patterns specific to emotions. The input is the text data, and the output is the emotion analysis results.

[0946] Step 7:

[0947] The server searches the preventive measures database based on the keywords and sentiment analysis results. It uses SQL queries to retrieve relevant information from the preventive measures database. The input is the keywords and sentiment analysis results, and the output is a list of preventive measures.

[0948] Step 8:

[0949] The server generates a customized response using a generative AI model (e.g., GPT-3) based on the search results and sentiment analysis results. A prompt is input to the generative AI model, which outputs a customized text response. The input is the prompt and search results, and the output is a customized response.

[0950] Step 9:

[0951] The server generates a response and sends it to the terminal as an HTTP response. The input is a customized response, and the output is an HTTP response.

[0952] Step 10:

[0953] The terminal parses the received HTTP response and extracts the generated response. The input is the HTTP response and the output is the text response.

[0954] Step 11:

[0955] The terminal displays the acquired text response on the display of the smart glasses. The input is the text response, and the output is the response displayed on the display.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Fourth embodiment]

[0960] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] 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.

[0967] 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.

[0968] 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.

[0969] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0970] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0971] In the 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.

[0972] 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."

[0973] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. To explain the present invention, a specific embodiment will be described below.

[0974] Users access this system using devices such as smartphones or PCs. They input a health-related question and press the send button to send the question to the system. For example, a user might input "I've been feeling tired a lot lately. What should I do?" and send it.

[0975] The terminal sends the question entered by the user to the server. Specifically, the terminal sends the user's question data to the server using a protocol such as an HTTP POST request. The server then analyzes the received user's question.

[0976] The server uses a natural language processing (NLP) engine to analyze the received question and extract keywords. For example, from the question "I've been feeling tired a lot lately, what should I do?", it extracts keywords such as "I get tired easily."

[0977] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. Specifically, it searches the database for health information and preventive measures related to the keyword "easily tired."

[0978] Based on the search results, the server uses a generative AI model to generate a customized response for the user, such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[0979] The server sends the generated response to the user's terminal. Specifically, it returns the generated response data as an HTTP response to the terminal. The terminal then displays the received response to the user.

[0980] For example, if a user inputs "I've been feeling tired a lot lately. What should I do?", the server will generate a response saying, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective," and send it to the user's device. The device will then display the response to the user.

[0981] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures tailored to their own circumstances. Furthermore, by utilizing a generative AI model, responses to users can be customized, providing more specific and useful information.

[0982] The above is a specific embodiment of the present invention.

[0983] The processing flow will be explained below.

[0984] Step 1:

[0985] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[0986] Step 2:

[0987] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[0988] Step 3:

[0989] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine.

[0990] Step 4:

[0991] The server analyzes the received question using an NLP engine and extracts keywords, for example, "getting tired easily."

[0992] Step 5:

[0993] The server searches a health knowledge database based on the extracted keywords and retrieves health information related to the keywords from the database.

[0994] Step 6:

[0995] The server searches the preventive measures database using the same keyword, and retrieves preventive measures information related to the keyword from the database.

[0996] Step 7:

[0997] The server integrates the health and prevention information obtained from the search results and provides it to a generative AI model, which then uses this information to generate a customized response.

[0998] Step 8:

[0999] The server then sends the generated response to the device as an HTTP response, which includes specific health advice and preventative measures.

[1000] Step 9:

[1001] The terminal analyzes the HTTP response received from the server, extracts the generated response, and displays the obtained response to the user.

[1002] Step 10:

[1003] Users can check and use customized health advice and preventative measures displayed on their device. For example, advice such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective."

[1004] Example 1

[1005] 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."

[1006] Many users today require fast and accurate access to health-related information. However, the Internet is overflowing with a wide variety of information, making it difficult to efficiently search for reliable information and to instantly obtain customized advice tailored to each user's situation and questions. The present invention aims to solve these problems by providing customized responses to questions entered by users in natural language.

[1007] 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.

[1008] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to the user terminal as an HTTP response, and means for displaying the generated response on the user terminal, thereby enabling users to efficiently obtain reliable health information and preventive measures.

[1009] A "user" is a person who uses the system to input questions in natural language and obtain information.

[1010] "Natural language" refers to words and sentences that humans use on a daily basis, and is not a specialized programming language.

[1011] The "means for receiving a question" refers to a function for receiving a question entered by a user in natural language and passing it to the system.

[1012] "Means for analyzing questions and extracting keywords" refers to a function for extracting key keywords from received questions using a natural language processing engine.

[1013] The "health knowledge database" is a database that organizes and stores health-related information, and allows users to search for information related to relevant keywords.

[1014] A "prevention measures database" is a database that describes methods and measures for preventing health problems.

[1015] A "generative AI model" refers to an artificial intelligence model that generates customized responses to users based on given input data.

[1016] An "HTTP response" refers to data that a server sends in response to an HTTP request from a client (user terminal).

[1017] "User terminal" refers to a device used by a user, such as a smartphone or PC.

[1018] "Means for displaying a response" refers to a function for visually displaying the generated response on the user terminal.

[1019] The present invention is a system that allows a user to input a health-related question in natural language and generates and provides a customized response to the question. Specific embodiments of the present invention are described below.

[1020] Users access the system using devices such as smartphones or PCs. Using a browser or a dedicated application, users input health-related questions in natural language and press the send button. For example, a user might input, "I've been feeling tired a lot lately. What should I do?"

[1021] The device sends the question entered by the user to the server using an HTTP POST request. Specifically, the device generates data containing the question text entered on the device and sends it to the specified API endpoint of the server.

[1022] The server receives the HTTP request, parses its contents, extracts the question text from the request body, and passes it to a backend application server, where a web server such as NGINX or Apache runs, and an application server such as Node.js or Django processes the request.

[1023] The server then uses a natural language processing (NLP) engine to analyze the received question and extract key keywords. For example, to extract the keyword "tired easily" from the question "I've been feeling tired a lot lately, what should I do?", it uses natural language processing tools such as spaCy and Google Cloud Natural Language API.

[1024] The server searches the health knowledge database and preventive measures database based on the extracted keywords. For the search, a database management system (e.g., MySQL or MongoDB) is used to retrieve health information and preventive measures related to "easily tired" through a database query.

[1025] The server uses a generative AI model to generate a response customized for the user based on the search results. As an example of a generative AI model, we use OpenAI GPT-3. For example, we send the following prompt to the generative AI model:

[1026] "If you're feeling tired recently, what measures would be effective?"

[1027] This allows the generative AI model to generate a specific response sentence and return it to the server.

[1028] The server sends the response to the user's device as an HTTP response, along with the appropriate HTTP status code and the generated response text.

[1029] Finally, the device analyzes the received response and displays it in a format that is easy for the user to see. For example, it could display a message on a web page or in an application that reads, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective."

[1030] In this way, users can easily obtain specific and relevant health advice and information to answer their questions. The system excels in that it utilizes generative AI models to customize responses to users and provide more useful information.

[1031] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1032] Step 1:

[1033] Users access the system using a smartphone or PC. They launch a browser or a dedicated application and input health-related questions in natural language. For example, they might input, "I've been feeling tired a lot lately. What should I do?" The input data is stored in the device's memory.

[1034] Step 2:

[1035] The device sends the entered question to the server as an HTTP POST request. Specifically, the device generates data including the question text and sends it to the server's API endpoint. The input data is the question text to be sent, and the output data is the HTTP request to the server.

[1036] Step 3:

[1037] The server receives the HTTP request and parses its content. A web server (e.g., NGINX or Apache) receives the request, and an application server (e.g., Node.js or Django) extracts the question text from the request body. The input data is the received HTTP request, and the output data is the extracted question text.

[1038] Step 4:

[1039] The server uses a natural language processing (NLP) engine (e.g., spaCy or Google Cloud Natural Language API) to analyze the received question and extract key keywords. For example, the keyword "gets tired easily" is extracted from the question "I've been feeling tired a lot lately. What should I do?" The input data is the question text, and the output data is the extracted keywords.

[1040] Step 5:

[1041] The server searches the health knowledge database and the preventive measures database based on the extracted keywords. It uses a database management system (e.g., MySQL or MongoDB) to retrieve information related to the corresponding keywords. The input data are the extracted keywords, and the output data are the search results.

[1042] Step 6:

[1043] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a personalized response for the user based on the search results. The server sends the following prompt to the generative AI model:

[1044] "If you're feeling tired recently, what measures would be effective?"

[1045] This allows the generative AI model to generate a specific response. The input data are the search results and the prompt, and the output data is the generated response.

[1046] Step 7:

[1047] The server sends the generated response to the user terminal as an HTTP response. The server creates response data and sends it to the terminal along with an appropriate HTTP status code. The input data is the generated response, and the output data is the HTTP response.

[1048] Step 8:

[1049] The terminal analyzes the HTTP response received from the server and displays its contents to the user. Specifically, the browser or application processes the response data and displays it on the screen in a form that the user can see. For example, a message such as "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective." is displayed. The input data is the received HTTP response, and the output data is the response message that is displayed.

[1050] (Application example 1)

[1051] 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."

[1052] Conventional health information systems lack the convenience of providing responses to user questions when the user is in a vehicle or using an autonomous vehicle. For example, when a passenger needs health advice while driving long distances, there are limited means to provide prompt and appropriate information. In such environments, providing prompt, appropriate, and customized responses to users is required, but this has been difficult with conventional systems.

[1053] 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.

[1054] In this invention, the server includes means for receiving a question input in natural language by a user, means for analyzing the received question to extract keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model to generate a customized response for the user, means for transmitting the generated response to a user terminal, and means for displaying the response on a display device used in the autonomous vehicle, thereby enabling passengers to instantly receive prompt and appropriate advice regarding their health condition while in the autonomous vehicle.

[1055] A "user" is an individual who utilizes the system to enter a question.

[1056] "Natural language" is a form of language expressed in words used by people in everyday life.

[1057] A "question" is a statement that a user enters into the system to request information or advice.

[1058] A "means" is a method or device designed to accomplish a particular purpose.

[1059] "Analysis" is the process of interpreting the input question and extracting the necessary information.

[1060] "Keywords" are words or phrases extracted from a question as important elements.

[1061] A "health knowledge database" is a database that compiles information and knowledge about health.

[1062] The "Preventive Measures Database" is a database that compiles information on preventive measures for health problems.

[1063] "Searching" is the process of finding information related to specific keywords within a database.

[1064] A "generative AI model" is a program that uses machine learning techniques to generate customized responses to users.

[1065] A "customized response" is a response that is individually generated in response to a user's specific question.

[1066] A "user terminal" is an electronic device that a user uses to enter questions and receive responses.

[1067] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without a driver.

[1068] A "display device" is a device for visually presenting the generated response to a user.

[1069] This invention is a system that processes questions entered by a user in natural language and provides customized health advice. This system is intended for use in autonomous vehicles and can use a display device such as smart glasses.

[1070] The server receives questions entered by the user in natural language. For example, if a user wears smart glasses and asks a question by voice, such as "I get tired easily when I sit for a long time. Is there anything I can do?", the voice recognition API of the smart glasses converts this into text and sends it to the server.

[1071] The server analyzes the received question using a natural language processing engine (such as Google Cloud NLP or spaCy) to extract keywords, such as "sitting for long periods of time" and "getting tired easily."

[1072] The server then searches the health knowledge database and the preventive measures database based on the extracted keywords, thereby obtaining relevant health information and preventive measures.

[1073] The server then provides the search results to a generative AI model (e.g., OpenAI's GPT-3) to generate a customized response for the user, such as "It's important to stretch regularly. Also, getting out of the car and taking breaks regularly can help reduce fatigue."

[1074] The generated response is sent as an HTTP response to the user's smart glasses, which then visually display the received response on their display, allowing the user to receive prompt and appropriate health advice within the autonomous vehicle.

[1075] For example, if a passenger on a long-distance drive asks, "I get tired when I sit for long periods of time. What should I do?", the following prompt sentence is input to the generative AI model:

[1076] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[1077] response:

[1078] Based on this prompt, the generative AI model generates an appropriate response and displays it on the passenger's smart glasses, providing specific advice such as, "It's important to stretch regularly. Staying hydrated and ventilating the car can also help reduce fatigue."

[1079] In this way, the present invention allows passengers to easily manage their health in autonomous vehicles through smart glasses.

[1080] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1081] Step 1:

[1082] The user inputs a question by voice through the smart glasses. For example, "I get tired easily when I sit for a long time. Is there anything I can do about it?" The input voice data is picked up by the microphone in the smart glasses.

[1083] Step 2:

[1084] The device (smart glasses) converts the acquired voice data into text data using a speech recognition API (e.g., Google Speech-to-Text API). The converted text data is generated.

[1085] Step 3:

[1086] The terminal sends the converted text data to the server using an HTTP POST request, and the sent data is received by the server.

[1087] Step 4:

[1088] The server analyzes the text data of the received question using a natural language processing engine (e.g., Google Cloud NLP, spaCy) and extracts keywords, such as "sitting for long periods of time" and "getting tired easily."

[1089] Step 5:

[1090] The server searches the health knowledge database and the preventive measures database based on the extracted keywords, and retrieves relevant information that matches the keywords.

[1091] Step 6:

[1092] The server inputs the search results into a generative AI model (e.g., OpenAI's GPT-3). For example, the following prompt is generated along with the search results:

[1093] User Question: I get tired easily when I sit for a long time. Is there anything I can do about it?

[1094] response:

[1095] The generative AI model uses this prompt to generate a customized response.

[1096] Step 7:

[1097] The server sends the generated response to the user's device (smart glasses) as an HTTP response. The sent response data is received by the device.

[1098] Step 8:

[1099] The device visually displays the received response data on the smart glasses display, providing advice to the user, such as, "It is important to stretch regularly. Also, staying hydrated and ventilating the car interior can help reduce fatigue."

[1100] 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.

[1101] The present invention relates to a system that allows a user to input a health-related question in natural language and generates and provides a response to the question. By further combining the present invention with an emotion engine, the system can recognize the user's emotion and provide a customized response according to the emotion. Specific embodiments of the present invention are described below.

[1102] Users access this system using devices such as smartphones or PCs. The user inputs a health-related question and sends it to the system by pressing the send button. For example, consider the case where a user inputs and sends "I've been feeling tired a lot lately. What should I do?"

[1103] The device sends the question entered by the user to the server as an HTTP POST request. Specifically, the destination is the system's API endpoint. The server analyzes the HTTP request received from the device and extracts the question. The received question is then sent to a natural language processing (NLP) engine and an emotion engine.

[1104] The server uses an NLP engine to analyze the question and extract keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the user's emotions and obtains the results. For example, if the user enters the question "gets tired easily," emotions such as anxiety and fatigue are recognized.

[1105] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions. Specifically, it retrieves health information and preventive measures related to keywords such as "easily tired" and emotions such as anxiety and fatigue from the database.

[1106] The server uses a generative AI model to generate a customized response based on the search results. For example, it takes into account the user's emotions recognized by the emotion engine and generates a response such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[1107] The server sends the generated response to the terminal as an HTTP response. The terminal analyzes the HTTP response received from the server and extracts the generated response. The terminal displays the obtained response to the user. The user can check and practice the customized health advice and preventive measures displayed on the terminal.

[1108] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[1109] This invention has the effect of enabling users to easily obtain appropriate health information and preventative measures according to their own situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses to users become more specific and useful, enabling the provision of personalized healthcare support.

[1110] The above is a specific embodiment of the present invention.

[1111] The processing flow will be explained below.

[1112] Step 1:

[1113] The user inputs a health-related question into the device in natural language and presses the send button. For example, the user inputs a question such as, "I've been feeling tired a lot lately. What should I do?"

[1114] Step 2:

[1115] The device sends the question entered by the user to the server as an HTTP POST request, specifically to the system's API endpoint.

[1116] Step 3:

[1117] The server analyzes the HTTP request received from the device and extracts the question, which is then sent to a natural language processing (NLP) engine and an emotion engine.

[1118] Step 4:

[1119] The server uses an NLP engine to analyze the question and extract keywords. For example, the server extracts the keyword "tired easily" from the question "I've been feeling tired a lot lately. What should I do?"

[1120] Step 5:

[1121] The server uses an emotion engine to recognize the emotion contained in the user's question. For example, it can recognize that the user is feeling tired or anxious based on keywords and context in the question.

[1122] Step 6:

[1123] The server searches a health knowledge database based on the extracted keywords and the recognized emotions. For example, based on the keywords "easily tired" and "anxiety," it retrieves related health information.

[1124] Step 7:

[1125] The server searches the preventive measures database using the same keywords and emotions, for example, to retrieve preventive measures related to fatigue recovery and mental stress reduction.

[1126] Step 8:

[1127] The server uses a generative AI model based on the acquired health and preventive measures information to generate a customized response, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. If you feel anxious, try relaxation techniques."

[1128] Step 9:

[1129] The server sends the generated response to the terminal as an HTTP response. Specifically, the server includes the generated response text in the HTTP response body and returns it to the terminal.

[1130] Step 10:

[1131] The terminal analyzes the HTTP response received from the server and extracts the generated response. Specifically, it obtains text data from the response body and displays it to the user.

[1132] Step 11:

[1133] Users can review and implement customized health advice and preventative measures displayed on their device, such as following suggested dietary changes and trying relaxation techniques.

[1134] The above is the flow of processing in a specific embodiment of the present invention.

[1135] Example 2

[1136] 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."

[1137] Conventional health information systems typically respond to users' questions in natural language and are often not customized to reflect the individual user's situation or emotions. This makes it difficult for users to obtain specific and useful advice. Furthermore, while taking the user's emotions into account would enable more appropriate and effective responses, conventional technologies lack such functionality.

[1138] 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.

[1139] In this invention, the server includes means for receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, means for searching a health knowledge database based on the keywords, means for searching a preventive measures database based on the keywords, means for providing the search results to a generative AI model and generating a customized response for the user, means for transmitting the generated response to a user terminal, means including an emotion engine for analyzing the user's emotions, and means for generating a customized response based on the emotions recognized by the emotion engine. This makes it possible to provide specific and useful advice in response to a user's health-related question, taking into account the user's individual situation and emotions.

[1140] "User" refers to a person who enters a health-related question into the system in natural language and intends to receive a response.

[1141] A "question" refers to a sentence in which a user expresses a question or concern about health in natural language, and this sentence is the subject of transmission to the system.

[1142] "Terminal" refers to the device used by the user to input questions and receive responses from the system, such as a smartphone or PC.

[1143] "Server" refers to a computing system that is responsible for receiving and analyzing a user's query, and generating and transmitting a response.

[1144] A "natural language processing engine" refers to software that analyzes natural language questions entered by users and extracts keywords and structures.

[1145] An "emotion engine" refers to software that analyzes and recognizes the emotions contained in a user's question.

[1146] A "health knowledge database" refers to a collection of data that systematically records health-related information and is used to generate answers to questions.

[1147] A "preventive measures database" refers to a collection of data containing specific measures for maintaining or improving health, and is used to generate answers to questions.

[1148] A "generative AI model" refers to an artificial intelligence that automatically generates natural language responses to users based on received data. Specifically, this includes deep learning models.

[1149] "Customized responses" refer to answers that are individually tailored based on the user's question and emotions, providing the user with the most relevant health advice and information.

[1150] The present invention provides a system that provides customized responses to health-related questions entered by a user in natural language, taking into account the user's individual circumstances and emotions. Specific embodiments of the system are described below.

[1151] A user accesses the system using a device such as a smartphone or PC. For example, they enter "I've been feeling tired a lot lately. What should I do?" into a text box displayed on a web browser and press the send button. The device then sends this question to the server as an HTTP POST request.

[1152] The server receives the HTTP POST request sent from the device and analyzes the request body to extract the question. This question is then sent to a natural language processing (NLP) engine and an emotion engine. The NLP engine analyzes the question and extracts key keywords. For example, the keyword "gets tired easily" is extracted. At the same time, the emotion engine analyzes the emotions contained in the question and recognizes "anxiety" and "fatigue."

[1153] Next, the server searches the health knowledge database and preventive measures database based on the keywords from the NLP engine and the emotion information from the emotion engine. For example, it retrieves health information and preventive measures related to "easily tired," "anxiety," and "fatigue" from the database. The retrieved information is then provided to a generative AI model (e.g., GPT-4).

[1154] The generative AI model generates a customized response based on the information provided, such as, "A balanced diet and sufficient rest are important for recovering from fatigue. Moderate exercise is also effective. Mental care is also important, so we recommend making time to relax."

[1155] The generated response is sent from the server to the device as an HTTP response. The device analyzes the received HTTP response and displays the generated response to the user. The user can then review and implement specific, customized health advice and preventive measures.

[1156] For example, if a user inputs "I've been feeling tired lately. What should I do?", the server will generate a response saying, "To recover from fatigue, it's important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Mental care is also important, so I recommend you make time to relax." and send it to the user's device. The device will then display the response to the user.

[1157] Examples of prompts:

[1158] If a user types, "I've been feeling tired lately, what should I do?", what response should the system generate? The user's emotions are anxiety and fatigue.

[1159] As described above, by implementing this invention, users can easily obtain specific and useful advice tailored to their health-related situation and emotions. Furthermore, by utilizing a generative AI model and an emotion engine, responses can be personalized, providing more beneficial healthcare support.

[1160] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1161] System program processing flow:

[1162] Step 1:

[1163] User inputs and submits a question

[1164] The user uses the terminal to input a health-related question in natural language. For example, the user might input "I've been feeling tired a lot lately. What should I do?" and click the send button.

[1165] Input: A user-entered natural language question.

[1166] Output: HTTP POST request from the terminal to the server.

[1167] Step 2:

[1168] Sending an HTTP request from the device to the server

[1169] The device sends the question entered by the user to the server as an HTTP POST request, which includes the question in JSON format.

[1170] Specific request example:

[1171] POST / api / health_query HTTP / 1.1

[1172] Host: api.example.com

[1173] Content-Type: application / json

[1174] {

[1175] "question": "I've been feeling tired a lot lately. What should I do?"

[1176] }

[1177] Input: The user's question.

[1178] Output: HTTP POST request to the server.

[1179] Step 3:

[1180] The server receives and analyzes the HTTP request

[1181] The server receives the HTTP POST request sent from the device, extracts the question from the request body, and sends it to the natural language processing engine and emotion engine for analysis.

[1182] Input: HTTP POST request.

[1183] Output: The question.

[1184] Step 4:

[1185] Question analysis by NLP engine

[1186] The server sends the question to a natural language processing (NLP) engine, which analyzes the question and extracts keywords, such as "easily tired."

[1187] Input: Question.

[1188] Output: Extracted keywords.

[1189] Step 5:

[1190] Emotion analysis using an emotion engine

[1191] The server sends the question to the emotion engine, which analyzes the user's emotions. For example, "anxiety" or "fatigue" is recognized.

[1192] Input: Question.

[1193] Output: Recognized emotion.

[1194] Step 6:

[1195] Database search by server

[1196] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the recognized emotions to obtain relevant health information and preventive measures. For example, information related to "easily tired," "anxiety," and "fatigue" is obtained.

[1197] Input: Extracted keywords, recognized sentiment.

[1198] Output: Health information and preventive measures.

[1199] Step 7:

[1200] Generating a response

[1201] The server provides the acquired health information and preventive measures to a generative AI model (e.g., GPT-4) to generate a customized response for the user. For example, a response might be generated such as, "To recover from fatigue, a balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so we recommend that you make time to relax."

[1202] Enter: health information and precautions.

[1203] Output: The customized response.

[1204] Step 8:

[1205] Sending HTTP responses from the server to the device

[1206] The server sends the generated customization response to the device as an HTTP response. For example, the response is sent in the following format:

[1207] HTTP / 1.1 200 OK

[1208] Content-Type: application / json

[1209] {

[1210] "response": "To recover from fatigue, it is important to eat a balanced diet and get enough rest. Moderate exercise is also effective. Taking care of your mind is also important, so I recommend making time to relax."

[1211] }

[1212] Input: Your customized response.

[1213] Output: HTTP response to the device.

[1214] Step 9:

[1215] Terminal receives and displays response

[1216] The device receives the HTTP response, parses it, extracts the generated response, and displays it to the user, who can then view and implement specific, customized health advice.

[1217] Input: HTTP response.

[1218] Output: The response displayed to the user.

[1219] The above are the specific processing steps of the program for this system. By following this flow, users can easily receive specific and useful advice tailored to their health condition.

[1220] (Application example 2)

[1221] 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."

[1222] In recent years, there has been an increasing demand for health consultations and advice via smart devices. However, conventional systems have difficulty providing customized responses that take the user's emotions into account in real time, resulting in a decline in user satisfaction. Furthermore, there is a demand for efficient information provision using wearable devices such as smart glasses, but the technology to achieve this is still in its infancy. Therefore, a system that analyzes the user's emotions and provides health advice accordingly is needed.

[1223] 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 receiving a question entered by a user in natural language, means for analyzing the received question and extracting keywords, and means for searching a health knowledge database based on the keywords. This makes it possible to analyze the user's emotions and generate customized responses in real time to display on the smart glasses. This also improves user satisfaction and makes it possible to provide health advice more effectively.

[1224] "Means for receiving questions entered by a user in natural language" refers to the function of recognizing questions entered by a user in natural language such as voice or text and sending them to the system.

[1225] "Means for analyzing received questions and extracting keywords" refers to a function that analyzes received questions using natural language processing technology and extracts important keywords.

[1226] "Means for searching a health knowledge database based on keywords" refers to a function for searching a database for relevant health information using the extracted keywords.

[1227] "Means for searching the database of preventive measures based on keywords" refers to a function that uses the extracted keywords to search the database for relevant preventive measures and advice.

[1228] "Means for analyzing user emotions" refers to a function for recognizing the user's emotions from the received questions and identifying the appropriate emotional state.

[1229] "Means of providing search results and sentiment analysis results to a generative AI model to generate a customized response for the user" refers to the function of using generative AI to create a customized response for the user based on the searched information and the results of sentiment analysis.

[1230] "Means for transmitting the generated response to the user terminal and displaying it on the display of the smart glasses" refers to a function for transmitting the generated response to the user's smart device via the Internet and displaying it on the display of the smart glasses.

[1231] "Natural language processing engine" refers to a software engine that analyzes received natural language text and understands its meaning.

[1232] "Emotion engine" refers to a software engine for recognizing a user's emotional state from text or speech.

[1233] A "generative AI model" refers to an artificial intelligence model that generates appropriate responses based on input data (keywords and sentiment analysis results).

[1234] "Smart glasses" are a wearable eyeglass-type device with a built-in display that allows users to receive visual information in real time.

[1235] The present invention relates to a system that allows users to input health-related questions in natural language and generates and provides responses to those questions, and that can provide real-time health advice using smart glasses.

[1236] Users can input health-related questions by voice through the smart glasses. The voice-input information is converted into text using voice recognition software (e.g., Google Speech-to-Text API) within the smart glasses. The converted text is then sent to a server over the Internet.

[1237] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) to extract keywords from the question, and simultaneously analyzes the user's sentiment using an emotion engine (e.g., Microsoft Azure's Text Analytics API) to obtain the results.

[1238] The server searches the health knowledge database and preventive measures database based on the extracted keywords and the results of emotion analysis. For example, if the keyword "easily tired" is extracted and "fatigue" and "anxiety" are recognized from the emotion analysis results, the server retrieves related health information and preventive measures from the database.

[1239] The server generates a customized response based on the search results and sentiment analysis results using a generative AI model (e.g., GPT-3), which is then sent over the internet to the user's smart glasses and displayed on their screen.

[1240] For example, if a user types, "I've been feeling tired a lot lately. What should I do?", the server will generate a response such as, "A balanced diet and sufficient rest are important. Moderate exercise is also effective. Mental care is also important, so I recommend that you make time to relax," and display this on the smart glasses.

[1241] This invention allows users to receive customized health advice in real time and enjoy individual health support, thereby improving user satisfaction and realizing a system that effectively provides health advice.

[1242] An example of a prompt sentence is as follows:

[1243] "Generate customized health advice based on the following questions and emotions: Question: 'I've been feeling tired lately, what should I do?' Emotion: 'I feel anxious and tired.'"

[1244] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1245] Step 1:

[1246] The user inputs health-related questions by voice through the smart glasses. The voice data is captured by the microphone of the smart glasses. The input data is in voice format, and the final output is a question in text format.

[1247] Step 2:

[1248] The smart glasses' voice recognition software converts the input voice data into text. Specifically, the Google Speech-to-Text API receives the voice data, analyzes its content, and generates corresponding text. The input is voice data, and the output is text data.

[1249] Step 3:

[1250] The terminal sends text data to a server over the Internet. The text data is sent using an HTTP POST request. The input is the text data, and the output is an HTTP request to the server.

[1251] Step 4:

[1252] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP, IBM Watson) and extracts keywords. Specifically, it tokenizes the text and extracts important keywords. The input is text data, and the output is a list of keywords.

[1253] Step 5:

[1254] The server searches the health knowledge database based on the keywords, and uses SQL queries to retrieve relevant health information from the database. The input is the keywords, and the output is a list of health information.

[1255] Step 6:

[1256] At the same time, the server uses an emotion engine (e.g., Microsoft Azure's Text Analytics API) to analyze the user's emotions. Specifically, it analyzes the text data to detect patterns specific to emotions. The input is the text data, and the output is the emotion analysis results.

[1257] Step 7:

[1258] The server searches the preventive measures database based on the keywords and sentiment analysis results. It uses SQL queries to retrieve relevant information from the preventive measures database. The input is the keywords and sentiment analysis results, and the output is a list of preventive measures.

[1259] Step 8:

[1260] The server generates a customized response using a generative AI model (e.g., GPT-3) based on the search results and sentiment analysis results. A prompt is input to the generative AI model, which outputs a customized text response. The input is the prompt and search results, and the output is a customized response.

[1261] Step 9:

[1262] The server generates a response and sends it to the terminal as an HTTP response. The input is a customized response, and the output is an HTTP response.

[1263] Step 10:

[1264] The terminal parses the received HTTP response and extracts the generated response. The input is the HTTP response and the output is the text response.

[1265] Step 11:

[1266] The terminal displays the acquired text response on the display of the smart glasses. The input is the text response, and the output is the response displayed on the display.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] FIG. 9 illustrates 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 behaviors 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.

[1272] 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.

[1273] 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).

[1274] 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.

[1275] 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."

[1276] 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.

[1277] 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).

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] The following is further disclosed regarding the above embodiment.

[1289] (Claim 1)

[1290] means for receiving a question entered by a user in natural language;

[1291] A means for analyzing the received question and extracting keywords;

[1292] a means for searching a health knowledge database based on keywords;

[1293] a means for searching the preventative measures database based on keywords;

[1294] a means for providing the search results to a generative AI model to generate a customized response for the user;

[1295] means for transmitting the generated response to the user terminal;

[1296] A system including:

[1297] (Claim 2)

[1298] 10. The system of claim 1, wherein the system analyzes the question using a natural language processing engine.

[1299] (Claim 3)

[1300] 10. The system of claim 1, wherein the system receives a user's question via an HTTP request and transmits a response via an HTTP response.

[1301] "Example 1"

[1302] (Claim 1)

[1303] means for receiving a question entered by a user in natural language;

[1304] A means for analyzing the received question and extracting keywords;

[1305] a means for searching a health knowledge database based on keywords;

[1306] a means for searching the preventative measures database based on keywords;

[1307] means for providing the search results to a generative AI model to generate a customized response for the user;

[1308] means for transmitting the generated response to a user terminal as an HTTP response;

[1309] means for displaying the generated response at the user terminal;

[1310] A system including:

[1311] (Claim 2)

[1312] 10. The system of claim 1, wherein the system analyzes the question using a natural language processing engine.

[1313] (Claim 3)

[1314] 10. The system of claim 1, wherein the system receives a user's question via an HTTP request and transmits a response via an HTTP response.

[1315] "Application Example 1"

[1316] (Claim 1)

[1317] means for receiving a question entered by a user in natural language;

[1318] A means for analyzing the received question and extracting keywords;

[1319] a means for searching a health knowledge database based on keywords;

[1320] a means for searching the preventative measures database based on keywords;

[1321] means for providing the search results to a generative AI model to generate a customized response for the user;

[1322] means for transmitting the generated response to the user terminal;

[1323] means for presenting the response on a display device utilized within the autonomous vehicle;

[1324] A system including:

[1325] (Claim 2)

[1326] 10. The system of claim 1, wherein the system analyzes the question using a natural language processing engine.

[1327] (Claim 3)

[1328] 10. The system of claim 1, wherein the system receives a user's question via an HTTP request and transmits a response via an HTTP response.

[1329] "Example 2: Combining Emotion Engines"

[1330] (Claim 1)

[1331] means for receiving a question entered by a user in natural language;

[1332] A means for analyzing the received question and extracting keywords;

[1333] a means for searching a health knowledge database based on keywords;

[1334] a means for searching the preventative measures database based on keywords;

[1335] a means for providing the search results to a generative AI model to generate a customized response for the user;

[1336] means for transmitting the generated response to the user terminal;

[1337] means including an emotion engine for analyzing the emotion of a user;

[1338] means for generating a customized response based on the emotion recognized by the emotion engine;

[1339] A system including:

[1340] (Claim 2)

[1341] 10. The system of claim 1, wherein the system analyzes the question using a natural language processing engine.

[1342] (Claim 3)

[1343] 10. The system of claim 1, wherein the system receives a user's question via an HTTP request and transmits a response via an HTTP response.

[1344] "Application example 2 when combining emotion engines"

[1345] (Claim 1)

[1346] means for receiving a question entered by a user in natural language;

[1347] A means for analyzing the received question and extracting keywords;

[1348] a means for searching a health knowledge database based on keywords;

[1349] a means for searching the preventative measures database based on keywords;

[1350] means for analyzing user emotions;

[1351] a means for providing the search results and sentiment analysis results to a generative AI model to generate a customized response for the user;

[1352] means for transmitting the generated response to the user terminal and displaying it on a display of the smart glasses;

[1353] A system including:

[1354] (Claim 2)

[1355] 10. The system of claim 1, wherein the system uses a natural language processing engine and an emotion engine to analyze questions and emotions.

[1356] (Claim 3)

[1357] 10. The system of claim 1, wherein the system receives a user's question via an HTTP request and sends a response via an HTTP response for display on a display of the smart glasses. [Explanation of symbols]

[1358] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a question entered by a user in natural language; A means for analyzing the received question and extracting keywords; a means for searching a health knowledge database based on keywords; a means for searching the preventative measures database based on keywords; a means for providing the search results to a generative AI model to generate a customized response for the user; means for transmitting the generated response to the user terminal; A system including:

2. The system of claim 1 , wherein the system analyzes the question using a natural language processing engine.

3. 10. The system of claim 1, wherein the system receives a user's question via an HTTP request and transmits a response via an HTTP response.

Images