System

Abstract

A system is provided.SOLUTION: A system comprising: means for requesting information corresponding to a type of trouble selected by a user from a server; means for receiving the request from the server and acquiring the corresponding information from a database; means for generating an answer to a specific question of the user by using an AI model generated by the server; means for analyzing the acquired information and shaping the information into a visual and auditory form; means for transmitting the shaped information to a user terminal; and means for displaying the transmitted information on the user terminal.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 modern society, when faced with unexpected problems in daily life or at work, it is difficult to obtain the information necessary to respond quickly and appropriately. In many cases, information is scattered or difficult to obtain, which can waste users' time and lead to further problems. There is a need to improve this situation and enable users to respond quickly and appropriately to the various problems they face. [Means for solving the problem]

[0005] This invention provides a system that includes: a means for requesting information corresponding to a type of problem selected by a user from a server; a means for the server to receive the request and retrieve the corresponding information from a database; a means for the server to generate an answer to the user's specific question using a generative AI model; a means for the server to analyze the retrieved information and format it visually and aurally; a means for the server to transmit the formatted information to a user terminal; and a means for the user terminal to display the transmitted information to the user. Furthermore, by using multimodal technology to provide information in visual and aural formats, the system allows users to easily understand and act on the information. Furthermore, by including a means for obtaining feedback from users and transmitting it to the server, this information can be used to provide future information and improve the system. In this way, it is possible to provide prompt and accurate information and comprehensive support when users encounter difficult situations.

[0006] "User" refers to an individual who uses this system to obtain and use information to address a specific problem.

[0007] "Server" refers to a computer system that receives requests from users and generates and provides appropriate information using a database and AI model.

[0008] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that has the ability to communicate with a server and display information.

[0009] "Generative AI model" refers to artificial intelligence technology used to generate answers to specific user questions.

[0010] "Request" means a request for specific information or action that a User sends to a Server via a Device.

[0011] A "database" refers to a storage device or system that stores information for dealing with problems.

[0012] "Visual format" refers to a visually perceptible method of presenting information, such as text or illustrations.

[0013] "Auditory format" refers to a method of providing information that can be perceived audibly, such as voice assistance.

[0014] "Multimodal technology" refers to technology that provides information using multiple senses (sight, hearing, etc.).

[0015] "Feedback" refers to any evaluation or follow-up questions a user may make in response to the information provided. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This system provides users with the necessary information quickly and accurately to deal with the various problems they may encounter. Below, we will explain in detail each component of this system and how it works.

[0038] System Overview

[0039] The system mainly includes the following components:

[0040] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0041] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0042] Database: A data storage system that stores information for troubleshooting.

[0043] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0044] How it works

[0045] Select a scenario and submit a request

[0046] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[0047] Based on the user's selection, the device generates and sends a request to the server, including the selected problem type and basic user information (such as location and language settings).

[0048] Information collection and analysis

[0049] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (for example, a list of allowances that can be applied for in the event of sudden hospitalization).

[0050] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[0051] The server analyzes the information and formats it in an appropriate format (text, graphics, audio) to be presented to the user.

[0052] Providing and Displaying Information

[0053] The server then sends the formatted information to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[0054] The device displays the received information on the user interface so that the user can visually confirm it, and also provides information audibly through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[0055] Specific examples

[0056] Example 1: How to apply for benefits in the event of sudden hospitalization

[0057] If the user selects "acute admission," the user will need information regarding the application for benefits.

[0058] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[0059] The server formats this information in diagram and text format and sends it to the user's terminal.

[0060] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0061] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0062] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[0063] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0064] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[0065] The server formats this information as text and illustrations and sends it to the user's terminal.

[0066] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[0067] In this way, the system can provide comprehensive support by quickly and accurately providing information on specific user problems.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Users launch the app and select the type of problem they are experiencing from the main menu.

[0071] Step 2:

[0072] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[0073] Step 3:

[0074] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[0075] Step 4:

[0076] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[0077] Step 5:

[0078] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[0079] Step 6:

[0080] The server formats the retrieved information and generated answers into visual (text, diagrams) and audible (voice-assisted) formats, such as a diagram of the benefits claim flow or steps in the repair procedure.

[0081] Step 7:

[0082] The server sends the formatted information to the user's terminal.

[0083] Step 8:

[0084] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, and, if necessary, voice assistance.

[0085] Step 9:

[0086] Users can check the information provided through their devices and take appropriate action.

[0087] Step 10:

[0088] (any)

[0089] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[0090] Step 11:

[0091] (any)

[0092] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model.

[0093] The above is the specific flow of processing of the program in this system.

[0094] Example 1

[0095] 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."

[0096] Conventional information provision systems have had difficulty in quickly and accurately providing information to address the various problems users face. Furthermore, there was a lack of systems that could provide information visually and audibly, which meant that users sometimes could not obtain sufficient information under certain circumstances. To solve these issues, a system that can comprehensively and flexibly respond to specific user requests is needed.

[0097] 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.

[0098] In this invention, the server includes a means for requesting data corresponding to the type of problem selected by the user from the server, a means for the server to receive the request and retrieve the corresponding data from the storage system, and a means for the server to generate an answer to the user's specific request using the generative AI model, thereby enabling the server to provide information quickly and accurately to the problem the user is facing.

[0099] "User" means an individual or organizational entity that seeks to obtain information using the system.

[0100] A "problem" is a specific challenge or situation a user faces, such as an emergency hospital stay or a device malfunction.

[0101] "Data" refers to the necessary information that the server retrieves from a storage system such as a database, including procedures and contact information necessary to resolve the user's problem.

[0102] A "server" is a computer system that has the ability to receive requests from users, retrieve data from a database, generate information using a generative AI model, and send it to the user's device.

[0103] A "request" is a data request that a user sends to the server via their terminal, and includes the type of question selected and basic information about the user.

[0104] A "storage system" is a database or other data storage device for storing data.

[0105] A "generative AI model" is an artificial intelligence technology used by the server to generate detailed answers to specific user requests.

[0106] "Textual information" means data in text form that is visually displayed to the user.

[0107] "Audio information" means data in audio format that is audibly presented to a user.

[0108] A "user terminal" is a device used by a user, such as a smartphone or tablet, that has the ability to communicate with a server and display information.

[0109] System Overview

[0110] This system is designed to provide the necessary information quickly and accurately to deal with the various problems users face. It mainly includes the following components:

[0111] 1. User terminal: A device such as a smartphone or tablet used by the user, which communicates with the server and displays information.

[0112] 2. Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0113] 3. Storage system: The data storage system where the data to address the problem is stored.

[0114] 4. Generative AI models: Artificial intelligence techniques for generating answers to specific user requests.

[0115] How it works

[0116] Select a scenario and submit a request

[0117] Users launch the app and select the type of problem they are facing from the main menu, such as "emergency hospitalization" or "smartphone breakdown."

[0118] Based on the user's selection, the device generates a request to the server, which includes the selected problem type and basic user information (such as location and language settings).

[0119] Data acquisition and analysis

[0120] The server determines the problem based on the received request and retrieves relevant data (for example, a list of allowances that can be applied for in the event of sudden hospitalization) from the storage system.

[0121] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[0122] For example, prompts include: "Where do I apply for benefits?", "Where is the nearest repair shop?", and "How do I contact you in an emergency?"

[0123] The server analyzes the acquired data and formats it into an appropriate format (text information, illustrations, audio information) to provide to the user.

[0124] Providing and Displaying Information

[0125] The server then sends the formatted data to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[0126] The device displays the received data on the user interface so that the user can visually confirm it, and also provides audible information through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[0127] Specific examples

[0128] Example 1: How to apply for benefits in the event of sudden hospitalization

[0129] If the user selects "Sudden Admission," information regarding the application for benefits is required.

[0130] The server retrieves information from the storage system, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures.

[0131] For example, prompts: "Where do I apply for benefits?", "What documents do I need to receive benefits?"

[0132] The server formats this information into diagrams and textual information and sends it to the user's terminal.

[0133] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0134] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0135] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[0136] The server obtains information from the storage system about basic troubleshooting steps for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0137] For example, prompts: "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[0138] The generative AI model generates answers to specific user questions and provides detailed instructions on how to deal with the problem.

[0139] The server formats this information into text and illustrations and sends it to the user's terminal.

[0140] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[0141] The above is an embodiment of the present invention, and the system can provide information quickly and accurately on specific problems of users and provide comprehensive support.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Processing flow

[0144] Step 1:

[0145] The user launches the app and selects the type of problem they are facing from the main menu.

[0146] Input: The type of problem the user selects (e.g., "Sudden hospitalization" or "Smartphone broken")

[0147] Specific operation: The user taps on the option displayed on the screen, which sends the selected question type to the device.

[0148] Step 2:

[0149] The device generates a request to the server based on the user's selection.

[0150] Input: User information such as the selected problem type, user location, and language preference.

[0151] Output: Generated request data

[0152] What happens: The device collects the selections and user information, formats the data, and sends it to the server as a request.

[0153] Step 3:

[0154] The server analyzes the incoming request and determines the type of problem it encounters.

[0155] Input: Request data sent from the terminal

[0156] Output: Search query based on issue type

[0157] What happens: The server analyzes the request and generates a search query to determine the type of problem.

[0158] Step 4:

[0159] The server retrieves the relevant data from the storage system.

[0160] Input: Search query based on issue type

[0161] Output: Relevant data (e.g., in case of sudden hospitalization, medical care-related data)

[0162] Specific operation: The server uses the generated search query to search for and retrieve the relevant data from the storage system.

[0163] Step 5:

[0164] The server uses a generative AI model to generate answers to specific user questions.

[0165] Input: relevant data obtained, specific user questions

[0166] Output: Detailed answers from a generative AI model

[0167] Specific operation: The server inputs the acquired data and the user's question as a prompt into a generative AI model (e.g., GPT-4 (registered trademark)) to generate a detailed answer.

[0168] Examples of prompts: "Where do I apply for benefits?", "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[0169] Step 6:

[0170] The server analyzes the acquired data and generated answers, and formats them into text and audio information.

[0171] Input: Response from the generative AI model, related data obtained

[0172] Output: Formatted text, illustrations, audio

[0173] Specific operation: The server analyzes the acquired data and the generated AI model's response, and formats it into text, charts, and audio data for delivery to the user. Formatting is done using HTML, CSS, JSON, etc.

[0174] Step 7:

[0175] The server sends the formatted data to the user's device.

[0176] Input: Formatted text, illustrations, audio information

[0177] Output: Data sent to the user's terminal

[0178] Specific operation: The server packets the formatted data and sends it to the user terminal.

[0179] Step 8:

[0180] The device displays the received data on the user interface and provides information using the voice assistant function.

[0181] Input: Text information, illustrations, and audio information sent from the server

[0182] Specific operation: The device analyzes the received data, displays text and illustrations on the screen, and uses TTS (Text-to-Speech) technology to provide audio guidance.

[0183] Users can see the information visually on the screen and hear more details through an audio guide.

[0184] The above are the specific processing steps of the system program.

[0185] (Application example 1)

[0186] 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."

[0187] Conventional troubleshooting systems often lack the functionality to provide users with prompt and appropriate responses to emergency situations, resulting in inconvenience. In particular, the methods of providing information to users with visual or speech impairments are limited, and comprehensive support is not provided. Furthermore, the lack of detailed explanations for specific user questions can increase anxiety when dealing with problems.

[0188] 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.

[0189] In this invention, the server includes: means for requesting information corresponding to a type of trouble selected by a user from the server; means for the server to receive the request and retrieve the corresponding information from a database; means for the server to generate answers to the user's specific questions using a generative AI model; means for the server to analyze the retrieved information and format it into visual and auditory formats; means for the server to send the formatted information to a user terminal; means for the user terminal to display the sent information to the user; emergency support means for the user to select an emergency situation and to provide countermeasures; and means for using a generative AI model to provide detailed explanations for the user's specific questions about the emergency situation. This allows the user to obtain quick and appropriate countermeasures when facing an emergency situation and receive comprehensive support using their vision and hearing.

[0190] The "means for requesting information corresponding to the type of trouble selected by the user from the server" is a function that allows the user to select a specific trouble they are facing and send detailed information about it as a request to the server.

[0191] "Means by which the server receives a request and retrieves the corresponding information from the database" refers to the function by which the server receives a request from a user and searches for and retrieves information based on that request from the database.

[0192] "Means for the server to use a generative AI model to generate answers to specific questions from users" refers to the function by which the server uses generative AI to create optimal answers to specific questions from users.

[0193] "Means for analyzing information acquired by the server and arranging it into visual and auditory formats" refers to the function by which the server analyzes information acquired and converts it into a format suitable for visual (text and illustrations) and auditory (audio) perception.

[0194] The "means for transmitting information formatted by the server to the user terminal" is a function for transmitting information formatted by the server in visual and auditory form to the user terminal.

[0195] "Means for the user terminal to display the transmitted information to the user" refers to a function by which the user terminal displays the information transmitted from the server so that the user can confirm it.

[0196] "Emergency support means that allows users to select an emergency situation and provides countermeasures" is a function that allows users to select an emergency situation through an application and provides appropriate countermeasures according to the situation.

[0197] "Means of using a generative AI model to provide detailed explanations in response to specific questions about a user's emergency situation" refers to a function that uses a generative AI model to provide specific and detailed explanations in response to questions about a user's emergency situation.

[0198] This invention is a system that provides a user with a prompt and appropriate response to an emergency situation they find themselves in. The components of this system and their operation will be described in detail below.

[0199] System Overview

[0200] The system mainly includes the following components:

[0201] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0202] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0203] Database: A data storage system that stores information for troubleshooting.

[0204] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0205] How it works

[0206] User selects emergency situation

[0207] The user launches the app and selects the type of emergency situation they are facing (e.g., burglary, fire, traffic accident).

[0208] Send request

[0209] Based on the selection, the user device generates and sends a request to the server, which includes the selected emergency situation type and basic user information (such as location and language settings).

[0210] Information Acquisition and Analysis

[0211] The server determines the relevant emergency situation based on the received request and retrieves relevant information from a database (evacuation routes, emergency contacts, initial emergency procedures, etc.) The server also uses a generative AI model to generate detailed explanations in response to the user's specific questions.

[0212] Formatting and providing information

[0213] The server analyzes the acquired information and formats it into an appropriate format (text, illustrations, or voice) for presentation to the user. The server then sends the formatted information to the user's device. The user's device then presents the received information to the user visually (text or illustrations) and audibly (voice assistance).

[0214] Specific names of hardware and software to be used

[0215] Hardware: Smartphone

[0216] Server: Backend using the Flask framework

[0217] Database: SQLite

[0218] Generative AI model: TENSORFLOW (registered trademark)

[0219] Example of operation

[0220] Example 1: Providing countermeasures in case of fire

[0221] If the user selects "fire," the server retrieves information from the database about evacuation routes, emergency contacts, and first aid procedures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[0222] Example prompt sentence:

[0223] "What is the safest way to escape in the event of a fire?"

[0224] Example of a generated answer:

[0225] "If a fire breaks out, immediately check the escape route and evacuate to a safe place. It is safest to move away from the source of the fire and stay as low as possible. While evacuating, cover your nose and mouth with a wet towel to ensure proper breathing."

[0226] Example 2: Providing countermeasures in case of burglary

[0227] If the user selects "burglary," the server retrieves information from the database about the necessary contacts and initial response measures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[0228] Example prompt sentence:

[0229] "If a burglar breaks in, what's the first thing you should do?"

[0230] Example of a generated answer:

[0231] "If a burglar breaks in, contact the police immediately and seek refuge in a safe location. Do not enter the residence."

[0232] In this way, the present invention allows users to obtain prompt and appropriate responses when faced with an emergency situation, and provides comprehensive support utilizing visual and auditory senses.

[0233] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0234] Step 1:

[0235] The user launches the app and selects the type of emergency, choosing from options such as "fire," "burglary," or "traffic accident." The input includes the user's selection, and the output generates a request with the selected emergency. The specific action involves the user tapping on the menu on the screen.

[0236] Step 2:

[0237] The user device sends a request for the selected emergency situation to the server, including the user's selection along with basic information such as location and language preference. The user's selection and basic information are used as inputs to generate the request. The output is the formation of a request that is sent to the server. Specific operations include the device communicating with the server.

[0238] Step 3:

[0239] The server analyzes the received request and retrieves information about the corresponding emergency situation from the database. At this stage, the request information is used as input to generate a database search query. Information is retrieved from the database using the database search query as input, and a retrieved information set is generated as output. Specific operations include database search and information extraction within the server.

[0240] Step 4:

[0241] The server uses the generative AI model to generate detailed answers to the user's specific questions. The input includes information about the emergency situation and basic information about the user, and the generative AI model uses this information to create a prompt. The output is an answer to the user's specific question. The specific operation involves a series of calculations in which the AI ​​model processes the prompt and generates an answer.

[0242] Step 5:

[0243] The server analyzes the information it receives and formats it into visual and auditory formats. It uses information retrieved from a database and answers from a generative AI model as input. After analysis and formatting, it generates an information set suitable for visual and auditory use as output. Specific operations include generating text data, image data, and creating audio files.

[0244] Step 6:

[0245] The server transmits the formatted information to the user terminal. The visual and auditory formatted information set is used as input, and a data packet is formed as output and transmitted to the user terminal. Specific operations include transmitting data from the server to the user terminal.

[0246] Step 7:

[0247] The user device displays the received information to the user. The input is the visually and audibly formatted information received from the server, and the output is information that the user can confirm visually and audibly. Specific operations include displaying text and illustrations on the screen and, if necessary, playing explanations through a voice assistant.

[0248] 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.

[0249] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation in a form that incorporates an emotion engine.

[0250] System Overview

[0251] The system mainly includes the following components:

[0252] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0253] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, and emotion engine.

[0254] Database: A data storage system that stores information for troubleshooting.

[0255] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0256] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[0257] How it works

[0258] Select a scenario and submit a request

[0259] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[0260] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[0261] Information collection and analysis

[0262] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (e.g., a list of allowances that can be applied for in the event of sudden hospitalization).

[0263] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[0264] The emotion engine recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information and assistance to help the user relax.

[0265] Providing and Displaying Information

[0266] The server integrates the acquired information and the output from the emotion engine and formats it into visual (text, diagrams) and auditory (voice assistance) formats, such as providing a diagram of the benefit application process or instructions on how to relax.

[0267] The server sends the formatted information to the user's terminal.

[0268] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[0269] Specific examples

[0270] Example 1: How to apply for benefits in the event of sudden hospitalization

[0271] If the user selects "acute admission," the user will need information regarding the application for benefits.

[0272] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[0273] The emotion engine recognizes the user's emotions and provides information to encourage relaxation if the user is feeling stressed.

[0274] The server formats this information into diagrams and text, and sends it to the user's device along with instructions on relaxation techniques.

[0275] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0276] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0277] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[0278] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0279] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[0280] The emotion engine recognizes the user's emotions and provides calming advice if the user is feeling anxious.

[0281] The server formats this information as text and illustrations and sends it to the user's terminal.

[0282] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[0283] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[0284] The processing flow will be explained below.

[0285] Step 1:

[0286] Users launch the app and select the type of problem they are experiencing from the main menu.

[0287] Step 2:

[0288] Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information (location information, language settings, device status information, etc.) and sends it to the server.

[0289] Step 3:

[0290] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[0291] Step 4:

[0292] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[0293] Step 5:

[0294] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[0295] Step 6:

[0296] The user device uses a camera and microphone to capture the user's facial expressions and tone of voice and transmit them to the emotion engine.

[0297] Step 7:

[0298] The emotion engine analyzes the user's emotion from the received data and sends the result to the server (e.g., the user is feeling anxious).

[0299] Step 8:

[0300] The server integrates information from the emotion engine and generates appropriate information and support based on the user's emotions. For example, if the user is feeling anxious, it can include relaxation techniques and emergency contact information.

[0301] Step 9:

[0302] The server formats the information into visual (text, diagrams) and audible (voice-assisted) formats.

[0303] Step 10:

[0304] The server sends the formatted information to the user's terminal.

[0305] Step 11:

[0306] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[0307] Step 12:

[0308] Users can check the information provided through their devices and take appropriate action.

[0309] Step 13:

[0310] (any)

[0311] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[0312] Step 14:

[0313] (any)

[0314] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model and emotion engine.

[0315] The above is the specific processing flow in this system incorporating the emotion engine.

[0316] Example 2

[0317] 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."

[0318] Conventional information provision systems have been limited in the information they provide when dealing with the various problems users face. Furthermore, they provide only uniform information without considering the user's emotions, resulting in a lack of support appropriate to the user's situation. This makes it difficult for users to receive adequate support in situations where they feel anxious or stressed. The purpose of this invention is to solve these problems and provide a system that provides users with prompt and accurate information and support tailored to their emotions.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring information corresponding to the type of trouble selected by the user from a database, means for generating answers to specific questions using a generative AI model, means for analyzing the user's emotions using an emotion engine and generating response information, and means for integrating the acquired information and output from the emotion engine and shaping them into visual and auditory formats. This allows the user to receive prompt and accurate information according to the type of trouble and appropriate support according to their emotional state.

[0320] "User" refers to any individual or entity that uses the System.

[0321] "Server" refers to a computer system that receives requests from users and processes and provides information.

[0322] A "request" refers to a request that a user makes by entering information such as the type of problem and sending it to the server.

[0323] "Database" refers to a data storage system in which information corresponding to a problem is stored.

[0324] A "generative AI model" refers to a system that uses artificial intelligence technology to generate answers to specific user questions.

[0325] An "emotion engine" refers to a system that recognizes the user's emotions and responds accordingly.

[0326] "Visual format" refers to the way information is presented, such as in text or illustrations.

[0327] "Auditory format" refers to methods of providing information in the form of voice assistance or the like.

[0328] "User terminal" refers to a device used by a user, such as a smartphone or tablet.

[0329] "Format" refers to the process of integrating and converting acquired information into visual and auditory form.

[0330] "Trouble" refers to problems or difficult situations that users face.

[0331] A "prompt sentence" refers to a text sentence that is input into a generative AI model.

[0332] This invention relates to a system that provides users with the information they need to quickly and accurately respond to various problems they encounter, while also recognizing and adapting to their emotions. Specifically, this system is realized by linking the following components: a user terminal, a server, a database, a generative AI model, and an emotion engine.

[0333] Hardware and Software Configuration

[0334] User terminal: A device such as a smartphone or tablet that communicates with the server and displays information.

[0335] Server: A computer system that receives requests from users and generates and provides appropriate information using a database, generative AI model, and emotion engine.

[0336] Database: A data storage system that stores information for troubleshooting.

[0337] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0338] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[0339] Operational Overview

[0340] 1. The user launches the app on their device, such as a smartphone or tablet, and selects the type of problem they are facing from the main menu. For example, "sudden hospitalization" or "smartphone breakdown."

[0341] 2. Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location and language settings) and sends it to the server.

[0342] 3. The server analyzes the received request, determines the corresponding problem scenario, and retrieves relevant information from the database, such as how to apply for benefits for sudden hospitalization or how to contact the user if their smartphone breaks down.

[0343] 4. The server uses the generative AI model to generate detailed answers and explanations for the user's specific questions. For example, the prompt "Please tell me how to apply for benefits in case of sudden hospitalization" is input to the generative AI model.

[0344] 5. The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates additional information and advice to help them relax.

[0345] 6. The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[0346] 7. The server sends the formatted information to the user device, which parses it and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, or voice assistance.

[0347] Specific examples

[0348] Example 1: How to apply for benefits in the event of sudden hospitalization

[0349] The user selects "urgent hospitalization."

[0350] The device generates a request including the scenario ID and basic information and sends it to the server.

[0351] The server receives the request and retrieves information from the database, such as how to apply for emergency hospitalization benefits, the necessary documents, and where to apply. It also uses a generative AI model to provide more specific explanations and procedures.

[0352] The emotion engine recognizes the user's stress and provides information to encourage relaxation.

[0353] The server formats the information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques.

[0354] The device displays the information and uses voice assistance to explain the details.

[0355] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0356] The user selects "Smartphone broken."

[0357] The device generates a request including the scenario ID and basic information and sends it to the server.

[0358] The server receives the request and retrieves information from the database about basic troubleshooting steps for when your smartphone breaks down, alternative contact methods (such as the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0359] Using a generative AI model, it generates answers to specific user questions and provides additional information, such as "where is the nearest repair shop?" or "how to contact someone in an emergency."

[0360] The emotion engine recognizes when the user is feeling anxious and provides advice to help them calm down.

[0361] The server formats the information as text and illustrations and sends it to the user's terminal.

[0362] The device displays the information and explains it using voice assistance.

[0363] In this way, the system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] Step 1: Select the user's problem and submit a request

[0366] Users launch the app on their smartphone, tablet, or other device and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction."

[0367] Input: Type of problem, basic user information (location, language settings)

[0368] Based on the user's selection, the device generates a request including the scenario ID and basic information about the user and sends it to the server.

[0369] Output: Request data sent to the server (scenario ID, user information)

[0370] Specific operation: When the user taps the selection button on the app screen, the device automatically generates request data (JSON format) and sends it to the server.

[0371] Step 2: Receiving and Parsing the Request

[0372] The server receives the request sent from the device, analyzes the request data, extracts the scenario ID and basic user information, and starts processing.

[0373] Input: Request data (scenario ID, user information)

[0374] Output: Analysis results of scenario ID and user information

[0375] Specific operation: The server analyzes the received request data, reads the scenario ID and the user's basic information (location, language settings), and passes it to the next processing step.

[0376] Step 3: Obtaining relevant information

[0377] The server retrieves information related to the problem from the database. For example, in the case of "sudden hospitalization," it retrieves information on how to apply for medical treatment, and in the case of "smartphone malfunction," it retrieves information on repair procedures and alternative contact methods.

[0378] Input: Scenario ID, user information

[0379] Output: Related information (application method, required documents, repair method, etc.)

[0380] Specific operation: The server generates an SQL query, sends it to the database to retrieve the relevant information, and loads the retrieved results into memory.

[0381] Step 4: Generative AI model generates answers

[0382] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation, for example, by entering a prompt such as "How do I apply for benefits in case of sudden hospitalization?"

[0383] Input: User question, related information

[0384] Output: Answer from the generative AI model

[0385] Specific operation: The server generates a prompt based on the user's question and sends it to the generative AI model, which then generates a specific answer in text and returns it to the server.

[0386] Step 5: Emotion engine analysis and response

[0387] The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates information and advice to help them relax.

[0388] Input: User response data (voice, text)

[0389] Output: Sentiment analysis results and corresponding information

[0390] Specific operation: The emotion engine determines the user's emotional state through voice recognition and text analysis, generates messages and actions according to that state, and returns them to the server.

[0391] Step 6: Integrate and format information

[0392] The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[0393] Input: relevant information, answers from generative AI models, and response information from emotion engines

[0394] Output: Formatted information (visual and auditory)

[0395] Specific operation: The server formats various information into HTML or JSON format, generates audio files as needed, and creates a data package to send to the user's device.

[0396] Step 7: Send and view information

[0397] The server then sends the formatted information to the user device, which then parses it and displays it in an appropriate format in a user interface, such as on-screen text, graphics, or voice assistance.

[0398] Input: Formatted information

[0399] Output: What is displayed on the user screen

[0400] Specific operation: The user device analyzes the received data, displays the information in the GUI component, and plays the voice assistance from the speaker.

[0401] (Application example 2)

[0402] 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."

[0403] Existing systems can provide appropriate information for problems users encounter, but they do not adequately consider the user's emotions or location information. This can result in stress for users, and it can take a long time for them to obtain appropriate information. Furthermore, even in physical store shopping experiences, there is a lack of functionality that considers the user's emotions and suggests optimal products. Therefore, there is a need for the development of a system that can respond more quickly to individual user needs and improve the experience.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0405] In this invention, the server includes an emotion recognition means for analyzing the user's emotions and providing information and services according to the user's emotional state, a location information analysis means for analyzing the user's location information and recommending products and services suitable for the user's current location, and a means for generating answers to the user's specific questions using a generative AI model, thereby enabling the provision of information based on the user's emotions and location information.

[0406] "User device" means an electronic device used by a user to receive information, including a smartphone or tablet.

[0407] A "server" is a computer system that receives and responds to requests from users, analyzes data, and generates information.

[0408] A "database" is a data storage system where the required information is stored.

[0409] A "generative AI model" is an artificial intelligence technology that generates answers to specific user questions.

[0410] "Emotion recognition means" is a technology that recognizes the user's emotions and responds accordingly.

[0411] "Location information analysis means" is a technology that analyzes the user's current location and provides information and services based on that location.

[0412] "Means for formatting information into visual and auditory form" refers to the means by which the server converts the information it obtains into a format that is easy for the user to see or hear.

[0413] "Emotional state" refers to the emotional state of the user, and includes specific emotions such as stress or joy.

[0414] "Multimodal technology" is a technology that provides information by combining multiple sensory information (visual, auditory, etc.).

[0415] "Feedback" refers to information such as opinions, impressions, and ratings provided by users.

[0416] "Type of trouble" refers to the specific type of problem or difficulty the user faces, such as sudden hospitalization or smartphone breakdown.

[0417] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation, in an embodiment that incorporates an emotion engine and a location information analysis engine.

[0418] System Components

[0419] The system mainly includes the following components:

[0420] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0421] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, emotion recognition means, and location information analysis means.

[0422] Database: A data storage system that stores information for troubleshooting.

[0423] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0424] Emotion recognition means: Technology that recognizes the user's emotions and responds accordingly.

[0425] Location information analysis means: Technology for providing appropriate information and services based on the user's location information.

[0426] How it works

[0427] Select a scenario and submit a request

[0428] The user launches the app and selects the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction." Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information and sends it to the server.

[0429] Information collection and analysis

[0430] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database. If the server includes a specific question from the user, it uses a generative AI model to generate a detailed answer or explanation for the question. The emotion recognition means recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information or assistance to help the user relax. The location information analysis means analyzes the user's current location and recommends products and services based on that location.

[0431] Providing and Displaying Information

[0432] The server combines the acquired information and the output from the emotion recognition and location analysis means and formats it into visual (text, illustrations) and auditory (voice assistance) formats. For example, it may provide an illustration of the benefit application process or instructions on how to relax. The server then sends the formatted information to the user's device. The device then analyzes the information received from the server and displays it in the appropriate format in the user interface. This may include on-screen text, illustrations, or voice assistance.

[0433] Hardware and Software Use Cases

[0434] Hardware: Smartphone (user device), server

[0435] software:

[0436] Face Recognition: OpenCV

[0437] Speech analysis: Google(R) Cloud Speech-to-Text

[0438] Sentiment Analysis: IBM Watson® Natural Language Understanding

[0439] Database: MySQL (registered trademark)

[0440] Generative AI model: OpenAI® GPT-4

[0441] Emotion Recognition Method: Custom TensorFlow Model

[0442] Location information analysis means: GNSS module and location information API

[0443] User Interface: React Native

[0444] Voice Assistance: Google Text-to-Speech API

[0445] Specific examples

[0446] Example 1: How to apply for benefits in the event of sudden hospitalization

[0447] If the user selects "Sudden Hospitalization," the user will need information regarding applying for benefits. The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures. The emotion recognition means recognizes the user's emotions, and if the user is feeling stressed, it also provides information encouraging relaxation. The server formats this information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques. The device displays the application flow with diagrams and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0448] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0449] If the user selects "Smartphone broken," they will need information on alternative contact methods and repair procedures. The server retrieves information from the database on basic steps to take when a smartphone breaks down, alternative contact methods, and repair procedures. The generative AI model generates answers to the user's specific questions, providing supplementary explanations such as "where is the nearest repair shop" and "how to contact in an emergency." The emotion recognition means recognizes the user's emotions and provides advice to help them calm down if they are panicking. The server formats this information as text and illustrations and sends it to the user's device. The device displays the repair flow and a list of alternative contact methods, and explains emergency procedures using voice assistance.

[0450] Prompt Sentence Examples

[0451] "A user is asking about a specific product. Please answer the following questions appropriately:

[0452] For example: "Where do these bananas come from?"

[0453] ---

[0454] answer:"

[0455] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[0456] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0457] Step 1:

[0458] Input: The user launches the app on their device and selects the type of problem they are experiencing from the main menu.

[0459] Action: The user taps the Select button.

[0460] Output: The device generates a request containing the selection (scenario ID) and basic user information (such as location and language preference).

[0461] Step 2:

[0462] Input: The request made by the device.

[0463] How it works: The device sends the generated request to the server, which receives the request and analyzes the user's needs.

[0464] Output: The server determines the corresponding trouble scenario and obtains the analysis results.

[0465] Step 3:

[0466] Input: The scenario ID of the problem identified by the server.

[0467] How it works: The server queries the database to retrieve relevant information (e.g., a list of benefits available for emergency hospitalization).

[0468] Output: Information retrieved from the database.

[0469] Step 4:

[0470] Input: A specific question from the user (optional).

[0471] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate detailed answers and explanations for questions.

[0472] Output: The generated answer and / or explanation.

[0473] Step 5:

[0474] Input: User's facial image and voice data.

[0475] How it works: The server analyzes the user's emotions using emotion recognition tools (e.g. IBM Watson, OpenCV).

[0476] Output: The user's emotional state (e.g., stress, joy).

[0477] Step 6:

[0478] Input: The user's location.

[0479] How it works: The server uses location analysis tools (e.g., GNSS module, location API) to analyze the current location and recommend suitable products and services.

[0480] Output: Information about the recommended product or service.

[0481] Step 7:

[0482] Input: Information from the acquired database, the answer of the generative AI model, the results of sentiment analysis, and the results of location analysis.

[0483] How it works: The server synthesizes this information and formats it into visual and auditory formats (e.g., text, diagrams, voice assistance).

[0484] Output: Formatted information.

[0485] Step 8:

[0486] Input: Formatted information.

[0487] How it works: The server sends the formatted information to the user's device.

[0488] Output: Information received by the user device.

[0489] Step 9:

[0490] Input: Information received by the user terminal.

[0491] How it works: The device parses the information it receives and displays it to the user in an appropriate format, which may include on-screen text, diagrams, or voice assistance.

[0492] Output: Information displayed to the user.

[0493] Step 10:

[0494] Input: User feedback.

[0495] How it works: The device gets feedback from the user and sends it to the server.

[0496] Output: The feedback received by the server.

[0497] In this way, a system is realized that responds to specific user problems and provides comprehensive information and support that takes into account the user's emotions and location information.

[0498] 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.

[0499] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0500] 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.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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).

[0508] 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.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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."

[0514] This system provides users with the necessary information quickly and accurately to deal with the various problems they may encounter. Below, we will explain in detail each component of this system and how it works.

[0515] System Overview

[0516] The system mainly includes the following components:

[0517] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0518] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0519] Database: A data storage system that stores information for troubleshooting.

[0520] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0521] How it works

[0522] Select a scenario and submit a request

[0523] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[0524] Based on the user's selection, the device generates and sends a request to the server, including the selected problem type and basic user information (such as location and language settings).

[0525] Information collection and analysis

[0526] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (for example, a list of allowances that can be applied for in the event of sudden hospitalization).

[0527] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[0528] The server analyzes the information and formats it in an appropriate format (text, graphics, audio) to be presented to the user.

[0529] Providing and Displaying Information

[0530] The server then sends the formatted information to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[0531] The device displays the received information on the user interface so that the user can visually confirm it, and also provides information audibly through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[0532] Specific examples

[0533] Example 1: How to apply for benefits in the event of sudden hospitalization

[0534] If the user selects "acute admission," the user will need information regarding the application for benefits.

[0535] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[0536] The server formats this information in diagram and text format and sends it to the user's terminal.

[0537] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0538] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0539] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[0540] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0541] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[0542] The server formats this information as text and illustrations and sends it to the user's terminal.

[0543] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[0544] In this way, the system can provide comprehensive support by quickly and accurately providing information on specific user problems.

[0545] The processing flow will be explained below.

[0546] Step 1:

[0547] Users launch the app and select the type of problem they are experiencing from the main menu.

[0548] Step 2:

[0549] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[0550] Step 3:

[0551] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[0552] Step 4:

[0553] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[0554] Step 5:

[0555] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[0556] Step 6:

[0557] The server formats the retrieved information and generated answers into visual (text, diagrams) and audible (voice-assisted) formats, such as a diagram of the benefits claim flow or steps in the repair procedure.

[0558] Step 7:

[0559] The server sends the formatted information to the user's terminal.

[0560] Step 8:

[0561] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, and, if necessary, voice assistance.

[0562] Step 9:

[0563] Users can check the information provided through their devices and take appropriate action.

[0564] Step 10:

[0565] (any)

[0566] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[0567] Step 11:

[0568] (any)

[0569] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model.

[0570] The above is the specific flow of processing of the program in this system.

[0571] Example 1

[0572] 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."

[0573] Conventional information provision systems have had difficulty in quickly and accurately providing information to address the various problems users face. Furthermore, there was a lack of systems that could provide information visually and audibly, which meant that users sometimes could not obtain sufficient information under certain circumstances. To solve these issues, a system that can comprehensively and flexibly respond to specific user requests is needed.

[0574] 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.

[0575] In this invention, the server includes a means for requesting data corresponding to the type of problem selected by the user from the server, a means for the server to receive the request and retrieve the corresponding data from the storage system, and a means for the server to generate an answer to the user's specific request using the generative AI model, thereby enabling the server to provide information quickly and accurately to the problem the user is facing.

[0576] "User" means an individual or organizational entity that seeks to obtain information using the system.

[0577] A "problem" is a specific challenge or situation a user faces, such as an emergency hospital stay or a device malfunction.

[0578] "Data" refers to the necessary information that the server retrieves from a storage system such as a database, including procedures and contact information necessary to resolve the user's problem.

[0579] A "server" is a computer system that has the ability to receive requests from users, retrieve data from a database, generate information using a generative AI model, and send it to the user's device.

[0580] A "request" is a data request that a user sends to the server via their terminal, and includes the type of question selected and basic information about the user.

[0581] A "storage system" is a database or other data storage device for storing data.

[0582] A "generative AI model" is an artificial intelligence technology used by the server to generate detailed answers to specific user requests.

[0583] "Textual information" means data in text form that is visually displayed to the user.

[0584] "Audio information" means data in audio format that is audibly presented to a user.

[0585] A "user terminal" is a device used by a user, such as a smartphone or tablet, that has the ability to communicate with a server and display information.

[0586] System Overview

[0587] This system is designed to provide the necessary information quickly and accurately to deal with the various problems users face. It mainly includes the following components:

[0588] 1. User terminal: A device such as a smartphone or tablet used by the user, which communicates with the server and displays information.

[0589] 2. Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0590] 3. Storage system: The data storage system where the data to address the problem is stored.

[0591] 4. Generative AI models: Artificial intelligence techniques for generating answers to specific user requests.

[0592] How it works

[0593] Select a scenario and submit a request

[0594] Users launch the app and select the type of problem they are facing from the main menu, such as "emergency hospitalization" or "smartphone breakdown."

[0595] Based on the user's selection, the device generates a request to the server, which includes the selected problem type and basic user information (such as location and language settings).

[0596] Data acquisition and analysis

[0597] The server determines the problem based on the received request and retrieves relevant data (for example, a list of allowances that can be applied for in the event of sudden hospitalization) from the storage system.

[0598] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[0599] For example, prompts include: "Where do I apply for benefits?", "Where is the nearest repair shop?", and "How do I contact you in an emergency?"

[0600] The server analyzes the acquired data and formats it into an appropriate format (text information, illustrations, audio information) to provide to the user.

[0601] Providing and Displaying Information

[0602] The server then sends the formatted data to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[0603] The device displays the received data on the user interface so that the user can visually confirm it, and also provides audible information through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[0604] Specific examples

[0605] Example 1: How to apply for benefits in the event of sudden hospitalization

[0606] If the user selects "Sudden Admission," information regarding the application for benefits is required.

[0607] The server retrieves information from the storage system, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures.

[0608] For example, prompts: "Where do I apply for benefits?", "What documents do I need to receive benefits?"

[0609] The server formats this information into diagrams and textual information and sends it to the user's terminal.

[0610] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0611] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0612] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[0613] The server obtains information from the storage system about basic troubleshooting steps for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0614] For example, prompts: "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[0615] The generative AI model generates answers to specific user questions and provides detailed instructions on how to deal with the problem.

[0616] The server formats this information into text and illustrations and sends it to the user's terminal.

[0617] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[0618] The above is an embodiment of the present invention, and the system can provide information quickly and accurately on specific problems of users and provide comprehensive support.

[0619] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0620] Processing flow

[0621] Step 1:

[0622] The user launches the app and selects the type of problem they are facing from the main menu.

[0623] Input: The type of problem the user selects (e.g., "Sudden hospitalization" or "Smartphone broken")

[0624] Specific operation: The user taps on the option displayed on the screen, which sends the selected question type to the device.

[0625] Step 2:

[0626] The device generates a request to the server based on the user's selection.

[0627] Input: User information such as the selected problem type, user location, and language preference.

[0628] Output: Generated request data

[0629] What happens: The device collects the selections and user information, formats the data, and sends it to the server as a request.

[0630] Step 3:

[0631] The server analyzes the incoming request and determines the type of problem it encounters.

[0632] Input: Request data sent from the terminal

[0633] Output: Search query based on issue type

[0634] What happens: The server analyzes the request and generates a search query to determine the type of problem.

[0635] Step 4:

[0636] The server retrieves the relevant data from the storage system.

[0637] Input: Search query based on issue type

[0638] Output: Relevant data (e.g., in case of sudden hospitalization, medical care-related data)

[0639] Specific operation: The server uses the generated search query to search for and retrieve the relevant data from the storage system.

[0640] Step 5:

[0641] The server uses a generative AI model to generate answers to specific user questions.

[0642] Input: relevant data obtained, specific user questions

[0643] Output: Detailed answers from a generative AI model

[0644] Specific operation: The server inputs the acquired data and the user's question as a prompt into a generative AI model (e.g., GPT-4) to generate a detailed answer.

[0645] Examples of prompts: "Where do I apply for benefits?", "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[0646] Step 6:

[0647] The server analyzes the acquired data and generated answers, and formats them into text and audio information.

[0648] Input: Response from the generative AI model, related data obtained

[0649] Output: Formatted text, illustrations, audio

[0650] Specific operation: The server analyzes the acquired data and the generated AI model's response, and formats it into text, charts, and audio data for delivery to the user. Formatting is done using HTML, CSS, JSON, etc.

[0651] Step 7:

[0652] The server sends the formatted data to the user's device.

[0653] Input: Formatted text, illustrations, audio information

[0654] Output: Data sent to the user's terminal

[0655] Specific operation: The server packets the formatted data and sends it to the user terminal.

[0656] Step 8:

[0657] The device displays the received data on the user interface and provides information using the voice assistant function.

[0658] Input: Text information, illustrations, and audio information sent from the server

[0659] Specific operation: The device analyzes the received data, displays text and illustrations on the screen, and uses TTS (Text-to-Speech) technology to provide audio guidance.

[0660] Users can see the information visually on the screen and hear more details through an audio guide.

[0661] The above are the specific processing steps of the system program.

[0662] (Application example 1)

[0663] 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."

[0664] Conventional troubleshooting systems often lack the functionality to provide users with prompt and appropriate responses to emergency situations, resulting in inconvenience. In particular, the methods of providing information to users with visual or speech impairments are limited, and comprehensive support is not provided. Furthermore, the lack of detailed explanations for specific user questions can increase anxiety when dealing with problems.

[0665] 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.

[0666] In this invention, the server includes: means for requesting information corresponding to a type of trouble selected by a user from the server; means for the server to receive the request and retrieve the corresponding information from a database; means for the server to generate answers to the user's specific questions using a generative AI model; means for the server to analyze the retrieved information and format it into visual and auditory formats; means for the server to send the formatted information to a user terminal; means for the user terminal to display the sent information to the user; emergency support means for the user to select an emergency situation and to provide countermeasures; and means for using a generative AI model to provide detailed explanations for the user's specific questions about the emergency situation. This allows the user to obtain quick and appropriate countermeasures when facing an emergency situation and receive comprehensive support using their vision and hearing.

[0667] The "means for requesting information corresponding to the type of trouble selected by the user from the server" is a function that allows the user to select a specific trouble they are facing and send detailed information about it as a request to the server.

[0668] "Means by which the server receives a request and retrieves the corresponding information from the database" refers to the function by which the server receives a request from a user and searches for and retrieves information based on that request from the database.

[0669] "Means for the server to use a generative AI model to generate answers to specific questions from users" refers to the function by which the server uses generative AI to create optimal answers to specific questions from users.

[0670] "Means for analyzing information acquired by the server and arranging it into visual and auditory formats" refers to the function by which the server analyzes information acquired and converts it into a format suitable for visual (text and illustrations) and auditory (audio) perception.

[0671] The "means for transmitting information formatted by the server to the user terminal" is a function for transmitting information formatted by the server in visual and auditory form to the user terminal.

[0672] "Means for the user terminal to display the transmitted information to the user" refers to a function by which the user terminal displays the information transmitted from the server so that the user can confirm it.

[0673] "Emergency support means that allows users to select an emergency situation and provides countermeasures" is a function that allows users to select an emergency situation through an application and provides appropriate countermeasures according to the situation.

[0674] "Means of using a generative AI model to provide detailed explanations in response to specific questions about a user's emergency situation" refers to a function that uses a generative AI model to provide specific and detailed explanations in response to questions about a user's emergency situation.

[0675] This invention is a system that provides a user with a prompt and appropriate response to an emergency situation they find themselves in. The components of this system and their operation will be described in detail below.

[0676] System Overview

[0677] The system mainly includes the following components:

[0678] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0679] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0680] Database: A data storage system that stores information for troubleshooting.

[0681] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0682] How it works

[0683] User selects emergency situation

[0684] The user launches the app and selects the type of emergency situation they are facing (e.g., burglary, fire, traffic accident).

[0685] Send request

[0686] Based on the selection, the user device generates and sends a request to the server, which includes the selected emergency situation type and basic user information (such as location and language settings).

[0687] Information Acquisition and Analysis

[0688] The server determines the relevant emergency situation based on the received request and retrieves relevant information from a database (evacuation routes, emergency contacts, initial emergency procedures, etc.) The server also uses a generative AI model to generate detailed explanations in response to the user's specific questions.

[0689] Formatting and providing information

[0690] The server analyzes the acquired information and formats it into an appropriate format (text, illustrations, or voice) for presentation to the user. The server then sends the formatted information to the user's device. The user's device then presents the received information to the user visually (text or illustrations) and audibly (voice assistance).

[0691] Specific names of hardware and software to be used

[0692] Hardware: Smartphone

[0693] Server: Backend using the Flask framework

[0694] Database: SQLite

[0695] Generative AI model: TensorFlow

[0696] Example of operation

[0697] Example 1: Providing countermeasures in case of fire

[0698] If the user selects "fire," the server retrieves information from the database about evacuation routes, emergency contacts, and first aid procedures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[0699] Example prompt sentence:

[0700] "What is the safest way to escape in the event of a fire?"

[0701] Example of a generated answer:

[0702] "If a fire breaks out, immediately check the escape route and evacuate to a safe place. It is safest to move away from the source of the fire and stay as low as possible. While evacuating, cover your nose and mouth with a wet towel to ensure proper breathing."

[0703] Example 2: Providing countermeasures in case of burglary

[0704] If the user selects "burglary," the server retrieves information from the database about the necessary contacts and initial response measures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[0705] Example prompt sentence:

[0706] "If a burglar breaks in, what's the first thing you should do?"

[0707] Example of a generated answer:

[0708] "If a burglar breaks in, contact the police immediately and seek refuge in a safe location. Do not enter the residence."

[0709] In this way, the present invention allows users to obtain prompt and appropriate responses when faced with an emergency situation, and provides comprehensive support utilizing visual and auditory senses.

[0710] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0711] Step 1:

[0712] The user launches the app and selects the type of emergency, choosing from options such as "fire," "burglary," or "traffic accident." The input includes the user's selection, and the output generates a request with the selected emergency. The specific action involves the user tapping on the menu on the screen.

[0713] Step 2:

[0714] The user device sends a request for the selected emergency situation to the server, including the user's selection along with basic information such as location and language preference. The user's selection and basic information are used as inputs to generate the request. The output is the formation of a request that is sent to the server. Specific operations include the device communicating with the server.

[0715] Step 3:

[0716] The server analyzes the received request and retrieves information about the corresponding emergency situation from the database. At this stage, the request information is used as input to generate a database search query. Information is retrieved from the database using the database search query as input, and a retrieved information set is generated as output. Specific operations include database search and information extraction within the server.

[0717] Step 4:

[0718] The server uses the generative AI model to generate detailed answers to the user's specific questions. The input includes information about the emergency situation and basic information about the user, and the generative AI model uses this information to create a prompt. The output is an answer to the user's specific question. The specific operation involves a series of calculations in which the AI ​​model processes the prompt and generates an answer.

[0719] Step 5:

[0720] The server analyzes the information it receives and formats it into visual and auditory formats. It uses information retrieved from a database and answers from a generative AI model as input. After analysis and formatting, it generates an information set suitable for visual and auditory use as output. Specific operations include generating text data, image data, and creating audio files.

[0721] Step 6:

[0722] The server transmits the formatted information to the user terminal. The visual and auditory formatted information set is used as input, and a data packet is formed as output and transmitted to the user terminal. Specific operations include transmitting data from the server to the user terminal.

[0723] Step 7:

[0724] The user device displays the received information to the user. The input is the visually and audibly formatted information received from the server, and the output is information that the user can confirm visually and audibly. Specific operations include displaying text and illustrations on the screen and, if necessary, playing explanations through a voice assistant.

[0725] 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.

[0726] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation in a form that incorporates an emotion engine.

[0727] System Overview

[0728] The system mainly includes the following components:

[0729] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0730] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, and emotion engine.

[0731] Database: A data storage system that stores information for troubleshooting.

[0732] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0733] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[0734] How it works

[0735] Select a scenario and submit a request

[0736] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[0737] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[0738] Information collection and analysis

[0739] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (e.g., a list of allowances that can be applied for in the event of sudden hospitalization).

[0740] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[0741] The emotion engine recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information and assistance to help the user relax.

[0742] Providing and Displaying Information

[0743] The server integrates the acquired information and the output from the emotion engine and formats it into visual (text, diagrams) and auditory (voice assistance) formats, such as providing a diagram of the benefit application process or instructions on how to relax.

[0744] The server sends the formatted information to the user's terminal.

[0745] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[0746] Specific examples

[0747] Example 1: How to apply for benefits in the event of sudden hospitalization

[0748] If the user selects "acute admission," the user will need information regarding the application for benefits.

[0749] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[0750] The emotion engine recognizes the user's emotions and provides information to encourage relaxation if the user is feeling stressed.

[0751] The server formats this information into diagrams and text, and sends it to the user's device along with instructions on relaxation techniques.

[0752] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0753] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0754] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[0755] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0756] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[0757] The emotion engine recognizes the user's emotions and provides calming advice if the user is feeling anxious.

[0758] The server formats this information as text and illustrations and sends it to the user's terminal.

[0759] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[0760] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[0761] The processing flow will be explained below.

[0762] Step 1:

[0763] Users launch the app and select the type of problem they are experiencing from the main menu.

[0764] Step 2:

[0765] Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information (location information, language settings, device status information, etc.) and sends it to the server.

[0766] Step 3:

[0767] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[0768] Step 4:

[0769] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[0770] Step 5:

[0771] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[0772] Step 6:

[0773] The user device uses a camera and microphone to capture the user's facial expressions and tone of voice and transmit them to the emotion engine.

[0774] Step 7:

[0775] The emotion engine analyzes the user's emotion from the received data and sends the result to the server (e.g., the user is feeling anxious).

[0776] Step 8:

[0777] The server integrates information from the emotion engine and generates appropriate information and support based on the user's emotions. For example, if the user is feeling anxious, it can include relaxation techniques and emergency contact information.

[0778] Step 9:

[0779] The server formats the information into visual (text, diagrams) and audible (voice-assisted) formats.

[0780] Step 10:

[0781] The server sends the formatted information to the user's terminal.

[0782] Step 11:

[0783] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[0784] Step 12:

[0785] Users can check the information provided through their devices and take appropriate action.

[0786] Step 13:

[0787] (any)

[0788] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[0789] Step 14:

[0790] (any)

[0791] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model and emotion engine.

[0792] The above is the specific processing flow in this system incorporating the emotion engine.

[0793] Example 2

[0794] 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."

[0795] Conventional information provision systems have been limited in the information they provide when dealing with the various problems users face. Furthermore, they provide only uniform information without considering the user's emotions, resulting in a lack of support appropriate to the user's situation. This makes it difficult for users to receive adequate support in situations where they feel anxious or stressed. The purpose of this invention is to solve these problems and provide a system that provides users with prompt and accurate information and support tailored to their emotions.

[0796] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring information corresponding to the type of trouble selected by the user from a database, means for generating answers to specific questions using a generative AI model, means for analyzing the user's emotions using an emotion engine and generating response information, and means for integrating the acquired information and output from the emotion engine and shaping them into visual and auditory formats. This allows the user to receive prompt and accurate information according to the type of trouble and appropriate support according to their emotional state.

[0797] "User" refers to any individual or entity that uses the System.

[0798] "Server" refers to a computer system that receives requests from users and processes and provides information.

[0799] A "request" refers to a request that a user makes by entering information such as the type of problem and sending it to the server.

[0800] "Database" refers to a data storage system in which information corresponding to a problem is stored.

[0801] A "generative AI model" refers to a system that uses artificial intelligence technology to generate answers to specific user questions.

[0802] An "emotion engine" refers to a system that recognizes the user's emotions and responds accordingly.

[0803] "Visual format" refers to the way information is presented, such as in text or illustrations.

[0804] "Auditory format" refers to methods of providing information in the form of voice assistance or the like.

[0805] "User terminal" refers to a device used by a user, such as a smartphone or tablet.

[0806] "Format" refers to the process of integrating and converting acquired information into visual and auditory form.

[0807] "Trouble" refers to problems or difficult situations that users face.

[0808] A "prompt sentence" refers to a text sentence that is input into a generative AI model.

[0809] This invention relates to a system that provides users with the information they need to quickly and accurately respond to various problems they encounter, while also recognizing and adapting to their emotions. Specifically, this system is realized by linking the following components: a user terminal, a server, a database, a generative AI model, and an emotion engine.

[0810] Hardware and Software Configuration

[0811] User terminal: A device such as a smartphone or tablet that communicates with the server and displays information.

[0812] Server: A computer system that receives requests from users and generates and provides appropriate information using a database, generative AI model, and emotion engine.

[0813] Database: A data storage system that stores information for troubleshooting.

[0814] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0815] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[0816] Operational Overview

[0817] 1. The user launches the app on their device, such as a smartphone or tablet, and selects the type of problem they are facing from the main menu. For example, "sudden hospitalization" or "smartphone breakdown."

[0818] 2. Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location and language settings) and sends it to the server.

[0819] 3. The server analyzes the received request, determines the corresponding problem scenario, and retrieves relevant information from the database, such as how to apply for benefits for sudden hospitalization or how to contact the user if their smartphone breaks down.

[0820] 4. The server uses the generative AI model to generate detailed answers and explanations for the user's specific questions. For example, the prompt "Please tell me how to apply for benefits in case of sudden hospitalization" is input to the generative AI model.

[0821] 5. The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates additional information and advice to help them relax.

[0822] 6. The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[0823] 7. The server sends the formatted information to the user device, which parses it and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, or voice assistance.

[0824] Specific examples

[0825] Example 1: How to apply for benefits in the event of sudden hospitalization

[0826] The user selects "urgent hospitalization."

[0827] The device generates a request including the scenario ID and basic information and sends it to the server.

[0828] The server receives the request and retrieves information from the database, such as how to apply for emergency hospitalization benefits, the necessary documents, and where to apply. It also uses a generative AI model to provide more specific explanations and procedures.

[0829] The emotion engine recognizes the user's stress and provides information to encourage relaxation.

[0830] The server formats the information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques.

[0831] The device displays the information and uses voice assistance to explain the details.

[0832] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0833] The user selects "Smartphone broken."

[0834] The device generates a request including the scenario ID and basic information and sends it to the server.

[0835] The server receives the request and retrieves information from the database about basic troubleshooting steps for when your smartphone breaks down, alternative contact methods (such as the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[0836] Using a generative AI model, it generates answers to specific user questions and provides additional information, such as "where is the nearest repair shop?" or "how to contact someone in an emergency."

[0837] The emotion engine recognizes when the user is feeling anxious and provides advice to help them calm down.

[0838] The server formats the information as text and illustrations and sends it to the user's terminal.

[0839] The device displays the information and explains it using voice assistance.

[0840] In this way, the system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[0841] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0842] Step 1: Select the user's problem and submit a request

[0843] Users launch the app on their smartphone, tablet, or other device and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction."

[0844] Input: Type of problem, basic user information (location, language settings)

[0845] Based on the user's selection, the device generates a request including the scenario ID and basic information about the user and sends it to the server.

[0846] Output: Request data sent to the server (scenario ID, user information)

[0847] Specific operation: When the user taps the selection button on the app screen, the device automatically generates request data (JSON format) and sends it to the server.

[0848] Step 2: Receiving and Parsing the Request

[0849] The server receives the request sent from the device, analyzes the request data, extracts the scenario ID and basic user information, and starts processing.

[0850] Input: Request data (scenario ID, user information)

[0851] Output: Analysis results of scenario ID and user information

[0852] Specific operation: The server analyzes the received request data, reads the scenario ID and the user's basic information (location, language settings), and passes it to the next processing step.

[0853] Step 3: Obtaining relevant information

[0854] The server retrieves information related to the problem from the database. For example, in the case of "sudden hospitalization," it retrieves information on how to apply for medical treatment, and in the case of "smartphone malfunction," it retrieves information on repair procedures and alternative contact methods.

[0855] Input: Scenario ID, user information

[0856] Output: Related information (application method, required documents, repair method, etc.)

[0857] Specific operation: The server generates an SQL query, sends it to the database to retrieve the relevant information, and loads the retrieved results into memory.

[0858] Step 4: Generative AI model generates answers

[0859] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation, for example, by entering a prompt such as "How do I apply for benefits in case of sudden hospitalization?"

[0860] Input: User question, related information

[0861] Output: Answer from the generative AI model

[0862] Specific operation: The server generates a prompt based on the user's question and sends it to the generative AI model, which then generates a specific answer in text and returns it to the server.

[0863] Step 5: Emotion engine analysis and response

[0864] The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates information and advice to help them relax.

[0865] Input: User response data (voice, text)

[0866] Output: Sentiment analysis results and corresponding information

[0867] Specific operation: The emotion engine determines the user's emotional state through voice recognition and text analysis, generates messages and actions according to that state, and returns them to the server.

[0868] Step 6: Integrate and format information

[0869] The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[0870] Input: relevant information, answers from generative AI models, and response information from emotion engines

[0871] Output: Formatted information (visual and auditory)

[0872] Specific operation: The server formats various information into HTML or JSON format, generates audio files as needed, and creates a data package to send to the user's device.

[0873] Step 7: Send and view information

[0874] The server then sends the formatted information to the user device, which then parses it and displays it in an appropriate format in a user interface, such as on-screen text, graphics, or voice assistance.

[0875] Input: Formatted information

[0876] Output: What is displayed on the user screen

[0877] Specific operation: The user device analyzes the received data, displays the information in the GUI component, and plays the voice assistance from the speaker.

[0878] (Application example 2)

[0879] 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."

[0880] Existing systems can provide appropriate information for problems users encounter, but they do not adequately consider the user's emotions or location information. This can result in stress for users, and it can take a long time for them to obtain appropriate information. Furthermore, even in physical store shopping experiences, there is a lack of functionality that considers the user's emotions and suggests optimal products. Therefore, there is a need for the development of a system that can respond more quickly to individual user needs and improve the experience.

[0881] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0882] In this invention, the server includes an emotion recognition means for analyzing the user's emotions and providing information and services according to the user's emotional state, a location information analysis means for analyzing the user's location information and recommending products and services suitable for the user's current location, and a means for generating answers to the user's specific questions using a generative AI model, thereby enabling the provision of information based on the user's emotions and location information.

[0883] "User device" means an electronic device used by a user to receive information, including a smartphone or tablet.

[0884] A "server" is a computer system that receives and responds to requests from users, analyzes data, and generates information.

[0885] A "database" is a data storage system where the required information is stored.

[0886] A "generative AI model" is an artificial intelligence technology that generates answers to specific user questions.

[0887] "Emotion recognition means" is a technology that recognizes the user's emotions and responds accordingly.

[0888] "Location information analysis means" is a technology that analyzes the user's current location and provides information and services based on that location.

[0889] "Means for formatting information into visual and auditory form" refers to the means by which the server converts the information it obtains into a format that is easy for the user to see or hear.

[0890] "Emotional state" refers to the emotional state of the user, and includes specific emotions such as stress or joy.

[0891] "Multimodal technology" is a technology that provides information by combining multiple sensory information (visual, auditory, etc.).

[0892] "Feedback" refers to information such as opinions, impressions, and ratings provided by users.

[0893] "Type of trouble" refers to the specific type of problem or difficulty the user faces, such as sudden hospitalization or smartphone breakdown.

[0894] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation, in an embodiment that incorporates an emotion engine and a location information analysis engine.

[0895] System Components

[0896] The system mainly includes the following components:

[0897] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0898] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, emotion recognition means, and location information analysis means.

[0899] Database: A data storage system that stores information for troubleshooting.

[0900] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0901] Emotion recognition means: Technology that recognizes the user's emotions and responds accordingly.

[0902] Location information analysis means: Technology for providing appropriate information and services based on the user's location information.

[0903] How it works

[0904] Select a scenario and submit a request

[0905] The user launches the app and selects the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction." Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information and sends it to the server.

[0906] Information collection and analysis

[0907] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database. If the server includes a specific question from the user, it uses a generative AI model to generate a detailed answer or explanation for the question. The emotion recognition means recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information or assistance to help the user relax. The location information analysis means analyzes the user's current location and recommends products and services based on that location.

[0908] Providing and Displaying Information

[0909] The server combines the acquired information and the output from the emotion recognition and location analysis means and formats it into visual (text, illustrations) and auditory (voice assistance) formats. For example, it may provide an illustration of the benefit application process or instructions on how to relax. The server then sends the formatted information to the user's device. The device then analyzes the information received from the server and displays it in the appropriate format in the user interface. This may include on-screen text, illustrations, or voice assistance.

[0910] Hardware and Software Use Cases

[0911] Hardware: Smartphone (user device), server

[0912] software:

[0913] Face Recognition: OpenCV

[0914] Speech analysis: Google Cloud Speech-to-Text

[0915] Sentiment analysis: IBM Watson Natural Language Understanding

[0916] Database: MySQL

[0917] Generative AI model: OpenAI GPT-4

[0918] Emotion Recognition Method: Custom TensorFlow Model

[0919] Location information analysis means: GNSS module and location information API

[0920] User Interface: React Native

[0921] Voice Assistance: Google Text-to-Speech API

[0922] Specific examples

[0923] Example 1: How to apply for benefits in the event of sudden hospitalization

[0924] If the user selects "Sudden Hospitalization," the user will need information regarding applying for benefits. The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures. The emotion recognition means recognizes the user's emotions, and if the user is feeling stressed, it also provides information encouraging relaxation. The server formats this information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques. The device displays the application flow with diagrams and a list of required documents, and uses voice assistance to explain the details of the procedure.

[0925] Example 2: Ensuring a means of communication in case of smartphone malfunction

[0926] If the user selects "Smartphone broken," they will need information on alternative contact methods and repair procedures. The server retrieves information from the database on basic steps to take when a smartphone breaks down, alternative contact methods, and repair procedures. The generative AI model generates answers to the user's specific questions, providing supplementary explanations such as "where is the nearest repair shop" and "how to contact in an emergency." The emotion recognition means recognizes the user's emotions and provides advice to help them calm down if they are panicking. The server formats this information as text and illustrations and sends it to the user's device. The device displays the repair flow and a list of alternative contact methods, and explains emergency procedures using voice assistance.

[0927] Prompt Sentence Examples

[0928] "A user is asking about a specific product. Please answer the following questions appropriately:

[0929] For example: "Where do these bananas come from?"

[0930] ---

[0931] answer:"

[0932] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

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

[0934] Step 1:

[0935] Input: The user launches the app on their device and selects the type of problem they are experiencing from the main menu.

[0936] Action: The user taps the Select button.

[0937] Output: The device generates a request containing the selection (scenario ID) and basic user information (such as location and language preference).

[0938] Step 2:

[0939] Input: The request made by the device.

[0940] How it works: The device sends the generated request to the server, which receives the request and analyzes the user's needs.

[0941] Output: The server determines the corresponding trouble scenario and obtains the analysis results.

[0942] Step 3:

[0943] Input: The scenario ID of the problem identified by the server.

[0944] How it works: The server queries the database to retrieve relevant information (e.g., a list of benefits available for emergency hospitalization).

[0945] Output: Information retrieved from the database.

[0946] Step 4:

[0947] Input: A specific question from the user (optional).

[0948] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate detailed answers and explanations for questions.

[0949] Output: The generated answer and / or explanation.

[0950] Step 5:

[0951] Input: User's facial image and voice data.

[0952] How it works: The server analyzes the user's emotions using emotion recognition tools (e.g. IBM Watson, OpenCV).

[0953] Output: The user's emotional state (e.g., stress, joy).

[0954] Step 6:

[0955] Input: The user's location.

[0956] How it works: The server uses location analysis tools (e.g., GNSS module, location API) to analyze the current location and recommend suitable products and services.

[0957] Output: Information about the recommended product or service.

[0958] Step 7:

[0959] Input: Information from the acquired database, the answer of the generative AI model, the results of sentiment analysis, and the results of location analysis.

[0960] How it works: The server synthesizes this information and formats it into visual and auditory formats (e.g., text, diagrams, voice assistance).

[0961] Output: Formatted information.

[0962] Step 8:

[0963] Input: Formatted information.

[0964] How it works: The server sends the formatted information to the user's device.

[0965] Output: Information received by the user device.

[0966] Step 9:

[0967] Input: Information received by the user terminal.

[0968] How it works: The device parses the information it receives and displays it to the user in an appropriate format, which may include on-screen text, diagrams, or voice assistance.

[0969] Output: Information displayed to the user.

[0970] Step 10:

[0971] Input: User feedback.

[0972] How it works: The device gets feedback from the user and sends it to the server.

[0973] Output: The feedback received by the server.

[0974] In this way, a system is realized that responds to specific user problems and provides comprehensive information and support that takes into account the user's emotions and location information.

[0975] 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.

[0976] 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.

[0977] 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.

[0978] [Third embodiment]

[0979] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0980] 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.

[0981] 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).

[0982] 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.

[0983] 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.

[0984] 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).

[0985] 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.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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."

[0991] This system provides users with the necessary information quickly and accurately to deal with the various problems they may encounter. Below, we will explain in detail each component of this system and how it works.

[0992] System Overview

[0993] The system mainly includes the following components:

[0994] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[0995] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[0996] Database: A data storage system that stores information for troubleshooting.

[0997] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[0998] How it works

[0999] Select a scenario and submit a request

[1000] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[1001] Based on the user's selection, the device generates and sends a request to the server, including the selected problem type and basic user information (such as location and language settings).

[1002] Information collection and analysis

[1003] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (for example, a list of allowances that can be applied for in the event of sudden hospitalization).

[1004] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[1005] The server analyzes the information and formats it in an appropriate format (text, graphics, audio) to be presented to the user.

[1006] Providing and Displaying Information

[1007] The server then sends the formatted information to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[1008] The device displays the received information on the user interface so that the user can visually confirm it, and also provides information audibly through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[1009] Specific examples

[1010] Example 1: How to apply for benefits in the event of sudden hospitalization

[1011] If the user selects "acute admission," the user will need information regarding the application for benefits.

[1012] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[1013] The server formats this information in diagram and text format and sends it to the user's terminal.

[1014] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1015] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1016] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[1017] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1018] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[1019] The server formats this information as text and illustrations and sends it to the user's terminal.

[1020] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[1021] In this way, the system can provide comprehensive support by quickly and accurately providing information on specific user problems.

[1022] The processing flow will be explained below.

[1023] Step 1:

[1024] Users launch the app and select the type of problem they are experiencing from the main menu.

[1025] Step 2:

[1026] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[1027] Step 3:

[1028] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[1029] Step 4:

[1030] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[1031] Step 5:

[1032] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[1033] Step 6:

[1034] The server formats the retrieved information and generated answers into visual (text, diagrams) and audible (voice-assisted) formats, such as a diagram of the benefits claim flow or steps in the repair procedure.

[1035] Step 7:

[1036] The server sends the formatted information to the user's terminal.

[1037] Step 8:

[1038] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, and, if necessary, voice assistance.

[1039] Step 9:

[1040] Users can check the information provided through their devices and take appropriate action.

[1041] Step 10:

[1042] (any)

[1043] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[1044] Step 11:

[1045] (any)

[1046] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model.

[1047] The above is the specific flow of processing of the program in this system.

[1048] Example 1

[1049] 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."

[1050] Conventional information provision systems have had difficulty in quickly and accurately providing information to address the various problems users face. Furthermore, there was a lack of systems that could provide information visually and audibly, which meant that users sometimes could not obtain sufficient information under certain circumstances. To solve these issues, a system that can comprehensively and flexibly respond to specific user requests is needed.

[1051] 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.

[1052] In this invention, the server includes a means for requesting data corresponding to the type of problem selected by the user from the server, a means for the server to receive the request and retrieve the corresponding data from the storage system, and a means for the server to generate an answer to the user's specific request using the generative AI model, thereby enabling the server to provide information quickly and accurately to the problem the user is facing.

[1053] "User" means an individual or organizational entity that seeks to obtain information using the system.

[1054] A "problem" is a specific challenge or situation a user faces, such as an emergency hospital stay or a device malfunction.

[1055] "Data" refers to the necessary information that the server retrieves from a storage system such as a database, including procedures and contact information necessary to resolve the user's problem.

[1056] A "server" is a computer system that has the ability to receive requests from users, retrieve data from a database, generate information using a generative AI model, and send it to the user's device.

[1057] A "request" is a data request that a user sends to the server via their terminal, and includes the type of question selected and basic information about the user.

[1058] A "storage system" is a database or other data storage device for storing data.

[1059] A "generative AI model" is an artificial intelligence technology used by the server to generate detailed answers to specific user requests.

[1060] "Textual information" means data in text form that is visually displayed to the user.

[1061] "Audio information" means data in audio format that is audibly presented to a user.

[1062] A "user terminal" is a device used by a user, such as a smartphone or tablet, that has the ability to communicate with a server and display information.

[1063] System Overview

[1064] This system is designed to provide the necessary information quickly and accurately to deal with the various problems users face. It mainly includes the following components:

[1065] 1. User terminal: A device such as a smartphone or tablet used by the user, which communicates with the server and displays information.

[1066] 2. Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[1067] 3. Storage system: The data storage system where the data to address the problem is stored.

[1068] 4. Generative AI models: Artificial intelligence techniques for generating answers to specific user requests.

[1069] How it works

[1070] Select a scenario and submit a request

[1071] Users launch the app and select the type of problem they are facing from the main menu, such as "emergency hospitalization" or "smartphone breakdown."

[1072] Based on the user's selection, the device generates a request to the server, which includes the selected problem type and basic user information (such as location and language settings).

[1073] Data acquisition and analysis

[1074] The server determines the problem based on the received request and retrieves relevant data (for example, a list of allowances that can be applied for in the event of sudden hospitalization) from the storage system.

[1075] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[1076] For example, prompts include: "Where do I apply for benefits?", "Where is the nearest repair shop?", and "How do I contact you in an emergency?"

[1077] The server analyzes the acquired data and formats it into an appropriate format (text information, illustrations, audio information) to provide to the user.

[1078] Providing and Displaying Information

[1079] The server then sends the formatted data to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[1080] The device displays the received data on the user interface so that the user can visually confirm it, and also provides audible information through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[1081] Specific examples

[1082] Example 1: How to apply for benefits in the event of sudden hospitalization

[1083] If the user selects "Sudden Admission," information regarding the application for benefits is required.

[1084] The server retrieves information from the storage system, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures.

[1085] For example, prompts: "Where do I apply for benefits?", "What documents do I need to receive benefits?"

[1086] The server formats this information into diagrams and textual information and sends it to the user's terminal.

[1087] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1088] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1089] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[1090] The server obtains information from the storage system about basic troubleshooting steps for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1091] For example, prompts: "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[1092] The generative AI model generates answers to specific user questions and provides detailed instructions on how to deal with the problem.

[1093] The server formats this information into text and illustrations and sends it to the user's terminal.

[1094] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[1095] The above is an embodiment of the present invention, and the system can provide information quickly and accurately on specific problems of users and provide comprehensive support.

[1096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1097] Processing flow

[1098] Step 1:

[1099] The user launches the app and selects the type of problem they are facing from the main menu.

[1100] Input: The type of problem the user selects (e.g., "Sudden hospitalization" or "Smartphone broken")

[1101] Specific operation: The user taps on the option displayed on the screen, which sends the selected question type to the device.

[1102] Step 2:

[1103] The device generates a request to the server based on the user's selection.

[1104] Input: User information such as the selected problem type, user location, and language preference.

[1105] Output: Generated request data

[1106] What happens: The device collects the selections and user information, formats the data, and sends it to the server as a request.

[1107] Step 3:

[1108] The server analyzes the incoming request and determines the type of problem it encounters.

[1109] Input: Request data sent from the terminal

[1110] Output: Search query based on issue type

[1111] What happens: The server analyzes the request and generates a search query to determine the type of problem.

[1112] Step 4:

[1113] The server retrieves the relevant data from the storage system.

[1114] Input: Search query based on issue type

[1115] Output: Relevant data (e.g., in case of sudden hospitalization, medical care-related data)

[1116] Specific operation: The server uses the generated search query to search for and retrieve the relevant data from the storage system.

[1117] Step 5:

[1118] The server uses a generative AI model to generate answers to specific user questions.

[1119] Input: relevant data obtained, specific user questions

[1120] Output: Detailed answers from a generative AI model

[1121] Specific operation: The server inputs the acquired data and the user's question as a prompt into a generative AI model (e.g., GPT-4) to generate a detailed answer.

[1122] Examples of prompts: "Where do I apply for benefits?", "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[1123] Step 6:

[1124] The server analyzes the acquired data and generated answers, and formats them into text and audio information.

[1125] Input: Response from the generative AI model, related data obtained

[1126] Output: Formatted text, illustrations, audio

[1127] Specific operation: The server analyzes the acquired data and the generated AI model's response, and formats it into text, charts, and audio data for delivery to the user. Formatting is done using HTML, CSS, JSON, etc.

[1128] Step 7:

[1129] The server sends the formatted data to the user's device.

[1130] Input: Formatted text, illustrations, audio information

[1131] Output: Data sent to the user's terminal

[1132] Specific operation: The server packets the formatted data and sends it to the user terminal.

[1133] Step 8:

[1134] The device displays the received data on the user interface and provides information using the voice assistant function.

[1135] Input: Text information, illustrations, and audio information sent from the server

[1136] Specific operation: The device analyzes the received data, displays text and illustrations on the screen, and uses TTS (Text-to-Speech) technology to provide audio guidance.

[1137] Users can see the information visually on the screen and hear more details through an audio guide.

[1138] The above are the specific processing steps of the system program.

[1139] (Application example 1)

[1140] 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."

[1141] Conventional troubleshooting systems often lack the functionality to provide users with prompt and appropriate responses to emergency situations, resulting in inconvenience. In particular, the methods of providing information to users with visual or speech impairments are limited, and comprehensive support is not provided. Furthermore, the lack of detailed explanations for specific user questions can increase anxiety when dealing with problems.

[1142] 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.

[1143] In this invention, the server includes: means for requesting information corresponding to a type of trouble selected by a user from the server; means for the server to receive the request and retrieve the corresponding information from a database; means for the server to generate answers to the user's specific questions using a generative AI model; means for the server to analyze the retrieved information and format it into visual and auditory formats; means for the server to send the formatted information to a user terminal; means for the user terminal to display the sent information to the user; emergency support means for the user to select an emergency situation and to provide countermeasures; and means for using a generative AI model to provide detailed explanations for the user's specific questions about the emergency situation. This allows the user to obtain quick and appropriate countermeasures when facing an emergency situation and receive comprehensive support using their vision and hearing.

[1144] The "means for requesting information corresponding to the type of trouble selected by the user from the server" is a function that allows the user to select a specific trouble they are facing and send detailed information about it as a request to the server.

[1145] "Means by which the server receives a request and retrieves the corresponding information from the database" refers to the function by which the server receives a request from a user and searches for and retrieves information based on that request from the database.

[1146] "Means for the server to use a generative AI model to generate answers to specific questions from users" refers to the function by which the server uses generative AI to create optimal answers to specific questions from users.

[1147] "Means for analyzing information acquired by the server and arranging it into visual and auditory formats" refers to the function by which the server analyzes information acquired and converts it into a format suitable for visual (text and illustrations) and auditory (audio) perception.

[1148] The "means for transmitting information formatted by the server to the user terminal" is a function for transmitting information formatted by the server in visual and auditory form to the user terminal.

[1149] "Means for the user terminal to display the transmitted information to the user" refers to a function by which the user terminal displays the information transmitted from the server so that the user can confirm it.

[1150] "Emergency support means that allows users to select an emergency situation and provides countermeasures" is a function that allows users to select an emergency situation through an application and provides appropriate countermeasures according to the situation.

[1151] "Means of using a generative AI model to provide detailed explanations in response to specific questions about a user's emergency situation" refers to a function that uses a generative AI model to provide specific and detailed explanations in response to questions about a user's emergency situation.

[1152] This invention is a system that provides a user with a prompt and appropriate response to an emergency situation they find themselves in. The components of this system and their operation will be described in detail below.

[1153] System Overview

[1154] The system mainly includes the following components:

[1155] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1156] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[1157] Database: A data storage system that stores information for troubleshooting.

[1158] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1159] How it works

[1160] User selects emergency situation

[1161] The user launches the app and selects the type of emergency situation they are facing (e.g., burglary, fire, traffic accident).

[1162] Send request

[1163] Based on the selection, the user device generates and sends a request to the server, which includes the selected emergency situation type and basic user information (such as location and language settings).

[1164] Information Acquisition and Analysis

[1165] The server determines the relevant emergency situation based on the received request and retrieves relevant information from a database (evacuation routes, emergency contacts, initial emergency procedures, etc.) The server also uses a generative AI model to generate detailed explanations in response to the user's specific questions.

[1166] Formatting and providing information

[1167] The server analyzes the acquired information and formats it into an appropriate format (text, illustrations, or voice) for presentation to the user. The server then sends the formatted information to the user's device. The user's device then presents the received information to the user visually (text or illustrations) and audibly (voice assistance).

[1168] Specific names of hardware and software to be used

[1169] Hardware: Smartphone

[1170] Server: Backend using the Flask framework

[1171] Database: SQLite

[1172] Generative AI model: TensorFlow

[1173] Example of operation

[1174] Example 1: Providing countermeasures in case of fire

[1175] If the user selects "fire," the server retrieves information from the database about evacuation routes, emergency contacts, and first aid procedures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[1176] Example prompt sentence:

[1177] "What is the safest way to escape in the event of a fire?"

[1178] Example of a generated answer:

[1179] "If a fire breaks out, immediately check the escape route and evacuate to a safe place. It is safest to move away from the source of the fire and stay as low as possible. While evacuating, cover your nose and mouth with a wet towel to ensure proper breathing."

[1180] Example 2: Providing countermeasures in case of burglary

[1181] If the user selects "burglary," the server retrieves information from the database about the necessary contacts and initial response measures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[1182] Example prompt sentence:

[1183] "If a burglar breaks in, what's the first thing you should do?"

[1184] Example of a generated answer:

[1185] "If a burglar breaks in, contact the police immediately and seek refuge in a safe location. Do not enter the residence."

[1186] In this way, the present invention allows users to obtain prompt and appropriate responses when faced with an emergency situation, and provides comprehensive support utilizing visual and auditory senses.

[1187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1188] Step 1:

[1189] The user launches the app and selects the type of emergency, choosing from options such as "fire," "burglary," or "traffic accident." The input includes the user's selection, and the output generates a request with the selected emergency. The specific action involves the user tapping on the menu on the screen.

[1190] Step 2:

[1191] The user device sends a request for the selected emergency situation to the server, including the user's selection along with basic information such as location and language preference. The user's selection and basic information are used as inputs to generate the request. The output is the formation of a request that is sent to the server. Specific operations include the device communicating with the server.

[1192] Step 3:

[1193] The server analyzes the received request and retrieves information about the corresponding emergency situation from the database. At this stage, the request information is used as input to generate a database search query. Information is retrieved from the database using the database search query as input, and a retrieved information set is generated as output. Specific operations include database search and information extraction within the server.

[1194] Step 4:

[1195] The server uses the generative AI model to generate detailed answers to the user's specific questions. The input includes information about the emergency situation and basic information about the user, and the generative AI model uses this information to create a prompt. The output is an answer to the user's specific question. The specific operation involves a series of calculations in which the AI ​​model processes the prompt and generates an answer.

[1196] Step 5:

[1197] The server analyzes the information it receives and formats it into visual and auditory formats. It uses information retrieved from a database and answers from a generative AI model as input. After analysis and formatting, it generates an information set suitable for visual and auditory use as output. Specific operations include generating text data, image data, and creating audio files.

[1198] Step 6:

[1199] The server transmits the formatted information to the user terminal. The visual and auditory formatted information set is used as input, and a data packet is formed as output and transmitted to the user terminal. Specific operations include transmitting data from the server to the user terminal.

[1200] Step 7:

[1201] The user device displays the received information to the user. The input is the visually and audibly formatted information received from the server, and the output is information that the user can confirm visually and audibly. Specific operations include displaying text and illustrations on the screen and, if necessary, playing explanations through a voice assistant.

[1202] 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.

[1203] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation in a form that incorporates an emotion engine.

[1204] System Overview

[1205] The system mainly includes the following components:

[1206] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1207] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, and emotion engine.

[1208] Database: A data storage system that stores information for troubleshooting.

[1209] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1210] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[1211] How it works

[1212] Select a scenario and submit a request

[1213] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[1214] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[1215] Information collection and analysis

[1216] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (e.g., a list of allowances that can be applied for in the event of sudden hospitalization).

[1217] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[1218] The emotion engine recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information and assistance to help the user relax.

[1219] Providing and Displaying Information

[1220] The server integrates the acquired information and the output from the emotion engine and formats it into visual (text, diagrams) and auditory (voice assistance) formats, such as providing a diagram of the benefit application process or instructions on how to relax.

[1221] The server sends the formatted information to the user's terminal.

[1222] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[1223] Specific examples

[1224] Example 1: How to apply for benefits in the event of sudden hospitalization

[1225] If the user selects "acute admission," the user will need information regarding the application for benefits.

[1226] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[1227] The emotion engine recognizes the user's emotions and provides information to encourage relaxation if the user is feeling stressed.

[1228] The server formats this information into diagrams and text, and sends it to the user's device along with instructions on relaxation techniques.

[1229] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1230] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1231] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[1232] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1233] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[1234] The emotion engine recognizes the user's emotions and provides calming advice if the user is feeling anxious.

[1235] The server formats this information as text and illustrations and sends it to the user's terminal.

[1236] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[1237] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[1238] The processing flow will be explained below.

[1239] Step 1:

[1240] Users launch the app and select the type of problem they are experiencing from the main menu.

[1241] Step 2:

[1242] Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information (location information, language settings, device status information, etc.) and sends it to the server.

[1243] Step 3:

[1244] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[1245] Step 4:

[1246] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[1247] Step 5:

[1248] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[1249] Step 6:

[1250] The user device uses a camera and microphone to capture the user's facial expressions and tone of voice and transmit them to the emotion engine.

[1251] Step 7:

[1252] The emotion engine analyzes the user's emotion from the received data and sends the result to the server (e.g., the user is feeling anxious).

[1253] Step 8:

[1254] The server integrates information from the emotion engine and generates appropriate information and support based on the user's emotions. For example, if the user is feeling anxious, it can include relaxation techniques and emergency contact information.

[1255] Step 9:

[1256] The server formats the information into visual (text, diagrams) and audible (voice-assisted) formats.

[1257] Step 10:

[1258] The server sends the formatted information to the user's terminal.

[1259] Step 11:

[1260] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[1261] Step 12:

[1262] Users can check the information provided through their devices and take appropriate action.

[1263] Step 13:

[1264] (any)

[1265] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[1266] Step 14:

[1267] (any)

[1268] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model and emotion engine.

[1269] The above is the specific processing flow in this system incorporating the emotion engine.

[1270] Example 2

[1271] 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."

[1272] Conventional information provision systems have been limited in the information they provide when dealing with the various problems users face. Furthermore, they provide only uniform information without considering the user's emotions, resulting in a lack of support appropriate to the user's situation. This makes it difficult for users to receive adequate support in situations where they feel anxious or stressed. The purpose of this invention is to solve these problems and provide a system that provides users with prompt and accurate information and support tailored to their emotions.

[1273] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring information corresponding to the type of trouble selected by the user from a database, means for generating answers to specific questions using a generative AI model, means for analyzing the user's emotions using an emotion engine and generating response information, and means for integrating the acquired information and output from the emotion engine and shaping them into visual and auditory formats. This allows the user to receive prompt and accurate information according to the type of trouble and appropriate support according to their emotional state.

[1274] "User" refers to any individual or entity that uses the System.

[1275] "Server" refers to a computer system that receives requests from users and processes and provides information.

[1276] A "request" refers to a request that a user makes by entering information such as the type of problem and sending it to the server.

[1277] "Database" refers to a data storage system in which information corresponding to a problem is stored.

[1278] A "generative AI model" refers to a system that uses artificial intelligence technology to generate answers to specific user questions.

[1279] An "emotion engine" refers to a system that recognizes the user's emotions and responds accordingly.

[1280] "Visual format" refers to the way information is presented, such as in text or illustrations.

[1281] "Auditory format" refers to methods of providing information in the form of voice assistance or the like.

[1282] "User terminal" refers to a device used by a user, such as a smartphone or tablet.

[1283] "Format" refers to the process of integrating and converting acquired information into visual and auditory form.

[1284] "Trouble" refers to problems or difficult situations that users face.

[1285] A "prompt sentence" refers to a text sentence that is input into a generative AI model.

[1286] This invention relates to a system that provides users with the information they need to quickly and accurately respond to various problems they encounter, while also recognizing and adapting to their emotions. Specifically, this system is realized by linking the following components: a user terminal, a server, a database, a generative AI model, and an emotion engine.

[1287] Hardware and Software Configuration

[1288] User terminal: A device such as a smartphone or tablet that communicates with the server and displays information.

[1289] Server: A computer system that receives requests from users and generates and provides appropriate information using a database, generative AI model, and emotion engine.

[1290] Database: A data storage system that stores information for troubleshooting.

[1291] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1292] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[1293] Operational Overview

[1294] 1. The user launches the app on their device, such as a smartphone or tablet, and selects the type of problem they are facing from the main menu. For example, "sudden hospitalization" or "smartphone breakdown."

[1295] 2. Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location and language settings) and sends it to the server.

[1296] 3. The server analyzes the received request, determines the corresponding problem scenario, and retrieves relevant information from the database, such as how to apply for benefits for sudden hospitalization or how to contact the user if their smartphone breaks down.

[1297] 4. The server uses the generative AI model to generate detailed answers and explanations for the user's specific questions. For example, the prompt "Please tell me how to apply for benefits in case of sudden hospitalization" is input to the generative AI model.

[1298] 5. The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates additional information and advice to help them relax.

[1299] 6. The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[1300] 7. The server sends the formatted information to the user device, which parses it and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, or voice assistance.

[1301] Specific examples

[1302] Example 1: How to apply for benefits in the event of sudden hospitalization

[1303] The user selects "urgent hospitalization."

[1304] The device generates a request including the scenario ID and basic information and sends it to the server.

[1305] The server receives the request and retrieves information from the database, such as how to apply for emergency hospitalization benefits, the necessary documents, and where to apply. It also uses a generative AI model to provide more specific explanations and procedures.

[1306] The emotion engine recognizes the user's stress and provides information to encourage relaxation.

[1307] The server formats the information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques.

[1308] The device displays the information and uses voice assistance to explain the details.

[1309] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1310] The user selects "Smartphone broken."

[1311] The device generates a request including the scenario ID and basic information and sends it to the server.

[1312] The server receives the request and retrieves information from the database about basic troubleshooting steps for when your smartphone breaks down, alternative contact methods (such as the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1313] Using a generative AI model, it generates answers to specific user questions and provides additional information, such as "where is the nearest repair shop?" or "how to contact someone in an emergency."

[1314] The emotion engine recognizes when the user is feeling anxious and provides advice to help them calm down.

[1315] The server formats the information as text and illustrations and sends it to the user's terminal.

[1316] The device displays the information and explains it using voice assistance.

[1317] In this way, the system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[1318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1319] Step 1: Select the user's problem and submit a request

[1320] Users launch the app on their smartphone, tablet, or other device and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction."

[1321] Input: Type of problem, basic user information (location, language settings)

[1322] Based on the user's selection, the device generates a request including the scenario ID and basic information about the user and sends it to the server.

[1323] Output: Request data sent to the server (scenario ID, user information)

[1324] Specific operation: When the user taps the selection button on the app screen, the device automatically generates request data (JSON format) and sends it to the server.

[1325] Step 2: Receiving and Parsing the Request

[1326] The server receives the request sent from the device, analyzes the request data, extracts the scenario ID and basic user information, and starts processing.

[1327] Input: Request data (scenario ID, user information)

[1328] Output: Analysis results of scenario ID and user information

[1329] Specific operation: The server analyzes the received request data, reads the scenario ID and the user's basic information (location, language settings), and passes it to the next processing step.

[1330] Step 3: Obtaining relevant information

[1331] The server retrieves information related to the problem from the database. For example, in the case of "sudden hospitalization," it retrieves information on how to apply for medical treatment, and in the case of "smartphone malfunction," it retrieves information on repair procedures and alternative contact methods.

[1332] Input: Scenario ID, user information

[1333] Output: Related information (application method, required documents, repair method, etc.)

[1334] Specific operation: The server generates an SQL query, sends it to the database to retrieve the relevant information, and loads the retrieved results into memory.

[1335] Step 4: Generative AI model generates answers

[1336] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation, for example, by entering a prompt such as "How do I apply for benefits in case of sudden hospitalization?"

[1337] Input: User question, related information

[1338] Output: Answer from the generative AI model

[1339] Specific operation: The server generates a prompt based on the user's question and sends it to the generative AI model, which then generates a specific answer in text and returns it to the server.

[1340] Step 5: Emotion engine analysis and response

[1341] The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates information and advice to help them relax.

[1342] Input: User response data (voice, text)

[1343] Output: Sentiment analysis results and corresponding information

[1344] Specific operation: The emotion engine determines the user's emotional state through voice recognition and text analysis, generates messages and actions according to that state, and returns them to the server.

[1345] Step 6: Integrate and format information

[1346] The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[1347] Input: relevant information, answers from generative AI models, and response information from emotion engines

[1348] Output: Formatted information (visual and auditory)

[1349] Specific operation: The server formats various information into HTML or JSON format, generates audio files as needed, and creates a data package to send to the user's device.

[1350] Step 7: Send and view information

[1351] The server then sends the formatted information to the user device, which then parses it and displays it in an appropriate format in a user interface, such as on-screen text, graphics, or voice assistance.

[1352] Input: Formatted information

[1353] Output: What is displayed on the user screen

[1354] Specific operation: The user device analyzes the received data, displays the information in the GUI component, and plays the voice assistance from the speaker.

[1355] (Application example 2)

[1356] 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."

[1357] Existing systems can provide appropriate information for problems users encounter, but they do not adequately consider the user's emotions or location information. This can result in stress for users, and it can take a long time for them to obtain appropriate information. Furthermore, even in physical store shopping experiences, there is a lack of functionality that considers the user's emotions and suggests optimal products. Therefore, there is a need for the development of a system that can respond more quickly to individual user needs and improve the experience.

[1358] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1359] In this invention, the server includes an emotion recognition means for analyzing the user's emotions and providing information and services according to the user's emotional state, a location information analysis means for analyzing the user's location information and recommending products and services suitable for the user's current location, and a means for generating answers to the user's specific questions using a generative AI model, thereby enabling the provision of information based on the user's emotions and location information.

[1360] "User device" means an electronic device used by a user to receive information, including a smartphone or tablet.

[1361] A "server" is a computer system that receives and responds to requests from users, analyzes data, and generates information.

[1362] A "database" is a data storage system where the required information is stored.

[1363] A "generative AI model" is an artificial intelligence technology that generates answers to specific user questions.

[1364] "Emotion recognition means" is a technology that recognizes the user's emotions and responds accordingly.

[1365] "Location information analysis means" is a technology that analyzes the user's current location and provides information and services based on that location.

[1366] "Means for formatting information into visual and auditory form" refers to the means by which the server converts the information it obtains into a format that is easy for the user to see or hear.

[1367] "Emotional state" refers to the emotional state of the user, and includes specific emotions such as stress or joy.

[1368] "Multimodal technology" is a technology that provides information by combining multiple sensory information (visual, auditory, etc.).

[1369] "Feedback" refers to information such as opinions, impressions, and ratings provided by users.

[1370] "Type of trouble" refers to the specific type of problem or difficulty the user faces, such as sudden hospitalization or smartphone breakdown.

[1371] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation, in an embodiment that incorporates an emotion engine and a location information analysis engine.

[1372] System Components

[1373] The system mainly includes the following components:

[1374] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1375] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, emotion recognition means, and location information analysis means.

[1376] Database: A data storage system that stores information for troubleshooting.

[1377] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1378] Emotion recognition means: Technology that recognizes the user's emotions and responds accordingly.

[1379] Location information analysis means: Technology for providing appropriate information and services based on the user's location information.

[1380] How it works

[1381] Select a scenario and submit a request

[1382] The user launches the app and selects the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction." Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information and sends it to the server.

[1383] Information collection and analysis

[1384] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database. If the server includes a specific question from the user, it uses a generative AI model to generate a detailed answer or explanation for the question. The emotion recognition means recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information or assistance to help the user relax. The location information analysis means analyzes the user's current location and recommends products and services based on that location.

[1385] Providing and Displaying Information

[1386] The server combines the acquired information and the output from the emotion recognition and location analysis means and formats it into visual (text, illustrations) and auditory (voice assistance) formats. For example, it may provide an illustration of the benefit application process or instructions on how to relax. The server then sends the formatted information to the user's device. The device then analyzes the information received from the server and displays it in the appropriate format in the user interface. This may include on-screen text, illustrations, or voice assistance.

[1387] Hardware and Software Use Cases

[1388] Hardware: Smartphone (user device), server

[1389] software:

[1390] Face Recognition: OpenCV

[1391] Speech analysis: Google Cloud Speech-to-Text

[1392] Sentiment analysis: IBM Watson Natural Language Understanding

[1393] Database: MySQL

[1394] Generative AI model: OpenAI GPT-4

[1395] Emotion Recognition Method: Custom TensorFlow Model

[1396] Location information analysis means: GNSS module and location information API

[1397] User Interface: React Native

[1398] Voice Assistance: Google Text-to-Speech API

[1399] Specific examples

[1400] Example 1: How to apply for benefits in the event of sudden hospitalization

[1401] If the user selects "Sudden Hospitalization," the user will need information regarding applying for benefits. The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures. The emotion recognition means recognizes the user's emotions, and if the user is feeling stressed, it also provides information encouraging relaxation. The server formats this information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques. The device displays the application flow with diagrams and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1402] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1403] If the user selects "Smartphone broken," they will need information on alternative contact methods and repair procedures. The server retrieves information from the database on basic steps to take when a smartphone breaks down, alternative contact methods, and repair procedures. The generative AI model generates answers to the user's specific questions, providing supplementary explanations such as "where is the nearest repair shop" and "how to contact in an emergency." The emotion recognition means recognizes the user's emotions and provides advice to help them calm down if they are panicking. The server formats this information as text and illustrations and sends it to the user's device. The device displays the repair flow and a list of alternative contact methods, and explains emergency procedures using voice assistance.

[1404] Prompt Sentence Examples

[1405] "A user is asking about a specific product. Please answer the following questions appropriately:

[1406] For example: "Where do these bananas come from?"

[1407] ---

[1408] answer:"

[1409] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[1410] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1411] Step 1:

[1412] Input: The user launches the app on their device and selects the type of problem they are experiencing from the main menu.

[1413] Action: The user taps the Select button.

[1414] Output: The device generates a request containing the selection (scenario ID) and basic user information (such as location and language preference).

[1415] Step 2:

[1416] Input: The request made by the device.

[1417] How it works: The device sends the generated request to the server, which receives the request and analyzes the user's needs.

[1418] Output: The server determines the corresponding trouble scenario and obtains the analysis results.

[1419] Step 3:

[1420] Input: The scenario ID of the problem identified by the server.

[1421] How it works: The server queries the database to retrieve relevant information (e.g., a list of benefits available for emergency hospitalization).

[1422] Output: Information retrieved from the database.

[1423] Step 4:

[1424] Input: A specific question from the user (optional).

[1425] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate detailed answers and explanations for questions.

[1426] Output: The generated answer and / or explanation.

[1427] Step 5:

[1428] Input: User's facial image and voice data.

[1429] How it works: The server analyzes the user's emotions using emotion recognition tools (e.g. IBM Watson, OpenCV).

[1430] Output: The user's emotional state (e.g., stress, joy).

[1431] Step 6:

[1432] Input: The user's location.

[1433] How it works: The server uses location analysis tools (e.g., GNSS module, location API) to analyze the current location and recommend suitable products and services.

[1434] Output: Information about the recommended product or service.

[1435] Step 7:

[1436] Input: Information from the acquired database, the answer of the generative AI model, the results of sentiment analysis, and the results of location analysis.

[1437] How it works: The server synthesizes this information and formats it into visual and auditory formats (e.g., text, diagrams, voice assistance).

[1438] Output: Formatted information.

[1439] Step 8:

[1440] Input: Formatted information.

[1441] How it works: The server sends the formatted information to the user's device.

[1442] Output: Information received by the user device.

[1443] Step 9:

[1444] Input: Information received by the user terminal.

[1445] How it works: The device parses the information it receives and displays it to the user in an appropriate format, which may include on-screen text, diagrams, or voice assistance.

[1446] Output: Information displayed to the user.

[1447] Step 10:

[1448] Input: User feedback.

[1449] How it works: The device gets feedback from the user and sends it to the server.

[1450] Output: The feedback received by the server.

[1451] In this way, a system is realized that responds to specific user problems and provides comprehensive information and support that takes into account the user's emotions and location information.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] [Fourth embodiment]

[1456] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1457] 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.

[1458] 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).

[1459] 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.

[1460] 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.

[1461] 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).

[1462] 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.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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."

[1469] This system provides users with the necessary information quickly and accurately to deal with the various problems they may encounter. Below, we will explain in detail each component of this system and how it works.

[1470] System Overview

[1471] The system mainly includes the following components:

[1472] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1473] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[1474] Database: A data storage system that stores information for troubleshooting.

[1475] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1476] How it works

[1477] Select a scenario and submit a request

[1478] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[1479] Based on the user's selection, the device generates and sends a request to the server, including the selected problem type and basic user information (such as location and language settings).

[1480] Information collection and analysis

[1481] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (for example, a list of allowances that can be applied for in the event of sudden hospitalization).

[1482] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[1483] The server analyzes the information and formats it in an appropriate format (text, graphics, audio) to be presented to the user.

[1484] Providing and Displaying Information

[1485] The server then sends the formatted information to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[1486] The device displays the received information on the user interface so that the user can visually confirm it, and also provides information audibly through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[1487] Specific examples

[1488] Example 1: How to apply for benefits in the event of sudden hospitalization

[1489] If the user selects "acute admission," the user will need information regarding the application for benefits.

[1490] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[1491] The server formats this information in diagram and text format and sends it to the user's terminal.

[1492] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1493] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1494] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[1495] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1496] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[1497] The server formats this information as text and illustrations and sends it to the user's terminal.

[1498] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[1499] In this way, the system can provide comprehensive support by quickly and accurately providing information on specific user problems.

[1500] The processing flow will be explained below.

[1501] Step 1:

[1502] Users launch the app and select the type of problem they are experiencing from the main menu.

[1503] Step 2:

[1504] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[1505] Step 3:

[1506] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[1507] Step 4:

[1508] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[1509] Step 5:

[1510] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[1511] Step 6:

[1512] The server formats the retrieved information and generated answers into visual (text, diagrams) and audible (voice-assisted) formats, such as a diagram of the benefits claim flow or steps in the repair procedure.

[1513] Step 7:

[1514] The server sends the formatted information to the user's terminal.

[1515] Step 8:

[1516] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, and, if necessary, voice assistance.

[1517] Step 9:

[1518] Users can check the information provided through their devices and take appropriate action.

[1519] Step 10:

[1520] (any)

[1521] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[1522] Step 11:

[1523] (any)

[1524] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model.

[1525] The above is the specific flow of processing of the program in this system.

[1526] Example 1

[1527] 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."

[1528] Conventional information provision systems have had difficulty in quickly and accurately providing information to address the various problems users face. Furthermore, there was a lack of systems that could provide information visually and audibly, which meant that users sometimes could not obtain sufficient information under certain circumstances. To solve these issues, a system that can comprehensively and flexibly respond to specific user requests is needed.

[1529] 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.

[1530] In this invention, the server includes a means for requesting data corresponding to the type of problem selected by the user from the server, a means for the server to receive the request and retrieve the corresponding data from the storage system, and a means for the server to generate an answer to the user's specific request using the generative AI model, thereby enabling the server to provide information quickly and accurately to the problem the user is facing.

[1531] "User" means an individual or organizational entity that seeks to obtain information using the system.

[1532] A "problem" is a specific challenge or situation a user faces, such as an emergency hospital stay or a device malfunction.

[1533] "Data" refers to the necessary information that the server retrieves from a storage system such as a database, including procedures and contact information necessary to resolve the user's problem.

[1534] A "server" is a computer system that has the ability to receive requests from users, retrieve data from a database, generate information using a generative AI model, and send it to the user's device.

[1535] A "request" is a data request that a user sends to the server via their terminal, and includes the type of question selected and basic information about the user.

[1536] A "storage system" is a database or other data storage device for storing data.

[1537] A "generative AI model" is an artificial intelligence technology used by the server to generate detailed answers to specific user requests.

[1538] "Textual information" means data in text form that is visually displayed to the user.

[1539] "Audio information" means data in audio format that is audibly presented to a user.

[1540] A "user terminal" is a device used by a user, such as a smartphone or tablet, that has the ability to communicate with a server and display information.

[1541] System Overview

[1542] This system is designed to provide the necessary information quickly and accurately to deal with the various problems users face. It mainly includes the following components:

[1543] 1. User terminal: A device such as a smartphone or tablet used by the user, which communicates with the server and displays information.

[1544] 2. Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[1545] 3. Storage system: The data storage system where the data to address the problem is stored.

[1546] 4. Generative AI models: Artificial intelligence techniques for generating answers to specific user requests.

[1547] How it works

[1548] Select a scenario and submit a request

[1549] Users launch the app and select the type of problem they are facing from the main menu, such as "emergency hospitalization" or "smartphone breakdown."

[1550] Based on the user's selection, the device generates a request to the server, which includes the selected problem type and basic user information (such as location and language settings).

[1551] Data acquisition and analysis

[1552] The server determines the problem based on the received request and retrieves relevant data (for example, a list of allowances that can be applied for in the event of sudden hospitalization) from the storage system.

[1553] The server uses generative AI models as needed to generate additional information or detailed explanations in response to specific user questions (e.g., "Where do I apply for benefits?").

[1554] For example, prompts include: "Where do I apply for benefits?", "Where is the nearest repair shop?", and "How do I contact you in an emergency?"

[1555] The server analyzes the acquired data and formats it into an appropriate format (text information, illustrations, audio information) to provide to the user.

[1556] Providing and Displaying Information

[1557] The server then sends the formatted data to the user's device, where it is presented in visual (diagrams and text) and auditory (voice assistance) formats.

[1558] The device displays the received data on the user interface so that the user can visually confirm it, and also provides audible information through voice assistance, making it possible to respond in situations where visual confirmation is difficult.

[1559] Specific examples

[1560] Example 1: How to apply for benefits in the event of sudden hospitalization

[1561] If the user selects "Sudden Admission," information regarding the application for benefits is required.

[1562] The server retrieves information from the storage system, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures.

[1563] For example, prompts: "Where do I apply for benefits?", "What documents do I need to receive benefits?"

[1564] The server formats this information into diagrams and textual information and sends it to the user's terminal.

[1565] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1566] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1567] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[1568] The server obtains information from the storage system about basic troubleshooting steps for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1569] For example, prompts: "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[1570] The generative AI model generates answers to specific user questions and provides detailed instructions on how to deal with the problem.

[1571] The server formats this information into text and illustrations and sends it to the user's terminal.

[1572] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[1573] The above is an embodiment of the present invention, and the system can provide information quickly and accurately on specific problems of users and provide comprehensive support.

[1574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1575] Processing flow

[1576] Step 1:

[1577] The user launches the app and selects the type of problem they are facing from the main menu.

[1578] Input: The type of problem the user selects (e.g., "Sudden hospitalization" or "Smartphone broken")

[1579] Specific operation: The user taps on the option displayed on the screen, which sends the selected question type to the device.

[1580] Step 2:

[1581] The device generates a request to the server based on the user's selection.

[1582] Input: User information such as the selected problem type, user location, and language preference.

[1583] Output: Generated request data

[1584] What happens: The device collects the selections and user information, formats the data, and sends it to the server as a request.

[1585] Step 3:

[1586] The server analyzes the incoming request and determines the type of problem it encounters.

[1587] Input: Request data sent from the terminal

[1588] Output: Search query based on issue type

[1589] What happens: The server analyzes the request and generates a search query to determine the type of problem.

[1590] Step 4:

[1591] The server retrieves the relevant data from the storage system.

[1592] Input: Search query based on issue type

[1593] Output: Relevant data (e.g., in case of sudden hospitalization, medical care-related data)

[1594] Specific operation: The server uses the generated search query to search for and retrieve the relevant data from the storage system.

[1595] Step 5:

[1596] The server uses a generative AI model to generate answers to specific user questions.

[1597] Input: relevant data obtained, specific user questions

[1598] Output: Detailed answers from a generative AI model

[1599] Specific operation: The server inputs the acquired data and the user's question as a prompt into a generative AI model (e.g., GPT-4) to generate a detailed answer.

[1600] Examples of prompts: "Where do I apply for benefits?", "Where is the nearest repair shop?", "How do I contact you in an emergency?"

[1601] Step 6:

[1602] The server analyzes the acquired data and generated answers, and formats them into text and audio information.

[1603] Input: Response from the generative AI model, related data obtained

[1604] Output: Formatted text, illustrations, audio

[1605] Specific operation: The server analyzes the acquired data and the generated AI model's response, and formats it into text, charts, and audio data for delivery to the user. Formatting is done using HTML, CSS, JSON, etc.

[1606] Step 7:

[1607] The server sends the formatted data to the user's device.

[1608] Input: Formatted text, illustrations, audio information

[1609] Output: Data sent to the user's terminal

[1610] Specific operation: The server packets the formatted data and sends it to the user terminal.

[1611] Step 8:

[1612] The device displays the received data on the user interface and provides information using the voice assistant function.

[1613] Input: Text information, illustrations, and audio information sent from the server

[1614] Specific operation: The device analyzes the received data, displays text and illustrations on the screen, and uses TTS (Text-to-Speech) technology to provide audio guidance.

[1615] Users can see the information visually on the screen and hear more details through an audio guide.

[1616] The above are the specific processing steps of the system program.

[1617] (Application example 1)

[1618] 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."

[1619] Conventional troubleshooting systems often lack the functionality to provide users with prompt and appropriate responses to emergency situations, resulting in inconvenience. In particular, the methods of providing information to users with visual or speech impairments are limited, and comprehensive support is not provided. Furthermore, the lack of detailed explanations for specific user questions can increase anxiety when dealing with problems.

[1620] 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.

[1621] In this invention, the server includes: means for requesting information corresponding to a type of trouble selected by a user from the server; means for the server to receive the request and retrieve the corresponding information from a database; means for the server to generate answers to the user's specific questions using a generative AI model; means for the server to analyze the retrieved information and format it into visual and auditory formats; means for the server to send the formatted information to a user terminal; means for the user terminal to display the sent information to the user; emergency support means for the user to select an emergency situation and to provide countermeasures; and means for using a generative AI model to provide detailed explanations for the user's specific questions about the emergency situation. This allows the user to obtain quick and appropriate countermeasures when facing an emergency situation and receive comprehensive support using their vision and hearing.

[1622] The "means for requesting information corresponding to the type of trouble selected by the user from the server" is a function that allows the user to select a specific trouble they are facing and send detailed information about it as a request to the server.

[1623] "Means by which the server receives a request and retrieves the corresponding information from the database" refers to the function by which the server receives a request from a user and searches for and retrieves information based on that request from the database.

[1624] "Means for the server to use a generative AI model to generate answers to specific questions from users" refers to the function by which the server uses generative AI to create optimal answers to specific questions from users.

[1625] "Means for analyzing information acquired by the server and arranging it into visual and auditory formats" refers to the function by which the server analyzes information acquired and converts it into a format suitable for visual (text and illustrations) and auditory (audio) perception.

[1626] The "means for transmitting information formatted by the server to the user terminal" is a function for transmitting information formatted by the server in visual and auditory form to the user terminal.

[1627] "Means for the user terminal to display the transmitted information to the user" refers to a function by which the user terminal displays the information transmitted from the server so that the user can confirm it.

[1628] "Emergency support means that allows users to select an emergency situation and provides countermeasures" is a function that allows users to select an emergency situation through an application and provides appropriate countermeasures according to the situation.

[1629] "Means of using a generative AI model to provide detailed explanations in response to specific questions about a user's emergency situation" refers to a function that uses a generative AI model to provide specific and detailed explanations in response to questions about a user's emergency situation.

[1630] This invention is a system that provides a user with a prompt and appropriate response to an emergency situation they find themselves in. The components of this system and their operation will be described in detail below.

[1631] System Overview

[1632] The system mainly includes the following components:

[1633] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1634] Server: Receives requests from users and generates and provides appropriate information using the database and generative AI model.

[1635] Database: A data storage system that stores information for troubleshooting.

[1636] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1637] How it works

[1638] User selects emergency situation

[1639] The user launches the app and selects the type of emergency situation they are facing (e.g., burglary, fire, traffic accident).

[1640] Send request

[1641] Based on the selection, the user device generates and sends a request to the server, which includes the selected emergency situation type and basic user information (such as location and language settings).

[1642] Information Acquisition and Analysis

[1643] The server determines the relevant emergency situation based on the received request and retrieves relevant information from a database (evacuation routes, emergency contacts, initial emergency procedures, etc.) The server also uses a generative AI model to generate detailed explanations in response to the user's specific questions.

[1644] Formatting and providing information

[1645] The server analyzes the acquired information and formats it into an appropriate format (text, illustrations, or voice) for presentation to the user. The server then sends the formatted information to the user's device. The user's device then presents the received information to the user visually (text or illustrations) and audibly (voice assistance).

[1646] Specific names of hardware and software to be used

[1647] Hardware: Smartphone

[1648] Server: Backend using the Flask framework

[1649] Database: SQLite

[1650] Generative AI model: TensorFlow

[1651] Example of operation

[1652] Example 1: Providing countermeasures in case of fire

[1653] If the user selects "fire," the server retrieves information from the database about evacuation routes, emergency contacts, and first aid procedures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[1654] Example prompt sentence:

[1655] "What is the safest way to escape in the event of a fire?"

[1656] Example of a generated answer:

[1657] "If a fire breaks out, immediately check the escape route and evacuate to a safe place. It is safest to move away from the source of the fire and stay as low as possible. While evacuating, cover your nose and mouth with a wet towel to ensure proper breathing."

[1658] Example 2: Providing countermeasures in case of burglary

[1659] If the user selects "burglary," the server retrieves information from the database about the necessary contacts and initial response measures, and the generative AI model provides detailed explanations in response to the user's specific questions.

[1660] Example prompt sentence:

[1661] "If a burglar breaks in, what's the first thing you should do?"

[1662] Example of a generated answer:

[1663] "If a burglar breaks in, contact the police immediately and seek refuge in a safe location. Do not enter the residence."

[1664] In this way, the present invention allows users to obtain prompt and appropriate responses when faced with an emergency situation, and provides comprehensive support utilizing visual and auditory senses.

[1665] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1666] Step 1:

[1667] The user launches the app and selects the type of emergency, choosing from options such as "fire," "burglary," or "traffic accident." The input includes the user's selection, and the output generates a request with the selected emergency. The specific action involves the user tapping on the menu on the screen.

[1668] Step 2:

[1669] The user device sends a request for the selected emergency situation to the server, including the user's selection along with basic information such as location and language preference. The user's selection and basic information are used as inputs to generate the request. The output is the formation of a request that is sent to the server. Specific operations include the device communicating with the server.

[1670] Step 3:

[1671] The server analyzes the received request and retrieves information about the corresponding emergency situation from the database. At this stage, the request information is used as input to generate a database search query. Information is retrieved from the database using the database search query as input, and a retrieved information set is generated as output. Specific operations include database search and information extraction within the server.

[1672] Step 4:

[1673] The server uses the generative AI model to generate detailed answers to the user's specific questions. The input includes information about the emergency situation and basic information about the user, and the generative AI model uses this information to create a prompt. The output is an answer to the user's specific question. The specific operation involves a series of calculations in which the AI ​​model processes the prompt and generates an answer.

[1674] Step 5:

[1675] The server analyzes the information it receives and formats it into visual and auditory formats. It uses information retrieved from a database and answers from a generative AI model as input. After analysis and formatting, it generates an information set suitable for visual and auditory use as output. Specific operations include generating text data, image data, and creating audio files.

[1676] Step 6:

[1677] The server transmits the formatted information to the user terminal. The visual and auditory formatted information set is used as input, and a data packet is formed as output and transmitted to the user terminal. Specific operations include transmitting data from the server to the user terminal.

[1678] Step 7:

[1679] The user device displays the received information to the user. The input is the visually and audibly formatted information received from the server, and the output is information that the user can confirm visually and audibly. Specific operations include displaying text and illustrations on the screen and, if necessary, playing explanations through a voice assistant.

[1680] 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.

[1681] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation in a form that incorporates an emotion engine.

[1682] System Overview

[1683] The system mainly includes the following components:

[1684] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1685] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, and emotion engine.

[1686] Database: A data storage system that stores information for troubleshooting.

[1687] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1688] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[1689] How it works

[1690] Select a scenario and submit a request

[1691] Users launch the app and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone breakdown."

[1692] Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location information and language settings) and sends it to the server.

[1693] Information collection and analysis

[1694] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database (e.g., a list of allowances that can be applied for in the event of sudden hospitalization).

[1695] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[1696] The emotion engine recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information and assistance to help the user relax.

[1697] Providing and Displaying Information

[1698] The server integrates the acquired information and the output from the emotion engine and formats it into visual (text, diagrams) and auditory (voice assistance) formats, such as providing a diagram of the benefit application process or instructions on how to relax.

[1699] The server sends the formatted information to the user's terminal.

[1700] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[1701] Specific examples

[1702] Example 1: How to apply for benefits in the event of sudden hospitalization

[1703] If the user selects "acute admission," the user will need information regarding the application for benefits.

[1704] The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and then uses a generative AI model to provide further specific explanations and procedures.

[1705] The emotion engine recognizes the user's emotions and provides information to encourage relaxation if the user is feeling stressed.

[1706] The server formats this information into diagrams and text, and sends it to the user's device along with instructions on relaxation techniques.

[1707] The device displays an illustrated application flow and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1708] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1709] If a user selects "Smartphone broken," they will need information about alternative contact methods and repair options.

[1710] The server retrieves information from the database about basic troubleshooting tips for when a smartphone breaks down, alternative contact methods (e.g., the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1711] The generative AI model generates answers to specific user questions, providing additional information such as "where is the nearest repair shop?" or "how to contact them in an emergency."

[1712] The emotion engine recognizes the user's emotions and provides calming advice if the user is feeling anxious.

[1713] The server formats this information as text and illustrations and sends it to the user's terminal.

[1714] The device displays a list of repair procedures and alternative contact methods, and uses voice assistance to explain emergency procedures.

[1715] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[1716] The processing flow will be explained below.

[1717] Step 1:

[1718] Users launch the app and select the type of problem they are experiencing from the main menu.

[1719] Step 2:

[1720] Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information (location information, language settings, device status information, etc.) and sends it to the server.

[1721] Step 3:

[1722] The server analyzes the request received from the terminal and determines the corresponding trouble scenario based on the scenario ID.

[1723] Step 4:

[1724] Based on the determined scenario, the server retrieves relevant information from the database (e.g., a list of benefits that can be applied for in the event of sudden hospitalization).

[1725] Step 5:

[1726] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation for that question.

[1727] Step 6:

[1728] The user device uses a camera and microphone to capture the user's facial expressions and tone of voice and transmit them to the emotion engine.

[1729] Step 7:

[1730] The emotion engine analyzes the user's emotion from the received data and sends the result to the server (e.g., the user is feeling anxious).

[1731] Step 8:

[1732] The server integrates information from the emotion engine and generates appropriate information and support based on the user's emotions. For example, if the user is feeling anxious, it can include relaxation techniques and emergency contact information.

[1733] Step 9:

[1734] The server formats the information into visual (text, diagrams) and audible (voice-assisted) formats.

[1735] Step 10:

[1736] The server sends the formatted information to the user's terminal.

[1737] Step 11:

[1738] The device analyzes the information received from the server and displays it in an appropriate format in the user interface, which may include on-screen text, illustrations, or voice assistance.

[1739] Step 12:

[1740] Users can check the information provided through their devices and take appropriate action.

[1741] Step 13:

[1742] (any)

[1743] If the user inputs feedback (satisfaction level or additional questions) on the information provided, the device sends this feedback to the server.

[1744] Step 14:

[1745] (any)

[1746] The server stores the received feedback in a database and uses it to provide future information and improve the AI ​​model and emotion engine.

[1747] The above is the specific processing flow in this system incorporating the emotion engine.

[1748] Example 2

[1749] 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."

[1750] Conventional information provision systems have been limited in the information they provide when dealing with the various problems users face. Furthermore, they provide only uniform information without considering the user's emotions, resulting in a lack of support appropriate to the user's situation. This makes it difficult for users to receive adequate support in situations where they feel anxious or stressed. The purpose of this invention is to solve these problems and provide a system that provides users with prompt and accurate information and support tailored to their emotions.

[1751] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring information corresponding to the type of trouble selected by the user from a database, means for generating answers to specific questions using a generative AI model, means for analyzing the user's emotions using an emotion engine and generating response information, and means for integrating the acquired information and output from the emotion engine and shaping them into visual and auditory formats. This allows the user to receive prompt and accurate information according to the type of trouble and appropriate support according to their emotional state.

[1752] "User" refers to any individual or entity that uses the System.

[1753] "Server" refers to a computer system that receives requests from users and processes and provides information.

[1754] A "request" refers to a request that a user makes by entering information such as the type of problem and sending it to the server.

[1755] "Database" refers to a data storage system in which information corresponding to a problem is stored.

[1756] A "generative AI model" refers to a system that uses artificial intelligence technology to generate answers to specific user questions.

[1757] An "emotion engine" refers to a system that recognizes the user's emotions and responds accordingly.

[1758] "Visual format" refers to the way information is presented, such as in text or illustrations.

[1759] "Auditory format" refers to methods of providing information in the form of voice assistance or the like.

[1760] "User terminal" refers to a device used by a user, such as a smartphone or tablet.

[1761] "Format" refers to the process of integrating and converting acquired information into visual and auditory form.

[1762] "Trouble" refers to problems or difficult situations that users face.

[1763] A "prompt sentence" refers to a text sentence that is input into a generative AI model.

[1764] This invention relates to a system that provides users with the information they need to quickly and accurately respond to various problems they encounter, while also recognizing and adapting to their emotions. Specifically, this system is realized by linking the following components: a user terminal, a server, a database, a generative AI model, and an emotion engine.

[1765] Hardware and Software Configuration

[1766] User terminal: A device such as a smartphone or tablet that communicates with the server and displays information.

[1767] Server: A computer system that receives requests from users and generates and provides appropriate information using a database, generative AI model, and emotion engine.

[1768] Database: A data storage system that stores information for troubleshooting.

[1769] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1770] Emotion engine: Technology that recognizes the user's emotions and responds accordingly.

[1771] Operational Overview

[1772] 1. The user launches the app on their device, such as a smartphone or tablet, and selects the type of problem they are facing from the main menu. For example, "sudden hospitalization" or "smartphone breakdown."

[1773] 2. Based on the user's selection, the device generates a request including the scenario ID and the user's basic information (such as location and language settings) and sends it to the server.

[1774] 3. The server analyzes the received request, determines the corresponding problem scenario, and retrieves relevant information from the database, such as how to apply for benefits for sudden hospitalization or how to contact the user if their smartphone breaks down.

[1775] 4. The server uses the generative AI model to generate detailed answers and explanations for the user's specific questions. For example, the prompt "Please tell me how to apply for benefits in case of sudden hospitalization" is input to the generative AI model.

[1776] 5. The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates additional information and advice to help them relax.

[1777] 6. The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[1778] 7. The server sends the formatted information to the user device, which parses it and displays it in an appropriate format in the user interface, which may include on-screen text, graphics, or voice assistance.

[1779] Specific examples

[1780] Example 1: How to apply for benefits in the event of sudden hospitalization

[1781] The user selects "urgent hospitalization."

[1782] The device generates a request including the scenario ID and basic information and sends it to the server.

[1783] The server receives the request and retrieves information from the database, such as how to apply for emergency hospitalization benefits, the necessary documents, and where to apply. It also uses a generative AI model to provide more specific explanations and procedures.

[1784] The emotion engine recognizes the user's stress and provides information to encourage relaxation.

[1785] The server formats the information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques.

[1786] The device displays the information and uses voice assistance to explain the details.

[1787] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1788] The user selects "Smartphone broken."

[1789] The device generates a request including the scenario ID and basic information and sends it to the server.

[1790] The server receives the request and retrieves information from the database about basic troubleshooting steps for when your smartphone breaks down, alternative contact methods (such as the location of public telephones and how to use Wi-Fi hotspots), and repair procedures.

[1791] Using a generative AI model, it generates answers to specific user questions and provides additional information, such as "where is the nearest repair shop?" or "how to contact someone in an emergency."

[1792] The emotion engine recognizes when the user is feeling anxious and provides advice to help them calm down.

[1793] The server formats the information as text and illustrations and sends it to the user's terminal.

[1794] The device displays the information and explains it using voice assistance.

[1795] In this way, the system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[1796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1797] Step 1: Select the user's problem and submit a request

[1798] Users launch the app on their smartphone, tablet, or other device and select the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction."

[1799] Input: Type of problem, basic user information (location, language settings)

[1800] Based on the user's selection, the device generates a request including the scenario ID and basic information about the user and sends it to the server.

[1801] Output: Request data sent to the server (scenario ID, user information)

[1802] Specific operation: When the user taps the selection button on the app screen, the device automatically generates request data (JSON format) and sends it to the server.

[1803] Step 2: Receiving and Parsing the Request

[1804] The server receives the request sent from the device, analyzes the request data, extracts the scenario ID and basic user information, and starts processing.

[1805] Input: Request data (scenario ID, user information)

[1806] Output: Analysis results of scenario ID and user information

[1807] Specific operation: The server analyzes the received request data, reads the scenario ID and the user's basic information (location, language settings), and passes it to the next processing step.

[1808] Step 3: Obtaining relevant information

[1809] The server retrieves information related to the problem from the database. For example, in the case of "sudden hospitalization," it retrieves information on how to apply for medical treatment, and in the case of "smartphone malfunction," it retrieves information on repair procedures and alternative contact methods.

[1810] Input: Scenario ID, user information

[1811] Output: Related information (application method, required documents, repair method, etc.)

[1812] Specific operation: The server generates an SQL query, sends it to the database to retrieve the relevant information, and loads the retrieved results into memory.

[1813] Step 4: Generative AI model generates answers

[1814] If the server contains a specific user question, it uses a generative AI model to generate a detailed answer or explanation, for example, by entering a prompt such as "How do I apply for benefits in case of sudden hospitalization?"

[1815] Input: User question, related information

[1816] Output: Answer from the generative AI model

[1817] Specific operation: The server generates a prompt based on the user's question and sends it to the generative AI model, which then generates a specific answer in text and returns it to the server.

[1818] Step 5: Emotion engine analysis and response

[1819] The emotion engine recognizes the user's emotions and, for example, if it determines that the user is feeling stressed, it generates information and advice to help them relax.

[1820] Input: User response data (voice, text)

[1821] Output: Sentiment analysis results and corresponding information

[1822] Specific operation: The emotion engine determines the user's emotional state through voice recognition and text analysis, generates messages and actions according to that state, and returns them to the server.

[1823] Step 6: Integrate and format information

[1824] The server integrates the information acquired and the output from the emotion engine and formats it into visual (text, illustrations) and auditory (voice assistance) formats.

[1825] Input: relevant information, answers from generative AI models, and response information from emotion engines

[1826] Output: Formatted information (visual and auditory)

[1827] Specific operation: The server formats various information into HTML or JSON format, generates audio files as needed, and creates a data package to send to the user's device.

[1828] Step 7: Send and view information

[1829] The server then sends the formatted information to the user device, which then parses it and displays it in an appropriate format in a user interface, such as on-screen text, graphics, or voice assistance.

[1830] Input: Formatted information

[1831] Output: What is displayed on the user screen

[1832] Specific operation: The user device analyzes the received data, displays the information in the GUI component, and plays the voice assistance from the speaker.

[1833] (Application example 2)

[1834] 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."

[1835] Existing systems can provide appropriate information for problems users encounter, but they do not adequately consider the user's emotions or location information. This can result in stress for users, and it can take a long time for them to obtain appropriate information. Furthermore, even in physical store shopping experiences, there is a lack of functionality that considers the user's emotions and suggests optimal products. Therefore, there is a need for the development of a system that can respond more quickly to individual user needs and improve the experience.

[1836] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1837] In this invention, the server includes an emotion recognition means for analyzing the user's emotions and providing information and services according to the user's emotional state, a location information analysis means for analyzing the user's location information and recommending products and services suitable for the user's current location, and a means for generating answers to the user's specific questions using a generative AI model, thereby enabling the provision of information based on the user's emotions and location information.

[1838] "User device" means an electronic device used by a user to receive information, including a smartphone or tablet.

[1839] A "server" is a computer system that receives and responds to requests from users, analyzes data, and generates information.

[1840] A "database" is a data storage system where the required information is stored.

[1841] A "generative AI model" is an artificial intelligence technology that generates answers to specific user questions.

[1842] "Emotion recognition means" is a technology that recognizes the user's emotions and responds accordingly.

[1843] "Location information analysis means" is a technology that analyzes the user's current location and provides information and services based on that location.

[1844] "Means for formatting information into visual and auditory form" refers to the means by which the server converts the information it obtains into a format that is easy for the user to see or hear.

[1845] "Emotional state" refers to the emotional state of the user, and includes specific emotions such as stress or joy.

[1846] "Multimodal technology" is a technology that provides information by combining multiple sensory information (visual, auditory, etc.).

[1847] "Feedback" refers to information such as opinions, impressions, and ratings provided by users.

[1848] "Type of trouble" refers to the specific type of problem or difficulty the user faces, such as sudden hospitalization or smartphone breakdown.

[1849] This invention relates to a system that provides necessary information and recognizes and adapts to the user's emotions in order to quickly and accurately respond to various problems the user may encounter. Below, we will explain in detail each component of this system and its operation, in an embodiment that incorporates an emotion engine and a location information analysis engine.

[1850] System Components

[1851] The system mainly includes the following components:

[1852] User terminal: A device used by a user, such as a smartphone or tablet, that communicates with the server and displays information.

[1853] Server: Receives requests from users and generates and provides appropriate information using the database, generative AI model, emotion recognition means, and location information analysis means.

[1854] Database: A data storage system that stores information for troubleshooting.

[1855] Generative AI models: Artificial intelligence techniques for generating answers to specific user questions.

[1856] Emotion recognition means: Technology that recognizes the user's emotions and responds accordingly.

[1857] Location information analysis means: Technology for providing appropriate information and services based on the user's location information.

[1858] How it works

[1859] Select a scenario and submit a request

[1860] The user launches the app and selects the type of problem they are facing from the main menu, such as "sudden hospitalization" or "smartphone malfunction." Based on the user's selection, the device generates a request containing the scenario ID and the user's basic information and sends it to the server.

[1861] Information collection and analysis

[1862] The server determines the corresponding trouble scenario based on the received request and retrieves relevant information from the database. If the server includes a specific question from the user, it uses a generative AI model to generate a detailed answer or explanation for the question. The emotion recognition means recognizes the user's emotions, and if it determines that the user is feeling stressed, for example, it generates information or assistance to help the user relax. The location information analysis means analyzes the user's current location and recommends products and services based on that location.

[1863] Providing and Displaying Information

[1864] The server combines the acquired information and the output from the emotion recognition and location analysis means and formats it into visual (text, illustrations) and auditory (voice assistance) formats. For example, it may provide an illustration of the benefit application process or instructions on how to relax. The server then sends the formatted information to the user's device. The device then analyzes the information received from the server and displays it in the appropriate format in the user interface. This may include on-screen text, illustrations, or voice assistance.

[1865] Hardware and Software Use Cases

[1866] Hardware: Smartphone (user device), server

[1867] software:

[1868] Face Recognition: OpenCV

[1869] Speech analysis: Google Cloud Speech-to-Text

[1870] Sentiment analysis: IBM Watson Natural Language Understanding

[1871] Database: MySQL

[1872] Generative AI model: OpenAI GPT-4

[1873] Emotion Recognition Method: Custom TensorFlow Model

[1874] Location information analysis means: GNSS module and location information API

[1875] User Interface: React Native

[1876] Voice Assistance: Google Text-to-Speech API

[1877] Specific examples

[1878] Example 1: How to apply for benefits in the event of sudden hospitalization

[1879] If the user selects "Sudden Hospitalization," the user will need information regarding applying for benefits. The server retrieves information from the database, such as how to apply for benefits related to sudden hospitalization, the necessary documents, and where to apply, and uses a generative AI model to supplement it with more specific explanations and procedures. The emotion recognition means recognizes the user's emotions, and if the user is feeling stressed, it also provides information encouraging relaxation. The server formats this information in diagram and text format, and sends it to the user's device along with instructions on relaxation techniques. The device displays the application flow with diagrams and a list of required documents, and uses voice assistance to explain the details of the procedure.

[1880] Example 2: Ensuring a means of communication in case of smartphone malfunction

[1881] If the user selects "Smartphone broken," they will need information on alternative contact methods and repair procedures. The server retrieves information from the database on basic steps to take when a smartphone breaks down, alternative contact methods, and repair procedures. The generative AI model generates answers to the user's specific questions, providing supplementary explanations such as "where is the nearest repair shop" and "how to contact in an emergency." The emotion recognition means recognizes the user's emotions and provides advice to help them calm down if they are panicking. The server formats this information as text and illustrations and sends it to the user's device. The device displays the repair flow and a list of alternative contact methods, and explains emergency procedures using voice assistance.

[1882] Prompt Sentence Examples

[1883] "A user is asking about a specific product. Please answer the following questions appropriately:

[1884] For example: "Where do these bananas come from?"

[1885] ---

[1886] answer:"

[1887] In this way, this system can provide comprehensive support by quickly and accurately providing information on the user's specific problem, and by recognizing the user's emotions and providing assistance appropriate to the situation.

[1888] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1889] Step 1:

[1890] Input: The user launches the app on their device and selects the type of problem they are experiencing from the main menu.

[1891] Action: The user taps the Select button.

[1892] Output: The device generates a request containing the selection (scenario ID) and basic user information (such as location and language preference).

[1893] Step 2:

[1894] Input: The request made by the device.

[1895] How it works: The device sends the generated request to the server, which receives the request and analyzes the user's needs.

[1896] Output: The server determines the corresponding trouble scenario and obtains the analysis results.

[1897] Step 3:

[1898] Input: The scenario ID of the problem identified by the server.

[1899] How it works: The server queries the database to retrieve relevant information (e.g., a list of benefits available for emergency hospitalization).

[1900] Output: Information retrieved from the database.

[1901] Step 4:

[1902] Input: A specific question from the user (optional).

[1903] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate detailed answers and explanations for questions.

[1904] Output: The generated answer and / or explanation.

[1905] Step 5:

[1906] Input: User's facial image and voice data.

[1907] How it works: The server analyzes the user's emotions using emotion recognition tools (e.g. IBM Watson, OpenCV).

[1908] Output: The user's emotional state (e.g., stress, joy).

[1909] Step 6:

[1910] Input: The user's location.

[1911] How it works: The server uses location analysis tools (e.g., GNSS module, location API) to analyze the current location and recommend suitable products and services.

[1912] Output: Information about the recommended product or service.

[1913] Step 7:

[1914] Input: Information from the acquired database, the answer of the generative AI model, the results of sentiment analysis, and the results of location analysis.

[1915] How it works: The server synthesizes this information and formats it into visual and auditory formats (e.g., text, diagrams, voice assistance).

[1916] Output: Formatted information.

[1917] Step 8:

[1918] Input: Formatted information.

[1919] How it works: The server sends the formatted information to the user's device.

[1920] Output: Information received by the user device.

[1921] Step 9:

[1922] Input: Information received by the user terminal.

[1923] How it works: The device parses the information it receives and displays it to the user in an appropriate format, which may include on-screen text, diagrams, or voice assistance.

[1924] Output: Information displayed to the user.

[1925] Step 10:

[1926] Input: User feedback.

[1927] How it works: The device gets feedback from the user and sends it to the server.

[1928] Output: The feedback received by the server.

[1929] In this way, a system is realized that responds to specific user problems and provides comprehensive information and support that takes into account the user's emotions and location information.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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.

[1934] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1935] 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.

[1936] 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).

[1937] 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.

[1938] 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."

[1939] 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.

[1940] 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).

[1941] 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.

[1942] 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.

[1943] 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.

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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.

[1951] The following is further disclosed regarding the above embodiment.

[1952] (Claim 1)

[1953] a means for requesting information from a server corresponding to a type of trouble selected by a user;

[1954] a means for the server to receive the request and retrieve the corresponding information from the database;

[1955] A means for the server to generate answers to specific questions from the user using the generative AI model;

[1956] means for the server to analyze and format the acquired information into visual and audio formats;

[1957] A means for transmitting the formatted information by the server to a user terminal;

[1958] means for the user terminal to display the transmitted information to the user;

[1959] A system including:

[1960] (Claim 2)

[1961] 10. The system of claim 1, wherein multimodal technology is used to provide information in visual and auditory formats.

[1962] (Claim 3)

[1963] 3. The system according to claim 1, further comprising means for obtaining feedback from the user and transmitting the feedback to the server.

[1964] "Example 1"

[1965] (Claim 1)

[1966] means for requesting data from a server corresponding to a user-selected question type;

[1967] A server receives a request and retrieves the corresponding data from the storage system;

[1968] A means for the server to generate a response to the user's specific request using the generative AI model; and

[1969] A means for analyzing the data acquired by the server and shaping it into text information and audio information format;

[1970] A means for transmitting the formatted data by the server to a user terminal;

[1971] means for the user terminal to present the transmitted data to the user;

[1972] A system including:

[1973] (Claim 2)

[1974] 10. The system of claim 1, wherein multimodal technology is used to provide data in textual and audio formats.

[1975] (Claim 3)

[1976] 10. The system of claim 1, further comprising means for collecting feedback from users and transmitting it to the server.

[1977] "Application Example 1"

[1978] (Claim 1)

[1979] a means for requesting information from a server corresponding to a type of trouble selected by a user;

[1980] a means for the server to receive the request and retrieve the corresponding information from the database;

[1981] A means for the server to generate answers to specific questions from the user using the generative AI model;

[1982] means for the server to analyze and format the acquired information into visual and audio formats;

[1983] A means for transmitting the formatted information by the server to a user terminal;

[1984] means for the user terminal to display the transmitted information to the user;

[1985] An emergency support method that allows users to select an emergency situation and provides countermeasures;

[1986] A means of using a generative AI model to provide detailed explanations in response to specific questions about the user's emergency situation; and

[1987] A system including:

[1988] (Claim 2)

[1989] 10. The system of claim 1, wherein multimodal technology is used to provide information in visual and auditory formats.

[1990] (Claim 3)

[1991] 3. The system according to claim 1, further comprising means for obtaining feedback from the user and transmitting the feedback to the server.

[1992] "Example 2: Combining Emotion Engines"

[1993] (Claim 1)

[1994] a means for requesting information from a server corresponding to a type of trouble selected by a user;

[1995] a means for the server to receive the request and retrieve the corresponding information from the database;

[1996] A means for the server to generate answers to specific questions from the user using the generative AI model;

[1997] A means for analyzing a user's emotions using an emotion engine and generating corresponding information;

[1998] means for integrating and formatting the information acquired by the server and the output from the emotion engine into visual and audio formats;

[1999] A means for transmitting the formatted information by the server to a user terminal;

[2000] means for the user terminal to display the transmitted information to the user;

[2001] A system including:

[2002] (Claim 2)

[2003] 10. The system of claim 1, wherein multimodal technology is used to provide information in visual and auditory formats.

[2004] (Claim 3)

[2005] 3. The system according to claim 1, further comprising means for obtaining feedback from the user and transmitting the feedback to the server.

[2006] "Application example 2 when combining emotion engines"

[2007] (Claim 1)

[2008] a means for requesting information from a server corresponding to a type of trouble selected by a user;

[2009] a means for the server to receive the request and retrieve the corresponding information from the database;

[2010] A means for the server to generate answers to specific questions from the user using the generative AI model;

[2011] means for the server to analyze and format the acquired information into visual and audio formats;

[2012] A means for transmitting the formatted information by the server to a user terminal;

[2013] means for the user terminal to display the transmitted information to the user;

[2014] An emotion recognition means for analyzing the user's emotions and providing information and services according to the user's emotional state;

[2015] A location analysis method that analyzes the user's location information and recommends products and services appropriate for the user's current location;

[2016] A system including:

[2017] (Claim 2)

[2018] 10. The system of claim 1, wherein multimodal technology is used to provide information in visual and auditory formats.

[2019] (Claim 3)

[2020] 10. The system of claim 1, further comprising means for obtaining feedback from the user and transmitting it to the server. [Explanation of symbols]

[2021] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devi...

Claims

1. a means for requesting information from a server corresponding to a type of trouble selected by a user; a means for the server to receive the request and retrieve the corresponding information from the database; A means for the server to generate answers to specific questions from the user using the generative AI model; means for the server to analyze and format the acquired information into visual and audio formats; A means for transmitting the formatted information by the server to a user terminal; means for the user terminal to display the transmitted information to the user; A system including:

2. 10. The system of claim 1, wherein multimodal technology is used to provide information in visual and audio formats.

3. 3. The system according to claim 1, further comprising means for obtaining feedback from the user and transmitting the feedback to the server.

Images