system

Abstract

Provide a system. [Solution] a terminal for a user to input and send questions about hobbies; A means for inputting a question received by the server from a user into a generative AI model; A means for the generative AI model to analyze questions and generate optimal advice; means for transmitting the advice generated by the server to a user's terminal; means for displaying the advice received by the user's terminal; A system including:

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] Currently, many people face the problem of finding the best information and appropriate procedures when starting a new hobby, resulting in a high barrier to participation. This issue prevents many people from easily starting a new hobby without investing time and effort, resulting in a situation where the diversity and richness of hobbies is limited. Furthermore, existing information sources have difficulty providing specific advice tailored to individual interests and questions, so a system to solve this problem is needed. [Means for solving the problem]

[0005] The present invention provides a system that uses generative AI to lower the barrier to entry for users when starting a new hobby. This system includes a terminal through which a user inputs and sends questions about the hobby, a server that inputs the questions received from the user into a generative AI model, a generative AI model that analyzes the questions and generates optimal advice, a server that sends the generated advice to the user's terminal, and a user's terminal that displays the received advice. This system allows users to easily obtain specific advice and procedures provided by the generative AI, significantly lowering the barrier to entry for new hobbies. Furthermore, by adding a means for generating advice for multiple types of hobbies and a database that records questions and generated advice, even greater convenience and flexibility can be provided.

[0006] A "user" is an individual or entity that utilizes the system to submit hobby-related questions and receive generated advice.

[0007] A "terminal" is an electronic device that allows a user to input and send questions about hobbies, and includes devices such as smartphones, tablets, and personal computers.

[0008] A "server" is a computer system that processes questions received from users, inputs them into a generative AI model, receives the results, and sends them to the user's device.

[0009] A "generative AI model" is an artificial intelligence model that analyzes questions entered by users and generates optimal advice and procedures based on those questions.

[0010] "Advice" refers to specific instructions or suggestions provided to users as a result of analysis by the generative AI model.

[0011] The "database means" is a database system for storing and managing questions sent by users and advice generated by users.

[0012] "Analysis" refers to a series of processes that a generative AI model performs to understand the content of a question entered by a user and generate appropriate advice. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention provides a system that uses generative AI to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[0035] System Configuration

[0036] 1. Terminal

[0037] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[0038] 2. Server

[0039] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[0040] Ability to receive questions from users

[0041] A function that allows users to input questions into a generative AI model and obtain analysis results.

[0042] A function to send generated advice to the user's device

[0043] Ability to store questions and generated advice in a database

[0044] 3. Generative AI Models

[0045] The generative AI model is an artificial intelligence that analyzes questions sent by users and generates optimal advice. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[0046] 4. Database Means

[0047] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0048] System Operation

[0049] A user inputs a question about a hobby into a terminal. For example, consider the question "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to the server.

[0050] The server inputs the question received from the user into the generative AI model. The generative AI model analyzes the question and generates optimal advice for the user. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube®."

[0051] Once the advice is generated, the server sends it to the user's device, which then displays it, allowing the user to receive specific instructions and follow them to start a new hobby.

[0052] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[0053] This system allows users to easily participate in new hobbies and quickly obtain specific information tailored to their interests. The database function also allows users to refer to past data, which is useful for continuous learning and information improvement.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user inputs a question about a hobby into the terminal and presses the send button. An example of this input is "How do I start playing the guitar?" The terminal sends this question to the server.

[0057] Step 2:

[0058] The server receives the question from the user and checks its content. For example, the server checks the content of "How do I start playing the guitar?"

[0059] Step 3:

[0060] The server sends the received message to the generative AI model and requests it to analyze it. At this time, the server inputs the question "guitar" into the AI ​​model.

[0061] Step 4:

[0062] A generative AI model analyzes the questions sent and generates optimal advice. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, start by practicing simple chords and watching YouTube tutorials."

[0063] Step 5:

[0064] The server receives the advice returned by the generative AI model and sends it to the user's device. Based on the user's ID, the server sends the advice, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube," to the appropriate device.

[0065] Step 6:

[0066] The user's device displays the advice received from the server. The device shows the user, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube."

[0067] Step 7:

[0068] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[0069] Step 8:

[0070] The server stores the questions submitted by users and the advice generated in a database, which makes it easy to retrieve past questions and advice for future reference.

[0071] Step 9:

[0072] If the user asks the question again, or if another user asks a similar question, the server can use its accumulated database to quickly provide appropriate advice. The process repeats.

[0073] Example 1

[0074] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0075] In modern society, interest in a variety of hobbies is growing, but gathering information and obtaining specific advice when starting a new hobby presents challenges. Beginners face particular challenges in the initial stages, such as determining the necessary procedures and tools, making it difficult to quickly obtain appropriate information. However, conventional methods require users to individually search for information and determine its reliability, making them inefficient and ineffective. Therefore, there is a need to develop a system that uses generative artificial intelligence models to provide users with optimal advice.

[0076] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0077] In this invention, the server includes an electronic device into which a user inputs and transmits a question about a hobby, means for inputting the question received from the user to a generative AI model, means for the generative AI model to analyze the question and generate optimal advice, means for the server to transmit the generated advice to the user's electronic device, and means for the user's electronic device to display the received advice, thereby enabling the user to quickly obtain specific information for starting a new hobby.

[0078] An "electronic device" is a device that has the function of accepting input from a user via the Internet and sending questions to a server, and specifically includes smartphones, tablets, and personal computers.

[0079] A "server" is a computer system that has the functionality to process questions received from users, input them into a generative artificial intelligence model, and send the generated advice to the user's electronic device.

[0080] A "generative artificial intelligence model" is an artificial intelligence system that analyzes questions entered by users and generates optimal advice. It is trained using natural language processing technology to be able to respond to questions about a variety of hobbies.

[0081] A "question" is a specific information request that a user enters when starting a new hobby, and is input data for analysis by the generative artificial intelligence model.

[0082] "Advice" refers to specific instructions or information that the generative artificial intelligence model outputs as an analysis result, and is used as a reference when a user starts a new hobby.

[0083] The "database means" is a system in which the server stores and manages user questions and generated advice, and has a function that allows past data to be easily referenced.

[0084] This invention provides a system that uses a generative AI model to lower the barrier to users starting a new hobby. The system is composed of five elements: a user, a terminal, a server, a generative AI model, and a database means.

[0085] System Configuration and Operation

[0086] 1. Users

[0087] A user inputs a question about a hobby into an electronic device (e.g., a smartphone, a tablet, or a PC). For example, consider a case where a user inputs the question "How can I start playing the guitar?" into a PC.

[0088] 2. Terminal

[0089] The terminal sends the user-entered question to the server via an Internet connection, using a JavaScript (registered trademark) form submission or an HTTP request.

[0090] 3. Server

[0091] The server receives user questions and inputs them into the generative artificial intelligence model. The server includes the following functions:

[0092] Question receiving function (e.g., implemented using the Django framework)

[0093] Inputting data into a generative AI model (e.g., using the OpenAI (registered trademark) API)

[0094] Receiving generated advice

[0095] Sending advice to user terminal

[0096] Database storage of questions and advice (e.g., managed using SQLite or PostgreSQL)

[0097] Specifically, the server is written in Python and built using the Django framework. This server processes HTTP requests from users and sends questions to a generative artificial intelligence model (e.g., OpenAI's GPT-3 (registered trademark) model) using an appropriate API. The generated advice is then sent back to the user's device as an HTTP response. In addition, a database is installed on the server to manage past questions and advice.

[0098] 4. Generative AI Models

[0099] A generative artificial intelligence model (e.g., OpenAI's GPT-3) analyzes questions sent via a server and generates optimal advice. The AI ​​model is trained to provide specific instructions and reference information in response to the user's question. For example, it might generate advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube."

[0100] 5. Database Means

[0101] The database means is a system in which the server stores user questions and generated advice, allowing users to easily refer to past questions and advice. The database uses a database management system such as SQLite or PostgreSQL.

[0102] Examples and prompts

[0103] For example, suppose a user wants to start playing the guitar as a new hobby. The user opens a browser on their device, types the question "How do I start playing the guitar?", and presses the send button. This question is sent to the server.

[0104] The server sends a question to the generative AI model, which generates a prompt, for example:

[0105] How do I start playing guitar?

[0106] The generative AI model analyzes this and generates advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube." This advice is sent to the user's device via the server, where the user can view it on their device.

[0107] The system allows users to quickly get specific advice on starting a new hobby, and a database on the server records past questions and advice for future reference.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] A user types a question about a hobby into an electronic device and presses the send button. Input: "How do I start playing guitar?" Output: A command is generated that sends the question to the device.

[0111] Step 2:

[0112] The device sends the user's question to the server via the Internet. Specific operations include submitting a form using JavaScript or an HTTP POST request. Input: Question from the user. Output: HTTP request to the server.

[0113] Step 3:

[0114] The server processes the questions received from the terminal. The Django framework written in Python receives the HTTP POST request and extracts the question. Input: HTTP request from the terminal. Output: Variable that stores the question content.

[0115] Step 4:

[0116] The question received by the server is input into the generative AI model. The Python code uses the OpenAI API to create a prompt to send the question. The specific operation is to execute openai.Completion.create(prompt="How do I start playing guitar?", ...). Input: Question content. Output: API request to the generative AI model.

[0117] Step 5:

[0118] A generative artificial intelligence model analyzes the question and generates the best advice. It uses a large neural network to understand the context and generate specific instructions. Input: Prompt. Output: Advice: "To start playing guitar, start by learning simple chords and watching YouTube tutorials."

[0119] Step 6:

[0120] The server receives the advice returned from the generative AI model and stores it in memory. It receives the response from the OpenAI API and extracts the advice content. Input: API response from the generative AI model. Output: Variable that stores the advice content.

[0121] Step 7:

[0122] The server sends the advice to the user's device. The advice is returned to the front end as an HTTP response. The specific operation is to execute return JsonResponse({'advice': advice}). Input: Advice content. Output: HTTP response to the device.

[0123] Step 8:

[0124] The device displays the advice received from the server. The advice is displayed on the screen using the browser's DOM operations. Input: Advice content in the HTTP response. Output: Advice displayed on the browser.

[0125] Step 9:

[0126] The server saves the user's question and the generated advice in a database. A record is added to the database using Django ORM, specifically Advice.objects.create(question="How can I start playing guitar?", advice=advice). Input: Question and advice. Output: Database record created.

[0127] (Application example 1)

[0128] 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."

[0129] Traditionally, when starting a new hobby, it takes time and effort to gather information and learn basic skills, which causes many people to give up midway. Beginners, in particular, often find it difficult to determine which information is reliable, and inconsistent information often reduces learning efficiency. Therefore, there has been a demand for a support system that allows users to easily and effectively start a new hobby.

[0130] 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.

[0131] In this invention, the server includes an electronic device for a user to input and send questions about hobbies, means for inputting the questions received from the user to a generative AI model, means for the generative AI model to analyze the questions and generate optimal advice, means for sending the generated advice to the user's electronic device, means for displaying the advice received by the user's electronic device, means for providing related videos and articles along with the generated advice, and database means for recording questions previously sent by the user and the generated advice. This allows the user to consistently receive reliable information and efficiently learn new hobbies.

[0132] "Electronic devices" are devices that allow users to input and send questions about hobbies, and include smartphones, tablets, and personal computers.

[0133] A "generative artificial intelligence model" is an artificial intelligence used to analyze questions sent by users and generate optimal advice.

[0134] A "server" is a device or system that inputs questions received from a user into a generative artificial intelligence model and transmits the generated advice to the user's electronic device.

[0135] "Advice" is instructions or suggestions generated by a generative artificial intelligence model based on the user's questions, providing specific guidance on starting a new hobby.

[0136] The "related videos and articles" are reference materials related to the generated advice, and provide supplementary information for the user to efficiently learn about their hobbies.

[0137] The "database means" is a means for recording questions sent by users and advice generated, and storing them for later reference.

[0138] The present invention relates to a system for providing useful information to users who are about to start a new hobby. An embodiment of the system will be described in detail below.

[0139] System Configuration

[0140] The system of the present invention is broadly composed of the following elements:

[0141] 1. User's electronic devices

[0142] 2. Server

[0143] 3. Generative AI Models

[0144] 4. Database Means

[0145] Program Description

[0146] User's electronic devices

[0147] Users input and send questions about their hobbies using electronic devices such as smartphones, tablets, and personal computers. These electronic devices are equipped with communication means for transmitting the questions input by the users to a server.

[0148] server

[0149] The server is responsible for inputting questions received from users into the generative AI model. Specifically, the server manages the reception and transmission of questions using a web framework such as Flask, and has the function of transmitting question data to the generative AI model using the OpenAI API.

[0150] Generative AI model

[0151] Generative AI models analyze user-submitted questions and generate optimal advice, such as OpenAI's GPT-3. This AI model has been trained to answer questions about a variety of hobbies and can generate specific advice, steps, and links to related videos and articles.

[0152] Database Means

[0153] The generated advice and questions are saved and accumulated in a database by the server, allowing users to refer to past questions and advice at a later date. A relational database such as PostgreSQL or MySQL (registered trademark) is used for database management.

[0154] Specific examples

[0155] For example, a user inputs a question such as "How do I start playing the guitar?" into an electronic device and presses a send button. The question is sent to a server via the Internet.

[0156] The server inputs the following prompt into the generative AI model:

[0157] User Question: How do I get started on guitar?

[0158] Best advice:

[0159] The generative artificial intelligence model generates advice such as "First, practice some simple code and watch some YouTube tutorials," sometimes accompanied by links to related videos or articles.

[0160] The server sends the generated advice to the user's electronic device, which displays the advice, and the question and advice are stored in a database for future reference.

[0161] With the above configuration, users can easily and effectively start a new hobby. In addition, the database means allows users to refer to past questions and advice, realizing continuous learning support.

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] The user uses the device to input and submit a question about a hobby.

[0165] Input: User types "How do I start playing guitar?"

[0166] Output: The user's question is sent from the terminal to the server.

[0167] Specific operation: The user opens the application on their device, enters a question, and presses the "Submit" button. This input data is then sent to the server via the Internet.

[0168] Step 2:

[0169] The server receives a question from a user and generates a prompt sentence to send to the generative artificial intelligence model.

[0170] Input: Question data submitted by the user.

[0171] Output: A prompt to be input to the generative artificial intelligence model.

[0172] Specific behavior: The server analyzes the received question and generates a prompt of the form "User's question: How can I start playing guitar? Best advice:"

[0173] Step 3:

[0174] The server sends the generated prompt to a generative artificial intelligence model, which generates optimal advice.

[0175] Input: Prompt text "User asks: How do I start playing guitar? Best advice:".

[0176] Output: Advice generated by the generative artificial intelligence model.

[0177] What it does: The server sends the prompt to a generative AI model, such as OpenAI's API, and receives advice from the model. In this case, the advice is "First, practice some simple code and watch some YouTube tutorials."

[0178] Step 4:

[0179] The server transmits the generated advice to the user's terminal.

[0180] Input: Advice from a generative artificial intelligence model.

[0181] Output: Advisory message to the user's terminal.

[0182] Specific operation: The server organizes the generated advice and sends it to the user's device, where the user can view the advice message.

[0183] Step 5:

[0184] The user's terminal displays the received advice.

[0185] Input: The advice message sent by the server.

[0186] Output: Advice displayed on the screen.

[0187] Specific operation: The user's device displays the received advice on the application screen. The user confirms the advice, which is to "First practice some simple code and watch a tutorial on YouTube."

[0188] Step 6:

[0189] The server stores the user's question and the generated advice in a database.

[0190] Input: User question data and generated advice data.

[0191] Output: Questions and advice stored in a database.

[0192] What it does: The server stores the received questions and advice in a database, which can be referenced later, allowing users to review past questions and advice.

[0193] Through these processing steps, users can receive specific advice on starting a new hobby. Furthermore, the accumulation of past questions and advice supports continuous learning.

[0194] 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.

[0195] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[0196] System Configuration

[0197] 1. Terminal

[0198] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are forwarded to a server via the Internet.

[0199] 2. Server

[0200] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[0201] Ability to receive questions from users

[0202] A function that inputs user questions into the emotion engine and requests emotion analysis.

[0203] A function that inputs questions and sentiment analysis results into a generative AI model and obtains the analysis results.

[0204] A function to send generated advice to the user's device

[0205] Ability to store questions and generated advice in a database

[0206] 3. Emotion Engine

[0207] The emotion engine is an engine that analyzes user emotions from the text of questions sent by users and provides the analysis results to a generative AI model. This engine uses natural language processing technology to recognize emotions from context.

[0208] 4. Generative AI Models

[0209] The generative AI model is an artificial intelligence that generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, and provides specific advice, procedures, and reference information.

[0210] 5. Database Means

[0211] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0212] System Operation

[0213] A user inputs a question about a hobby into a terminal. For example, the user inputs a question such as "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to a server.

[0214] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion engine recognizes emotions such as "excited" or "anxious."

[0215] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[0216] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[0217] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[0218] The system allows users to easily participate in new hobbies and receives specific advice that takes their emotions into consideration during the process. It also features a database that allows users to refer to past data, which helps with continuous learning and information improvement.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] A user inputs a question about a hobby into a terminal and presses the send button. For example, the user inputs a question such as "How can I start playing the guitar?" The terminal then sends the question to the server.

[0222] Step 2:

[0223] The server receives the question from the user and passes it to the emotion engine. The server inputs the message "How do I start playing the guitar?" into the emotion engine.

[0224] Step 3:

[0225] The emotion engine analyzes the user's question and recognizes their emotion. For example, the emotion engine returns a result such as "This user is feeling anxious."

[0226] Step 4:

[0227] The server receives the emotion analysis results from the emotion engine and sends the analyzed emotion and the original question to the generative AI model.

[0228] Step 5:

[0229] The generative AI model generates optimal advice based on the question and the results of sentiment analysis. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed, unsettling state."

[0230] Step 6:

[0231] The server receives the advice returned by the generative AI model and sends it to the user's device. The server sends the following advice to the user's device: "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[0232] Step 7:

[0233] The user's device displays the advice received from the server: "To learn how to play guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[0234] Step 8:

[0235] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[0236] Step 9:

[0237] The server stores the questions sent by the user and the generated advice in a database. For example, the server records the question "How should I start playing guitar?" and the advice "Practice simple chords for beginners and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed manner without feeling anxious." This allows the server to quickly provide appropriate advice if the user asks a similar question later.

[0238] Example 2

[0239] 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."

[0240] It is important to provide an environment that allows users to easily start a new hobby by solving problems such as the high psychological hurdles, anxiety, and lack of concrete advice that users feel when starting a new hobby. In addition, it is necessary to provide more personalized and appropriate support by generating advice that takes into account the user's emotional state.

[0241] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting a question received from a user to an emotion analysis device to perform emotion analysis, a means for inputting the emotion analysis result and the question to a generative AI model, and a means for the generative AI model to analyze the emotion analysis result and the question and generate optimal advice. This makes it possible to provide specific advice that takes into account the user's emotional state.

[0242] "User" refers to an individual who utilizes the system to input hobby-related questions and obtain advice.

[0243] "Terminal" refers to an electronic device used by a user to input and send a question, and specifically includes a smartphone, tablet, PC, etc.

[0244] "Server" refers to a computer system that processes questions received from users, works with an emotion analysis device and a generative artificial intelligence model to generate advice, and transmits that advice to the user's terminal.

[0245] An "emotion analysis device" is a device that analyzes emotions from questions entered by users, and uses natural language processing technology to recognize emotions from context.

[0246] "Generative AI model" refers to an AI model that generates optimal advice based on a user's question and the results of sentiment analysis, and specifically includes trained machine learning models.

[0247] "Data repository" refers to a storage system for saving user questions and generated advice, and managing the data for future reference.

[0248] "Data management means" refers to means for recording and managing past questions and generated advice stored in a data storage device.

[0249] MODE FOR CARRYING OUT THE INVENTION

[0250] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. This system generates appropriate advice in response to user questions and provides support that takes into account the user's emotional state.

[0251] System Configuration

[0252] 1. Terminal

[0253] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[0254] 2. Server

[0255] The server processes questions received from users and generates advice in cooperation with the emotion analysis device and generative AI model. Specifically, it has the following functions:

[0256] Ability to receive questions from users

[0257] A function that inputs user questions into the emotion analysis device and requests emotion analysis.

[0258] A function that inputs sentiment analysis results and questions into a generative AI model and obtains the analysis results.

[0259] A function to send generated advice to the user's device

[0260] Ability to store questions and generated advice in a data repository

[0261] 3. Emotion analysis device

[0262] The emotion analysis device is a device for analyzing a user's emotion from the text of a question sent by the user, and recognizes the emotion from the context using natural language processing technology.

[0263] 4. Generative AI Models

[0264] The generative AI model generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[0265] 5. Data Storage Device

[0266] The data storage device stores and manages questions sent by users and advice generated by them, allowing users to refer to past questions and advice.

[0267] Hardware and software used

[0268] Devices: smartphones, tablets, computers

[0269] Server infrastructure: AWS (registered trademark) (Amazon Web Services) or Google (registered trademark) Cloud

[0270] Sentiment analysis software: Hume AI or Affectiva

[0271] Generative AI model: OpenAI's GPT-3 or GPT-4 (registered trademark)

[0272] Database: MySQL or MongoDB

[0273] Example of system operation

[0274] A user inputs a question about a hobby into a terminal. For example, "How can I start playing the guitar?" and presses the send button. The terminal sends this question to the server.

[0275] The server inputs the question received from the user into the emotion analysis device and requests emotion analysis. The emotion analysis device analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion analysis device recognizes emotions such as "excited" or "anxious."

[0276] The server inputs the sentiment analysis results and questions into a generative AI model, which then generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[0277] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[0278] Furthermore, the server stores the questions submitted by the user and the advice generated in a data storage device, so that past questions and advice can be easily retrieved for future reference.

[0279] Prompt Sentence Examples

[0280] "User Question: How do I start playing guitar?"

[0281] "Sentiment analysis result: excited"

[0282] "Generated advice: Practice simple beginner chords, watch beginner tutorials on YouTube, and relax before you start."

[0283] This method allows users to easily participate in new hobbies and receive specific advice that takes their emotions into consideration during the process. Furthermore, the data storage device allows users to refer to past data, which is useful for continuous learning and information improvement.

[0284] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0285] Step 1:

[0286] The user inputs a question about a hobby into the terminal and presses the send button.

[0287] Type: Type a question such as "How do I start playing guitar?"

[0288] Output: The question is waiting to be sent in the terminal.

[0289] Specifically, a user enters a question into an input field on the screen of a smartphone or computer, and then presses the "Send" button to send the question to the system.

[0290] Step 2:

[0291] The terminal sends a question to the server.

[0292] Input: The question entered by the user.

[0293] Output: The question is sent over the internet to a server.

[0294] Specifically, the device sends question data to the server's API endpoint using an HTTP POST request.

[0295] Step 3:

[0296] The server receives the query.

[0297] Input: The question sent from the terminal.

[0298] Output: The question is saved on the server and added to the processing queue.

[0299] Specifically, the server analyzes the received question data and prepares to proceed to the next step.

[0300] Step 4:

[0301] The server inputs a question into the emotion analysis device and requests emotion analysis.

[0302] Input: Question data stored on the server.

[0303] Output: An HTTP request for sentiment analysis is sent to the sentiment analyzer.

[0304] Specifically, the server sends the question data to the sentiment analysis API and waits for the results of the sentiment analysis.

[0305] Step 5:

[0306] The emotion analyzer analyzes the question and returns the analysis results to the server.

[0307] Input: Question data for which sentiment analysis was requested.

[0308] Output: JSON data containing the sentiment analysis results, such as "excited" or "anxious," is sent to the server.

[0309] Specifically, the emotion analysis device uses natural language processing technology to analyze emotions from the question text and returns the results to the server.

[0310] Step 6:

[0311] The server inputs the analysis results and questions into the generative AI model.

[0312] Input: Sentiment analysis results and question data.

[0313] Output: HTTP request to the generative AI model to generate advice.

[0314] Specifically, the server sends the emotion analysis results and question data as a prompt to the generative AI model's API. It creates and sends the prompt, "User question: What should I do to start playing guitar?" and "Emotion analysis result: I'm excited."

[0315] Step 7:

[0316] The generative AI model generates advice and sends it back to the server.

[0317] Input: A prompt statement containing sentiment analysis results and question data.

[0318] Output: JSON data containing the advice is sent back to the server.

[0319] Specifically, the generative AI model analyzes the prompt sentence, generates optimal advice, and sends it back to the server.

[0320] Step 8:

[0321] The server receives the advice and sends it to the user's terminal.

[0322] Input: Advice data from a generative AI model.

[0323] Output: The advice is sent to the user's terminal.

[0324] Specifically, the server sends the generated advice to the user's terminal as an HTTP response and prepares data for display.

[0325] Step 9:

[0326] The terminal displays the advice to the user.

[0327] Input: Advice data sent by the server.

[0328] Output: The advice is displayed on the terminal screen.

[0329] Specifically, the terminal reflects the received advice on the display screen, and the user can check the specific instructions on the screen.

[0330] Step 10:

[0331] The server stores the questions and advice in a data storage device.

[0332] Input: User question and generated advice data.

[0333] Output: Questions and advice are saved in a database.

[0334] Specifically, the server inserts the questions and advice into a database and manages them for future reference.

[0335] (Application example 2)

[0336] 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."

[0337] In modern factory work, it is important to reduce the anxiety and confusion workers feel when adapting to new equipment and work methods. In particular, lack of knowledge about new tasks and equipment and difficulty in operating them can cause stress and reduced work efficiency. Conventional support systems simply provide manuals and videos, making it difficult to provide specific advice in real time while taking into consideration the worker's feelings. The present invention solves these problems and provides a system that allows workers to tackle new tasks with peace of mind.

[0338] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal through which a user inputs and transmits a question about a hobby, a means for the server to input the question received from the user to a generative AI model, a means for the generative AI model to generate optimal advice based on the question and emotion analysis results, a means for the server to transmit the generated advice to the user's terminal, a means for the user's terminal to display the received advice, a means for inputting a question via voice input, and a means for analyzing emotions from the user's question using an emotion engine. This enables workers to easily ask questions via voice input and receive specific advice in real time that takes their emotions into consideration.

[0339] A "user" is an individual or worker who uses the system to enter hobby-related questions and receive advice.

[0340] A "terminal" is an electronic device used by a user, and includes a smartphone, tablet, PC, voice input device, etc. for inputting and sending a question.

[0341] The "server" is a computer system that receives data from users, works with generative AI models and emotion engines to generate advice, and sends that advice to the user's device.

[0342] A "generative AI model" is an artificial intelligence model that generates optimal advice based on the user's questions and the results of emotional analysis, and is trained to respond to questions about a variety of hobbies and tasks.

[0343] The "emotion engine" is an engine for analyzing a user's emotions from the text of a question sent by the user, and recognizes emotions from the context using natural language processing technology.

[0344] "Advice" refers to specific instructions, steps, and reference information generated by generative AI models to help users get started on a new hobby or task.

[0345] "Voice input" is a method in which a user inputs a question by voice using a microphone or the like, and the question is converted into text data using voice recognition technology.

[0346] "Emotion analysis result" refers to the emotional state (e.g., anxiety, excitement, hesitation, etc.) extracted from the user's question by the emotion engine.

[0347] This invention is a system that uses a generative AI model and an emotion engine to reduce anxiety about new tasks and equipment in factory work, allowing workers to work safely and efficiently. This system is implemented with the following configuration.

[0348] System Configuration

[0349] 1. Terminal

[0350] This is an electronic device that allows users (factory workers) to input and send questions about work. Terminals include smartphones, tablets, voice input devices, and microphones built into robots. Questions sent by the terminals are transferred to a server via the Internet.

[0351] 2. Server

[0352] The server processes questions received from users, generates advice through a generative AI model and emotion engine, and sends it to the user's device. Specifically, the server has the following functions:

[0353] Ability to receive questions from users

[0354] A function that inputs user questions into the emotion engine and requests emotion analysis.

[0355] A function that inputs questions and sentiment analysis results into a generative AI model to generate advice.

[0356] A function to send generated advice to the user's device

[0357] Ability to store questions and generated advice in a database

[0358] 3. Emotion Engine

[0359] The emotion engine is an engine that analyzes the user's emotions from the text of the question sent by the user, and recognizes emotions from the context using natural language processing technology. For example, it analyzes emotions such as "anxiety," "excitement," and "hesitation," and provides the results to the generative AI model.

[0360] 4. Generative AI Models

[0361] A generative AI model is an artificial intelligence that generates optimal advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to handle a wide range of tasks, providing specific advice, procedures, and reference information.

[0362] 5. Database Means

[0363] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0364] System Operation

[0365] Voice input

[0366] A user (factory worker) uses the voice input function of the terminal to input a question about work. For example, the user inputs a question such as, "I'm worried because I don't know how to operate the new welding machine. What should I do?"

[0367] Submit a Question

[0368] When the user presses the send button, the terminal sends this question to the server.

[0369] Emotion analysis

[0370] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, it may recognize "anxiety" as the analysis result.

[0371] Advice Generation

[0372] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the following advice: "When operating a new welding machine, we recommend that you first review basic safety guidelines and watch the manufacturer's official tutorial video. Also, when welding for the first time, try practicing on some scrap metal and relax."

[0373] Sending and viewing advice

[0374] The server receives the generated advice and sends the contents of the advice to the user's terminal, which displays the received advice.

[0375] Specific examples and prompts for generative AI models

[0376] For example, if a worker asks the robot the following question:

[0377] Input Audio:

[0378] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[0379] Example prompt:

[0380] Q: I'm worried about how to operate my new welding machine. What should I do?

[0381] Emotion: Anxiety

[0382] This system allows factory workers to easily ask questions through voice input and receive specific advice in real time that takes their emotions into consideration, reducing anxiety about new tasks and equipment and enabling them to work efficiently and with peace of mind.

[0383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0384] Step 1:

[0385] User question input

[0386] The user (factory worker) uses the device's voice input function to input a question about work. For example, the user might say, "I'm worried because I don't know how to operate the new welding machine. What should I do?" The input data here is voice data. The device converts this voice data into text data using voice recognition software (for example, Google Speech Recognition). The converted text data is then output.

[0387] Step 2:

[0388] Submit a Question

[0389] The question converted into text data is sent from the terminal to the server. The terminal then sends this data to the server via the Internet. The input is text data, and the output is the text data sent to the server.

[0390] Step 3:

[0391] Sentiment analysis request

[0392] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The input is text data, and the emotion engine uses natural language processing technology to analyze the text data and recognize emotions (such as "anxiety" or "excitement"). Emotion data is output as the analysis result.

[0393] Step 4:

[0394] Request for advice generation

[0395] The server inputs the emotion analysis results and the question into the generative AI model and requests it to generate advice. The input is text data and emotion data. The generative AI model generates appropriate advice based on this input data. The generated advice (text data) is output.

[0396] Step 5:

[0397] Sending Advice

[0398] The server receives the generated advice and sends it to the user's terminal. The input is the generated advice (text data), and the output is the advice sent to the terminal.

[0399] Step 6:

[0400] Displaying Advice

[0401] The user's device displays the received advice. The device provides the user with visual information by outputting the advice content on the display. The input is the advice (text data), and the output is the advice displayed on the display.

[0402] Examples and prompts

[0403] For example, if a worker asks the robot the following question:

[0404] Input Audio:

[0405] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[0406] Example prompt:

[0407] Q: I'm worried about how to operate my new welding machine. What should I do?

[0408] Emotion: Anxiety

[0409] In this case, users can simply ask questions through voice input and receive specific advice in real time that takes their emotions into consideration.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Second embodiment]

[0414] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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."

[0426] This invention provides a system that uses generative AI to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[0427] System Configuration

[0428] 1. Terminal

[0429] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[0430] 2. Server

[0431] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[0432] Ability to receive questions from users

[0433] A function that allows users to input questions into a generative AI model and obtain analysis results.

[0434] A function to send generated advice to the user's device

[0435] Ability to store questions and generated advice in a database

[0436] 3. Generative AI Models

[0437] The generative AI model is an artificial intelligence that analyzes questions sent by users and generates optimal advice. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[0438] 4. Database Means

[0439] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0440] System Operation

[0441] A user inputs a question about a hobby into a terminal. For example, consider the question "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to the server.

[0442] The server inputs the question received from the user into the generative AI model. The generative AI model analyzes the question and generates the best advice for the user. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, first practice simple chords and watch YouTube tutorials."

[0443] Once the advice is generated, the server sends it to the user's device, which then displays it, allowing the user to receive specific instructions and follow them to start a new hobby.

[0444] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[0445] This system allows users to easily participate in new hobbies and quickly obtain specific information tailored to their interests. The database function also allows users to refer to past data, which is useful for continuous learning and information improvement.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The user inputs a question about a hobby into the terminal and presses the send button. An example of this input is "How do I start playing the guitar?" The terminal sends this question to the server.

[0449] Step 2:

[0450] The server receives the question from the user and checks its content. For example, the server checks the content of "How do I start playing the guitar?"

[0451] Step 3:

[0452] The server sends the received message to the generative AI model and requests it to analyze it. At this time, the server inputs the question "guitar" into the AI ​​model.

[0453] Step 4:

[0454] A generative AI model analyzes the questions sent and generates optimal advice. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, start by practicing simple chords and watching YouTube tutorials."

[0455] Step 5:

[0456] The server receives the advice returned by the generative AI model and sends it to the user's device. Based on the user's ID, the server sends the advice, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube," to the appropriate device.

[0457] Step 6:

[0458] The user's device displays the advice received from the server. The device shows the user, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube."

[0459] Step 7:

[0460] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[0461] Step 8:

[0462] The server stores the questions submitted by users and the advice generated in a database, which makes it easy to retrieve past questions and advice for future reference.

[0463] Step 9:

[0464] If the user asks the question again, or if another user asks a similar question, the server can use its accumulated database to quickly provide appropriate advice. The process repeats.

[0465] Example 1

[0466] 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."

[0467] In modern society, interest in a variety of hobbies is growing, but gathering information and obtaining specific advice when starting a new hobby presents challenges. Beginners face particular challenges in the initial stages, such as determining the necessary procedures and tools, making it difficult to quickly obtain appropriate information. However, conventional methods require users to individually search for information and determine its reliability, making them inefficient and ineffective. Therefore, there is a need to develop a system that uses generative artificial intelligence models to provide users with optimal advice.

[0468] 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.

[0469] In this invention, the server includes an electronic device into which a user inputs and transmits a question about a hobby, means for inputting the question received from the user to a generative AI model, means for the generative AI model to analyze the question and generate optimal advice, means for the server to transmit the generated advice to the user's electronic device, and means for the user's electronic device to display the received advice, thereby enabling the user to quickly obtain specific information for starting a new hobby.

[0470] An "electronic device" is a device that has the function of accepting input from a user via the Internet and sending questions to a server, and specifically includes smartphones, tablets, and personal computers.

[0471] A "server" is a computer system that has the functionality to process questions received from users, input them into a generative artificial intelligence model, and send the generated advice to the user's electronic device.

[0472] A "generative artificial intelligence model" is an artificial intelligence system that analyzes questions entered by users and generates optimal advice. It is trained using natural language processing technology to be able to respond to questions about a variety of hobbies.

[0473] A "question" is a specific information request that a user enters when starting a new hobby, and is input data for analysis by the generative artificial intelligence model.

[0474] "Advice" refers to specific instructions or information that the generative artificial intelligence model outputs as an analysis result, and is used as a reference when a user starts a new hobby.

[0475] The "database means" is a system in which the server stores and manages user questions and generated advice, and has a function that allows past data to be easily referenced.

[0476] This invention provides a system that uses a generative AI model to lower the barrier to users starting a new hobby. The system is composed of five elements: a user, a terminal, a server, a generative AI model, and a database means.

[0477] System Configuration and Operation

[0478] 1. Users

[0479] A user inputs a question about a hobby into an electronic device (e.g., a smartphone, a tablet, or a PC). For example, consider a case where a user inputs the question "How can I start playing the guitar?" into a PC.

[0480] 2. Terminal

[0481] The device sends the questions entered by the user to the server via an Internet connection, using JavaScript form submissions or HTTP requests.

[0482] 3. Server

[0483] The server receives user questions and inputs them into the generative artificial intelligence model. The server includes the following functions:

[0484] Question receiving function (e.g., implemented using the Django framework)

[0485] Inputting data into a generative AI model (e.g., using OpenAI API)

[0486] Receiving generated advice

[0487] Sending advice to user terminal

[0488] Database storage of questions and advice (e.g., managed using SQLite or PostgreSQL)

[0489] Specifically, the server is written in Python and built using the Django framework. This server processes HTTP requests from users and sends questions to a generative artificial intelligence model (e.g., OpenAI's GPT-3 model) using an appropriate API. The generated advice is then sent back to the user's device as an HTTP response. In addition, a database is installed on the server to manage past questions and advice.

[0490] 4. Generative AI Models

[0491] A generative artificial intelligence model (e.g., OpenAI's GPT-3) analyzes questions sent via a server and generates optimal advice. The AI ​​model is trained to provide specific instructions and reference information in response to the user's question. For example, it might generate advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube."

[0492] 5. Database Means

[0493] The database means is a system in which the server stores user questions and generated advice, allowing users to easily refer to past questions and advice. The database uses a database management system such as SQLite or PostgreSQL.

[0494] Examples and prompts

[0495] For example, suppose a user wants to start playing the guitar as a new hobby. The user opens a browser on their device, types the question "How do I start playing the guitar?", and presses the send button. This question is sent to the server.

[0496] The server sends a question to the generative AI model, which generates a prompt, for example:

[0497] How do I start playing guitar?

[0498] The generative AI model analyzes this and generates advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube." This advice is sent to the user's device via the server, where the user can view it on their device.

[0499] The system allows users to quickly get specific advice on starting a new hobby, and a database on the server records past questions and advice for future reference.

[0500] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0501] Step 1:

[0502] A user types a question about a hobby into an electronic device and presses the send button. Input: "How do I start playing guitar?" Output: A command is generated that sends the question to the device.

[0503] Step 2:

[0504] The device sends the user's question to the server via the Internet. Specific operations include submitting a form using JavaScript or an HTTP POST request. Input: Question from the user. Output: HTTP request to the server.

[0505] Step 3:

[0506] The server processes the questions received from the terminal. The Django framework written in Python receives the HTTP POST request and extracts the question. Input: HTTP request from the terminal. Output: Variable that stores the question content.

[0507] Step 4:

[0508] The question received by the server is input into the generative AI model. The Python code uses the OpenAI API to create a prompt to send the question. The specific operation is to execute openai.Completion.create(prompt="How do I start playing guitar?", ...). Input: Question content. Output: API request to the generative AI model.

[0509] Step 5:

[0510] A generative artificial intelligence model analyzes the question and generates the best advice. It uses a large neural network to understand the context and generate specific instructions. Input: Prompt. Output: Advice: "To start playing guitar, start by learning simple chords and watching YouTube tutorials."

[0511] Step 6:

[0512] The server receives the advice returned from the generative AI model and stores it in memory. It receives the response from the OpenAI API and extracts the advice content. Input: API response from the generative AI model. Output: Variable that stores the advice content.

[0513] Step 7:

[0514] The server sends the advice to the user's device. The advice is returned to the front end as an HTTP response. The specific operation is to execute return JsonResponse({'advice': advice}). Input: Advice content. Output: HTTP response to the device.

[0515] Step 8:

[0516] The device displays the advice received from the server. The advice is displayed on the screen using the browser's DOM operations. Input: Advice content in the HTTP response. Output: Advice displayed on the browser.

[0517] Step 9:

[0518] The server saves the user's question and the generated advice in a database. A record is added to the database using Django ORM, specifically Advice.objects.create(question="How can I start playing guitar?", advice=advice). Input: Question and advice. Output: Database record created.

[0519] (Application example 1)

[0520] 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."

[0521] Traditionally, when starting a new hobby, it takes time and effort to gather information and learn basic skills, which causes many people to give up midway. Beginners, in particular, often find it difficult to determine which information is reliable, and inconsistent information often reduces learning efficiency. Therefore, there has been a demand for a support system that allows users to easily and effectively start a new hobby.

[0522] 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.

[0523] In this invention, the server includes an electronic device for a user to input and send questions about hobbies, means for inputting the questions received from the user to a generative AI model, means for the generative AI model to analyze the questions and generate optimal advice, means for sending the generated advice to the user's electronic device, means for displaying the advice received by the user's electronic device, means for providing related videos and articles along with the generated advice, and database means for recording questions previously sent by the user and the generated advice. This allows the user to consistently receive reliable information and efficiently learn new hobbies.

[0524] "Electronic devices" are devices that allow users to input and send questions about hobbies, and include smartphones, tablets, and personal computers.

[0525] A "generative artificial intelligence model" is an artificial intelligence used to analyze questions sent by users and generate optimal advice.

[0526] A "server" is a device or system that inputs questions received from a user into a generative artificial intelligence model and transmits the generated advice to the user's electronic device.

[0527] "Advice" is instructions or suggestions generated by a generative artificial intelligence model based on the user's questions, providing specific guidance on starting a new hobby.

[0528] The "related videos and articles" are reference materials related to the generated advice, and provide supplementary information for the user to efficiently learn about their hobbies.

[0529] The "database means" is a means for recording questions sent by users and advice generated, and storing them for later reference.

[0530] The present invention relates to a system for providing useful information to users who are about to start a new hobby. An embodiment of the system will be described in detail below.

[0531] System Configuration

[0532] The system of the present invention is broadly composed of the following elements:

[0533] 1. User's electronic devices

[0534] 2. Server

[0535] 3. Generative AI Models

[0536] 4. Database Means

[0537] Program Description

[0538] User's electronic devices

[0539] Users input and send questions about their hobbies using electronic devices such as smartphones, tablets, and personal computers. These electronic devices are equipped with communication means for transmitting the questions input by the users to a server.

[0540] server

[0541] The server is responsible for inputting questions received from users into the generative AI model. Specifically, the server manages the reception and transmission of questions using a web framework such as Flask, and has the function of transmitting question data to the generative AI model using the OpenAI API.

[0542] Generative AI model

[0543] Generative AI models analyze user-submitted questions and generate optimal advice, such as OpenAI's GPT-3. This AI model has been trained to answer questions about a variety of hobbies and can generate specific advice, steps, and links to related videos and articles.

[0544] Database Means

[0545] The generated advice and questions are saved and accumulated in a database by the server, allowing users to refer to past questions and advice later.For database management, a relational database such as PostgreSQL or MySQL is used.

[0546] Specific examples

[0547] For example, a user inputs a question such as "How do I start playing the guitar?" into an electronic device and presses a send button. The question is sent to a server via the Internet.

[0548] The server inputs the following prompt into the generative AI model:

[0549] User Question: How do I get started on guitar?

[0550] Best advice:

[0551] The generative artificial intelligence model generates advice such as "First, practice some simple code and watch some YouTube tutorials," sometimes accompanied by links to related videos or articles.

[0552] The server sends the generated advice to the user's electronic device, which displays the advice, and the question and advice are stored in a database for future reference.

[0553] With the above configuration, users can easily and effectively start a new hobby. In addition, the database means allows users to refer to past questions and advice, realizing continuous learning support.

[0554] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0555] Step 1:

[0556] The user uses the device to input and submit a question about a hobby.

[0557] Input: User types "How do I start playing guitar?"

[0558] Output: The user's question is sent from the terminal to the server.

[0559] Specific operation: The user opens the application on their device, enters a question, and presses the "Submit" button. This input data is then sent to the server via the Internet.

[0560] Step 2:

[0561] The server receives a question from a user and generates a prompt sentence to send to the generative artificial intelligence model.

[0562] Input: Question data submitted by the user.

[0563] Output: A prompt to be input to the generative artificial intelligence model.

[0564] Specific behavior: The server analyzes the received question and generates a prompt of the form "User's question: How can I start playing guitar? Best advice:"

[0565] Step 3:

[0566] The server sends the generated prompt to a generative artificial intelligence model, which generates optimal advice.

[0567] Input: Prompt text "User asks: How do I start playing guitar? Best advice:".

[0568] Output: Advice generated by the generative artificial intelligence model.

[0569] What it does: The server sends the prompt to a generative AI model, such as OpenAI's API, and receives advice from the model. In this case, the advice is "First, practice some simple code and watch some YouTube tutorials."

[0570] Step 4:

[0571] The server transmits the generated advice to the user's terminal.

[0572] Input: Advice from a generative artificial intelligence model.

[0573] Output: Advisory message to the user's terminal.

[0574] Specific operation: The server organizes the generated advice and sends it to the user's device, where the user can view the advice message.

[0575] Step 5:

[0576] The user's terminal displays the received advice.

[0577] Input: The advice message sent by the server.

[0578] Output: Advice displayed on the screen.

[0579] Specific operation: The user's device displays the received advice on the application screen. The user confirms the advice, which is to "First practice some simple code and watch a tutorial on YouTube."

[0580] Step 6:

[0581] The server stores the user's question and the generated advice in a database.

[0582] Input: User question data and generated advice data.

[0583] Output: Questions and advice stored in a database.

[0584] What it does: The server stores the received questions and advice in a database, which can be referenced later, allowing users to review past questions and advice.

[0585] Through these processing steps, users can receive specific advice on starting a new hobby. Furthermore, the accumulation of past questions and advice supports continuous learning.

[0586] 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.

[0587] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[0588] System Configuration

[0589] 1. Terminal

[0590] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are forwarded to a server via the Internet.

[0591] 2. Server

[0592] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[0593] Ability to receive questions from users

[0594] A function that inputs user questions into the emotion engine and requests emotion analysis.

[0595] A function that inputs questions and sentiment analysis results into a generative AI model and obtains the analysis results.

[0596] A function to send generated advice to the user's device

[0597] Ability to store questions and generated advice in a database

[0598] 3. Emotion Engine

[0599] The emotion engine is an engine that analyzes user emotions from the text of questions sent by users and provides the analysis results to a generative AI model. This engine uses natural language processing technology to recognize emotions from context.

[0600] 4. Generative AI Models

[0601] The generative AI model is an artificial intelligence that generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, and provides specific advice, procedures, and reference information.

[0602] 5. Database Means

[0603] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0604] System Operation

[0605] A user inputs a question about a hobby into a terminal. For example, the user inputs a question such as "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to a server.

[0606] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion engine recognizes emotions such as "excited" or "anxious."

[0607] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[0608] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[0609] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[0610] The system allows users to easily participate in new hobbies and receives specific advice that takes their emotions into consideration during the process. It also features a database that allows users to refer to past data, which helps with continuous learning and information improvement.

[0611] The processing flow will be explained below.

[0612] Step 1:

[0613] A user inputs a question about a hobby into a terminal and presses the send button. For example, the user inputs a question such as "How can I start playing the guitar?" The terminal then sends the question to the server.

[0614] Step 2:

[0615] The server receives the question from the user and passes it to the emotion engine. The server inputs the message "How do I start playing the guitar?" into the emotion engine.

[0616] Step 3:

[0617] The emotion engine analyzes the user's question and recognizes their emotion. For example, the emotion engine returns a result such as "This user is feeling anxious."

[0618] Step 4:

[0619] The server receives the emotion analysis results from the emotion engine and sends the analyzed emotion and the original question to the generative AI model.

[0620] Step 5:

[0621] The generative AI model generates optimal advice based on the question and the results of sentiment analysis. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed, unsettling state."

[0622] Step 6:

[0623] The server receives the advice returned by the generative AI model and sends it to the user's device. The server sends the following advice to the user's device: "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[0624] Step 7:

[0625] The user's device displays the advice received from the server: "To learn how to play guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[0626] Step 8:

[0627] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[0628] Step 9:

[0629] The server stores the questions sent by the user and the generated advice in a database. For example, the server records the question "How should I start playing guitar?" and the advice "Practice simple chords for beginners and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed manner without feeling anxious." This allows the server to quickly provide appropriate advice if the user asks a similar question later.

[0630] Example 2

[0631] 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."

[0632] It is important to provide an environment that allows users to easily start a new hobby by solving problems such as the high psychological hurdles, anxiety, and lack of concrete advice that users feel when starting a new hobby. In addition, it is necessary to provide more personalized and appropriate support by generating advice that takes into account the user's emotional state.

[0633] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting a question received from a user to an emotion analysis device to perform emotion analysis, a means for inputting the emotion analysis result and the question to a generative AI model, and a means for the generative AI model to analyze the emotion analysis result and the question and generate optimal advice. This makes it possible to provide specific advice that takes into account the user's emotional state.

[0634] "User" refers to an individual who utilizes the system to input hobby-related questions and obtain advice.

[0635] "Terminal" refers to an electronic device used by a user to input and send a question, and specifically includes a smartphone, tablet, PC, etc.

[0636] "Server" refers to a computer system that processes questions received from users, works with an emotion analysis device and a generative artificial intelligence model to generate advice, and transmits that advice to the user's terminal.

[0637] An "emotion analysis device" is a device that analyzes emotions from questions entered by users, and uses natural language processing technology to recognize emotions from context.

[0638] "Generative AI model" refers to an AI model that generates optimal advice based on a user's question and the results of sentiment analysis, and specifically includes trained machine learning models.

[0639] "Data repository" refers to a storage system for saving user questions and generated advice, and managing the data for future reference.

[0640] "Data management means" refers to means for recording and managing past questions and generated advice stored in a data storage device.

[0641] MODE FOR CARRYING OUT THE INVENTION

[0642] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. This system generates appropriate advice in response to user questions and provides support that takes into account the user's emotional state.

[0643] System Configuration

[0644] 1. Terminal

[0645] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[0646] 2. Server

[0647] The server processes questions received from users and generates advice in cooperation with the emotion analysis device and generative AI model. Specifically, it has the following functions:

[0648] Ability to receive questions from users

[0649] A function that inputs user questions into the emotion analysis device and requests emotion analysis.

[0650] A function that inputs sentiment analysis results and questions into a generative AI model and obtains the analysis results.

[0651] A function to send generated advice to the user's device

[0652] Ability to store questions and generated advice in a data repository

[0653] 3. Emotion analysis device

[0654] The emotion analysis device is a device for analyzing a user's emotion from the text of a question sent by the user, and recognizes the emotion from the context using natural language processing technology.

[0655] 4. Generative AI Models

[0656] The generative AI model generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[0657] 5. Data Storage Device

[0658] The data storage device stores and manages questions sent by users and advice generated by them, allowing users to refer to past questions and advice.

[0659] Hardware and software used

[0660] Devices: smartphones, tablets, computers

[0661] Server infrastructure: AWS (Amazon Web Services) or Google Cloud

[0662] Sentiment analysis software: Hume AI or Affectiva

[0663] Generative AI model: OpenAI's GPT-3 or GPT-4

[0664] Database: MySQL or MongoDB

[0665] Example of system operation

[0666] A user inputs a question about a hobby into a terminal. For example, "How can I start playing the guitar?" and presses the send button. The terminal sends this question to the server.

[0667] The server inputs the question received from the user into the emotion analysis device and requests emotion analysis. The emotion analysis device analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion analysis device recognizes emotions such as "excited" or "anxious."

[0668] The server inputs the sentiment analysis results and questions into a generative AI model, which then generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[0669] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[0670] Furthermore, the server stores the questions submitted by the user and the advice generated in a data storage device, so that past questions and advice can be easily retrieved for future reference.

[0671] Prompt Sentence Examples

[0672] "User Question: How do I start playing guitar?"

[0673] "Sentiment analysis result: excited"

[0674] "Generated advice: Practice simple beginner chords, watch beginner tutorials on YouTube, and relax before you start."

[0675] This method allows users to easily participate in new hobbies and receive specific advice that takes their emotions into consideration during the process. Furthermore, the data storage device allows users to refer to past data, which is useful for continuous learning and information improvement.

[0676] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0677] Step 1:

[0678] The user inputs a question about a hobby into the terminal and presses the send button.

[0679] Type: Type a question such as "How do I start playing guitar?"

[0680] Output: The question is waiting to be sent in the terminal.

[0681] Specifically, a user enters a question into an input field on the screen of a smartphone or computer, and then presses the "Send" button to send the question to the system.

[0682] Step 2:

[0683] The terminal sends a question to the server.

[0684] Input: The question entered by the user.

[0685] Output: The question is sent over the internet to a server.

[0686] Specifically, the device sends question data to the server's API endpoint using an HTTP POST request.

[0687] Step 3:

[0688] The server receives the query.

[0689] Input: The question sent from the terminal.

[0690] Output: The question is saved on the server and added to the processing queue.

[0691] Specifically, the server analyzes the received question data and prepares to proceed to the next step.

[0692] Step 4:

[0693] The server inputs a question into the emotion analysis device and requests emotion analysis.

[0694] Input: Question data stored on the server.

[0695] Output: An HTTP request for sentiment analysis is sent to the sentiment analyzer.

[0696] Specifically, the server sends the question data to the sentiment analysis API and waits for the results of the sentiment analysis.

[0697] Step 5:

[0698] The emotion analyzer analyzes the question and returns the analysis results to the server.

[0699] Input: Question data for which sentiment analysis was requested.

[0700] Output: JSON data containing the sentiment analysis results, such as "excited" or "anxious," is sent to the server.

[0701] Specifically, the emotion analysis device uses natural language processing technology to analyze emotions from the question text and returns the results to the server.

[0702] Step 6:

[0703] The server inputs the analysis results and questions into the generative AI model.

[0704] Input: Sentiment analysis results and question data.

[0705] Output: HTTP request to the generative AI model to generate advice.

[0706] Specifically, the server sends the emotion analysis results and question data as a prompt to the generative AI model's API. It creates and sends the prompt, "User question: What should I do to start playing guitar?" and "Emotion analysis result: I'm excited."

[0707] Step 7:

[0708] The generative AI model generates advice and sends it back to the server.

[0709] Input: A prompt statement containing sentiment analysis results and question data.

[0710] Output: JSON data containing the advice is sent back to the server.

[0711] Specifically, the generative AI model analyzes the prompt sentence, generates optimal advice, and sends it back to the server.

[0712] Step 8:

[0713] The server receives the advice and sends it to the user's terminal.

[0714] Input: Advice data from a generative AI model.

[0715] Output: The advice is sent to the user's terminal.

[0716] Specifically, the server sends the generated advice to the user's terminal as an HTTP response and prepares data for display.

[0717] Step 9:

[0718] The terminal displays the advice to the user.

[0719] Input: Advice data sent by the server.

[0720] Output: The advice is displayed on the terminal screen.

[0721] Specifically, the terminal reflects the received advice on the display screen, and the user can check the specific instructions on the screen.

[0722] Step 10:

[0723] The server stores the questions and advice in a data storage device.

[0724] Input: User question and generated advice data.

[0725] Output: Questions and advice are saved in a database.

[0726] Specifically, the server inserts the questions and advice into a database and manages them for future reference.

[0727] (Application example 2)

[0728] 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."

[0729] In modern factory work, it is important to reduce the anxiety and confusion workers feel when adapting to new equipment and work methods. In particular, lack of knowledge about new tasks and equipment and difficulty in operating them can cause stress and reduced work efficiency. Conventional support systems simply provide manuals and videos, making it difficult to provide specific advice in real time while taking into consideration the worker's feelings. The present invention solves these problems and provides a system that allows workers to tackle new tasks with peace of mind.

[0730] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal through which a user inputs and transmits a question about a hobby, a means for the server to input the question received from the user to a generative AI model, a means for the generative AI model to generate optimal advice based on the question and emotion analysis results, a means for the server to transmit the generated advice to the user's terminal, a means for the user's terminal to display the received advice, a means for inputting a question via voice input, and a means for analyzing emotions from the user's question using an emotion engine. This enables workers to easily ask questions via voice input and receive specific advice in real time that takes their emotions into consideration.

[0731] A "user" is an individual or worker who uses the system to enter hobby-related questions and receive advice.

[0732] A "terminal" is an electronic device used by a user, and includes a smartphone, tablet, PC, voice input device, etc. for inputting and sending a question.

[0733] The "server" is a computer system that receives data from users, works with generative AI models and emotion engines to generate advice, and sends that advice to the user's device.

[0734] A "generative AI model" is an artificial intelligence model that generates optimal advice based on the user's questions and the results of emotional analysis, and is trained to respond to questions about a variety of hobbies and tasks.

[0735] The "emotion engine" is an engine for analyzing a user's emotions from the text of a question sent by the user, and recognizes emotions from the context using natural language processing technology.

[0736] "Advice" refers to specific instructions, steps, and reference information generated by generative AI models to help users get started on a new hobby or task.

[0737] "Voice input" is a method in which a user inputs a question by voice using a microphone or the like, and the question is converted into text data using voice recognition technology.

[0738] "Emotion analysis result" refers to the emotional state (e.g., anxiety, excitement, hesitation, etc.) extracted from the user's question by the emotion engine.

[0739] This invention is a system that uses a generative AI model and an emotion engine to reduce anxiety about new tasks and equipment in factory work, allowing workers to work safely and efficiently. This system is implemented with the following configuration.

[0740] System Configuration

[0741] 1. Terminal

[0742] This is an electronic device that allows users (factory workers) to input and send questions about work. Terminals include smartphones, tablets, voice input devices, and microphones built into robots. Questions sent by the terminals are transferred to a server via the Internet.

[0743] 2. Server

[0744] The server processes questions received from users, generates advice through a generative AI model and emotion engine, and sends it to the user's device. Specifically, the server has the following functions:

[0745] Ability to receive questions from users

[0746] A function that inputs user questions into the emotion engine and requests emotion analysis.

[0747] A function that inputs questions and sentiment analysis results into a generative AI model to generate advice.

[0748] A function to send generated advice to the user's device

[0749] Ability to store questions and generated advice in a database

[0750] 3. Emotion Engine

[0751] The emotion engine is an engine that analyzes the user's emotions from the text of the question sent by the user, and recognizes emotions from the context using natural language processing technology. For example, it analyzes emotions such as "anxiety," "excitement," and "hesitation," and provides the results to the generative AI model.

[0752] 4. Generative AI Models

[0753] A generative AI model is an artificial intelligence that generates optimal advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to handle a wide range of tasks, providing specific advice, procedures, and reference information.

[0754] 5. Database Means

[0755] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0756] System Operation

[0757] Voice input

[0758] A user (factory worker) uses the voice input function of the terminal to input a question about work. For example, the user inputs a question such as, "I'm worried because I don't know how to operate the new welding machine. What should I do?"

[0759] Submit a Question

[0760] When the user presses the send button, the terminal sends this question to the server.

[0761] Emotion analysis

[0762] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, it may recognize "anxiety" as the analysis result.

[0763] Advice Generation

[0764] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the following advice: "When operating a new welding machine, we recommend that you first review basic safety guidelines and watch the manufacturer's official tutorial video. Also, when welding for the first time, try practicing on some scrap metal and relax."

[0765] Sending and viewing advice

[0766] The server receives the generated advice and sends the contents of the advice to the user's terminal, which displays the received advice.

[0767] Specific examples and prompts for generative AI models

[0768] For example, if a worker asks the robot the following question:

[0769] Input Audio:

[0770] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[0771] Example prompt:

[0772] Q: I'm worried about how to operate my new welding machine. What should I do?

[0773] Emotion: Anxiety

[0774] This system allows factory workers to easily ask questions through voice input and receive specific advice in real time that takes their emotions into consideration, reducing anxiety about new tasks and equipment and enabling them to work efficiently and with peace of mind.

[0775] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0776] Step 1:

[0777] User question input

[0778] The user (factory worker) uses the device's voice input function to input a question about work. For example, the user might say, "I'm worried because I don't know how to operate the new welding machine. What should I do?" The input data here is voice data. The device converts this voice data into text data using voice recognition software (for example, Google Speech Recognition). The converted text data is then output.

[0779] Step 2:

[0780] Submit a Question

[0781] The question converted into text data is sent from the terminal to the server. The terminal then sends this data to the server via the Internet. The input is text data, and the output is the text data sent to the server.

[0782] Step 3:

[0783] Sentiment analysis request

[0784] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The input is text data, and the emotion engine uses natural language processing technology to analyze the text data and recognize emotions (such as "anxiety" or "excitement"). Emotion data is output as the analysis result.

[0785] Step 4:

[0786] Request for advice generation

[0787] The server inputs the emotion analysis results and the question into the generative AI model and requests it to generate advice. The input is text data and emotion data. The generative AI model generates appropriate advice based on this input data. The generated advice (text data) is output.

[0788] Step 5:

[0789] Sending Advice

[0790] The server receives the generated advice and sends it to the user's terminal. The input is the generated advice (text data), and the output is the advice sent to the terminal.

[0791] Step 6:

[0792] Displaying Advice

[0793] The user's device displays the received advice. The device provides the user with visual information by outputting the advice content on the display. The input is the advice (text data), and the output is the advice displayed on the display.

[0794] Examples and prompts

[0795] For example, if a worker asks the robot the following question:

[0796] Input Audio:

[0797] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[0798] Example prompt:

[0799] Q: I'm worried about how to operate my new welding machine. What should I do?

[0800] Emotion: Anxiety

[0801] In this case, users can simply ask questions through voice input and receive specific advice in real time that takes their emotions into consideration.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] [Third embodiment]

[0806] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0807] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0808] 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).

[0809] 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.

[0810] 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.

[0811] 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).

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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."

[0818] This invention provides a system that uses generative AI to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[0819] System Configuration

[0820] 1. Terminal

[0821] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[0822] 2. Server

[0823] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[0824] Ability to receive questions from users

[0825] A function that allows users to input questions into a generative AI model and obtain analysis results.

[0826] A function to send generated advice to the user's device

[0827] Ability to store questions and generated advice in a database

[0828] 3. Generative AI Models

[0829] The generative AI model is an artificial intelligence that analyzes questions sent by users and generates optimal advice. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[0830] 4. Database Means

[0831] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0832] System Operation

[0833] A user inputs a question about a hobby into a terminal. For example, consider the question "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to the server.

[0834] The server inputs the question received from the user into the generative AI model. The generative AI model analyzes the question and generates the best advice for the user. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, first practice simple chords and watch YouTube tutorials."

[0835] Once the advice is generated, the server sends it to the user's device, which then displays it, allowing the user to receive specific instructions and follow them to start a new hobby.

[0836] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[0837] This system allows users to easily participate in new hobbies and quickly obtain specific information tailored to their interests. The database function also allows users to refer to past data, which is useful for continuous learning and information improvement.

[0838] The processing flow will be explained below.

[0839] Step 1:

[0840] The user inputs a question about a hobby into the terminal and presses the send button. An example of this input is "How do I start playing the guitar?" The terminal sends this question to the server.

[0841] Step 2:

[0842] The server receives the question from the user and checks its content. For example, the server checks the content of "How do I start playing the guitar?"

[0843] Step 3:

[0844] The server sends the received message to the generative AI model and requests it to analyze it. At this time, the server inputs the question "guitar" into the AI ​​model.

[0845] Step 4:

[0846] A generative AI model analyzes the questions sent and generates optimal advice. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, start by practicing simple chords and watching YouTube tutorials."

[0847] Step 5:

[0848] The server receives the advice returned by the generative AI model and sends it to the user's device. Based on the user's ID, the server sends the advice, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube," to the appropriate device.

[0849] Step 6:

[0850] The user's device displays the advice received from the server. The device shows the user, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube."

[0851] Step 7:

[0852] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[0853] Step 8:

[0854] The server stores the questions submitted by users and the advice generated in a database, which makes it easy to retrieve past questions and advice for future reference.

[0855] Step 9:

[0856] If the user asks the question again, or if another user asks a similar question, the server can use its accumulated database to quickly provide appropriate advice. The process repeats.

[0857] Example 1

[0858] 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."

[0859] In modern society, interest in a variety of hobbies is growing, but gathering information and obtaining specific advice when starting a new hobby presents challenges. Beginners face particular challenges in the initial stages, such as determining the necessary procedures and tools, making it difficult to quickly obtain appropriate information. However, conventional methods require users to individually search for information and determine its reliability, making them inefficient and ineffective. Therefore, there is a need to develop a system that uses generative artificial intelligence models to provide users with optimal advice.

[0860] 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.

[0861] In this invention, the server includes an electronic device into which a user inputs and transmits a question about a hobby, means for inputting the question received from the user to a generative AI model, means for the generative AI model to analyze the question and generate optimal advice, means for the server to transmit the generated advice to the user's electronic device, and means for the user's electronic device to display the received advice, thereby enabling the user to quickly obtain specific information for starting a new hobby.

[0862] An "electronic device" is a device that has the function of accepting input from a user via the Internet and sending questions to a server, and specifically includes smartphones, tablets, and personal computers.

[0863] A "server" is a computer system that has the functionality to process questions received from users, input them into a generative artificial intelligence model, and send the generated advice to the user's electronic device.

[0864] A "generative artificial intelligence model" is an artificial intelligence system that analyzes questions entered by users and generates optimal advice. It is trained using natural language processing technology to be able to respond to questions about a variety of hobbies.

[0865] A "question" is a specific information request that a user enters when starting a new hobby, and is input data for analysis by the generative artificial intelligence model.

[0866] "Advice" refers to specific instructions or information that the generative artificial intelligence model outputs as an analysis result, and is used as a reference when a user starts a new hobby.

[0867] The "database means" is a system in which the server stores and manages user questions and generated advice, and has a function that allows past data to be easily referenced.

[0868] This invention provides a system that uses a generative AI model to lower the barrier to users starting a new hobby. The system is composed of five elements: a user, a terminal, a server, a generative AI model, and a database means.

[0869] System Configuration and Operation

[0870] 1. Users

[0871] A user inputs a question about a hobby into an electronic device (e.g., a smartphone, a tablet, or a PC). For example, consider a case where a user inputs the question "How can I start playing the guitar?" into a PC.

[0872] 2. Terminal

[0873] The device sends the questions entered by the user to the server via an Internet connection, using JavaScript form submissions or HTTP requests.

[0874] 3. Server

[0875] The server receives user questions and inputs them into the generative artificial intelligence model. The server includes the following functions:

[0876] Question receiving function (e.g., implemented using the Django framework)

[0877] Inputting data into a generative AI model (e.g., using OpenAI API)

[0878] Receiving generated advice

[0879] Sending advice to user terminal

[0880] Database storage of questions and advice (e.g., managed using SQLite or PostgreSQL)

[0881] Specifically, the server is written in Python and built using the Django framework. This server processes HTTP requests from users and sends questions to a generative artificial intelligence model (e.g., OpenAI's GPT-3 model) using an appropriate API. The generated advice is then sent back to the user's device as an HTTP response. In addition, a database is installed on the server to manage past questions and advice.

[0882] 4. Generative AI Models

[0883] A generative artificial intelligence model (e.g., OpenAI's GPT-3) analyzes questions sent via a server and generates optimal advice. The AI ​​model is trained to provide specific instructions and reference information in response to the user's question. For example, it might generate advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube."

[0884] 5. Database Means

[0885] The database means is a system in which the server stores user questions and generated advice, allowing users to easily refer to past questions and advice. The database uses a database management system such as SQLite or PostgreSQL.

[0886] Examples and prompts

[0887] For example, suppose a user wants to start playing the guitar as a new hobby. The user opens a browser on their device, types the question "How do I start playing the guitar?", and presses the send button. This question is sent to the server.

[0888] The server sends a question to the generative AI model, which generates a prompt, for example:

[0889] How do I start playing guitar?

[0890] The generative AI model analyzes this and generates advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube." This advice is sent to the user's device via the server, where the user can view it on their device.

[0891] The system allows users to quickly get specific advice on starting a new hobby, and a database on the server records past questions and advice for future reference.

[0892] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0893] Step 1:

[0894] A user types a question about a hobby into an electronic device and presses the send button. Input: "How do I start playing guitar?" Output: A command is generated that sends the question to the device.

[0895] Step 2:

[0896] The device sends the user's question to the server via the Internet. Specific operations include submitting a form using JavaScript or an HTTP POST request. Input: Question from the user. Output: HTTP request to the server.

[0897] Step 3:

[0898] The server processes the questions received from the terminal. The Django framework written in Python receives the HTTP POST request and extracts the question. Input: HTTP request from the terminal. Output: Variable that stores the question content.

[0899] Step 4:

[0900] The question received by the server is input into the generative AI model. The Python code uses the OpenAI API to create a prompt to send the question. The specific operation is to execute openai.Completion.create(prompt="How do I start playing guitar?", ...). Input: Question content. Output: API request to the generative AI model.

[0901] Step 5:

[0902] A generative artificial intelligence model analyzes the question and generates the best advice. It uses a large neural network to understand the context and generate specific instructions. Input: Prompt. Output: Advice: "To start playing guitar, start by learning simple chords and watching YouTube tutorials."

[0903] Step 6:

[0904] The server receives the advice returned from the generative AI model and stores it in memory. It receives the response from the OpenAI API and extracts the advice content. Input: API response from the generative AI model. Output: Variable that stores the advice content.

[0905] Step 7:

[0906] The server sends the advice to the user's device. The advice is returned to the front end as an HTTP response. The specific operation is to execute return JsonResponse({'advice': advice}). Input: Advice content. Output: HTTP response to the device.

[0907] Step 8:

[0908] The device displays the advice received from the server. The advice is displayed on the screen using the browser's DOM operations. Input: Advice content in the HTTP response. Output: Advice displayed on the browser.

[0909] Step 9:

[0910] The server saves the user's question and the generated advice in a database. A record is added to the database using Django ORM, specifically Advice.objects.create(question="How can I start playing guitar?", advice=advice). Input: Question and advice. Output: Database record created.

[0911] (Application example 1)

[0912] 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."

[0913] Traditionally, when starting a new hobby, it takes time and effort to gather information and learn basic skills, which causes many people to give up midway. Beginners, in particular, often find it difficult to determine which information is reliable, and inconsistent information often reduces learning efficiency. Therefore, there has been a demand for a support system that allows users to easily and effectively start a new hobby.

[0914] 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.

[0915] In this invention, the server includes an electronic device for a user to input and send questions about hobbies, means for inputting the questions received from the user to a generative AI model, means for the generative AI model to analyze the questions and generate optimal advice, means for sending the generated advice to the user's electronic device, means for displaying the advice received by the user's electronic device, means for providing related videos and articles along with the generated advice, and database means for recording questions previously sent by the user and the generated advice. This allows the user to consistently receive reliable information and efficiently learn new hobbies.

[0916] "Electronic devices" are devices that allow users to input and send questions about hobbies, and include smartphones, tablets, and personal computers.

[0917] A "generative artificial intelligence model" is an artificial intelligence used to analyze questions sent by users and generate optimal advice.

[0918] A "server" is a device or system that inputs questions received from a user into a generative artificial intelligence model and transmits the generated advice to the user's electronic device.

[0919] "Advice" is instructions or suggestions generated by a generative artificial intelligence model based on the user's questions, providing specific guidance on starting a new hobby.

[0920] The "related videos and articles" are reference materials related to the generated advice, and provide supplementary information for the user to efficiently learn about their hobbies.

[0921] The "database means" is a means for recording questions sent by users and advice generated, and storing them for later reference.

[0922] The present invention relates to a system for providing useful information to users who are about to start a new hobby. An embodiment of the system will be described in detail below.

[0923] System Configuration

[0924] The system of the present invention is broadly composed of the following elements:

[0925] 1. User's electronic devices

[0926] 2. Server

[0927] 3. Generative AI Models

[0928] 4. Database Means

[0929] Program Description

[0930] User's electronic devices

[0931] Users input and send questions about their hobbies using electronic devices such as smartphones, tablets, and personal computers. These electronic devices are equipped with communication means for transmitting the questions input by the users to a server.

[0932] server

[0933] The server is responsible for inputting questions received from users into the generative AI model. Specifically, the server manages the reception and transmission of questions using a web framework such as Flask, and has the function of transmitting question data to the generative AI model using the OpenAI API.

[0934] Generative AI model

[0935] Generative AI models analyze user-submitted questions and generate optimal advice, such as OpenAI's GPT-3. This AI model has been trained to answer questions about a variety of hobbies and can generate specific advice, steps, and links to related videos and articles.

[0936] Database Means

[0937] The generated advice and questions are saved and accumulated in a database by the server, allowing users to refer to past questions and advice later.For database management, a relational database such as PostgreSQL or MySQL is used.

[0938] Specific examples

[0939] For example, a user inputs a question such as "How do I start playing the guitar?" into an electronic device and presses a send button. The question is sent to a server via the Internet.

[0940] The server inputs the following prompt into the generative AI model:

[0941] User Question: How do I get started on guitar?

[0942] Best advice:

[0943] The generative artificial intelligence model generates advice such as "First, practice some simple code and watch some YouTube tutorials," sometimes accompanied by links to related videos or articles.

[0944] The server sends the generated advice to the user's electronic device, which displays the advice, and the question and advice are stored in a database for future reference.

[0945] With the above configuration, users can easily and effectively start a new hobby. In addition, the database means allows users to refer to past questions and advice, realizing continuous learning support.

[0946] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0947] Step 1:

[0948] The user uses the device to input and submit a question about a hobby.

[0949] Input: User types "How do I start playing guitar?"

[0950] Output: The user's question is sent from the terminal to the server.

[0951] Specific operation: The user opens the application on their device, enters a question, and presses the "Submit" button. This input data is then sent to the server via the Internet.

[0952] Step 2:

[0953] The server receives a question from a user and generates a prompt sentence to send to the generative artificial intelligence model.

[0954] Input: Question data submitted by the user.

[0955] Output: A prompt to be input to the generative artificial intelligence model.

[0956] Specific behavior: The server analyzes the received question and generates a prompt of the form "User's question: How can I start playing guitar? Best advice:"

[0957] Step 3:

[0958] The server sends the generated prompt to a generative artificial intelligence model, which generates optimal advice.

[0959] Input: Prompt text "User asks: How do I start playing guitar? Best advice:".

[0960] Output: Advice generated by the generative artificial intelligence model.

[0961] What it does: The server sends the prompt to a generative AI model, such as OpenAI's API, and receives advice from the model. In this case, the advice is "First, practice some simple code and watch some YouTube tutorials."

[0962] Step 4:

[0963] The server transmits the generated advice to the user's terminal.

[0964] Input: Advice from a generative artificial intelligence model.

[0965] Output: Advisory message to the user's terminal.

[0966] Specific operation: The server organizes the generated advice and sends it to the user's device, where the user can view the advice message.

[0967] Step 5:

[0968] The user's terminal displays the received advice.

[0969] Input: The advice message sent by the server.

[0970] Output: Advice displayed on the screen.

[0971] Specific operation: The user's device displays the received advice on the application screen. The user confirms the advice, which is to "First practice some simple code and watch a tutorial on YouTube."

[0972] Step 6:

[0973] The server stores the user's question and the generated advice in a database.

[0974] Input: User question data and generated advice data.

[0975] Output: Questions and advice stored in a database.

[0976] What it does: The server stores the received questions and advice in a database, which can be referenced later, allowing users to review past questions and advice.

[0977] Through these processing steps, users can receive specific advice on starting a new hobby. Furthermore, the accumulation of past questions and advice supports continuous learning.

[0978] 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.

[0979] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[0980] System Configuration

[0981] 1. Terminal

[0982] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are forwarded to a server via the Internet.

[0983] 2. Server

[0984] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[0985] Ability to receive questions from users

[0986] A function that inputs user questions into the emotion engine and requests emotion analysis.

[0987] A function that inputs questions and sentiment analysis results into a generative AI model and obtains the analysis results.

[0988] A function to send generated advice to the user's device

[0989] Ability to store questions and generated advice in a database

[0990] 3. Emotion Engine

[0991] The emotion engine is an engine that analyzes user emotions from the text of questions sent by users and provides the analysis results to a generative AI model. This engine uses natural language processing technology to recognize emotions from context.

[0992] 4. Generative AI Models

[0993] The generative AI model is an artificial intelligence that generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, and provides specific advice, procedures, and reference information.

[0994] 5. Database Means

[0995] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[0996] System Operation

[0997] A user inputs a question about a hobby into a terminal. For example, the user inputs a question such as "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to a server.

[0998] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion engine recognizes emotions such as "excited" or "anxious."

[0999] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[1000] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[1001] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[1002] The system allows users to easily participate in new hobbies and receives specific advice that takes their emotions into consideration during the process. It also features a database that allows users to refer to past data, which helps with continuous learning and information improvement.

[1003] The processing flow will be explained below.

[1004] Step 1:

[1005] A user inputs a question about a hobby into a terminal and presses the send button. For example, the user inputs a question such as "How can I start playing the guitar?" The terminal then sends the question to the server.

[1006] Step 2:

[1007] The server receives the question from the user and passes it to the emotion engine. The server inputs the message "How do I start playing the guitar?" into the emotion engine.

[1008] Step 3:

[1009] The emotion engine analyzes the user's question and recognizes their emotion. For example, the emotion engine returns a result such as "This user is feeling anxious."

[1010] Step 4:

[1011] The server receives the emotion analysis results from the emotion engine and sends the analyzed emotion and the original question to the generative AI model.

[1012] Step 5:

[1013] The generative AI model generates optimal advice based on the question and the results of sentiment analysis. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed, unsettling state."

[1014] Step 6:

[1015] The server receives the advice returned by the generative AI model and sends it to the user's device. The server sends the following advice to the user's device: "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[1016] Step 7:

[1017] The user's device displays the advice received from the server: "To learn how to play guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[1018] Step 8:

[1019] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[1020] Step 9:

[1021] The server stores the questions sent by the user and the generated advice in a database. For example, the server records the question "How should I start playing guitar?" and the advice "Practice simple chords for beginners and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed manner without feeling anxious." This allows the server to quickly provide appropriate advice if the user asks a similar question later.

[1022] Example 2

[1023] 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."

[1024] It is important to provide an environment that allows users to easily start a new hobby by solving problems such as the high psychological hurdles, anxiety, and lack of concrete advice that users feel when starting a new hobby. In addition, it is necessary to provide more personalized and appropriate support by generating advice that takes into account the user's emotional state.

[1025] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting a question received from a user to an emotion analysis device to perform emotion analysis, a means for inputting the emotion analysis result and the question to a generative AI model, and a means for the generative AI model to analyze the emotion analysis result and the question and generate optimal advice. This makes it possible to provide specific advice that takes into account the user's emotional state.

[1026] "User" refers to an individual who utilizes the system to input hobby-related questions and obtain advice.

[1027] "Terminal" refers to an electronic device used by a user to input and send a question, and specifically includes a smartphone, tablet, PC, etc.

[1028] "Server" refers to a computer system that processes questions received from users, works with an emotion analysis device and a generative artificial intelligence model to generate advice, and transmits that advice to the user's terminal.

[1029] An "emotion analysis device" is a device that analyzes emotions from questions entered by users, and uses natural language processing technology to recognize emotions from context.

[1030] "Generative AI model" refers to an AI model that generates optimal advice based on a user's question and the results of sentiment analysis, and specifically includes trained machine learning models.

[1031] "Data repository" refers to a storage system for saving user questions and generated advice, and managing the data for future reference.

[1032] "Data management means" refers to means for recording and managing past questions and generated advice stored in a data storage device.

[1033] MODE FOR CARRYING OUT THE INVENTION

[1034] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. This system generates appropriate advice in response to user questions and provides support that takes into account the user's emotional state.

[1035] System Configuration

[1036] 1. Terminal

[1037] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[1038] 2. Server

[1039] The server processes questions received from users and generates advice in cooperation with the emotion analysis device and generative AI model. Specifically, it has the following functions:

[1040] Ability to receive questions from users

[1041] A function that inputs user questions into the emotion analysis device and requests emotion analysis.

[1042] A function that inputs sentiment analysis results and questions into a generative AI model and obtains the analysis results.

[1043] A function to send generated advice to the user's device

[1044] Ability to store questions and generated advice in a data repository

[1045] 3. Emotion analysis device

[1046] The emotion analysis device is a device for analyzing a user's emotion from the text of a question sent by the user, and recognizes the emotion from the context using natural language processing technology.

[1047] 4. Generative AI Models

[1048] The generative AI model generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[1049] 5. Data Storage Device

[1050] The data storage device stores and manages questions sent by users and advice generated by them, allowing users to refer to past questions and advice.

[1051] Hardware and software used

[1052] Devices: smartphones, tablets, computers

[1053] Server infrastructure: AWS (Amazon Web Services) or Google Cloud

[1054] Sentiment analysis software: Hume AI or Affectiva

[1055] Generative AI model: OpenAI's GPT-3 or GPT-4

[1056] Database: MySQL or MongoDB

[1057] Example of system operation

[1058] A user inputs a question about a hobby into a terminal. For example, "How can I start playing the guitar?" and presses the send button. The terminal sends this question to the server.

[1059] The server inputs the question received from the user into the emotion analysis device and requests emotion analysis. The emotion analysis device analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion analysis device recognizes emotions such as "excited" or "anxious."

[1060] The server inputs the sentiment analysis results and questions into a generative AI model, which then generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[1061] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[1062] Furthermore, the server stores the questions submitted by the user and the advice generated in a data storage device, so that past questions and advice can be easily retrieved for future reference.

[1063] Prompt Sentence Examples

[1064] "User Question: How do I start playing guitar?"

[1065] "Sentiment analysis result: excited"

[1066] "Generated advice: Practice simple beginner chords, watch beginner tutorials on YouTube, and relax before you start."

[1067] This method allows users to easily participate in new hobbies and receive specific advice that takes their emotions into consideration during the process. Furthermore, the data storage device allows users to refer to past data, which is useful for continuous learning and information improvement.

[1068] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1069] Step 1:

[1070] The user inputs a question about a hobby into the terminal and presses the send button.

[1071] Type: Type a question such as "How do I start playing guitar?"

[1072] Output: The question is waiting to be sent in the terminal.

[1073] Specifically, a user enters a question into an input field on the screen of a smartphone or computer, and then presses the "Send" button to send the question to the system.

[1074] Step 2:

[1075] The terminal sends a question to the server.

[1076] Input: The question entered by the user.

[1077] Output: The question is sent over the internet to a server.

[1078] Specifically, the device sends question data to the server's API endpoint using an HTTP POST request.

[1079] Step 3:

[1080] The server receives the query.

[1081] Input: The question sent from the terminal.

[1082] Output: The question is saved on the server and added to the processing queue.

[1083] Specifically, the server analyzes the received question data and prepares to proceed to the next step.

[1084] Step 4:

[1085] The server inputs a question into the emotion analysis device and requests emotion analysis.

[1086] Input: Question data stored on the server.

[1087] Output: An HTTP request for sentiment analysis is sent to the sentiment analyzer.

[1088] Specifically, the server sends the question data to the sentiment analysis API and waits for the results of the sentiment analysis.

[1089] Step 5:

[1090] The emotion analyzer analyzes the question and returns the analysis results to the server.

[1091] Input: Question data for which sentiment analysis was requested.

[1092] Output: JSON data containing the sentiment analysis results, such as "excited" or "anxious," is sent to the server.

[1093] Specifically, the emotion analysis device uses natural language processing technology to analyze emotions from the question text and returns the results to the server.

[1094] Step 6:

[1095] The server inputs the analysis results and questions into the generative AI model.

[1096] Input: Sentiment analysis results and question data.

[1097] Output: HTTP request to the generative AI model to generate advice.

[1098] Specifically, the server sends the emotion analysis results and question data as a prompt to the generative AI model's API. It creates and sends the prompt, "User question: What should I do to start playing guitar?" and "Emotion analysis result: I'm excited."

[1099] Step 7:

[1100] The generative AI model generates advice and sends it back to the server.

[1101] Input: A prompt statement containing sentiment analysis results and question data.

[1102] Output: JSON data containing the advice is sent back to the server.

[1103] Specifically, the generative AI model analyzes the prompt sentence, generates optimal advice, and sends it back to the server.

[1104] Step 8:

[1105] The server receives the advice and sends it to the user's terminal.

[1106] Input: Advice data from a generative AI model.

[1107] Output: The advice is sent to the user's terminal.

[1108] Specifically, the server sends the generated advice to the user's terminal as an HTTP response and prepares data for display.

[1109] Step 9:

[1110] The terminal displays the advice to the user.

[1111] Input: Advice data sent by the server.

[1112] Output: The advice is displayed on the terminal screen.

[1113] Specifically, the terminal reflects the received advice on the display screen, and the user can check the specific instructions on the screen.

[1114] Step 10:

[1115] The server stores the questions and advice in a data storage device.

[1116] Input: User question and generated advice data.

[1117] Output: Questions and advice are saved in a database.

[1118] Specifically, the server inserts the questions and advice into a database and manages them for future reference.

[1119] (Application example 2)

[1120] 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."

[1121] In modern factory work, it is important to reduce the anxiety and confusion workers feel when adapting to new equipment and work methods. In particular, lack of knowledge about new tasks and equipment and difficulty in operating them can cause stress and reduced work efficiency. Conventional support systems simply provide manuals and videos, making it difficult to provide specific advice in real time while taking into consideration the worker's feelings. The present invention solves these problems and provides a system that allows workers to tackle new tasks with peace of mind.

[1122] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal through which a user inputs and transmits a question about a hobby, a means for the server to input the question received from the user to a generative AI model, a means for the generative AI model to generate optimal advice based on the question and emotion analysis results, a means for the server to transmit the generated advice to the user's terminal, a means for the user's terminal to display the received advice, a means for inputting a question via voice input, and a means for analyzing emotions from the user's question using an emotion engine. This enables workers to easily ask questions via voice input and receive specific advice in real time that takes their emotions into consideration.

[1123] A "user" is an individual or worker who uses the system to enter hobby-related questions and receive advice.

[1124] A "terminal" is an electronic device used by a user, and includes a smartphone, tablet, PC, voice input device, etc. for inputting and sending a question.

[1125] The "server" is a computer system that receives data from users, works with generative AI models and emotion engines to generate advice, and sends that advice to the user's device.

[1126] A "generative AI model" is an artificial intelligence model that generates optimal advice based on the user's questions and the results of emotional analysis, and is trained to respond to questions about a variety of hobbies and tasks.

[1127] The "emotion engine" is an engine for analyzing a user's emotions from the text of a question sent by the user, and recognizes emotions from the context using natural language processing technology.

[1128] "Advice" refers to specific instructions, steps, and reference information generated by generative AI models to help users get started on a new hobby or task.

[1129] "Voice input" is a method in which a user inputs a question by voice using a microphone or the like, and the question is converted into text data using voice recognition technology.

[1130] "Emotion analysis result" refers to the emotional state (e.g., anxiety, excitement, hesitation, etc.) extracted from the user's question by the emotion engine.

[1131] This invention is a system that uses a generative AI model and an emotion engine to reduce anxiety about new tasks and equipment in factory work, allowing workers to work safely and efficiently. This system is implemented with the following configuration.

[1132] System Configuration

[1133] 1. Terminal

[1134] This is an electronic device that allows users (factory workers) to input and send questions about work. Terminals include smartphones, tablets, voice input devices, and microphones built into robots. Questions sent by the terminals are transferred to a server via the Internet.

[1135] 2. Server

[1136] The server processes questions received from users, generates advice through a generative AI model and emotion engine, and sends it to the user's device. Specifically, the server has the following functions:

[1137] Ability to receive questions from users

[1138] A function that inputs user questions into the emotion engine and requests emotion analysis.

[1139] A function that inputs questions and sentiment analysis results into a generative AI model to generate advice.

[1140] A function to send generated advice to the user's device

[1141] Ability to store questions and generated advice in a database

[1142] 3. Emotion Engine

[1143] The emotion engine is an engine that analyzes the user's emotions from the text of the question sent by the user, and recognizes emotions from the context using natural language processing technology. For example, it analyzes emotions such as "anxiety," "excitement," and "hesitation," and provides the results to the generative AI model.

[1144] 4. Generative AI Models

[1145] A generative AI model is an artificial intelligence that generates optimal advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to handle a wide range of tasks, providing specific advice, procedures, and reference information.

[1146] 5. Database Means

[1147] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[1148] System Operation

[1149] Voice input

[1150] A user (factory worker) uses the voice input function of the terminal to input a question about work. For example, the user inputs a question such as, "I'm worried because I don't know how to operate the new welding machine. What should I do?"

[1151] Submit a Question

[1152] When the user presses the send button, the terminal sends this question to the server.

[1153] Emotion analysis

[1154] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, it may recognize "anxiety" as the analysis result.

[1155] Advice Generation

[1156] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the following advice: "When operating a new welding machine, we recommend that you first review basic safety guidelines and watch the manufacturer's official tutorial video. Also, when welding for the first time, try practicing on some scrap metal and relax."

[1157] Sending and viewing advice

[1158] The server receives the generated advice and sends the contents of the advice to the user's terminal, which displays the received advice.

[1159] Specific examples and prompts for generative AI models

[1160] For example, if a worker asks the robot the following question:

[1161] Input Audio:

[1162] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[1163] Example prompt:

[1164] Q: I'm worried about how to operate my new welding machine. What should I do?

[1165] Emotion: Anxiety

[1166] This system allows factory workers to easily ask questions through voice input and receive specific advice in real time that takes their emotions into consideration, reducing anxiety about new tasks and equipment and enabling them to work efficiently and with peace of mind.

[1167] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1168] Step 1:

[1169] User question input

[1170] The user (factory worker) uses the device's voice input function to input a question about work. For example, the user might say, "I'm worried because I don't know how to operate the new welding machine. What should I do?" The input data here is voice data. The device converts this voice data into text data using voice recognition software (for example, Google Speech Recognition). The converted text data is then output.

[1171] Step 2:

[1172] Submit a Question

[1173] The question converted into text data is sent from the terminal to the server. The terminal then sends this data to the server via the Internet. The input is text data, and the output is the text data sent to the server.

[1174] Step 3:

[1175] Sentiment analysis request

[1176] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The input is text data, and the emotion engine uses natural language processing technology to analyze the text data and recognize emotions (such as "anxiety" or "excitement"). Emotion data is output as the analysis result.

[1177] Step 4:

[1178] Request for advice generation

[1179] The server inputs the emotion analysis results and the question into the generative AI model and requests it to generate advice. The input is text data and emotion data. The generative AI model generates appropriate advice based on this input data. The generated advice (text data) is output.

[1180] Step 5:

[1181] Sending Advice

[1182] The server receives the generated advice and sends it to the user's terminal. The input is the generated advice (text data), and the output is the advice sent to the terminal.

[1183] Step 6:

[1184] Displaying Advice

[1185] The user's device displays the received advice. The device provides the user with visual information by outputting the advice content on the display. The input is the advice (text data), and the output is the advice displayed on the display.

[1186] Examples and prompts

[1187] For example, if a worker asks the robot the following question:

[1188] Input Audio:

[1189] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[1190] Example prompt:

[1191] Q: I'm worried about how to operate my new welding machine. What should I do?

[1192] Emotion: Anxiety

[1193] In this case, users can simply ask questions through voice input and receive specific advice in real time that takes their emotions into consideration.

[1194] 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.

[1195] 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.

[1196] 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.

[1197] [Fourth embodiment]

[1198] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1199] 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.

[1200] 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).

[1201] 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.

[1202] 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.

[1203] 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).

[1204] 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.

[1205] 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.

[1206] 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.

[1207] 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.

[1208] 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.

[1209] 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.

[1210] 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."

[1211] This invention provides a system that uses generative AI to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[1212] System Configuration

[1213] 1. Terminal

[1214] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[1215] 2. Server

[1216] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[1217] Ability to receive questions from users

[1218] A function that allows users to input questions into a generative AI model and obtain analysis results.

[1219] A function to send generated advice to the user's device

[1220] Ability to store questions and generated advice in a database

[1221] 3. Generative AI Models

[1222] The generative AI model is an artificial intelligence that analyzes questions sent by users and generates optimal advice. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[1223] 4. Database Means

[1224] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[1225] System Operation

[1226] A user inputs a question about a hobby into a terminal. For example, consider the question "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to the server.

[1227] The server inputs the question received from the user into the generative AI model. The generative AI model analyzes the question and generates the best advice for the user. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, first practice simple chords and watch YouTube tutorials."

[1228] Once the advice is generated, the server sends it to the user's device, which then displays it, allowing the user to receive specific instructions and follow them to start a new hobby.

[1229] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[1230] This system allows users to easily participate in new hobbies and quickly obtain specific information tailored to their interests. The database function also allows users to refer to past data, which is useful for continuous learning and information improvement.

[1231] The processing flow will be explained below.

[1232] Step 1:

[1233] The user inputs a question about a hobby into the terminal and presses the send button. An example of this input is "How do I start playing the guitar?" The terminal sends this question to the server.

[1234] Step 2:

[1235] The server receives the question from the user and checks its content. For example, the server checks the content of "How do I start playing the guitar?"

[1236] Step 3:

[1237] The server sends the received message to the generative AI model and requests it to analyze it. At this time, the server inputs the question "guitar" into the AI ​​model.

[1238] Step 4:

[1239] A generative AI model analyzes the questions sent and generates optimal advice. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, start by practicing simple chords and watching YouTube tutorials."

[1240] Step 5:

[1241] The server receives the advice returned by the generative AI model and sends it to the user's device. Based on the user's ID, the server sends the advice, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube," to the appropriate device.

[1242] Step 6:

[1243] The user's device displays the advice received from the server. The device shows the user, "To learn how to play the guitar, start by practicing simple chords and watching tutorials on YouTube."

[1244] Step 7:

[1245] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[1246] Step 8:

[1247] The server stores the questions submitted by users and the advice generated in a database, which makes it easy to retrieve past questions and advice for future reference.

[1248] Step 9:

[1249] If the user asks the question again, or if another user asks a similar question, the server can use its accumulated database to quickly provide appropriate advice. The process repeats.

[1250] Example 1

[1251] 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."

[1252] In modern society, interest in a variety of hobbies is growing, but gathering information and obtaining specific advice when starting a new hobby presents challenges. Beginners face particular challenges in the initial stages, such as determining the necessary procedures and tools, making it difficult to quickly obtain appropriate information. However, conventional methods require users to individually search for information and determine its reliability, making them inefficient and ineffective. Therefore, there is a need to develop a system that uses generative artificial intelligence models to provide users with optimal advice.

[1253] 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.

[1254] In this invention, the server includes an electronic device into which a user inputs and transmits a question about a hobby, means for inputting the question received from the user to a generative AI model, means for the generative AI model to analyze the question and generate optimal advice, means for the server to transmit the generated advice to the user's electronic device, and means for the user's electronic device to display the received advice, thereby enabling the user to quickly obtain specific information for starting a new hobby.

[1255] An "electronic device" is a device that has the function of accepting input from a user via the Internet and sending questions to a server, and specifically includes smartphones, tablets, and personal computers.

[1256] A "server" is a computer system that has the functionality to process questions received from users, input them into a generative artificial intelligence model, and send the generated advice to the user's electronic device.

[1257] A "generative artificial intelligence model" is an artificial intelligence system that analyzes questions entered by users and generates optimal advice. It is trained using natural language processing technology to be able to respond to questions about a variety of hobbies.

[1258] A "question" is a specific information request that a user enters when starting a new hobby, and is input data for analysis by the generative artificial intelligence model.

[1259] "Advice" refers to specific instructions or information that the generative artificial intelligence model outputs as an analysis result, and is used as a reference when a user starts a new hobby.

[1260] The "database means" is a system in which the server stores and manages user questions and generated advice, and has a function that allows past data to be easily referenced.

[1261] This invention provides a system that uses a generative AI model to lower the barrier to users starting a new hobby. The system is composed of five elements: a user, a terminal, a server, a generative AI model, and a database means.

[1262] System Configuration and Operation

[1263] 1. Users

[1264] A user inputs a question about a hobby into an electronic device (e.g., a smartphone, a tablet, or a PC). For example, consider a case where a user inputs the question "How can I start playing the guitar?" into a PC.

[1265] 2. Terminal

[1266] The device sends the questions entered by the user to the server via an Internet connection, using JavaScript form submissions or HTTP requests.

[1267] 3. Server

[1268] The server receives user questions and inputs them into the generative artificial intelligence model. The server includes the following functions:

[1269] Question receiving function (e.g., implemented using the Django framework)

[1270] Inputting data into a generative AI model (e.g., using OpenAI API)

[1271] Receiving generated advice

[1272] Sending advice to user terminal

[1273] Database storage of questions and advice (e.g., managed using SQLite or PostgreSQL)

[1274] Specifically, the server is written in Python and built using the Django framework. This server processes HTTP requests from users and sends questions to a generative artificial intelligence model (e.g., OpenAI's GPT-3 model) using an appropriate API. The generated advice is then sent back to the user's device as an HTTP response. In addition, a database is installed on the server to manage past questions and advice.

[1275] 4. Generative AI Models

[1276] A generative artificial intelligence model (e.g., OpenAI's GPT-3) analyzes questions sent via a server and generates optimal advice. The AI ​​model is trained to provide specific instructions and reference information in response to the user's question. For example, it might generate advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube."

[1277] 5. Database Means

[1278] The database means is a system in which the server stores user questions and generated advice, allowing users to easily refer to past questions and advice. The database uses a database management system such as SQLite or PostgreSQL.

[1279] Examples and prompts

[1280] For example, suppose a user wants to start playing the guitar as a new hobby. The user opens a browser on their device, types the question "How do I start playing the guitar?", and presses the send button. This question is sent to the server.

[1281] The server sends a question to the generative AI model, which generates a prompt, for example:

[1282] How do I start playing guitar?

[1283] The generative AI model analyzes this and generates advice such as, "To learn how to play the guitar, first practice simple chords and watch tutorials on YouTube." This advice is sent to the user's device via the server, where the user can view it on their device.

[1284] The system allows users to quickly get specific advice on starting a new hobby, and a database on the server records past questions and advice for future reference.

[1285] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1286] Step 1:

[1287] A user types a question about a hobby into an electronic device and presses the send button. Input: "How do I start playing guitar?" Output: A command is generated that sends the question to the device.

[1288] Step 2:

[1289] The device sends the user's question to the server via the Internet. Specific operations include submitting a form using JavaScript or an HTTP POST request. Input: Question from the user. Output: HTTP request to the server.

[1290] Step 3:

[1291] The server processes the questions received from the terminal. The Django framework written in Python receives the HTTP POST request and extracts the question. Input: HTTP request from the terminal. Output: Variable that stores the question content.

[1292] Step 4:

[1293] The question received by the server is input into the generative AI model. The Python code uses the OpenAI API to create a prompt to send the question. The specific operation is to execute openai.Completion.create(prompt="How do I start playing guitar?", ...). Input: Question content. Output: API request to the generative AI model.

[1294] Step 5:

[1295] A generative artificial intelligence model analyzes the question and generates the best advice. It uses a large neural network to understand the context and generate specific instructions. Input: Prompt. Output: Advice: "To start playing guitar, start by learning simple chords and watching YouTube tutorials."

[1296] Step 6:

[1297] The server receives the advice returned from the generative AI model and stores it in memory. It receives the response from the OpenAI API and extracts the advice content. Input: API response from the generative AI model. Output: Variable that stores the advice content.

[1298] Step 7:

[1299] The server sends the advice to the user's device. The advice is returned to the front end as an HTTP response. The specific operation is to execute return JsonResponse({'advice': advice}). Input: Advice content. Output: HTTP response to the device.

[1300] Step 8:

[1301] The device displays the advice received from the server. The advice is displayed on the screen using the browser's DOM operations. Input: Advice content in the HTTP response. Output: Advice displayed on the browser.

[1302] Step 9:

[1303] The server saves the user's question and the generated advice in a database. A record is added to the database using Django ORM, specifically Advice.objects.create(question="How can I start playing guitar?", advice=advice). Input: Question and advice. Output: Database record created.

[1304] (Application example 1)

[1305] 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."

[1306] Traditionally, when starting a new hobby, it takes time and effort to gather information and learn basic skills, which causes many people to give up midway. Beginners, in particular, often find it difficult to determine which information is reliable, and inconsistent information often reduces learning efficiency. Therefore, there has been a demand for a support system that allows users to easily and effectively start a new hobby.

[1307] 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.

[1308] In this invention, the server includes an electronic device for a user to input and send questions about hobbies, means for inputting the questions received from the user to a generative AI model, means for the generative AI model to analyze the questions and generate optimal advice, means for sending the generated advice to the user's electronic device, means for displaying the advice received by the user's electronic device, means for providing related videos and articles along with the generated advice, and database means for recording questions previously sent by the user and the generated advice. This allows the user to consistently receive reliable information and efficiently learn new hobbies.

[1309] "Electronic devices" are devices that allow users to input and send questions about hobbies, and include smartphones, tablets, and personal computers.

[1310] A "generative artificial intelligence model" is an artificial intelligence used to analyze questions sent by users and generate optimal advice.

[1311] A "server" is a device or system that inputs questions received from a user into a generative artificial intelligence model and transmits the generated advice to the user's electronic device.

[1312] "Advice" is instructions or suggestions generated by a generative artificial intelligence model based on the user's questions, providing specific guidance on starting a new hobby.

[1313] The "related videos and articles" are reference materials related to the generated advice, and provide supplementary information for the user to efficiently learn about their hobbies.

[1314] The "database means" is a means for recording questions sent by users and advice generated, and storing them for later reference.

[1315] The present invention relates to a system for providing useful information to users who are about to start a new hobby. An embodiment of the system will be described in detail below.

[1316] System Configuration

[1317] The system of the present invention is broadly composed of the following elements:

[1318] 1. User's electronic devices

[1319] 2. Server

[1320] 3. Generative AI Models

[1321] 4. Database Means

[1322] Program Description

[1323] User's electronic devices

[1324] Users input and send questions about their hobbies using electronic devices such as smartphones, tablets, and personal computers. These electronic devices are equipped with communication means for transmitting the questions input by the users to a server.

[1325] server

[1326] The server is responsible for inputting questions received from users into the generative AI model. Specifically, the server manages the reception and transmission of questions using a web framework such as Flask, and has the function of transmitting question data to the generative AI model using the OpenAI API.

[1327] Generative AI model

[1328] Generative AI models analyze user-submitted questions and generate optimal advice, such as OpenAI's GPT-3. This AI model has been trained to answer questions about a variety of hobbies and can generate specific advice, steps, and links to related videos and articles.

[1329] Database Means

[1330] The generated advice and questions are saved and accumulated in a database by the server, allowing users to refer to past questions and advice later.For database management, a relational database such as PostgreSQL or MySQL is used.

[1331] Specific examples

[1332] For example, a user inputs a question such as "How do I start playing the guitar?" into an electronic device and presses a send button. The question is sent to a server via the Internet.

[1333] The server inputs the following prompt into the generative AI model:

[1334] User Question: How do I get started on guitar?

[1335] Best advice:

[1336] The generative artificial intelligence model generates advice such as "First, practice some simple code and watch some YouTube tutorials," sometimes accompanied by links to related videos or articles.

[1337] The server sends the generated advice to the user's electronic device, which displays the advice, and the question and advice are stored in a database for future reference.

[1338] With the above configuration, users can easily and effectively start a new hobby. In addition, the database means allows users to refer to past questions and advice, realizing continuous learning support.

[1339] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1340] Step 1:

[1341] The user uses the device to input and submit a question about a hobby.

[1342] Input: User types "How do I start playing guitar?"

[1343] Output: The user's question is sent from the terminal to the server.

[1344] Specific operation: The user opens the application on their device, enters a question, and presses the "Submit" button. This input data is then sent to the server via the Internet.

[1345] Step 2:

[1346] The server receives a question from a user and generates a prompt sentence to send to the generative artificial intelligence model.

[1347] Input: Question data submitted by the user.

[1348] Output: A prompt to be input to the generative artificial intelligence model.

[1349] Specific behavior: The server analyzes the received question and generates a prompt of the form "User's question: How can I start playing guitar? Best advice:"

[1350] Step 3:

[1351] The server sends the generated prompt to a generative artificial intelligence model, which generates optimal advice.

[1352] Input: Prompt text "User asks: How do I start playing guitar? Best advice:".

[1353] Output: Advice generated by the generative artificial intelligence model.

[1354] What it does: The server sends the prompt to a generative AI model, such as OpenAI's API, and receives advice from the model. In this case, the advice is "First, practice some simple code and watch some YouTube tutorials."

[1355] Step 4:

[1356] The server transmits the generated advice to the user's terminal.

[1357] Input: Advice from a generative artificial intelligence model.

[1358] Output: Advisory message to the user's terminal.

[1359] Specific operation: The server organizes the generated advice and sends it to the user's device, where the user can view the advice message.

[1360] Step 5:

[1361] The user's terminal displays the received advice.

[1362] Input: The advice message sent by the server.

[1363] Output: Advice displayed on the screen.

[1364] Specific operation: The user's device displays the received advice on the application screen. The user confirms the advice, which is to "First practice some simple code and watch a tutorial on YouTube."

[1365] Step 6:

[1366] The server stores the user's question and the generated advice in a database.

[1367] Input: User question data and generated advice data.

[1368] Output: Questions and advice stored in a database.

[1369] What it does: The server stores the received questions and advice in a database, which can be referenced later, allowing users to review past questions and advice.

[1370] Through these processing steps, users can receive specific advice on starting a new hobby. Furthermore, the accumulation of past questions and advice supports continuous learning.

[1371] 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.

[1372] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. The system is implemented with the following configuration.

[1373] System Configuration

[1374] 1. Terminal

[1375] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are forwarded to a server via the Internet.

[1376] 2. Server

[1377] The server inputs questions received from users into the generative AI model and sends the advice returned by the generative AI model to the user's device. Specifically, the server has the following functions:

[1378] Ability to receive questions from users

[1379] A function that inputs user questions into the emotion engine and requests emotion analysis.

[1380] A function that inputs questions and sentiment analysis results into a generative AI model and obtains the analysis results.

[1381] A function to send generated advice to the user's device

[1382] Ability to store questions and generated advice in a database

[1383] 3. Emotion Engine

[1384] The emotion engine is an engine that analyzes user emotions from the text of questions sent by users and provides the analysis results to a generative AI model. This engine uses natural language processing technology to recognize emotions from context.

[1385] 4. Generative AI Models

[1386] The generative AI model is an artificial intelligence that generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, and provides specific advice, procedures, and reference information.

[1387] 5. Database Means

[1388] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[1389] System Operation

[1390] A user inputs a question about a hobby into a terminal. For example, the user inputs a question such as "How can I start playing the guitar?" When the user presses the send button, the terminal sends this question to a server.

[1391] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion engine recognizes emotions such as "excited" or "anxious."

[1392] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[1393] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[1394] Furthermore, the server stores the questions submitted by users and the advice generated in a database, which allows users to easily retrieve past questions and advice for future reference.

[1395] The system allows users to easily participate in new hobbies and receives specific advice that takes their emotions into consideration during the process. It also features a database that allows users to refer to past data, which helps with continuous learning and information improvement.

[1396] The processing flow will be explained below.

[1397] Step 1:

[1398] A user inputs a question about a hobby into a terminal and presses the send button. For example, the user inputs a question such as "How can I start playing the guitar?" The terminal then sends the question to the server.

[1399] Step 2:

[1400] The server receives the question from the user and passes it to the emotion engine. The server inputs the message "How do I start playing the guitar?" into the emotion engine.

[1401] Step 3:

[1402] The emotion engine analyzes the user's question and recognizes their emotion. For example, the emotion engine returns a result such as "This user is feeling anxious."

[1403] Step 4:

[1404] The server receives the emotion analysis results from the emotion engine and sends the analyzed emotion and the original question to the generative AI model.

[1405] Step 5:

[1406] The generative AI model generates optimal advice based on the question and the results of sentiment analysis. For example, the AI ​​model might generate advice like, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed, unsettling state."

[1407] Step 6:

[1408] The server receives the advice returned by the generative AI model and sends it to the user's device. The server sends the following advice to the user's device: "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[1409] Step 7:

[1410] The user's device displays the advice received from the server: "To learn how to play guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed and unassuming manner."

[1411] Step 8:

[1412] The user begins to act on the displayed advice. For example, the user searches for guitar tutorials on YouTube and begins practicing simple chords.

[1413] Step 9:

[1414] The server stores the questions sent by the user and the generated advice in a database. For example, the server records the question "How should I start playing guitar?" and the advice "Practice simple chords for beginners and watch beginner tutorials on YouTube. We also recommend that you start in a relaxed manner without feeling anxious." This allows the server to quickly provide appropriate advice if the user asks a similar question later.

[1415] Example 2

[1416] 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."

[1417] It is important to provide an environment that allows users to easily start a new hobby by solving problems such as the high psychological hurdles, anxiety, and lack of concrete advice that users feel when starting a new hobby. In addition, it is necessary to provide more personalized and appropriate support by generating advice that takes into account the user's emotional state.

[1418] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting a question received from a user to an emotion analysis device to perform emotion analysis, a means for inputting the emotion analysis result and the question to a generative AI model, and a means for the generative AI model to analyze the emotion analysis result and the question and generate optimal advice. This makes it possible to provide specific advice that takes into account the user's emotional state.

[1419] "User" refers to an individual who utilizes the system to input hobby-related questions and obtain advice.

[1420] "Terminal" refers to an electronic device used by a user to input and send a question, and specifically includes a smartphone, tablet, PC, etc.

[1421] "Server" refers to a computer system that processes questions received from users, works with an emotion analysis device and a generative artificial intelligence model to generate advice, and transmits that advice to the user's terminal.

[1422] An "emotion analysis device" is a device that analyzes emotions from questions entered by users, and uses natural language processing technology to recognize emotions from context.

[1423] "Generative AI model" refers to an AI model that generates optimal advice based on a user's question and the results of sentiment analysis, and specifically includes trained machine learning models.

[1424] "Data repository" refers to a storage system for saving user questions and generated advice, and managing the data for future reference.

[1425] "Data management means" refers to means for recording and managing past questions and generated advice stored in a data storage device.

[1426] MODE FOR CARRYING OUT THE INVENTION

[1427] This invention provides a system that uses generative AI and an emotion engine to lower the barrier to users starting a new hobby. This system generates appropriate advice in response to user questions and provides support that takes into account the user's emotional state.

[1428] System Configuration

[1429] 1. Terminal

[1430] This is an electronic device that allows users to input and send questions about their hobbies. The device can be a smartphone, tablet, or PC. The questions sent by the device are transferred to a server via the Internet.

[1431] 2. Server

[1432] The server processes questions received from users and generates advice in cooperation with the emotion analysis device and generative AI model. Specifically, it has the following functions:

[1433] Ability to receive questions from users

[1434] A function that inputs user questions into the emotion analysis device and requests emotion analysis.

[1435] A function that inputs sentiment analysis results and questions into a generative AI model and obtains the analysis results.

[1436] A function to send generated advice to the user's device

[1437] Ability to store questions and generated advice in a data repository

[1438] 3. Emotion analysis device

[1439] The emotion analysis device is a device for analyzing a user's emotion from the text of a question sent by the user, and recognizes the emotion from the context using natural language processing technology.

[1440] 4. Generative AI Models

[1441] The generative AI model generates advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to respond to questions about a variety of hobbies, providing specific advice, procedures, and reference information.

[1442] 5. Data Storage Device

[1443] The data storage device stores and manages questions sent by users and advice generated by them, allowing users to refer to past questions and advice.

[1444] Hardware and software used

[1445] Devices: smartphones, tablets, computers

[1446] Server infrastructure: AWS (Amazon Web Services) or Google Cloud

[1447] Sentiment analysis software: Hume AI or Affectiva

[1448] Generative AI model: OpenAI's GPT-3 or GPT-4

[1449] Database: MySQL or MongoDB

[1450] Example of system operation

[1451] A user inputs a question about a hobby into a terminal. For example, "How can I start playing the guitar?" and presses the send button. The terminal sends this question to the server.

[1452] The server inputs the question received from the user into the emotion analysis device and requests emotion analysis. The emotion analysis device analyzes the emotion from the user's input sentence and returns the result to the server. For example, the emotion analysis device recognizes emotions such as "excited" or "anxious."

[1453] The server inputs the sentiment analysis results and questions into a generative AI model, which then generates optimal advice based on this information. In this case, the AI ​​model generates the advice, "To learn how to play the guitar, practice simple beginner chords and watch beginner tutorials on YouTube. We also recommend that you start relaxed."

[1454] The server receives the advice returned by the generative AI model and sends it to the user's device, which then displays the advice. This allows the user to receive specific instructions and start a new hobby.

[1455] Furthermore, the server stores the questions submitted by the user and the advice generated in a data storage device, so that past questions and advice can be easily retrieved for future reference.

[1456] Prompt Sentence Examples

[1457] "User Question: How do I start playing guitar?"

[1458] "Sentiment analysis result: excited"

[1459] "Generated advice: Practice simple beginner chords, watch beginner tutorials on YouTube, and relax before you start."

[1460] This method allows users to easily participate in new hobbies and receive specific advice that takes their emotions into consideration during the process. Furthermore, the data storage device allows users to refer to past data, which is useful for continuous learning and information improvement.

[1461] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1462] Step 1:

[1463] The user inputs a question about a hobby into the terminal and presses the send button.

[1464] Type: Type a question such as "How do I start playing guitar?"

[1465] Output: The question is waiting to be sent in the terminal.

[1466] Specifically, a user enters a question into an input field on the screen of a smartphone or computer, and then presses the "Send" button to send the question to the system.

[1467] Step 2:

[1468] The terminal sends a question to the server.

[1469] Input: The question entered by the user.

[1470] Output: The question is sent over the internet to a server.

[1471] Specifically, the device sends question data to the server's API endpoint using an HTTP POST request.

[1472] Step 3:

[1473] The server receives the query.

[1474] Input: The question sent from the terminal.

[1475] Output: The question is saved on the server and added to the processing queue.

[1476] Specifically, the server analyzes the received question data and prepares to proceed to the next step.

[1477] Step 4:

[1478] The server inputs a question into the emotion analysis device and requests emotion analysis.

[1479] Input: Question data stored on the server.

[1480] Output: An HTTP request for sentiment analysis is sent to the sentiment analyzer.

[1481] Specifically, the server sends the question data to the sentiment analysis API and waits for the results of the sentiment analysis.

[1482] Step 5:

[1483] The emotion analyzer analyzes the question and returns the analysis results to the server.

[1484] Input: Question data for which sentiment analysis was requested.

[1485] Output: JSON data containing the sentiment analysis results, such as "excited" or "anxious," is sent to the server.

[1486] Specifically, the emotion analysis device uses natural language processing technology to analyze emotions from the question text and returns the results to the server.

[1487] Step 6:

[1488] The server inputs the analysis results and questions into the generative AI model.

[1489] Input: Sentiment analysis results and question data.

[1490] Output: HTTP request to the generative AI model to generate advice.

[1491] Specifically, the server sends the emotion analysis results and question data as a prompt to the generative AI model's API. It creates and sends the prompt, "User question: What should I do to start playing guitar?" and "Emotion analysis result: I'm excited."

[1492] Step 7:

[1493] The generative AI model generates advice and sends it back to the server.

[1494] Input: A prompt statement containing sentiment analysis results and question data.

[1495] Output: JSON data containing the advice is sent back to the server.

[1496] Specifically, the generative AI model analyzes the prompt sentence, generates optimal advice, and sends it back to the server.

[1497] Step 8:

[1498] The server receives the advice and sends it to the user's terminal.

[1499] Input: Advice data from a generative AI model.

[1500] Output: The advice is sent to the user's terminal.

[1501] Specifically, the server sends the generated advice to the user's terminal as an HTTP response and prepares data for display.

[1502] Step 9:

[1503] The terminal displays the advice to the user.

[1504] Input: Advice data sent by the server.

[1505] Output: The advice is displayed on the terminal screen.

[1506] Specifically, the terminal reflects the received advice on the display screen, and the user can check the specific instructions on the screen.

[1507] Step 10:

[1508] The server stores the questions and advice in a data storage device.

[1509] Input: User question and generated advice data.

[1510] Output: Questions and advice are saved in a database.

[1511] Specifically, the server inserts the questions and advice into a database and manages them for future reference.

[1512] (Application example 2)

[1513] 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."

[1514] In modern factory work, it is important to reduce the anxiety and confusion workers feel when adapting to new equipment and work methods. In particular, lack of knowledge about new tasks and equipment and difficulty in operating them can cause stress and reduced work efficiency. Conventional support systems simply provide manuals and videos, making it difficult to provide specific advice in real time while taking into consideration the worker's feelings. The present invention solves these problems and provides a system that allows workers to tackle new tasks with peace of mind.

[1515] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a terminal through which a user inputs and transmits a question about a hobby, a means for the server to input the question received from the user to a generative AI model, a means for the generative AI model to generate optimal advice based on the question and emotion analysis results, a means for the server to transmit the generated advice to the user's terminal, a means for the user's terminal to display the received advice, a means for inputting a question via voice input, and a means for analyzing emotions from the user's question using an emotion engine. This enables workers to easily ask questions via voice input and receive specific advice in real time that takes their emotions into consideration.

[1516] A "user" is an individual or worker who uses the system to enter hobby-related questions and receive advice.

[1517] A "terminal" is an electronic device used by a user, and includes a smartphone, tablet, PC, voice input device, etc. for inputting and sending a question.

[1518] The "server" is a computer system that receives data from users, works with generative AI models and emotion engines to generate advice, and sends that advice to the user's device.

[1519] A "generative AI model" is an artificial intelligence model that generates optimal advice based on the user's questions and the results of emotional analysis, and is trained to respond to questions about a variety of hobbies and tasks.

[1520] The "emotion engine" is an engine for analyzing a user's emotions from the text of a question sent by the user, and recognizes emotions from the context using natural language processing technology.

[1521] "Advice" refers to specific instructions, steps, and reference information generated by generative AI models to help users get started on a new hobby or task.

[1522] "Voice input" is a method in which a user inputs a question by voice using a microphone or the like, and the question is converted into text data using voice recognition technology.

[1523] "Emotion analysis result" refers to the emotional state (e.g., anxiety, excitement, hesitation, etc.) extracted from the user's question by the emotion engine.

[1524] This invention is a system that uses a generative AI model and an emotion engine to reduce anxiety about new tasks and equipment in factory work, allowing workers to work safely and efficiently. This system is implemented with the following configuration.

[1525] System Configuration

[1526] 1. Terminal

[1527] This is an electronic device that allows users (factory workers) to input and send questions about work. Terminals include smartphones, tablets, voice input devices, and microphones built into robots. Questions sent by the terminals are transferred to a server via the Internet.

[1528] 2. Server

[1529] The server processes questions received from users, generates advice through a generative AI model and emotion engine, and sends it to the user's device. Specifically, the server has the following functions:

[1530] Ability to receive questions from users

[1531] A function that inputs user questions into the emotion engine and requests emotion analysis.

[1532] A function that inputs questions and sentiment analysis results into a generative AI model to generate advice.

[1533] A function to send generated advice to the user's device

[1534] Ability to store questions and generated advice in a database

[1535] 3. Emotion Engine

[1536] The emotion engine is an engine that analyzes the user's emotions from the text of the question sent by the user, and recognizes emotions from the context using natural language processing technology. For example, it analyzes emotions such as "anxiety," "excitement," and "hesitation," and provides the results to the generative AI model.

[1537] 4. Generative AI Models

[1538] A generative AI model is an artificial intelligence that generates optimal advice based on questions submitted by users and the results of sentiment analysis. The AI ​​model is trained to handle a wide range of tasks, providing specific advice, procedures, and reference information.

[1539] 5. Database Means

[1540] The database means is for storing and managing questions sent by users and advice generated by users, thereby allowing users to refer to past questions and advice.

[1541] System Operation

[1542] Voice input

[1543] A user (factory worker) uses the voice input function of the terminal to input a question about work. For example, the user inputs a question such as, "I'm worried because I don't know how to operate the new welding machine. What should I do?"

[1544] Submit a Question

[1545] When the user presses the send button, the terminal sends this question to the server.

[1546] Emotion analysis

[1547] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The emotion engine analyzes the emotion from the user's input sentence and returns the result to the server. For example, it may recognize "anxiety" as the analysis result.

[1548] Advice Generation

[1549] The server inputs the emotion analysis results and questions obtained from the emotion engine into the generative AI model. The generative AI model generates optimal advice based on this information. In this case, the AI ​​model generates the following advice: "When operating a new welding machine, we recommend that you first review basic safety guidelines and watch the manufacturer's official tutorial video. Also, when welding for the first time, try practicing on some scrap metal and relax."

[1550] Sending and viewing advice

[1551] The server receives the generated advice and sends the contents of the advice to the user's terminal, which displays the received advice.

[1552] Specific examples and prompts for generative AI models

[1553] For example, if a worker asks the robot the following question:

[1554] Input Audio:

[1555] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[1556] Example prompt:

[1557] Q: I'm worried about how to operate my new welding machine. What should I do?

[1558] Emotion: Anxiety

[1559] This system allows factory workers to easily ask questions through voice input and receive specific advice in real time that takes their emotions into consideration, reducing anxiety about new tasks and equipment and enabling them to work efficiently and with peace of mind.

[1560] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1561] Step 1:

[1562] User question input

[1563] The user (factory worker) uses the device's voice input function to input a question about work. For example, the user might say, "I'm worried because I don't know how to operate the new welding machine. What should I do?" The input data here is voice data. The device converts this voice data into text data using voice recognition software (for example, Google Speech Recognition). The converted text data is then output.

[1564] Step 2:

[1565] Submit a Question

[1566] The question converted into text data is sent from the terminal to the server. The terminal then sends this data to the server via the Internet. The input is text data, and the output is the text data sent to the server.

[1567] Step 3:

[1568] Sentiment analysis request

[1569] The server inputs the question received from the user into the emotion engine and requests emotion analysis. The input is text data, and the emotion engine uses natural language processing technology to analyze the text data and recognize emotions (such as "anxiety" or "excitement"). Emotion data is output as the analysis result.

[1570] Step 4:

[1571] Request for advice generation

[1572] The server inputs the emotion analysis results and the question into the generative AI model and requests it to generate advice. The input is text data and emotion data. The generative AI model generates appropriate advice based on this input data. The generated advice (text data) is output.

[1573] Step 5:

[1574] Sending Advice

[1575] The server receives the generated advice and sends it to the user's terminal. The input is the generated advice (text data), and the output is the advice sent to the terminal.

[1576] Step 6:

[1577] Displaying Advice

[1578] The user's device displays the received advice. The device provides the user with visual information by outputting the advice content on the display. The input is the advice (text data), and the output is the advice displayed on the display.

[1579] Examples and prompts

[1580] For example, if a worker asks the robot the following question:

[1581] Input Audio:

[1582] "I'm worried because I don't know how to operate my new welding machine. What should I do?"

[1583] Example prompt:

[1584] Q: I'm worried about how to operate my new welding machine. What should I do?

[1585] Emotion: Anxiety

[1586] In this case, users can simply ask questions through voice input and receive specific advice in real time that takes their emotions into consideration.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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.

[1592] 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.

[1593] 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).

[1594] 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.

[1595] 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."

[1596] 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.

[1597] 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).

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] The following is further disclosed regarding the above embodiment.

[1609] (Claim 1)

[1610] a terminal for a user to input and send questions about hobbies;

[1611] A means for inputting a question received by the server from a user into a generative AI model;

[1612] A means for the generative AI model to analyze questions and generate optimal advice;

[1613] means for transmitting the advice generated by the server to a user's terminal;

[1614] means for displaying the advice received by the user's terminal;

[1615] A system including:

[1616] (Claim 2)

[1617] 10. The system of claim 1, wherein the generative AI model further comprises means for generating a plurality of pieces of advice related to different types of hobbies based on a user's question.

[1618] (Claim 3)

[1619] 2. The system according to claim 1, further comprising database means for storing questions sent by the user's terminal in a server and recording past questions and generated advice.

[1620] "Example 1"

[1621] (Claim 1)

[1622] an electronic device in which a user inputs and transmits a question about a hobby;

[1623] a means for inputting a question received by the server from a user into a generative artificial intelligence model;

[1624] means for the generative artificial intelligence model to analyze questions and generate optimal advice;

[1625] means for transmitting the generated advice to the user's electronic device by the server;

[1626] means for displaying the advice received by the user's electronic device;

[1627] A system including:

[1628] (Claim 2)

[1629] 10. The system of claim 1, wherein the generative artificial intelligence model further comprises means for generating a plurality of pieces of advice related to different types of hobbies based on a user's question.

[1630] (Claim 3)

[1631] 10. The system of claim 1, wherein said server further comprises means for storing user questions and generated advice in a database means.

[1632] "Application Example 1"

[1633] (Claim 1)

[1634] an electronic device in which a user inputs and transmits a question about a hobby;

[1635] a means for inputting a question received by the server from a user into a generative artificial intelligence model;

[1636] means for the generative artificial intelligence model to analyze questions and generate optimal advice;

[1637] means for transmitting the generated advice to the user's electronic device by the server;

[1638] means for displaying the advice received by the user's electronic device;

[1639] a means of providing related videos and articles along with the generated advice;

[1640] a database means for recording questions previously submitted by users and advice generated;

[1641] A system including:

[1642] (Claim 2)

[1643] 10. The system of claim 1, wherein the generative artificial intelligence model further comprises means for generating a plurality of pieces of advice related to different types of hobbies based on a user's question.

[1644] (Claim 3)

[1645] 2. The system according to claim 1, further comprising a database means for storing questions sent by the user's electronic device and recording past questions and generated advice.

[1646] "Example 2: Combining Emotion Engines"

[1647] (Claim 1)

[1648] a terminal for a user to input and send questions about hobbies;

[1649] a means for inputting the question received from the user by the server into an emotion analysis device to perform emotion analysis;

[1650] A means for the server to input the emotion analysis results and questions into a generative artificial intelligence model;

[1651] A means for a generative artificial intelligence model to analyze the emotion analysis results and questions and generate optimal advice;

[1652] means for the server to transmit the generated advice to the user's terminal;

[1653] means for displaying the advice received by the user's terminal;

[1654] means for storing the questions and generated advice in a data storage device;

[1655] A system including:

[1656] (Claim 2)

[1657] 2. The system of claim 1, wherein the generative artificial intelligence model further comprises means for generating a plurality of pieces of advice on different types of hobbies based on a user's question and a sentiment analysis result.

[1658] (Claim 3)

[1659] 10. The system of claim 1, further comprising data management means for recording past questions and generated advice in said data storage means.

[1660] "Application example 2 when combining emotion engines"

[1661] (Claim 1)

[1662] a terminal for a user to input and send questions about hobbies;

[1663] A means for inputting a question received by the server from a user into a generative AI model;

[1664] A means for the generative AI model to generate optimal advice based on the question and emotion analysis results;

[1665] means for transmitting the advice generated by the server to a user's terminal;

[1666] means for displaying the advice received by the user's terminal;

[1667] a means for inputting a question via voice input;

[1668] A means for analyzing emotions from a user's question using an emotion engine;

[1669] A system including:

[1670] (Claim 2)

[1671] 2. The system of claim 1, wherein the generative AI model further comprises means for generating a plurality of pieces of advice on different types of hobbies based on a user's question and a sentiment analysis result.

[1672] (Claim 3)

[1673] 2. The system according to claim 1, further comprising database means for storing questions sent by the user's terminal in a server and recording past questions and generated advice. [Explanation of symbols]

[1674] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a terminal for a user to input and send questions about hobbies; A means for inputting a question received by the server from a user into a generative AI model; A means for the generative AI model to analyze questions and generate optimal advice; means for transmitting the advice generated by the server to a user's terminal; means for displaying the advice received by the user's terminal; A system including:

2. The system of claim 1 , further comprising means for the generative AI model to generate a plurality of pieces of advice related to different types of hobbies based on a user's question.

3. 2. The system according to claim 1, further comprising database means for storing questions sent by the user's terminal and recording past questions and generated advice.

Images