system

Abstract

We provide the system. [Solution] A means for a person with specialized knowledge to input that knowledge and speaking style as information, A method for training an AI model using natural language processing technology based on that input information, A means of storing and making available trained AI models on the platform, A means for users to search for AI models through the platform and begin interacting with them, A means by which an AI model generates a response to that AC input and sends it back to the user, A means of providing responses as an interactive learning experience and enhancing immersion through visual and auditory means, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, there is a problem that there is a lack of efficient means for widely sharing the knowledge of experts and the personalities of famous people. In particular, there is no platform to reproduce their specialized knowledge and talk styles and meet the needs of general consumers who want to use them. For this reason, there is a problem that it is difficult to effectively deploy specialized knowledge and use it as a new source of income.

Means for Solving the Problems

[0005] To address the above challenges, the present invention provides a system in which individuals with specialized knowledge input their knowledge and speaking style as data, and an AI model is trained based on that data. This allows the trained AI model to be stored on the platform, enabling general users to search for it and initiate a conversation. Furthermore, by providing a payment processing mechanism for general users to purchase the trained AI model and receive a customized conversational experience, as well as a mechanism for dynamically changing the model's speaking style, it becomes possible to effectively deploy and monetize the knowledge of experts and prominent figures.

[0006] A "person with specialized knowledge" is an individual who possesses advanced knowledge and experience in a specific field and has the ability to communicate that knowledge to others.

[0007] "Means of inputting knowledge and speaking style as data" refers to methods and devices for experts and prominent figures to provide their specialized information and unique speaking style in digital format as training data for AI models.

[0008] "Natural language processing technology" is an artificial intelligence technology used to analyze, understand, and generate human language using computers, and is used to build AI capable of natural conversation.

[0009] "Methods for training AI models" refer to algorithms and processes used to enable AI to learn and generate appropriate responses based on the provided data.

[0010] A "platform" is a general term for the infrastructure and services that store AI models and allow users to access and utilize them.

[0011] "Means of initiating dialogue" refer to methods and technologies that enable the exchange of messages between a user and an AI model.

[0012] A "payment processing method" refers to a system or process for securely and efficiently processing payments related to the purchase of AI models online.

[0013] "Means for dynamically changing the talk style" refers to technologies and methods for adjusting the response style of an AI model in real time according to the user's preferences and circumstances. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system according to the present invention provides a platform for individuals with specialized knowledge to reflect their knowledge and speaking style in AI models. This platform enables experts and prominent figures to leverage their expertise to generate customizable AI agents and offer them to a wide range of consumers.

[0036] The system primarily operates in the following way: First, users (experts and prominent figures) register their profiles on the platform. Next, users input their expertise and speaking style as data into the platform. This data includes past dialogue examples, scripts, and Q&A format information. The server receives this input data and prepares it as training data for the AI ​​model. Once trained, the AI ​​model gains the ability to generate responses that reflect the user's unique characteristics.

[0037] This trained AI model will be made publicly available through the platform, accessible to the general public. Users can search for AI agents, and once they find one they are interested in, they can make a purchase or initiate a conversation. Purchases will utilize secure payment processing methods on the platform.

[0038] During the interaction, the terminal (the user's device) sends user input to the server. The server generates responses to the user's questions and requests based on a trained AI model and sends them back to the terminal. By experiencing these responses, the user can get a feel for the speaking styles of experts and prominent figures, and obtain diverse information.

[0039] Furthermore, the system is designed to dynamically change the AI ​​model's speaking style. This allows the AI's response style to be adjusted according to the user's preferences and circumstances, providing a more customized conversational experience. In this way, the present invention aims to realize seamless knowledge sharing between experts, prominent figures, and general users, and to create new business models.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] Users access the platform as experts or celebrities and register a new account. They enter the required personal information and authentication details to create the account.

[0043] Step 2:

[0044] The server receives registration information submitted by users and stores it in the database. This activates the accounts of authenticated professionals and prominent figures.

[0045] Step 3:

[0046] Users input content into the platform that reflects their expertise and unique speaking style. Specifically, they upload data such as text, audio files, and example conversations.

[0047] Step 4:

[0048] The server prepares an AI model based on the input data. In this process, natural language processing techniques are used to format the provided dataset as training data for the AI ​​model.

[0049] Step 5:

[0050] The server uses training data to train the AI ​​model. This allows the model to learn specific knowledge and speaking styles, and acquire the ability to generate responses.

[0051] Step 6:

[0052] The server stores the trained AI model on the platform and prepares it for publication. At this point, the user configures the deployment settings.

[0053] Step 7:

[0054] General users access the platform, search for AI agents that interest them, initiate the purchase process, and complete the transaction using secure payment methods.

[0055] Step 8:

[0056] A regular user enters a message to initiate a conversation with the AI ​​agent. The terminal then sends this input to the server.

[0057] Step 9:

[0058] The server passes the received message to a trained AI model, which then generates an appropriate response. This response is based on the user's input and the AI ​​model's learning.

[0059] Step 10:

[0060] The server sends the generated response to the terminal. The terminal displays this response to the user, and the interaction is established.

[0061] This series of processes allows users to experience personalized interactions with AI and enables the widespread sharing of knowledge from experts and prominent figures.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] The goal is to provide a means for individual users with specialized knowledge to easily translate their knowledge and conversational style into digital agents and widely share them with the general public. Furthermore, it aims to create an environment where general consumers can intuitively interact with these agents and easily access specialized information.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for users with specialized knowledge to input their knowledge and interaction methods as information, means for training an agent using language processing technology based on the input information, and means for maintaining and making available the trained agent on a shared platform. This enables the widespread sharing of specialized knowledge and allows individual consumers to use digital agents as a source of specialized information.

[0067] "Specialized information" refers to information possessed by users who have deep knowledge and experience in a particular field, and is used in dialogue and knowledge sharing.

[0068] A "user" is an individual or organization that possesses specialized information and seeks to translate that knowledge and interaction methods into digital agents.

[0069] "Dialogue method" refers to the specific way a user speaks or expresses themselves when providing information.

[0070] "Information" refers to data entered by users and used to train agents, and includes knowledge and conversational style.

[0071] An "agent" is a trained AI model that reflects the user's expertise and communication style, enabling it to interact with consumers.

[0072] A "shared infrastructure" is a platform where trained agents are stored and accessible to consumers.

[0073] A "consumer" is an ordinary user who interacts with agents using a shared platform.

[0074] "Payment processing" refers to the settlement process that takes place when a consumer acquires a trained agent.

[0075] "Dynamically adaptable" means that the way a trained agent interacts can be flexibly changed in response to the situation and user input.

[0076] This system provides a platform that easily converts specialized information into digital agents and makes it available to a wide range of consumers. The operation of the entire system is described below.

[0077] First, users access the platform and create their own profile. Here, they register their expertise and speaking style as data on the platform. This data includes past dialogue examples, scripts, and Q&A format information.

[0078] Next, the server receives data provided by the user and prepares it as training data to generate an AI agent. The techniques used here include natural language processing and machine learning algorithms. The server processes this data and trains the generative AI model. Through this training, the agent gains the ability to generate natural responses that reflect the user's expertise and conversational style.

[0079] Trained AI agents are made publicly available on the platform, and ordinary users can access them. Ordinary users can search for agents that interest them and initiate a conversation. During the conversation, the terminal sends prompt messages from the ordinary user to the server. The server uses these prompts to have the AI ​​agent generate a response and sends the result back to the terminal.

[0080] As a concrete example, in the case of an AI agent specializing in cooking, a regular user might input a prompt such as, "Please tell me an easy and delicious pasta recipe." In response to this prompt, the agent provides expert advice or a recipe, which the regular user then receives.

[0081] As described above, the system allows individual users with specialized knowledge to reflect their expertise in digital agents, providing a platform where many consumers can access and acquire specialized information. All of these processes are carried out through the coordinated efforts of the server, terminals, and users.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] Users access the platform and create their own profile. Here, they provide basic information such as their name, area of ​​expertise, and contact details as input. As output, a user account is generated on the platform, ready for agent creation.

[0085] Step 2:

[0086] Users register their expertise and speaking style on the platform. At this stage, past dialogue data, scripts, and Q&A format information are input. The server receives this data and builds a training dataset as output. This dataset forms the basis for training the AI ​​model.

[0087] Step 3:

[0088] The server trains an AI model using data provided by the user. The training dataset prepared in step 2 is used as input here. The server applies natural language processing techniques and uses a generative AI model to train an agent capable of generating data-driven responses. The output is a trained AI agent that reflects the user's expertise.

[0089] Step 4:

[0090] Trained AI agents are made available on the platform by a server. General users access the platform and search for AI agents. Here, the input is a topic or keyword of interest to the user. The output is a list of relevant AI agents presented to the user.

[0091] Step 5:

[0092] A regular user initiates an interaction with a selected agent. The terminal receives prompts from the user as input and sends this information to the server. The server uses a trained AI agent to generate a response based on this input. The output, which includes the information the user requested and the results of the interaction, is sent back to the terminal.

[0093] Step 6:

[0094] The server dynamically adjusts the AI ​​agent's speaking style as needed. Input includes feedback from regular users and the results of conversations. Based on this, the server modifies the AI ​​agent's response style to provide a better conversational experience. The adjusted agent is provided as output, allowing the conversation with the user to continue.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] The challenge lies in providing a way for the general public to learn through interactive and immersive experiences with AI agents that reflect the knowledge and communication style of experts. Furthermore, there is a need for these AI agents to be customized for individual users, offering flexible dialogue models that can address diverse needs.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes means for a person with expertise to input their knowledge and speaking style as information, means for training an AI model using natural language processing technology based on that input information, and means for providing responses as an interactive learning experience and enhancing immersion through visual and auditory means. This enables users to enjoy a customized learning experience while effectively learning expert knowledge through interaction with an AI agent.

[0100] A "person with specialized knowledge" refers to an individual who possesses advanced information and skills in a specific field and has the ability to communicate that knowledge to others.

[0101] "Knowledge and communication style" refers to a person's specialized information and views, as well as the linguistic methods they use to convey that information.

[0102] "Means of inputting information" refers to methods and devices for registering specialized knowledge and speaking styles in a digital format within a system.

[0103] "Natural language processing technology" refers to all technologies that enable computers to understand and generate human language.

[0104] "Methods for training AI models" refers to the process of training an AI based on the data necessary to generate appropriate responses.

[0105] A "platform" refers to the environment or interface provided by a system that enables the search, access, and interaction of AI agents.

[0106] An "interactive learning experience" refers to an educational process in which users actively participate and deepen their knowledge through interaction.

[0107] "Means of enhancing immersion through visual and auditory means" refer to methods and technologies that use images and sounds to give users a sense of reality and connection.

[0108] A "customized learning experience" refers to an educational and learning process that is uniquely tailored to the individual needs and preferences of each user.

[0109] The system for realizing this invention involves individuals with specialized knowledge inputting their knowledge and speaking style as digital information, and using that information to build an AI model. A server uses specific natural language processing software, such as Transformers, to perform calculations to train the AI ​​model based on the input data. This training enables the AI ​​model to engage in conversations that reflect its specialized knowledge and unique speaking style.

[0110] The server stores this AI model on a cloud-based platform, making it accessible to users via the internet. Users connect to the platform through their device (smartphone or head-mounted display), search for a specific AI agent, and begin a conversation. At this time, input from the device is sent to the server, which generates a response based on the conversation and sends it back to the device.

[0111] This dialogue system utilizes a dialogue AI platform like Dialogflow, and further leverages real-time speech synthesis and video rendering technologies to provide an interactive learning experience through audio and video. For example, if a user types "Start Galileo's Astronomy Lecture" on their smartphone, the AI ​​agent will then teach the basics of astronomy from Galileo's perspective based on that command.

[0112] As a concrete example of a prompt in this system, input such as "Consult Shakespeare for ideas for a new play" allows the AI ​​agent to provide creative advice. This enables users to experience a rich learning environment through interaction with an AI agent possessing specialized knowledge.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1: Entering Expertise Data

[0115] Users input their expertise and unique speaking style digitally into the server using a terminal. This input data includes text data, scripts, and past dialogue examples. This information is registered as the system's foundational data.

[0116] Step 2: Training the AI ​​model

[0117] The server processes the input expertise data and begins training an AI model using Transformers, a natural language processing technique. Here, the server analyzes the input data and optimizes the AI ​​model to respond in a way that reflects the speaker's style and expertise. The output is the trained AI model.

[0118] Step 3: Save and publish the AI ​​model

[0119] The trained AI model is stored on a server-based platform. The server then makes this model publicly accessible to the general public. The output is a list of available AI agents.

[0120] Step 4: Search for and select an AI agent

[0121] Users access the platform from their devices and search for AI agents of interest. The input is a search query, and the output is agent information as search results.

[0122] Step 5: Start the interaction and send the prompt.

[0123] The user initiates an interaction with the selected AI agent and sends prompt messages from the terminal to the server. The input is the user's prompt message.

[0124] Step 6: Response generation and return

[0125] The server generates a response using a trained AI model based on the received prompt. As part of the data processing, an appropriate response is generated from the prompt. The output is the generated response, which is sent back from the server to the terminal.

[0126] Step 7: Provide interactive learning

[0127] The device presents the received responses to the user visually and audibly. This provides an interactive learning experience, allowing the user to acquire specialized knowledge.

[0128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0129] This invention is a system that combines an AI model incorporating the knowledge and speaking style of a person with expertise in that field with an emotion engine that recognizes the user's emotions and dynamically adjusts its responses. The aim of this system is to provide a personalized conversational experience.

[0130] In this system embodiment, users (experts or prominent figures) first input their knowledge and speaking style as data into the platform. The server then trains an AI model, building a model capable of reproducing the expert's unique characteristics. This model is then made publicly available on the platform.

[0131] The system further incorporates an emotion engine to analyze the user's emotional state in real time and reflect the results in the AI ​​model's responses. Specifically, it can extract emotions from text and voice input by ordinary users during a conversation, and respond in a friendly style if the emotion is positive, or in an empathetic or encouraging style if it is negative.

[0132] The device sends user input data and the emotional information contained therein to the emotion engine, and then sends the analysis results to the server. The server generates a response from the AI ​​model based on the feedback from the emotion engine and adjusts the talk style. This function enables not only the provision of information, but also interaction that is sensitive to the user's emotions.

[0133] Furthermore, the system can learn the user's emotional patterns based on long-term conversation history, thereby improving the accuracy of response predictions in future conversations. This learning process takes place on the server, enabling continuous service improvement.

[0134] In this way, the present invention provides a system that takes user emotions into consideration, offers a more sophisticated dialogue experience, and enables the more effective and widespread dissemination of the knowledge of experts and prominent figures.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] Users access the platform and create an account as an expert or public figure. They enter the required profile information and verifications and register with the system.

[0138] Step 2:

[0139] Users input data into the platform to replicate their expertise and speaking style. This data includes information such as past conversation examples and specific speaking characteristics.

[0140] Step 3:

[0141] The server receives data provided by the user and formats it as training data for the AI ​​model. It uses natural language processing techniques to transform the data into a learnable format.

[0142] Step 4:

[0143] The server trains the AI ​​model using the prepared data. This allows the model to acquire the ability to replicate the user's knowledge and speaking style. The trained model is then stored on the platform.

[0144] Step 5:

[0145] General users search for AI agents on the platform and select an agent that interests them. If necessary, they proceed with the purchase process and begin interacting with the agent.

[0146] Step 6:

[0147] The user enters a message to interact with the AI ​​agent. During this process, the emotion engine analyzes the message and identifies the user's emotional state.

[0148] Step 7:

[0149] The terminal sends the entered message and sentiment analysis results to the server. Sentiment information includes emotions extracted from the text context and speech.

[0150] Step 8:

[0151] The server adjusts the response generated by the AI ​​model based on the received emotional data. If the emotion is positive, it selects a friendly response; if it is negative, it selects an empathetic response.

[0152] Step 9:

[0153] The server sends the generated response back to the terminal and presents it to the user in an appropriate conversational style. This allows the user to experience a personalized interaction.

[0154] Step 10:

[0155] The server records the dialogue history and emotion patterns, and uses this to improve the accuracy of responses in future dialogues. The learned data is continuously used to improve the AI ​​model.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] In modern society, it is crucial to effectively convey the unique knowledge and conversational styles of experts to a wide audience. However, existing artificial intelligence response systems have struggled to achieve emotionally resonant interactions, resulting in an inability to optimize the user experience. Furthermore, they lack the functionality to leverage a user's past conversation history to improve response accuracy in subsequent interactions. These challenges need to be addressed.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for a person with expertise to input their knowledge and conversational style as information, means for training an artificial intelligence model using language processing technology based on the input information, and means for analyzing the user's emotional state and reflecting the analysis results in the response of the artificial intelligence model. This makes it possible to provide interaction that takes the user's emotions into consideration and to effectively convey expertise.

[0161] A "person with specialized knowledge" is an individual who possesses specialized knowledge and skills in a particular field and has the ability to communicate that knowledge to others.

[0162] "Conversation style" refers to a distinctive way of speaking or communication style possessed by a particular person, and includes their unique methods of expression and language choices.

[0163] An "information sharing platform" is a system or platform for storing and managing digital information and making it accessible to users.

[0164] "Language processing technology" refers to technical methods used to process, understand, and generate natural language, primarily performed by computers.

[0165] An "artificial intelligence model" is a computer program that has the ability to learn from data and perform specific tasks.

[0166] "Users" refers to end users who operate a system or service and utilize its functions.

[0167] "Emotional state analysis" is the process of extracting emotional nuances from user input data and identifying those emotions.

[0168] "Improved response accuracy" means that the system's responses to the user become more accurate and appropriate, based on past interactions and new information.

[0169] The system implementing this invention utilizes data from individuals with specialized knowledge and unique conversational styles to train and operate artificial intelligence models.

[0170] Users first input their expertise and conversational style as data into the platform. This data includes input in text and audio formats and represents the user's knowledge and characteristics. The data is collected in a secure and reliable digital environment.

[0171] The server uses data provided by users to train a generative AI model. In this process, natural language processing techniques are utilized to learn the user's unique style. Specifically, the server uses natural language processing libraries and frameworks (e.g., TENSORFLOW® and PyTorch) to learn the expert's knowledge and style. The trained model is stored on an information sharing platform and made accessible to other users.

[0172] Furthermore, the terminal is responsible for receiving text and voice data entered by the user and sending it to the server. The terminal operates in real time and is equipped with software for rapid emotion analysis, utilizing a specific emotion analysis engine (e.g., voice analysis software).

[0173] In this system, the server analyzes the user's emotional state using an emotion engine, and an artificial intelligence model generates an appropriate response based on that analysis. For example, if a user prompts, "Tell me more about dog behavior psychology," the server generates a detailed explanation based on its expertise and responds to the user. This allows the user to have a higher quality, more personalized conversational experience.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] Users input their expertise and conversational style as data. This input can be in text or audio format. For example, users generate text data by writing sentences and record audio data using a voice recorder. This data is then uploaded to the platform and sent to the server.

[0177] Step 2:

[0178] The server trains an artificial intelligence model based on input data received from the user. In this process, the server uses a natural language processing framework (e.g., TensorFlow or PyTorch) to perform calculations that learn the user's expertise and conversational style. It analyzes the data and generates a model that includes the content of the knowledge and characteristic speech patterns. The trained model is stored on an information sharing platform.

[0179] Step 3:

[0180] The terminal acquires input data (text or voice) from regular users in real time. This input data is formatted for analysis and sent to the emotion engine. The terminal uses speech recognition software or a text interface to convert speech to text and prepares the data to be sent to the server in the appropriate format.

[0181] Step 4:

[0182] The server receives data from a regular user sent from the terminal and analyzes their emotional state using an emotion engine. During the analysis, the server recognizes the nuances of the emotion and classifies it as positive, negative, or neutral. Based on the analysis results, the server begins generating a response using an artificial intelligence model.

[0183] Step 5:

[0184] The server generates a response using an artificial intelligence model, taking into account the sentiment analysis results. During generation, it incorporates information from a knowledge base and adjusts the response's tone and content to match the user's emotions. The generated response is then sent to the terminal.

[0185] Step 6:

[0186] The terminal receives responses sent from the server and presents them to the user. The terminal uses a display screen and audio output device to provide the responses to the user in an appropriate format. Through this process, the user can experience a personalized interaction based on expert knowledge.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] In modern society, there is a growing need to alleviate the loneliness and anxiety that elderly people, in particular, face in care settings, and to provide appropriate dialogue and support that takes their emotions into consideration. However, due to limited human resources and time constraints, they may not always receive sufficient support. To improve this situation, effective means are needed to consistently provide appropriate emotional support to those receiving care.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes means for an individual with specialized knowledge to input their knowledge and conversational style as information; means for sentiment analysis to analyze the emotional state of general users and adjust the AI ​​model's response based on the results; and means for analyzing everyday conversations in a care support environment and generating appropriate support messages. This makes it possible for people receiving care to receive conversations and support tailored to their individual circumstances and emotions.

[0192] A "specialized individual" is someone who possesses deep knowledge and experience in a specific field and is capable of providing meaningful information based on that knowledge.

[0193] "Conversation style" is a general term for the way a particular speaker speaks, the characteristics of their communication, and their tone of voice, which they use on a daily basis.

[0194] "Information" refers to data and materials such as specialized knowledge and conversational style, which form the basis for training AI models.

[0195] "Natural language processing technology" refers to the technology used to enable computers to understand and generate human language.

[0196] An "AI model" is a model obtained through learning natural language processing technology, capable of reproducing specific knowledge and conversational styles.

[0197] A "digital platform" refers to an online system where AI models are stored and accessible to the general public.

[0198] "General users" are people who can interact with AI models through a digital platform, even without possessing specific expertise.

[0199] "Exploration" refers to the act of general users finding and selecting AI models on a digital platform.

[0200] "Dialogue" refers to the process of information exchange and communication that takes place between an AI model and a general user.

[0201] "Emotional state" refers to the user's psychological mood and emotional state, and is identified through emotion analysis.

[0202] "Emotional analysis means" refers to a technology or system that identifies a user's emotional state and uses that information to adjust their response.

[0203] "Care support environment" refers to the setting where care services are provided, as well as the living and support spaces for people receiving care.

[0204] A "support message" is a message of encouragement, advice, or other similar messages provided to people receiving care.

[0205] One embodiment of this invention is to provide an emotionally sensitive dialogue system in a care support environment by utilizing a generative AI model that reflects the knowledge and conversational style of experts.

[0206] First, the server provides a way for individuals with specialized knowledge to input their knowledge and conversational style as information. Based on the input information, an AI model is trained using natural language processing technology, and this trained AI model is stored on a digital platform. This allows general users to access this platform, explore the AI ​​model, and initiate conversations.

[0207] When a user interacts with a generative AI model, the terminal receives voice or text input and sends it to the server. The server uses sentiment analysis tools (e.g., sentiment analysis APIs) to analyze the user's emotional state in real time. Based on this analysis, the generative AI model determines the appropriate response and provides a appropriately adjusted conversation. For the AI ​​model adjustment process, for example, the generative model API from OpenAI® can be used.

[0208] For example, if an elderly person receiving care says, "I feel a bit down today," the server might respond with kind words like, "Why don't you reminisce about some wonderful memories? I might be able to help you with that." This kind of virtual support system allows users to always experience empathetic dialogue.

[0209] Example of a prompt:

[0210] This is an AI system that identifies user emotions and engages in conversation tailored to their feelings. Input: 'I've been feeling unwell and anxious lately.' Understand the emotion and generate a message to encourage the user.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The device receives voice or text input from the user. It recognizes this input and converts it into text data. In the case of voice input, this includes a process of converting it to text using speech recognition software. The recognized input is prepared as data to determine the user's emotional state.

[0214] Step 2:

[0215] The terminal sends the received text data to the server. This data is used as information to analyze the user's emotional state. The server passes the received text data to an emotion analysis tool. The emotion analysis tool (e.g., an emotion analysis API) uses natural language processing techniques to perform data calculations to estimate the user's current emotion (positive, negative, neutral, etc.).

[0216] Step 3:

[0217] The server utilizes a generative AI model to determine an appropriate response based on the analysis results. A process is initiated to generate a response that considers the user's emotional state while fitting the prompt. The generative AI model (e.g., OpenAI's generative model API) applies algorithms to optimize the tone and content of the conversation using the sentiment analysis results. The generated response is then refined based on a template and prepared in a format suitable for the user.

[0218] Step 4:

[0219] The server sends the generated response to the terminal. The terminal responds to this response as feedback to the user, either visually or audibly. The information the user obtains through interaction with the AI ​​serves as care support and emotional support. The user's feelings are cared for through the responses they receive. In this step, the system also prepares responses to await further input from the user, ensuring that the conversation continues smoothly.

[0220] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0236] The system according to the present invention provides a platform for individuals with specialized knowledge to reflect their knowledge and speaking style in AI models. This platform enables experts and prominent figures to leverage their expertise to generate customizable AI agents and offer them to a wide range of consumers.

[0237] The system primarily operates in the following way: First, users (experts and prominent figures) register their profiles on the platform. Next, users input their expertise and speaking style as data into the platform. This data includes past dialogue examples, scripts, and Q&A format information. The server receives this input data and prepares it as training data for the AI ​​model. Once trained, the AI ​​model gains the ability to generate responses that reflect the user's unique characteristics.

[0238] This trained AI model will be made publicly available through the platform, accessible to the general public. Users can search for AI agents, and once they find one they are interested in, they can make a purchase or initiate a conversation. Purchases will utilize secure payment processing methods on the platform.

[0239] During the interaction, the terminal (the user's device) sends user input to the server. The server generates responses to the user's questions and requests based on a trained AI model and sends them back to the terminal. By experiencing these responses, the user can get a feel for the speaking styles of experts and prominent figures, and obtain diverse information.

[0240] Furthermore, the system is designed to dynamically change the AI ​​model's speaking style. This allows the AI's response style to be adjusted according to the user's preferences and circumstances, providing a more customized conversational experience. In this way, the present invention aims to realize seamless knowledge sharing between experts, prominent figures, and general users, and to create new business models.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] Users access the platform as experts or celebrities and register a new account. They enter the required personal information and authentication details to create the account.

[0244] Step 2:

[0245] The server receives registration information submitted by users and stores it in the database. This activates the accounts of authenticated professionals and prominent figures.

[0246] Step 3:

[0247] Users input content into the platform that reflects their expertise and unique speaking style. Specifically, they upload data such as text, audio files, and example conversations.

[0248] Step 4:

[0249] The server prepares an AI model based on the input data. In this process, natural language processing techniques are used to format the provided dataset as training data for the AI ​​model.

[0250] Step 5:

[0251] The server uses training data to train the AI ​​model. This allows the model to learn specific knowledge and speaking styles, and acquire the ability to generate responses.

[0252] Step 6:

[0253] The server stores the trained AI model on the platform and prepares it for publication. At this point, the user configures the deployment settings.

[0254] Step 7:

[0255] General users access the platform, search for AI agents that interest them, initiate the purchase process, and complete the transaction using secure payment methods.

[0256] Step 8:

[0257] A regular user enters a message to initiate a conversation with the AI ​​agent. The terminal then sends this input to the server.

[0258] Step 9:

[0259] The server passes the received message to a trained AI model, which then generates an appropriate response. This response is based on the user's input and the AI ​​model's learning.

[0260] Step 10:

[0261] The server sends the generated response to the terminal. The terminal displays this response to the user, and the interaction is established.

[0262] This series of processes allows users to experience personalized interactions with AI and enables the widespread sharing of knowledge from experts and prominent figures.

[0263] (Example 1)

[0264] Next, we will describe Example 1. 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."

[0265] The goal is to provide a means for individual users with specialized knowledge to easily translate their knowledge and conversational style into digital agents and widely share them with the general public. Furthermore, it aims to create an environment where general consumers can intuitively interact with these agents and easily access specialized information.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for users with specialized knowledge to input their knowledge and interaction methods as information, means for training an agent using language processing technology based on the input information, and means for maintaining and making available the trained agent on a shared platform. This enables the widespread sharing of specialized knowledge and allows individual consumers to use digital agents as a source of specialized information.

[0268] "Specialized information" refers to information possessed by users who have deep knowledge and experience in a particular field, and is used in dialogue and knowledge sharing.

[0269] A "user" is an individual or organization that possesses specialized information and seeks to translate that knowledge and interaction methods into digital agents.

[0270] "Dialogue method" refers to the specific way a user speaks or expresses themselves when providing information.

[0271] "Information" refers to data entered by users and used to train agents, and includes knowledge and conversational style.

[0272] An "agent" is a trained AI model that reflects the user's expertise and communication style, enabling it to interact with consumers.

[0273] A "shared infrastructure" is a platform where trained agents are stored and accessible to consumers.

[0274] A "consumer" is an ordinary user who interacts with agents using a shared platform.

[0275] "Payment processing" refers to the settlement process that takes place when a consumer acquires a trained agent.

[0276] "Dynamically adaptable" means that the way a trained agent interacts can be flexibly changed in response to the situation and user input.

[0277] This system provides a platform that easily converts specialized information into digital agents and makes it available to a wide range of consumers. The operation of the entire system is described below.

[0278] First, users access the platform and create their own profile. Here, they register their expertise and speaking style as data on the platform. This data includes past dialogue examples, scripts, and Q&A format information.

[0279] Next, the server receives data provided by the user and prepares it as training data to generate an AI agent. The techniques used here include natural language processing and machine learning algorithms. The server processes this data and trains the generative AI model. Through this training, the agent gains the ability to generate natural responses that reflect the user's expertise and conversational style.

[0280] Trained AI agents are made publicly available on the platform, and ordinary users can access them. Ordinary users can search for agents that interest them and initiate a conversation. During the conversation, the terminal sends prompt messages from the ordinary user to the server. The server uses these prompts to have the AI ​​agent generate a response and sends the result back to the terminal.

[0281] As a concrete example, in the case of an AI agent specializing in cooking, a regular user might input a prompt such as, "Please tell me an easy and delicious pasta recipe." In response to this prompt, the agent provides expert advice or a recipe, which the regular user then receives.

[0282] As described above, the system provides a platform where individual users with specialized knowledge can reflect their knowledge in digital agents, and many consumers can access it to obtain specialized information. All these processes are carried out through the cooperation of the server, the terminal, and the users respectively.

[0283] The flow of specific processing in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The user accesses the platform to create their profile. Here, basic information such as the user's name, field of expertise, and contact information is provided as input. As output, the user's account is generated on the platform, and preparations for agent creation are completed.

[0286] Step 2:

[0287] The user registers their specialized information and conversation style on the platform. At this stage, past conversation data, scripts, and Q&A-formatted information are input. The server receives this data and constructs a training dataset as output. This dataset serves as the basis for training the AI model.

[0288] Step 3:

[0289] The server uses the data provided by the user to train the AI model. The training dataset prepared in Step 2 is used as input here. The server applies natural language processing technology and uses a generative AI model to train an agent with the ability to generate responses based on the data. The output is a trained AI agent that reflects the user's expertise.

[0290] Step 4:

[0291] Trained AI agents are made available on the platform by a server. General users access the platform and search for AI agents. Here, the input is a topic or keyword of interest to the user. The output is a list of relevant AI agents presented to the user.

[0292] Step 5:

[0293] A regular user initiates an interaction with a selected agent. The terminal receives prompts from the user as input and sends this information to the server. The server uses a trained AI agent to generate a response based on this input. The output, which includes the information the user requested and the results of the interaction, is sent back to the terminal.

[0294] Step 6:

[0295] The server dynamically adjusts the AI ​​agent's speaking style as needed. Input includes feedback from regular users and the results of conversations. Based on this, the server modifies the AI ​​agent's response style to provide a better conversational experience. The adjusted agent is provided as output, allowing the conversation with the user to continue.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] The challenge lies in providing a way for the general public to learn through interactive and immersive experiences with AI agents that reflect the knowledge and communication style of experts. Furthermore, there is a need for these AI agents to be customized for individual users, offering flexible dialogue models that can address diverse needs.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for a person with expertise to input their knowledge and speaking style as information, means for training an AI model using natural language processing technology based on the input information, and means for providing responses as an interactive learning experience and enhancing immersion through vision and sound. As a result, users can effectively learn specialized knowledge through interaction with the AI agent and enjoy a customized learning experience.

[0301] A "person with expertise" refers to an individual who has advanced information and skills in a specific field and the ability to convey them to others.

[0302] "Knowledge and speaking style" refers to the specialized information and opinions held by that person and the linguistic methods for conveying that information.

[0303] "Means for inputting as information" refers to the methods and devices for registering expertise and speaking style in digital form into the system.

[0304] "Natural language processing technology" generally refers to the technology that enables a computer to understand and generate human language.

[0305] "Means for training the AI model" refers to the process of training the AI to learn based on the data necessary for generating appropriate responses.

[0306] "Platform" refers to the environment and interface provided by the system that enables searching, accessing, and interacting with the AI agent.

[0307] "Interactive learning experience" refers to an educational process in which users actively participate and deepen their knowledge through interaction.

[0308] "Means of enhancing immersion through visuals and sound" refers to methods and technologies that use images and sounds to give users a sense of reality and connection.

[0309] A "customized learning experience" refers to an educational and learning process that is uniquely tailored to the individual needs and preferences of each user.

[0310] The system for realizing this invention involves individuals with specialized knowledge inputting their knowledge and speaking style as digital information, and using that information to build an AI model. A server uses specific natural language processing software, such as Transformers, to perform calculations to train the AI ​​model based on the input data. This training enables the AI ​​model to engage in conversations that reflect its specialized knowledge and unique speaking style.

[0311] The server stores this AI model on a cloud-based platform, making it accessible to users via the internet. Users connect to the platform through their device (smartphone or head-mounted display), search for a specific AI agent, and begin a conversation. At this time, input from the device is sent to the server, which generates a response based on the conversation and sends it back to the device.

[0312] This dialogue system utilizes a dialogue AI platform like Dialogflow, and further leverages real-time speech synthesis and video rendering technologies to provide an interactive learning experience through audio and video. For example, if a user types "Start Galileo's Astronomy Lecture" on their smartphone, the AI ​​agent will then teach the basics of astronomy from Galileo's perspective based on that command.

[0313] As a concrete example of a prompt in this system, input such as "Consult Shakespeare for ideas for a new play" allows the AI ​​agent to provide creative advice. This enables users to experience a rich learning environment through interaction with an AI agent possessing specialized knowledge.

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1: Entering Expertise Data

[0316] Users input their expertise and unique speaking style digitally into the server using a terminal. This input data includes text data, scripts, and past dialogue examples. This information is registered as the system's foundational data.

[0317] Step 2: Training the AI ​​model

[0318] The server processes the input expertise data and begins training an AI model using Transformers, a natural language processing technique. Here, the server analyzes the input data and optimizes the AI ​​model to respond in a way that reflects the speaker's style and expertise. The output is the trained AI model.

[0319] Step 3: Save and publish the AI ​​model

[0320] The trained AI model is stored on a server-based platform. The server then makes this model publicly accessible to the general public. The output is a list of available AI agents.

[0321] Step 4: Search for and select an AI agent

[0322] Users access the platform from their devices and search for AI agents of interest. The input is a search query, and the output is agent information as search results.

[0323] Step 5: Start the interaction and send the prompt.

[0324] The user initiates an interaction with the selected AI agent and sends prompt messages from the terminal to the server. The input is the user's prompt message.

[0325] Step 6: Response generation and return

[0326] The server generates a response using a trained AI model based on the received prompt. As part of the data processing, an appropriate response is generated from the prompt. The output is the generated response, which is sent back from the server to the terminal.

[0327] Step 7: Provide interactive learning

[0328] The device presents the received responses to the user visually and audibly. This provides an interactive learning experience, allowing the user to acquire specialized knowledge.

[0329] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0330] This invention is a system that combines an AI model incorporating the knowledge and speaking style of a person with expertise, with an emotion engine that recognizes user emotions and dynamically adjusts responses. The aim of this system is to provide a personalized conversational experience.

[0331] In this system embodiment, users (experts or prominent figures) first input their knowledge and speaking style as data into the platform. The server then trains an AI model, building a model capable of reproducing the expert's unique characteristics. This model is then made publicly available on the platform.

[0332] The system further incorporates an emotion engine to analyze the user's emotional state in real time and reflect the results in the AI ​​model's responses. Specifically, it can extract emotions from text and voice input by ordinary users during a conversation, and respond in a friendly style if the emotion is positive, or in an empathetic or encouraging style if it is negative.

[0333] The device sends user input data and the emotional information contained therein to the emotion engine, and then sends the analysis results to the server. The server generates a response from the AI ​​model based on the feedback from the emotion engine and adjusts the talk style. This function enables not only the provision of information, but also interaction that is sensitive to the user's emotions.

[0334] Furthermore, the system can learn the user's emotional patterns based on long-term conversation history, thereby improving the accuracy of response predictions in future conversations. This learning process takes place on the server, enabling continuous service improvement.

[0335] In this way, the present invention provides a system that takes user emotions into consideration, offers a more sophisticated dialogue experience, and enables the more effective and widespread dissemination of the knowledge of experts and prominent figures.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] Users access the platform and create an account as an expert or public figure. They enter the required profile information and verifications and register with the system.

[0339] Step 2:

[0340] Users input data into the platform to replicate their expertise and speaking style. This data includes information such as past conversation examples and specific speaking characteristics.

[0341] Step 3:

[0342] The server receives data provided by the user and formats it as training data for the AI ​​model. It uses natural language processing techniques to transform the data into a learnable format.

[0343] Step 4:

[0344] The server trains the AI ​​model using the prepared data. This allows the model to acquire the ability to replicate the user's knowledge and speaking style. The trained model is then stored on the platform.

[0345] Step 5:

[0346] General users search for AI agents on the platform and select an agent that interests them. If necessary, they proceed with the purchase process and begin interacting with the agent.

[0347] Step 6:

[0348] The user enters a message to interact with the AI ​​agent. During this process, the emotion engine analyzes the message and identifies the user's emotional state.

[0349] Step 7:

[0350] The terminal sends the entered message and sentiment analysis results to the server. Sentiment information includes emotions extracted from the text context and speech.

[0351] Step 8:

[0352] The server adjusts the response generated by the AI ​​model based on the received emotion data. If the emotion is positive, it selects a friendly response; if it is negative, it selects an empathetic response.

[0353] Step 9:

[0354] The server sends the generated response back to the terminal and presents it to the user in an appropriate conversational style. This allows the user to experience a personalized interaction.

[0355] Step 10:

[0356] The server records the dialogue history and emotion patterns, and uses this to improve the accuracy of responses in future dialogues. The learned data is continuously used to improve the AI ​​model.

[0357] (Example 2)

[0358] Next, we will describe Example 2. 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".

[0359] In modern society, it is crucial to effectively convey the unique knowledge and conversational styles of experts to a wide audience. However, existing artificial intelligence response systems have struggled to achieve emotionally resonant interactions, resulting in an inability to optimize the user experience. Furthermore, they lack the functionality to leverage a user's past conversation history to improve response accuracy in subsequent interactions. These challenges need to be addressed.

[0360] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0361] In this invention, the server includes means for a person with expertise to input their knowledge and conversational style as information, means for training an artificial intelligence model using language processing technology based on the input information, and means for analyzing the user's emotional state and reflecting the analysis results in the response of the artificial intelligence model. This makes it possible to provide interaction that takes the user's emotions into consideration and to effectively convey expertise.

[0362] A "person with specialized knowledge" is an individual who possesses specialized knowledge and skills in a particular field and has the ability to communicate that knowledge to others.

[0363] "Conversation style" refers to a distinctive way of speaking or communication style possessed by a particular person, and includes their unique methods of expression and language choices.

[0364] An "information sharing platform" is a system or platform for storing and managing digital information and making it accessible to users.

[0365] "Language processing technology" refers to technical methods used to process, understand, and generate natural language, primarily performed by computers.

[0366] An "artificial intelligence model" is a computer program that has the ability to learn from data and perform specific tasks.

[0367] "Users" refers to end users who operate a system or service and utilize its functions.

[0368] "Emotional state analysis" is the process of extracting emotional nuances from user input data and identifying those emotions.

[0369] "Improved response accuracy" means that the system's responses to the user become more accurate and appropriate, based on past interactions and new information.

[0370] The system implementing this invention utilizes data from individuals with specialized knowledge and unique conversational styles to train and operate artificial intelligence models.

[0371] Users first input their expertise and conversational style as data into the platform. This data includes input in text and audio formats and represents the user's knowledge and characteristics. The data is collected in a secure and reliable digital environment.

[0372] The server uses data provided by users to train a generative AI model. In this process, natural language processing techniques are utilized to learn the user's unique style. Specifically, the server uses natural language processing libraries and frameworks (e.g., TensorFlow and PyTorch) to learn the expert's knowledge and style. The trained model is stored on an information sharing platform and made accessible to other users.

[0373] Furthermore, the terminal is responsible for receiving text and voice data entered by the user and sending it to the server. The terminal operates in real time and is equipped with software for rapid emotion analysis, utilizing a specific emotion analysis engine (e.g., voice analysis software).

[0374] In this system, the server analyzes the user's emotional state using an emotion engine, and an artificial intelligence model generates an appropriate response based on that analysis. For example, if a user prompts, "Tell me more about dog behavior psychology," the server generates a detailed explanation based on its expertise and responds to the user. This allows the user to have a higher quality, more personalized conversational experience.

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] Users input their expertise and conversational style as data. This input can be in text or audio format. For example, users generate text data by writing sentences and record audio data using a voice recorder. This data is then uploaded to the platform and sent to the server.

[0378] Step 2:

[0379] The server trains an artificial intelligence model based on input data received from the user. In this process, the server uses a natural language processing framework (e.g., TensorFlow or PyTorch) to perform calculations that learn the user's expertise and conversational style. It analyzes the data and generates a model that includes the content of the knowledge and characteristic speech patterns. The trained model is stored on an information sharing platform.

[0380] Step 3:

[0381] The terminal acquires input data (text or voice) from regular users in real time. This input data is formatted for analysis and sent to the emotion engine. The terminal uses speech recognition software or a text interface to convert speech to text and prepares the data to be sent to the server in the appropriate format.

[0382] Step 4:

[0383] The server receives data from a regular user sent from the terminal and analyzes their emotional state using an emotion engine. During the analysis, the server recognizes the nuances of the emotion and classifies it as positive, negative, or neutral. Based on the analysis results, the server begins generating a response using an artificial intelligence model.

[0384] Step 5:

[0385] The server generates a response using an artificial intelligence model, taking into account the sentiment analysis results. During generation, it incorporates information from a knowledge base and adjusts the response's tone and content to match the user's emotions. The generated response is then sent to the terminal.

[0386] Step 6:

[0387] The terminal receives responses sent from the server and presents them to the user. The terminal uses a display screen and audio output device to provide the responses to the user in an appropriate format. Through this process, the user can experience a personalized interaction based on expert knowledge.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0390] In modern society, there is a growing need to alleviate the loneliness and anxiety that elderly people, in particular, face in care settings, and to provide appropriate dialogue and support that takes their emotions into consideration. However, due to limited human resources and time constraints, they may not always receive sufficient support. To improve this situation, effective means are needed to consistently provide appropriate emotional support to those receiving care.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes means for an individual with specialized knowledge to input their knowledge and conversational style as information; means for sentiment analysis to analyze the emotional state of general users and adjust the AI ​​model's response based on the results; and means for analyzing everyday conversations in a care support environment and generating appropriate support messages. This makes it possible for people receiving care to receive conversations and support tailored to their individual circumstances and emotions.

[0393] A "specialized individual" is someone who possesses deep knowledge and experience in a specific field and is capable of providing meaningful information based on that knowledge.

[0394] "Conversation style" is a general term for the way a particular speaker speaks, the characteristics of their communication, and their tone of voice, which they use on a daily basis.

[0395] "Information" refers to data and materials such as specialized knowledge and conversational style, which form the basis for training AI models.

[0396] "Natural language processing technology" refers to the technology used to enable computers to understand and generate human language.

[0397] An "AI model" is a model obtained through learning natural language processing technology, capable of reproducing specific knowledge and conversational styles.

[0398] A "digital platform" refers to an online system where AI models are stored and accessible to the general public.

[0399] "General users" are people who can interact with AI models through a digital platform, even without possessing specific expertise.

[0400] "Exploration" refers to the act of general users finding and selecting AI models on a digital platform.

[0401] "Dialogue" refers to the process of information exchange and communication that takes place between an AI model and a general user.

[0402] "Emotional state" refers to the user's psychological mood and emotional state, and is identified through emotion analysis.

[0403] "Emotional analysis means" refers to a technology or system that identifies a user's emotional state and uses that information to adjust their response.

[0404] "Care support environment" refers to the setting where care services are provided, as well as the living and support spaces for people receiving care.

[0405] A "support message" is a message of encouragement, advice, or other similar messages provided to people receiving care.

[0406] One embodiment of this invention is to provide an emotionally sensitive dialogue system in a care support environment by utilizing a generative AI model that reflects the knowledge and conversational style of experts.

[0407] First, the server provides a way for individuals with specialized knowledge to input their knowledge and conversational style as information. Based on the input information, an AI model is trained using natural language processing technology, and this trained AI model is stored on a digital platform. This allows general users to access this platform, explore the AI ​​model, and initiate conversations.

[0408] When a user interacts with a generative AI model, the terminal receives voice or text input and sends it to the server. The server uses sentiment analysis tools (e.g., sentiment analysis APIs) to analyze the user's emotional state in real time. Based on this analysis, the generative AI model determines the appropriate response and provides a appropriately adjusted conversation. For the AI ​​model adjustment process, for example, the OpenAI generative model API can be used.

[0409] For example, if an elderly person receiving care says, "I feel a bit down today," the server might respond with kind words like, "Why don't you reminisce about some wonderful memories? I might be able to help you with that." This kind of virtual support system allows users to always experience empathetic dialogue.

[0410] Example of a prompt:

[0411] This is an AI system that identifies user emotions and engages in conversation tailored to their feelings. Input: 'I've been feeling unwell and anxious lately.' Understand the emotion and generate a message to encourage the user.

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The device receives voice or text input from the user. It recognizes this input and converts it into text data. In the case of voice input, this includes a process of converting it to text using speech recognition software. The recognized input is prepared as data to determine the user's emotional state.

[0415] Step 2:

[0416] The terminal sends the received text data to the server. This data is used as information to analyze the user's emotional state. The server passes the received text data to an emotion analysis tool. The emotion analysis tool (e.g., an emotion analysis API) uses natural language processing techniques to perform data calculations to estimate the user's current emotion (positive, negative, neutral, etc.).

[0417] Step 3:

[0418] The server utilizes a generative AI model to determine an appropriate response based on the analysis results. A process is initiated to generate a response that considers the user's emotional state while fitting the prompt. The generative AI model (e.g., OpenAI's generative model API) applies algorithms to optimize the tone and content of the conversation using the sentiment analysis results. The generated response is then refined based on a template and prepared in a format suitable for the user.

[0419] Step 4:

[0420] The server sends the generated response to the terminal. The terminal responds to this response as feedback to the user, either visually or audibly. The information the user obtains through interaction with the AI ​​serves as care support and emotional support. The user's feelings are cared for through the responses they receive. In this step, the system also prepares responses to await further input from the user, ensuring that the conversation continues smoothly.

[0421] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0422] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0423] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0427] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0428] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0429] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0430] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0431] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0432] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0433] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0434] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0435] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0436] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0437] The system according to the present invention provides a platform for individuals with specialized knowledge to reflect their knowledge and speaking style in AI models. This platform enables experts and prominent figures to leverage their expertise to generate customizable AI agents and offer them to a wide range of consumers.

[0438] The system primarily operates in the following way: First, users (experts and prominent figures) register their profiles on the platform. Next, users input their expertise and speaking style as data into the platform. This data includes past dialogue examples, scripts, and Q&A format information. The server receives this input data and prepares it as training data for the AI ​​model. Once trained, the AI ​​model gains the ability to generate responses that reflect the user's unique characteristics.

[0439] This trained AI model will be made publicly available through the platform, accessible to the general public. Users can search for AI agents, and once they find one they are interested in, they can make a purchase or initiate a conversation. Purchases will utilize secure payment processing methods on the platform.

[0440] During the interaction, the terminal (the user's device) sends user input to the server. The server generates responses to the user's questions and requests based on a trained AI model and sends them back to the terminal. By experiencing these responses, the user can get a feel for the speaking styles of experts and prominent figures, and obtain diverse information.

[0441] Furthermore, the system is designed to dynamically change the AI ​​model's speaking style. This allows the AI's response style to be adjusted according to the user's preferences and circumstances, providing a more customized conversational experience. In this way, the present invention aims to realize seamless knowledge sharing between experts, prominent figures, and general users, and to create new business models.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] Users access the platform as experts or celebrities and register a new account. They enter the required personal information and authentication details to create the account.

[0445] Step 2:

[0446] The server receives registration information submitted by users and stores it in the database. This activates the accounts of authenticated professionals and prominent figures.

[0447] Step 3:

[0448] Users input content into the platform that reflects their expertise and unique speaking style. Specifically, they upload data such as text, audio files, and example conversations.

[0449] Step 4:

[0450] The server prepares an AI model based on the input data. In this process, natural language processing techniques are used to format the provided dataset as training data for the AI ​​model.

[0451] Step 5:

[0452] The server uses training data to train the AI ​​model. This allows the model to learn specific knowledge and speaking styles, and acquire the ability to generate responses.

[0453] Step 6:

[0454] The server stores the trained AI model on the platform and prepares it for publication. At this point, the user configures the deployment settings.

[0455] Step 7:

[0456] General users access the platform, search for AI agents that interest them, initiate the purchase process, and complete the transaction using secure payment methods.

[0457] Step 8:

[0458] A regular user enters a message to initiate a conversation with the AI ​​agent. The terminal then sends this input to the server.

[0459] Step 9:

[0460] The server passes the received message to a trained AI model, which then generates an appropriate response. This response is based on the user's input and the AI ​​model's learning.

[0461] Step 10:

[0462] The server sends the generated response to the terminal. The terminal displays this response to the user, and the interaction is established.

[0463] This series of processes allows users to experience personalized interactions with AI and enables the widespread sharing of knowledge from experts and prominent figures.

[0464] (Example 1)

[0465] Next, we will describe Example 1. 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."

[0466] The goal is to provide a means for individual users with specialized knowledge to easily translate their knowledge and conversational style into digital agents and widely share them with the general public. Furthermore, it aims to create an environment where general consumers can intuitively interact with these agents and easily access specialized information.

[0467] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0468] In this invention, the server includes means for users with specialized knowledge to input their knowledge and interaction methods as information, means for training an agent using language processing technology based on the input information, and means for maintaining and making available the trained agent on a shared platform. This enables the widespread sharing of specialized knowledge and allows individual consumers to use digital agents as a source of specialized information.

[0469] "Specialized information" refers to information possessed by users who have deep knowledge and experience in a particular field, and is used in dialogue and knowledge sharing.

[0470] A "user" is an individual or organization that possesses specialized information and seeks to translate that knowledge and interaction methods into digital agents.

[0471] "Dialogue method" refers to the specific way a user speaks or expresses themselves when providing information.

[0472] "Information" refers to data entered by users and used to train agents, and includes knowledge and conversational style.

[0473] An "agent" is a trained AI model that reflects the user's expertise and communication style, enabling it to interact with consumers.

[0474] A "shared infrastructure" is a platform where trained agents are stored and accessible to consumers.

[0475] A "consumer" is an ordinary user who interacts with agents using a shared platform.

[0476] "Payment processing" refers to the settlement process that takes place when a consumer acquires a trained agent.

[0477] "Dynamically adaptable" means that the way a trained agent interacts can be flexibly changed in response to the situation and user input.

[0478] This system provides a platform that easily converts specialized information into digital agents and makes it available to a wide range of consumers. The operation of the entire system is described below.

[0479] First, users access the platform and create their own profile. Here, they register their expertise and speaking style as data on the platform. This data includes past dialogue examples, scripts, and Q&A format information.

[0480] Next, the server receives data provided by the user and prepares it as training data to generate an AI agent. The techniques used here include natural language processing and machine learning algorithms. The server processes this data and trains the generative AI model. Through this training, the agent gains the ability to generate natural responses that reflect the user's expertise and conversational style.

[0481] Trained AI agents are made publicly available on the platform, and ordinary users can access them. Ordinary users can search for agents that interest them and initiate a conversation. During the conversation, the terminal sends prompt messages from the ordinary user to the server. The server uses these prompts to have the AI ​​agent generate a response and sends the result back to the terminal.

[0482] As a concrete example, in the case of an AI agent specializing in cooking, a regular user might input a prompt such as, "Please tell me an easy and delicious pasta recipe." In response to this prompt, the agent provides expert advice or a recipe, which the regular user then receives.

[0483] As described above, the system allows individual users with specialized knowledge to reflect their expertise in digital agents, providing a platform where many consumers can access and acquire specialized information. All of these processes are carried out through the coordinated efforts of the server, terminals, and users.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] Users access the platform and create their own profile. Here, they provide basic information such as their name, area of ​​expertise, and contact details as input. As output, a user account is generated on the platform, ready for agent creation.

[0487] Step 2:

[0488] Users register their expertise and speaking style on the platform. At this stage, past dialogue data, scripts, and Q&A format information are input. The server receives this data and builds a training dataset as output. This dataset forms the basis for training the AI ​​model.

[0489] Step 3:

[0490] The server trains an AI model using data provided by the user. The training dataset prepared in step 2 is used as input here. The server applies natural language processing techniques and uses a generative AI model to train an agent capable of generating data-driven responses. The output is a trained AI agent that reflects the user's expertise.

[0491] Step 4:

[0492] Trained AI agents are made available on the platform by a server. General users access the platform and search for AI agents. Here, the input is a topic or keyword of interest to the user. The output is a list of relevant AI agents presented to the user.

[0493] Step 5:

[0494] A regular user initiates an interaction with a selected agent. The terminal receives prompts from the user as input and sends this information to the server. The server uses a trained AI agent to generate a response based on this input. The output, which includes the information the user requested and the results of the interaction, is sent back to the terminal.

[0495] Step 6:

[0496] The server dynamically adjusts the AI ​​agent's speaking style as needed. Input includes feedback from regular users and the results of conversations. Based on this, the server modifies the AI ​​agent's response style to provide a better conversational experience. The adjusted agent is provided as output, allowing the conversation with the user to continue.

[0497] (Application Example 1)

[0498] Next, we will explain Application Example 1. In the following explanation, 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."

[0499] The challenge lies in providing a way for the general public to learn through interactive and immersive experiences with AI agents that reflect the knowledge and communication style of experts. Furthermore, there is a need for these AI agents to be customized for individual users, offering flexible dialogue models that can address diverse needs.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0501] In this invention, the server includes means for a person with expertise to input their knowledge and speaking style as information, means for training an AI model using natural language processing technology based on that input information, and means for providing responses as an interactive learning experience and enhancing immersion through visual and auditory means. This enables users to enjoy a customized learning experience while effectively learning expert knowledge through interaction with an AI agent.

[0502] A "person with specialized knowledge" refers to an individual who possesses advanced information and skills in a specific field and has the ability to communicate that knowledge to others.

[0503] "Knowledge and speaking style" refers to a person's specialized information and views, as well as the linguistic methods they use to communicate that information.

[0504] "Means of inputting information" refers to methods and devices for registering specialized knowledge and speaking styles in a digital format within a system.

[0505] "Natural language processing technology" refers to all technologies that enable computers to understand and generate human language.

[0506] "Methods for training an AI model" refers to the process of training an AI based on the data necessary to generate appropriate responses.

[0507] A "platform" refers to the environment or interface provided by a system that enables the search, access, and interaction of AI agents.

[0508] An "interactive learning experience" refers to an educational process in which users actively participate and deepen their knowledge through interaction.

[0509] "Means of enhancing immersion through visuals and sound" refers to methods and technologies that use images and sounds to give users a sense of reality and connection.

[0510] A "customized learning experience" refers to an educational and learning process that is uniquely tailored to the individual needs and preferences of each user.

[0511] The system for realizing this invention involves individuals with specialized knowledge inputting their knowledge and speaking style as digital information, and using that information to build an AI model. A server uses specific natural language processing software, such as Transformers, to perform calculations to train the AI ​​model based on the input data. This training enables the AI ​​model to engage in conversations that reflect its specialized knowledge and unique speaking style.

[0512] The server stores this AI model on a cloud-based platform, making it accessible to users via the internet. Users connect to the platform through their device (smartphone or head-mounted display), search for a specific AI agent, and begin a conversation. At this time, input from the device is sent to the server, which generates a response based on the conversation and sends it back to the device.

[0513] This dialogue system utilizes a dialogue AI platform like Dialogflow, and further leverages real-time speech synthesis and video rendering technologies to provide an interactive learning experience through audio and video. For example, if a user types "Start Galileo's Astronomy Lecture" on their smartphone, the AI ​​agent will then teach the basics of astronomy from Galileo's perspective based on that command.

[0514] As a concrete example of a prompt in this system, input such as "Consult Shakespeare for ideas for a new play" allows the AI ​​agent to provide creative advice. This enables users to experience a rich learning environment through interaction with an AI agent possessing specialized knowledge.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1: Entering Expertise Data

[0517] Users input their expertise and unique speaking style digitally into the server using a terminal. This input data includes text data, scripts, and past dialogue examples. This information is registered as the system's foundational data.

[0518] Step 2: Training the AI ​​model

[0519] The server processes the input expertise data and begins training an AI model using Transformers, a natural language processing technique. Here, the server analyzes the input data and optimizes the AI ​​model to respond in a way that reflects the speaker's style and expertise. The output is the trained AI model.

[0520] Step 3: Save and publish the AI ​​model

[0521] The trained AI model is stored on a server-based platform. The server then makes this model publicly accessible to the general public. The output is a list of available AI agents.

[0522] Step 4: Search for and select an AI agent

[0523] Users access the platform from their devices and search for AI agents of interest. The input is a search query, and the output is agent information as search results.

[0524] Step 5: Start the interaction and send the prompt.

[0525] The user initiates an interaction with the selected AI agent and sends prompt messages from the terminal to the server. The input is the user's prompt message.

[0526] Step 6: Response generation and return

[0527] The server generates a response using a trained AI model based on the received prompt. As part of the data processing, an appropriate response is generated from the prompt. The output is the generated response, which is sent back from the server to the terminal.

[0528] Step 7: Provide interactive learning

[0529] The device presents the received responses to the user visually and audibly. This provides an interactive learning experience, allowing the user to acquire specialized knowledge.

[0530] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0531] This invention is a system that combines an AI model incorporating the knowledge and speaking style of a person with expertise, with an emotion engine that recognizes user emotions and dynamically adjusts responses. The aim of this system is to provide a personalized conversational experience.

[0532] In this system embodiment, users (experts or prominent figures) first input their knowledge and speaking style as data into the platform. The server then trains an AI model, building a model capable of reproducing the expert's unique characteristics. This model is then made publicly available on the platform.

[0533] The system further incorporates an emotion engine to analyze the user's emotional state in real time and reflect the results in the AI ​​model's responses. Specifically, it can extract emotions from text and voice input by ordinary users during a conversation, and respond in a friendly style if the emotion is positive, or in an empathetic or encouraging style if it is negative.

[0534] The device sends user input data and the emotional information contained therein to the emotion engine, and then sends the analysis results to the server. The server generates a response from the AI ​​model based on the feedback from the emotion engine and adjusts the talk style. This function enables not only the provision of information, but also interaction that is sensitive to the user's emotions.

[0535] Furthermore, the system can learn the user's emotional patterns based on long-term conversation history, thereby improving the accuracy of response predictions in future conversations. This learning process takes place on the server, enabling continuous service improvement.

[0536] In this way, the present invention provides a system that takes user emotions into consideration, offers a more sophisticated dialogue experience, and enables the more effective and widespread dissemination of the knowledge of experts and prominent figures.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] Users access the platform and create an account as an expert or public figure. They enter the required profile information and verifications and register with the system.

[0540] Step 2:

[0541] Users input data into the platform to replicate their expertise and speaking style. This data includes information such as past conversation examples and specific speaking characteristics.

[0542] Step 3:

[0543] The server receives data provided by the user and formats it as training data for the AI ​​model. It uses natural language processing techniques to transform the data into a learnable format.

[0544] Step 4:

[0545] The server trains the AI ​​model using the prepared data. This allows the model to acquire the ability to replicate the user's knowledge and speaking style. The trained model is then stored on the platform.

[0546] Step 5:

[0547] General users search for AI agents on the platform and select an agent that interests them. If necessary, they proceed with the purchase process and begin interacting with the agent.

[0548] Step 6:

[0549] The user enters a message to interact with the AI ​​agent. During this process, the emotion engine analyzes the message and identifies the user's emotional state.

[0550] Step 7:

[0551] The terminal sends the entered message and sentiment analysis results to the server. Sentiment information includes emotions extracted from the text context and speech.

[0552] Step 8:

[0553] The server adjusts the response generated by the AI ​​model based on the received emotion data. If the emotion is positive, it selects a friendly response; if it is negative, it selects an empathetic response.

[0554] Step 9:

[0555] The server sends the generated response back to the terminal and presents it to the user in an appropriate conversational style. This allows the user to experience a personalized interaction.

[0556] Step 10:

[0557] The server records the dialogue history and emotion patterns, and uses this to improve the accuracy of responses in future dialogues. The learned data is continuously used to improve the AI ​​model.

[0558] (Example 2)

[0559] Next, we will describe Example 2. 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."

[0560] In modern society, it is crucial to effectively convey the unique knowledge and conversational styles of experts to a wide audience. However, existing artificial intelligence response systems have struggled to achieve emotionally resonant interactions, resulting in an inability to optimize the user experience. Furthermore, they lack the functionality to leverage a user's past conversation history to improve response accuracy in subsequent interactions. These challenges need to be addressed.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0562] In this invention, the server includes means for a person with expertise to input their knowledge and conversational style as information, means for training an artificial intelligence model using language processing technology based on the input information, and means for analyzing the user's emotional state and reflecting the analysis results in the response of the artificial intelligence model. This makes it possible to provide interaction that takes the user's emotions into consideration and to effectively convey expertise.

[0563] A "person with specialized knowledge" is an individual who possesses specialized knowledge and skills in a particular field and has the ability to communicate that knowledge to others.

[0564] "Conversation style" refers to a distinctive way of speaking or communication style possessed by a particular person, and includes their unique methods of expression and language choices.

[0565] An "information sharing platform" is a system or platform for storing and managing digital information and making it accessible to users.

[0566] "Language processing technology" refers to technical methods used to process, understand, and generate natural language, primarily performed by computers.

[0567] An "artificial intelligence model" is a computer program that has the ability to learn from data and perform specific tasks.

[0568] "Users" refers to end users who operate a system or service and utilize its functions.

[0569] "Emotional state analysis" is the process of extracting emotional nuances from user input data and identifying those emotions.

[0570] "Improved response accuracy" means that the system's responses to the user become more accurate and appropriate, based on past interactions and new information.

[0571] The system implementing this invention utilizes data from individuals with specialized knowledge and unique conversational styles to train and operate artificial intelligence models.

[0572] Users first input their expertise and conversational style as data into the platform. This data includes input in text and audio formats and represents the user's knowledge and characteristics. The data is collected in a secure and reliable digital environment.

[0573] The server uses data provided by users to train a generative AI model. In this process, natural language processing techniques are utilized to learn the user's unique style. Specifically, the server uses natural language processing libraries and frameworks (e.g., TensorFlow and PyTorch) to learn the expert's knowledge and style. The trained model is stored on an information sharing platform and made accessible to other users.

[0574] Furthermore, the terminal is responsible for receiving text and voice data entered by the user and sending it to the server. The terminal operates in real time and is equipped with software for rapid emotion analysis, utilizing a specific emotion analysis engine (e.g., voice analysis software).

[0575] In this system, the server analyzes the user's emotional state using an emotion engine, and an artificial intelligence model generates an appropriate response based on that analysis. For example, if a user prompts, "Tell me more about dog behavior psychology," the server generates a detailed explanation based on its expertise and responds to the user. This allows the user to have a higher quality, more personalized conversational experience.

[0576] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0577] Step 1:

[0578] Users input their expertise and conversational style as data. This input can be in text or audio format. For example, users generate text data by writing sentences and record audio data using a voice recorder. This data is then uploaded to the platform and sent to the server.

[0579] Step 2:

[0580] The server trains an artificial intelligence model based on input data received from the user. In this process, the server uses a natural language processing framework (e.g., TensorFlow or PyTorch) to perform calculations that learn the user's expertise and conversational style. It analyzes the data and generates a model that includes the content of the knowledge and characteristic speech patterns. The trained model is stored on an information sharing platform.

[0581] Step 3:

[0582] The terminal acquires input data (text or voice) from regular users in real time. This input data is formatted for analysis and sent to the emotion engine. The terminal uses speech recognition software or a text interface to convert speech to text and prepares the data to be sent to the server in the appropriate format.

[0583] Step 4:

[0584] The server receives data from a regular user sent from the terminal and analyzes their emotional state using an emotion engine. During the analysis, the server recognizes the nuances of the emotion and classifies it as positive, negative, or neutral. Based on the analysis results, the server begins generating a response using an artificial intelligence model.

[0585] Step 5:

[0586] The server generates a response using an artificial intelligence model, taking into account the sentiment analysis results. During generation, it incorporates information from a knowledge base and adjusts the response's tone and content to match the user's emotions. The generated response is then sent to the terminal.

[0587] Step 6:

[0588] The terminal receives responses sent from the server and presents them to the user. The terminal uses a display screen and audio output device to provide the responses to the user in an appropriate format. Through this process, the user can experience a personalized interaction based on expert knowledge.

[0589] (Application Example 2)

[0590] Next, we will explain application example 2. In the following explanation, 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."

[0591] In modern society, there is a growing need to alleviate the loneliness and anxiety that elderly people, in particular, face in care settings, and to provide appropriate dialogue and support that takes their emotions into consideration. However, due to limited human resources and time constraints, they may not always receive sufficient support. To improve this situation, effective means are needed to consistently provide appropriate emotional support to those receiving care.

[0592] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0593] In this invention, the server includes means for an individual with specialized knowledge to input their knowledge and conversational style as information; means for sentiment analysis to analyze the emotional state of general users and adjust the AI ​​model's response based on the results; and means for analyzing everyday conversations in a care support environment and generating appropriate support messages. This makes it possible for people receiving care to receive conversations and support tailored to their individual circumstances and emotions.

[0594] A "specialized individual" is someone who possesses deep knowledge and experience in a specific field and is capable of providing meaningful information based on that knowledge.

[0595] "Conversation style" is a general term for the way a particular speaker speaks, the characteristics of their communication, and their tone of voice, which they use on a daily basis.

[0596] "Information" refers to data and materials such as specialized knowledge and conversational style, which form the basis for training AI models.

[0597] "Natural language processing technology" refers to the technology used to enable computers to understand and generate human language.

[0598] An "AI model" is a model obtained through learning natural language processing technology, capable of reproducing specific knowledge and conversational styles.

[0599] A "digital platform" refers to an online system where AI models are stored and accessible to the general public.

[0600] "General users" are people who can interact with AI models through a digital platform, even without possessing specific expertise.

[0601] "Exploration" refers to the act of general users finding and selecting AI models on a digital platform.

[0602] "Dialogue" refers to the process of information exchange and communication that takes place between an AI model and a general user.

[0603] "Emotional state" refers to the user's psychological mood and emotional state, and is identified through emotion analysis.

[0604] "Emotional analysis means" refers to a technology or system that identifies a user's emotional state and uses that information to adjust their response.

[0605] "Care support environment" refers to the setting where care services are provided, as well as the living and support spaces for people receiving care.

[0606] A "support message" is a message of encouragement, advice, or other similar messages provided to people receiving care.

[0607] One embodiment of this invention is to provide an emotionally sensitive dialogue system in a care support environment by utilizing a generative AI model that reflects the knowledge and conversational style of experts.

[0608] First, the server provides a way for individuals with specialized knowledge to input their knowledge and conversational style as information. Based on the input information, an AI model is trained using natural language processing technology, and this trained AI model is stored on a digital platform. This allows general users to access this platform, explore the AI ​​model, and initiate conversations.

[0609] When a user interacts with a generative AI model, the terminal receives voice or text input and sends it to the server. The server uses sentiment analysis tools (e.g., sentiment analysis APIs) to analyze the user's emotional state in real time. Based on this analysis, the generative AI model determines the appropriate response and provides a appropriately adjusted conversation. For the AI ​​model adjustment process, for example, the OpenAI generative model API can be used.

[0610] For example, if an elderly person receiving care says, "I feel a bit down today," the server might respond with kind words like, "Why don't you reminisce about some wonderful memories? I might be able to help you with that." This kind of virtual support system allows users to always experience empathetic dialogue.

[0611] Example of a prompt:

[0612] This is an AI system that identifies user emotions and engages in conversation tailored to their feelings. Input: 'I've been feeling unwell and anxious lately.' Understand the emotion and generate a message to encourage the user.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The device receives voice or text input from the user. It recognizes this input and converts it into text data. In the case of voice input, this includes a process of converting it to text using speech recognition software. The recognized input is prepared as data to determine the user's emotional state.

[0616] Step 2:

[0617] The terminal sends the received text data to the server. This data is used as information to analyze the user's emotional state. The server passes the received text data to an emotion analysis tool. The emotion analysis tool (e.g., an emotion analysis API) uses natural language processing techniques to perform data calculations to estimate the user's current emotion (positive, negative, neutral, etc.).

[0618] Step 3:

[0619] The server utilizes a generative AI model to determine an appropriate response based on the analysis results. A process is initiated to generate a response that considers the user's emotional state while fitting the prompt. The generative AI model (e.g., OpenAI's generative model API) applies algorithms to optimize the tone and content of the conversation using the sentiment analysis results. The generated response is then refined based on a template and prepared in a format suitable for the user.

[0620] Step 4:

[0621] The server sends the generated response to the terminal. The terminal responds to this response as feedback to the user, either visually or audibly. The information the user obtains through interaction with the AI ​​serves as care support and emotional support. The user's feelings are cared for through the responses they receive. In this step, the system also prepares responses to await further input from the user, ensuring that the conversation continues smoothly.

[0622] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0623] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0624] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0625] [Fourth Embodiment]

[0626] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0627] As shown in Figure 7, the 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.

[0628] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0629] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0630] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0631] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0632] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0633] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0634] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0635] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0636] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0637] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0638] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0639] The system according to the present invention provides a platform for individuals with specialized knowledge to reflect their knowledge and speaking style in AI models. This platform enables experts and prominent figures to leverage their expertise to generate customizable AI agents and offer them to a wide range of consumers.

[0640] The system primarily operates in the following way: First, users (experts and prominent figures) register their profiles on the platform. Next, users input their expertise and speaking style as data into the platform. This data includes past dialogue examples, scripts, and Q&A format information. The server receives this input data and prepares it as training data for the AI ​​model. Once trained, the AI ​​model gains the ability to generate responses that reflect the user's unique characteristics.

[0641] This trained AI model will be made publicly available through the platform, accessible to the general public. Users can search for AI agents, and once they find one they are interested in, they can make a purchase or initiate a conversation. Purchases will utilize secure payment processing methods on the platform.

[0642] During the interaction, the terminal (the user's device) sends user input to the server. The server generates responses to the user's questions and requests based on a trained AI model and sends them back to the terminal. By experiencing these responses, the user can get a feel for the speaking styles of experts and prominent figures, and obtain diverse information.

[0643] Furthermore, the system is designed to dynamically change the AI ​​model's speaking style. This allows the AI's response style to be adjusted according to the user's preferences and circumstances, providing a more customized conversational experience. In this way, the present invention aims to realize seamless knowledge sharing between experts, prominent figures, and general users, and to create new business models.

[0644] The following describes the processing flow.

[0645] Step 1:

[0646] Users access the platform as experts or celebrities and register a new account. They enter the required personal information and authentication details to create the account.

[0647] Step 2:

[0648] The server receives registration information submitted by users and stores it in the database. This activates the accounts of authenticated professionals and prominent figures.

[0649] Step 3:

[0650] Users input content into the platform that reflects their expertise and unique speaking style. Specifically, they upload data such as text, audio files, and example conversations.

[0651] Step 4:

[0652] The server prepares an AI model based on the input data. In this process, natural language processing techniques are used to format the provided dataset as training data for the AI ​​model.

[0653] Step 5:

[0654] The server uses training data to train the AI ​​model. This allows the model to learn specific knowledge and speaking styles, and acquire the ability to generate responses.

[0655] Step 6:

[0656] The server stores the trained AI model on the platform and prepares it for publication. At this point, the user configures the deployment settings.

[0657] Step 7:

[0658] General users access the platform, search for AI agents that interest them, initiate the purchase process, and complete the transaction using secure payment methods.

[0659] Step 8:

[0660] A regular user enters a message to initiate a conversation with the AI ​​agent. The terminal then sends this input to the server.

[0661] Step 9:

[0662] The server passes the received message to a trained AI model, which then generates an appropriate response. This response is based on the user's input and the AI ​​model's learning.

[0663] Step 10:

[0664] The server sends the generated response to the terminal. The terminal displays this response to the user, and the interaction is established.

[0665] This series of processes allows users to experience personalized interactions with AI and enables the widespread sharing of knowledge from experts and prominent figures.

[0666] (Example 1)

[0667] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] The goal is to provide a means for individual users with specialized knowledge to easily translate their knowledge and conversational style into digital agents and widely share them with the general public. Furthermore, it aims to create an environment where general consumers can intuitively interact with these agents and easily access specialized information.

[0669] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0670] In this invention, the server includes means for users with specialized knowledge to input their knowledge and interaction methods as information, means for training an agent using language processing technology based on the input information, and means for maintaining and making available the trained agent on a shared platform. This enables the widespread sharing of specialized knowledge and allows individual consumers to use digital agents as a source of specialized information.

[0671] "Specialized information" refers to information possessed by users who have deep knowledge and experience in a particular field, and is used in dialogue and knowledge sharing.

[0672] A "user" is an individual or organization that possesses specialized information and seeks to translate that knowledge and interaction methods into digital agents.

[0673] "Dialogue method" refers to the specific way a user speaks or expresses themselves when providing information.

[0674] "Information" refers to data entered by users and used to train agents, and includes knowledge and conversational style.

[0675] An "agent" is a trained AI model that reflects the user's expertise and communication style, enabling it to interact with consumers.

[0676] A "shared infrastructure" is a platform where trained agents are stored and accessible to consumers.

[0677] A "consumer" is an ordinary user who interacts with agents using a shared platform.

[0678] "Payment processing" refers to the settlement process that takes place when a consumer acquires a trained agent.

[0679] "Dynamically adaptable" means that the way a trained agent interacts can be flexibly changed in response to the situation and user input.

[0680] This system provides a platform that easily converts specialized information into digital agents and makes it available to a wide range of consumers. The operation of the entire system is described below.

[0681] First, users access the platform and create their own profile. Here, they register their expertise and speaking style as data on the platform. This data includes past dialogue examples, scripts, and Q&A format information.

[0682] Next, the server receives data provided by the user and prepares it as training data to generate an AI agent. The techniques used here include natural language processing and machine learning algorithms. The server processes this data and trains the generative AI model. Through this training, the agent gains the ability to generate natural responses that reflect the user's expertise and conversational style.

[0683] Trained AI agents are made publicly available on the platform, and ordinary users can access them. Ordinary users can search for agents that interest them and initiate a conversation. During the conversation, the terminal sends prompt messages from the ordinary user to the server. The server uses these prompts to have the AI ​​agent generate a response and sends the result back to the terminal.

[0684] As a concrete example, in the case of an AI agent specializing in cooking, a regular user might input a prompt such as, "Please tell me an easy and delicious pasta recipe." In response to this prompt, the agent provides expert advice or a recipe, which the regular user then receives.

[0685] As described above, the system allows individual users with specialized knowledge to reflect their expertise in digital agents, providing a platform where many consumers can access and acquire specialized information. All of these processes are carried out through the coordinated efforts of the server, terminals, and users.

[0686] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0687] Step 1:

[0688] Users access the platform and create their own profile. Here, they provide basic information such as their name, area of ​​expertise, and contact details as input. As output, a user account is generated on the platform, ready for agent creation.

[0689] Step 2:

[0690] Users register their expertise and speaking style on the platform. At this stage, past dialogue data, scripts, and Q&A format information are input. The server receives this data and builds a training dataset as output. This dataset forms the basis for training the AI ​​model.

[0691] Step 3:

[0692] The server trains an AI model using data provided by the user. The training dataset prepared in step 2 is used as input here. The server applies natural language processing techniques and uses a generative AI model to train an agent capable of generating data-driven responses. The output is a trained AI agent that reflects the user's expertise.

[0693] Step 4:

[0694] Trained AI agents are made available on the platform by a server. General users access the platform and search for AI agents. Here, the input is a topic or keyword of interest to the user. The output is a list of relevant AI agents presented to the user.

[0695] Step 5:

[0696] A regular user initiates an interaction with a selected agent. The terminal receives prompts from the user as input and sends this information to the server. The server uses a trained AI agent to generate a response based on this input. The output, which includes the information the user requested and the results of the interaction, is sent back to the terminal.

[0697] Step 6:

[0698] The server dynamically adjusts the AI ​​agent's speaking style as needed. Input includes feedback from regular users and the results of conversations. Based on this, the server modifies the AI ​​agent's response style to provide a better conversational experience. The adjusted agent is provided as output, allowing the conversation with the user to continue.

[0699] (Application Example 1)

[0700] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0701] The challenge lies in providing a way for the general public to learn through interactive and immersive experiences with AI agents that reflect the knowledge and communication style of experts. Furthermore, there is a need for these AI agents to be customized for individual users, offering flexible dialogue models that can address diverse needs.

[0702] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0703] In this invention, the server includes means for a person with expertise to input their knowledge and speaking style as information, means for training an AI model using natural language processing technology based on that input information, and means for providing responses as an interactive learning experience and enhancing immersion through visual and auditory means. This enables users to enjoy a customized learning experience while effectively learning expert knowledge through interaction with an AI agent.

[0704] A "person with specialized knowledge" refers to an individual who possesses advanced information and skills in a specific field and has the ability to communicate that knowledge to others.

[0705] "Knowledge and speaking style" refers to a person's specialized information and views, as well as the linguistic methods they use to communicate that information.

[0706] "Means of inputting information" refers to methods and devices for registering specialized knowledge and speaking styles in a digital format within a system.

[0707] "Natural language processing technology" refers to all technologies that enable computers to understand and generate human language.

[0708] "Methods for training an AI model" refers to the process of training an AI based on the data necessary to generate appropriate responses.

[0709] A "platform" refers to the environment or interface provided by a system that enables the search, access, and interaction of AI agents.

[0710] An "interactive learning experience" refers to an educational process in which users actively participate and deepen their knowledge through interaction.

[0711] "Means of enhancing immersion through visuals and sound" refers to methods and technologies that use images and sounds to give users a sense of reality and connection.

[0712] A "customized learning experience" refers to an educational and learning process that is uniquely tailored to the individual needs and preferences of each user.

[0713] The system for realizing this invention involves individuals with specialized knowledge inputting their knowledge and speaking style as digital information, and using that information to build an AI model. A server uses specific natural language processing software, such as Transformers, to perform calculations to train the AI ​​model based on the input data. This training enables the AI ​​model to engage in conversations that reflect its specialized knowledge and unique speaking style.

[0714] The server stores this AI model on a cloud-based platform, making it accessible to users via the internet. Users connect to the platform through their device (smartphone or head-mounted display), search for a specific AI agent, and begin a conversation. At this time, input from the device is sent to the server, which generates a response based on the conversation and sends it back to the device.

[0715] This dialogue system utilizes a dialogue AI platform like Dialogflow, and further leverages real-time speech synthesis and video rendering technologies to provide an interactive learning experience through audio and video. For example, if a user types "Start Galileo's Astronomy Lecture" on their smartphone, the AI ​​agent will then teach the basics of astronomy from Galileo's perspective based on that command.

[0716] As a concrete example of a prompt in this system, input such as "Consult Shakespeare for ideas for a new play" allows the AI ​​agent to provide creative advice. This enables users to experience a rich learning environment through interaction with an AI agent possessing specialized knowledge.

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1: Entering Expertise Data

[0719] Users input their expertise and unique speaking style digitally into the server using a terminal. This input data includes text data, scripts, and past dialogue examples. This information is registered as the system's foundational data.

[0720] Step 2: Training the AI ​​model

[0721] The server processes the input expertise data and begins training an AI model using Transformers, a natural language processing technique. Here, the server analyzes the input data and optimizes the AI ​​model to respond in a way that reflects the speaker's style and expertise. The output is the trained AI model.

[0722] Step 3: Save and publish the AI ​​model

[0723] The trained AI model is stored on a server-based platform. The server then makes this model publicly accessible to the general public. The output is a list of available AI agents.

[0724] Step 4: Search for and select an AI agent

[0725] Users access the platform from their devices and search for AI agents of interest. The input is a search query, and the output is agent information as search results.

[0726] Step 5: Start the interaction and send the prompt.

[0727] The user initiates an interaction with the selected AI agent and sends prompt messages from the terminal to the server. The input is the user's prompt message.

[0728] Step 6: Response generation and return

[0729] The server generates a response using a trained AI model based on the received prompt. As part of the data processing, an appropriate response is generated from the prompt. The output is the generated response, which is sent back from the server to the terminal.

[0730] Step 7: Provide interactive learning

[0731] The device presents the received responses to the user visually and audibly. This provides an interactive learning experience, allowing the user to acquire specialized knowledge.

[0732] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0733] This invention is a system that combines an AI model incorporating the knowledge and speaking style of a person with expertise, with an emotion engine that recognizes user emotions and dynamically adjusts responses. The aim of this system is to provide a personalized conversational experience.

[0734] In this system embodiment, users (experts or prominent figures) first input their knowledge and speaking style as data into the platform. The server then trains an AI model, building a model capable of reproducing the expert's unique characteristics. This model is then made publicly available on the platform.

[0735] The system further incorporates an emotion engine to analyze the user's emotional state in real time and reflect the results in the AI ​​model's responses. Specifically, it can extract emotions from text and voice input by ordinary users during a conversation, and respond in a friendly style if the emotion is positive, or in an empathetic or encouraging style if it is negative.

[0736] The device sends user input data and the emotional information contained therein to the emotion engine, and then sends the analysis results to the server. The server generates a response from the AI ​​model based on the feedback from the emotion engine and adjusts the talk style. This function enables not only the provision of information, but also interaction that is sensitive to the user's emotions.

[0737] Furthermore, the system can learn the user's emotional patterns based on long-term conversation history, thereby improving the accuracy of response predictions in future conversations. This learning process takes place on the server, enabling continuous service improvement.

[0738] In this way, the present invention provides a system that takes user emotions into consideration, offers a more sophisticated dialogue experience, and enables the more effective and widespread dissemination of the knowledge of experts and prominent figures.

[0739] The following describes the processing flow.

[0740] Step 1:

[0741] Users access the platform and create an account as an expert or public figure. They enter the required profile information and verifications and register with the system.

[0742] Step 2:

[0743] Users input data into the platform to replicate their expertise and speaking style. This data includes information such as past conversation examples and specific speaking characteristics.

[0744] Step 3:

[0745] The server receives data provided by the user and formats it as training data for the AI ​​model. It uses natural language processing techniques to transform the data into a learnable format.

[0746] Step 4:

[0747] The server trains the AI ​​model using the prepared data. This allows the model to acquire the ability to replicate the user's knowledge and speaking style. The trained model is then stored on the platform.

[0748] Step 5:

[0749] General users search for AI agents on the platform and select an agent that interests them. If necessary, they proceed with the purchase process and begin interacting with the agent.

[0750] Step 6:

[0751] The user enters a message to interact with the AI ​​agent. During this process, the emotion engine analyzes the message and identifies the user's emotional state.

[0752] Step 7:

[0753] The terminal sends the entered message and sentiment analysis results to the server. Sentiment information includes emotions extracted from the text context and speech.

[0754] Step 8:

[0755] The server adjusts the response generated by the AI ​​model based on the received emotion data. If the emotion is positive, it selects a friendly response; if it is negative, it selects an empathetic response.

[0756] Step 9:

[0757] The server sends the generated response back to the terminal and presents it to the user in an appropriate conversational style. This allows the user to experience a personalized interaction.

[0758] Step 10:

[0759] The server records the dialogue history and emotion patterns, and uses this to improve the accuracy of responses in future dialogues. The learned data is continuously used to improve the AI ​​model.

[0760] (Example 2)

[0761] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] In modern society, it is crucial to effectively convey the unique knowledge and conversational styles of experts to a wide audience. However, existing artificial intelligence response systems have struggled to achieve emotionally resonant interactions, resulting in an inability to optimize the user experience. Furthermore, they lack the functionality to leverage a user's past conversation history to improve response accuracy in subsequent interactions. These challenges need to be addressed.

[0763] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0764] In this invention, the server includes means for a person with expertise to input their knowledge and conversational style as information, means for training an artificial intelligence model using language processing technology based on the input information, and means for analyzing the user's emotional state and reflecting the analysis results in the response of the artificial intelligence model. This makes it possible to provide interaction that takes the user's emotions into consideration and to effectively convey expertise.

[0765] A "person with specialized knowledge" is an individual who possesses specialized knowledge and skills in a particular field and has the ability to communicate that knowledge to others.

[0766] "Conversation style" refers to a distinctive way of speaking or communication style possessed by a particular person, and includes their unique methods of expression and language choices.

[0767] An "information sharing platform" is a system or platform for storing and managing digital information and making it accessible to users.

[0768] "Language processing technology" refers to technical methods used to process, understand, and generate natural language, primarily performed by computers.

[0769] An "artificial intelligence model" is a computer program that has the ability to learn from data and perform specific tasks.

[0770] "Users" refers to end users who operate a system or service and utilize its functions.

[0771] "Emotional state analysis" is the process of extracting emotional nuances from user input data and identifying those emotions.

[0772] "Improved response accuracy" means that the system's responses to the user become more accurate and appropriate, based on past interactions and new information.

[0773] The system implementing this invention utilizes data from individuals with specialized knowledge and unique conversational styles to train and operate artificial intelligence models.

[0774] Users first input their expertise and conversational style as data into the platform. This data includes input in text and audio formats and represents the user's knowledge and characteristics. The data is collected in a secure and reliable digital environment.

[0775] The server uses data provided by users to train a generative AI model. In this process, natural language processing techniques are utilized to learn the user's unique style. Specifically, the server uses natural language processing libraries and frameworks (e.g., TensorFlow and PyTorch) to learn the expert's knowledge and style. The trained model is stored on an information sharing platform and made accessible to other users.

[0776] Furthermore, the terminal is responsible for receiving text and voice data entered by the user and sending it to the server. The terminal operates in real time and is equipped with software for rapid emotion analysis, utilizing a specific emotion analysis engine (e.g., voice analysis software).

[0777] In this system, the server analyzes the user's emotional state using an emotion engine, and an artificial intelligence model generates an appropriate response based on that analysis. For example, if a user prompts, "Tell me more about dog behavior psychology," the server generates a detailed explanation based on its expertise and responds to the user. This allows the user to have a higher quality, more personalized conversational experience.

[0778] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0779] Step 1:

[0780] Users input their expertise and conversational style as data. This input can be in text or audio format. For example, users generate text data by writing sentences and record audio data using a voice recorder. This data is then uploaded to the platform and sent to the server.

[0781] Step 2:

[0782] The server trains an artificial intelligence model based on input data received from the user. In this process, the server uses a natural language processing framework (e.g., TensorFlow or PyTorch) to perform calculations that learn the user's expertise and conversational style. It analyzes the data and generates a model that includes the content of the knowledge and characteristic speech patterns. The trained model is stored on an information sharing platform.

[0783] Step 3:

[0784] The terminal acquires input data (text or voice) from regular users in real time. This input data is formatted for analysis and sent to the emotion engine. The terminal uses speech recognition software or a text interface to convert speech to text and prepares the data to be sent to the server in the appropriate format.

[0785] Step 4:

[0786] The server receives data from a regular user sent from the terminal and analyzes their emotional state using an emotion engine. During the analysis, the server recognizes the nuances of the emotion and classifies it as positive, negative, or neutral. Based on the analysis results, the server begins generating a response using an artificial intelligence model.

[0787] Step 5:

[0788] The server generates a response using an artificial intelligence model, taking into account the sentiment analysis results. During generation, it incorporates information from a knowledge base and adjusts the response's tone and content to match the user's emotions. The generated response is then sent to the terminal.

[0789] Step 6:

[0790] The terminal receives responses sent from the server and presents them to the user. The terminal uses a display screen and audio output device to provide the responses to the user in an appropriate format. Through this process, the user can experience a personalized interaction based on expert knowledge.

[0791] (Application Example 2)

[0792] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0793] In modern society, there is a growing need to alleviate the loneliness and anxiety that elderly people, in particular, face in care settings, and to provide appropriate dialogue and support that takes their emotions into consideration. However, due to limited human resources and time constraints, they may not always receive sufficient support. To improve this situation, effective means are needed to consistently provide appropriate emotional support to those receiving care.

[0794] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0795] In this invention, the server includes means for an individual with specialized knowledge to input their knowledge and conversational style as information; means for sentiment analysis to analyze the emotional state of general users and adjust the AI ​​model's response based on the results; and means for analyzing everyday conversations in a care support environment and generating appropriate support messages. This makes it possible for people receiving care to receive conversations and support tailored to their individual circumstances and emotions.

[0796] A "specialized individual" is someone who possesses deep knowledge and experience in a specific field and is capable of providing meaningful information based on that knowledge.

[0797] "Conversation style" is a general term for the way a particular speaker speaks, the characteristics of their communication, and their tone of voice, which they use on a daily basis.

[0798] "Information" refers to data and materials such as specialized knowledge and conversational style, which form the basis for training AI models.

[0799] "Natural language processing technology" refers to the technology used to enable computers to understand and generate human language.

[0800] An "AI model" is a model obtained through learning natural language processing technology, capable of reproducing specific knowledge and conversational styles.

[0801] A "digital platform" refers to an online system where AI models are stored and accessible to the general public.

[0802] "General users" are people who can interact with AI models through a digital platform, even without possessing specific expertise.

[0803] "Exploration" refers to the act of general users finding and selecting AI models on a digital platform.

[0804] "Dialogue" refers to the process of information exchange and communication that takes place between an AI model and a general user.

[0805] "Emotional state" refers to the user's psychological mood and emotional state, and is identified through emotion analysis.

[0806] "Emotional analysis means" refers to a technology or system that identifies a user's emotional state and uses that information to adjust their response.

[0807] "Care support environment" refers to the setting where care services are provided, as well as the living and support spaces for people receiving care.

[0808] A "support message" is a message of encouragement, advice, or other similar messages provided to people receiving care.

[0809] One embodiment of this invention is to provide an emotionally sensitive dialogue system in a care support environment by utilizing a generative AI model that reflects the knowledge and conversational style of experts.

[0810] First, the server provides a way for individuals with specialized knowledge to input their knowledge and conversational style as information. Based on the input information, an AI model is trained using natural language processing technology, and this trained AI model is stored on a digital platform. This allows general users to access this platform, explore the AI ​​model, and initiate conversations.

[0811] When a user interacts with a generative AI model, the terminal receives voice or text input and sends it to the server. The server uses sentiment analysis tools (e.g., sentiment analysis APIs) to analyze the user's emotional state in real time. Based on this analysis, the generative AI model determines the appropriate response and provides a appropriately adjusted conversation. For the AI ​​model adjustment process, for example, the OpenAI generative model API can be used.

[0812] For example, if an elderly person receiving care says, "I feel a bit down today," the server might respond with kind words like, "Why don't you reminisce about some wonderful memories? I might be able to help you with that." This kind of virtual support system allows users to always experience empathetic dialogue.

[0813] Example of a prompt:

[0814] This is an AI system that identifies user emotions and engages in conversation tailored to their feelings. Input: 'I've been feeling unwell and anxious lately.' Understand the emotion and generate a message to encourage the user.

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The device receives voice or text input from the user. It recognizes this input and converts it into text data. In the case of voice input, this includes a process of converting it to text using speech recognition software. The recognized input is prepared as data to determine the user's emotional state.

[0818] Step 2:

[0819] The terminal sends the received text data to the server. This data is used as information to analyze the user's emotional state. The server passes the received text data to an emotion analysis tool. The emotion analysis tool (e.g., an emotion analysis API) uses natural language processing techniques to perform data calculations to estimate the user's current emotion (positive, negative, neutral, etc.).

[0820] Step 3:

[0821] The server utilizes a generative AI model to determine an appropriate response based on the analysis results. A process is initiated to generate a response that considers the user's emotional state while fitting the prompt. The generative AI model (e.g., OpenAI's generative model API) applies algorithms to optimize the tone and content of the conversation using the sentiment analysis results. The generated response is then refined based on a template and prepared in a format suitable for the user.

[0822] Step 4:

[0823] The server sends the generated response to the terminal. The terminal responds to this response as feedback to the user, either visually or audibly. The information the user obtains through interaction with the AI ​​serves as care support and emotional support. The user's feelings are cared for through the responses they receive. In this step, the system also prepares responses to await further input from the user, ensuring that the conversation continues smoothly.

[0824] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0825] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0826] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0827] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0828] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0829] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0830] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0831] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0832] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0833] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0834] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0835] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0836] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0837] 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.

[0838] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0839] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0840] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0841] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0842] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0843] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0844] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0845] The following is further disclosed regarding the embodiments described above.

[0846] (Claim 1)

[0847] A means for individuals with specialized knowledge to input that knowledge and their speaking style as data,

[0848] A method for training an AI model using natural language processing technology based on that input data,

[0849] A means of storing and making accessible trained AI models on the platform,

[0850] A means for general users to search for AI models through the platform and initiate conversations,

[0851] A means by which the AI ​​model generates a response to that dialogue input and sends it back to the user,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, further comprising a payment processing means for general users to purchase a trained AI model.

[0855] (Claim 3)

[0856] The system according to claim 1, further comprising means for dynamically changing the talk style of a trained AI model in accordance with the customization of the model.

[0857] "Example 1"

[0858] (Claim 1)

[0859] A means for users with specialized knowledge to input that knowledge and methods of interaction as information,

[0860] A means of training an agent using language processing technology based on the input information,

[0861] A means of maintaining and making available trained agents on a shared platform,

[0862] A means for consumers to find agents and initiate interaction through a shared platform,

[0863] The agent prepares a response based on the information gathered from that interaction and sends it back to the consumer.

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising a payment processing means for a consumer to acquire a trained agent.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for dynamically changing the way a trained agent interacts in accordance with agent adjustments.

[0869] "Application Example 1"

[0870] (Claim 1)

[0871] A means for a person with specialized knowledge to input that knowledge and speaking style as information,

[0872] A method for training an AI model using natural language processing technology based on that input information,

[0873] A means of storing and making available trained AI models on the platform,

[0874] A means for users to search for AI models through the platform and begin interacting with them,

[0875] A means by which an AI model generates a response to that AC input and sends it back to the user,

[0876] A means of providing responses as an interactive learning experience and enhancing immersion through visual and auditory means,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising a payment processing means for general users to purchase a trained AI model.

[0880] (Claim 3)

[0881] The system according to claim 1, further comprising means for dynamically changing the speaking style of a trained AI model in accordance with the customization of the model.

[0882] "Example 2 of combining an emotion engine"

[0883] (Claim 1)

[0884] A means for a person with specialized knowledge to input that knowledge and conversational style as information,

[0885] A means of training an artificial intelligence model using language processing technology based on that input information,

[0886] A means of storing and making accessible trained artificial intelligence models on an information sharing platform,

[0887] A means for users to search for artificial intelligence models through an information sharing platform and initiate dialogue,

[0888] A means by which an artificial intelligence model generates a response to that dialogue input and sends it back to the user,

[0889] A means of analyzing the emotional state of a user and reflecting the results of that analysis in the response of an artificial intelligence model,

[0890] A means to learn from the dialogue history and improve the accuracy of response prediction in the next dialogue,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, further comprising a payment processing means for a user to acquire a trained artificial intelligence model.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for dynamically changing the conversational style of a trained artificial intelligence model in accordance with the customization of the model.

[0896] "Application example 2 when combining with an emotional engine"

[0897] (Claim 1)

[0898] A means for individuals with specialized knowledge to input that knowledge and conversational style as information,

[0899] A method for training an AI model using natural language processing technology based on that input information,

[0900] A means of storing and making available trained AI models on a digital platform,

[0901] A means for general users to explore and initiate conversations with AI models through a digital platform,

[0902] A means by which an AI model creates a response to that dialogue input and sends it to the user,

[0903] An emotion analysis method that analyzes the user's emotional state and adjusts the AI ​​model's response based on the results,

[0904] A means of analyzing everyday conversations in a care support environment and generating appropriate support messages,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, further comprising a payment processing means for general users to acquire a trained AI model.

[0908] (Claim 3)

[0909] The system according to claim 1, further comprising means for dynamically modifying the conversational style of a trained AI model in response to changes in the model's settings. [Explanation of Symbols]

[0910] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a person with specialized knowledge to input that knowledge and speaking style as information, A method for training an AI model using natural language processing technology based on that input information, A means of storing and making available trained AI models on the platform, A means for users to search for AI models through the platform and begin interacting with them, A means by which an AI model generates a response to that AC input and sends it back to the user, A means of providing responses as an interactive learning experience and enhancing immersion through visual and auditory means, A system that includes this.

2. The system according to claim 1, further comprising a payment processing means for general users to purchase a trained AI model.

3. The system according to claim 1, further comprising means for dynamically changing the speaking style of a trained AI model in accordance with the customization of the model.

Images