System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing author authoring data and analyzing the document using natural language processing techniques to extract features; means for accepting user input and invoking a particular author model based on the input to generate a response; means for displaying the generated response to the user; and means for accepting user reactions and continuing to generate new responses based on the reactions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional methods of learning from books and documents are inefficient because they require a great deal of time and effort to gain a deep understanding of a particular author's thought patterns and knowledge. Furthermore, simply reading a book has limited effect on changing a user's own behavior and thinking. Therefore, there is a need for a method to efficiently learn the thoughts of specific best-selling authors and, through this, transform the user's own thinking, behavior, and decision-making. [Means for solving the problem]

[0005] This invention provides a means for importing author work data, analyzing the document using natural language processing technology, and extracting features. It also includes a means for accepting user input, invoking a specific author model based on that input, and generating a response. It also includes a means for displaying the generated response to the user, accepting the user's reaction, and continually generating new responses based on that reaction. By analyzing the user's reaction and reflecting the analysis results in the generation of the next response, more appropriate dialogue can be achieved. This allows users to efficiently learn the thought patterns of specific authors and bring about changes in their own thinking and behavior.

[0006] "Copyright data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0007] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze natural language.

[0008] "Feature extraction" refers to identifying and extracting themes, writing style, frequently used expressions, logical development patterns, etc. from a document.

[0009] "User input" refers to instructions such as questions or topics from the user that are accepted by the system.

[0010] An "author model" is a generative AI model that is trained based on the writing data of a specific author and imitates the author's thought patterns and writing style.

[0011] "Response generation" refers to creating an appropriate answer from the author model based on the user's input.

[0012] "Displaying the response" means displaying the generated response in a user interface for the user.

[0013] "User responses" are any additional questions or comments from the user in response to the displayed response.

[0014] "Generating a new response" means creating an appropriate answer again based on the user's response.

[0015] "Continuous dialogue" refers to the process in which the user and the system engage in repeated dialogue and continue to interact.

[0016] "Feedback" means analyzing the user's reaction and reflecting that information in generating the next response.

[0017] A "thought pattern" is a particular writer's unique logic or method for thinking about and solving problems.

[0018] Decision-making is the process of choosing the best course of action or judgment from a range of options. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that incorporates the writing data of a specific best-selling author, and through dialogue with the user, provides the author's thought patterns and knowledge, ultimately aiming to change the user's behavior and decision-making. This system is implemented through processing between a server, a terminal, and the user.

[0041] Importing and analyzing copyright data

[0042] The server imports the author's work data into a database. Specifically, it collects text data such as books, papers, and essays, and analyzes the documents using natural language processing (NLP) technology. From the analyzed data, themes, writing style, frequently used expressions, and logical development patterns are extracted. This provides the basic data for training a specific author model.

[0043] Accepting and parsing user input

[0044] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." This input data is sent from the terminal to the server.

[0045] Call and response generation for writer models

[0046] The server analyzes the user's input and calls the corresponding author model. Based on the user's question and topic, the author model generates an appropriate response. The generated response reflects the author's thought patterns and writing style, making the user feel as if they are interacting with a specific author.

[0047] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[0048] Response display and feedback

[0049] The generated response is displayed to the user via the terminal, and the user can then input a new question or reaction based on the displayed response, such as "Do you have a more specific example?"

[0050] The server again analyzes the user's input and generates appropriate responses from the author model. This process repeats, allowing the user to continually gain a deeper understanding of a particular author's thought patterns and knowledge.

[0051] Continuous dialogue and learning outcomes

[0052] By continually using this system, users can acquire the thought patterns and knowledge of specific authors, which can bring about changes in their own behavior and decision-making. For example, they will naturally improve their news filtering ability and develop the habit of selecting only important information.

[0053] In this way, the present invention aims to efficiently provide author knowledge through dialogue with users, ultimately transforming their behavior and decision-making.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[0057] Step 2:

[0058] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[0059] Step 3:

[0060] The server uses the extracted features to train a writer model, which is a generative AI model that mimics the thought patterns and writing style of a particular author.

[0061] Step 4:

[0062] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[0063] Step 5:

[0064] The terminal transmits the user's input data to the server.

[0065] Step 6:

[0066] The server analyzes the user's input, calls the corresponding author model, and generates an appropriate response based on the user's question and topic.

[0067] Step 7:

[0068] The server sends the generated response to the terminal.

[0069] Step 8:

[0070] The terminal displays the received response on the user interface and provides it to the user.

[0071] Step 9:

[0072] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[0073] Step 10:

[0074] The terminal sends the user's new input to the server.

[0075] Step 11:

[0076] The server again parses the user's input and uses the author model to generate an appropriate response.

[0077] Step 12:

[0078] The server generates a new response and sends it to the terminal.

[0079] Step 13:

[0080] The terminal again displays the response in the user interface, providing information for the user to guide the next interaction.

[0081] Step 14:

[0082] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, which can bring about changes in their behavior and decision-making.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] With conventional systems, it was difficult for users to learn the thought patterns and knowledge of a specific author through dialogue and then reflect that author's actions and decision-making. Furthermore, conventional systems lacked the ability to generate new responses for each user input, making it impossible to enhance learning through continuous dialogue.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features, means for accepting user input, invoking a specific author model based on the input, and generating a response, means for displaying the generated response to the user, means for accepting user responses and continuously generating new responses based on the responses, means for preparing basic data for training different author models, and means for analyzing user input and generating appropriate responses based on different author models. This allows users to efficiently learn the thought patterns and knowledge of specific authors and realize continuous dialogue that reflects their own actions and decision-making.

[0088] The following are definitions of important terms contained in the claims.

[0089] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0090] "Natural language processing technology" is a general term for technologies that enable computers to understand, process, and generate human language.

[0091] "Means for analyzing documents and extracting features" refers to methods and technologies for analyzing text data and extracting features such as themes, writing style, frequently occurring expressions, and logical development patterns.

[0092] "Means for accepting user input" refers to the interface that allows users to input the name of the author or topic they wish to discuss, and the method or technology for transmitting the input to the server.

[0093] "Means for invoking a specific writer model and generating a response" refers to a method or technology that uses a model that mimics the thought patterns and writing style of a pre-trained writer to generate an appropriate response to a user's input.

[0094] "Means for displaying the generated response to the user" refers to an interface or method for receiving the generated response from the server and visually presenting it to the user.

[0095] "Means for accepting user responses and continually generating new responses based on those responses" refers to methods and technologies for analyzing questions and responses re-entered by the user and generating appropriate responses again.

[0096] "Means for preparing basic data for training models of different authors" refers to methods and techniques for preparing data for training models that reflect the thought patterns and writing styles of different authors based on collected writing data.

[0097] "Means for analyzing user input and generating appropriate responses based on different writer models" refers to methods or techniques for analyzing the content of a user input, selecting the most appropriate writer model for it, and generating a response.

[0098] In this invention, the system is implemented using the following methods and techniques: The main components are a server, a terminal, and a user.

[0099] The server first collects the author's work data, which is retrieved using Python's "requests" library or an e-book API, and then stores the collected data in a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0100] The server then analyzes the stored author data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as spaCy and the Natural Language Toolkit (NLTK). During this analysis, the data is tokenized, tagged with parts of speech, and analyzed for grammar. This allows for the extraction of themes, writing style, frequent phrases, and logical development patterns. The results of this analysis are used as the basis for training different author models.

[0101] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might say, "I want to talk about the news with a specific author." The device converts the input data into JSON format and sends it to the server via an HTTP POST request. HTTP is used as the communication protocol.

[0102] The server analyzes the received user input and selects a specific author model, which is pre-trained to mimic the author's unique thought patterns and writing style, and then uses a generative AI model (e.g., GPT-3) to generate the best response to the user-entered prompt.

[0103] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[0104] This generated response is sent from the server to the terminal and displayed to the user. The user can then look at the displayed response and input a new question or response. For example, they can re-input "Do you have a more specific example?" This new input data is again sent to the server, which generates a new response.

[0105] By repeating this process, users can efficiently learn the thought patterns and knowledge of a particular author and ultimately reflect this in their own actions and decision-making. In this way, this invention aims to provide authors' knowledge through continuous dialogue with users and to change their decisions and behaviors.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1:

[0108] Data collection

[0109] The server collects the author's work data from the internet or e-book stores using APIs. The input here is the author's name and a request to obtain data such as books and papers. The server collects this using the "requests" library and obtains the work data in text format as output. Specifically, it sends an API request and saves the text data obtained as a response.

[0110] Step 2:

[0111] Saving to a database

[0112] The server stores the collected copyright data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. The input is the text data collected in step 1, and the output is the data correctly stored in the database. Specific operations include connecting to the database, creating a table, and inserting data.

[0113] Step 3:

[0114] Natural Language Processing (NLP) Analysis

[0115] The server analyzes the stored data using NLP libraries such as "spaCy" and "Natural Language Toolkit (NLTK)." The input is text data retrieved from the database, and the output is feature extraction data as the analysis result. Specific operations include tokenization, morphological analysis, and grammatical analysis to extract themes, writing style, frequently occurring vocabulary, and logical development patterns.

[0116] Step 4:

[0117] Accepting user input

[0118] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might input something like "I want to talk about the news with a specific author." The input is the data entered by the user, and the output is data converted into JSON format. Specific operations involve entering data into the input form and clicking the submit button.

[0119] Step 5:

[0120] Sending data

[0121] The terminal converts the user's input data into JSON format and sends it to the server via an HTTP POST request. The input is the user input data from step 4, and the output is the request to be sent to the server. Specific operations include converting the input data into JSON, and creating and sending an HTTP request.

[0122] Step 6:

[0123] Parsing user input

[0124] The server analyzes the received user input. The input is JSON format data sent from the terminal, and the output is the analyzed author name and topic. Specifically, it parses the JSON data and extracts the author name and topic.

[0125] Step 7:

[0126] Artist model selection

[0127] The server selects the corresponding author model based on the analysis results. The input is the author name and topic analyzed in step 6, and the output is the specified author model. Specifically, the server selects an appropriate model from multiple pre-trained author models.

[0128] Step 8:

[0129] Generating a response

[0130] The server uses a generative AI model to generate a response to the user's question. The input is the selected author model and the user's input prompt, and the output is the generated response. Specifically, the server invokes a generative AI model (e.g., GPT-3) to generate the optimal response to the prompt.

[0131] Step 9:

[0132] Viewing the response

[0133] The terminal displays the response sent by the server to the user. The input is the response generated by the server, and the output is the response visually presented to the user. Specific operations include receiving the response data and displaying it in a text view.

[0134] Step 10:

[0135] Accepting user responses and continuing dialogue

[0136] The user then enters a new question or response based on the displayed response. The input is the user's new input data, and the output is the data that is sent back to the server. Specific actions include re-entering data into the input form and clicking the submit button. By repeating this process, a continuous dialogue is achieved.

[0137] These specific processing steps allow users to efficiently learn the thought patterns and knowledge of specific authors through dialogue with them, which can positively influence their behavior and decision-making.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] Conventional interactive systems have had difficulty providing users with a realistic experience, as if they were conversing with a specific author. Furthermore, they have limitations in providing information that influences users' behavior and decisions, making it impossible to provide highly satisfying interactive content. There is a need to solve this problem and realize more advanced and interactive content delivery.

[0141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0142] In this invention, the server includes means for importing author work data, analyzing documents using natural language processing technology, and extracting features, means for accepting user input, calling a specific author model based on the input, and generating a response using a generative AI model, and means for displaying the generated response to the user. This provides a realistic experience as if the user were interacting with a specific author, making it possible to influence the user's behavior and decision-making.

[0143] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0144] "Natural language processing technology" refers to all technologies that enable computers to understand, analyze, and generate natural language.

[0145] "Specific author model" refers to a generative AI model trained based on collected and analyzed author data.

[0146] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate appropriate responses from input data.

[0147] "Means for generating a response" refers to methods and devices for using a generative AI model to create an appropriate response based on user input.

[0148] "User input" refers to text or voice input information entered by a user through a content distribution service terminal.

[0149] "User response" refers to new input or action by the user after receiving the generated response.

[0150] "Operation device" refers to a device that allows users to input or interact, such as a smartphone, smart glasses, or head-mounted display.

[0151] This invention is a system that incorporates the writing data of a specific author, provides the author's thought patterns and knowledge through dialogue with the user, and ultimately aims to change the user's behavior and decision-making. This system is realized mainly through processing between a server, a terminal, and the user.

[0152] Server Roles

[0153] The server collects the author's writing data and analyzes it using natural language processing technology. From the analyzed data, characteristics such as themes, writing style, frequently used expressions, and logical development patterns are extracted. Specifically, APIs and crawlers are used to collect the writing data and store it in a database. Natural language processing libraries such as spaCy are used for analysis. Furthermore, OpenAI's GPT-3 and other technologies are used to train author models based on the collected and analyzed data.

[0154] Device Role

[0155] The device is responsible for accepting input from the user and sending it to the server. The user enters the name of the author they want to talk to and the topic in text format. For example, they might say, "I want to talk about the news with a specific author." The device can be a smartphone, smart glasses, or a head-mounted display.

[0156] User Roles

[0157] The user is the subject of interactive content consumption, and engages in a dialogue with the artist through their device. The user receives responses generated by the server based on their input, and continues the dialogue by entering new questions and reactions.

[0158] Specific examples of processing

[0159] When a user types, "I'd like a specific author to give me advice on how to filter information," the server invokes the corresponding author model and generates a response such as, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, for example, "Do you have any more specific examples?", the server again uses the author model to generate a response such as, "For example, you might want to refer to reliable news sites or academic papers."

[0160] Prompt Sentence Examples

[0161] Below are some example prompts to input to the generative AI model:

[0162] Author Model: A specific author

[0163] User Input: Do you have any specific examples of writers?

[0164] Response:

[0165] Hardware and Software

[0166] Server: High-performance database and calculation servers are used to collect, store, and analyze data.

[0167] Natural language processing libraries: use spaCy and NLTK to parse documents.

[0168] Generative AI model: Leveraging OpenAI's GPT-3 to generate writer responses.

[0169] Device: A device that accepts user input and displays responses, such as a smartphone, smart glasses, or head-mounted display.

[0170] This makes it possible to virtually recreate the thought patterns and knowledge of an author and provide them to users through dialogue. Through an experience that makes users feel as if they are conversing with a specific author, users can acquire the thought patterns and knowledge and bring about changes in their behavior and decision-making.

[0171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0172] Step 1: The server collects the author's work data and stores it in a database

[0173] The server collects the work data (books, papers, essays, etc.) of a particular author using APIs, crawlers, etc. This data is stored in a database. The input is the author's work data, and the output is the raw work data stored in the database.

[0174] Step 2: The server analyzes the copyright data using natural language processing technology

[0175] The server analyzes the collected author data using natural language processing libraries such as spaCy and NLTK, extracting features such as document themes, writing style, frequently used expressions, and logical development patterns. The input is the raw author data in the database, and the output is feature information of the analyzed author data.

[0176] Step 3: The server trains the generative AI model

[0177] The server trains a generative AI model, such as OpenAI's GPT-3, based on the analyzed author data's feature information. The input is the feature information, and the output is a specific author model.

[0178] Step 4: The user inputs the author name and topic they want to discuss into the terminal.

[0179] The user uses a device such as a smartphone or a head-mounted display to input the name of the author they want to interact with and the topic in text format. The input is the user's input data, and the output is request data sent to the server.

[0180] Step 5: The server invokes the author model based on the user's input and generates a response using the generative AI model.

[0181] The server analyzes the user's input, calls the corresponding specific author model, and then generates an appropriate response using a generative AI model. The input is the user's request data, and the output is the generated response data.

[0182] Step 6: The terminal displays the generated response to the user

[0183] The terminal displays the response data sent from the server to the user. The input is the response data sent from the server, and the output is text or audio displayed to the user.

[0184] Step 7: The user enters a new question or response, and the server generates a new response.

[0185] The user inputs a new question or reaction based on the displayed response. This input is sent back to the server, which then uses the generative AI model to generate a new response. The input is the user's new input data, and the output is the newly generated response data.

[0186] Step 8: This process repeats as the user continues to interact

[0187] The server and the terminal continuously execute a dialogue with the user, allowing the user to gain a deeper understanding of the thought patterns and knowledge of a particular author. The input is continuous user input data, and the output is continuously generated response data.

[0188] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0189] This system incorporates data on the works of specific best-selling authors and provides users with the author's thought patterns and knowledge through dialogue with them, combined with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[0190] Importing and analyzing copyright data

[0191] The server imports the author's work data and stores it in a database. This data includes books, papers, essays, etc. The imported data is analyzed using natural language processing (NLP) technology to extract themes, writing style, frequently used expressions, logical development patterns, etc. This provides the basic data for training the author model.

[0192] Accepting and parsing user input

[0193] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." The input data is sent from the terminal to the server.

[0194] Invoking the author model and emotion recognition

[0195] The server analyzes the user's input, calls the corresponding author model, and uses an emotion engine to recognize emotions from the user's input. It then generates an appropriate response based on the user's question, theme, and emotional state.

[0196] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call the corresponding author model, analyze the tone of the input, and respond with, "It's important to focus on the quality of the information and choose reliable sources."

[0197] Displaying responses and adjusting based on emotions

[0198] The generated response is displayed to the user via the device. The user's reaction is also analyzed by the emotion engine and reflected in the next response generation. For example, if the user further inputs, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, we recommend that you make it a habit to check a reliable news site only once a week."

[0199] Continuous dialogue and learning outcomes

[0200] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, enabling more natural interactions through emotional responses. Continuing to respond to the user's emotional state can more easily bring about changes in the user's behavior and decision-making.

[0201] In this way, the present invention aims to efficiently provide authors' knowledge through dialogue that takes into account the user's emotions, and further to change the user's behavior and decision-making.

[0202] The processing flow will be explained below.

[0203] Step 1:

[0204] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[0205] Step 2:

[0206] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[0207] Step 3:

[0208] The server uses the extracted features to train a writer model, a generative AI model that mimics the thought patterns and writing style of a specific author.

[0209] Step 4:

[0210] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[0211] Step 5:

[0212] The terminal transmits the user's input data to the server.

[0213] Step 6:

[0214] The server analyzes the user's input and uses an emotion engine to recognize emotions from the input. At the same time, it invokes the corresponding author model to generate an appropriate response based on the user's question, topic, and emotional state.

[0215] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server analyzes the tone of the input and generates an appropriate response: "It's important to prioritize the quality of information and choose reliable sources."

[0216] Step 7:

[0217] The server sends the generated response to the terminal.

[0218] Step 8:

[0219] The terminal displays the received response on the user interface and provides it to the user.

[0220] Step 9:

[0221] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[0222] Step 10:

[0223] The terminal sends the user's new input to the server.

[0224] Step 11:

[0225] The server again analyzes the user's input and sentiment, and uses the writer model and emotion engine to generate an appropriate response, such as "We recommend that you make it a habit to check a trusted news site only once a week."

[0226] Step 12:

[0227] The server generates a new response and sends it to the terminal.

[0228] Step 13:

[0229] The terminal again displays the response in its user interface, providing information for the user to guide their next interaction.

[0230] Step 14:

[0231] By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and emotional responses enable a more natural dialogue. Continuing to respond to the user's emotional state can bring about changes in the user's behavior and decision-making.

[0232] Example 2

[0233] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0234] Conventional dialogue systems have the problem that it is difficult to model the thought patterns and knowledge of a specific author, and it is also difficult to generate flexible responses that correspond to the user's emotions. Furthermore, it is not possible to analyze the user's reactions and reflect them in the next response, making it difficult to achieve natural and sustainable dialogue.

[0235] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0236] In this invention, the server includes means for collecting authorship data of specific authors, analyzing documents using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; and means for recognizing emotions from the user input using an emotion engine. This enables natural and friendly dialogue that responds to the user's emotions by utilizing the thought patterns and knowledge of specific authors. Furthermore, by analyzing the user's reactions and reflecting them in the generation of the next response, it is possible to provide a sustainable and effective dialogue.

[0237] "Specified Author" refers to the author of the specified work with whom the user wishes to interact.

[0238] "Copyrighted data" refers to documents and text data created by a specific author, such as books, papers, and essays.

[0239] "Natural language processing technology" refers to technology that uses computers to understand, analyze, and generate natural human language.

[0240] "Document analysis" refers to the process of using natural language processing technology to analyze the content of a specific author's written data and extract features such as themes, writing style, frequently used expressions, and logical development patterns.

[0241] "Characteristics" refers to the author's unique document structure and style, such as themes, writing style, frequent expressions, and logical development patterns that appear in the work data of a particular author.

[0242] "User" refers to a person who interacts with the system.

[0243] "Author model" refers to a generative AI model that is trained to mimic the thought patterns and knowledge of a specific author based on their work data.

[0244] "Means for generating a response" refers to a process that generates an appropriate response using a particular authorship model based on user input.

[0245] An "emotion engine" is a technology that recognizes emotions from user input and adjusts the content and tone of responses accordingly.

[0246] "User response" refers to the user's feedback or re-input to the generated response.

[0247] "Means for recognizing emotions" refers to the process of extracting an emotional state from a user's input text using an emotion engine.

[0248] "Sustained interaction" refers to multiple consecutive interaction sessions with a user, where each interaction is appropriately adjusted based on previous responses and user reactions.

[0249] "Natural and friendly dialogue" refers to dialogue that provides appropriate responses according to the user's emotions and proceeds smoothly without any sense of discomfort to the user.

[0250] This system incorporates the copyright data of a specific author and provides the user with the author's thought patterns and knowledge through dialogue with the user, and combines it with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[0251] Specifically, the server collects the writing data of a specific author and analyzes the document using natural language processing techniques (e.g., Python's NLTK or Spacy) to extract features such as themes, writing style, frequently used expressions, and logical development patterns. This information is then used to train a generative AI model (e.g., Hugging Face's Transformer model) to build a model that mimics the thinking and knowledge of the specific author.

[0252] The user inputs the name of the author they want to talk to and the topic they want to talk about (for example, a prompt such as "I want to talk to a specific author about the news" or "I want a specific author to give me advice on how to filter information.") The device sends this input data to the server, which analyzes it and calls the corresponding author model. Furthermore, it uses an emotion engine (for example, Google Cloud Natural Language API or Azure's Text Analytics) to recognize emotions from the user's input.

[0253] The server generates an appropriate response based on the user's question, topic, and emotional state. The generated response is displayed to the user via their device. For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call up the corresponding author model, analyze the tone of the input, and respond, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, I recommend making it a habit to check reliable news sites only once a week."

[0254] The emotion engine also analyzes the user's reactions and reflects them in the next response generation. This allows the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, enabling more natural conversations through responses that correspond to the author's emotions.

[0255] Repeating this process brings about changes in the user's behavior and decision-making. This system efficiently provides knowledge of specific authors and contributes to changing the user's behavior through dialogue that takes into account the user's emotions.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1: Collecting and storing copyright data

[0258] Input: Collecting copyright data from specific author websites and online databases.

[0259] Specific operation: The server uses a web scraping tool (e.g., Python's BeautifulSoup) to collect authorship data (e.g., books, papers, essays) from the web for a specific author.

[0260] Data processing: Preprocessing the collected text data to make it easier for subsequent analysis, for example, removing unnecessary HTML tags and special characters.

[0261] Output: The preprocessed copyright data is stored in a database (e.g., MongoDB) in JSON format.

[0262] Step 2: Analyzing copyright data

[0263] Input: Copyright data saved in step 1.

[0264] Specific operation: The server analyzes the copyright data using natural language processing technology (e.g., Python's NLTK or Spacy).

[0265] Data processing: This analysis extracts themes, writing style, frequently used expressions, logical development patterns, etc. For example, it counts frequently used words and phrases and analyzes sentence structure.

[0266] Output: The extracted feature data is saved as training data for the generative AI model.

[0267] Step 3: Accepting User Input

[0268] Input: The author name and topic of conversation that the user wants to discuss, entered through the terminal.

[0269] Specific operation: The user enters the prompt "I would like to discuss the news with a specific author" into a form on a web browser.

[0270] Data operation: The terminal sends this prompt text to the server as an HTTP request.

[0271] Output: The server receives the user input and prepares it for analysis.

[0272] Step 4: Invoking the writer model and emotion recognition

[0273] Input: The user input data received in step 3.

[0274] How it works: The server analyzes the input data and calls the corresponding author model using the Hugging Face Transformer model, and then uses the Google Cloud Natural Language API for emotion recognition to analyze the user's emotions.

[0275] Data Computing: Extracting emotional states from user input text and integrating sentiment analysis and text analysis to generate responses.

[0276] Output: Response content and sentiment analysis data.

[0277] Step 5: Generate and display the response

[0278] Input: Response content and sentiment analysis data generated in step 4.

[0279] Specific operation: The server sends the generated response to the terminal as an HTTP response. The terminal displays the received response to the user.

[0280] Data calculation: Displaying responses and collecting user reactions.

[0281] Output: The response text displayed on the terminal.

[0282] Step 6: Analyzing user responses and generating the next response

[0283] Input: Any responses or follow-up questions the user enters in step 5.

[0284] Specific operation: When the user enters additional questions or responses, the device sends them back to the server, where the server analyzes the received responses using its emotion engine and reflects them in generating the next response.

[0285] Data calculation: Analyze user responses and update data for the next response. For example, use Scikit-learn to update a machine learning model based on the previous response and user responses.

[0286] Output: Next response and updated emotion data.

[0287] Step 7: Sustained dialogue and learning outcomes

[0288] Input: A continuous interactive session.

[0289] Specific operation: By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and the server learns the user's emotions and reactions to improve the accuracy of the dialogue.

[0290] Data calculation: Data obtained from each dialogue session is accumulated and used to generate responses in the future.

[0291] Output: Highly accurate, emotion-based responses and user learning effects.

[0292] (Application example 2)

[0293] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0294] Current content distribution services lack mechanisms that allow users to enjoy high-quality dialogue based on a specific author's thought patterns and knowledge. There is also a need for improved systems that can tailor the content and tone of responses to the user's emotions to provide a more natural and friendly dialogue. Furthermore, there is a need to provide a more personalized user experience by recommending related content based on the user's dialogue content and emotions.

[0295] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; means for displaying the generated response to the user; means for accepting user reactions and continuously generating new responses based on the reactions; means for recognizing the user's emotions and adjusting the content and tone of the response; and means for recommending related content to the user. This not only enables the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, but also allows the user to enjoy more natural dialogue through responses that correspond to their emotions. Furthermore, the user can receive recommendations of more relevant content, providing a personalized user experience.

[0296] definition statement

[0297] "Author's work data" refers to document data such as books, papers, essays, etc. written by an author.

[0298] "Natural language processing technology" is a technology that allows computers to analyze, generate, and understand human language.

[0299] A "specific author model" is a generative AI model trained to reproduce the thought patterns, writing style, and logical structure of a specific author.

[0300] "User input" means any text or voice inquiry or question that a user makes to the system.

[0301] A "means for generating a response" is a method or technique for generating an appropriate answer using the author model based on the user's input.

[0302] "Means for displaying to the user" refers to the interface or technology for displaying the generated response on the user's terminal.

[0303] "User response" refers to the user's responses and emotional reactions to the system.

[0304] A "means for continuously generating new responses" is a method or technology for continuously generating new responses based on user reactions.

[0305] "Means for recognizing emotions" refers to technologies or engines for analyzing emotions from a user's text or voice.

[0306] A "means for adjusting the content or tone of a response" is a method or technique for varying the content or tone of a response based on the perceived user sentiment.

[0307] "Means for recommending related content" refers to methods and technologies for recommending related books and documents based on the user's dialogue and emotions.

[0308] MODE FOR CARRYING OUT THE INVENTION

[0309] System Overview

[0310] The system incorporates the writings of a specific author and provides that author's thought patterns and knowledge through dialogue with the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the response accordingly, enabling a more natural and friendly dialogue.

[0311] Hardware and software used

[0312] Hardware

[0313] Server: for data storage and processing

[0314] Device: The user's smartphone or head-mounted display (HMD)

[0315] software

[0316] Natural language processing engine (e.g. Google Cloud Natural Language API)

[0317] Emotion recognition engine (e.g. Microsoft Azure Cognitive Services)

[0318] Generative AI models (e.g., OpenAI GPT-4)

[0319] Program processing and behavior

[0320] 1. Data Acquisition and Analysis

[0321] The server ingests the author-specific work data and uses the Google Cloud Natural Language API to analyze the documents and extract features, providing the basis for training the author-specific model.

[0322] 2. Accepting and Parsing User Input

[0323] The user inputs the name of the author and the topic of conversation through the terminal, and this input data is sent from the terminal to the server.

[0324] An emotion recognition engine is used to recognize emotions from user input and analyze the input content.

[0325] 3. Generating a Response

[0326] Based on the user's input and emotional data, the server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response. For example, in response to the question "What do you think about the recent news?", it generates an answer that reflects the writer's thought patterns.

[0327] 4. Displaying responses and adjusting based on emotions

[0328] The generated response is displayed to the user via the device, and the user's reaction is also analyzed by the emotion recognition engine, and this feedback is reflected in the generation of the next response.

[0329] 5. Recommending related content

[0330] Based on the user's conversations and emotions, it recommends related books and documents, providing a more personalized experience for users.

[0331] Specific examples

[0332] Imagine a scenario in which a user interacts with a specific author on their smartphone. Here is an example of a specific prompt:

[0333] Prompt Sentence Examples

[0334] User: "Writer, what do you think about the recent news?"

[0335] System: (After sentiment analysis) "The world is undergoing a lot of change, but what matters is the quality and reliability of the information."

[0336] In this way, users can have an experience that feels as if they are having a conversation with the author themselves, and in the process, they can gain a wealth of knowledge by receiving recommendations for related content.

[0337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0338] Program processing flow

[0339] Step-by-step explanation

[0340] Step 1:

[0341] The server takes in the author's work data and uses the Google Cloud Natural Language API to analyze the document and extract features. This feature data is stored in a database. The input is the author's work data, and the output is the analyzed feature data.

[0342] Step 2:

[0343] The user inputs the name of the author and the topic of conversation through the terminal. This input data is sent from the terminal to the server. The input is the user's text input, and the output is the data sent to the server.

[0344] Step 3:

[0345] The server uses an emotion recognition engine to recognize emotions from the user's input and analyzes the input content. The input is the user's text data, and the output is the analyzed emotion data and the input content.

[0346] Step 4:

[0347] The server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response based on the analyzed input and emotion data, with the input and emotion data as input and the generated response data as output.

[0348] Step 5:

[0349] The generated response is displayed to the user through the terminal. The input is the generated response data, and the output is the display data for the user.

[0350] Step 6:

[0351] The user's reaction is sent back to the server via the device, where it is analyzed by an emotion recognition engine. The input is the user's reaction data, and the output is the analyzed emotion data and the content of the reaction.

[0352] Step 7:

[0353] The server uses the analyzed user reaction data and emotion data as data to generate a new response. The reaction data and emotion data are input, and the data required to generate the next response is output.

[0354] Step 8:

[0355] The server recommends related content based on the user's dialogue and emotional data. For example, it recommends related books and documents based on the dialogue. The input is the dialogue and emotional data, and the output is a list of recommended content.

[0356] Through this process, users can interact with a specific author and gain a deeper understanding of that author's thought patterns and knowledge. They can also enjoy more natural interactions with emotional responses, and receive more relevant content recommendations, resulting in a more personalized experience.

[0357] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0358] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0359] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0360] [Second embodiment]

[0361] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0362] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0363] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0364] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0365] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0366] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0367] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0368] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0369] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0370] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0371] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0372] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0373] This invention is a system that incorporates the writing data of a specific best-selling author, and through dialogue with the user, provides the author's thought patterns and knowledge, ultimately aiming to change the user's behavior and decision-making. This system is implemented through processing between a server, a terminal, and the user.

[0374] Importing and analyzing copyright data

[0375] The server imports the author's work data into a database. Specifically, it collects text data such as books, papers, and essays, and analyzes the documents using natural language processing (NLP) technology. From the analyzed data, themes, writing style, frequently used expressions, and logical development patterns are extracted. This provides the basic data for training a specific author model.

[0376] Accepting and parsing user input

[0377] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." This input data is sent from the terminal to the server.

[0378] Call and response generation for writer models

[0379] The server analyzes the user's input and calls the corresponding author model. Based on the user's question and topic, the author model generates an appropriate response. The generated response reflects the author's thought patterns and writing style, making the user feel as if they are interacting with a specific author.

[0380] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[0381] Response display and feedback

[0382] The generated response is displayed to the user via the terminal, and the user can then input a new question or reaction based on the displayed response, such as "Do you have a more specific example?"

[0383] The server again analyzes the user's input and generates appropriate responses from the author model. This process repeats, allowing the user to continually gain a deeper understanding of a particular author's thought patterns and knowledge.

[0384] Continuous dialogue and learning outcomes

[0385] By continually using this system, users can acquire the thought patterns and knowledge of specific authors, which can bring about changes in their own behavior and decision-making. For example, they will naturally improve their news filtering ability and develop the habit of selecting only important information.

[0386] In this way, the present invention aims to efficiently provide author knowledge through dialogue with users, ultimately transforming their behavior and decision-making.

[0387] The processing flow will be explained below.

[0388] Step 1:

[0389] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[0390] Step 2:

[0391] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[0392] Step 3:

[0393] The server uses the extracted features to train a writer model, which is a generative AI model that mimics the thought patterns and writing style of a particular author.

[0394] Step 4:

[0395] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[0396] Step 5:

[0397] The terminal transmits the user's input data to the server.

[0398] Step 6:

[0399] The server analyzes the user's input, calls the corresponding author model, and generates an appropriate response based on the user's question and topic.

[0400] Step 7:

[0401] The server sends the generated response to the terminal.

[0402] Step 8:

[0403] The terminal displays the received response on the user interface and provides it to the user.

[0404] Step 9:

[0405] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[0406] Step 10:

[0407] The terminal sends the user's new input to the server.

[0408] Step 11:

[0409] The server again parses the user's input and uses the author model to generate an appropriate response.

[0410] Step 12:

[0411] The server generates a new response and sends it to the terminal.

[0412] Step 13:

[0413] The terminal again displays the response in the user interface, providing information for the user to guide the next interaction.

[0414] Step 14:

[0415] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, which can bring about changes in their behavior and decision-making.

[0416] Example 1

[0417] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0418] With conventional systems, it was difficult for users to learn the thought patterns and knowledge of a specific author through dialogue and then reflect that author's actions and decision-making. Furthermore, conventional systems lacked the ability to generate new responses for each user input, making it impossible to enhance learning through continuous dialogue.

[0419] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0420] In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features, means for accepting user input, invoking a specific author model based on the input, and generating a response, means for displaying the generated response to the user, means for accepting user responses and continuously generating new responses based on the responses, means for preparing basic data for training different author models, and means for analyzing user input and generating appropriate responses based on different author models. This allows users to efficiently learn the thought patterns and knowledge of specific authors and realize continuous dialogue that reflects their own actions and decision-making.

[0421] The following are definitions of important terms contained in the claims.

[0422] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0423] "Natural language processing technology" is a general term for technologies that enable computers to understand, process, and generate human language.

[0424] "Means for analyzing documents and extracting features" refers to methods and technologies for analyzing text data and extracting features such as themes, writing style, frequently occurring expressions, and logical development patterns.

[0425] "Means for accepting user input" refers to the interface that allows users to input the name of the author or topic they wish to discuss, and the method or technology for transmitting the input to the server.

[0426] "Means for invoking a specific writer model and generating a response" refers to a method or technology that uses a model that mimics the thought patterns and writing style of a pre-trained writer to generate an appropriate response to a user's input.

[0427] "Means for displaying the generated response to the user" refers to an interface or method for receiving the generated response from the server and visually presenting it to the user.

[0428] "Means for accepting user responses and continually generating new responses based on those responses" refers to methods and technologies for analyzing questions and responses re-entered by the user and generating appropriate responses again.

[0429] "Means for preparing basic data for training models of different authors" refers to methods and techniques for preparing data for training models that reflect the thought patterns and writing styles of different authors based on collected writing data.

[0430] "Means for analyzing user input and generating appropriate responses based on different writer models" refers to methods or techniques for analyzing the content of a user input, selecting the most appropriate writer model for it, and generating a response.

[0431] In this invention, the system is implemented using the following methods and techniques: The main components are a server, a terminal, and a user.

[0432] The server first collects the author's work data, which is retrieved using Python's "requests" library or an e-book API, and then stores the collected data in a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0433] The server then analyzes the stored author data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as spaCy and the Natural Language Toolkit (NLTK). During this analysis, the data is tokenized, tagged with parts of speech, and analyzed for grammar. This allows for the extraction of themes, writing style, frequent phrases, and logical development patterns. The results of this analysis are used as the basis for training different author models.

[0434] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might say, "I want to talk about the news with a specific author." The device converts the input data into JSON format and sends it to the server via an HTTP POST request. HTTP is used as the communication protocol.

[0435] The server analyzes the received user input and selects a specific author model, which is pre-trained to mimic the author's unique thought patterns and writing style, and then uses a generative AI model (e.g., GPT-3) to generate the best response to the user-entered prompt.

[0436] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[0437] This generated response is sent from the server to the terminal and displayed to the user. The user can then look at the displayed response and input a new question or response. For example, they can re-input "Do you have a more specific example?" This new input data is again sent to the server, which generates a new response.

[0438] By repeating this process, users can efficiently learn the thought patterns and knowledge of a particular author and ultimately reflect this in their own actions and decision-making. In this way, this invention aims to provide authors' knowledge through continuous dialogue with users and to change their decisions and behaviors.

[0439] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0440] Step 1:

[0441] Data collection

[0442] The server collects the author's work data from the internet or e-book stores using APIs. The input here is the author's name and a request to obtain data such as books and papers. The server collects this using the "requests" library and obtains the work data in text format as output. Specifically, it sends an API request and saves the text data obtained as a response.

[0443] Step 2:

[0444] Saving to a database

[0445] The server stores the collected copyright data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. The input is the text data collected in step 1, and the output is the data correctly stored in the database. Specific operations include connecting to the database, creating a table, and inserting data.

[0446] Step 3:

[0447] Natural Language Processing (NLP) Analysis

[0448] The server analyzes the stored data using NLP libraries such as "spaCy" and "Natural Language Toolkit (NLTK)." The input is text data retrieved from the database, and the output is feature extraction data as the analysis result. Specific operations include tokenization, morphological analysis, and grammatical analysis to extract themes, writing style, frequently occurring vocabulary, and logical development patterns.

[0449] Step 4:

[0450] Accepting user input

[0451] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might input something like "I want to talk about the news with a specific author." The input is the data entered by the user, and the output is data converted into JSON format. Specific operations involve entering data into the input form and clicking the submit button.

[0452] Step 5:

[0453] Sending data

[0454] The terminal converts the user's input data into JSON format and sends it to the server via an HTTP POST request. The input is the user input data from step 4, and the output is the request to be sent to the server. Specific operations include converting the input data into JSON, and creating and sending an HTTP request.

[0455] Step 6:

[0456] Parsing user input

[0457] The server analyzes the received user input. The input is JSON format data sent from the terminal, and the output is the analyzed author name and topic. Specifically, it parses the JSON data and extracts the author name and topic.

[0458] Step 7:

[0459] Artist model selection

[0460] The server selects the corresponding author model based on the analysis results. The input is the author name and topic analyzed in step 6, and the output is the specified author model. Specifically, the server selects an appropriate model from multiple pre-trained author models.

[0461] Step 8:

[0462] Generating a response

[0463] The server uses a generative AI model to generate a response to the user's question. The input is the selected author model and the user's input prompt, and the output is the generated response. Specifically, the server invokes a generative AI model (e.g., GPT-3) to generate the optimal response to the prompt.

[0464] Step 9:

[0465] Viewing the response

[0466] The terminal displays the response sent by the server to the user. The input is the response generated by the server, and the output is the response visually presented to the user. Specific operations include receiving the response data and displaying it in a text view.

[0467] Step 10:

[0468] Accepting user responses and continuing dialogue

[0469] The user then enters a new question or response based on the displayed response. The input is the user's new input data, and the output is the data that is sent back to the server. Specific actions include re-entering data into the input form and clicking the submit button. By repeating this process, a continuous dialogue is achieved.

[0470] These specific processing steps allow users to efficiently learn the thought patterns and knowledge of specific authors through dialogue with them, which can positively influence their behavior and decision-making.

[0471] (Application example 1)

[0472] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] Conventional interactive systems have had difficulty providing users with a realistic experience, as if they were conversing with a specific author. Furthermore, they have limitations in providing information that influences users' behavior and decisions, making it impossible to provide highly satisfying interactive content. There is a need to solve this problem and realize more advanced and interactive content delivery.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0475] In this invention, the server includes means for importing author work data, analyzing documents using natural language processing technology, and extracting features, means for accepting user input, calling a specific author model based on the input, and generating a response using a generative AI model, and means for displaying the generated response to the user. This provides a realistic experience as if the user were interacting with a specific author, making it possible to influence the user's behavior and decision-making.

[0476] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0477] "Natural language processing technology" refers to all technologies that enable computers to understand, analyze, and generate natural language.

[0478] "Specific author model" refers to a generative AI model trained based on collected and analyzed author data.

[0479] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate appropriate responses from input data.

[0480] "Means for generating a response" refers to methods and devices for using a generative AI model to create an appropriate response based on user input.

[0481] "User input" refers to text or voice input information entered by a user through a content distribution service terminal.

[0482] "User response" refers to new input or action by the user after receiving the generated response.

[0483] "Operation device" refers to a device that allows users to input or interact, such as a smartphone, smart glasses, or head-mounted display.

[0484] This invention is a system that incorporates the writing data of a specific author, provides the author's thought patterns and knowledge through dialogue with the user, and ultimately aims to change the user's behavior and decision-making. This system is realized mainly through processing between a server, a terminal, and the user.

[0485] Server Roles

[0486] The server collects the author's writing data and analyzes it using natural language processing technology. From the analyzed data, characteristics such as themes, writing style, frequently used expressions, and logical development patterns are extracted. Specifically, APIs and crawlers are used to collect the writing data and store it in a database. Natural language processing libraries such as spaCy are used for analysis. Furthermore, OpenAI's GPT-3 and other technologies are used to train author models based on the collected and analyzed data.

[0487] Device Role

[0488] The device is responsible for accepting input from the user and sending it to the server. The user enters the name of the author they want to talk to and the topic in text format. For example, they might say, "I want to talk about the news with a specific author." The device can be a smartphone, smart glasses, or a head-mounted display.

[0489] User Roles

[0490] The user is the subject of interactive content consumption, and engages in a dialogue with the artist through their device. The user receives responses generated by the server based on their input, and continues the dialogue by entering new questions and reactions.

[0491] Specific examples of processing

[0492] When a user types, "I'd like a specific author to give me advice on how to filter information," the server invokes the corresponding author model and generates a response such as, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, for example, "Do you have any more specific examples?", the server again uses the author model to generate a response such as, "For example, you might want to refer to reliable news sites or academic papers."

[0493] Prompt Sentence Examples

[0494] Below are some example prompts to input to the generative AI model:

[0495] Author Model: A specific author

[0496] User Input: Do you have any specific examples of writers?

[0497] Response:

[0498] Hardware and Software

[0499] Server: High-performance database and calculation servers are used to collect, store, and analyze data.

[0500] Natural language processing libraries: use spaCy and NLTK to parse documents.

[0501] Generative AI model: Leveraging OpenAI's GPT-3 to generate writer responses.

[0502] Device: A device that accepts user input and displays responses, such as a smartphone, smart glasses, or head-mounted display.

[0503] This makes it possible to virtually recreate the thought patterns and knowledge of an author and provide them to users through dialogue. Through an experience that makes users feel as if they are conversing with a specific author, users can acquire the thought patterns and knowledge and bring about changes in their behavior and decision-making.

[0504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0505] Step 1: The server collects the author's work data and stores it in a database

[0506] The server collects the work data (books, papers, essays, etc.) of a particular author using APIs, crawlers, etc. This data is stored in a database. The input is the author's work data, and the output is the raw work data stored in the database.

[0507] Step 2: The server analyzes the copyright data using natural language processing technology

[0508] The server analyzes the collected author data using natural language processing libraries such as spaCy and NLTK, extracting features such as document themes, writing style, frequently used expressions, and logical development patterns. The input is the raw author data in the database, and the output is feature information of the analyzed author data.

[0509] Step 3: The server trains the generative AI model

[0510] The server trains a generative AI model, such as OpenAI's GPT-3, based on the analyzed author data's feature information. The input is the feature information, and the output is a specific author model.

[0511] Step 4: The user inputs the author name and topic they want to discuss into the terminal.

[0512] The user uses a device such as a smartphone or a head-mounted display to input the name of the author they want to interact with and the topic in text format. The input is the user's input data, and the output is request data sent to the server.

[0513] Step 5: The server invokes the author model based on the user's input and generates a response using the generative AI model.

[0514] The server analyzes the user's input, calls the corresponding specific author model, and then generates an appropriate response using a generative AI model. The input is the user's request data, and the output is the generated response data.

[0515] Step 6: The terminal displays the generated response to the user

[0516] The terminal displays the response data sent from the server to the user. The input is the response data sent from the server, and the output is text or audio displayed to the user.

[0517] Step 7: The user enters a new question or response, and the server generates a new response.

[0518] The user inputs a new question or reaction based on the displayed response. This input is sent back to the server, which then uses the generative AI model to generate a new response. The input is the user's new input data, and the output is the newly generated response data.

[0519] Step 8: This process repeats as the user continues to interact

[0520] The server and the terminal continuously execute a dialogue with the user, allowing the user to gain a deeper understanding of the thought patterns and knowledge of a particular author. The input is continuous user input data, and the output is continuously generated response data.

[0521] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0522] This system incorporates data on the works of specific best-selling authors and provides users with the author's thought patterns and knowledge through dialogue with them, combined with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[0523] Importing and analyzing copyright data

[0524] The server imports the author's work data and stores it in a database. This data includes books, papers, essays, etc. The imported data is analyzed using natural language processing (NLP) technology to extract themes, writing style, frequently used expressions, logical development patterns, etc. This provides the basic data for training the author model.

[0525] Accepting and parsing user input

[0526] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." The input data is sent from the terminal to the server.

[0527] Invoking the author model and emotion recognition

[0528] The server analyzes the user's input, calls the corresponding author model, and uses an emotion engine to recognize emotions from the user's input. It then generates an appropriate response based on the user's question, theme, and emotional state.

[0529] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call the corresponding author model, analyze the tone of the input, and respond with, "It's important to focus on the quality of the information and choose reliable sources."

[0530] Displaying responses and adjusting based on emotions

[0531] The generated response is displayed to the user via the device. The user's reaction is also analyzed by the emotion engine and reflected in the next response generation. For example, if the user further inputs, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, we recommend that you make it a habit to check a reliable news site only once a week."

[0532] Continuous dialogue and learning outcomes

[0533] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, enabling more natural interactions through emotional responses. Continuing to respond to the user's emotional state can more easily bring about changes in the user's behavior and decision-making.

[0534] In this way, the present invention aims to efficiently provide authors' knowledge through dialogue that takes into account the user's emotions, and further to change the user's behavior and decision-making.

[0535] The processing flow will be explained below.

[0536] Step 1:

[0537] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[0538] Step 2:

[0539] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[0540] Step 3:

[0541] The server uses the extracted features to train a writer model, a generative AI model that mimics the thought patterns and writing style of a specific author.

[0542] Step 4:

[0543] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[0544] Step 5:

[0545] The terminal transmits the user's input data to the server.

[0546] Step 6:

[0547] The server analyzes the user's input and uses an emotion engine to recognize emotions from the input. At the same time, it invokes the corresponding author model to generate an appropriate response based on the user's question, topic, and emotional state.

[0548] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server analyzes the tone of the input and generates an appropriate response: "It's important to prioritize the quality of information and choose reliable sources."

[0549] Step 7:

[0550] The server sends the generated response to the terminal.

[0551] Step 8:

[0552] The terminal displays the received response on the user interface and provides it to the user.

[0553] Step 9:

[0554] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[0555] Step 10:

[0556] The terminal sends the user's new input to the server.

[0557] Step 11:

[0558] The server again analyzes the user's input and sentiment, and uses the writer model and emotion engine to generate an appropriate response, such as "We recommend that you make it a habit to check a trusted news site only once a week."

[0559] Step 12:

[0560] The server generates a new response and sends it to the terminal.

[0561] Step 13:

[0562] The terminal again displays the response in its user interface, providing information for the user to guide their next interaction.

[0563] Step 14:

[0564] By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and emotional responses enable a more natural dialogue. Continuing to respond to the user's emotional state can bring about changes in the user's behavior and decision-making.

[0565] Example 2

[0566] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] Conventional dialogue systems have the problem that it is difficult to model the thought patterns and knowledge of a specific author, and it is also difficult to generate flexible responses that correspond to the user's emotions. Furthermore, it is not possible to analyze the user's reactions and reflect them in the next response, making it difficult to achieve natural and sustainable dialogue.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0569] In this invention, the server includes means for collecting authorship data of specific authors, analyzing documents using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; and means for recognizing emotions from the user input using an emotion engine. This enables natural and friendly dialogue that responds to the user's emotions by utilizing the thought patterns and knowledge of specific authors. Furthermore, by analyzing the user's reactions and reflecting them in the generation of the next response, it is possible to provide a sustainable and effective dialogue.

[0570] "Specified Author" refers to the author of the specified work with whom the user wishes to interact.

[0571] "Copyrighted data" refers to documents and text data created by a specific author, such as books, papers, and essays.

[0572] "Natural language processing technology" refers to technology that uses computers to understand, analyze, and generate natural human language.

[0573] "Document analysis" refers to the process of using natural language processing technology to analyze the content of a specific author's written data and extract features such as themes, writing style, frequently used expressions, and logical development patterns.

[0574] "Characteristics" refers to the author's unique document structure and style, such as themes, writing style, frequent expressions, and logical development patterns that appear in the work data of a particular author.

[0575] "User" refers to a person who interacts with the system.

[0576] "Author model" refers to a generative AI model that is trained to mimic the thought patterns and knowledge of a specific author based on their work data.

[0577] "Means for generating a response" refers to a process that generates an appropriate response using a particular authorship model based on user input.

[0578] An "emotion engine" is a technology that recognizes emotions from user input and adjusts the content and tone of responses accordingly.

[0579] "User response" refers to the user's feedback or re-input to the generated response.

[0580] "Means for recognizing emotions" refers to the process of extracting an emotional state from a user's input text using an emotion engine.

[0581] "Sustained interaction" refers to multiple consecutive interaction sessions with a user, where each interaction is appropriately adjusted based on previous responses and user reactions.

[0582] "Natural and friendly dialogue" refers to dialogue that provides appropriate responses according to the user's emotions and proceeds smoothly without any sense of discomfort to the user.

[0583] This system incorporates the copyright data of a specific author and provides the user with the author's thought patterns and knowledge through dialogue with the user, and combines it with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[0584] Specifically, the server collects the writing data of a specific author and analyzes the document using natural language processing techniques (e.g., Python's NLTK or Spacy) to extract features such as themes, writing style, frequently used expressions, and logical development patterns. This information is then used to train a generative AI model (e.g., Hugging Face's Transformer model) to build a model that mimics the thinking and knowledge of the specific author.

[0585] The user inputs the name of the author they want to talk to and the topic they want to talk about (for example, a prompt such as "I want to talk to a specific author about the news" or "I want a specific author to give me advice on how to filter information.") The device sends this input data to the server, which analyzes it and calls the corresponding author model. Furthermore, it uses an emotion engine (for example, Google Cloud Natural Language API or Azure's Text Analytics) to recognize emotions from the user's input.

[0586] The server generates an appropriate response based on the user's question, topic, and emotional state. The generated response is displayed to the user via their device. For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call up the corresponding author model, analyze the tone of the input, and respond, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, I recommend making it a habit to check reliable news sites only once a week."

[0587] The emotion engine also analyzes the user's reactions and reflects them in the next response generation. This allows the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, enabling more natural conversations through responses that correspond to the author's emotions.

[0588] Repeating this process brings about changes in the user's behavior and decision-making. This system efficiently provides knowledge of specific authors and contributes to changing the user's behavior through dialogue that takes into account the user's emotions.

[0589] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0590] Step 1: Collecting and storing copyright data

[0591] Input: Collecting copyright data from specific author websites and online databases.

[0592] Specific operation: The server uses a web scraping tool (e.g., Python's BeautifulSoup) to collect authorship data (e.g., books, papers, essays) from the web for a specific author.

[0593] Data processing: Preprocessing the collected text data to make it easier for subsequent analysis, for example, removing unnecessary HTML tags and special characters.

[0594] Output: The preprocessed copyright data is stored in a database (e.g., MongoDB) in JSON format.

[0595] Step 2: Analyzing copyright data

[0596] Input: Copyright data saved in step 1.

[0597] Specific operation: The server analyzes the copyright data using natural language processing technology (e.g., Python's NLTK or Spacy).

[0598] Data processing: This analysis extracts themes, writing style, frequently used expressions, logical development patterns, etc. For example, it counts frequently used words and phrases and analyzes sentence structure.

[0599] Output: The extracted feature data is saved as training data for the generative AI model.

[0600] Step 3: Accepting User Input

[0601] Input: The author name and topic of conversation that the user wants to discuss, entered through the terminal.

[0602] Specific operation: The user enters the prompt "I would like to discuss the news with a specific author" into a form on a web browser.

[0603] Data operation: The terminal sends this prompt text to the server as an HTTP request.

[0604] Output: The server receives the user input and prepares it for analysis.

[0605] Step 4: Invoking the writer model and emotion recognition

[0606] Input: The user input data received in step 3.

[0607] How it works: The server analyzes the input data and calls the corresponding author model using the Hugging Face Transformer model, and then uses the Google Cloud Natural Language API for emotion recognition to analyze the user's emotions.

[0608] Data Computing: Extracting emotional states from user input text and integrating sentiment analysis and text analysis to generate responses.

[0609] Output: Response content and sentiment analysis data.

[0610] Step 5: Generate and display the response

[0611] Input: Response content and sentiment analysis data generated in step 4.

[0612] Specific operation: The server sends the generated response to the terminal as an HTTP response. The terminal displays the received response to the user.

[0613] Data calculation: Displaying responses and collecting user reactions.

[0614] Output: The response text displayed on the terminal.

[0615] Step 6: Analyzing user responses and generating the next response

[0616] Input: Any responses or follow-up questions the user enters in step 5.

[0617] Specific operation: When the user enters additional questions or responses, the device sends them back to the server, where the server analyzes the received responses using its emotion engine and reflects them in generating the next response.

[0618] Data calculation: Analyze user responses and update data for the next response. For example, use Scikit-learn to update a machine learning model based on the previous response and user responses.

[0619] Output: Next response and updated emotion data.

[0620] Step 7: Sustained dialogue and learning outcomes

[0621] Input: A continuous interactive session.

[0622] Specific operation: By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and the server learns the user's emotions and reactions to improve the accuracy of the dialogue.

[0623] Data calculation: Data obtained from each dialogue session is accumulated and used to generate responses in the future.

[0624] Output: Highly accurate, emotion-based responses and user learning effects.

[0625] (Application example 2)

[0626] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0627] Current content distribution services lack mechanisms that allow users to enjoy high-quality dialogue based on a specific author's thought patterns and knowledge. There is also a need for improved systems that can tailor the content and tone of responses to the user's emotions to provide a more natural and friendly dialogue. Furthermore, there is a need to provide a more personalized user experience by recommending related content based on the user's dialogue content and emotions.

[0628] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; means for displaying the generated response to the user; means for accepting user reactions and continuously generating new responses based on the reactions; means for recognizing the user's emotions and adjusting the content and tone of the response; and means for recommending related content to the user. This not only enables the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, but also allows the user to enjoy more natural dialogue through responses that correspond to their emotions. Furthermore, the user can receive recommendations of more relevant content, providing a personalized user experience.

[0629] definition statement

[0630] "Author's work data" refers to document data such as books, papers, essays, etc. written by an author.

[0631] "Natural language processing technology" is a technology that allows computers to analyze, generate, and understand human language.

[0632] A "specific author model" is a generative AI model trained to reproduce the thought patterns, writing style, and logical structure of a specific author.

[0633] "User input" means any text or voice inquiry or question that a user makes to the system.

[0634] A "means for generating a response" is a method or technique for generating an appropriate answer using the author model based on the user's input.

[0635] "Means for displaying to the user" refers to the interface or technology for displaying the generated response on the user's terminal.

[0636] "User response" refers to the user's responses and emotional reactions to the system.

[0637] A "means for continuously generating new responses" is a method or technology for continuously generating new responses based on user reactions.

[0638] "Means for recognizing emotions" refers to technologies or engines for analyzing emotions from a user's text or voice.

[0639] A "means for adjusting the content or tone of a response" is a method or technique for varying the content or tone of a response based on the perceived user sentiment.

[0640] "Means for recommending related content" refers to methods and technologies for recommending related books and documents based on the user's dialogue and emotions.

[0641] MODE FOR CARRYING OUT THE INVENTION

[0642] System Overview

[0643] The system incorporates the writings of a specific author and provides that author's thought patterns and knowledge through dialogue with the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the response accordingly, enabling a more natural and friendly dialogue.

[0644] Hardware and software used

[0645] Hardware

[0646] Server: for data storage and processing

[0647] Device: The user's smartphone or head-mounted display (HMD)

[0648] software

[0649] Natural language processing engine (e.g. Google Cloud Natural Language API)

[0650] Emotion recognition engine (e.g. Microsoft Azure Cognitive Services)

[0651] Generative AI models (e.g., OpenAI GPT-4)

[0652] Program processing and behavior

[0653] 1. Data Acquisition and Analysis

[0654] The server ingests the author-specific work data and uses the Google Cloud Natural Language API to analyze the documents and extract features, providing the basis for training the author-specific model.

[0655] 2. Accepting and Parsing User Input

[0656] The user inputs the name of the author and the topic of conversation through the terminal, and this input data is sent from the terminal to the server.

[0657] An emotion recognition engine is used to recognize emotions from user input and analyze the input content.

[0658] 3. Generating a Response

[0659] Based on the user's input and emotional data, the server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response. For example, in response to the question "What do you think about the recent news?", it generates an answer that reflects the writer's thought patterns.

[0660] 4. Displaying responses and adjusting based on emotions

[0661] The generated response is displayed to the user via the device, and the user's reaction is also analyzed by the emotion recognition engine, and this feedback is reflected in the generation of the next response.

[0662] 5. Recommending related content

[0663] Based on the user's conversations and emotions, it recommends related books and documents, providing a more personalized experience for users.

[0664] Specific examples

[0665] Imagine a scenario in which a user interacts with a specific author on their smartphone. Here is an example of a specific prompt:

[0666] Prompt Sentence Examples

[0667] User: "Writer, what do you think about the recent news?"

[0668] System: (After sentiment analysis) "The world is undergoing a lot of change, but what matters is the quality and reliability of the information."

[0669] In this way, users can have an experience that feels as if they are having a conversation with the author themselves, and in the process, they can gain a wealth of knowledge by receiving recommendations for related content.

[0670] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0671] Program processing flow

[0672] Step-by-step explanation

[0673] Step 1:

[0674] The server takes in the author's work data and uses the Google Cloud Natural Language API to analyze the document and extract features. This feature data is stored in a database. The input is the author's work data, and the output is the analyzed feature data.

[0675] Step 2:

[0676] The user inputs the name of the author and the topic of conversation through the terminal. This input data is sent from the terminal to the server. The input is the user's text input, and the output is the data sent to the server.

[0677] Step 3:

[0678] The server uses an emotion recognition engine to recognize emotions from the user's input and analyzes the input content. The input is the user's text data, and the output is the analyzed emotion data and the input content.

[0679] Step 4:

[0680] The server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response based on the analyzed input and emotion data, with the input and emotion data as input and the generated response data as output.

[0681] Step 5:

[0682] The generated response is displayed to the user through the terminal. The input is the generated response data, and the output is the display data for the user.

[0683] Step 6:

[0684] The user's reaction is sent back to the server via the device, where it is analyzed by an emotion recognition engine. The input is the user's reaction data, and the output is the analyzed emotion data and the content of the reaction.

[0685] Step 7:

[0686] The server uses the analyzed user reaction data and emotion data as data to generate a new response. The reaction data and emotion data are input, and the data required to generate the next response is output.

[0687] Step 8:

[0688] The server recommends related content based on the user's dialogue and emotional data. For example, it recommends related books and documents based on the dialogue. The input is the dialogue and emotional data, and the output is a list of recommended content.

[0689] Through this process, users can interact with a specific author and gain a deeper understanding of that author's thought patterns and knowledge. They can also enjoy more natural interactions with emotional responses, and receive more relevant content recommendations, resulting in a more personalized experience.

[0690] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0691] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0692] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0693] [Third embodiment]

[0694] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0695] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0696] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0697] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0698] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0699] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0700] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0701] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0702] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0703] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0704] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0705] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0706] This invention is a system that incorporates the writing data of a specific best-selling author, and through dialogue with the user, provides the author's thought patterns and knowledge, ultimately aiming to change the user's behavior and decision-making. This system is implemented through processing between a server, a terminal, and the user.

[0707] Importing and analyzing copyright data

[0708] The server imports the author's work data into a database. Specifically, it collects text data such as books, papers, and essays, and analyzes the documents using natural language processing (NLP) technology. From the analyzed data, themes, writing style, frequently used expressions, and logical development patterns are extracted. This provides the basic data for training a specific author model.

[0709] Accepting and parsing user input

[0710] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." This input data is sent from the terminal to the server.

[0711] Call and response generation for writer models

[0712] The server analyzes the user's input and calls the corresponding author model. Based on the user's question and topic, the author model generates an appropriate response. The generated response reflects the author's thought patterns and writing style, making the user feel as if they are interacting with a specific author.

[0713] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[0714] Response display and feedback

[0715] The generated response is displayed to the user via the terminal, and the user can then input a new question or reaction based on the displayed response, such as "Do you have a more specific example?"

[0716] The server again analyzes the user's input and generates appropriate responses from the author model. This process repeats, allowing the user to continually gain a deeper understanding of a particular author's thought patterns and knowledge.

[0717] Continuous dialogue and learning outcomes

[0718] By continually using this system, users can acquire the thought patterns and knowledge of specific authors, which can bring about changes in their own behavior and decision-making. For example, they will naturally improve their news filtering ability and develop the habit of selecting only important information.

[0719] In this way, the present invention aims to efficiently provide author knowledge through dialogue with users, ultimately transforming their behavior and decision-making.

[0720] The processing flow will be explained below.

[0721] Step 1:

[0722] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[0723] Step 2:

[0724] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[0725] Step 3:

[0726] The server uses the extracted features to train a writer model, which is a generative AI model that mimics the thought patterns and writing style of a particular author.

[0727] Step 4:

[0728] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[0729] Step 5:

[0730] The terminal transmits the user's input data to the server.

[0731] Step 6:

[0732] The server analyzes the user's input, calls the corresponding author model, and generates an appropriate response based on the user's question and topic.

[0733] Step 7:

[0734] The server sends the generated response to the terminal.

[0735] Step 8:

[0736] The terminal displays the received response on the user interface and provides it to the user.

[0737] Step 9:

[0738] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[0739] Step 10:

[0740] The terminal sends the user's new input to the server.

[0741] Step 11:

[0742] The server again parses the user's input and uses the author model to generate an appropriate response.

[0743] Step 12:

[0744] The server generates a new response and sends it to the terminal.

[0745] Step 13:

[0746] The terminal again displays the response in the user interface, providing information for the user to guide the next interaction.

[0747] Step 14:

[0748] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, which can bring about changes in their behavior and decision-making.

[0749] Example 1

[0750] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0751] With conventional systems, it was difficult for users to learn the thought patterns and knowledge of a specific author through dialogue and then reflect that author's actions and decision-making. Furthermore, conventional systems lacked the ability to generate new responses for each user input, making it impossible to enhance learning through continuous dialogue.

[0752] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0753] In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features, means for accepting user input, invoking a specific author model based on the input, and generating a response, means for displaying the generated response to the user, means for accepting user responses and continuously generating new responses based on the responses, means for preparing basic data for training different author models, and means for analyzing user input and generating appropriate responses based on different author models. This allows users to efficiently learn the thought patterns and knowledge of specific authors and realize continuous dialogue that reflects their own actions and decision-making.

[0754] The following are definitions of important terms contained in the claims.

[0755] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0756] "Natural language processing technology" is a general term for technologies that enable computers to understand, process, and generate human language.

[0757] "Means for analyzing documents and extracting features" refers to methods and technologies for analyzing text data and extracting features such as themes, writing style, frequently occurring expressions, and logical development patterns.

[0758] "Means for accepting user input" refers to the interface that allows users to input the name of the author or topic they wish to discuss, and the method or technology for transmitting the input to the server.

[0759] "Means for invoking a specific writer model and generating a response" refers to a method or technology that uses a model that mimics the thought patterns and writing style of a pre-trained writer to generate an appropriate response to a user's input.

[0760] "Means for displaying the generated response to the user" refers to an interface or method for receiving the generated response from the server and visually presenting it to the user.

[0761] "Means for accepting user responses and continually generating new responses based on those responses" refers to methods and technologies for analyzing questions and responses re-entered by the user and generating appropriate responses again.

[0762] "Means for preparing basic data for training models of different authors" refers to methods and techniques for preparing data for training models that reflect the thought patterns and writing styles of different authors based on collected writing data.

[0763] "Means for analyzing user input and generating appropriate responses based on different writer models" refers to methods or techniques for analyzing the content of a user input, selecting the most appropriate writer model for it, and generating a response.

[0764] In this invention, the system is implemented using the following methods and techniques: The main components are a server, a terminal, and a user.

[0765] The server first collects the author's work data, which is retrieved using Python's "requests" library or an e-book API, and then stores the collected data in a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[0766] The server then analyzes the stored author data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as spaCy and the Natural Language Toolkit (NLTK). During this analysis, the data is tokenized, tagged with parts of speech, and analyzed for grammar. This allows for the extraction of themes, writing style, frequent phrases, and logical development patterns. The results of this analysis are used as the basis for training different author models.

[0767] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might say, "I want to talk about the news with a specific author." The device converts the input data into JSON format and sends it to the server via an HTTP POST request. HTTP is used as the communication protocol.

[0768] The server analyzes the received user input and selects a specific author model, which is pre-trained to mimic the author's unique thought patterns and writing style, and then uses a generative AI model (e.g., GPT-3) to generate the best response to the user-entered prompt.

[0769] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[0770] This generated response is sent from the server to the terminal and displayed to the user. The user can then look at the displayed response and input a new question or response. For example, they can re-input "Do you have a more specific example?" This new input data is again sent to the server, which generates a new response.

[0771] By repeating this process, users can efficiently learn the thought patterns and knowledge of a particular author and ultimately reflect this in their own actions and decision-making. In this way, this invention aims to provide authors' knowledge through continuous dialogue with users and to change their decisions and behaviors.

[0772] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0773] Step 1:

[0774] Data collection

[0775] The server collects the author's work data from the internet or e-book stores using APIs. The input here is the author's name and a request to obtain data such as books and papers. The server collects this using the "requests" library and obtains the work data in text format as output. Specifically, it sends an API request and saves the text data obtained as a response.

[0776] Step 2:

[0777] Saving to a database

[0778] The server stores the collected copyright data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. The input is the text data collected in step 1, and the output is the data correctly stored in the database. Specific operations include connecting to the database, creating a table, and inserting data.

[0779] Step 3:

[0780] Natural Language Processing (NLP) Analysis

[0781] The server analyzes the stored data using NLP libraries such as "spaCy" and "Natural Language Toolkit (NLTK)." The input is text data retrieved from the database, and the output is feature extraction data as the analysis result. Specific operations include tokenization, morphological analysis, and grammatical analysis to extract themes, writing style, frequently occurring vocabulary, and logical development patterns.

[0782] Step 4:

[0783] Accepting user input

[0784] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might input something like "I want to talk about the news with a specific author." The input is the data entered by the user, and the output is data converted into JSON format. Specific operations involve entering data into the input form and clicking the submit button.

[0785] Step 5:

[0786] Sending data

[0787] The terminal converts the user's input data into JSON format and sends it to the server via an HTTP POST request. The input is the user input data from step 4, and the output is the request to be sent to the server. Specific operations include converting the input data into JSON, and creating and sending an HTTP request.

[0788] Step 6:

[0789] Parsing user input

[0790] The server analyzes the received user input. The input is JSON format data sent from the terminal, and the output is the analyzed author name and topic. Specifically, it parses the JSON data and extracts the author name and topic.

[0791] Step 7:

[0792] Artist model selection

[0793] The server selects the corresponding author model based on the analysis results. The input is the author name and topic analyzed in step 6, and the output is the specified author model. Specifically, the server selects an appropriate model from multiple pre-trained author models.

[0794] Step 8:

[0795] Generating a response

[0796] The server uses a generative AI model to generate a response to the user's question. The input is the selected author model and the user's input prompt, and the output is the generated response. Specifically, the server invokes a generative AI model (e.g., GPT-3) to generate the optimal response to the prompt.

[0797] Step 9:

[0798] Viewing the response

[0799] The terminal displays the response sent by the server to the user. The input is the response generated by the server, and the output is the response visually presented to the user. Specific operations include receiving the response data and displaying it in a text view.

[0800] Step 10:

[0801] Accepting user responses and continuing dialogue

[0802] The user then enters a new question or response based on the displayed response. The input is the user's new input data, and the output is the data that is sent back to the server. Specific actions include re-entering data into the input form and clicking the submit button. By repeating this process, a continuous dialogue is achieved.

[0803] These specific processing steps allow users to efficiently learn the thought patterns and knowledge of specific authors through dialogue with them, which can positively influence their behavior and decision-making.

[0804] (Application example 1)

[0805] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0806] Conventional interactive systems have had difficulty providing users with a realistic experience, as if they were conversing with a specific author. Furthermore, they have limitations in providing information that influences users' behavior and decisions, making it impossible to provide highly satisfying interactive content. There is a need to solve this problem and realize more advanced and interactive content delivery.

[0807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0808] In this invention, the server includes means for importing author work data, analyzing documents using natural language processing technology, and extracting features, means for accepting user input, calling a specific author model based on the input, and generating a response using a generative AI model, and means for displaying the generated response to the user. This provides a realistic experience as if the user were interacting with a specific author, making it possible to influence the user's behavior and decision-making.

[0809] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[0810] "Natural language processing technology" refers to all technologies that enable computers to understand, analyze, and generate natural language.

[0811] "Specific author model" refers to a generative AI model trained based on collected and analyzed author data.

[0812] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate appropriate responses from input data.

[0813] "Means for generating a response" refers to methods and devices for using a generative AI model to create an appropriate response based on user input.

[0814] "User input" refers to text or voice input information entered by a user through a content distribution service terminal.

[0815] "User response" refers to new input or action by the user after receiving the generated response.

[0816] "Operation device" refers to a device that allows users to input or interact, such as a smartphone, smart glasses, or head-mounted display.

[0817] This invention is a system that incorporates the writing data of a specific author, provides the author's thought patterns and knowledge through dialogue with the user, and ultimately aims to change the user's behavior and decision-making. This system is realized mainly through processing between a server, a terminal, and the user.

[0818] Server Roles

[0819] The server collects the author's writing data and analyzes it using natural language processing technology. From the analyzed data, characteristics such as themes, writing style, frequently used expressions, and logical development patterns are extracted. Specifically, APIs and crawlers are used to collect the writing data and store it in a database. Natural language processing libraries such as spaCy are used for analysis. Furthermore, OpenAI's GPT-3 and other technologies are used to train author models based on the collected and analyzed data.

[0820] Device Role

[0821] The device is responsible for accepting input from the user and sending it to the server. The user enters the name of the author they want to talk to and the topic in text format. For example, they might say, "I want to talk about the news with a specific author." The device can be a smartphone, smart glasses, or a head-mounted display.

[0822] User Roles

[0823] The user is the subject of interactive content consumption, and engages in a dialogue with the artist through their device. The user receives responses generated by the server based on their input, and continues the dialogue by entering new questions and reactions.

[0824] Specific examples of processing

[0825] When a user types, "I'd like a specific author to give me advice on how to filter information," the server invokes the corresponding author model and generates a response such as, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, for example, "Do you have any more specific examples?", the server again uses the author model to generate a response such as, "For example, you might want to refer to reliable news sites or academic papers."

[0826] Prompt Sentence Examples

[0827] Below are some example prompts to input to the generative AI model:

[0828] Author Model: A specific author

[0829] User Input: Do you have any specific examples of writers?

[0830] Response:

[0831] Hardware and Software

[0832] Server: High-performance database and calculation servers are used to collect, store, and analyze data.

[0833] Natural language processing libraries: use spaCy and NLTK to parse documents.

[0834] Generative AI model: Leveraging OpenAI's GPT-3 to generate writer responses.

[0835] Device: A device that accepts user input and displays responses, such as a smartphone, smart glasses, or head-mounted display.

[0836] This makes it possible to virtually recreate the thought patterns and knowledge of an author and provide them to users through dialogue. Through an experience that makes users feel as if they are conversing with a specific author, users can acquire the thought patterns and knowledge and bring about changes in their behavior and decision-making.

[0837] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0838] Step 1: The server collects the author's work data and stores it in a database

[0839] The server collects the work data (books, papers, essays, etc.) of a particular author using APIs, crawlers, etc. This data is stored in a database. The input is the author's work data, and the output is the raw work data stored in the database.

[0840] Step 2: The server analyzes the copyright data using natural language processing technology

[0841] The server analyzes the collected author data using natural language processing libraries such as spaCy and NLTK, extracting features such as document themes, writing style, frequently used expressions, and logical development patterns. The input is the raw author data in the database, and the output is feature information of the analyzed author data.

[0842] Step 3: The server trains the generative AI model

[0843] The server trains a generative AI model, such as OpenAI's GPT-3, based on the analyzed author data's feature information. The input is the feature information, and the output is a specific author model.

[0844] Step 4: The user inputs the author name and topic they want to discuss into the terminal.

[0845] The user uses a device such as a smartphone or a head-mounted display to input the name of the author they want to interact with and the topic in text format. The input is the user's input data, and the output is request data sent to the server.

[0846] Step 5: The server invokes the author model based on the user's input and generates a response using the generative AI model.

[0847] The server analyzes the user's input, calls the corresponding specific author model, and then generates an appropriate response using a generative AI model. The input is the user's request data, and the output is the generated response data.

[0848] Step 6: The terminal displays the generated response to the user

[0849] The terminal displays the response data sent from the server to the user. The input is the response data sent from the server, and the output is text or audio displayed to the user.

[0850] Step 7: The user enters a new question or response, and the server generates a new response.

[0851] The user inputs a new question or reaction based on the displayed response. This input is sent back to the server, which then uses the generative AI model to generate a new response. The input is the user's new input data, and the output is the newly generated response data.

[0852] Step 8: This process repeats as the user continues to interact

[0853] The server and the terminal continuously execute a dialogue with the user, allowing the user to gain a deeper understanding of the thought patterns and knowledge of a particular author. The input is continuous user input data, and the output is continuously generated response data.

[0854] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0855] This system incorporates data on the works of specific best-selling authors and provides users with the author's thought patterns and knowledge through dialogue with them, combined with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[0856] Importing and analyzing copyright data

[0857] The server imports the author's work data and stores it in a database. This data includes books, papers, essays, etc. The imported data is analyzed using natural language processing (NLP) technology to extract themes, writing style, frequently used expressions, logical development patterns, etc. This provides the basic data for training the author model.

[0858] Accepting and parsing user input

[0859] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." The input data is sent from the terminal to the server.

[0860] Invoking the author model and emotion recognition

[0861] The server analyzes the user's input, calls the corresponding author model, and uses an emotion engine to recognize emotions from the user's input. It then generates an appropriate response based on the user's question, theme, and emotional state.

[0862] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call the corresponding author model, analyze the tone of the input, and respond with, "It's important to focus on the quality of the information and choose reliable sources."

[0863] Displaying responses and adjusting based on emotions

[0864] The generated response is displayed to the user via the device. The user's reaction is also analyzed by the emotion engine and reflected in the next response generation. For example, if the user further inputs, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, we recommend that you make it a habit to check a reliable news site only once a week."

[0865] Continuous dialogue and learning outcomes

[0866] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, enabling more natural interactions through emotional responses. Continuing to respond to the user's emotional state can more easily bring about changes in the user's behavior and decision-making.

[0867] In this way, the present invention aims to efficiently provide authors' knowledge through dialogue that takes into account the user's emotions, and further to change the user's behavior and decision-making.

[0868] The processing flow will be explained below.

[0869] Step 1:

[0870] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[0871] Step 2:

[0872] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[0873] Step 3:

[0874] The server uses the extracted features to train a writer model, a generative AI model that mimics the thought patterns and writing style of a specific author.

[0875] Step 4:

[0876] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[0877] Step 5:

[0878] The terminal transmits the user's input data to the server.

[0879] Step 6:

[0880] The server analyzes the user's input and uses an emotion engine to recognize emotions from the input. At the same time, it invokes the corresponding author model to generate an appropriate response based on the user's question, topic, and emotional state.

[0881] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server analyzes the tone of the input and generates an appropriate response: "It's important to prioritize the quality of information and choose reliable sources."

[0882] Step 7:

[0883] The server sends the generated response to the terminal.

[0884] Step 8:

[0885] The terminal displays the received response on the user interface and provides it to the user.

[0886] Step 9:

[0887] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[0888] Step 10:

[0889] The terminal sends the user's new input to the server.

[0890] Step 11:

[0891] The server again analyzes the user's input and sentiment, and uses the writer model and emotion engine to generate an appropriate response, such as "We recommend that you make it a habit to check a trusted news site only once a week."

[0892] Step 12:

[0893] The server generates a new response and sends it to the terminal.

[0894] Step 13:

[0895] The terminal again displays the response in its user interface, providing information for the user to guide their next interaction.

[0896] Step 14:

[0897] By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and emotional responses enable a more natural dialogue. Continuing to respond to the user's emotional state can bring about changes in the user's behavior and decision-making.

[0898] Example 2

[0899] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0900] Conventional dialogue systems have the problem that it is difficult to model the thought patterns and knowledge of a specific author, and it is also difficult to generate flexible responses that correspond to the user's emotions. Furthermore, it is not possible to analyze the user's reactions and reflect them in the next response, making it difficult to achieve natural and sustainable dialogue.

[0901] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0902] In this invention, the server includes means for collecting authorship data of specific authors, analyzing documents using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; and means for recognizing emotions from the user input using an emotion engine. This enables natural and friendly dialogue that responds to the user's emotions by utilizing the thought patterns and knowledge of specific authors. Furthermore, by analyzing the user's reactions and reflecting them in the generation of the next response, it is possible to provide a sustainable and effective dialogue.

[0903] "Specified Author" refers to the author of the specified work with whom the user wishes to interact.

[0904] "Copyrighted data" refers to documents and text data created by a specific author, such as books, papers, and essays.

[0905] "Natural language processing technology" refers to technology that uses computers to understand, analyze, and generate natural human language.

[0906] "Document analysis" refers to the process of using natural language processing technology to analyze the content of a specific author's written data and extract features such as themes, writing style, frequently used expressions, and logical development patterns.

[0907] "Characteristics" refers to the author's unique document structure and style, such as themes, writing style, frequent expressions, and logical development patterns that appear in the work data of a particular author.

[0908] "User" refers to a person who interacts with the system.

[0909] "Author model" refers to a generative AI model that is trained to mimic the thought patterns and knowledge of a specific author based on their work data.

[0910] "Means for generating a response" refers to a process that generates an appropriate response using a particular authorship model based on user input.

[0911] An "emotion engine" is a technology that recognizes emotions from user input and adjusts the content and tone of responses accordingly.

[0912] "User response" refers to the user's feedback or re-input to the generated response.

[0913] "Means for recognizing emotions" refers to the process of extracting an emotional state from a user's input text using an emotion engine.

[0914] "Sustained interaction" refers to multiple consecutive interaction sessions with a user, where each interaction is appropriately adjusted based on previous responses and user reactions.

[0915] "Natural and friendly dialogue" refers to dialogue that provides appropriate responses according to the user's emotions and proceeds smoothly without any sense of discomfort to the user.

[0916] This system incorporates the copyright data of a specific author and provides the user with the author's thought patterns and knowledge through dialogue with the user, and combines it with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[0917] Specifically, the server collects the writing data of a specific author and analyzes the document using natural language processing techniques (e.g., Python's NLTK or Spacy) to extract features such as themes, writing style, frequently used expressions, and logical development patterns. This information is then used to train a generative AI model (e.g., Hugging Face's Transformer model) to build a model that mimics the thinking and knowledge of the specific author.

[0918] The user inputs the name of the author they want to talk to and the topic they want to talk about (for example, a prompt such as "I want to talk to a specific author about the news" or "I want a specific author to give me advice on how to filter information.") The device sends this input data to the server, which analyzes it and calls the corresponding author model. Furthermore, it uses an emotion engine (for example, Google Cloud Natural Language API or Azure's Text Analytics) to recognize emotions from the user's input.

[0919] The server generates an appropriate response based on the user's question, topic, and emotional state. The generated response is displayed to the user via their device. For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call up the corresponding author model, analyze the tone of the input, and respond, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, I recommend making it a habit to check reliable news sites only once a week."

[0920] The emotion engine also analyzes the user's reactions and reflects them in the next response generation. This allows the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, enabling more natural conversations through responses that correspond to the author's emotions.

[0921] Repeating this process brings about changes in the user's behavior and decision-making. This system efficiently provides knowledge of specific authors and contributes to changing the user's behavior through dialogue that takes into account the user's emotions.

[0922] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0923] Step 1: Collecting and storing copyright data

[0924] Input: Collecting copyright data from specific author websites and online databases.

[0925] Specific operation: The server uses a web scraping tool (e.g., Python's BeautifulSoup) to collect authorship data (e.g., books, papers, essays) from the web for a specific author.

[0926] Data processing: Preprocessing the collected text data to make it easier for subsequent analysis, for example, removing unnecessary HTML tags and special characters.

[0927] Output: The preprocessed copyright data is stored in a database (e.g., MongoDB) in JSON format.

[0928] Step 2: Analyzing copyright data

[0929] Input: Copyright data saved in step 1.

[0930] Specific operation: The server analyzes the copyright data using natural language processing technology (e.g., Python's NLTK or Spacy).

[0931] Data processing: This analysis extracts themes, writing style, frequently used expressions, logical development patterns, etc. For example, it counts frequently used words and phrases and analyzes sentence structure.

[0932] Output: The extracted feature data is saved as training data for the generative AI model.

[0933] Step 3: Accepting User Input

[0934] Input: The author name and topic of conversation that the user wants to discuss, entered through the terminal.

[0935] Specific operation: The user enters the prompt "I would like to discuss the news with a specific author" into a form on a web browser.

[0936] Data operation: The terminal sends this prompt text to the server as an HTTP request.

[0937] Output: The server receives the user input and prepares it for analysis.

[0938] Step 4: Invoking the writer model and emotion recognition

[0939] Input: The user input data received in step 3.

[0940] How it works: The server analyzes the input data and calls the corresponding author model using the Hugging Face Transformer model, and then uses the Google Cloud Natural Language API for emotion recognition to analyze the user's emotions.

[0941] Data Computing: Extracting emotional states from user input text and integrating sentiment analysis and text analysis to generate responses.

[0942] Output: Response content and sentiment analysis data.

[0943] Step 5: Generate and display the response

[0944] Input: Response content and sentiment analysis data generated in step 4.

[0945] Specific operation: The server sends the generated response to the terminal as an HTTP response. The terminal displays the received response to the user.

[0946] Data calculation: Displaying responses and collecting user reactions.

[0947] Output: The response text displayed on the terminal.

[0948] Step 6: Analyzing user responses and generating the next response

[0949] Input: Any responses or follow-up questions the user enters in step 5.

[0950] Specific operation: When the user enters additional questions or responses, the device sends them back to the server, where the server analyzes the received responses using its emotion engine and reflects them in generating the next response.

[0951] Data calculation: Analyze user responses and update data for the next response. For example, use Scikit-learn to update a machine learning model based on the previous response and user responses.

[0952] Output: Next response and updated emotion data.

[0953] Step 7: Sustained dialogue and learning outcomes

[0954] Input: A continuous interactive session.

[0955] Specific operation: By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and the server learns the user's emotions and reactions to improve the accuracy of the dialogue.

[0956] Data calculation: Data obtained from each dialogue session is accumulated and used to generate responses in the future.

[0957] Output: Highly accurate, emotion-based responses and user learning effects.

[0958] (Application example 2)

[0959] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0960] Current content distribution services lack mechanisms that allow users to enjoy high-quality dialogue based on a specific author's thought patterns and knowledge. There is also a need for improved systems that can tailor the content and tone of responses to the user's emotions to provide a more natural and friendly dialogue. Furthermore, there is a need to provide a more personalized user experience by recommending related content based on the user's dialogue content and emotions.

[0961] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; means for displaying the generated response to the user; means for accepting user reactions and continuously generating new responses based on the reactions; means for recognizing the user's emotions and adjusting the content and tone of the response; and means for recommending related content to the user. This not only enables the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, but also allows the user to enjoy more natural dialogue through responses that correspond to their emotions. Furthermore, the user can receive recommendations of more relevant content, providing a personalized user experience.

[0962] definition statement

[0963] "Author's work data" refers to document data such as books, papers, essays, etc. written by an author.

[0964] "Natural language processing technology" is a technology that allows computers to analyze, generate, and understand human language.

[0965] A "specific author model" is a generative AI model trained to reproduce the thought patterns, writing style, and logical structure of a specific author.

[0966] "User input" means any text or voice inquiry or question that a user makes to the system.

[0967] A "means for generating a response" is a method or technique for generating an appropriate answer using the author model based on the user's input.

[0968] "Means for displaying to the user" refers to the interface or technology for displaying the generated response on the user's terminal.

[0969] "User response" refers to the user's responses and emotional reactions to the system.

[0970] A "means for continuously generating new responses" is a method or technology for continuously generating new responses based on user reactions.

[0971] "Means for recognizing emotions" refers to technologies or engines for analyzing emotions from a user's text or voice.

[0972] A "means for adjusting the content or tone of a response" is a method or technique for varying the content or tone of a response based on the perceived user sentiment.

[0973] "Means for recommending related content" refers to methods and technologies for recommending related books and documents based on the user's dialogue and emotions.

[0974] MODE FOR CARRYING OUT THE INVENTION

[0975] System Overview

[0976] The system incorporates the writings of a specific author and provides that author's thought patterns and knowledge through dialogue with the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the response accordingly, enabling a more natural and friendly dialogue.

[0977] Hardware and software used

[0978] Hardware

[0979] Server: for data storage and processing

[0980] Device: The user's smartphone or head-mounted display (HMD)

[0981] software

[0982] Natural language processing engine (e.g. Google Cloud Natural Language API)

[0983] Emotion recognition engine (e.g. Microsoft Azure Cognitive Services)

[0984] Generative AI models (e.g., OpenAI GPT-4)

[0985] Program processing and behavior

[0986] 1. Data Acquisition and Analysis

[0987] The server ingests the author-specific work data and uses the Google Cloud Natural Language API to analyze the documents and extract features, providing the basis for training the author-specific model.

[0988] 2. Accepting and Parsing User Input

[0989] The user inputs the name of the author and the topic of conversation through the terminal, and this input data is sent from the terminal to the server.

[0990] An emotion recognition engine is used to recognize emotions from user input and analyze the input content.

[0991] 3. Generating a Response

[0992] Based on the user's input and emotional data, the server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response. For example, in response to the question "What do you think about the recent news?", it generates an answer that reflects the writer's thought patterns.

[0993] 4. Displaying responses and adjusting based on emotions

[0994] The generated response is displayed to the user via the device, and the user's reaction is also analyzed by the emotion recognition engine, and this feedback is reflected in the generation of the next response.

[0995] 5. Recommending related content

[0996] Based on the user's conversations and emotions, it recommends related books and documents, providing a more personalized experience for users.

[0997] Specific examples

[0998] Imagine a scenario in which a user interacts with a specific author on their smartphone. Here is an example of a specific prompt:

[0999] Prompt Sentence Examples

[1000] User: "Writer, what do you think about the recent news?"

[1001] System: (After sentiment analysis) "The world is undergoing a lot of change, but what matters is the quality and reliability of the information."

[1002] In this way, users can have an experience that feels as if they are having a conversation with the author themselves, and in the process, they can gain a wealth of knowledge by receiving recommendations for related content.

[1003] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1004] Program processing flow

[1005] Step-by-step explanation

[1006] Step 1:

[1007] The server takes in the author's work data and uses the Google Cloud Natural Language API to analyze the document and extract features. This feature data is stored in a database. The input is the author's work data, and the output is the analyzed feature data.

[1008] Step 2:

[1009] The user inputs the name of the author and the topic of conversation through the terminal. This input data is sent from the terminal to the server. The input is the user's text input, and the output is the data sent to the server.

[1010] Step 3:

[1011] The server uses an emotion recognition engine to recognize emotions from the user's input and analyzes the input content. The input is the user's text data, and the output is the analyzed emotion data and the input content.

[1012] Step 4:

[1013] The server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response based on the analyzed input and emotion data, with the input and emotion data as input and the generated response data as output.

[1014] Step 5:

[1015] The generated response is displayed to the user through the terminal. The input is the generated response data, and the output is the display data for the user.

[1016] Step 6:

[1017] The user's reaction is sent back to the server via the device, where it is analyzed by an emotion recognition engine. The input is the user's reaction data, and the output is the analyzed emotion data and the content of the reaction.

[1018] Step 7:

[1019] The server uses the analyzed user reaction data and emotion data as data to generate a new response. The reaction data and emotion data are input, and the data required to generate the next response is output.

[1020] Step 8:

[1021] The server recommends related content based on the user's dialogue and emotional data. For example, it recommends related books and documents based on the dialogue. The input is the dialogue and emotional data, and the output is a list of recommended content.

[1022] Through this process, users can interact with a specific author and gain a deeper understanding of that author's thought patterns and knowledge. They can also enjoy more natural interactions with emotional responses, and receive more relevant content recommendations, resulting in a more personalized experience.

[1023] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1024] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1025] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1026] [Fourth embodiment]

[1027] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1028] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1030] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1031] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1032] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1034] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1035] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1036] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1038] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1040] This invention is a system that incorporates the writing data of a specific best-selling author, and through dialogue with the user, provides the author's thought patterns and knowledge, ultimately aiming to change the user's behavior and decision-making. This system is implemented through processing between a server, a terminal, and the user.

[1041] Importing and analyzing copyright data

[1042] The server imports the author's work data into a database. Specifically, it collects text data such as books, papers, and essays, and analyzes the documents using natural language processing (NLP) technology. From the analyzed data, themes, writing style, frequently used expressions, and logical development patterns are extracted. This provides the basic data for training a specific author model.

[1043] Accepting and parsing user input

[1044] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." This input data is sent from the terminal to the server.

[1045] Call and response generation for writer models

[1046] The server analyzes the user's input and calls the corresponding author model. Based on the user's question and topic, the author model generates an appropriate response. The generated response reflects the author's thought patterns and writing style, making the user feel as if they are interacting with a specific author.

[1047] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[1048] Response display and feedback

[1049] The generated response is displayed to the user via the terminal, and the user can then input a new question or reaction based on the displayed response, such as "Do you have a more specific example?"

[1050] The server again analyzes the user's input and generates appropriate responses from the author model. This process repeats, allowing the user to continually gain a deeper understanding of a particular author's thought patterns and knowledge.

[1051] Continuous dialogue and learning outcomes

[1052] By continually using this system, users can acquire the thought patterns and knowledge of specific authors, which can bring about changes in their own behavior and decision-making. For example, they will naturally improve their news filtering ability and develop the habit of selecting only important information.

[1053] In this way, the present invention aims to efficiently provide author knowledge through dialogue with users, ultimately transforming their behavior and decision-making.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[1057] Step 2:

[1058] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[1059] Step 3:

[1060] The server uses the extracted features to train a writer model, which is a generative AI model that mimics the thought patterns and writing style of a particular author.

[1061] Step 4:

[1062] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[1063] Step 5:

[1064] The terminal transmits the user's input data to the server.

[1065] Step 6:

[1066] The server analyzes the user's input, calls the corresponding author model, and generates an appropriate response based on the user's question and topic.

[1067] Step 7:

[1068] The server sends the generated response to the terminal.

[1069] Step 8:

[1070] The terminal displays the received response on the user interface and provides it to the user.

[1071] Step 9:

[1072] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[1073] Step 10:

[1074] The terminal sends the user's new input to the server.

[1075] Step 11:

[1076] The server again parses the user's input and uses the author model to generate an appropriate response.

[1077] Step 12:

[1078] The server generates a new response and sends it to the terminal.

[1079] Step 13:

[1080] The terminal again displays the response in the user interface, providing information for the user to guide the next interaction.

[1081] Step 14:

[1082] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, which can bring about changes in their behavior and decision-making.

[1083] Example 1

[1084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1085] With conventional systems, it was difficult for users to learn the thought patterns and knowledge of a specific author through dialogue and then reflect that author's actions and decision-making. Furthermore, conventional systems lacked the ability to generate new responses for each user input, making it impossible to enhance learning through continuous dialogue.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1087] In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features, means for accepting user input, invoking a specific author model based on the input, and generating a response, means for displaying the generated response to the user, means for accepting user responses and continuously generating new responses based on the responses, means for preparing basic data for training different author models, and means for analyzing user input and generating appropriate responses based on different author models. This allows users to efficiently learn the thought patterns and knowledge of specific authors and realize continuous dialogue that reflects their own actions and decision-making.

[1088] The following are definitions of important terms contained in the claims.

[1089] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[1090] "Natural language processing technology" is a general term for technologies that enable computers to understand, process, and generate human language.

[1091] "Means for analyzing documents and extracting features" refers to methods and technologies for analyzing text data and extracting features such as themes, writing style, frequently occurring expressions, and logical development patterns.

[1092] "Means for accepting user input" refers to the interface that allows users to input the name of the author or topic they wish to discuss, and the method or technology for transmitting the input to the server.

[1093] "Means for invoking a specific writer model and generating a response" refers to a method or technology that uses a model that mimics the thought patterns and writing style of a pre-trained writer to generate an appropriate response to a user's input.

[1094] "Means for displaying the generated response to the user" refers to an interface or method for receiving the generated response from the server and visually presenting it to the user.

[1095] "Means for accepting user responses and continually generating new responses based on those responses" refers to methods and technologies for analyzing questions and responses re-entered by the user and generating appropriate responses again.

[1096] "Means for preparing basic data for training models of different authors" refers to methods and techniques for preparing data for training models that reflect the thought patterns and writing styles of different authors based on collected writing data.

[1097] "Means for analyzing user input and generating appropriate responses based on different writer models" refers to methods or techniques for analyzing the content of a user input, selecting the most appropriate writer model for it, and generating a response.

[1098] In this invention, the system is implemented using the following methods and techniques: The main components are a server, a terminal, and a user.

[1099] The server first collects the author's work data, which is retrieved using Python's "requests" library or an e-book API, and then stores the collected data in a relational database management system (RDBMS) such as MySQL or PostgreSQL.

[1100] The server then analyzes the stored author data using natural language processing (NLP) techniques. Specifically, it uses NLP libraries such as spaCy and the Natural Language Toolkit (NLTK). During this analysis, the data is tokenized, tagged with parts of speech, and analyzed for grammar. This allows for the extraction of themes, writing style, frequent phrases, and logical development patterns. The results of this analysis are used as the basis for training different author models.

[1101] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might say, "I want to talk about the news with a specific author." The device converts the input data into JSON format and sends it to the server via an HTTP POST request. HTTP is used as the communication protocol.

[1102] The server analyzes the received user input and selects a specific author model, which is pre-trained to mimic the author's unique thought patterns and writing style, and then uses a generative AI model (e.g., GPT-3) to generate the best response to the user-entered prompt.

[1103] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will invoke the appropriate author model and generate a response that says, "It's important to focus on the quality of the information and choose reliable sources."

[1104] This generated response is sent from the server to the terminal and displayed to the user. The user can then look at the displayed response and input a new question or response. For example, they can re-input "Do you have a more specific example?" This new input data is again sent to the server, which generates a new response.

[1105] By repeating this process, users can efficiently learn the thought patterns and knowledge of a particular author and ultimately reflect this in their own actions and decision-making. In this way, this invention aims to provide authors' knowledge through continuous dialogue with users and to change their decisions and behaviors.

[1106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1107] Step 1:

[1108] Data collection

[1109] The server collects the author's work data from the internet or e-book stores using APIs. The input here is the author's name and a request to obtain data such as books and papers. The server collects this using the "requests" library and obtains the work data in text format as output. Specifically, it sends an API request and saves the text data obtained as a response.

[1110] Step 2:

[1111] Saving to a database

[1112] The server stores the collected copyright data in a relational database management system (RDBMS) such as MySQL or PostgreSQL. The input is the text data collected in step 1, and the output is the data correctly stored in the database. Specific operations include connecting to the database, creating a table, and inserting data.

[1113] Step 3:

[1114] Natural Language Processing (NLP) Analysis

[1115] The server analyzes the stored data using NLP libraries such as "spaCy" and "Natural Language Toolkit (NLTK)." The input is text data retrieved from the database, and the output is feature extraction data as the analysis result. Specific operations include tokenization, morphological analysis, and grammatical analysis to extract themes, writing style, frequently occurring vocabulary, and logical development patterns.

[1116] Step 4:

[1117] Accepting user input

[1118] The user inputs the name of the author they want to talk to and the topic they want to talk about through their device. For example, they might input something like "I want to talk about the news with a specific author." The input is the data entered by the user, and the output is data converted into JSON format. Specific operations involve entering data into the input form and clicking the submit button.

[1119] Step 5:

[1120] Sending data

[1121] The terminal converts the user's input data into JSON format and sends it to the server via an HTTP POST request. The input is the user input data from step 4, and the output is the request to be sent to the server. Specific operations include converting the input data into JSON, and creating and sending an HTTP request.

[1122] Step 6:

[1123] Parsing user input

[1124] The server analyzes the received user input. The input is JSON format data sent from the terminal, and the output is the analyzed author name and topic. Specifically, it parses the JSON data and extracts the author name and topic.

[1125] Step 7:

[1126] Artist model selection

[1127] The server selects the corresponding author model based on the analysis results. The input is the author name and topic analyzed in step 6, and the output is the specified author model. Specifically, the server selects an appropriate model from multiple pre-trained author models.

[1128] Step 8:

[1129] Generating a response

[1130] The server uses a generative AI model to generate a response to the user's question. The input is the selected author model and the user's input prompt, and the output is the generated response. Specifically, the server invokes a generative AI model (e.g., GPT-3) to generate the optimal response to the prompt.

[1131] Step 9:

[1132] Viewing the response

[1133] The terminal displays the response sent by the server to the user. The input is the response generated by the server, and the output is the response visually presented to the user. Specific operations include receiving the response data and displaying it in a text view.

[1134] Step 10:

[1135] Accepting user responses and continuing dialogue

[1136] The user then enters a new question or response based on the displayed response. The input is the user's new input data, and the output is the data that is sent back to the server. Specific actions include re-entering data into the input form and clicking the submit button. By repeating this process, a continuous dialogue is achieved.

[1137] These specific processing steps allow users to efficiently learn the thought patterns and knowledge of specific authors through dialogue with them, which can positively influence their behavior and decision-making.

[1138] (Application example 1)

[1139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1140] Conventional interactive systems have had difficulty providing users with a realistic experience, as if they were conversing with a specific author. Furthermore, they have limitations in providing information that influences users' behavior and decisions, making it impossible to provide highly satisfying interactive content. There is a need to solve this problem and realize more advanced and interactive content delivery.

[1141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1142] In this invention, the server includes means for importing author work data, analyzing documents using natural language processing technology, and extracting features, means for accepting user input, calling a specific author model based on the input, and generating a response using a generative AI model, and means for displaying the generated response to the user. This provides a realistic experience as if the user were interacting with a specific author, making it possible to influence the user's behavior and decision-making.

[1143] "Author's work data" refers to text data such as books, papers, essays, etc. written by a particular author.

[1144] "Natural language processing technology" refers to all technologies that enable computers to understand, analyze, and generate natural language.

[1145] "Specific author model" refers to a generative AI model trained based on collected and analyzed author data.

[1146] A "generative AI model" refers to an artificial intelligence model that uses natural language processing technology to generate appropriate responses from input data.

[1147] "Means for generating a response" refers to methods and devices for using a generative AI model to create an appropriate response based on user input.

[1148] "User input" refers to text or voice input information entered by a user through a content distribution service terminal.

[1149] "User response" refers to new input or action by the user after receiving the generated response.

[1150] "Operation device" refers to a device that allows users to input or interact, such as a smartphone, smart glasses, or head-mounted display.

[1151] This invention is a system that incorporates the writing data of a specific author, provides the author's thought patterns and knowledge through dialogue with the user, and ultimately aims to change the user's behavior and decision-making. This system is realized mainly through processing between a server, a terminal, and the user.

[1152] Server Roles

[1153] The server collects the author's writing data and analyzes it using natural language processing technology. From the analyzed data, characteristics such as themes, writing style, frequently used expressions, and logical development patterns are extracted. Specifically, APIs and crawlers are used to collect the writing data and store it in a database. Natural language processing libraries such as spaCy are used for analysis. Furthermore, OpenAI's GPT-3 and other technologies are used to train author models based on the collected and analyzed data.

[1154] Device Role

[1155] The device is responsible for accepting input from the user and sending it to the server. The user enters the name of the author they want to talk to and the topic in text format. For example, they might say, "I want to talk about the news with a specific author." The device can be a smartphone, smart glasses, or a head-mounted display.

[1156] User Roles

[1157] The user is the subject of interactive content consumption, and engages in a dialogue with the artist through their device. The user receives responses generated by the server based on their input, and continues the dialogue by entering new questions and reactions.

[1158] Specific examples of processing

[1159] When a user types, "I'd like a specific author to give me advice on how to filter information," the server invokes the corresponding author model and generates a response such as, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, for example, "Do you have any more specific examples?", the server again uses the author model to generate a response such as, "For example, you might want to refer to reliable news sites or academic papers."

[1160] Prompt Sentence Examples

[1161] Below are some example prompts to input to the generative AI model:

[1162] Author Model: A specific author

[1163] User Input: Do you have any specific examples of writers?

[1164] Response:

[1165] Hardware and Software

[1166] Server: High-performance database and calculation servers are used to collect, store, and analyze data.

[1167] Natural language processing libraries: use spaCy and NLTK to parse documents.

[1168] Generative AI model: Leveraging OpenAI's GPT-3 to generate writer responses.

[1169] Device: A device that accepts user input and displays responses, such as a smartphone, smart glasses, or head-mounted display.

[1170] This makes it possible to virtually recreate the thought patterns and knowledge of an author and provide them to users through dialogue. Through an experience that makes users feel as if they are conversing with a specific author, users can acquire the thought patterns and knowledge and bring about changes in their behavior and decision-making.

[1171] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1172] Step 1: The server collects the author's work data and stores it in a database

[1173] The server collects the work data (books, papers, essays, etc.) of a particular author using APIs, crawlers, etc. This data is stored in a database. The input is the author's work data, and the output is the raw work data stored in the database.

[1174] Step 2: The server analyzes the copyright data using natural language processing technology

[1175] The server analyzes the collected author data using natural language processing libraries such as spaCy and NLTK, extracting features such as document themes, writing style, frequently used expressions, and logical development patterns. The input is the raw author data in the database, and the output is feature information of the analyzed author data.

[1176] Step 3: The server trains the generative AI model

[1177] The server trains a generative AI model, such as OpenAI's GPT-3, based on the analyzed author data's feature information. The input is the feature information, and the output is a specific author model.

[1178] Step 4: The user inputs the author name and topic they want to discuss into the terminal.

[1179] The user uses a device such as a smartphone or a head-mounted display to input the name of the author they want to interact with and the topic in text format. The input is the user's input data, and the output is request data sent to the server.

[1180] Step 5: The server invokes the author model based on the user's input and generates a response using the generative AI model.

[1181] The server analyzes the user's input, calls the corresponding specific author model, and then generates an appropriate response using a generative AI model. The input is the user's request data, and the output is the generated response data.

[1182] Step 6: The terminal displays the generated response to the user

[1183] The terminal displays the response data sent from the server to the user. The input is the response data sent from the server, and the output is text or audio displayed to the user.

[1184] Step 7: The user enters a new question or response, and the server generates a new response.

[1185] The user inputs a new question or reaction based on the displayed response. This input is sent back to the server, which then uses the generative AI model to generate a new response. The input is the user's new input data, and the output is the newly generated response data.

[1186] Step 8: This process repeats as the user continues to interact

[1187] The server and the terminal continuously execute a dialogue with the user, allowing the user to gain a deeper understanding of the thought patterns and knowledge of a particular author. The input is continuous user input data, and the output is continuously generated response data.

[1188] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1189] This system incorporates data on the works of specific best-selling authors and provides users with the author's thought patterns and knowledge through dialogue with them, combined with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[1190] Importing and analyzing copyright data

[1191] The server imports the author's work data and stores it in a database. This data includes books, papers, essays, etc. The imported data is analyzed using natural language processing (NLP) technology to extract themes, writing style, frequently used expressions, logical development patterns, etc. This provides the basic data for training the author model.

[1192] Accepting and parsing user input

[1193] The user inputs the name of the author they want to talk to and the topic they want to talk about through their terminal. For example, they might say, "I want to talk about the news with a specific author." The input data is sent from the terminal to the server.

[1194] Invoking the author model and emotion recognition

[1195] The server analyzes the user's input, calls the corresponding author model, and uses an emotion engine to recognize emotions from the user's input. It then generates an appropriate response based on the user's question, theme, and emotional state.

[1196] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call the corresponding author model, analyze the tone of the input, and respond with, "It's important to focus on the quality of the information and choose reliable sources."

[1197] Displaying responses and adjusting based on emotions

[1198] The generated response is displayed to the user via the device. The user's reaction is also analyzed by the emotion engine and reflected in the next response generation. For example, if the user further inputs, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, we recommend that you make it a habit to check a reliable news site only once a week."

[1199] Continuous dialogue and learning outcomes

[1200] By repeating this process, users can gain a deeper understanding of a particular author's thought patterns and knowledge, enabling more natural interactions through emotional responses. Continuing to respond to the user's emotional state can more easily bring about changes in the user's behavior and decision-making.

[1201] In this way, the present invention aims to efficiently provide authors' knowledge through dialogue that takes into account the user's emotions, and further to change the user's behavior and decision-making.

[1202] The processing flow will be explained below.

[1203] Step 1:

[1204] The server retrieves the author's work data and stores it in a database, including books, papers, essays, etc.

[1205] Step 2:

[1206] The server analyzes the imported copyright data using natural language processing technology. Specifically, it tokenizes the data, tags it with parts of speech, and analyzes sentence structure to extract themes, writing style, frequently used expressions, and patterns of logical development.

[1207] Step 3:

[1208] The server uses the extracted features to train a writer model, a generative AI model that mimics the thought patterns and writing style of a specific author.

[1209] Step 4:

[1210] The user inputs the name of the author they want to talk to and the topic they want to talk about into the terminal. For example, they can input "I want to talk about the news with a specific author."

[1211] Step 5:

[1212] The terminal transmits the user's input data to the server.

[1213] Step 6:

[1214] The server analyzes the user's input and uses an emotion engine to recognize emotions from the input. At the same time, it invokes the corresponding author model to generate an appropriate response based on the user's question, topic, and emotional state.

[1215] For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server analyzes the tone of the input and generates an appropriate response: "It's important to prioritize the quality of information and choose reliable sources."

[1216] Step 7:

[1217] The server sends the generated response to the terminal.

[1218] Step 8:

[1219] The terminal displays the received response on the user interface and provides it to the user.

[1220] Step 9:

[1221] The user reads the displayed response and types a new question or reaction into the terminal, for example, "Can you give us a more specific example?"

[1222] Step 10:

[1223] The terminal sends the user's new input to the server.

[1224] Step 11:

[1225] The server again analyzes the user's input and sentiment, and uses the writer model and emotion engine to generate an appropriate response, such as "We recommend that you make it a habit to check a trusted news site only once a week."

[1226] Step 12:

[1227] The server generates a new response and sends it to the terminal.

[1228] Step 13:

[1229] The terminal again displays the response in its user interface, providing information for the user to guide their next interaction.

[1230] Step 14:

[1231] By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and emotional responses enable a more natural dialogue. Continuing to respond to the user's emotional state can bring about changes in the user's behavior and decision-making.

[1232] Example 2

[1233] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1234] Conventional dialogue systems have the problem that it is difficult to model the thought patterns and knowledge of a specific author, and it is also difficult to generate flexible responses that correspond to the user's emotions. Furthermore, it is not possible to analyze the user's reactions and reflect them in the next response, making it difficult to achieve natural and sustainable dialogue.

[1235] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1236] In this invention, the server includes means for collecting authorship data of specific authors, analyzing documents using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; and means for recognizing emotions from the user input using an emotion engine. This enables natural and friendly dialogue that responds to the user's emotions by utilizing the thought patterns and knowledge of specific authors. Furthermore, by analyzing the user's reactions and reflecting them in the generation of the next response, it is possible to provide a sustainable and effective dialogue.

[1237] "Specified Author" refers to the author of the specified work with whom the user wishes to interact.

[1238] "Copyrighted data" refers to documents and text data created by a specific author, such as books, papers, and essays.

[1239] "Natural language processing technology" refers to technology that uses computers to understand, analyze, and generate natural human language.

[1240] "Document analysis" refers to the process of using natural language processing technology to analyze the content of a specific author's written data and extract features such as themes, writing style, frequently used expressions, and logical development patterns.

[1241] "Characteristics" refers to the author's unique document structure and style, such as themes, writing style, frequent expressions, and logical development patterns that appear in the work data of a particular author.

[1242] "User" refers to a person who interacts with the system.

[1243] "Author model" refers to a generative AI model that is trained to mimic the thought patterns and knowledge of a specific author based on their work data.

[1244] "Means for generating a response" refers to a process that generates an appropriate response using a particular authorship model based on user input.

[1245] An "emotion engine" is a technology that recognizes emotions from user input and adjusts the content and tone of responses accordingly.

[1246] "User response" refers to the user's feedback or re-input to the generated response.

[1247] "Means for recognizing emotions" refers to the process of extracting an emotional state from a user's input text using an emotion engine.

[1248] "Sustained interaction" refers to multiple consecutive interaction sessions with a user, where each interaction is appropriately adjusted based on previous responses and user reactions.

[1249] "Natural and friendly dialogue" refers to dialogue that provides appropriate responses according to the user's emotions and proceeds smoothly without any sense of discomfort to the user.

[1250] This system incorporates the copyright data of a specific author and provides the user with the author's thought patterns and knowledge through dialogue with the user, and combines it with an emotion engine that recognizes the user's emotions. This allows the system to adjust the content and tone of responses according to the user's emotions, enabling more natural and friendly dialogue.

[1251] Specifically, the server collects the writing data of a specific author and analyzes the document using natural language processing techniques (e.g., Python's NLTK or Spacy) to extract features such as themes, writing style, frequently used expressions, and logical development patterns. This information is then used to train a generative AI model (e.g., Hugging Face's Transformer model) to build a model that mimics the thinking and knowledge of the specific author.

[1252] The user inputs the name of the author they want to talk to and the topic they want to talk about (for example, a prompt such as "I want to talk to a specific author about the news" or "I want a specific author to give me advice on how to filter information.") The device sends this input data to the server, which analyzes it and calls the corresponding author model. Furthermore, it uses an emotion engine (for example, Google Cloud Natural Language API or Azure's Text Analytics) to recognize emotions from the user's input.

[1253] The server generates an appropriate response based on the user's question, topic, and emotional state. The generated response is displayed to the user via their device. For example, if a user types, "I'd like a specific author to give me advice on how to filter information," the server will call up the corresponding author model, analyze the tone of the input, and respond, "It's important to prioritize the quality of information and choose reliable sources." If the user also types, "Do you have any more specific examples?", the server will recognize the emotion from the user's input and respond, "For example, I recommend making it a habit to check reliable news sites only once a week."

[1254] The emotion engine also analyzes the user's reactions and reflects them in the next response generation. This allows the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, enabling more natural conversations through responses that correspond to the author's emotions.

[1255] Repeating this process brings about changes in the user's behavior and decision-making. This system efficiently provides knowledge of specific authors and contributes to changing the user's behavior through dialogue that takes into account the user's emotions.

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Step 1: Collecting and storing copyright data

[1258] Input: Collecting copyright data from specific author websites and online databases.

[1259] Specific operation: The server uses a web scraping tool (e.g., Python's BeautifulSoup) to collect authorship data (e.g., books, papers, essays) from the web for a specific author.

[1260] Data processing: Preprocessing the collected text data to make it easier for subsequent analysis, for example, removing unnecessary HTML tags and special characters.

[1261] Output: The preprocessed copyright data is stored in a database (e.g., MongoDB) in JSON format.

[1262] Step 2: Analyzing copyright data

[1263] Input: Copyright data saved in step 1.

[1264] Specific operation: The server analyzes the copyright data using natural language processing technology (e.g., Python's NLTK or Spacy).

[1265] Data processing: This analysis extracts themes, writing style, frequently used expressions, logical development patterns, etc. For example, it counts frequently used words and phrases and analyzes sentence structure.

[1266] Output: The extracted feature data is saved as training data for the generative AI model.

[1267] Step 3: Accepting User Input

[1268] Input: The author name and topic of conversation that the user wants to discuss, entered through the terminal.

[1269] Specific operation: The user enters the prompt "I would like to discuss the news with a specific author" into a form on a web browser.

[1270] Data operation: The terminal sends this prompt text to the server as an HTTP request.

[1271] Output: The server receives the user input and prepares it for analysis.

[1272] Step 4: Invoking the writer model and emotion recognition

[1273] Input: The user input data received in step 3.

[1274] How it works: The server analyzes the input data and calls the corresponding author model using the Hugging Face Transformer model, and then uses the Google Cloud Natural Language API for emotion recognition to analyze the user's emotions.

[1275] Data Computing: Extracting emotional states from user input text and integrating sentiment analysis and text analysis to generate responses.

[1276] Output: Response content and sentiment analysis data.

[1277] Step 5: Generate and display the response

[1278] Input: Response content and sentiment analysis data generated in step 4.

[1279] Specific operation: The server sends the generated response to the terminal as an HTTP response. The terminal displays the received response to the user.

[1280] Data calculation: Displaying responses and collecting user reactions.

[1281] Output: The response text displayed on the terminal.

[1282] Step 6: Analyzing user responses and generating the next response

[1283] Input: Any responses or follow-up questions the user enters in step 5.

[1284] Specific operation: When the user enters additional questions or responses, the device sends them back to the server, where the server analyzes the received responses using its emotion engine and reflects them in generating the next response.

[1285] Data calculation: Analyze user responses and update data for the next response. For example, use Scikit-learn to update a machine learning model based on the previous response and user responses.

[1286] Output: Next response and updated emotion data.

[1287] Step 7: Sustained dialogue and learning outcomes

[1288] Input: A continuous interactive session.

[1289] Specific operation: By repeating this process, the user gains a deeper understanding of the thought patterns and knowledge of a particular author, and the server learns the user's emotions and reactions to improve the accuracy of the dialogue.

[1290] Data calculation: Data obtained from each dialogue session is accumulated and used to generate responses in the future.

[1291] Output: Highly accurate, emotion-based responses and user learning effects.

[1292] (Application example 2)

[1293] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1294] Current content distribution services lack mechanisms that allow users to enjoy high-quality dialogue based on a specific author's thought patterns and knowledge. There is also a need for improved systems that can tailor the content and tone of responses to the user's emotions to provide a more natural and friendly dialogue. Furthermore, there is a need to provide a more personalized user experience by recommending related content based on the user's dialogue content and emotions.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for importing author work data, analyzing the document using natural language processing technology, and extracting features; means for accepting user input, invoking a specific author model based on the input, and generating a response; means for displaying the generated response to the user; means for accepting user reactions and continuously generating new responses based on the reactions; means for recognizing the user's emotions and adjusting the content and tone of the response; and means for recommending related content to the user. This not only enables the user to gain a deeper understanding of the thought patterns and knowledge of a specific author, but also allows the user to enjoy more natural dialogue through responses that correspond to their emotions. Furthermore, the user can receive recommendations of more relevant content, providing a personalized user experience.

[1296] definition statement

[1297] "Author's work data" refers to document data such as books, papers, essays, etc. written by an author.

[1298] "Natural language processing technology" is a technology that allows computers to analyze, generate, and understand human language.

[1299] A "specific author model" is a generative AI model trained to reproduce the thought patterns, writing style, and logical structure of a specific author.

[1300] "User input" means any text or voice inquiry or question that a user makes to the system.

[1301] A "means for generating a response" is a method or technique for generating an appropriate answer using the author model based on the user's input.

[1302] "Means for displaying to the user" refers to the interface or technology for displaying the generated response on the user's terminal.

[1303] "User response" refers to the user's responses and emotional reactions to the system.

[1304] A "means for continuously generating new responses" is a method or technology for continuously generating new responses based on user reactions.

[1305] "Means for recognizing emotions" refers to technologies or engines for analyzing emotions from a user's text or voice.

[1306] A "means for adjusting the content or tone of a response" is a method or technique for varying the content or tone of a response based on the perceived user sentiment.

[1307] "Means for recommending related content" refers to methods and technologies for recommending related books and documents based on the user's dialogue and emotions.

[1308] MODE FOR CARRYING OUT THE INVENTION

[1309] System Overview

[1310] The system incorporates the writings of a specific author and provides that author's thought patterns and knowledge through dialogue with the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the response accordingly, enabling a more natural and friendly dialogue.

[1311] Hardware and software used

[1312] Hardware

[1313] Server: for data storage and processing

[1314] Device: The user's smartphone or head-mounted display (HMD)

[1315] software

[1316] Natural language processing engine (e.g. Google Cloud Natural Language API)

[1317] Emotion recognition engine (e.g. Microsoft Azure Cognitive Services)

[1318] Generative AI models (e.g., OpenAI GPT-4)

[1319] Program processing and behavior

[1320] 1. Data Acquisition and Analysis

[1321] The server ingests the author-specific work data and uses the Google Cloud Natural Language API to analyze the documents and extract features, providing the basis for training the author-specific model.

[1322] 2. Accepting and Parsing User Input

[1323] The user inputs the name of the author and the topic of conversation through the terminal, and this input data is sent from the terminal to the server.

[1324] An emotion recognition engine is used to recognize emotions from user input and analyze the input content.

[1325] 3. Generating a Response

[1326] Based on the user's input and emotional data, the server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response. For example, in response to the question "What do you think about the recent news?", it generates an answer that reflects the writer's thought patterns.

[1327] 4. Displaying responses and adjusting based on emotions

[1328] The generated response is displayed to the user via the device, and the user's reaction is also analyzed by the emotion recognition engine, and this feedback is reflected in the generation of the next response.

[1329] 5. Recommending related content

[1330] Based on the user's conversations and emotions, it recommends related books and documents, providing a more personalized experience for users.

[1331] Specific examples

[1332] Imagine a scenario in which a user interacts with a specific author on their smartphone. Here is an example of a specific prompt:

[1333] Prompt Sentence Examples

[1334] User: "Writer, what do you think about the recent news?"

[1335] System: (After sentiment analysis) "The world is undergoing a lot of change, but what matters is the quality and reliability of the information."

[1336] In this way, users can have an experience that feels as if they are having a conversation with the author themselves, and in the process, they can gain a wealth of knowledge by receiving recommendations for related content.

[1337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1338] Program processing flow

[1339] Step-by-step explanation

[1340] Step 1:

[1341] The server takes in the author's work data and uses the Google Cloud Natural Language API to analyze the document and extract features. This feature data is stored in a database. The input is the author's work data, and the output is the analyzed feature data.

[1342] Step 2:

[1343] The user inputs the name of the author and the topic of conversation through the terminal. This input data is sent from the terminal to the server. The input is the user's text input, and the output is the data sent to the server.

[1344] Step 3:

[1345] The server uses an emotion recognition engine to recognize emotions from the user's input and analyzes the input content. The input is the user's text data, and the output is the analyzed emotion data and the input content.

[1346] Step 4:

[1347] The server invokes the OpenAI GPT-4 generative AI model to generate an appropriate response based on the analyzed input and emotion data, with the input and emotion data as input and the generated response data as output.

[1348] Step 5:

[1349] The generated response is displayed to the user through the terminal. The input is the generated response data, and the output is the display data for the user.

[1350] Step 6:

[1351] The user's reaction is sent back to the server via the device, where it is analyzed by an emotion recognition engine. The input is the user's reaction data, and the output is the analyzed emotion data and the content of the reaction.

[1352] Step 7:

[1353] The server uses the analyzed user reaction data and emotion data as data to generate a new response. The reaction data and emotion data are input, and the data required to generate the next response is output.

[1354] Step 8:

[1355] The server recommends related content based on the user's dialogue and emotional data. For example, it recommends related books and documents based on the dialogue. The input is the dialogue and emotional data, and the output is a list of recommended content.

[1356] Through this process, users can interact with a specific author and gain a deeper understanding of that author's thought patterns and knowledge. They can also enjoy more natural interactions with emotional responses, and receive more relevant content recommendations, resulting in a more personalized experience.

[1357] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1358] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1359] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1360] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1361] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1362] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1363] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1364] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1365] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1366] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1367] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1368] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1369] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1370] 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.

[1371] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1372] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1373] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1374] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1375] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1376] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1377] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1378] The following is further disclosed regarding the above embodiment.

[1379] (Claim 1)

[1380] A means of importing author's writing data, analyzing the document using natural language processing technology, and extracting features;

[1381] means for accepting user input and, based on the input, invoking a particular author model to generate a response;

[1382] a means for displaying the generated response to the user;

[1383] A means for receiving user responses and continually generating new responses based on the responses;

[1384] A system including:

[1385] (Claim 2)

[1386] 2. The system according to claim 1, further comprising means for analyzing the user's reaction and reflecting the analysis result in the next response generation.

[1387] (Claim 3)

[1388] 10. The system of claim 1, further comprising means for influencing user behavior or decision-making through interaction between the user and a particular author.

[1389] "Example 1"

[1390] (Claim 1)

[1391] A means of importing author's writing data, analyzing the document using natural language processing technology, and extracting features;

[1392] means for accepting user input and, based on the input, invoking a particular author model to generate a response;

[1393] a means for displaying the generated response to the user;

[1394] A means for receiving user responses and continually generating new responses based on the responses;

[1395] A means of preparing basic data for training different writer models;

[1396] means for parsing user input and generating appropriate responses based on different author models;

[1397] A system including:

[1398] (Claim 2)

[1399] 2. The system according to claim 1, further comprising means for analyzing the user's reaction and reflecting the analysis result in the next response generation.

[1400] (Claim 3)

[1401] 10. The system of claim 1, further comprising means for influencing user behavior or decision-making through interaction between the user and a particular author.

[1402] "Application Example 1"

[1403] (Claim 1)

[1404] A means of importing author's writing data, analyzing the document using natural language processing technology, and extracting features;

[1405] a means for accepting user input, invoking a specific author model based on the input, and generating a response using a generative AI model;

[1406] a means for displaying the generated response to the user;

[1407] A means for receiving user responses and continually generating new responses based on the responses;

[1408] a means for accepting input from a user's control device;

[1409] A system including:

[1410] (Claim 2)

[1411] 2. The system according to claim 1, further comprising means for analyzing the user's reaction and reflecting the analysis result in the next response generation.

[1412] (Claim 3)

[1413] 10. The system of claim 1, further comprising means for influencing user behavior or decision-making through interaction between the user and a particular author.

[1414] "Example 2: Combining Emotion Engines"

[1415] (Claim 1)

[1416] A means for collecting copyright data of a specific author, analyzing the document using natural language processing technology, and extracting features;

[1417] means for accepting user input and, based on the input, invoking a particular authorship model to generate a response;

[1418] means for recognizing emotions from a user's input using an emotion engine;

[1419] means for displaying the generated response to the user, accepting a response from the user, and continuing to generate new responses based on the response;

[1420] A system including:

[1421] (Claim 2)

[1422] 2. The system according to claim 1, further comprising means for analyzing the user's reaction and reflecting the analysis result in the next response generation.

[1423] (Claim 3)

[1424] 10. The system of claim 1, further comprising means for inducing a change in a user's behavior or decision-making through a user's interaction with a particular author.

[1425] "Application example 2 when combining emotion engines"

[1426] New Claims

[1427] (Claim 1)

[1428] A means of importing author's writing data, analyzing the document using natural language processing technology, and extracting features;

[1429] means for accepting user input and, based on the input, invoking a particular author model to generate a response;

[1430] a means for displaying the generated response to the user;

[1431] A means for receiving user responses and continually generating new responses based on the responses;

[1432] A way to recognize user emotions and tailor the content and tone of responses;

[1433] a means of recommending relevant content to users;

[1434] A system including:

[1435] (Claim 2)

[1436] 2. The system according to claim 1, further comprising means for analyzing the user's reaction and reflecting the analysis result in the next response generation.

[1437] (Claim 3)

[1438] 10. The system of claim 1, further comprising means for influencing user behavior or decision-making through interaction between the user and a particular author. [Explanation of symbols]

[1439] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of importing author's writing data, analyzing the document using natural language processing technology, and extracting features; means for accepting user input and, based on the input, invoking a particular author model to generate a response; a means for displaying the generated response to the user; A means for receiving user responses and continually generating new responses based on the responses; A system including:

2. 2. The system according to claim 1, further comprising means for analyzing the user's reaction and reflecting the analysis result in the generation of a next response.

3. 10. The system of claim 1, further comprising means for influencing user behavior and decision-making through user interaction with a particular author.

Images