system

Abstract

We provide the system. [Solution] A means for receiving user input and obtaining information about a specified author, work, and specific scene of a story, A means of analyzing the characteristics of the acquired authors and extracting their writing style and themes, Based on the aforementioned analysis results, a means for generating new story branches using a generative artificial intelligence model, A means of providing the generated story to the user terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, stories such as novels and manga usually have only one ending, and there is a problem that there is no means for readers to materialize other developments imagined by themselves. Also, there was no specific technology for readers to enjoy new story branches while maintaining the style of an author they are familiar with.

Means for Solving the Problems

[0005] This invention provides a system that analyzes the characteristics of a specified author and work based on user input and generates a new story branch accordingly. Specifically, it includes means for analyzing user input information and extracting the author's writing style and themes, and uses a generation artificial intelligence model based on the obtained analysis results to generate a new branch story. This generated story is then provided to the user terminal, realizing a means for the user to enjoy a different story.

[0006] "User input" refers to information provided by the user to the system to specify the author's name, the title of the work, and a particular scene from the story.

[0007] "Analyzing the author's characteristics" refers to the process of extracting characteristics such as writing style, themes, and expressions used from the past works of a specified author.

[0008] A "generative artificial intelligence model" is a pre-trained AI system used to automatically generate new story branches based on the author's characteristics.

[0009] "Story branching" refers to a new narrative path that unfolds based on different choices made from the original story.

[0010] A "user terminal" is a device used to display the generated story to the user, and generally includes computers, smartphones, and other similar devices.

[0011] "Collecting feedback" refers to the process of users providing opinions and impressions about the system and accumulating that data.

[0012] A "database" is an information management system that stores data on an author's past works and analysis results, and is used by systems to access them. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system of the present invention comprises a user, a server, and a terminal. The operation of the system will be described in detail below.

[0035] First, the user enters information via their device indicating their desire for a new story branching point in a work by a specific author. This information includes the author's name, the title of the work, and the scene where the story branching point is desired. This input is then sent from the device to the server.

[0036] Based on the information received, the server retrieves the corresponding author's work data from its internal database. The server uses natural language processing to analyze this work data and extract characteristics such as the author's writing style, themes, and methods of expression used.

[0037] Based on these analysis results, the server uses a generative artificial intelligence model to hypothesize different choices in the specified scenarios and generates a new story branch that the user desires. This model creates a sophisticated hypothetical story that takes into account the author's style and themes.

[0038] The generated story is formatted and then sent from the server to the user's device. The device then presents the new story in a viewable format. This allows the user to enjoy the work again, exploring the "what if" scenario.

[0039] As a concrete example, if a user requests a story in author A's work B where character C makes a different choice at a specific point, the system can generate and present a new development based on that request. This allows the user to experience something different from the original story. Through this process, the system realizes diverse narrative possibilities and provides users with a new reading experience.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses a terminal to input the author's name, the title of the work, and a specific scene into the system, indicating the desired branching of the story. This information is then sent from the terminal to the server.

[0043] Step 2:

[0044] The server accesses the database based on the received information and retrieves related works data for the specified author. During this process, it organizes and prepares the necessary data sets.

[0045] Step 3:

[0046] The server applies natural language processing technology to the acquired artwork data to analyze and extract author-specific characteristics such as writing style, themes, and methods of expression used.

[0047] Step 4:

[0048] The server sets generation conditions based on the analysis results and inputs these conditions into the generation artificial intelligence model. The model generates new story branches that take into account various choices in the specified scenario.

[0049] Step 5:

[0050] The server reviews the generated story, formats it as needed, and modifies it to make it easy for the user to read.

[0051] Step 6:

[0052] The server sends the output to the user's device, and the device presents the new story to the user. The user can then view and enjoy it.

[0053] Step 7:

[0054] Users can send their thoughts and feedback about the story content provided by the system via their devices, and the server collects this feedback and records it as data.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In recent years, many readers have expressed a desire to freely alter stories to suit their own expectations and enjoy new plot developments. Traditional systems designed to meet this demand struggle to generate new story branches that accurately mimic the author's intentions and style, requiring considerable time and effort. Furthermore, providing a wide range of options while maintaining story quality has been challenging.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for receiving user information and acquiring data relating to a specific author, work, and designated scene of a story; means for analyzing the acquired characteristics of the author and extracting expressive styles and concepts; and means for generating new story branches using a generative artificial intelligence model based on the analysis results. This allows for the rapid and efficient provision of new story branches while faithfully reproducing the author's style, enabling users to enjoy a variety of story possibilities.

[0060] "Users" refer to individuals or groups who operate the system and are entities that seek new branching paths in the narrative based on specific desires.

[0061] "Means of receiving information" refers to the process of receiving input from users and acquiring data related to specified authors, works, or specific scenes in stories.

[0062] "Means for analyzing the characteristics of authors and extracting their expressive style and concepts" refers to techniques for analyzing acquired works by authors and identifying their expressive and thematic characteristics.

[0063] A "generative artificial intelligence model" refers to an advanced algorithm used to generate new story branches based on given conditions and characteristics.

[0064] "Means of providing stories" refers to the process of presenting newly generated stories to users in a way that they can actually see.

[0065] "Natural language processing technology" is a general term for computer-based technologies used to analyze, understand, and generate text data.

[0066] An "information management system" refers to database technology built to organize data from multiple works and extract the characteristics of the author.

[0067] The system of the present invention comprises a user, a server, and a terminal. Specific embodiments are described below.

[0068] The user accesses a dedicated interface using their device and enters information indicating the desired branching point in the story. This information includes the author's name, the title of the work, and a specific story scene. The device aggregates this information and generates data packets to send to the server.

[0069] The server uses its internal management system to access a database based on the data received from the terminal and searches for the author's works. This database utilizes information management systems such as MongoDB or MySQL (registered trademark). Subsequently, the server uses natural language processing technology (for example, spaCy) to analyze and extract stylistic and thematic characteristics.

[0070] Once the analysis is complete, the server uses a generative artificial intelligence model (e.g., OpenAI's GPT model) to generate new story branches based on the user's requests. The generated stories are then formatted by the server and sent to the terminal. The terminal displays the received stories to the user, presenting the narrative in an easy-to-read format.

[0071] As a concrete example, a user might want a scenario where a character makes a different choice at a specific point in a particular work by a certain author. The AI ​​model on the server generates a new story based on this request. An example of a prompt would be, "Please generate a story where character Z makes choice V in scene W of author X's work Y."

[0072] Through this system, users can explore new possibilities for stories and enjoy diverse plot developments.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The user accesses a dedicated interface using a terminal and enters information indicating the desired branching point in the story. Specifically, they enter the author's name, the title of the work, and the specific scene in the story they wish to branch off from. The input form provides checks and auto-completion features to support user input. The terminal aggregates this information and generates data packets to send to the server. The input is processed as text data, and the output is structured data packets.

[0076] Step 2:

[0077] The server receives data packets sent from the terminal. Based on the received data, the server accesses its internal information management system to search for the works of a specified author. Here, it executes database queries using IDs and keywords to extract relevant data. The input is a data packet, and the output is a set of works data for the author.

[0078] Step 3:

[0079] The server analyzes the acquired artwork data using natural language processing techniques. Specifically, it uses spaCy to extract stylistic, expressive, and thematic features. This analysis clarifies the author's style and narrative structure. The input is the artwork data, and the output is a list of extracted features.

[0080] Step 4:

[0081] The server inputs prompts into the generating artificial intelligence model based on the analysis results, generating a new story branch. The OpenAI GPT model is used for generation, with the prompt being "Generate a story where character Z makes choice V in scene W, in author X's work Y." The AI ​​model follows this prompt and generates a new story development. The input consists of the prompt and a feature list, and the output is the newly generated story.

[0082] Step 5:

[0083] The server receives the generated story and formats it. This involves adjusting paragraphs, unifying fonts, and converting it into a readable format. The formatted story is then sent to the terminal. The input is the generated story, and the output is the formatted story data.

[0084] Step 6:

[0085] The device receives formatted story data sent from the server. The device then displays this data to the user, presenting it in an easy-to-read interface. The user can then read and enjoy this new story through the device. The input is the formatted story data, and the output is the user's viewing screen.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] When users desire unique story branching paths, traditional methods have made it difficult to generate new developments while maintaining the author's style. Furthermore, there has been a lack of efficient ways to deliver these new developments and allow users to experience them interactively. Therefore, there is a need for technology that can generate new stories tailored to the author's characteristics and enable users to experience them on their devices.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for receiving user requests and obtaining information about a specified creator, work, and specific scenes of a story; means for analyzing the obtained characteristics of the creator and extracting formatting and themes; and means for generating new story branches using a generation algorithm based on the analysis results. This enables users to enjoy an interactive story experience.

[0091] A "user" is an entity that provides information in order to enjoy new developments in the story using the system.

[0092] A "request" is the act of a user providing information to a specific creator or work expressing a desire for a new branching storyline.

[0093] The term "creator" refers to a writer or author who has created an original story.

[0094] A "work" is a book or digital content, whether a story or a form of expression, created by a creator.

[0095] A "story" refers to a plot that includes specific situations or scenes within a designated work.

[0096] An "information processing device" is an electronic device used by users to experience a story.

[0097] A "generative algorithm" is a computational method used to generate new story branches that suit the creator's style.

[0098] An "information aggregate" is a structure that aggregates data and is used when analyzing multiple works by a creator.

[0099] "Interactive" refers to a system that allows users to actively make choices and express their desires, enabling them to experience the story in a two-way manner.

[0100] The system for carrying out the present invention comprises a server and a terminal which is a user information processing device. The following process is performed for the user to have an interactive narrative experience through the terminal.

[0101] First, the user uses their device to input information about the creator, a specific work, and a scene from the story. The device then sends this information to the server.

[0102] The server retrieves creator data from its internal database based on information received from the user and analyzes it using natural language processing (NLP) techniques. Specifically, it extracts the creator's writing style, themes, and formatting. For this purpose, an NLP framework such as spaCy is used.

[0103] Next, based on the analyzed data, the server generates a new story branch using a generative AI model (for example, GPT-3®). In this generation process, prompt sentences corresponding to the user's request are input to the generative AI model, and a new story that matches the author's style is output.

[0104] Finally, the generated story is formatted and then sent from the server to the user's device. The user can then view this new story through their device. This allows them to experience a different choice from traditional stories and enjoy a new reading experience.

[0105] As a concrete example, if a user desires a different development in a particular story by a certain author, the story generated by the server will adhere to the original author's style. An example of a prompt to the generation AI model is as follows: "Generate a story for a specific scene in the specified work, where a different choice is made. Please ensure the development is in line with the creator's style."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] Users input information about the creator, the work, and specific scenes from the story through their device. The input data includes the creator's name, the title of the work, and the desired scene. This information is collected and sent from the device to the server.

[0109] Step 2:

[0110] The server retrieves the creator's artwork data from its internal database based on the received user information. The input is user information, and the output is the creator's artwork data retrieved through the search. The server efficiently performs database searches and extracts the relevant data.

[0111] Step 3:

[0112] The server performs natural language processing on the artwork data to analyze the creator's writing style, themes, and formatting. The input is the artwork data, and the output is the analyzed characteristics of the writing style and themes. This process uses an NLP framework (e.g., spaCy) to analyze the text data and extract features.

[0113] Step 4:

[0114] The server inputs prompt sentences into a generative AI model based on the analysis results, generating a new story branch. The input is the analysis results and the generated prompt sentences, and the output is the development of the new story. GPT-3 is one example of a generative AI model used here. The model generates content that meets the request based on the prompt sentences.

[0115] Step 5:

[0116] The server formats the newly generated story and prepares it for transmission to the terminal. The input is the newly generated story, and the output is the story formatted into a readable format. Paragraph divisions and character encoding adjustments are made at this stage.

[0117] Step 6:

[0118] The terminal displays new stories sent from the server to the user. The input is a formatted story, and the output is a screen display for the user. The terminal displays it clearly on the user's screen, allowing the user to experience the story interactively.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention provides a more personalized experience by incorporating an emotion engine into a system that generates new story branches based on information provided by the user and delivers them to the user. This system mainly consists of the user, server, and terminal.

[0121] First, the user inputs information via their device about an alternative story branch they wish to experience within a specific author's work. This information includes the author's name, the title of the work, and a specific scene from the story. This input information is then sent from the device to the server.

[0122] The server retrieves data on the corresponding author's works from the database based on the information received and analyzes the author's characteristics through natural language processing. Simultaneously, the server recognizes the user's current emotional state using an emotion engine. This is analyzed using the user's voice tone, entered text, or other interaction data.

[0123] Based on the analyzed author characteristics and the user's emotional state, the server utilizes a generative artificial intelligence model to generate new story branches that take the user's emotions into account. These stories are adjusted to best fit the user's emotions while maintaining the author's style.

[0124] The generated story is formatted and then sent from the server to the user's device. The device displays the emotionally sensitive new story to the user, who can then view and enjoy it.

[0125] For example, if a user is experiencing a sad or melancholic emotion, the system will generate a story that aligns with that emotion. In this way, the user can not only experience the original story but also gain a new experience that resonates with their own feelings. By providing a personalized story experience, this system can give users a deeper reading experience.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The user provides information to the system using their device, including the author's name, the title of the work, and the specific scene where they want to change the story branch. This information is then sent from the device to the server.

[0129] Step 2:

[0130] The server searches the database based on the received information and retrieves the work data of the specified author. This prepares the data relevant to the user's request.

[0131] Step 3:

[0132] The server applies natural language processing to the acquired artwork data, analyzing and extracting characteristics such as the author's writing style and themes. This forms the foundation for story generation.

[0133] Step 4:

[0134] Simultaneously, the server activates the emotion engine and analyzes the user's emotional state. This is done through user input data and interaction with the interface, with the aim of identifying the emotions the user is currently experiencing.

[0135] Step 5:

[0136] The server uses a generative artificial intelligence model to generate new story branches, taking into account the analyzed author's characteristics and the user's emotional state. During this process, the story is adjusted to fit the user's emotions.

[0137] Step 6:

[0138] The generated stories are formatted and styled on the server, and then adjusted to a visually easy-to-read format for users.

[0139] Step 7:

[0140] The server sends the final story to the user's device. The device then presents the received story to the user, who can then view and enjoy it.

[0141] Step 8:

[0142] Users can provide their thoughts and feedback on the presented story through their devices, and the server collects and records this feedback to use for future system improvements.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] Traditional story generation systems have faced the challenge of providing personalized experiences that reflect the individual emotional states of users. In particular, when users request specific story branching paths within a particular author or work, existing technologies have struggled to generate appropriate narratives that meet those requests.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes means for receiving user input and obtaining information about a specified author, work, and specific scenes of an event; means for generating new narrative branches using a generative artificial intelligence model based on the analyzed author's characteristics and the user's emotional state; and emotion analysis means for analyzing emotions using the user's voice tone or input text. This makes it possible to provide a personalized narrative experience that fits the user's emotions.

[0148] "User" refers to an individual who uses the system to input information and enjoy a narrative experience.

[0149] "Means of receiving input" refers to the interface or process for users to provide data via their devices and for acquiring that data.

[0150] The term "author" refers to the creator of a work, and the person whose writing style and themes are analyzed by the system.

[0151] "Work" refers to all content created by an author and is the data that is referenced in the process of generating a story.

[0152] An "event" refers to a specific scene or situation within the story, and it is an element that users can use to generate new story branches.

[0153] "Analysis methods" refer to algorithms and techniques used to extract specific features or themes from input data.

[0154] A "generative artificial intelligence model" is an AI technology used to generate new stories, referring to a system that creates content using natural language processing and machine learning.

[0155] "Story branching" refers to different story developments or sequels within existing works, and means new content generated in response to user requests.

[0156] "Terminal" refers to all devices used by users to access the system, including computers and smartphones.

[0157] "Emotional analysis methods" refer to processes and technologies for evaluating and recognizing a user's emotional state, and include methods for analyzing voice tone and text.

[0158] A description of the embodiment for carrying out the invention will be provided.

[0159] This invention is a system consisting of three main components: a user, a server, and a terminal. The detailed operation and role of each component are described below.

[0160] Users access the system using their personal devices and input information based on their interests and preferences. This information includes specific author names, work titles, and specific scenes from stories. The information users input may also include their current emotional state, which forms the basis for state analysis.

[0161] The terminal plays the role of properly transmitting information entered by the user to the server. While terminals can take various forms, they are generally devices such as computers and smartphones. In this process, the terminal often sends the input data as an HTTP request.

[0162] The server retrieves author data from a database based on the received information. Next, it uses natural language processing (NLP) to analyze the author's writing style and themes from the data. Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This emotion analysis is based on voice tone, input text, and other emotional expression data.

[0163] Based on the analysis results, the server generates a new narrative branch using a generative AI model. In this process, the AI ​​model uses "author name, work title, scene, and user's emotional state" as prompts to generate an appropriate story. The generated story maintains the author's style while resonating with the user's emotions.

[0164] Examples of specific prompt messages are as follows:

[0165] "Author: Taro Yamamoto, Title: Book of Adventures, Scene: The scene where the protagonist meets new companions."

[0166] Based on this prompt, the system can create a special story that matches the user's emotional state.

[0167] In this way, the present invention provides users with a personalized and immersive narrative experience.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The user uses their device to input information such as the author's name, the title of the work, and specific scenes from the story. This input serves as initial data for generating specific story branches. Specifically, this involves the user entering text using the device's keyboard or touch interface.

[0171] Step 2:

[0172] The terminal sends information entered by the user to the server. The terminal converts the information into an HTTP request format and sends it over the network. At this point, the input is the text data initially provided by the user, and the output is the data sent to reach the server.

[0173] Step 3:

[0174] Based on the received information, the server executes a query to retrieve the corresponding author's work data from the database. The input is the author information submitted by the user, and the output is the work data retrieved from the database. In this step, data retrieval is performed using SQL queries, etc.

[0175] Step 4:

[0176] The server analyzes the author's characteristics through natural language processing on the acquired data. Specifically, it uses NLP techniques to analyze text data and extract writing style and themes. In this step, the input is the work data acquired from the database, and the output is the analyzed information about the author's style and themes.

[0177] Step 5:

[0178] The server uses an emotion analysis engine to recognize the user's emotional state. Input is information such as voice tone and text input; the user's emotions are recognized based on the emotion analysis method, and the output is information about the user's emotional state. Specifically, this involves a process of classifying emotions using a machine learning model.

[0179] Step 6:

[0180] The server uses a generative AI model to generate new story branches based on the analyzed author characteristics and the user's emotional state. The input is writing style, theme, and user emotional information, and the output is the generated story branch. In this step, the AI ​​model generates an appropriate story by inputting prompt sentences.

[0181] Step 7:

[0182] The server formats the generated story and sends it to the user's terminal. The input is the generated story data, and the output is the formatted and sent story. The terminal displays the received story and includes actions to visually entertain the user.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0185] Traditional story delivery systems have struggled to provide story experiences that respond to the individual emotional states of users. Because they provide uniform content without considering user emotions, readers' experiences are limited, and there is a problem in that they cannot deliver personalized emotional experiences.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes means for using an emotion analysis engine to analyze the user's emotional state, means for generating a new, personalized story branch using a generative artificial intelligence model based on the analysis results and the emotion analysis results, and means for providing the generated story to the user terminal. This makes it possible to provide a personalized story experience that corresponds to the user's emotional state.

[0188] "Means for receiving user information input" refers to a function that provides an interface for users to input information about the story they want to experience into the system.

[0189] "Information about the specified author, work, and relevant scenes of the story" refers to data provided by the user regarding specific author names, work titles, and specific scenes from selected stories.

[0190] "Means for analyzing acquired author characteristics" refers to a function that extracts and analyzes characteristics such as the author's writing style and themes from a database.

[0191] "Style and themes" refer to the author's unique style and the fundamental ideas and themes that consistently run through their work.

[0192] A "sentiment analysis engine for analyzing a user's emotional state" is software that analyzes a user's emotions from sources such as voice tone and text input, and recognizes that emotional state.

[0193] A "generative artificial intelligence model" refers to a machine learning model that can generate new information or content based on the data provided.

[0194] "Methods for generating story branching" refers to a function that uses analytical data to construct new story developments tailored to the user's emotions.

[0195] "Means of providing generated stories to user terminals" refers to a function that transfers and displays newly created stories on the user's device.

[0196] The system of this invention consists of a user terminal, a server, and software that processes and generates data between them. The user terminal is provided with an interface for inputting information about the story the user wants to experience. The user can input information about a specified author, work, or specific scene.

[0197] The input information is sent to the server, which retrieves the author's work information from the database. Next, natural language processing is used to analyze the author's characteristics based on this work information. This involves using libraries and tools that perform text analysis (for example, NLTK or SpaCy).

[0198] Furthermore, to sense the user's emotional state, the server utilizes an emotion analysis engine. This engine performs voice and text analysis to recognize the user's emotions in real time, and uses services such as Google Cloud's emotion analysis API.

[0199] After analysis, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate new story branches based on the user's emotions and the analyzed author's style. This generation process is initiated by a prompt. An example of a specific prompt might be, "Generate a relaxed story development that matches the current emotions, using the specified author's style."

[0200] The generated story is automatically formatted and sent to the user's device. The user's device then displays the story, allowing them to continue the narrative experience. This system enables users to enjoy a more personalized storytelling experience that takes their emotions into account at any given moment.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The user uses their device to input information about the author, the work, and relevant scenes from the story. The entered data is collected using forms or voice input to clarify the user's intent. This information is then sent to the server for further processing.

[0204] Step 2:

[0205] Based on the information received, the server retrieves the corresponding author's work data from the database. The server uses SQL queries to search for entries for specific authors and works, and retrieves this data. This data then becomes the input for the subsequent natural language processing.

[0206] Step 3:

[0207] The server analyzes the acquired artwork data and performs natural language processing to extract the author's characteristics. Tools used here include libraries such as NLTK and SpaCy. This process tokenizes and tags the text of the artwork, identifying its style and themes. The results of this processing become crucial elemental data for story generation.

[0208] Step 4:

[0209] Simultaneously, the server activates an emotion analysis engine to analyze the user's emotional state from voice and text inputs. Using Google Cloud's emotion analysis API, it evaluates the emotional nuances of the user's voice tone and text, obtaining the user's current emotional state as output. This information serves as foundational data for shaping the generated story to best suit the user.

[0210] Step 5:

[0211] The server combines the analyzed characteristics and emotional state and generates new story branches using a generative AI model. Specifically, it manipulates generative AI such as OpenAI's GPT-3 using prompts. These prompts include specific instructions such as, "Generate a relaxed story development that matches the current emotion, in the style of the specified author." This process ensures that the output is an emotionally appropriate story while maintaining the originality of the work.

[0212] Step 6:

[0213] The server formats the generated story and adjusts it for display on the device. HTML or Markdown may be used to adjust the document format. This final story format is then sent to the user's terminal.

[0214] Step 7:

[0215] The user's device displays the received story, allowing the user to enjoy a personalized narrative experience. Appropriately laid-out text is displayed on the device's screen, and the user can freely turn pages or listen using the audio function.

[0216] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0217] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0218] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0222] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0223] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0224] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0225] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0226] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0227] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0228] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0229] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0230] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0231] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0232] The system of the present invention comprises a user, a server, and a terminal. The operation of the system will be described in detail below.

[0233] First, the user enters information via their device indicating their desire for a new story branching point in a work by a specific author. This information includes the author's name, the title of the work, and the scene where the story branching point is desired. This input is then sent from the device to the server.

[0234] Based on the information received, the server retrieves the corresponding author's work data from its internal database. The server uses natural language processing to analyze this work data and extract characteristics such as the author's writing style, themes, and methods of expression used.

[0235] Based on these analysis results, the server uses a generative artificial intelligence model to hypothesize different choices in the specified scenarios and generates a new story branch that the user desires. This model creates a sophisticated hypothetical story that takes into account the author's style and themes.

[0236] The generated story is formatted and then sent from the server to the user's device. The device then presents the new story in a viewable format. This allows the user to enjoy the work again, exploring the "what if" scenario.

[0237] As a concrete example, if a user requests a story in author A's work B where character C makes a different choice at a specific point, the system can generate and present a new development based on that request. This allows the user to experience something different from the original story. Through this process, the system realizes diverse narrative possibilities and provides users with a new reading experience.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user uses a terminal to input the author's name, the title of the work, and a specific scene into the system, indicating the desired branching of the story. This information is then sent from the terminal to the server.

[0241] Step 2:

[0242] The server accesses the database based on the received information and retrieves related works data for the specified author. During this process, it organizes and prepares the necessary data sets.

[0243] Step 3:

[0244] The server applies natural language processing technology to the acquired artwork data to analyze and extract author-specific characteristics such as writing style, themes, and methods of expression used.

[0245] Step 4:

[0246] The server sets generation conditions based on the analysis results and inputs these conditions into the generation artificial intelligence model. The model generates new story branches that take into account various choices in the specified scenario.

[0247] Step 5:

[0248] The server reviews the generated story, formats it as needed, and modifies it to make it easy for the user to read.

[0249] Step 6:

[0250] The server sends the output to the user's device, and the device presents the new story to the user. The user can then view and enjoy it.

[0251] Step 7:

[0252] Users can send their thoughts and feedback about the story content provided by the system via their devices, and the server collects this feedback and records it as data.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] In recent years, many readers have expressed a desire to freely alter stories to suit their own expectations and enjoy new plot developments. Traditional systems designed to meet this demand struggle to generate new story branches that accurately mimic the author's intentions and style, requiring considerable time and effort. Furthermore, providing a wide range of options while maintaining story quality has been challenging.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for receiving user information and acquiring data relating to a specific author, work, and designated scene of a story; means for analyzing the acquired characteristics of the author and extracting expressive styles and concepts; and means for generating new story branches using a generative artificial intelligence model based on the analysis results. This allows for the rapid and efficient provision of new story branches while faithfully reproducing the author's style, enabling users to enjoy a variety of story possibilities.

[0258] "Users" refer to individuals or groups who operate the system and are entities that seek new branching paths in the narrative based on specific desires.

[0259] "Means of receiving information" refers to the process of receiving input from users and acquiring data related to specified authors, works, or specific scenes in stories.

[0260] "Means for analyzing the characteristics of authors and extracting their expressive style and concepts" refers to techniques for analyzing acquired works by authors and identifying their expressive and thematic characteristics.

[0261] A "generative artificial intelligence model" refers to an advanced algorithm used to generate new story branches based on given conditions and characteristics.

[0262] "Means of providing stories" refers to the process of presenting newly generated stories to users in a way that they can actually see.

[0263] "Natural language processing technology" is a general term for computer-based technologies used to analyze, understand, and generate text data.

[0264] An "information management system" refers to database technology built to organize data from multiple works and extract the characteristics of the author.

[0265] The system of the present invention comprises a user, a server, and a terminal. Specific embodiments are described below.

[0266] The user accesses a dedicated interface using their device and enters information indicating the desired branching point in the story. This information includes the author's name, the title of the work, and a specific story scene. The device aggregates this information and generates data packets to send to the server.

[0267] The server uses its internal management system to access a database based on the data received from the terminal and searches for the author's works. This database utilizes information management systems such as MongoDB or MySQL. Subsequently, the server uses natural language processing technology (for example, spaCy) to analyze and extract stylistic and thematic characteristics.

[0268] Once the analysis is complete, the server uses a generative artificial intelligence model (e.g., OpenAI's GPT model) to generate new story branches based on the user's requests. The generated stories are then formatted by the server and sent to the terminal. The terminal displays the received stories to the user, presenting the narrative in an easy-to-read format.

[0269] As a concrete example, a user might want a scenario where a character makes a different choice at a specific point in a particular work by a certain author. The AI ​​model on the server generates a new story based on this request. An example of a prompt would be, "Please generate a story where character Z makes choice V in scene W of author X's work Y."

[0270] Through this system, users can explore new possibilities for stories and enjoy diverse plot developments.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The user accesses a dedicated interface using a terminal and enters information indicating the desired branching point in the story. Specifically, they enter the author's name, the title of the work, and the specific scene in the story they wish to branch off from. The input form provides checks and auto-completion features to support user input. The terminal aggregates this information and generates data packets to send to the server. The input is processed as text data, and the output is structured data packets.

[0274] Step 2:

[0275] The server receives data packets sent from the terminal. Based on the received data, the server accesses its internal information management system to search for the works of a specified author. Here, it executes database queries using IDs and keywords to extract relevant data. The input is a data packet, and the output is a set of works data for the author.

[0276] Step 3:

[0277] The server analyzes the acquired work data using natural language processing technology. Specifically, it uses spaCy to extract features of the style, expression, and theme. Through this analysis, the author's style and the structure of the story become clear. The input is the work data, and the output is a list of the extracted features.

[0278] Step 4:

[0279] The server inputs a prompt into the artificial intelligence model generated based on the analysis results to generate a new branch of the story. For the generation, the GPT model of OpenAI is used, and the prompt sentence "Please generate a story where in the work Y of author X, character Z makes choice V in scene W" is used. The AI model generates a new development of the story according to this prompt. The input is the prompt sentence and the feature list, and the output is the newly generated story.

[0280] Step 5:

[0281] The server receives the generated story and formats it. Here, adjustments to paragraphs, unification of fonts, and conversion to an easy-to-read form are performed. The formatted story is sent to the terminal. The input is the generated story, and the output is the formatted story data.

[0282] Step 6:

[0283] The terminal receives the formatted story data sent from the server. The terminal displays this to the user and presents it in an easy-to-read interface. The user can read and enjoy this new story through the terminal. The input is the formatted story data, and the output is the user's viewing screen.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] When a user desires an original story branch for a story, it has been difficult to generate a new development while maintaining the author's style with conventional methods. Also, there has been a lack of means to efficiently distribute it and enable the user to experience it interactively. Therefore, there is a demand for a technology that can newly generate a story that matches the characteristics of the author and allow the user to experience it on their terminal.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes means for receiving a user's request and acquiring information regarding a specified creator, work, and specific scene of a story; means for analyzing the acquired characteristics of the creator and extracting the format and theme; and means for generating a new story branch using a generation algorithm based on the analysis result. As a result, it becomes possible for the user to enjoy an interactive story experience.

[0289] A "user" is a subject that provides information in order to enjoy a new development of a story using the system.

[0290] A "request" is an act of providing information in which a user desires a new story branch for a specific creator or work.

[0291] A "creator" is a concept that refers to a writer or author who creates an original story.

[0292] A "work" is a book or digital content of a story or expression form created by a creator.

[0293] A "story" refers to a plot including specific situations or scenes within a specified work.

[0294] An "information processing device" is an electronic device used by a user for a story experience.

[0295] A "generative algorithm" is a computational method used to generate new story branches that suit the creator's style.

[0296] An "information aggregate" is a structure that aggregates data and is used when analyzing multiple works by a creator.

[0297] "Interactive" refers to a system that allows users to actively make choices and express their desires, enabling them to experience the story in a two-way manner.

[0298] The system for carrying out the present invention comprises a server and a terminal which is a user information processing device. The following process is performed for the user to have an interactive narrative experience through the terminal.

[0299] First, the user uses their device to input information about the creator, a specific work, and a scene from the story. The device then sends this information to the server.

[0300] The server retrieves creator data from its internal database based on information received from the user and analyzes it using natural language processing (NLP) techniques. Specifically, it extracts the creator's writing style, themes, and formatting. For this purpose, an NLP framework such as spaCy is used.

[0301] Next, based on the analyzed data, the server uses a generative AI model (GPT-3, for example) to generate a new story branch. In this generation process, prompt sentences corresponding to the user's request are input to the generative AI model, and a new story that matches the author's style is output.

[0302] Finally, the generated story is formatted and then sent from the server to the user's device. The user can then view this new story through their device. This allows them to experience a different choice from traditional stories and enjoy a new reading experience.

[0303] As a specific example, when a user hopes for a different development in a specific story of a certain author, the story generated by the server is based on the style of the original author. An example of a prompt sentence for the generation AI model is as follows. "Please generate a story when different choices are made in a specific scene of the specified work. Please make the development in line with the style of the creator."

[0304] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0305] Step 1:

[0306] The user inputs information regarding the creator, the work, and a specific scene of the story through the terminal. As input data, the user provides the creator's name, the work name, and the hope for a specific scene. This information is collected and sent from the terminal to the server.

[0307] Step 2:

[0308] Based on the received user information, the server retrieves the work data of the corresponding creator from the internal database. The input is the user information, and the output is the work data of the creator retrieved by the search. The server performs an efficient database search and extracts the corresponding data.

[0309] Step 3:

[0310] The server performs natural language processing on the work data and analyzes the style, theme, and format of the creator. The input is the work data, and the output is the analyzed style and theme features. For this process, an NLP framework (e.g., spaCy) is used to analyze the text data and extract features.

[0311] Step 4:

[0312] The server inputs prompt sentences into a generative AI model based on the analysis results, generating a new story branch. The input is the analysis results and the generated prompt sentences, and the output is the development of the new story. GPT-3 is one example of a generative AI model used here. The model generates content that meets the request based on the prompt sentences.

[0313] Step 5:

[0314] The server formats the newly generated story and prepares it for transmission to the terminal. The input is the newly generated story, and the output is the story formatted into a readable format. Paragraph divisions and character encoding adjustments are made at this stage.

[0315] Step 6:

[0316] The terminal displays new stories sent from the server to the user. The input is a formatted story, and the output is a screen display for the user. The terminal displays it clearly on the user's screen, allowing the user to experience the story interactively.

[0317] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0318] This invention provides a more personalized experience by incorporating an emotion engine into a system that generates new story branches based on information provided by the user and delivers them to the user. This system mainly consists of the user, server, and terminal.

[0319] First, the user inputs information via their device about an alternative story branch they wish to experience within a specific author's work. This information includes the author's name, the title of the work, and a specific scene from the story. This input information is then sent from the device to the server.

[0320] The server retrieves data on the corresponding author's works from the database based on the information received and analyzes the author's characteristics through natural language processing. Simultaneously, the server recognizes the user's current emotional state using an emotion engine. This is analyzed using the user's voice tone, entered text, or other interaction data.

[0321] Based on the analyzed author characteristics and the user's emotional state, the server utilizes a generative artificial intelligence model to generate new story branches that take the user's emotions into account. These stories are adjusted to best fit the user's emotions while maintaining the author's style.

[0322] The generated story is formatted and then sent from the server to the user's device. The device displays the emotionally sensitive new story to the user, who can then view and enjoy it.

[0323] For example, if a user is experiencing a sad or melancholic emotion, the system will generate a story that aligns with that emotion. In this way, the user can not only experience the original story but also gain a new experience that resonates with their own feelings. By providing a personalized story experience, this system can give users a deeper reading experience.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The user provides information to the system using their device, including the author's name, the title of the work, and the specific scene where they want to change the story branch. This information is then sent from the device to the server.

[0327] Step 2:

[0328] The server searches the database based on the received information and retrieves the work data of the specified author. This prepares the data relevant to the user's request.

[0329] Step 3:

[0330] The server applies natural language processing to the acquired artwork data, analyzing and extracting characteristics such as the author's writing style and themes. This forms the foundation for story generation.

[0331] Step 4:

[0332] Simultaneously, the server activates the emotion engine and analyzes the user's emotional state. This is done through user input data and interaction with the interface, with the aim of identifying the emotions the user is currently experiencing.

[0333] Step 5:

[0334] The server uses a generative artificial intelligence model to generate new story branches, taking into account the analyzed author's characteristics and the user's emotional state. During this process, the story is adjusted to fit the user's emotions.

[0335] Step 6:

[0336] The generated stories are formatted and styled on the server, and then adjusted to a visually easy-to-read format for users.

[0337] Step 7:

[0338] The server sends the final story to the user's device. The device then presents the received story to the user, who can then view and enjoy it.

[0339] Step 8:

[0340] Users can provide their thoughts and feedback on the presented story through their devices, and the server collects and records this feedback to use for future system improvements.

[0341] (Example 2)

[0342] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] Traditional story generation systems have faced the challenge of providing personalized experiences that reflect the individual emotional states of users. In particular, when users request specific story branching paths within a particular author or work, existing technologies have struggled to generate appropriate narratives that meet those requests.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for receiving user input and obtaining information about a specified author, work, and specific scenes of an event; means for generating new narrative branches using a generative artificial intelligence model based on the analyzed author's characteristics and the user's emotional state; and emotion analysis means for analyzing emotions using the user's voice tone or input text. This makes it possible to provide a personalized narrative experience that fits the user's emotions.

[0346] "User" refers to an individual who uses the system to input information and enjoy a narrative experience.

[0347] "Means of receiving input" refers to the interface or process for users to provide data via their devices and for acquiring that data.

[0348] The term "author" refers to the creator of a work, and the person whose writing style and themes are analyzed by the system.

[0349] "Work" refers to all content created by an author and is the data that is referenced in the process of generating a story.

[0350] An "event" refers to a specific scene or situation within the story, and it is an element that users can use to generate new story branches.

[0351] "Analysis methods" refer to algorithms and techniques used to extract specific features or themes from input data.

[0352] A "generative artificial intelligence model" is an AI technology used to generate new stories, referring to a system that creates content using natural language processing and machine learning.

[0353] "Story branching" refers to different story developments or sequels within existing works, and means new content generated in response to user requests.

[0354] "Terminal" refers to all devices used by users to access the system, including computers and smartphones.

[0355] "Emotional analysis methods" refer to processes and technologies for evaluating and recognizing a user's emotional state, and include methods for analyzing voice tone and text.

[0356] A description of the embodiment for carrying out the invention will be provided.

[0357] This invention is a system consisting of three main components: a user, a server, and a terminal. The detailed operation and role of each component are described below.

[0358] Users access the system using their personal devices and input information based on their interests and preferences. This information includes specific author names, work titles, and specific scenes from stories. The information users input may also include their current emotional state, which forms the basis for state analysis.

[0359] The terminal plays the role of properly transmitting information entered by the user to the server. While terminals can take various forms, they are generally devices such as computers and smartphones. In this process, the terminal often sends the input data as an HTTP request.

[0360] The server retrieves author data from a database based on the received information. Next, it uses natural language processing (NLP) to analyze the author's writing style and themes from the data. Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This emotion analysis is based on voice tone, input text, and other emotional expression data.

[0361] Based on the analysis results, the server generates a new narrative branch using a generative AI model. In this process, the AI ​​model uses "author name, work title, scene, and user's emotional state" as prompts to generate an appropriate story. The generated story maintains the author's style while resonating with the user's emotions.

[0362] Examples of specific prompt messages are as follows:

[0363] "Author: Taro Yamamoto, Title: Book of Adventures, Scene: The scene where the protagonist meets new companions."

[0364] Based on this prompt, the system can create a special story that matches the user's emotional state.

[0365] In this way, the present invention provides users with a personalized and immersive narrative experience.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] The user uses their device to input information such as the author's name, the title of the work, and specific scenes from the story. This input serves as initial data for generating specific story branches. Specifically, this involves the user entering text using the device's keyboard or touch interface.

[0369] Step 2:

[0370] The terminal sends information entered by the user to the server. The terminal converts the information into an HTTP request format and sends it over the network. At this point, the input is the text data initially provided by the user, and the output is the data sent to reach the server.

[0371] Step 3:

[0372] Based on the received information, the server executes a query to retrieve the corresponding author's work data from the database. The input is the author information submitted by the user, and the output is the work data retrieved from the database. In this step, data retrieval is performed using SQL queries, etc.

[0373] Step 4:

[0374] The server analyzes the author's characteristics through natural language processing on the acquired data. Specifically, it uses NLP techniques to analyze text data and extract writing style and themes. In this step, the input is the work data acquired from the database, and the output is the analyzed information about the author's style and themes.

[0375] Step 5:

[0376] The server uses an emotion analysis engine to recognize the user's emotional state. Input is information such as voice tone and text input; the user's emotions are recognized based on the emotion analysis method, and the output is information about the user's emotional state. Specifically, this involves a process of classifying emotions using a machine learning model.

[0377] Step 6:

[0378] The server uses a generative AI model to generate new story branches based on the analyzed author characteristics and the user's emotional state. The input is writing style, theme, and user emotional information, and the output is the generated story branch. In this step, the AI ​​model generates an appropriate story by inputting prompt sentences.

[0379] Step 7:

[0380] The server formats the generated story and sends it to the user's terminal. The input is the generated story data, and the output is the formatted and sent story. The terminal displays the received story and includes actions to visually entertain the user.

[0381] (Application Example 2)

[0382] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0383] Traditional story delivery systems have struggled to provide story experiences that respond to the individual emotional states of users. Because they provide uniform content without considering user emotions, readers' experiences are limited, and there is a problem in that they cannot deliver personalized emotional experiences.

[0384] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0385] In this invention, the server includes means for using an emotion analysis engine to analyze the user's emotional state, means for generating a new, personalized story branch using a generative artificial intelligence model based on the analysis results and the emotion analysis results, and means for providing the generated story to the user terminal. This makes it possible to provide a personalized story experience that corresponds to the user's emotional state.

[0386] "Means for receiving user information input" refers to a function that provides an interface for users to input information about the story they want to experience into the system.

[0387] "Information about the specified author, work, and relevant scenes of the story" refers to data provided by the user regarding specific author names, work titles, and specific scenes from selected stories.

[0388] "Means for analyzing acquired author characteristics" refers to a function that extracts and analyzes characteristics such as the author's writing style and themes from a database.

[0389] "Style and themes" refer to the author's unique style and the fundamental ideas and themes that consistently run through their work.

[0390] A "sentiment analysis engine for analyzing a user's emotional state" is software that analyzes a user's emotions from sources such as voice tone and text input, and recognizes that emotional state.

[0391] A "generative artificial intelligence model" refers to a machine learning model that can generate new information or content based on the data provided.

[0392] "Methods for generating story branching" refers to a function that uses analytical data to construct new story developments tailored to the user's emotions.

[0393] "Means of providing generated stories to user terminals" refers to a function that transfers and displays newly created stories on the user's device.

[0394] The system of this invention consists of a user terminal, a server, and software that processes and generates data between them. The user terminal is provided with an interface for inputting information about the story the user wants to experience. The user can input information about a specified author, work, or specific scene.

[0395] The input information is sent to the server, which retrieves the author's work information from the database. Next, natural language processing is used to analyze the author's characteristics based on this work information. This involves using libraries and tools that perform text analysis (for example, NLTK or SpaCy).

[0396] Furthermore, to sense the user's emotional state, the server utilizes an emotion analysis engine. This engine performs voice and text analysis to recognize the user's emotions in real time, and uses services such as Google Cloud's emotion analysis API.

[0397] After analysis, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate new story branches based on the user's emotions and the analyzed author's style. This generation process is initiated by a prompt. An example of a specific prompt might be, "Generate a relaxed story development that matches the current emotions, using the specified author's style."

[0398] The generated story is automatically formatted and sent to the user's device. The user's device then displays the story, allowing them to continue the narrative experience. This system enables users to enjoy a more personalized storytelling experience that takes their emotions into account at any given moment.

[0399] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0400] Step 1:

[0401] The user uses their device to input information about the author, the work, and relevant scenes from the story. The entered data is collected using forms or voice input to clarify the user's intent. This information is then sent to the server for further processing.

[0402] Step 2:

[0403] Based on the information received, the server retrieves the corresponding author's work data from the database. The server uses SQL queries to search for entries for specific authors and works, and retrieves this data. This data then becomes the input for the subsequent natural language processing.

[0404] Step 3:

[0405] The server analyzes the acquired artwork data and performs natural language processing to extract the author's characteristics. Tools used here include libraries such as NLTK and SpaCy. This process tokenizes and tags the text of the artwork, identifying its style and themes. The results of this processing become crucial elemental data for story generation.

[0406] Step 4:

[0407] Simultaneously, the server activates an emotion analysis engine to analyze the user's emotional state from voice and text inputs. Using Google Cloud's emotion analysis API, it evaluates the emotional nuances of the user's voice tone and text, obtaining the user's current emotional state as output. This information serves as foundational data for shaping the generated story to best suit the user.

[0408] Step 5:

[0409] The server combines the analyzed characteristics and emotional state and generates new story branches using a generative AI model. Specifically, it manipulates generative AI such as OpenAI's GPT-3 using prompts. These prompts include specific instructions such as, "Generate a relaxed story development that matches the current emotion, in the style of the specified author." This process ensures that the output is an emotionally appropriate story while maintaining the originality of the work.

[0410] Step 6:

[0411] The server formats the generated story and adjusts it for display on the device. HTML or Markdown may be used to adjust the document format. This final story format is then sent to the user's terminal.

[0412] Step 7:

[0413] The user's device displays the received story, allowing the user to enjoy a personalized narrative experience. Appropriately laid-out text is displayed on the device's screen, and the user can freely turn pages or listen using the audio function.

[0414] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0415] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0420] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0421] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0422] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0423] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0424] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0425] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0426] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0427] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0428] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0429] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0430] The system of the present invention comprises a user, a server, and a terminal. The operation of the system will be described in detail below.

[0431] First, the user enters information via their device indicating their desire for a new story branching point in a work by a specific author. This information includes the author's name, the title of the work, and the scene where the story branching point is desired. This input is then sent from the device to the server.

[0432] Based on the information received, the server retrieves the corresponding author's work data from its internal database. The server uses natural language processing to analyze this work data and extract characteristics such as the author's writing style, themes, and methods of expression used.

[0433] Based on these analysis results, the server uses a generative artificial intelligence model to hypothesize different choices in the specified scenarios and generates a new story branch that the user desires. This model creates a sophisticated hypothetical story that takes into account the author's style and themes.

[0434] The generated story is formatted and then sent from the server to the user's device. The device then presents the new story in a viewable format. This allows the user to enjoy the work again, exploring the "what if" scenario.

[0435] As a concrete example, if a user requests a story in author A's work B where character C makes a different choice at a specific point, the system can generate and present a new development based on that request. This allows the user to experience something different from the original story. Through this process, the system realizes diverse narrative possibilities and provides users with a new reading experience.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] The user uses a terminal to input the author's name, the title of the work, and a specific scene into the system, indicating the desired branching of the story. This information is then sent from the terminal to the server.

[0439] Step 2:

[0440] The server accesses the database based on the received information and retrieves related works data for the specified author. During this process, it organizes and prepares the necessary data sets.

[0441] Step 3:

[0442] The server applies natural language processing technology to the acquired artwork data to analyze and extract author-specific characteristics such as writing style, themes, and methods of expression used.

[0443] Step 4:

[0444] The server sets generation conditions based on the analysis results and inputs these conditions into the generation artificial intelligence model. The model generates new story branches that take into account various choices in the specified scenario.

[0445] Step 5:

[0446] The server reviews the generated story, formats it as needed, and modifies it to make it easy for the user to read.

[0447] Step 6:

[0448] The server sends the output to the user's device, and the device presents the new story to the user. The user can then view and enjoy it.

[0449] Step 7:

[0450] Users can send their thoughts and feedback about the story content provided by the system via their devices, and the server collects this feedback and records it as data.

[0451] (Example 1)

[0452] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0453] In recent years, many readers have expressed a desire to freely alter stories to suit their own expectations and enjoy new plot developments. Traditional systems designed to meet this demand struggle to generate new story branches that accurately mimic the author's intentions and style, requiring considerable time and effort. Furthermore, providing a wide range of options while maintaining story quality has been challenging.

[0454] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0455] In this invention, the server includes means for receiving user information and acquiring data relating to a specific author, work, and designated scene of a story; means for analyzing the acquired characteristics of the author and extracting expressive styles and concepts; and means for generating new story branches using a generative artificial intelligence model based on the analysis results. This allows for the rapid and efficient provision of new story branches while faithfully reproducing the author's style, enabling users to enjoy a variety of story possibilities.

[0456] "Users" refer to individuals or groups who operate the system and are entities that seek new branching paths in the narrative based on specific desires.

[0457] "Means of receiving information" refers to the process of receiving input from users and acquiring data related to specified authors, works, or specific scenes in stories.

[0458] "Means for analyzing the characteristics of authors and extracting their expressive style and concepts" refers to techniques for analyzing acquired works by authors and identifying their expressive and thematic characteristics.

[0459] A "generative artificial intelligence model" refers to an advanced algorithm used to generate new story branches based on given conditions and characteristics.

[0460] "Means of providing stories" refers to the process of presenting newly generated stories to users in a way that they can actually see.

[0461] "Natural language processing technology" is a general term for computer-based technologies used to analyze, understand, and generate text data.

[0462] An "information management system" refers to database technology built to organize data from multiple works and extract the characteristics of the author.

[0463] The system of the present invention comprises a user, a server, and a terminal. Specific embodiments are described below.

[0464] The user accesses a dedicated interface using their device and enters information indicating the desired branching point in the story. This information includes the author's name, the title of the work, and a specific story scene. The device aggregates this information and generates data packets to send to the server.

[0465] The server uses its internal management system to access a database based on the data received from the terminal and searches for the author's works. This database utilizes information management systems such as MongoDB or MySQL. Subsequently, the server uses natural language processing technology (for example, spaCy) to analyze and extract stylistic and thematic characteristics.

[0466] Once the analysis is complete, the server uses a generative artificial intelligence model (e.g., OpenAI's GPT model) to generate new story branches based on the user's requests. The generated stories are then formatted by the server and sent to the terminal. The terminal displays the received stories to the user, presenting the narrative in an easy-to-read format.

[0467] As a concrete example, a user might want a scenario where a character makes a different choice at a specific point in a particular work by a certain author. The AI ​​model on the server generates a new story based on this request. An example of a prompt would be, "Please generate a story where character Z makes choice V in scene W of author X's work Y."

[0468] Through this system, users can explore new possibilities for stories and enjoy diverse plot developments.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] The user accesses a dedicated interface using a terminal and enters information indicating the desired branching point in the story. Specifically, they enter the author's name, the title of the work, and the specific scene in the story they wish to branch off from. The input form provides checks and auto-completion features to support user input. The terminal aggregates this information and generates data packets to send to the server. The input is processed as text data, and the output is structured data packets.

[0472] Step 2:

[0473] The server receives data packets sent from the terminal. Based on the received data, the server accesses its internal information management system to search for the works of a specified author. Here, it executes database queries using IDs and keywords to extract relevant data. The input is a data packet, and the output is a set of works data for the author.

[0474] Step 3:

[0475] The server analyzes the acquired artwork data using natural language processing techniques. Specifically, it uses spaCy to extract stylistic, expressive, and thematic features. This analysis clarifies the author's style and narrative structure. The input is the artwork data, and the output is a list of extracted features.

[0476] Step 4:

[0477] The server inputs prompts into the generating artificial intelligence model based on the analysis results, generating a new story branch. The OpenAI GPT model is used for generation, with the prompt being "Generate a story where character Z makes choice V in scene W, in author X's work Y." The AI ​​model follows this prompt and generates a new story development. The input consists of the prompt and a feature list, and the output is the newly generated story.

[0478] Step 5:

[0479] The server receives the generated story and formats it. This involves adjusting paragraphs, unifying fonts, and converting it into a readable format. The formatted story is then sent to the terminal. The input is the generated story, and the output is the formatted story data.

[0480] Step 6:

[0481] The device receives formatted story data sent from the server. The device then displays this data to the user, presenting it in an easy-to-read interface. The user can then read and enjoy this new story through the device. The input is the formatted story data, and the output is the user's viewing screen.

[0482] (Application Example 1)

[0483] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0484] When users desire unique story branching paths, traditional methods have made it difficult to generate new developments while maintaining the author's style. Furthermore, there has been a lack of efficient ways to deliver these new developments and allow users to experience them interactively. Therefore, there is a need for technology that can generate new stories tailored to the author's characteristics and enable users to experience them on their devices.

[0485] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0486] In this invention, the server includes means for receiving user requests and obtaining information about a specified creator, work, and specific scenes of a story; means for analyzing the obtained characteristics of the creator and extracting formatting and themes; and means for generating new story branches using a generation algorithm based on the analysis results. This enables users to enjoy an interactive story experience.

[0487] A "user" is an entity that provides information in order to enjoy new developments in the story using the system.

[0488] A "request" is the act of a user providing information to a specific creator or work expressing a desire for a new branching storyline.

[0489] The term "creator" refers to a writer or author who has created an original story.

[0490] A "work" is a book or digital content, whether a story or a form of expression, created by a creator.

[0491] A "story" refers to a plot that includes specific situations or scenes within a designated work.

[0492] An "information processing device" is an electronic device used by users to experience a story.

[0493] A "generative algorithm" is a computational method used to generate new story branches that suit the creator's style.

[0494] An "information aggregate" is a structure that aggregates data and is used when analyzing multiple works by a creator.

[0495] "Interactive" refers to a system that allows users to actively make choices and express their desires, enabling them to experience the story in a two-way manner.

[0496] The system for carrying out the present invention comprises a server and a terminal which is a user information processing device. The following process is performed for the user to have an interactive narrative experience through the terminal.

[0497] First, the user uses their device to input information about the creator, a specific work, and a scene from the story. The device then sends this information to the server.

[0498] The server retrieves creator data from its internal database based on information received from the user and analyzes it using natural language processing (NLP) techniques. Specifically, it extracts the creator's writing style, themes, and formatting. For this purpose, an NLP framework such as spaCy is used.

[0499] Next, based on the analyzed data, the server uses a generative AI model (GPT-3, for example) to generate a new story branch. In this generation process, prompt sentences corresponding to the user's request are input to the generative AI model, and a new story that matches the author's style is output.

[0500] Finally, the generated story is formatted and then sent from the server to the user's device. The user can then view this new story through their device. This allows them to experience a different choice from traditional stories and enjoy a new reading experience.

[0501] As a concrete example, if a user desires a different development in a particular story by a certain author, the story generated by the server will adhere to the original author's style. An example of a prompt to the generation AI model is as follows: "Generate a story for a specific scene in the specified work, where a different choice is made. Please ensure the development is in line with the creator's style."

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] Users input information about the creator, the work, and specific scenes from the story through their device. The input data includes the creator's name, the title of the work, and the desired scene. This information is collected and sent from the device to the server.

[0505] Step 2:

[0506] The server retrieves the creator's artwork data from its internal database based on the received user information. The input is user information, and the output is the creator's artwork data retrieved through the search. The server efficiently performs database searches and extracts the relevant data.

[0507] Step 3:

[0508] The server performs natural language processing on the artwork data to analyze the creator's writing style, themes, and formatting. The input is the artwork data, and the output is the analyzed characteristics of the writing style and themes. This process uses an NLP framework (e.g., spaCy) to analyze the text data and extract features.

[0509] Step 4:

[0510] The server inputs prompt sentences into a generative AI model based on the analysis results, generating a new story branch. The input is the analysis results and the generated prompt sentences, and the output is the development of the new story. GPT-3 is one example of a generative AI model used here. The model generates content that meets the request based on the prompt sentences.

[0511] Step 5:

[0512] The server formats the newly generated story and prepares it for transmission to the terminal. The input is the newly generated story, and the output is the story formatted into a readable format. Paragraph divisions and character encoding adjustments are made at this stage.

[0513] Step 6:

[0514] The terminal displays new stories sent from the server to the user. The input is a formatted story, and the output is a screen display for the user. The terminal displays it clearly on the user's screen, allowing the user to experience the story interactively.

[0515] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0516] This invention provides a more personalized experience by incorporating an emotion engine into a system that generates new story branches based on information provided by the user and delivers them to the user. This system mainly consists of the user, server, and terminal.

[0517] First, the user inputs information via their device about an alternative story branch they wish to experience within a specific author's work. This information includes the author's name, the title of the work, and a specific scene from the story. This input information is then sent from the device to the server.

[0518] The server retrieves data on the corresponding author's works from the database based on the information received and analyzes the author's characteristics through natural language processing. Simultaneously, the server recognizes the user's current emotional state using an emotion engine. This is analyzed using the user's voice tone, entered text, or other interaction data.

[0519] Based on the analyzed author characteristics and the user's emotional state, the server utilizes a generative artificial intelligence model to generate new story branches that take the user's emotions into account. These stories are adjusted to best fit the user's emotions while maintaining the author's style.

[0520] The generated story is formatted and then sent from the server to the user's device. The device displays the emotionally sensitive new story to the user, who can then view and enjoy it.

[0521] For example, if a user is experiencing a sad or melancholic emotion, the system will generate a story that aligns with that emotion. In this way, the user can not only experience the original story but also gain a new experience that resonates with their own feelings. By providing a personalized story experience, this system can give users a deeper reading experience.

[0522] The following describes the processing flow.

[0523] Step 1:

[0524] The user provides information to the system using their device, including the author's name, the title of the work, and the specific scene where they want to change the story branch. This information is then sent from the device to the server.

[0525] Step 2:

[0526] The server searches the database based on the received information and retrieves the work data of the specified author. This prepares the data relevant to the user's request.

[0527] Step 3:

[0528] The server applies natural language processing to the acquired artwork data, analyzing and extracting characteristics such as the author's writing style and themes. This forms the foundation for story generation.

[0529] Step 4:

[0530] Simultaneously, the server activates the emotion engine and analyzes the user's emotional state. This is done through user input data and interaction with the interface, with the aim of identifying the emotions the user is currently experiencing.

[0531] Step 5:

[0532] The server uses a generative artificial intelligence model to generate new story branches, taking into account the analyzed author's characteristics and the user's emotional state. During this process, the story is adjusted to fit the user's emotions.

[0533] Step 6:

[0534] The generated stories are formatted and styled on the server, and then adjusted to a visually easy-to-read format for users.

[0535] Step 7:

[0536] The server sends the final story to the user's device. The device then presents the received story to the user, who can then view and enjoy it.

[0537] Step 8:

[0538] Users can provide their thoughts and feedback on the presented story through their devices, and the server collects and records this feedback to use for future system improvements.

[0539] (Example 2)

[0540] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0541] Traditional story generation systems have faced the challenge of providing personalized experiences that reflect the individual emotional states of users. In particular, when users request specific story branching paths within a particular author or work, existing technologies have struggled to generate appropriate narratives that meet those requests.

[0542] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0543] In this invention, the server includes means for receiving user input and obtaining information about a specified author, work, and specific scenes of an event; means for generating new narrative branches using a generative artificial intelligence model based on the analyzed author's characteristics and the user's emotional state; and emotion analysis means for analyzing emotions using the user's voice tone or input text. This makes it possible to provide a personalized narrative experience that fits the user's emotions.

[0544] "User" refers to an individual who uses the system to input information and enjoy a narrative experience.

[0545] "Means of receiving input" refers to the interface or process for users to provide data via their devices and for acquiring that data.

[0546] The term "author" refers to the creator of a work, and the person whose writing style and themes are analyzed by the system.

[0547] "Work" refers to all content created by an author and is the data that is referenced in the process of generating a story.

[0548] An "event" refers to a specific scene or situation within the story, and it is an element that users can use to generate new story branches.

[0549] "Analysis methods" refer to algorithms and techniques used to extract specific features or themes from input data.

[0550] A "generative artificial intelligence model" is an AI technology used to generate new stories, referring to a system that creates content using natural language processing and machine learning.

[0551] "Story branching" refers to different story developments or sequels within existing works, and means new content generated in response to user requests.

[0552] "Terminal" refers to all devices used by users to access the system, including computers and smartphones.

[0553] "Emotional analysis methods" refer to processes and technologies for evaluating and recognizing a user's emotional state, and include methods for analyzing voice tone and text.

[0554] A description of the embodiment for carrying out the invention will be provided.

[0555] This invention is a system consisting of three main components: a user, a server, and a terminal. The detailed operation and role of each component are described below.

[0556] Users access the system using their personal devices and input information based on their interests and preferences. This information includes specific author names, work titles, and specific scenes from stories. The information users input may also include their current emotional state, which forms the basis for state analysis.

[0557] The terminal plays the role of properly transmitting information entered by the user to the server. While terminals can take various forms, they are generally devices such as computers and smartphones. In this process, the terminal often sends the input data as an HTTP request.

[0558] The server retrieves author data from a database based on the received information. Next, it uses natural language processing (NLP) to analyze the author's writing style and themes from the data. Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This emotion analysis is based on voice tone, input text, and other emotional expression data.

[0559] Based on the analysis results, the server generates a new narrative branch using a generative AI model. In this process, the AI ​​model uses "author name, work title, scene, and user's emotional state" as prompts to generate an appropriate story. The generated story maintains the author's style while resonating with the user's emotions.

[0560] Examples of specific prompt messages are as follows:

[0561] "Author: Taro Yamamoto, Title: Book of Adventures, Scene: The scene where the protagonist meets new companions."

[0562] Based on this prompt, the system can create a special story that matches the user's emotional state.

[0563] In this way, the present invention provides users with a personalized and immersive narrative experience.

[0564] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0565] Step 1:

[0566] The user uses their device to input information such as the author's name, the title of the work, and specific scenes from the story. This input serves as initial data for generating specific story branches. Specifically, this involves the user entering text using the device's keyboard or touch interface.

[0567] Step 2:

[0568] The terminal sends information entered by the user to the server. The terminal converts the information into an HTTP request format and sends it over the network. At this point, the input is the text data initially provided by the user, and the output is the data sent to reach the server.

[0569] Step 3:

[0570] Based on the received information, the server executes a query to retrieve the corresponding author's work data from the database. The input is the author information submitted by the user, and the output is the work data retrieved from the database. In this step, data retrieval is performed using SQL queries, etc.

[0571] Step 4:

[0572] The server analyzes the author's characteristics through natural language processing on the acquired data. Specifically, it uses NLP techniques to analyze text data and extract writing style and themes. In this step, the input is the work data acquired from the database, and the output is the analyzed information about the author's style and themes.

[0573] Step 5:

[0574] The server uses an emotion analysis engine to recognize the user's emotional state. Input is information such as voice tone and text input; the user's emotions are recognized based on the emotion analysis method, and the output is information about the user's emotional state. Specifically, this involves a process of classifying emotions using a machine learning model.

[0575] Step 6:

[0576] The server uses a generative AI model to generate new story branches based on the analyzed author characteristics and the user's emotional state. The input is writing style, theme, and user emotional information, and the output is the generated story branch. In this step, the AI ​​model generates an appropriate story by inputting prompt sentences.

[0577] Step 7:

[0578] The server formats the generated story and sends it to the user's terminal. The input is the generated story data, and the output is the formatted and sent story. The terminal displays the received story and includes actions to visually entertain the user.

[0579] (Application Example 2)

[0580] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0581] Traditional story delivery systems have struggled to provide story experiences that respond to the individual emotional states of users. Because they provide uniform content without considering user emotions, readers' experiences are limited, and there is a problem in that they cannot deliver personalized emotional experiences.

[0582] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0583] In this invention, the server includes means for using an emotion analysis engine to analyze the user's emotional state, means for generating a new, personalized story branch using a generative artificial intelligence model based on the analysis results and the emotion analysis results, and means for providing the generated story to the user terminal. This makes it possible to provide a personalized story experience that corresponds to the user's emotional state.

[0584] "Means for receiving user information input" refers to a function that provides an interface for users to input information about the story they want to experience into the system.

[0585] "Information about the specified author, work, and relevant scenes of the story" refers to data provided by the user regarding specific author names, work titles, and specific scenes from selected stories.

[0586] "Means for analyzing acquired author characteristics" refers to a function that extracts and analyzes characteristics such as the author's writing style and themes from a database.

[0587] "Style and themes" refer to the author's unique style and the fundamental ideas and themes that consistently run through their work.

[0588] A "sentiment analysis engine for analyzing a user's emotional state" is software that analyzes a user's emotions from sources such as voice tone and text input, and recognizes that emotional state.

[0589] A "generative artificial intelligence model" refers to a machine learning model that can generate new information or content based on the data provided.

[0590] "Methods for generating story branching" refers to a function that uses analytical data to construct new story developments tailored to the user's emotions.

[0591] "Means of providing generated stories to user terminals" refers to a function that transfers and displays newly created stories on the user's device.

[0592] The system of this invention consists of a user terminal, a server, and software that processes and generates data between them. The user terminal is provided with an interface for inputting information about the story the user wants to experience. The user can input information about a specified author, work, or specific scene.

[0593] The input information is sent to the server, which retrieves the author's work information from the database. Next, natural language processing is used to analyze the author's characteristics based on this work information. This involves using libraries and tools that perform text analysis (for example, NLTK or SpaCy).

[0594] Furthermore, to sense the user's emotional state, the server utilizes an emotion analysis engine. This engine performs voice and text analysis to recognize the user's emotions in real time, and uses services such as Google Cloud's emotion analysis API.

[0595] After analysis, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate new story branches based on the user's emotions and the analyzed author's style. This generation process is initiated by a prompt. An example of a specific prompt might be, "Generate a relaxed story development that matches the current emotions, using the specified author's style."

[0596] The generated story is automatically formatted and sent to the user's device. The user's device then displays the story, allowing them to continue the narrative experience. This system enables users to enjoy a more personalized storytelling experience that takes their emotions into account at any given moment.

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] The user uses their device to input information about the author, the work, and relevant scenes from the story. The entered data is collected using forms or voice input to clarify the user's intent. This information is then sent to the server for further processing.

[0600] Step 2:

[0601] Based on the information received, the server retrieves the corresponding author's work data from the database. The server uses SQL queries to search for entries for specific authors and works, and retrieves this data. This data then becomes the input for the subsequent natural language processing.

[0602] Step 3:

[0603] The server analyzes the acquired artwork data and performs natural language processing to extract the author's characteristics. Tools used here include libraries such as NLTK and SpaCy. This process tokenizes and tags the text of the artwork, identifying its style and themes. The results of this processing become crucial elemental data for story generation.

[0604] Step 4:

[0605] Simultaneously, the server activates an emotion analysis engine to analyze the user's emotional state from voice and text inputs. Using Google Cloud's emotion analysis API, it evaluates the emotional nuances of the user's voice tone and text, obtaining the user's current emotional state as output. This information serves as foundational data for shaping the generated story to best suit the user.

[0606] Step 5:

[0607] The server combines the analyzed characteristics and emotional state and generates new story branches using a generative AI model. Specifically, it manipulates generative AI such as OpenAI's GPT-3 using prompts. These prompts include specific instructions such as, "Generate a relaxed story development that matches the current emotion, in the style of the specified author." This process ensures that the output is an emotionally appropriate story while maintaining the originality of the work.

[0608] Step 6:

[0609] The server formats the generated story and adjusts it for display on the device. HTML or Markdown may be used to adjust the document format. This final story format is then sent to the user's terminal.

[0610] Step 7:

[0611] The user's device displays the received story, allowing the user to enjoy a personalized narrative experience. Appropriately laid-out text is displayed on the device's screen, and the user can freely turn pages or listen using the audio function.

[0612] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0613] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0614] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0615] [Fourth Embodiment]

[0616] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0617] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0618] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0619] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0620] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0621] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0622] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0623] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0624] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0625] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0626] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0627] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0628] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0629] The system of the present invention comprises a user, a server, and a terminal. The operation of the system will be described in detail below.

[0630] First, the user enters information via their device indicating their desire for a new story branching point in a work by a specific author. This information includes the author's name, the title of the work, and the scene where the story branching point is desired. This input is then sent from the device to the server.

[0631] Based on the information received, the server retrieves the corresponding author's work data from its internal database. The server uses natural language processing to analyze this work data and extract characteristics such as the author's writing style, themes, and methods of expression used.

[0632] Based on these analysis results, the server uses a generative artificial intelligence model to hypothesize different choices in the specified scenarios and generates a new story branch that the user desires. This model creates a sophisticated hypothetical story that takes into account the author's style and themes.

[0633] The generated story is formatted and then sent from the server to the user's device. The device then presents the new story in a viewable format. This allows the user to enjoy the work again, exploring the "what if" scenario.

[0634] As a concrete example, if a user requests a story in author A's work B where character C makes a different choice at a specific point, the system can generate and present a new development based on that request. This allows the user to experience something different from the original story. Through this process, the system realizes diverse narrative possibilities and provides users with a new reading experience.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The user uses a terminal to input the author's name, the title of the work, and a specific scene into the system, indicating the desired branching of the story. This information is then sent from the terminal to the server.

[0638] Step 2:

[0639] The server accesses the database based on the received information and retrieves related works data for the specified author. During this process, it organizes and prepares the necessary data sets.

[0640] Step 3:

[0641] The server applies natural language processing technology to the acquired artwork data to analyze and extract author-specific characteristics such as writing style, themes, and methods of expression used.

[0642] Step 4:

[0643] The server sets generation conditions based on the analysis results and inputs these conditions into the generation artificial intelligence model. The model generates new story branches that take into account various choices in the specified scenario.

[0644] Step 5:

[0645] The server reviews the generated story, formats it as needed, and modifies it to make it easy for the user to read.

[0646] Step 6:

[0647] The server sends the output to the user's device, and the device presents the new story to the user. The user can then view and enjoy it.

[0648] Step 7:

[0649] Users can send their thoughts and feedback about the story content provided by the system via their devices, and the server collects this feedback and records it as data.

[0650] (Example 1)

[0651] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0652] In recent years, many readers have expressed a desire to freely alter stories to suit their own expectations and enjoy new plot developments. Traditional systems designed to meet this demand struggle to generate new story branches that accurately mimic the author's intentions and style, requiring considerable time and effort. Furthermore, providing a wide range of options while maintaining story quality has been challenging.

[0653] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0654] In this invention, the server includes means for receiving user information and acquiring data relating to a specific author, work, and designated scene of a story; means for analyzing the acquired characteristics of the author and extracting expressive styles and concepts; and means for generating new story branches using a generative artificial intelligence model based on the analysis results. This allows for the rapid and efficient provision of new story branches while faithfully reproducing the author's style, enabling users to enjoy a variety of story possibilities.

[0655] "Users" refer to individuals or groups who operate the system and are entities that seek new branching paths in the narrative based on specific desires.

[0656] "Means of receiving information" refers to the process of receiving input from users and acquiring data related to specified authors, works, or specific scenes in stories.

[0657] "Means for analyzing the characteristics of authors and extracting their expressive style and concepts" refers to techniques for analyzing acquired works by authors and identifying their expressive and thematic characteristics.

[0658] A "generative artificial intelligence model" refers to an advanced algorithm used to generate new story branches based on given conditions and characteristics.

[0659] "Means of providing stories" refers to the process of presenting newly generated stories to users in a way that they can actually see.

[0660] "Natural language processing technology" is a general term for computer-based technologies used to analyze, understand, and generate text data.

[0661] An "information management system" refers to database technology built to organize data from multiple works and extract the characteristics of the author.

[0662] The system of the present invention comprises a user, a server, and a terminal. Specific embodiments are described below.

[0663] The user accesses a dedicated interface using their device and enters information indicating the desired branching point in the story. This information includes the author's name, the title of the work, and a specific story scene. The device aggregates this information and generates data packets to send to the server.

[0664] The server uses its internal management system to access a database based on the data received from the terminal and searches for the author's works. This database utilizes information management systems such as MongoDB or MySQL. Subsequently, the server uses natural language processing technology (for example, spaCy) to analyze and extract stylistic and thematic characteristics.

[0665] Once the analysis is complete, the server uses a generative artificial intelligence model (e.g., OpenAI's GPT model) to generate new story branches based on the user's requests. The generated stories are then formatted by the server and sent to the terminal. The terminal displays the received stories to the user, presenting the narrative in an easy-to-read format.

[0666] As a concrete example, a user might want a scenario where a character makes a different choice at a specific point in a particular work by a certain author. The AI ​​model on the server generates a new story based on this request. An example of a prompt would be, "Please generate a story where character Z makes choice V in scene W of author X's work Y."

[0667] Through this system, users can explore new possibilities for stories and enjoy diverse plot developments.

[0668] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0669] Step 1:

[0670] The user accesses a dedicated interface using a terminal and enters information indicating the desired branching point in the story. Specifically, they enter the author's name, the title of the work, and the specific scene in the story they wish to branch off from. The input form provides checks and auto-completion features to support user input. The terminal aggregates this information and generates data packets to send to the server. The input is processed as text data, and the output is structured data packets.

[0671] Step 2:

[0672] The server receives data packets sent from the terminal. Based on the received data, the server accesses its internal information management system to search for the works of a specified author. Here, it executes database queries using IDs and keywords to extract relevant data. The input is a data packet, and the output is a set of works data for the author.

[0673] Step 3:

[0674] The server analyzes the acquired artwork data using natural language processing techniques. Specifically, it uses spaCy to extract stylistic, expressive, and thematic features. This analysis clarifies the author's style and narrative structure. The input is the artwork data, and the output is a list of extracted features.

[0675] Step 4:

[0676] The server inputs prompts into the generating artificial intelligence model based on the analysis results, generating a new story branch. The OpenAI GPT model is used for generation, with the prompt being "Generate a story where character Z makes choice V in scene W, in author X's work Y." The AI ​​model follows this prompt and generates a new story development. The input consists of the prompt and a feature list, and the output is the newly generated story.

[0677] Step 5:

[0678] The server receives the generated story and formats it. This involves adjusting paragraphs, unifying fonts, and converting it into a readable format. The formatted story is then sent to the terminal. The input is the generated story, and the output is the formatted story data.

[0679] Step 6:

[0680] The device receives formatted story data sent from the server. The device then displays this data to the user, presenting it in an easy-to-read interface. The user can then read and enjoy this new story through the device. The input is the formatted story data, and the output is the user's viewing screen.

[0681] (Application Example 1)

[0682] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0683] When users desire unique story branching paths, traditional methods have made it difficult to generate new developments while maintaining the author's style. Furthermore, there has been a lack of efficient ways to deliver these new developments and allow users to experience them interactively. Therefore, there is a need for technology that can generate new stories tailored to the author's characteristics and enable users to experience them on their devices.

[0684] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0685] In this invention, the server includes means for receiving user requests and obtaining information about a specified creator, work, and specific scenes of a story; means for analyzing the obtained characteristics of the creator and extracting formatting and themes; and means for generating new story branches using a generation algorithm based on the analysis results. This enables users to enjoy an interactive story experience.

[0686] A "user" is an entity that provides information in order to enjoy new developments in the story using the system.

[0687] A "request" is the act of a user providing information to a specific creator or work expressing a desire for a new branching storyline.

[0688] The term "creator" refers to a writer or author who has created an original story.

[0689] A "work" is a book or digital content, whether a story or a form of expression, created by a creator.

[0690] A "story" refers to a plot that includes specific situations or scenes within a designated work.

[0691] An "information processing device" is an electronic device used by users to experience a story.

[0692] A "generative algorithm" is a computational method used to generate new story branches that suit the creator's style.

[0693] An "information aggregate" is a structure that aggregates data and is used when analyzing multiple works by a creator.

[0694] "Interactive" refers to a system that allows users to actively make choices and express their desires, enabling them to experience the story in a two-way manner.

[0695] The system for carrying out the present invention comprises a server and a terminal which is a user information processing device. The following process is performed for the user to have an interactive narrative experience through the terminal.

[0696] First, the user uses their device to input information about the creator, a specific work, and a scene from the story. The device then sends this information to the server.

[0697] The server retrieves creator data from its internal database based on information received from the user and analyzes it using natural language processing (NLP) techniques. Specifically, it extracts the creator's writing style, themes, and formatting. For this purpose, an NLP framework such as spaCy is used.

[0698] Next, based on the analyzed data, the server uses a generative AI model (GPT-3, for example) to generate a new story branch. In this generation process, prompt sentences corresponding to the user's request are input to the generative AI model, and a new story that matches the author's style is output.

[0699] Finally, the generated story is formatted and then sent from the server to the user's device. The user can then view this new story through their device. This allows them to experience a different choice from traditional stories and enjoy a new reading experience.

[0700] As a concrete example, if a user desires a different development in a particular story by a certain author, the story generated by the server will adhere to the original author's style. An example of a prompt to the generation AI model is as follows: "Generate a story for a specific scene in the specified work, where a different choice is made. Please ensure the development is in line with the creator's style."

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] Users input information about the creator, the work, and specific scenes from the story through their device. The input data includes the creator's name, the title of the work, and the desired scene. This information is collected and sent from the device to the server.

[0704] Step 2:

[0705] The server retrieves the creator's artwork data from its internal database based on the received user information. The input is user information, and the output is the creator's artwork data retrieved through the search. The server efficiently performs database searches and extracts the relevant data.

[0706] Step 3:

[0707] The server performs natural language processing on the artwork data to analyze the creator's writing style, themes, and formatting. The input is the artwork data, and the output is the analyzed characteristics of the writing style and themes. This process uses an NLP framework (e.g., spaCy) to analyze the text data and extract features.

[0708] Step 4:

[0709] The server inputs prompt sentences into a generative AI model based on the analysis results, generating a new story branch. The input is the analysis results and the generated prompt sentences, and the output is the development of the new story. GPT-3 is one example of a generative AI model used here. The model generates content that meets the request based on the prompt sentences.

[0710] Step 5:

[0711] The server formats the newly generated story and prepares it for transmission to the terminal. The input is the newly generated story, and the output is the story formatted into a readable format. Paragraph divisions and character encoding adjustments are made at this stage.

[0712] Step 6:

[0713] The terminal displays new stories sent from the server to the user. The input is a formatted story, and the output is a screen display for the user. The terminal displays it clearly on the user's screen, allowing the user to experience the story interactively.

[0714] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0715] This invention provides a more personalized experience by incorporating an emotion engine into a system that generates new story branches based on information provided by the user and delivers them to the user. This system mainly consists of the user, server, and terminal.

[0716] First, the user inputs information via their device about an alternative story branch they wish to experience within a specific author's work. This information includes the author's name, the title of the work, and a specific scene from the story. This input information is then sent from the device to the server.

[0717] The server retrieves data on the corresponding author's works from the database based on the information received and analyzes the author's characteristics through natural language processing. Simultaneously, the server recognizes the user's current emotional state using an emotion engine. This is analyzed using the user's voice tone, entered text, or other interaction data.

[0718] Based on the analyzed author characteristics and the user's emotional state, the server utilizes a generative artificial intelligence model to generate new story branches that take the user's emotions into account. These stories are adjusted to best fit the user's emotions while maintaining the author's style.

[0719] The generated story is formatted and then sent from the server to the user's device. The device displays the emotionally sensitive new story to the user, who can then view and enjoy it.

[0720] For example, if a user is experiencing a sad or melancholic emotion, the system will generate a story that aligns with that emotion. In this way, the user can not only experience the original story but also gain a new experience that resonates with their own feelings. By providing a personalized story experience, this system can give users a deeper reading experience.

[0721] The following describes the processing flow.

[0722] Step 1:

[0723] The user provides information to the system using their device, including the author's name, the title of the work, and the specific scene where they want to change the story branch. This information is then sent from the device to the server.

[0724] Step 2:

[0725] The server searches the database based on the received information and retrieves the work data of the specified author. This prepares the data relevant to the user's request.

[0726] Step 3:

[0727] The server applies natural language processing to the acquired artwork data, analyzing and extracting characteristics such as the author's writing style and themes. This forms the foundation for story generation.

[0728] Step 4:

[0729] Simultaneously, the server activates the emotion engine and analyzes the user's emotional state. This is done through user input data and interaction with the interface, with the aim of identifying the emotions the user is currently experiencing.

[0730] Step 5:

[0731] The server uses a generative artificial intelligence model to generate new story branches, taking into account the analyzed author's characteristics and the user's emotional state. During this process, the story is adjusted to fit the user's emotions.

[0732] Step 6:

[0733] The generated stories are formatted and styled on the server, and then adjusted to a visually easy-to-read format for users.

[0734] Step 7:

[0735] The server sends the final story to the user's device. The device then presents the received story to the user, who can then view and enjoy it.

[0736] Step 8:

[0737] Users can provide their thoughts and feedback on the presented story through their devices, and the server collects and records this feedback to use for future system improvements.

[0738] (Example 2)

[0739] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0740] Traditional story generation systems have faced the challenge of providing personalized experiences that reflect the individual emotional states of users. In particular, when users request specific story branching paths within a particular author or work, existing technologies have struggled to generate appropriate narratives that meet those requests.

[0741] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0742] In this invention, the server includes means for receiving user input and obtaining information about a specified author, work, and specific scenes of an event; means for generating new narrative branches using a generative artificial intelligence model based on the analyzed author's characteristics and the user's emotional state; and emotion analysis means for analyzing emotions using the user's voice tone or input text. This makes it possible to provide a personalized narrative experience that fits the user's emotions.

[0743] "User" refers to an individual who uses the system to input information and enjoy a narrative experience.

[0744] "Means of receiving input" refers to the interface or process for users to provide data via their devices and for acquiring that data.

[0745] The term "author" refers to the creator of a work, and the person whose writing style and themes are analyzed by the system.

[0746] "Work" refers to all content created by an author and is the data that is referenced in the process of generating a story.

[0747] An "event" refers to a specific scene or situation within the story, and it is an element that users can use to generate new story branches.

[0748] "Analysis methods" refer to algorithms and techniques used to extract specific features or themes from input data.

[0749] A "generative artificial intelligence model" is an AI technology used to generate new stories, referring to a system that creates content using natural language processing and machine learning.

[0750] "Story branching" refers to different story developments or sequels within existing works, and means new content generated in response to user requests.

[0751] "Terminal" refers to all devices used by users to access the system, including computers and smartphones.

[0752] "Emotional analysis methods" refer to processes and technologies for evaluating and recognizing a user's emotional state, and include methods for analyzing voice tone and text.

[0753] A description of the embodiment for carrying out the invention will be provided.

[0754] This invention is a system consisting of three main components: a user, a server, and a terminal. The detailed operation and role of each component are described below.

[0755] Users access the system using their personal devices and input information based on their interests and preferences. This information includes specific author names, work titles, and specific scenes from stories. The information users input may also include their current emotional state, which forms the basis for state analysis.

[0756] The terminal plays the role of properly transmitting information entered by the user to the server. While terminals can take various forms, they are generally devices such as computers and smartphones. In this process, the terminal often sends the input data as an HTTP request.

[0757] The server retrieves author data from a database based on the received information. Next, it uses natural language processing (NLP) to analyze the author's writing style and themes from the data. Furthermore, the server uses an emotion analysis engine to identify the user's emotional state. This emotion analysis is based on voice tone, input text, and other emotional expression data.

[0758] Based on the analysis results, the server generates a new narrative branch using a generative AI model. In this process, the AI ​​model uses "author name, work title, scene, and user's emotional state" as prompts to generate an appropriate story. The generated story maintains the author's style while resonating with the user's emotions.

[0759] Examples of specific prompt messages are as follows:

[0760] "Author: Taro Yamamoto, Title: Book of Adventures, Scene: The scene where the protagonist meets new companions."

[0761] Based on this prompt, the system can create a special story that matches the user's emotional state.

[0762] In this way, the present invention provides users with a personalized and immersive narrative experience.

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1:

[0765] The user uses their device to input information such as the author's name, the title of the work, and specific scenes from the story. This input serves as initial data for generating specific story branches. Specifically, this involves the user entering text using the device's keyboard or touch interface.

[0766] Step 2:

[0767] The terminal sends information entered by the user to the server. The terminal converts the information into an HTTP request format and sends it over the network. At this point, the input is the text data initially provided by the user, and the output is the data sent to reach the server.

[0768] Step 3:

[0769] Based on the received information, the server executes a query to retrieve the corresponding author's work data from the database. The input is the author information submitted by the user, and the output is the work data retrieved from the database. In this step, data retrieval is performed using SQL queries, etc.

[0770] Step 4:

[0771] The server analyzes the author's characteristics through natural language processing on the acquired data. Specifically, it uses NLP techniques to analyze text data and extract writing style and themes. In this step, the input is the work data acquired from the database, and the output is the analyzed information about the author's style and themes.

[0772] Step 5:

[0773] The server uses an emotion analysis engine to recognize the user's emotional state. Input is information such as voice tone and text input; the user's emotions are recognized based on the emotion analysis method, and the output is information about the user's emotional state. Specifically, this involves a process of classifying emotions using a machine learning model.

[0774] Step 6:

[0775] The server uses a generative AI model to generate new story branches based on the analyzed author characteristics and the user's emotional state. The input is writing style, theme, and user emotional information, and the output is the generated story branch. In this step, the AI ​​model generates an appropriate story by inputting prompt sentences.

[0776] Step 7:

[0777] The server formats the generated story and sends it to the user's terminal. The input is the generated story data, and the output is the formatted and sent story. The terminal displays the received story and includes actions to visually entertain the user.

[0778] (Application Example 2)

[0779] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0780] Traditional story delivery systems have struggled to provide story experiences that respond to the individual emotional states of users. Because they provide uniform content without considering user emotions, readers' experiences are limited, and there is a problem in that they cannot deliver personalized emotional experiences.

[0781] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0782] In this invention, the server includes means for using an emotion analysis engine to analyze the user's emotional state, means for generating a new, personalized story branch using a generative artificial intelligence model based on the analysis results and the emotion analysis results, and means for providing the generated story to the user terminal. This makes it possible to provide a personalized story experience that corresponds to the user's emotional state.

[0783] "Means for receiving user information input" refers to a function that provides an interface for users to input information about the story they want to experience into the system.

[0784] "Information about the specified author, work, and relevant scenes of the story" refers to data provided by the user regarding specific author names, work titles, and specific scenes from selected stories.

[0785] "Means for analyzing acquired author characteristics" refers to a function that extracts and analyzes characteristics such as the author's writing style and themes from a database.

[0786] "Style and themes" refer to the author's unique style and the fundamental ideas and themes that consistently run through their work.

[0787] A "sentiment analysis engine for analyzing a user's emotional state" is software that analyzes a user's emotions from sources such as voice tone and text input, and recognizes that emotional state.

[0788] A "generative artificial intelligence model" refers to a machine learning model that can generate new information or content based on the data provided.

[0789] "Methods for generating story branching" refers to a function that uses analytical data to construct new story developments tailored to the user's emotions.

[0790] "Means of providing generated stories to user terminals" refers to a function that transfers and displays newly created stories on the user's device.

[0791] The system of this invention consists of a user terminal, a server, and software that processes and generates data between them. The user terminal is provided with an interface for inputting information about the story the user wants to experience. The user can input information about a specified author, work, or specific scene.

[0792] The input information is sent to the server, which retrieves the author's work information from the database. Next, natural language processing is used to analyze the author's characteristics based on this work information. This involves using libraries and tools that perform text analysis (for example, NLTK or SpaCy).

[0793] Furthermore, to sense the user's emotional state, the server utilizes an emotion analysis engine. This engine performs voice and text analysis to recognize the user's emotions in real time, and uses services such as Google Cloud's emotion analysis API.

[0794] After analysis, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate new story branches based on the user's emotions and the analyzed author's style. This generation process is initiated by a prompt. An example of a specific prompt might be, "Generate a relaxed story development that matches the current emotions, using the specified author's style."

[0795] The generated story is automatically formatted and sent to the user's device. The user's device then displays the story, allowing them to continue the narrative experience. This system enables users to enjoy a more personalized storytelling experience that takes their emotions into account at any given moment.

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The user uses their device to input information about the author, the work, and relevant scenes from the story. The entered data is collected using forms or voice input to clarify the user's intent. This information is then sent to the server for further processing.

[0799] Step 2:

[0800] Based on the information received, the server retrieves the corresponding author's work data from the database. The server uses SQL queries to search for entries for specific authors and works, and retrieves this data. This data then becomes the input for the subsequent natural language processing.

[0801] Step 3:

[0802] The server analyzes the acquired artwork data and performs natural language processing to extract the author's characteristics. Tools used here include libraries such as NLTK and SpaCy. This process tokenizes and tags the text of the artwork, identifying its style and themes. The results of this processing become crucial elemental data for story generation.

[0803] Step 4:

[0804] Simultaneously, the server activates an emotion analysis engine to analyze the user's emotional state from voice and text inputs. Using Google Cloud's emotion analysis API, it evaluates the emotional nuances of the user's voice tone and text, obtaining the user's current emotional state as output. This information serves as foundational data for shaping the generated story to best suit the user.

[0805] Step 5:

[0806] The server combines the analyzed characteristics and emotional state and generates new story branches using a generative AI model. Specifically, it manipulates generative AI such as OpenAI's GPT-3 using prompts. These prompts include specific instructions such as, "Generate a relaxed story development that matches the current emotion, in the style of the specified author." This process ensures that the output is an emotionally appropriate story while maintaining the originality of the work.

[0807] Step 6:

[0808] The server formats the generated story and adjusts it for display on the device. HTML or Markdown may be used to adjust the document format. This final story format is then sent to the user's terminal.

[0809] Step 7:

[0810] The user's device displays the received story, allowing the user to enjoy a personalized narrative experience. Appropriately laid-out text is displayed on the device's screen, and the user can freely turn pages or listen using the audio function.

[0811] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0812] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0813] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0814] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0815] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0816] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0817] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0818] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0819] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0820] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0821] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0822] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0823] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0824] 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.

[0825] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0826] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0827] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0828] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0829] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0830] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0831] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0832] The following is further disclosed regarding the embodiments described above.

[0833] (Claim 1)

[0834] A means for receiving user input and obtaining information about a specified author, work, and specific scene of a story,

[0835] A means of analyzing the characteristics of the acquired authors and extracting their writing style and themes,

[0836] Based on the aforementioned analysis results, a means for generating new story branches using a generative artificial intelligence model,

[0837] A means of providing the generated story to the user terminal,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, which collects user feedback and incorporates it into system improvements.

[0841] (Claim 3)

[0842] The system according to claim 1, which analyzes multiple works by an author and uses a database to improve the accuracy of feature extraction.

[0843] "Example 1"

[0844] (Claim 1)

[0845] A means for receiving user information and obtaining data relating to a specific author, work, and designated scene of a story,

[0846] A means of analyzing the characteristics of the acquired authors and extracting their expressive style and concepts,

[0847] Based on the aforementioned analysis results, a means for generating new story branches using a generative artificial intelligence model,

[0848] A means of providing the generated story to the user device,

[0849] A means of processing data using natural language processing techniques,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, which obtains feedback from users and reflects it in improving the system.

[0853] (Claim 3)

[0854] The system according to claim 1, which examines multiple works by an author and uses an information management system to improve the accuracy of feature extraction.

[0855] "Application Example 1"

[0856] (Claim 1)

[0857] A means of receiving user requests and obtaining information about a specified creator, work, and specific scenes of a story,

[0858] A means of analyzing the characteristics of the acquired creator and extracting formatting and themes,

[0859] Based on the aforementioned analysis results, a means for generating a new story branch using a generation algorithm,

[0860] A means of providing the generated story to the user's information processing device, enabling an interactive experience,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, which collects user feedback and incorporates it into system improvements.

[0864] (Claim 3)

[0865] The system according to claim 1, which analyzes multiple works by a creator and uses an information set to improve the accuracy of feature extraction.

[0866] "Example 2 of combining an emotion engine"

[0867] (Claim 1)

[0868] A means of receiving user input and obtaining information about a specified author, work, and specific scene of an event,

[0869] A means of analyzing the characteristics of the acquired authors and extracting their writing style and themes,

[0870] A means of generating new narrative branches using a generative artificial intelligence model based on the analyzed characteristics of the author and the emotional state of the user,

[0871] A means of providing the generated story to the user's terminal,

[0872] A system including an emotion analysis means that analyzes emotions using the user's voice tone or entered text.

[0873] (Claim 2)

[0874] The system according to claim 1, which collects user feedback and incorporates it into system improvements.

[0875] (Claim 3)

[0876] The system according to claim 1, which analyzes multiple works by an author and uses information storage to improve the accuracy of feature extraction.

[0877] "Application example 2 of combining emotional engines"

[0878] (Claim 1)

[0879] A means for receiving user information input and obtaining information about the specified author, work, and relevant scenes of the story,

[0880] A means of analyzing the characteristics of the acquired authors and extracting their writing style and themes,

[0881] A means of using an emotion analysis engine to analyze the emotional state of a user,

[0882] A means for generating a new, personalized story branch using a generative artificial intelligence model based on the aforementioned analysis results and sentiment analysis results,

[0883] A means of providing the generated story to the user terminal,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, which collects user feedback and uses it to improve the system.

[0887] (Claim 3)

[0888] The system according to claim 1, which uses a database capable of analyzing multiple works by an author and accumulating information to improve the accuracy of characteristic extraction. [Explanation of Symbols]

[0889] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving user input and obtaining information about a specified author, work, and specific scene of a story, A means of analyzing the characteristics of the acquired authors and extracting their writing style and themes, Based on the aforementioned analysis results, a means for generating new story branches using a generative artificial intelligence model, A means of providing the generated story to the user terminal, A system that includes this.

2. The system according to claim 1, which collects user feedback and incorporates it into system improvements.

3. The system according to claim 1, which uses a database to analyze multiple works by an author and improve the accuracy of feature extraction.

Images