System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to input story preferences and character settings; means for sending the user input information to a generative model; means for generating a story based on each character's viewpoint from the generative model; means for receiving the generated story data; means for categorizing and storing the received story data; and means for a user to view the story by viewpoint.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional narrative experiences, storytelling is often based primarily on the protagonist's perspective, making it difficult to gain a deep understanding of the perspectives and inner thoughts of other characters. As a result, there is a lack of concrete methods for cultivating the ability to understand and act out stories from multiple perspectives in school performances, home education, and moral education settings. To solve this problem, a new system is needed that allows for a deeper exploration of the story from each character's perspective, allowing all characters to be perceived as the protagonist. [Means for solving the problem]

[0005] The present invention provides a system including a means for a user to input basic story settings and character settings, a means for transmitting the user-input information to a generative model, a means for generating a story based on each character's perspective from the generative model, a means for receiving the generated story data, a means for categorizing and storing the received story data, and a means for the user to browse stories by perspective. This system allows users to understand and learn stories from multiple perspectives by inputting story setting information, and the generative model generates stories from each character's perspective based on that information and storing them in a database. The system also includes a means for converting the user-input information into a format suitable for the generative model and a means for saving the generated story data in a database, supporting use in a variety of situations and improving educational effectiveness.

[0006] "Story setting" refers to the theme, plot, and background information of a story, which form the framework for the entire story.

[0007] "Characterization" refers to detailed information about the characters in a story, such as their names, roles, personalities, and backgrounds, and defines their actions and their impact on the story.

[0008] A "generative model" refers to a set of systems or algorithms that use artificial intelligence to automatically generate new text or stories based on input data.

[0009] "User-input information" refers to data such as basic story settings and character settings that users provide to the system, and is information necessary for the system to operate.

[0010] "Narrative data" refers to text information containing a story based on the perspective of each character generated by a generative model.

[0011] "Categorization" refers to the process of classifying and organizing received narrative data based on specific criteria.

[0012] "Storage" refers to the act of saving the generated story data in a storage device such as a database.

[0013] A "point-of-view story" refers to a story told from the perspective of each character in the story, with the content of the story depicted being different for each different perspective.

[0014] The "system" refers to a set of devices and software that work together to combine the above means, helping users understand and learn stories from multiple perspectives. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system in which a user inputs the basic setting and character settings of a story, and a generative model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[0037] System Program Overview

[0038] The system includes the following means:

[0039] 1. Means for inputting and sending story settings

[0040] 2. Means of sending to the generative model

[0041] 3. Narrative Generation Methods

[0042] 4. Means of receiving the generative story

[0043] 5. Storage of story data

[0044] 6. How to view stories from different perspectives

[0045] A natural language description of the program

[0046] A means of inputting and sending story settings

[0047] The user uses the terminal to input the basic story settings and character settings (for example, the story title, the names and roles of the characters).

[0048] The terminal sends the entered information to the server. Specifically, when a user enters data into an input form and clicks the "Submit" button, the terminal sends this data to the server as an HTTP request.

[0049] Sending to the Generative Model

[0050] The server converts the received input data into a format suitable for the generative model, often JSON format.

[0051] The server sends the transformed data to the generative model, which is done as an API call, providing the generative model with the data it needs.

[0052] Story Generation Method

[0053] Based on the data received, the generative AI model generates a story from each character's perspective.

[0054] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[0055] Means of receiving generative stories

[0056] The server receives the story data generated by the generative AI model. The received data is divided into perspectives for each character.

[0057] A means of storing story data

[0058] The server categorizes the received story data and stores it in a database.

[0059] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[0060] A way to view stories from different perspectives

[0061] Users use their devices to access the YourSTORY library and view stories from each character's perspective.

[0062] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[0063] Explanation of specific examples

[0064] 1. The user inputs the basic setting of the story "Cinderella" into the device, including the characters "Cinderella," "Stepmother," "Sisters," and "Prince," along with their detailed settings.

[0065] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[0066] 3. The server sends the transformed data to the generative model, which then generates a story from each character's point of view.

[0067] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[0068] 5. Users can access the YourSTORY library using their device, select and view "Cinderella from the Stepmother's Point of View," and understand the story from multiple perspectives.

[0069] This system works by combining these methods to help users understand and learn stories from multiple perspectives.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[0073] Step 2:

[0074] The terminal sends the data entered by the user to the server. Specifically, the terminal collects the data from the input form and sends it to the server as an HTTP request.

[0075] Step 3:

[0076] The server parses the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into an appropriate data format.

[0077] Step 4:

[0078] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the data.

[0079] Step 5:

[0080] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses its internal algorithm to generate a story from each perspective and returns it as a response.

[0081] Step 6:

[0082] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response, analyzes it, and extracts the story for each perspective.

[0083] Step 7:

[0084] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[0085] Step 8:

[0086] Users access the YourSTORY library using their device and view stories from different perspectives. Specifically, users log in to the YourSTORY library using the browser on their device, select the story from the perspective they want to view, and then perform the necessary operations to display it.

[0087] Step 9:

[0088] In response to a user request, the device retrieves the appropriate story data from the database and displays it on the screen. Specifically, the device sends an HTTP request to the server and displays the story data returned by the server in the browser.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] Conventional story generation systems require large amounts of data processing and complex procedures when generating stories based on each character's perspective from the basic story and character settings entered by the user, making operation cumbersome. Furthermore, there were not enough systems that allowed users to easily browse stories by perspective. Furthermore, there was a lack of systems that automatically categorized and saved the generated story data. This made it difficult for users to create, manage, and browse stories efficiently and in a unified manner.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the input user information to the server, means for the server to convert the user-input information into a format suitable for the generative model, means for the server to transmit the converted information to the generative AI model, means for the generative AI model to generate a story based on the perspective of each character, means for the server to receive the generated story data, means for the server to categorize and store the received story data, and means for the user to view stories by perspective using a terminal. This enables users to efficiently and intuitively set basic story settings and character settings, and easily generate, manage, and view stories from each character's perspective.

[0094] A "user" is a person who uses the system to input basic story settings and character settings and view the generated story data.

[0095] A "terminal" is an electronic device such as a computer, smartphone, or tablet operated by a user, and is a device for inputting and transmitting story settings and viewing stories from different perspectives.

[0096] The "server" is a central processing unit that receives data entered by the user, sends it to the generative AI model, receives the results, and stores them in a database.

[0097] A "generative AI model" is an artificial intelligence model that generates a story from each character's perspective based on the basic story settings and character settings provided by the user.

[0098] "Basic story setting" refers to information that constitutes the outline of the entire story, such as the story's title and theme.

[0099] "Character settings" refers to information such as the names, roles, and characteristics of the characters that appear in the story.

[0100] A "form" is a set of input fields on a web page that allows a user to enter basic story and character settings.

[0101] An "HTTP request" is an Internet communication protocol used to send user input data to a server.

[0102] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a lightweight data exchange format for structuring and expressing data.

[0103] A "REST API" is an application programming interface based on Representational State Transfer, a standardized means of sending and receiving data between systems.

[0104] The "database" is an electronic data repository for systematically storing and managing received story data.

[0105] "Categorization" refers to classifying the generated narrative data according to specific perspectives.

[0106] "YourSTORY Library" is a collection of data storage and user interfaces within the system that users access to view narrative data from different perspectives.

[0107] A "prompt sentence" is an instruction sentence that instructs the generative AI model to generate a story, and is a sentence that contains the necessary input data.

[0108] The present invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[0109] The system consists of the following main means:

[0110] 1. Means for inputting and sending story settings

[0111] The user uses the device to input the basic story and character settings (e.g., the story title, the names and roles of the characters). To do this, the user opens a browser and enters the necessary information into a dedicated input form. When the user clicks the "Submit" button, the device asynchronously sends this data to the server as an HTTP POST request.

[0112] 2. Means of converting and transmitting data to the generative model

[0113] The server converts the received user input information into a format suitable for the generative model (for example, JSON format). To do this, the server structures the received data and processes it into a format that is easy for the generative model to understand. After conversion, the server sends this data to the generative AI model as an API call. As a concrete example, we will implement the API call using Python's requests library.

[0114] 3. Narrative Generation Methods

[0115] Based on the data received, the generative AI model generates a story from each character's perspective. Using the story of Cinderella as an example, the generative AI model generates different stories from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective. Stories from each perspective are generated using the generative AI model's prompt sentences.

[0116] Example prompt sentence:

[0117] "Generate a story from Cinderella's point of view: {configuration data}"

[0118] "Generate a story from the stepmother's point of view: {config data}"

[0119] 4. Means of receiving the generative story

[0120] The server receives the story data generated by the generative AI model. The generated data is divided into separate data for each character's perspective, and the server receives this data all at once.

[0121] 5. Storage of story data

[0122] The server categorizes the received story data and stores it in a NoSQL database (e.g., MongoDB). Specifically, the generated story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince" based on each perspective, and each piece of data is saved as a document in the database.

[0123] 6. How to view stories from different perspectives

[0124] Users access the YourSTORY library using their device and view stories from each character's perspective. When the user selects a specific perspective from the displayed list, the device retrieves the necessary story data from the database and displays it on the screen in a format that is easy for the user to view. Specifically, it uses a front-end framework (e.g., Vue.js or React) to asynchronously retrieve data using AJAX or the Fetch API and dynamically updates the screen display.

[0125] In this way, the system of the present invention is configured to allow the user to set basic story and character settings, and to easily create, manage, and view stories from each character's perspective.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] The user inputs the basic story setting and character settings.

[0129] The user opens a browser on their device and enters details such as the story title, theme, and the names and roles of the characters into a dedicated input form. Once the input is complete, they click the "Submit" button.

[0130] Input: Basic story setting and character information

[0131] Output: Data packet to send (in JSON format)

[0132] Step 2:

[0133] The terminal transmits the input information to the server.

[0134] When the user clicks the "Submit" button, the terminal uses AJAX to send the input data to the server as an HTTP POST request.

[0135] Input: Story setting and character setting information entered by the user

[0136] Output: Data packets sent to the server

[0137] Step 3:

[0138] The server converts the received input data into a format suitable for the generative model.

[0139] The server converts the received data into JSON format, creating a structure that is easy for the generative AI model to understand.

[0140] Input: User input data sent from the terminal

[0141] Output: Structured JSON data to send to a generative AI model

[0142] Step 4:

[0143] The server sends the converted data to the generative AI model.

[0144] The server sends a POST request to an API endpoint, providing the data required for the generative AI model.

[0145] Input: User-supplied data in JSON format

[0146] Output: API call to the generative AI model and its response

[0147] Step 5:

[0148] Based on the data received, the generative AI model generates a story from each character's perspective.

[0149] The generative AI model generates a story from each character's perspective using prompt sentences based on the input data provided.

[0150] For example, the prompt is:

[0151] "Generate a story from Cinderella's point of view: {configuration data}", "Generate a story from the stepmother's point of view: {configuration data}"

[0152] Input: JSON data sent to the generative AI model

[0153] Output: Story data for each character's perspective

[0154] Step 6:

[0155] The server receives the narrative data generated from the generative AI model.

[0156] The server checks the API response and receives the narrative data for each generated perspective.

[0157] Input: Response data from the generative AI model

[0158] Output: Story data stored on the server

[0159] Step 7:

[0160] The server categorizes the received story data and stores it in a database.

[0161] The server classifies the received story data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and stores each piece of data in a NoSQL database.

[0162] Input: Story data divided into perspectives

[0163] Output: Categorized narrative data stored in a database

[0164] Step 8:

[0165] Users use their devices to access the YourSTORY library and browse stories from different perspectives.

[0166] When a user accesses the library and selects a story from a particular perspective from the displayed list, the terminal sends a request to the server to obtain the required data.

[0167] Input: Request information for the viewpoint selected by the user

[0168] Output: Narrative data from a specified point of view

[0169] Step 9:

[0170] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[0171] The device retrieves data asynchronously using AJAX or the Fetch API, and updates the screen display in a user-friendly format using Vue.js or React.

[0172] Input: Data retrieval request based on user request

[0173] Output: Story data displayed on the user's device

[0174] (Application example 1)

[0175] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0176] There is a need for a system that allows users to easily input basic story settings and character settings, generate stories from multiple perspectives based on that information, and allow users to easily view those stories. However, existing technologies lack the ability to properly process user-input information or manage data received from the generative model, making deployment as a smartphone application particularly difficult. There is also a need for a system that allows the generated story data to be easily saved and managed, and be viewable by perspective.

[0177] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0178] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user-input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for a user to view stories by perspective, means for delivering the story data to a content delivery service, and means for providing the story data as an application that runs on a smartphone. This allows story data generated from multiple perspectives to be efficiently managed and delivered, and allows users to easily access and view it.

[0179] "Story Basics" is information that the user enters to form the framework of the story, such as the story's theme, background, and major events.

[0180] "Character settings" involve the user entering detailed attributes of each character appearing in the story, such as their name, role, personality, and characteristics.

[0181] "User-input information" is a general term for information about the basic story setting and character settings that a user provides to the system.

[0182] A "generative model" is an artificial intelligence model for automatically generating a story based on received user input information, and here it is particularly applicable to generating a story from multiple perspectives.

[0183] "Narrative data" refers to textual data of a story created by a generative model, including multiple versions based on each character's perspective.

[0184] "Categorization" is the act of classifying and organizing received narrative data according to specific criteria.

[0185] "Storage" refers to saving the received story data in a database or storage.

[0186] "Perspective stories" refers to different versions of a story that are generated based on the perspective of each character in the story.

[0187] "Content distribution service" is a general term for online platforms that provide generated story data to users via the Internet.

[0188] "Smartphone-enabled application" refers to a software program that can be installed and executed on a smartphone device, and here means, in particular, one that has story creation and viewing capabilities.

[0189] This invention provides a system that generates stories from multiple perspectives and allows users to view them from different perspectives. Specifically, the system configures a means for users to input basic story settings and character settings, send the data to a generative AI model for processing, and store and distribute the generated story data.

[0190] 1. System Configuration

[0191] The basic components of the system are:

[0192] 1. How to input and submit story settings:

[0193] The user uses the terminal to input the basic story settings and character settings.

[0194] The entered information is sent to the server as an HTTP request.

[0195] 2. Means of sending to the generative model:

[0196] The input data received by the server is converted into JSON format.

[0197] The transformed data is sent to a generative AI model, which may be powered by OpenAI or a similar generative model.

[0198] 3. Narrative generation tools:

[0199] Based on the data received, the generative AI model generates a story from each character's perspective.

[0200] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[0201] 4. Means of receiving the generative story:

[0202] The server receives the narrative data generated from the generative AI model.

[0203] The received data is divided into perspectives for each character.

[0204] 5. Narrative data storage means:

[0205] The server categorizes the received story data and stores it in a database.

[0206] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[0207] 6. How to view the story by point of view:

[0208] The user uses a device such as a smartphone to view the story from a different perspective.

[0209] In response to a user's request, the server retrieves the appropriate story data from the database and displays it on the screen.

[0210] 7. Content Delivery Methods:

[0211] The server distributes the generated story data to a platform (content distribution service) that provides it to users via the Internet.

[0212] This allows users to easily access and view stories generated from multiple perspectives.

[0213] 8. Application Delivery Method:

[0214] All of the above functions are implemented as an application for smartphones.

[0215] The application again provides an interface for users to input story settings and view the stories generated by the generative model.

[0216] 2. Program Processing

[0217] The system is built using Python and the Flask framework, and uses the HTTP protocol for data communication, with JSON as the data format.

[0218] 1. Hardware and Software:

[0219] The hardware used includes the user's device (smartphone or computer) and a server.

[0220] The software used includes a generative AI model (e.g., GPT-4 (registered trademark) by OpenAI (registered trademark)), a framework (Flask), and a database management system (e.g., SQLite or MongoDB).

[0221] 2. Data processing and calculation:

[0222] User input data is received by the server and converted to JSON format.

[0223] The converted data is sent to a generative AI model to generate a story.

[0224] The generated story data is received, categorized by character, and stored in a database.

[0225] - Upon user request, story data from a specific character's perspective is retrieved from the database and displayed on the screen.

[0226] 3. Specific Examples

[0227] For example, the user enters the following:

[0228] Title: Cinderella

[0229] character:

[0230] Cinderella: "She has a kind heart"

[0231] Stepmother: "Strict and jealous"

[0232] Older sisters: "Mean personality"

[0233] Prince: "True and brave"

[0234] An example of a prompt for the generative AI model would be, "Please describe the story in detail from Cinderella's point of view." This will enable efficient management and distribution of stories generated from multiple perspectives, making them easily accessible and viewable by users.

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1:

[0237] The user uses the terminal to input the basic story settings and character settings.

[0238] The entered information (story title, character name, role, personality, etc.) is converted into JSON format within the device application and sent to the server as an HTTP request.

[0239] Input: Data entered by the user for the setting.

[0240] Output: JSON formatted data sent to the server.

[0241] Step 2:

[0242] The server rechecks the received JSON data and converts it into a format suitable for the generative model.

[0243] Validate and format the data as needed, and create prompts to send to the generative AI model.

[0244] Input: JSON formatted data received from the user.

[0245] Output: The prompt sent to the generative AI model.

[0246] Step 3:

[0247] The server sends the prompt sentence to the generative AI model as an API request.

[0248] The generative AI model generates a story from each character's perspective based on the prompt text it receives.

[0249] Input: The prompt sentence sent to the generative AI model.

[0250] Output: Generated narrative text data.

[0251] Step 4:

[0252] The server receives the generated story data as a response from the generative AI model.

[0253] This data is divided into perspectives for each character.

[0254] Input: Narrative data received as a response from a generative AI model.

[0255] Output: Generated narrative data by viewpoint.

[0256] Step 5:

[0257] The server categorizes the received story data by character and stores it in a database.

[0258] When storing, it creates appropriate indexes to facilitate later retrieval and access.

[0259] Input: Narrative data separated by point of view.

[0260] Output: Narrative data stored in a database.

[0261] Step 6:

[0262] The user uses the terminal to request a story from each character's perspective.

[0263] The application on the terminal sends the request to the server.

[0264] Input: A story view request from a user.

[0265] Output: The request data sent to the server.

[0266] Step 7:

[0267] The server retrieves the story data from the relevant character's perspective from the database and sends it to the terminal.

[0268] Here, the appropriate data is retrieved based on the request and a response is sent to the user.

[0269] Input: The browse request sent to the server.

[0270] Output: The narrative data sent back to the terminal.

[0271] Step 8:

[0272] The device displays the received story data to the user.

[0273] Users can read the story from each character's perspective through the device screen.

[0274] Input: Story data sent from the server.

[0275] Output: The story that is displayed to the user.

[0276] Step 9:

[0277] The server distributes the generated story data to a content distribution service via the Internet.

[0278] This is to allow more users to view stories on different devices.

[0279] Input: Generated narrative data.

[0280] Output: Narrative data delivered to a content delivery service.

[0281] Step 10:

[0282] The device is designed to run all of the above functions as smartphone applications.

[0283] The application provides an interface for users to re-enter story settings and view the stories generated by the generative model.

[0284] Input: Various user inputs and data from the server.

[0285] Output: An integrated narrative generation and viewing experience provided to the user.

[0286] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0287] This invention combines an emotion engine with a system in which a user inputs the basic story setting and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[0288] System Program Overview

[0289] The system includes the following means:

[0290] 1. Means for inputting and sending story settings

[0291] 2. Means of sending to the generative model

[0292] 3. Narrative Generation Methods

[0293] 4. Means of receiving the generative story

[0294] 5. Storage of story data

[0295] 6. How to view stories from different perspectives

[0296] 7. Emotion Engine

[0297] 8. Emotion-based narrative adjustment

[0298] A natural language description of the program

[0299] A means of inputting and sending story settings

[0300] The user uses the terminal to input the basic story and character settings, including the story title, the names, roles, and personalities of the characters.

[0301] The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[0302] Sending to the Generative Model

[0303] The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[0304] The server sends the transformed data to the generative model, which is then passed to the model via an API call.

[0305] Story Generation Method

[0306] Based on the data received, the generative AI model generates a story from each character's perspective, for example, the story of Cinderella from multiple characters' perspectives.

[0307] Means of receiving generative stories

[0308] The server receives the response from the generative AI model and the generated story data, which includes story data divided into perspectives for each character.

[0309] A means of storing story data

[0310] The server categorizes the received story data and stores it in a database. Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and saved in the database.

[0311] A way to view stories from different perspectives

[0312] The user accesses the YourSTORY library using a device and reads stories from each character's perspective. They log in to the library using the device's browser, select the story from the perspective they want to see, and display it.

[0313] Emotion engine and emotion-based story adjustment

[0314] Emotion Engine

[0315] The emotion engine recognizes the user's emotions by analyzing their facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[0316] Emotion-based narrative adjustment

[0317] The server receives the emotion data sent from the emotion engine.

[0318] The generative model dynamically adjusts the story based on the user's emotional data, for example, changing the tone of the story to be more positive if the user is in a happy state.

[0319] The story the user views on the device is dynamically adjusted to correspond to the user's emotional state.

[0320] Explanation of specific examples

[0321] 1. The user inputs the story setting of "Cinderella" on the device, including details of the characters "Cinderella," "Stepmother," "Sisters," and "Prince."

[0322] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[0323] 3. The server sends the converted data to the generative model, which then generates a story from each character's perspective.

[0324] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[0325] 5. The user uses the device to access the YourSTORY library, selects "Cinderella from the Stepmother's Point of View," and views it.

[0326] 6. The emotion engine recognizes the user's emotion, and the server receives this emotion data.

[0327] 7. The generative model dynamically adjusts the story content based on emotional data. For example, if the user is sad, the tone of the story will be changed to be more emotional.

[0328] 8. The stories users view on their devices will respond to their emotional state, providing a more personalized experience.

[0329] In this way, the system generates stories that take the user's emotions into account, allowing the user to have a more multifaceted and emotionally rich story experience.

[0330] The processing flow will be explained below.

[0331] Step 1:

[0332] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[0333] Step 2:

[0334] The terminal sends the data entered by the user to the server. Specifically, the data in the input form is collected and sent to the server as an HTTP request.

[0335] Step 3:

[0336] The server analyzes the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into the required format.

[0337] Step 4:

[0338] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the required data.

[0339] Step 5:

[0340] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses an internal algorithm to generate a story from Cinderella's perspective, the stepmother's perspective, the sisters' perspective, and the prince's perspective.

[0341] Step 6:

[0342] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response and analyzes and extracts story data for each perspective.

[0343] Step 7:

[0344] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[0345] Step 8:

[0346] The user accesses the YourSTORY library using a device and browses stories from different perspectives. Specifically, the user logs into the YourSTORY library using the device's browser, selects the story from the perspective they want to view, and displays it.

[0347] Step 9:

[0348] The emotion engine recognizes the user's emotions by capturing the user's facial expressions and voice through the device's camera and microphone, and then uses an emotion analysis algorithm to determine the user's emotional state.

[0349] Step 10:

[0350] The server receives the emotional data sent from the emotion engine. Specifically, the server receives the analysis results of the emotional data and uses them to adjust the tone and content of the story.

[0351] Step 11:

[0352] The generative model dynamically adjusts the content of the story based on the emotional data. Specifically, the generative model receives emotional data as input and changes the tone and event content of the story according to the user's emotions.

[0353] Step 12:

[0354] The story that the user is viewing on the device is dynamically adjusted according to the user's emotional state. Specifically, if the user is in a happy state, the tone of the story is adjusted to a positive one.

[0355] This series of processes allows users to enjoy a personalized story experience that is tailored to their emotions.

[0356] Example 2

[0357] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0358] Conventional story generation systems generate static stories based on basic settings and character configurations entered by the user, and suffer from a lack of personalization based on the user's emotional state, making it difficult for users to obtain an emotionally rich story experience.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0360] In this invention, the server includes means for the user to input basic story settings and character settings, means for transmitting the information input by the user to the generative model, means for generating a story based on the viewpoint of each character, means for receiving the generated story data, means for categorizing and storing the received story data, an emotion engine for recognizing the user's emotions, means for dynamically adjusting the story based on the emotion data from the emotion engine, and means for the user to view stories from different viewpoints, thereby enabling dynamic story generation that corresponds to the user's emotional state.

[0361] A "user" is a person who uses this system to input story settings and character settings.

[0362] "Basic story settings" are information that forms the framework of the story, such as the title of the story, the main storyline, and the setting.

[0363] "Character settings" are detailed information about the characters that appear in the story, such as their names, personalities, and roles.

[0364] A "generative model" is an algorithm or program that generates a story based on information input by a user.

[0365] "Story data" is data containing the content of a story generated by a generative model.

[0366] An "emotion engine" is software or hardware capable of recognizing a user's emotional state and adapting dialogue and output accordingly.

[0367] "Emotion data" is data obtained as a result of the emotion engine analyzing the user's emotions.

[0368] "Dynamic adjustment means" is a function that changes the content of the generated story in real time according to the user's emotional state.

[0369] A "perspective story" is a multiple story told from the perspective of each character in the story.

[0370] This invention combines an emotion engine with a system in which a user inputs basic story settings and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[0371] Hardware and Software Examples

[0372] Devices: PCs, smartphones, tablets, etc.

[0373] Server: Cloud server, web server

[0374] Generative AI model: A generative model using natural language processing (NLP) (e.g., GPT-3 (registered trademark))

[0375] Emotion engine: facial expression recognition software, voice analysis software (e.g., Amazon Rekognition, Microsoft® Azure® Emotion API)

[0376] Specific system configuration

[0377] 1. The user uses a terminal to input the basic story and character settings, including the story title and the names, roles, and personalities of the characters.

[0378] Specifically, the user inputs the story title "Cinderella" and details (personalities and roles) of the characters appearing in the story: "Cinderella," "Prince," "Stepmother," and "Sisters."

[0379] 2. The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[0380] 3. The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[0381] 4. The server sends the transformed data to the generative model, which is passed to the model via an API call.

[0382] 5. Based on the received data, the generative AI model generates a story from each character's perspective. For example, the story of Cinderella is generated from the perspectives of multiple characters.

[0383] 6. The server receives the response from the generative AI model and the generated story data, which includes story data separated by each character's perspective.

[0384] 7. The server categorizes the received story data and stores it in the database. Specifically, the story data is classified into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and saved in the database.

[0385] 8. The user accesses the YourSTORY library using a device and browses stories from each character's perspective. The user logs in to the library using the device's browser, selects the story from the perspective they want to view, and displays it.

[0386] 9. The emotion engine recognizes the user's emotions by analyzing the user's facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[0387] 10. The server receives the emotion data sent from the emotion engine.

[0388] 11. The generative model dynamically adjusts the story based on the user's emotional data. For example, if the user is in a happy state, it changes the tone of the story to be more positive.

[0389] 12. The story the user views on their device is dynamically adjusted to correspond to the user's emotional state.

[0390] Specific prompt examples

[0391] Example 1: Generate a story from Cinderella's point of view.

[0392] Example 2: If the user is in a happy state, change the tone of the story to a positive one.

[0393] As described above, the present invention is a system that generates and dynamically adjusts a story based on user input, providing a more personalized story experience.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] The flow of this system's program processing

[0396] Step 1:

[0397] The user uses a terminal to input the basic setting and character settings of the story.

[0398] Input: The user enters information such as the story title, character names, roles, and personalities into an input form.

[0399] Specific actions: For example, enter the story title "Cinderella" and the names and personalities of "Cinderella," "Prince," "Stepmother," and "Stepsisters" (e.g., Cinderella = kind, Prince = brave).

[0400] Output: The entered information is stored in a data structure within the terminal.

[0401] Step 2:

[0402] The terminal transmits the input information to the server.

[0403] Input: Story and character data entered by the user in Step 1.

[0404] Specific behavior: When the user clicks the "Submit" button, the data is sent to the server as an HTTP request.

[0405] Output: The data sent to the server.

[0406] Step 3:

[0407] The server converts the received data into a format suitable for the generative model.

[0408] Input: Story and character setting data received by the server.

[0409] Specific operation: Converts received data into, for example, JSON format and organizes the data into a fair format.

[0410] Output: Data converted to JSON format.

[0411] Step 4:

[0412] The server sends the transformed data to the generative model.

[0413] Input: Story and characterization data converted to JSON format.

[0414] What it does: Makes an API call and sends data to the appropriate endpoint.

[0415] Output: The data passed to the generative model.

[0416] Step 5:

[0417] Based on the data received, the generative AI model generates a story from each character's perspective.

[0418] Input: Story and characterization data in JSON format.

[0419] How it works: The generative AI model uses algorithms to dynamically generate a story from each character's perspective.

[0420] Output: Narrative data generated for each character.

[0421] Step 6:

[0422] The server receives the response from the generative AI model and receives the generated story data.

[0423] Input: Response data from the generative AI model.

[0424] Specific operation: Analyze the response and save the story data divided by character's perspective on the server.

[0425] Output: Story data from each character's perspective.

[0426] Step 7:

[0427] The server stores the received story data in a database by category.

[0428] Input: Story data from character perspectives.

[0429] Specific operation: For example, classify into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and save them in a database.

[0430] Output: Story data in a categorized database.

[0431] Step 8:

[0432] The user uses a terminal to access the YourSTORY library and view stories from each character's perspective.

[0433] Input: Categorized story data.

[0434] Specific operation: Log in to the library using your device's browser, select the story from the perspective you want to see, and display it.

[0435] Output: Narrative content from a user-specified point of view.

[0436] Step 9:

[0437] The emotion engine recognizes the user's emotions.

[0438] Input: The user's facial expressions, voice, and other biometric signals acquired from the device.

[0439] Specific operation: Data is acquired through the camera and microphone, and analyzed to detect emotional state.

[0440] Output: Detected user emotion data.

[0441] Step 10:

[0442] The server receives the emotion data sent from the emotion engine.

[0443] Input: Emotion data sent from the emotion engine.

[0444] Specific operation: The server receives the emotion data and inputs it into the analysis system.

[0445] Output: Emotion data in the server.

[0446] Step 11:

[0447] A generative model dynamically adjusts the narrative based on the user's emotional data.

[0448] Input: User emotion data.

[0449] What it does: The generative model analyzes the emotional data and changes the tone and content of the generated story based on that.

[0450] Output: Dynamically adjusted narrative data that responds to the user's emotions.

[0451] Step 12:

[0452] The story the user views on their device will correspond to the user's emotional state.

[0453] Input: Dynamically adjusted narrative data.

[0454] What it does: When users revisit a story, they will see real-time updates based on sentiment.

[0455] Output: A personalized narrative experience.

[0456] (Application example 2)

[0457] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0458] Conventional story generation systems were able to generate a story from a fixed perspective based on user-entered settings, but lacked the ability to dynamically adjust the story content in response to the user's emotional state. This made it difficult to provide a story optimized for each user's individual emotional experience. Furthermore, there was a lack of an efficient system for generating stories from each character's perspective. This limited the user's ability to enjoy the story by changing their perspective.

[0459] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0460] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for the user to view stories by perspective, means for recognizing the user's emotions, and means for dynamically adjusting the content of the story based on the emotions. This enables a personalized story experience according to the user's emotional state, making it possible to provide a system that allows users to enjoy stories from different perspectives.

[0461] "Means for users to input basic story settings and character settings" refers to the means by which users input the story title, characters' names, roles, personalities, etc.

[0462] "Means for sending user-input information to a generative model" refers to means for sending information on the basic story setting and character settings entered by the user to a generative AI model.

[0463] "Means for generating a story from each character's perspective from a generative model" refers to a means for a generative AI model to generate a story from each character's perspective based on information received from the user.

[0464] "Means for receiving generated story data" refers to means for receiving story data generated from a generative AI model.

[0465] The "means for categorizing and storing received story data" is a means for classifying received story data into specific categories and storing them in a database.

[0466] "Means for users to view stories from different perspectives" refers to means for users to view stories generated from the perspectives of each character.

[0467] "Means for recognizing the user's emotions" refers to a means for analyzing the user's facial expressions, voice, biometric signals, etc. to detect the user's emotional state.

[0468] "Means for dynamically adjusting story content based on emotions" refers to means for adapting and adjusting the content of a generated story in real time based on the recognized emotional state of a user.

[0469] MODE FOR CARRYING OUT THE INVENTION

[0470] System Overview

[0471] This invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. Furthermore, the system has the ability to recognize the user's emotions and dynamically adjust the story content based on those emotions. This system allows users to experience a personalized story from each perspective.

[0472] Hardware and software used

[0473] Hardware: Smartphones, smart glasses, head-mounted displays

[0474] Software: Python 3.8+, Flask (server-side), Emotion Recognition API

[0475] Data processing and data calculation

[0476] Enter and submit story settings

[0477] The user inputs the story title, characters' names, roles, personalities, etc. into a smartphone or other device. The input data is converted into JSON format and sent to the server as an HTTP request, allowing the server to receive the input data from the user.

[0478] Sending to the Generative Model

[0479] The server converts the received user story setting and character setting information into a format suitable for the generative AI model, and then sends the converted data to the generative AI model via an API call.

[0480] Story Generation

[0481] The generative AI model generates a story from each character's perspective based on the received data. For example, it generates the story of the fairy tale "Cinderella" from each character's perspective. This generated story data is sent back to the server.

[0482] Receiving and storing generated stories

[0483] The server receives the story data generated by the generative AI model, categorizes it by each character's perspective, and stores it in a database, improving search efficiency when users later view the story by perspective.

[0484] Viewing stories by point of view

[0485] Users can use their devices to view stories from different points of view, for example, they can select the Cinderella story as "from the stepmother's point of view" and start reading.

[0486] Emotion recognition and dynamic adjustment of narrative

[0487] The user's device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API. This emotional data is sent to the server, which then invokes a generative AI model based on the emotional data to dynamically adjust the content of the story. For example, if the user is in a happy state, the tone of the story will be changed to a more positive one.

[0488] Specific examples

[0489] 1. Enter the story setting

[0490] The user inputs the story setting for "Cinderella" on the device, along with details of the characters: "protagonist," "villain," "rival," and "savior."

[0491] Example prompt sentence:

[0492] Enter the story setting for Cinderella. Characters:

[0493] Name: Cinderella, Role: Protagonist, Personality: Kind

[0494] Name: Stepmother, Role: Antagonist, Character: Ruthless

[0495] Name: Older sisters, Role: Rival, Personality: Jealous

[0496] Name: Prince, Role: Savior, Personality: Sense of Justice

[0497] 2. Send to the generative model

[0498] The server sends the story setting to the generative AI model, which generates a story from each perspective.

[0499] 3. Receiving and storing generated stories

[0500] The generated stories are stored in a database by point of view.

[0501] 4. Emotion recognition

[0502] If the user's emotion is recognized as "happy," the system adjusts the story to a more positive tone.

[0503] 5. Viewing stories from different perspectives

[0504] Users view the adapted story on their device.

[0505] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0506] Step 1:

[0507] The user inputs the story setting.

[0508] Specifically, users use their smartphones or other devices to input the story title, characters' names, roles, personalities, etc. The input data is retrieved from the form and converted into JSON format.

[0509] Input: Basic story setting and character settings

[0510] Output: Story setting data converted to JSON format

[0511] Step 2:

[0512] The terminal transmits story setting data to the server.

[0513] Once the user has finished entering the settings, they press the "Submit" button, which sends an HTTP request from the device to the server, which then checks the received data and converts it into an appropriate format (e.g., JSON).

[0514] Input: Story setting data converted to JSON format

[0515] Output: Story setting data sent to the server

[0516] Step 3:

[0517] The server sends the data to the generative AI model.

[0518] The server verifies the accuracy of the received data, then converts it into a format suitable for the generative AI model, and sends this converted data to the generative AI model via an API call.

[0519] Input: Data converted into a format suitable for generative AI models

[0520] Output: Data sent to the generative AI model

[0521] Step 4:

[0522] A generative AI model generates the story.

[0523] The generative AI model generates a story from each character's perspective based on the received data. This generation process uses natural language processing technology, particularly analyzing prompts to develop the story. The generated story data is organized by each character's perspective and sent back to the server.

[0524] Input: Data sent to the generative AI model

[0525] Output: Narrative data generated by perspective

[0526] Step 5:

[0527] The server receives the generated story data and stores it in a database.

[0528] The server receives the story data sent from the generative AI model, categorizes the received data by perspective, and stores it in a database, which improves future search efficiency.

[0529] Input: Narrative data generated by perspective

[0530] Output: Categorized narrative data stored in a database

[0531] Step 6:

[0532] Users view stories from different perspectives.

[0533] The user uses the terminal to select a story by point of view and begin viewing. The terminal accesses the database and displays the selected story.

[0534] Input: Narrative data stored by point of view

[0535] Output: The story displayed on the user's terminal

[0536] Step 7:

[0537] The device recognizes the user's emotions.

[0538] The device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API, and sends the resulting data to the server.

[0539] Input: Emotional data such as user facial expressions, voice, and biometric signals

[0540] Output: Emotion state data analyzed by the Emotion Recognition API

[0541] Step 8:

[0542] The server invokes a generative AI model based on the emotional data and dynamically adjusts the content of the story.

[0543] The server receives the emotional state data and sends prompts to the generative AI model again to adjust the story content, changing the tone and development of the story according to the user's emotional state. The adjusted story data is then regenerated and sent to the user's device.

[0544] Input: Emotion state data sent from the Emotion Recognition API

[0545] Output: Dynamically adjusted narrative data

[0546] Step 9:

[0547] The user views the tailored story.

[0548] The user then views the adjusted story on their device again, providing a story experience optimized for the user's emotional state.

[0549] Input: Dynamically adjusted narrative data

[0550] Output: The adjusted story displayed on the user's terminal

[0551] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0552] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0553] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0554] [Second embodiment]

[0555] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0556] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0557] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0558] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0559] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0560] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0561] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0562] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0563] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0564] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0565] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0566] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0567] The present invention is a system in which a user inputs the basic setting and character settings of a story, and a generative model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[0568] System Program Overview

[0569] The system includes the following means:

[0570] 1. Means for inputting and sending story settings

[0571] 2. Means of sending to the generative model

[0572] 3. Narrative Generation Methods

[0573] 4. Means of receiving the generative story

[0574] 5. Storage of story data

[0575] 6. How to view stories from different perspectives

[0576] A natural language description of the program

[0577] A means of inputting and sending story settings

[0578] The user uses the terminal to input the basic story settings and character settings (for example, the story title, the names and roles of the characters).

[0579] The terminal sends the entered information to the server. Specifically, when a user enters data into an input form and clicks the "Submit" button, the terminal sends this data to the server as an HTTP request.

[0580] Sending to the Generative Model

[0581] The server converts the received input data into a format suitable for the generative model, often JSON format.

[0582] The server sends the transformed data to the generative model, which is done as an API call, providing the generative model with the data it needs.

[0583] Story Generation Method

[0584] Based on the data received, the generative AI model generates a story from each character's perspective.

[0585] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[0586] Means of receiving generative stories

[0587] The server receives the story data generated by the generative AI model. The received data is divided into perspectives for each character.

[0588] A means of storing story data

[0589] The server categorizes the received story data and stores it in a database.

[0590] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[0591] A way to view stories from different perspectives

[0592] Users use their devices to access the YourSTORY library and view stories from each character's perspective.

[0593] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[0594] Explanation of specific examples

[0595] 1. The user inputs the basic setting of the story "Cinderella" into the device, including the characters "Cinderella," "Stepmother," "Sisters," and "Prince," along with their detailed settings.

[0596] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[0597] 3. The server sends the transformed data to the generative model, which then generates a story from each character's point of view.

[0598] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[0599] 5. Users can access the YourSTORY library using their device, select and view "Cinderella from the Stepmother's Point of View," and understand the story from multiple perspectives.

[0600] This system works by combining these methods to help users understand and learn stories from multiple perspectives.

[0601] The processing flow will be explained below.

[0602] Step 1:

[0603] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[0604] Step 2:

[0605] The terminal sends the data entered by the user to the server. Specifically, the terminal collects the data from the input form and sends it to the server as an HTTP request.

[0606] Step 3:

[0607] The server parses the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into an appropriate data format.

[0608] Step 4:

[0609] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the data.

[0610] Step 5:

[0611] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses its internal algorithm to generate a story from each perspective and returns it as a response.

[0612] Step 6:

[0613] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response, analyzes it, and extracts the story for each perspective.

[0614] Step 7:

[0615] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[0616] Step 8:

[0617] Users access the YourSTORY library using their device and view stories from different perspectives. Specifically, users log in to the YourSTORY library using the browser on their device, select the story from the perspective they want to view, and then perform the necessary operations to display it.

[0618] Step 9:

[0619] In response to a user request, the device retrieves the appropriate story data from the database and displays it on the screen. Specifically, the device sends an HTTP request to the server and displays the story data returned by the server in the browser.

[0620] Example 1

[0621] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0622] Conventional story generation systems require large amounts of data processing and complex procedures when generating stories based on each character's perspective from the basic story and character settings entered by the user, making operation cumbersome. Furthermore, there were not enough systems that allowed users to easily browse stories by perspective. Furthermore, there was a lack of systems that automatically categorized and saved the generated story data. This made it difficult for users to create, manage, and browse stories efficiently and in a unified manner.

[0623] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0624] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the input user information to the server, means for the server to convert the user-input information into a format suitable for the generative model, means for the server to transmit the converted information to the generative AI model, means for the generative AI model to generate a story based on the perspective of each character, means for the server to receive the generated story data, means for the server to categorize and store the received story data, and means for the user to view stories by perspective using a terminal. This enables users to efficiently and intuitively set basic story settings and character settings, and easily generate, manage, and view stories from each character's perspective.

[0625] A "user" is a person who uses the system to input basic story settings and character settings and view the generated story data.

[0626] A "terminal" is an electronic device such as a computer, smartphone, or tablet operated by a user, and is a device for inputting and transmitting story settings and viewing stories from different perspectives.

[0627] The "server" is a central processing unit that receives data entered by the user, sends it to the generative AI model, receives the results, and stores them in a database.

[0628] A "generative AI model" is an artificial intelligence model that generates a story from each character's perspective based on the basic story settings and character settings provided by the user.

[0629] "Basic story setting" refers to information that constitutes the outline of the entire story, such as the story's title and theme.

[0630] "Character settings" refers to information such as the names, roles, and characteristics of the characters that appear in the story.

[0631] A "form" is a set of input fields on a web page that allows a user to enter basic story and character settings.

[0632] An "HTTP request" is an Internet communication protocol used to send user input data to a server.

[0633] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and representing data.

[0634] A "REST API" is an application programming interface based on Representational State Transfer, a standardized means of sending and receiving data between systems.

[0635] The "database" is an electronic data repository for systematically storing and managing received story data.

[0636] "Categorization" refers to classifying the generated narrative data according to specific perspectives.

[0637] "YourSTORY Library" is a collection of data storage and user interfaces within the system that users access to view narrative data from different perspectives.

[0638] A "prompt sentence" is an instruction sentence that instructs the generative AI model to generate a story, and is a sentence that contains the necessary input data.

[0639] The present invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[0640] The system consists of the following main means:

[0641] 1. Means for inputting and sending story settings

[0642] The user uses the device to input the basic story and character settings (e.g., the story title, the names and roles of the characters). To do this, the user opens a browser and enters the necessary information into a dedicated input form. When the user clicks the "Submit" button, the device asynchronously sends this data to the server as an HTTP POST request.

[0643] 2. Means of converting and transmitting data to the generative model

[0644] The server converts the received user input information into a format suitable for the generative model (for example, JSON format). To do this, the server structures the received data and processes it into a format that is easy for the generative model to understand. After conversion, the server sends this data to the generative AI model as an API call. As a concrete example, we will implement the API call using Python's requests library.

[0645] 3. Narrative Generation Methods

[0646] Based on the data received, the generative AI model generates a story from each character's perspective. Using the story of Cinderella as an example, the generative AI model generates different stories from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective. Stories from each perspective are generated using the generative AI model's prompt sentences.

[0647] Example prompt sentence:

[0648] "Generate a story from Cinderella's point of view: {configuration data}"

[0649] "Generate a story from the stepmother's point of view: {config data}"

[0650] 4. Means of receiving the generative story

[0651] The server receives the story data generated by the generative AI model. The generated data is divided into separate data for each character's perspective, and the server receives this data all at once.

[0652] 5. Storage of story data

[0653] The server categorizes the received story data and stores it in a NoSQL database (e.g., MongoDB). Specifically, the generated story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince" based on each perspective, and each piece of data is saved as a document in the database.

[0654] 6. How to view stories from different perspectives

[0655] Users access the YourSTORY library using their device and view stories from each character's perspective. When the user selects a specific perspective from the displayed list, the device retrieves the necessary story data from the database and displays it on the screen in a format that is easy for the user to view. Specifically, it uses a front-end framework (e.g., Vue.js or React) to asynchronously retrieve data using AJAX or the Fetch API and dynamically updates the screen display.

[0656] In this way, the system of the present invention is configured to allow the user to set basic story and character settings, and to easily create, manage, and view stories from each character's perspective.

[0657] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0658] Step 1:

[0659] The user inputs the basic story setting and character settings.

[0660] The user opens a browser on their device and enters details such as the story title, theme, and the names and roles of the characters into a dedicated input form. Once the input is complete, they click the "Submit" button.

[0661] Input: Basic story setting and character information

[0662] Output: Data packet to send (in JSON format)

[0663] Step 2:

[0664] The terminal transmits the input information to the server.

[0665] When the user clicks the "Submit" button, the terminal uses AJAX to send the input data to the server as an HTTP POST request.

[0666] Input: Story setting and character setting information entered by the user

[0667] Output: Data packets sent to the server

[0668] Step 3:

[0669] The server converts the received input data into a format suitable for the generative model.

[0670] The server converts the received data into JSON format, creating a structure that is easy for the generative AI model to understand.

[0671] Input: User input data sent from the terminal

[0672] Output: Structured JSON data to send to a generative AI model

[0673] Step 4:

[0674] The server sends the converted data to the generative AI model.

[0675] The server sends a POST request to an API endpoint, providing the data required for the generative AI model.

[0676] Input: User-supplied data in JSON format

[0677] Output: API call to the generative AI model and its response

[0678] Step 5:

[0679] Based on the data received, the generative AI model generates a story from each character's perspective.

[0680] The generative AI model generates a story from each character's perspective using prompt sentences based on the input data provided.

[0681] For example, the prompt is:

[0682] "Generate a story from Cinderella's point of view: {configuration data}", "Generate a story from the stepmother's point of view: {configuration data}"

[0683] Input: JSON data sent to the generative AI model

[0684] Output: Story data for each character's perspective

[0685] Step 6:

[0686] The server receives the narrative data generated from the generative AI model.

[0687] The server checks the API response and receives the narrative data for each generated perspective.

[0688] Input: Response data from the generative AI model

[0689] Output: Story data stored on the server

[0690] Step 7:

[0691] The server categorizes the received story data and stores it in a database.

[0692] The server classifies the received story data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and stores each piece of data in a NoSQL database.

[0693] Input: Story data divided into perspectives

[0694] Output: Categorized narrative data stored in a database

[0695] Step 8:

[0696] Users use their devices to access the YourSTORY library and browse stories from different perspectives.

[0697] When a user accesses the library and selects a story from a particular perspective from the displayed list, the terminal sends a request to the server to obtain the required data.

[0698] Input: Request information for the viewpoint selected by the user

[0699] Output: Narrative data from a specified point of view

[0700] Step 9:

[0701] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[0702] The device retrieves data asynchronously using AJAX or the Fetch API, and updates the screen display in a user-friendly format using Vue.js or React.

[0703] Input: Data retrieval request based on user request

[0704] Output: Story data displayed on the user's device

[0705] (Application example 1)

[0706] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0707] There is a need for a system that allows users to easily input basic story settings and character settings, generate stories from multiple perspectives based on that information, and allow users to easily view those stories. However, existing technologies lack the ability to properly process user-input information or manage data received from the generative model, making deployment as a smartphone application particularly difficult. There is also a need for a system that allows the generated story data to be easily saved and managed, and be viewable by perspective.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0709] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user-input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for a user to view stories by perspective, means for delivering the story data to a content delivery service, and means for providing the story data as an application that runs on a smartphone. This allows story data generated from multiple perspectives to be efficiently managed and delivered, and allows users to easily access and view it.

[0710] "Story Basics" is information that the user enters to form the framework of the story, such as the story's theme, background, and major events.

[0711] "Character settings" involve the user entering detailed attributes of each character appearing in the story, such as their name, role, personality, and characteristics.

[0712] "User-input information" is a general term for information about the basic story setting and character settings that a user provides to the system.

[0713] A "generative model" is an artificial intelligence model for automatically generating a story based on received user input information, and here it is particularly applicable to generating a story from multiple perspectives.

[0714] "Narrative data" refers to textual data of a story created by a generative model, including multiple versions based on each character's perspective.

[0715] "Categorization" is the act of classifying and organizing received narrative data according to specific criteria.

[0716] "Storage" refers to saving the received story data in a database or storage.

[0717] "Perspective stories" refers to different versions of a story that are generated based on the perspective of each character in the story.

[0718] "Content distribution service" is a general term for online platforms that provide generated story data to users via the Internet.

[0719] "Smartphone-enabled application" refers to a software program that can be installed and executed on a smartphone device, and here means, in particular, one that has story creation and viewing capabilities.

[0720] This invention provides a system that generates stories from multiple perspectives and allows users to view them from different perspectives. Specifically, the system configures a means for users to input basic story settings and character settings, send the data to a generative AI model for processing, and store and distribute the generated story data.

[0721] 1. System Configuration

[0722] The basic components of the system are:

[0723] 1. How to input and submit story settings:

[0724] The user uses the terminal to input the basic story settings and character settings.

[0725] The entered information is sent to the server as an HTTP request.

[0726] 2. Means of sending to the generative model:

[0727] The input data received by the server is converted into JSON format.

[0728] The transformed data is sent to a generative AI model, which may be powered by OpenAI or a similar generative model.

[0729] 3. Narrative generation tools:

[0730] Based on the data received, the generative AI model generates a story from each character's perspective.

[0731] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[0732] 4. Means of receiving the generative story:

[0733] The server receives the narrative data generated from the generative AI model.

[0734] The received data is divided into perspectives for each character.

[0735] 5. Narrative data storage means:

[0736] The server categorizes the received story data and stores it in a database.

[0737] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[0738] 6. How to view the story by point of view:

[0739] The user uses a device such as a smartphone to view the story from a different perspective.

[0740] In response to a user's request, the server retrieves the appropriate story data from the database and displays it on the screen.

[0741] 7. Content Delivery Methods:

[0742] The server distributes the generated story data to a platform (content distribution service) that provides it to users via the Internet.

[0743] This allows users to easily access and view stories generated from multiple perspectives.

[0744] 8. Application Delivery Method:

[0745] All of the above functions are implemented as an application for smartphones.

[0746] The application again provides an interface for users to input story settings and view the stories generated by the generative model.

[0747] 2. Program Processing

[0748] The system is built using Python and the Flask framework, and uses the HTTP protocol for data communication, with JSON as the data format.

[0749] 1. Hardware and Software:

[0750] The hardware used includes the user's device (smartphone or computer) and a server.

[0751] The software used includes generative AI models (e.g., OpenAI's GPT-4), frameworks (Flask), and database management systems (e.g., SQLite or MongoDB).

[0752] 2. Data processing and calculation:

[0753] User input data is received by the server and converted to JSON format.

[0754] The converted data is sent to a generative AI model to generate a story.

[0755] The generated story data is received, categorized by character, and stored in a database.

[0756] - Upon user request, story data from a specific character's perspective is retrieved from the database and displayed on the screen.

[0757] 3. Specific Examples

[0758] For example, the user enters the following:

[0759] Title: Cinderella

[0760] character:

[0761] Cinderella: "She has a kind heart"

[0762] Stepmother: "Strict and jealous"

[0763] Older sisters: "Mean personality"

[0764] Prince: "True and brave"

[0765] An example of a prompt for the generative AI model would be, "Please describe the story in detail from Cinderella's point of view." This will enable efficient management and distribution of stories generated from multiple perspectives, making them easily accessible and viewable by users.

[0766] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0767] Step 1:

[0768] The user uses the terminal to input the basic story settings and character settings.

[0769] The entered information (story title, character name, role, personality, etc.) is converted into JSON format within the device application and sent to the server as an HTTP request.

[0770] Input: Data entered by the user for the setting.

[0771] Output: JSON formatted data sent to the server.

[0772] Step 2:

[0773] The server rechecks the received JSON data and converts it into a format suitable for the generative model.

[0774] Validate and format the data as needed, and create prompts to send to the generative AI model.

[0775] Input: JSON formatted data received from the user.

[0776] Output: The prompt sent to the generative AI model.

[0777] Step 3:

[0778] The server sends the prompt sentence to the generative AI model as an API request.

[0779] The generative AI model generates a story from each character's perspective based on the prompt text it receives.

[0780] Input: The prompt sentence sent to the generative AI model.

[0781] Output: Generated narrative text data.

[0782] Step 4:

[0783] The server receives the generated story data as a response from the generative AI model.

[0784] This data is divided into perspectives for each character.

[0785] Input: Narrative data received as a response from a generative AI model.

[0786] Output: Generated narrative data by viewpoint.

[0787] Step 5:

[0788] The server categorizes the received story data by character and stores it in a database.

[0789] When storing, it creates appropriate indexes to facilitate later retrieval and access.

[0790] Input: Narrative data separated by point of view.

[0791] Output: Narrative data stored in a database.

[0792] Step 6:

[0793] The user uses the terminal to request a story from each character's perspective.

[0794] The application on the terminal sends the request to the server.

[0795] Input: A story view request from a user.

[0796] Output: The request data sent to the server.

[0797] Step 7:

[0798] The server retrieves the story data from the relevant character's perspective from the database and sends it to the terminal.

[0799] Here, the appropriate data is retrieved based on the request and a response is sent to the user.

[0800] Input: The browse request sent to the server.

[0801] Output: The narrative data sent back to the terminal.

[0802] Step 8:

[0803] The device displays the received story data to the user.

[0804] Users can read the story from each character's perspective through the device screen.

[0805] Input: Story data sent from the server.

[0806] Output: The story that is displayed to the user.

[0807] Step 9:

[0808] The server distributes the generated story data to a content distribution service via the Internet.

[0809] This is to allow more users to view stories on different devices.

[0810] Input: Generated narrative data.

[0811] Output: Narrative data delivered to a content delivery service.

[0812] Step 10:

[0813] The device is designed to run all of the above functions as smartphone applications.

[0814] The application provides an interface for users to re-enter story settings and view the stories generated by the generative model.

[0815] Input: Various user inputs and data from the server.

[0816] Output: An integrated narrative generation and viewing experience provided to the user.

[0817] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0818] This invention combines an emotion engine with a system in which a user inputs the basic story setting and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[0819] System Program Overview

[0820] The system includes the following means:

[0821] 1. Means for inputting and sending story settings

[0822] 2. Means of sending to the generative model

[0823] 3. Narrative Generation Methods

[0824] 4. Means of receiving the generative story

[0825] 5. Storage of story data

[0826] 6. How to view stories from different perspectives

[0827] 7. Emotion Engine

[0828] 8. Emotion-based narrative adjustment

[0829] A natural language description of the program

[0830] A means of inputting and sending story settings

[0831] The user uses the terminal to input the basic story and character settings, including the story title, the names, roles, and personalities of the characters.

[0832] The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[0833] Sending to the Generative Model

[0834] The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[0835] The server sends the transformed data to the generative model, which is then passed to the model via an API call.

[0836] Story Generation Method

[0837] Based on the data received, the generative AI model generates a story from each character's perspective, for example, the story of Cinderella from multiple characters' perspectives.

[0838] Means of receiving generative stories

[0839] The server receives the response from the generative AI model and the generated story data, which includes story data divided into perspectives for each character.

[0840] A means of storing story data

[0841] The server categorizes the received story data and stores it in a database. Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and saved in the database.

[0842] A way to view stories from different perspectives

[0843] The user accesses the YourSTORY library using a device and reads stories from each character's perspective. They log in to the library using the device's browser, select the story from the perspective they want to see, and display it.

[0844] Emotion engine and emotion-based story adjustment

[0845] Emotion Engine

[0846] The emotion engine recognizes the user's emotions by analyzing their facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[0847] Emotion-based narrative adjustment

[0848] The server receives the emotion data sent from the emotion engine.

[0849] The generative model dynamically adjusts the story based on the user's emotional data, for example, changing the tone of the story to be more positive if the user is in a happy state.

[0850] The story the user views on the device is dynamically adjusted to correspond to the user's emotional state.

[0851] Explanation of specific examples

[0852] 1. The user inputs the story setting of "Cinderella" on the device, including details of the characters "Cinderella," "Stepmother," "Sisters," and "Prince."

[0853] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[0854] 3. The server sends the converted data to the generative model, which then generates a story from each character's perspective.

[0855] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[0856] 5. The user uses the device to access the YourSTORY library, selects "Cinderella from the Stepmother's Point of View," and views it.

[0857] 6. The emotion engine recognizes the user's emotion, and the server receives this emotion data.

[0858] 7. The generative model dynamically adjusts the story content based on emotional data. For example, if the user is sad, the tone of the story will be changed to be more emotional.

[0859] 8. The stories users view on their devices will respond to their emotional state, providing a more personalized experience.

[0860] In this way, the system generates stories that take the user's emotions into account, allowing the user to have a more multifaceted and emotionally rich story experience.

[0861] The processing flow will be explained below.

[0862] Step 1:

[0863] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[0864] Step 2:

[0865] The terminal sends the data entered by the user to the server. Specifically, the data in the input form is collected and sent to the server as an HTTP request.

[0866] Step 3:

[0867] The server analyzes the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into the required format.

[0868] Step 4:

[0869] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the required data.

[0870] Step 5:

[0871] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses an internal algorithm to generate a story from Cinderella's perspective, the stepmother's perspective, the sisters' perspective, and the prince's perspective.

[0872] Step 6:

[0873] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response and analyzes and extracts story data for each perspective.

[0874] Step 7:

[0875] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[0876] Step 8:

[0877] The user accesses the YourSTORY library using a device and browses stories from different perspectives. Specifically, the user logs into the YourSTORY library using the device's browser, selects the story from the perspective they want to view, and displays it.

[0878] Step 9:

[0879] The emotion engine recognizes the user's emotions by capturing the user's facial expressions and voice through the device's camera and microphone, and then uses an emotion analysis algorithm to determine the user's emotional state.

[0880] Step 10:

[0881] The server receives the emotional data sent from the emotion engine. Specifically, the server receives the analysis results of the emotional data and uses them to adjust the tone and content of the story.

[0882] Step 11:

[0883] The generative model dynamically adjusts the content of the story based on the emotional data. Specifically, the generative model receives emotional data as input and changes the tone and event content of the story according to the user's emotions.

[0884] Step 12:

[0885] The story that the user is viewing on the device is dynamically adjusted according to the user's emotional state. Specifically, if the user is in a happy state, the tone of the story is adjusted to a positive one.

[0886] This series of processes allows users to enjoy a personalized story experience that is tailored to their emotions.

[0887] Example 2

[0888] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0889] Conventional story generation systems generate static stories based on basic settings and character configurations entered by the user, and suffer from a lack of personalization based on the user's emotional state, making it difficult for users to obtain an emotionally rich story experience.

[0890] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0891] In this invention, the server includes means for the user to input basic story settings and character settings, means for transmitting the information input by the user to the generative model, means for generating a story based on the viewpoint of each character, means for receiving the generated story data, means for categorizing and storing the received story data, an emotion engine for recognizing the user's emotions, means for dynamically adjusting the story based on the emotion data from the emotion engine, and means for the user to view stories from different viewpoints, thereby enabling dynamic story generation that corresponds to the user's emotional state.

[0892] A "user" is a person who uses this system to input story settings and character settings.

[0893] "Basic story settings" are information that forms the framework of the story, such as the title of the story, the main storyline, and the setting.

[0894] "Character settings" are detailed information about the characters that appear in the story, such as their names, personalities, and roles.

[0895] A "generative model" is an algorithm or program that generates a story based on information input by a user.

[0896] "Story data" is data containing the content of a story generated by a generative model.

[0897] An "emotion engine" is software or hardware capable of recognizing a user's emotional state and adapting dialogue and output accordingly.

[0898] "Emotion data" is data obtained as a result of the emotion engine analyzing the user's emotions.

[0899] "Dynamic adjustment means" is a function that changes the content of the generated story in real time according to the user's emotional state.

[0900] A "perspective story" is a multiple story told from the perspective of each character in the story.

[0901] This invention combines an emotion engine with a system in which a user inputs basic story settings and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[0902] Hardware and Software Examples

[0903] Devices: PCs, smartphones, tablets, etc.

[0904] Server: Cloud server, web server

[0905] Generative AI models: Generative models using natural language processing (NLP) (e.g., GPT-3)

[0906] Emotion engine: facial expression recognition software, voice analysis software (e.g., Amazon Rekognition, Microsoft Azure Emotion API)

[0907] Specific system configuration

[0908] 1. The user uses a terminal to input the basic story and character settings, including the story title and the names, roles, and personalities of the characters.

[0909] Specifically, the user inputs the story title "Cinderella" and details (personalities and roles) of the characters appearing in the story: "Cinderella," "Prince," "Stepmother," and "Sisters."

[0910] 2. The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[0911] 3. The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[0912] 4. The server sends the transformed data to the generative model, which is passed to the model via an API call.

[0913] 5. Based on the received data, the generative AI model generates a story from each character's perspective. For example, the story of Cinderella is generated from the perspectives of multiple characters.

[0914] 6. The server receives the response from the generative AI model and the generated story data, which includes story data separated by each character's perspective.

[0915] 7. The server categorizes the received story data and stores it in the database. Specifically, the story data is classified into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and saved in the database.

[0916] 8. The user accesses the YourSTORY library using a device and browses stories from each character's perspective. The user logs in to the library using the device's browser, selects the story from the perspective they want to view, and displays it.

[0917] 9. The emotion engine recognizes the user's emotions by analyzing the user's facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[0918] 10. The server receives the emotion data sent from the emotion engine.

[0919] 11. The generative model dynamically adjusts the story based on the user's emotional data. For example, if the user is in a happy state, it changes the tone of the story to be more positive.

[0920] 12. The story the user views on their device is dynamically adjusted to correspond to the user's emotional state.

[0921] Specific prompt examples

[0922] Example 1: Generate a story from Cinderella's point of view.

[0923] Example 2: If the user is in a happy state, change the tone of the story to a positive one.

[0924] As described above, the present invention is a system that generates and dynamically adjusts a story based on user input, providing a more personalized story experience.

[0925] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0926] The flow of this system's program processing

[0927] Step 1:

[0928] The user uses a terminal to input the basic setting and character settings of the story.

[0929] Input: The user enters information such as the story title, character names, roles, and personalities into an input form.

[0930] Specific actions: For example, enter the story title "Cinderella" and the names and personalities of "Cinderella," "Prince," "Stepmother," and "Stepsisters" (e.g., Cinderella = kind, Prince = brave).

[0931] Output: The entered information is stored in a data structure within the terminal.

[0932] Step 2:

[0933] The terminal transmits the input information to the server.

[0934] Input: Story and character data entered by the user in Step 1.

[0935] Specific behavior: When the user clicks the "Submit" button, the data is sent to the server as an HTTP request.

[0936] Output: The data sent to the server.

[0937] Step 3:

[0938] The server converts the received data into a format suitable for the generative model.

[0939] Input: Story and character setting data received by the server.

[0940] Specific operation: Converts received data into, for example, JSON format and organizes the data into a fair format.

[0941] Output: Data converted to JSON format.

[0942] Step 4:

[0943] The server sends the transformed data to the generative model.

[0944] Input: Story and characterization data converted to JSON format.

[0945] What it does: Makes an API call and sends data to the appropriate endpoint.

[0946] Output: The data passed to the generative model.

[0947] Step 5:

[0948] Based on the data received, the generative AI model generates a story from each character's perspective.

[0949] Input: Story and characterization data in JSON format.

[0950] How it works: The generative AI model uses algorithms to dynamically generate a story from each character's perspective.

[0951] Output: Narrative data generated for each character.

[0952] Step 6:

[0953] The server receives the response from the generative AI model and receives the generated story data.

[0954] Input: Response data from the generative AI model.

[0955] Specific operation: Analyze the response and save the story data divided by character's perspective on the server.

[0956] Output: Story data from each character's perspective.

[0957] Step 7:

[0958] The server stores the received story data in a database by category.

[0959] Input: Story data from character perspectives.

[0960] Specific operation: For example, classify into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and save them in a database.

[0961] Output: Story data in a categorized database.

[0962] Step 8:

[0963] The user uses a terminal to access the YourSTORY library and view stories from each character's perspective.

[0964] Input: Categorized story data.

[0965] Specific operation: Log in to the library using your device's browser, select the story from the perspective you want to see, and display it.

[0966] Output: Narrative content from a user-specified point of view.

[0967] Step 9:

[0968] The emotion engine recognizes the user's emotions.

[0969] Input: The user's facial expressions, voice, and other biometric signals acquired from the device.

[0970] Specific operation: Data is acquired through the camera and microphone, and analyzed to detect emotional state.

[0971] Output: Detected user emotion data.

[0972] Step 10:

[0973] The server receives the emotion data sent from the emotion engine.

[0974] Input: Emotion data sent from the emotion engine.

[0975] Specific operation: The server receives the emotion data and inputs it into the analysis system.

[0976] Output: Emotion data in the server.

[0977] Step 11:

[0978] A generative model dynamically adjusts the narrative based on the user's emotional data.

[0979] Input: User emotion data.

[0980] What it does: The generative model analyzes the emotional data and changes the tone and content of the generated story based on that.

[0981] Output: Dynamically adjusted narrative data that responds to the user's emotions.

[0982] Step 12:

[0983] The story the user views on their device will correspond to the user's emotional state.

[0984] Input: Dynamically adjusted narrative data.

[0985] What it does: When users revisit a story, they will see real-time updates based on sentiment.

[0986] Output: A personalized narrative experience.

[0987] (Application example 2)

[0988] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0989] Conventional story generation systems were able to generate a story from a fixed perspective based on user-entered settings, but lacked the ability to dynamically adjust the story content in response to the user's emotional state. This made it difficult to provide a story optimized for each user's individual emotional experience. Furthermore, there was a lack of an efficient system for generating stories from each character's perspective. This limited the user's ability to enjoy the story by changing their perspective.

[0990] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0991] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for the user to view stories by perspective, means for recognizing the user's emotions, and means for dynamically adjusting the content of the story based on the emotions. This enables a personalized story experience according to the user's emotional state, making it possible to provide a system that allows users to enjoy stories from different perspectives.

[0992] "Means for users to input basic story settings and character settings" refers to the means by which users input the story title, characters' names, roles, personalities, etc.

[0993] "Means for sending user-input information to a generative model" refers to means for sending information on the basic story setting and character settings entered by the user to a generative AI model.

[0994] "Means for generating a story from each character's perspective from a generative model" refers to a means for a generative AI model to generate a story from each character's perspective based on information received from the user.

[0995] "Means for receiving generated story data" refers to means for receiving story data generated from a generative AI model.

[0996] The "means for categorizing and storing received story data" is a means for classifying received story data into specific categories and storing them in a database.

[0997] "Means for users to view stories from different perspectives" refers to means for users to view stories generated from the perspectives of each character.

[0998] "Means for recognizing the user's emotions" refers to a means for analyzing the user's facial expressions, voice, biometric signals, etc. to detect the user's emotional state.

[0999] "Means for dynamically adjusting story content based on emotions" refers to means for adapting and adjusting the content of a generated story in real time based on the recognized emotional state of a user.

[1000] MODE FOR CARRYING OUT THE INVENTION

[1001] System Overview

[1002] This invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. Furthermore, the system has the ability to recognize the user's emotions and dynamically adjust the story content based on those emotions. This system allows users to experience a personalized story from each perspective.

[1003] Hardware and software used

[1004] Hardware: Smartphones, smart glasses, head-mounted displays

[1005] Software: Python 3.8+, Flask (server-side), Emotion Recognition API

[1006] Data processing and data calculation

[1007] Enter and submit story settings

[1008] The user inputs the story title, characters' names, roles, personalities, etc. into a smartphone or other device. The input data is converted into JSON format and sent to the server as an HTTP request, allowing the server to receive the input data from the user.

[1009] Sending to the Generative Model

[1010] The server converts the received user story setting and character setting information into a format suitable for the generative AI model, and then sends the converted data to the generative AI model via an API call.

[1011] Story Generation

[1012] The generative AI model generates a story from each character's perspective based on the received data. For example, it generates the story of the fairy tale "Cinderella" from each character's perspective. This generated story data is sent back to the server.

[1013] Receiving and storing generated stories

[1014] The server receives the story data generated by the generative AI model, categorizes it by each character's perspective, and stores it in a database, improving search efficiency when users later view the story by perspective.

[1015] Viewing stories by point of view

[1016] Users can use their devices to view stories from different points of view, for example, they can select the Cinderella story as "from the stepmother's point of view" and start reading.

[1017] Emotion recognition and dynamic adjustment of narrative

[1018] The user's device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API. This emotional data is sent to the server, which then invokes a generative AI model based on the emotional data to dynamically adjust the content of the story. For example, if the user is in a happy state, the tone of the story will be changed to a more positive one.

[1019] Specific examples

[1020] 1. Enter the story setting

[1021] The user inputs the story setting for "Cinderella" on the device, along with details of the characters: "protagonist," "villain," "rival," and "savior."

[1022] Example prompt sentence:

[1023] Enter the story setting for Cinderella. Characters:

[1024] Name: Cinderella, Role: Protagonist, Personality: Kind

[1025] Name: Stepmother, Role: Antagonist, Character: Ruthless

[1026] Name: Older sisters, Role: Rival, Personality: Jealous

[1027] Name: Prince, Role: Savior, Personality: Sense of Justice

[1028] 2. Send to the generative model

[1029] The server sends the story setting to the generative AI model, which generates a story from each perspective.

[1030] 3. Receiving and storing generated stories

[1031] The generated stories are stored in a database by point of view.

[1032] 4. Emotion recognition

[1033] If the user's emotion is recognized as "happy," the system adjusts the story to a more positive tone.

[1034] 5. Viewing stories from different perspectives

[1035] Users view the adapted story on their device.

[1036] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1037] Step 1:

[1038] The user inputs the story setting.

[1039] Specifically, users use their smartphones or other devices to input the story title, characters' names, roles, personalities, etc. The input data is retrieved from the form and converted into JSON format.

[1040] Input: Basic story setting and character settings

[1041] Output: Story setting data converted to JSON format

[1042] Step 2:

[1043] The terminal transmits story setting data to the server.

[1044] Once the user has finished entering the settings, they press the "Submit" button, which sends an HTTP request from the device to the server, which then checks the received data and converts it into an appropriate format (e.g., JSON).

[1045] Input: Story setting data converted to JSON format

[1046] Output: Story setting data sent to the server

[1047] Step 3:

[1048] The server sends the data to the generative AI model.

[1049] The server verifies the accuracy of the received data, then converts it into a format suitable for the generative AI model, and sends this converted data to the generative AI model via an API call.

[1050] Input: Data converted into a format suitable for generative AI models

[1051] Output: Data sent to the generative AI model

[1052] Step 4:

[1053] A generative AI model generates the story.

[1054] The generative AI model generates a story from each character's perspective based on the received data. This generation process uses natural language processing technology, particularly analyzing prompts to develop the story. The generated story data is organized by each character's perspective and sent back to the server.

[1055] Input: Data sent to the generative AI model

[1056] Output: Narrative data generated by perspective

[1057] Step 5:

[1058] The server receives the generated story data and stores it in a database.

[1059] The server receives the story data sent from the generative AI model, categorizes the received data by perspective, and stores it in a database, which improves future search efficiency.

[1060] Input: Narrative data generated by perspective

[1061] Output: Categorized narrative data stored in a database

[1062] Step 6:

[1063] Users view stories from different perspectives.

[1064] The user uses the terminal to select a story by point of view and begin viewing. The terminal accesses the database and displays the selected story.

[1065] Input: Narrative data stored by point of view

[1066] Output: The story displayed on the user's terminal

[1067] Step 7:

[1068] The device recognizes the user's emotions.

[1069] The device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API, and sends the resulting data to the server.

[1070] Input: Emotional data such as user facial expressions, voice, and biometric signals

[1071] Output: Emotion state data analyzed by the Emotion Recognition API

[1072] Step 8:

[1073] The server invokes a generative AI model based on the emotional data and dynamically adjusts the content of the story.

[1074] The server receives the emotional state data and sends prompts to the generative AI model again to adjust the story content, changing the tone and development of the story according to the user's emotional state. The adjusted story data is then regenerated and sent to the user's device.

[1075] Input: Emotion state data sent from the Emotion Recognition API

[1076] Output: Dynamically adjusted narrative data

[1077] Step 9:

[1078] The user views the tailored story.

[1079] The user then views the adjusted story on their device again, providing a story experience optimized for the user's emotional state.

[1080] Input: Dynamically adjusted narrative data

[1081] Output: The adjusted story displayed on the user's terminal

[1082] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1084] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1085] [Third embodiment]

[1086] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1087] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1089] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1090] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1093] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1094] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1096] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1097] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1098] The present invention is a system in which a user inputs the basic setting and character settings of a story, and a generative model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[1099] System Program Overview

[1100] The system includes the following means:

[1101] 1. Means for inputting and sending story settings

[1102] 2. Means of sending to the generative model

[1103] 3. Narrative Generation Methods

[1104] 4. Means of receiving the generative story

[1105] 5. Storage of story data

[1106] 6. How to view stories from different perspectives

[1107] A natural language description of the program

[1108] A means of inputting and sending story settings

[1109] The user uses the terminal to input the basic story settings and character settings (for example, the story title, the names and roles of the characters).

[1110] The terminal sends the entered information to the server. Specifically, when a user enters data into an input form and clicks the "Submit" button, the terminal sends this data to the server as an HTTP request.

[1111] Sending to the Generative Model

[1112] The server converts the received input data into a format suitable for the generative model, often JSON format.

[1113] The server sends the transformed data to the generative model, which is done as an API call, providing the generative model with the data it needs.

[1114] Story Generation Method

[1115] Based on the data received, the generative AI model generates a story from each character's perspective.

[1116] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[1117] Means of receiving generative stories

[1118] The server receives the story data generated by the generative AI model. The received data is divided into perspectives for each character.

[1119] A means of storing story data

[1120] The server categorizes the received story data and stores it in a database.

[1121] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[1122] A way to view stories from different perspectives

[1123] Users use their devices to access the YourSTORY library and view stories from each character's perspective.

[1124] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[1125] Explanation of specific examples

[1126] 1. The user inputs the basic setting of the story "Cinderella" into the device, including the characters "Cinderella," "Stepmother," "Sisters," and "Prince," along with their detailed settings.

[1127] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[1128] 3. The server sends the transformed data to the generative model, which then generates a story from each character's point of view.

[1129] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[1130] 5. Users can access the YourSTORY library using their device, select and view "Cinderella from the Stepmother's Point of View," and understand the story from multiple perspectives.

[1131] This system works by combining these methods to help users understand and learn stories from multiple perspectives.

[1132] The processing flow will be explained below.

[1133] Step 1:

[1134] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[1135] Step 2:

[1136] The terminal sends the data entered by the user to the server. Specifically, the terminal collects the data from the input form and sends it to the server as an HTTP request.

[1137] Step 3:

[1138] The server parses the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into an appropriate data format.

[1139] Step 4:

[1140] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the data.

[1141] Step 5:

[1142] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses its internal algorithm to generate a story from each perspective and returns it as a response.

[1143] Step 6:

[1144] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response, analyzes it, and extracts the story for each perspective.

[1145] Step 7:

[1146] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[1147] Step 8:

[1148] Users access the YourSTORY library using their device and view stories from different perspectives. Specifically, users log in to the YourSTORY library using the browser on their device, select the story from the perspective they want to view, and then perform the necessary operations to display it.

[1149] Step 9:

[1150] In response to a user request, the device retrieves the appropriate story data from the database and displays it on the screen. Specifically, the device sends an HTTP request to the server and displays the story data returned by the server in the browser.

[1151] Example 1

[1152] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1153] Conventional story generation systems require large amounts of data processing and complex procedures when generating stories based on each character's perspective from the basic story and character settings entered by the user, making operation cumbersome. Furthermore, there were not enough systems that allowed users to easily browse stories by perspective. Furthermore, there was a lack of systems that automatically categorized and saved the generated story data. This made it difficult for users to create, manage, and browse stories efficiently and in a unified manner.

[1154] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1155] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the input user information to the server, means for the server to convert the user-input information into a format suitable for the generative model, means for the server to transmit the converted information to the generative AI model, means for the generative AI model to generate a story based on the perspective of each character, means for the server to receive the generated story data, means for the server to categorize and store the received story data, and means for the user to view stories by perspective using a terminal. This enables users to efficiently and intuitively set basic story settings and character settings, and easily generate, manage, and view stories from each character's perspective.

[1156] A "user" is a person who uses the system to input basic story settings and character settings and view the generated story data.

[1157] A "terminal" is an electronic device such as a computer, smartphone, or tablet operated by a user, and is a device for inputting and transmitting story settings and viewing stories from different perspectives.

[1158] The "server" is a central processing unit that receives data entered by the user, sends it to the generative AI model, receives the results, and stores them in a database.

[1159] A "generative AI model" is an artificial intelligence model that generates a story from each character's perspective based on the basic story settings and character settings provided by the user.

[1160] "Basic story setting" refers to information that constitutes the outline of the entire story, such as the story's title and theme.

[1161] "Character settings" refers to information such as the names, roles, and characteristics of the characters that appear in the story.

[1162] A "form" is a set of input fields on a web page that allows a user to enter basic story and character settings.

[1163] An "HTTP request" is an Internet communication protocol used to send user input data to a server.

[1164] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and representing data.

[1165] A "REST API" is an application programming interface based on Representational State Transfer, a standardized means of sending and receiving data between systems.

[1166] The "database" is an electronic data repository for systematically storing and managing received story data.

[1167] "Categorization" refers to classifying the generated narrative data according to specific perspectives.

[1168] "YourSTORY Library" is a collection of data storage and user interfaces within the system that users access to view narrative data from different perspectives.

[1169] A "prompt sentence" is an instruction sentence that instructs the generative AI model to generate a story, and is a sentence that contains the necessary input data.

[1170] The present invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[1171] The system consists of the following main means:

[1172] 1. Means for inputting and sending story settings

[1173] The user uses the device to input the basic story and character settings (e.g., the story title, the names and roles of the characters). To do this, the user opens a browser and enters the necessary information into a dedicated input form. When the user clicks the "Submit" button, the device asynchronously sends this data to the server as an HTTP POST request.

[1174] 2. Means of converting and transmitting data to the generative model

[1175] The server converts the received user input information into a format suitable for the generative model (for example, JSON format). To do this, the server structures the received data and processes it into a format that is easy for the generative model to understand. After conversion, the server sends this data to the generative AI model as an API call. As a concrete example, we will implement the API call using Python's requests library.

[1176] 3. Narrative Generation Methods

[1177] Based on the data received, the generative AI model generates a story from each character's perspective. Using the story of Cinderella as an example, the generative AI model generates different stories from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective. Stories from each perspective are generated using the generative AI model's prompt sentences.

[1178] Example prompt sentence:

[1179] "Generate a story from Cinderella's point of view: {configuration data}"

[1180] "Generate a story from the stepmother's point of view: {config data}"

[1181] 4. Means of receiving the generative story

[1182] The server receives the story data generated by the generative AI model. The generated data is divided into separate data for each character's perspective, and the server receives this data all at once.

[1183] 5. Storage of story data

[1184] The server categorizes the received story data and stores it in a NoSQL database (e.g., MongoDB). Specifically, the generated story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince" based on each perspective, and each piece of data is saved as a document in the database.

[1185] 6. How to view stories from different perspectives

[1186] Users access the YourSTORY library using their device and view stories from each character's perspective. When the user selects a specific perspective from the displayed list, the device retrieves the necessary story data from the database and displays it on the screen in a format that is easy for the user to view. Specifically, it uses a front-end framework (e.g., Vue.js or React) to asynchronously retrieve data using AJAX or the Fetch API and dynamically updates the screen display.

[1187] In this way, the system of the present invention is configured to allow the user to set basic story and character settings, and to easily create, manage, and view stories from each character's perspective.

[1188] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] The user inputs the basic story setting and character settings.

[1191] The user opens a browser on their device and enters details such as the story title, theme, and the names and roles of the characters into a dedicated input form. Once the input is complete, they click the "Submit" button.

[1192] Input: Basic story setting and character information

[1193] Output: Data packet to send (in JSON format)

[1194] Step 2:

[1195] The terminal transmits the input information to the server.

[1196] When the user clicks the "Submit" button, the terminal uses AJAX to send the input data to the server as an HTTP POST request.

[1197] Input: Story setting and character setting information entered by the user

[1198] Output: Data packets sent to the server

[1199] Step 3:

[1200] The server converts the received input data into a format suitable for the generative model.

[1201] The server converts the received data into JSON format, creating a structure that is easy for the generative AI model to understand.

[1202] Input: User input data sent from the terminal

[1203] Output: Structured JSON data to send to a generative AI model

[1204] Step 4:

[1205] The server sends the converted data to the generative AI model.

[1206] The server sends a POST request to an API endpoint, providing the data required for the generative AI model.

[1207] Input: User-supplied data in JSON format

[1208] Output: API call to the generative AI model and its response

[1209] Step 5:

[1210] Based on the data received, the generative AI model generates a story from each character's perspective.

[1211] The generative AI model generates a story from each character's perspective using prompt sentences based on the input data provided.

[1212] For example, the prompt is:

[1213] "Generate a story from Cinderella's point of view: {configuration data}", "Generate a story from the stepmother's point of view: {configuration data}"

[1214] Input: JSON data sent to the generative AI model

[1215] Output: Story data for each character's perspective

[1216] Step 6:

[1217] The server receives the narrative data generated from the generative AI model.

[1218] The server checks the API response and receives the narrative data for each generated perspective.

[1219] Input: Response data from the generative AI model

[1220] Output: Story data stored on the server

[1221] Step 7:

[1222] The server categorizes the received story data and stores it in a database.

[1223] The server classifies the received story data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and stores each piece of data in a NoSQL database.

[1224] Input: Story data divided into perspectives

[1225] Output: Categorized narrative data stored in a database

[1226] Step 8:

[1227] Users use their devices to access the YourSTORY library and browse stories from different perspectives.

[1228] When a user accesses the library and selects a story from a particular perspective from the displayed list, the terminal sends a request to the server to obtain the required data.

[1229] Input: Request information for the viewpoint selected by the user

[1230] Output: Narrative data from a specified point of view

[1231] Step 9:

[1232] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[1233] The device retrieves data asynchronously using AJAX or the Fetch API, and updates the screen display in a user-friendly format using Vue.js or React.

[1234] Input: Data retrieval request based on user request

[1235] Output: Story data displayed on the user's device

[1236] (Application example 1)

[1237] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1238] There is a need for a system that allows users to easily input basic story settings and character settings, generate stories from multiple perspectives based on that information, and allow users to easily view those stories. However, existing technologies lack the ability to properly process user-input information or manage data received from the generative model, making deployment as a smartphone application particularly difficult. There is also a need for a system that allows the generated story data to be easily saved and managed, and be viewable by perspective.

[1239] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1240] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user-input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for a user to view stories by perspective, means for delivering the story data to a content delivery service, and means for providing the story data as an application that runs on a smartphone. This allows story data generated from multiple perspectives to be efficiently managed and delivered, and allows users to easily access and view it.

[1241] "Story Basics" is information that the user enters to form the framework of the story, such as the story's theme, background, and major events.

[1242] "Character settings" involve the user entering detailed attributes of each character appearing in the story, such as their name, role, personality, and characteristics.

[1243] "User-input information" is a general term for information about the basic story setting and character settings that a user provides to the system.

[1244] A "generative model" is an artificial intelligence model for automatically generating a story based on received user input information, and here it is particularly applicable to generating a story from multiple perspectives.

[1245] "Narrative data" refers to textual data of a story created by a generative model, including multiple versions based on each character's perspective.

[1246] "Categorization" is the act of classifying and organizing received narrative data according to specific criteria.

[1247] "Storage" refers to saving the received story data in a database or storage.

[1248] "Perspective stories" refers to different versions of a story that are generated based on the perspective of each character in the story.

[1249] "Content distribution service" is a general term for online platforms that provide generated story data to users via the Internet.

[1250] "Smartphone-enabled application" refers to a software program that can be installed and executed on a smartphone device, and here means, in particular, one that has story creation and viewing capabilities.

[1251] This invention provides a system that generates stories from multiple perspectives and allows users to view them from different perspectives. Specifically, the system configures a means for users to input basic story settings and character settings, send the data to a generative AI model for processing, and store and distribute the generated story data.

[1252] 1. System Configuration

[1253] The basic components of the system are:

[1254] 1. How to input and submit story settings:

[1255] The user uses the terminal to input the basic story settings and character settings.

[1256] The entered information is sent to the server as an HTTP request.

[1257] 2. Means of sending to the generative model:

[1258] The input data received by the server is converted into JSON format.

[1259] The transformed data is sent to a generative AI model, which may be powered by OpenAI or a similar generative model.

[1260] 3. Narrative generation tools:

[1261] Based on the data received, the generative AI model generates a story from each character's perspective.

[1262] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[1263] 4. Means of receiving the generative story:

[1264] The server receives the narrative data generated from the generative AI model.

[1265] The received data is divided into perspectives for each character.

[1266] 5. Narrative data storage means:

[1267] The server categorizes the received story data and stores it in a database.

[1268] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[1269] 6. How to view the story by point of view:

[1270] The user uses a device such as a smartphone to view the story from a different perspective.

[1271] In response to a user's request, the server retrieves the appropriate story data from the database and displays it on the screen.

[1272] 7. Content Delivery Methods:

[1273] The server distributes the generated story data to a platform (content distribution service) that provides it to users via the Internet.

[1274] This allows users to easily access and view stories generated from multiple perspectives.

[1275] 8. Application Delivery Method:

[1276] All of the above functions are implemented as an application for smartphones.

[1277] The application again provides an interface for users to input story settings and view the stories generated by the generative model.

[1278] 2. Program Processing

[1279] The system is built using Python and the Flask framework, and uses the HTTP protocol for data communication, with JSON as the data format.

[1280] 1. Hardware and Software:

[1281] The hardware used includes the user's device (smartphone or computer) and a server.

[1282] The software used includes generative AI models (e.g., OpenAI's GPT-4), frameworks (Flask), and database management systems (e.g., SQLite or MongoDB).

[1283] 2. Data processing and calculation:

[1284] User input data is received by the server and converted to JSON format.

[1285] The converted data is sent to a generative AI model to generate a story.

[1286] The generated story data is received, categorized by character, and stored in a database.

[1287] - Upon user request, story data from a specific character's perspective is retrieved from the database and displayed on the screen.

[1288] 3. Specific Examples

[1289] For example, the user enters the following:

[1290] Title: Cinderella

[1291] character:

[1292] Cinderella: "She has a kind heart"

[1293] Stepmother: "Strict and jealous"

[1294] Older sisters: "Mean personality"

[1295] Prince: "True and brave"

[1296] An example of a prompt for the generative AI model would be, "Please describe the story in detail from Cinderella's point of view." This will enable efficient management and distribution of stories generated from multiple perspectives, making them easily accessible and viewable by users.

[1297] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1298] Step 1:

[1299] The user uses the terminal to input the basic story settings and character settings.

[1300] The entered information (story title, character name, role, personality, etc.) is converted into JSON format within the device application and sent to the server as an HTTP request.

[1301] Input: Data entered by the user for the setting.

[1302] Output: JSON formatted data sent to the server.

[1303] Step 2:

[1304] The server rechecks the received JSON data and converts it into a format suitable for the generative model.

[1305] Validate and format the data as needed, and create prompts to send to the generative AI model.

[1306] Input: JSON formatted data received from the user.

[1307] Output: The prompt sent to the generative AI model.

[1308] Step 3:

[1309] The server sends the prompt sentence to the generative AI model as an API request.

[1310] The generative AI model generates a story from each character's perspective based on the prompt text it receives.

[1311] Input: The prompt sentence sent to the generative AI model.

[1312] Output: Generated narrative text data.

[1313] Step 4:

[1314] The server receives the generated story data as a response from the generative AI model.

[1315] This data is divided into perspectives for each character.

[1316] Input: Narrative data received as a response from a generative AI model.

[1317] Output: Generated narrative data by viewpoint.

[1318] Step 5:

[1319] The server categorizes the received story data by character and stores it in a database.

[1320] When storing, it creates appropriate indexes to facilitate later retrieval and access.

[1321] Input: Narrative data separated by point of view.

[1322] Output: Narrative data stored in a database.

[1323] Step 6:

[1324] The user uses the terminal to request a story from each character's perspective.

[1325] The application on the terminal sends the request to the server.

[1326] Input: A story view request from a user.

[1327] Output: The request data sent to the server.

[1328] Step 7:

[1329] The server retrieves the story data from the relevant character's perspective from the database and sends it to the terminal.

[1330] Here, the appropriate data is retrieved based on the request and a response is sent to the user.

[1331] Input: The browse request sent to the server.

[1332] Output: The narrative data sent back to the terminal.

[1333] Step 8:

[1334] The device displays the received story data to the user.

[1335] Users can read the story from each character's perspective through the device screen.

[1336] Input: Story data sent from the server.

[1337] Output: The story that is displayed to the user.

[1338] Step 9:

[1339] The server distributes the generated story data to a content distribution service via the Internet.

[1340] This is to allow more users to view stories on different devices.

[1341] Input: Generated narrative data.

[1342] Output: Narrative data delivered to a content delivery service.

[1343] Step 10:

[1344] The device is designed to run all of the above functions as smartphone applications.

[1345] The application provides an interface for users to re-enter story settings and view the stories generated by the generative model.

[1346] Input: Various user inputs and data from the server.

[1347] Output: An integrated narrative generation and viewing experience provided to the user.

[1348] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1349] This invention combines an emotion engine with a system in which a user inputs the basic story setting and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[1350] System Program Overview

[1351] The system includes the following means:

[1352] 1. Means for inputting and sending story settings

[1353] 2. Means of sending to the generative model

[1354] 3. Narrative Generation Methods

[1355] 4. Means of receiving the generative story

[1356] 5. Storage of story data

[1357] 6. How to view stories from different perspectives

[1358] 7. Emotion Engine

[1359] 8. Emotion-based narrative adjustment

[1360] A natural language description of the program

[1361] A means of inputting and sending story settings

[1362] The user uses the terminal to input the basic story and character settings, including the story title, the names, roles, and personalities of the characters.

[1363] The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[1364] Sending to the Generative Model

[1365] The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[1366] The server sends the transformed data to the generative model, which is then passed to the model via an API call.

[1367] Story Generation Method

[1368] Based on the data received, the generative AI model generates a story from each character's perspective, for example, the story of Cinderella from multiple characters' perspectives.

[1369] Means of receiving generative stories

[1370] The server receives the response from the generative AI model and the generated story data, which includes story data divided into perspectives for each character.

[1371] A means of storing story data

[1372] The server categorizes the received story data and stores it in a database. Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and saved in the database.

[1373] A way to view stories from different perspectives

[1374] The user accesses the YourSTORY library using a device and reads stories from each character's perspective. They log in to the library using the device's browser, select the story from the perspective they want to see, and display it.

[1375] Emotion engine and emotion-based story adjustment

[1376] Emotion Engine

[1377] The emotion engine recognizes the user's emotions by analyzing their facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[1378] Emotion-based narrative adjustment

[1379] The server receives the emotion data sent from the emotion engine.

[1380] The generative model dynamically adjusts the story based on the user's emotional data, for example, changing the tone of the story to be more positive if the user is in a happy state.

[1381] The story the user views on the device is dynamically adjusted to correspond to the user's emotional state.

[1382] Explanation of specific examples

[1383] 1. The user inputs the story setting of "Cinderella" on the device, including details of the characters "Cinderella," "Stepmother," "Sisters," and "Prince."

[1384] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[1385] 3. The server sends the converted data to the generative model, which then generates a story from each character's perspective.

[1386] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[1387] 5. The user uses the device to access the YourSTORY library, selects "Cinderella from the Stepmother's Point of View," and views it.

[1388] 6. The emotion engine recognizes the user's emotion, and the server receives this emotion data.

[1389] 7. The generative model dynamically adjusts the story content based on emotional data. For example, if the user is sad, the tone of the story will be changed to be more emotional.

[1390] 8. The stories users view on their devices will respond to their emotional state, providing a more personalized experience.

[1391] In this way, the system generates stories that take the user's emotions into account, allowing the user to have a more multifaceted and emotionally rich story experience.

[1392] The processing flow will be explained below.

[1393] Step 1:

[1394] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[1395] Step 2:

[1396] The terminal sends the data entered by the user to the server. Specifically, the data in the input form is collected and sent to the server as an HTTP request.

[1397] Step 3:

[1398] The server analyzes the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into the required format.

[1399] Step 4:

[1400] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the required data.

[1401] Step 5:

[1402] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses an internal algorithm to generate a story from Cinderella's perspective, the stepmother's perspective, the sisters' perspective, and the prince's perspective.

[1403] Step 6:

[1404] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response and analyzes and extracts story data for each perspective.

[1405] Step 7:

[1406] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[1407] Step 8:

[1408] The user accesses the YourSTORY library using a device and browses stories from different perspectives. Specifically, the user logs into the YourSTORY library using the device's browser, selects the story from the perspective they want to view, and displays it.

[1409] Step 9:

[1410] The emotion engine recognizes the user's emotions by capturing the user's facial expressions and voice through the device's camera and microphone, and then uses an emotion analysis algorithm to determine the user's emotional state.

[1411] Step 10:

[1412] The server receives the emotional data sent from the emotion engine. Specifically, the server receives the analysis results of the emotional data and uses them to adjust the tone and content of the story.

[1413] Step 11:

[1414] The generative model dynamically adjusts the content of the story based on the emotional data. Specifically, the generative model receives emotional data as input and changes the tone and event content of the story according to the user's emotions.

[1415] Step 12:

[1416] The story that the user is viewing on the device is dynamically adjusted according to the user's emotional state. Specifically, if the user is in a happy state, the tone of the story is adjusted to a positive one.

[1417] This series of processes allows users to enjoy a personalized story experience that is tailored to their emotions.

[1418] Example 2

[1419] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1420] Conventional story generation systems generate static stories based on basic settings and character configurations entered by the user, and suffer from a lack of personalization based on the user's emotional state, making it difficult for users to obtain an emotionally rich story experience.

[1421] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1422] In this invention, the server includes means for the user to input basic story settings and character settings, means for transmitting the information input by the user to the generative model, means for generating a story based on the viewpoint of each character, means for receiving the generated story data, means for categorizing and storing the received story data, an emotion engine for recognizing the user's emotions, means for dynamically adjusting the story based on the emotion data from the emotion engine, and means for the user to view stories from different viewpoints, thereby enabling dynamic story generation that corresponds to the user's emotional state.

[1423] A "user" is a person who uses this system to input story settings and character settings.

[1424] "Basic story settings" are information that forms the framework of the story, such as the title of the story, the main storyline, and the setting.

[1425] "Character settings" are detailed information about the characters that appear in the story, such as their names, personalities, and roles.

[1426] A "generative model" is an algorithm or program that generates a story based on information input by a user.

[1427] "Story data" is data containing the content of a story generated by a generative model.

[1428] An "emotion engine" is software or hardware capable of recognizing a user's emotional state and adapting dialogue and output accordingly.

[1429] "Emotion data" is data obtained as a result of the emotion engine analyzing the user's emotions.

[1430] "Dynamic adjustment means" is a function that changes the content of the generated story in real time according to the user's emotional state.

[1431] A "perspective story" is a multiple story told from the perspective of each character in the story.

[1432] This invention combines an emotion engine with a system in which a user inputs basic story settings and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[1433] Hardware and Software Examples

[1434] Devices: PCs, smartphones, tablets, etc.

[1435] Server: Cloud server, web server

[1436] Generative AI models: Generative models using natural language processing (NLP) (e.g., GPT-3)

[1437] Emotion engine: facial expression recognition software, voice analysis software (e.g., Amazon Rekognition, Microsoft Azure Emotion API)

[1438] Specific system configuration

[1439] 1. The user uses a terminal to input the basic story and character settings, including the story title and the names, roles, and personalities of the characters.

[1440] Specifically, the user inputs the story title "Cinderella" and details (personalities and roles) of the characters appearing in the story: "Cinderella," "Prince," "Stepmother," and "Sisters."

[1441] 2. The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[1442] 3. The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[1443] 4. The server sends the transformed data to the generative model, which is passed to the model via an API call.

[1444] 5. Based on the received data, the generative AI model generates a story from each character's perspective. For example, the story of Cinderella is generated from the perspectives of multiple characters.

[1445] 6. The server receives the response from the generative AI model and the generated story data, which includes story data separated by each character's perspective.

[1446] 7. The server categorizes the received story data and stores it in the database. Specifically, the story data is classified into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and saved in the database.

[1447] 8. The user accesses the YourSTORY library using a device and browses stories from each character's perspective. The user logs in to the library using the device's browser, selects the story from the perspective they want to view, and displays it.

[1448] 9. The emotion engine recognizes the user's emotions by analyzing the user's facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[1449] 10. The server receives the emotion data sent from the emotion engine.

[1450] 11. The generative model dynamically adjusts the story based on the user's emotional data. For example, if the user is in a happy state, it changes the tone of the story to be more positive.

[1451] 12. The story the user views on their device is dynamically adjusted to correspond to the user's emotional state.

[1452] Specific prompt examples

[1453] Example 1: Generate a story from Cinderella's point of view.

[1454] Example 2: If the user is in a happy state, change the tone of the story to a positive one.

[1455] As described above, the present invention is a system that generates and dynamically adjusts a story based on user input, providing a more personalized story experience.

[1456] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1457] The flow of this system's program processing

[1458] Step 1:

[1459] The user uses a terminal to input the basic setting and character settings of the story.

[1460] Input: The user enters information such as the story title, character names, roles, and personalities into an input form.

[1461] Specific actions: For example, enter the story title "Cinderella" and the names and personalities of "Cinderella," "Prince," "Stepmother," and "Stepsisters" (e.g., Cinderella = kind, Prince = brave).

[1462] Output: The entered information is stored in a data structure within the terminal.

[1463] Step 2:

[1464] The terminal transmits the input information to the server.

[1465] Input: Story and character data entered by the user in Step 1.

[1466] Specific behavior: When the user clicks the "Submit" button, the data is sent to the server as an HTTP request.

[1467] Output: The data sent to the server.

[1468] Step 3:

[1469] The server converts the received data into a format suitable for the generative model.

[1470] Input: Story and character setting data received by the server.

[1471] Specific operation: Converts received data into, for example, JSON format and organizes the data into a fair format.

[1472] Output: Data converted to JSON format.

[1473] Step 4:

[1474] The server sends the transformed data to the generative model.

[1475] Input: Story and characterization data converted to JSON format.

[1476] What it does: Makes an API call and sends data to the appropriate endpoint.

[1477] Output: The data passed to the generative model.

[1478] Step 5:

[1479] Based on the data received, the generative AI model generates a story from each character's perspective.

[1480] Input: Story and characterization data in JSON format.

[1481] How it works: The generative AI model uses algorithms to dynamically generate a story from each character's perspective.

[1482] Output: Narrative data generated for each character.

[1483] Step 6:

[1484] The server receives the response from the generative AI model and receives the generated story data.

[1485] Input: Response data from the generative AI model.

[1486] Specific operation: Analyze the response and save the story data divided by character's perspective on the server.

[1487] Output: Story data from each character's perspective.

[1488] Step 7:

[1489] The server stores the received story data in a database by category.

[1490] Input: Story data from character perspectives.

[1491] Specific operation: For example, classify into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and save them in a database.

[1492] Output: Story data in a categorized database.

[1493] Step 8:

[1494] The user uses a terminal to access the YourSTORY library and view stories from each character's perspective.

[1495] Input: Categorized story data.

[1496] Specific operation: Log in to the library using your device's browser, select the story from the perspective you want to see, and display it.

[1497] Output: Narrative content from a user-specified point of view.

[1498] Step 9:

[1499] The emotion engine recognizes the user's emotions.

[1500] Input: The user's facial expressions, voice, and other biometric signals acquired from the device.

[1501] Specific operation: Data is acquired through the camera and microphone, and analyzed to detect emotional state.

[1502] Output: Detected user emotion data.

[1503] Step 10:

[1504] The server receives the emotion data sent from the emotion engine.

[1505] Input: Emotion data sent from the emotion engine.

[1506] Specific operation: The server receives the emotion data and inputs it into the analysis system.

[1507] Output: Emotion data in the server.

[1508] Step 11:

[1509] A generative model dynamically adjusts the narrative based on the user's emotional data.

[1510] Input: User emotion data.

[1511] What it does: The generative model analyzes the emotional data and changes the tone and content of the generated story based on that.

[1512] Output: Dynamically adjusted narrative data that responds to the user's emotions.

[1513] Step 12:

[1514] The story the user views on their device will correspond to the user's emotional state.

[1515] Input: Dynamically adjusted narrative data.

[1516] What it does: When users revisit a story, they will see real-time updates based on sentiment.

[1517] Output: A personalized narrative experience.

[1518] (Application example 2)

[1519] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1520] Conventional story generation systems were able to generate a story from a fixed perspective based on user-entered settings, but lacked the ability to dynamically adjust the story content in response to the user's emotional state. This made it difficult to provide a story optimized for each user's individual emotional experience. Furthermore, there was a lack of an efficient system for generating stories from each character's perspective. This limited the user's ability to enjoy the story by changing their perspective.

[1521] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1522] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for the user to view stories by perspective, means for recognizing the user's emotions, and means for dynamically adjusting the content of the story based on the emotions. This enables a personalized story experience according to the user's emotional state, making it possible to provide a system that allows users to enjoy stories from different perspectives.

[1523] "Means for users to input basic story settings and character settings" refers to the means by which users input the story title, characters' names, roles, personalities, etc.

[1524] "Means for sending user-input information to a generative model" refers to means for sending information on the basic story setting and character settings entered by the user to a generative AI model.

[1525] "Means for generating a story from each character's perspective from a generative model" refers to a means for a generative AI model to generate a story from each character's perspective based on information received from the user.

[1526] "Means for receiving generated story data" refers to means for receiving story data generated from a generative AI model.

[1527] The "means for categorizing and storing received story data" is a means for classifying received story data into specific categories and storing them in a database.

[1528] "Means for users to view stories from different perspectives" refers to means for users to view stories generated from the perspectives of each character.

[1529] "Means for recognizing the user's emotions" refers to a means for analyzing the user's facial expressions, voice, biometric signals, etc. to detect the user's emotional state.

[1530] "Means for dynamically adjusting story content based on emotions" refers to means for adapting and adjusting the content of a generated story in real time based on the recognized emotional state of a user.

[1531] MODE FOR CARRYING OUT THE INVENTION

[1532] System Overview

[1533] This invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. Furthermore, the system has the ability to recognize the user's emotions and dynamically adjust the story content based on those emotions. This system allows users to experience a personalized story from each perspective.

[1534] Hardware and software used

[1535] Hardware: Smartphones, smart glasses, head-mounted displays

[1536] Software: Python 3.8+, Flask (server-side), Emotion Recognition API

[1537] Data processing and data calculation

[1538] Enter and submit story settings

[1539] The user inputs the story title, characters' names, roles, personalities, etc. into a smartphone or other device. The input data is converted into JSON format and sent to the server as an HTTP request, allowing the server to receive the input data from the user.

[1540] Sending to the Generative Model

[1541] The server converts the received user story setting and character setting information into a format suitable for the generative AI model, and then sends the converted data to the generative AI model via an API call.

[1542] Story Generation

[1543] The generative AI model generates a story from each character's perspective based on the received data. For example, it generates the story of the fairy tale "Cinderella" from each character's perspective. This generated story data is sent back to the server.

[1544] Receiving and storing generated stories

[1545] The server receives the story data generated by the generative AI model, categorizes it by each character's perspective, and stores it in a database, improving search efficiency when users later view the story by perspective.

[1546] Viewing stories by point of view

[1547] Users can use their devices to view stories from different points of view, for example, they can select the Cinderella story as "from the stepmother's point of view" and start reading.

[1548] Emotion recognition and dynamic adjustment of narrative

[1549] The user's device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API. This emotional data is sent to the server, which then invokes a generative AI model based on the emotional data to dynamically adjust the content of the story. For example, if the user is in a happy state, the tone of the story will be changed to a more positive one.

[1550] Specific examples

[1551] 1. Enter the story setting

[1552] The user inputs the story setting for "Cinderella" on the device, along with details of the characters: "protagonist," "villain," "rival," and "savior."

[1553] Example prompt sentence:

[1554] Enter the story setting for Cinderella. Characters:

[1555] Name: Cinderella, Role: Protagonist, Personality: Kind

[1556] Name: Stepmother, Role: Antagonist, Character: Ruthless

[1557] Name: Older sisters, Role: Rival, Personality: Jealous

[1558] Name: Prince, Role: Savior, Personality: Sense of Justice

[1559] 2. Send to the generative model

[1560] The server sends the story setting to the generative AI model, which generates a story from each perspective.

[1561] 3. Receiving and storing generated stories

[1562] The generated stories are stored in a database by point of view.

[1563] 4. Emotion recognition

[1564] If the user's emotion is recognized as "happy," the system adjusts the story to a more positive tone.

[1565] 5. Viewing stories from different perspectives

[1566] Users view the adapted story on their device.

[1567] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1568] Step 1:

[1569] The user inputs the story setting.

[1570] Specifically, users use their smartphones or other devices to input the story title, characters' names, roles, personalities, etc. The input data is retrieved from the form and converted into JSON format.

[1571] Input: Basic story setting and character settings

[1572] Output: Story setting data converted to JSON format

[1573] Step 2:

[1574] The terminal transmits story setting data to the server.

[1575] Once the user has finished entering the settings, they press the "Submit" button, which sends an HTTP request from the device to the server, which then checks the received data and converts it into an appropriate format (e.g., JSON).

[1576] Input: Story setting data converted to JSON format

[1577] Output: Story setting data sent to the server

[1578] Step 3:

[1579] The server sends the data to the generative AI model.

[1580] The server verifies the accuracy of the received data, then converts it into a format suitable for the generative AI model, and sends this converted data to the generative AI model via an API call.

[1581] Input: Data converted into a format suitable for generative AI models

[1582] Output: Data sent to the generative AI model

[1583] Step 4:

[1584] A generative AI model generates the story.

[1585] The generative AI model generates a story from each character's perspective based on the received data. This generation process uses natural language processing technology, particularly analyzing prompts to develop the story. The generated story data is organized by each character's perspective and sent back to the server.

[1586] Input: Data sent to the generative AI model

[1587] Output: Narrative data generated by perspective

[1588] Step 5:

[1589] The server receives the generated story data and stores it in a database.

[1590] The server receives the story data sent from the generative AI model, categorizes the received data by perspective, and stores it in a database, which improves future search efficiency.

[1591] Input: Narrative data generated by perspective

[1592] Output: Categorized narrative data stored in a database

[1593] Step 6:

[1594] Users view stories from different perspectives.

[1595] The user uses the terminal to select a story by point of view and begin viewing. The terminal accesses the database and displays the selected story.

[1596] Input: Narrative data stored by point of view

[1597] Output: The story displayed on the user's terminal

[1598] Step 7:

[1599] The device recognizes the user's emotions.

[1600] The device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API, and sends the resulting data to the server.

[1601] Input: Emotional data such as user facial expressions, voice, and biometric signals

[1602] Output: Emotion state data analyzed by the Emotion Recognition API

[1603] Step 8:

[1604] The server invokes a generative AI model based on the emotional data and dynamically adjusts the content of the story.

[1605] The server receives the emotional state data and sends prompts to the generative AI model again to adjust the story content, changing the tone and development of the story according to the user's emotional state. The adjusted story data is then regenerated and sent to the user's device.

[1606] Input: Emotion state data sent from the Emotion Recognition API

[1607] Output: Dynamically adjusted narrative data

[1608] Step 9:

[1609] The user views the tailored story.

[1610] The user then views the adjusted story on their device again, providing a story experience optimized for the user's emotional state.

[1611] Input: Dynamically adjusted narrative data

[1612] Output: The adjusted story displayed on the user's terminal

[1613] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1614] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1615] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1616] [Fourth embodiment]

[1617] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1618] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1619] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1621] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1623] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1624] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1625] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1626] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1627] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1628] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1629] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1630] The present invention is a system in which a user inputs the basic setting and character settings of a story, and a generative model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[1631] System Program Overview

[1632] The system includes the following means:

[1633] 1. Means for inputting and sending story settings

[1634] 2. Means of sending to the generative model

[1635] 3. Narrative Generation Methods

[1636] 4. Means of receiving the generative story

[1637] 5. Storage of story data

[1638] 6. How to view stories from different perspectives

[1639] A natural language description of the program

[1640] A means of inputting and sending story settings

[1641] The user uses the terminal to input the basic story settings and character settings (for example, the story title, the names and roles of the characters).

[1642] The terminal sends the entered information to the server. Specifically, when a user enters data into an input form and clicks the "Submit" button, the terminal sends this data to the server as an HTTP request.

[1643] Sending to the Generative Model

[1644] The server converts the received input data into a format suitable for the generative model, often JSON format.

[1645] The server sends the transformed data to the generative model, which is done as an API call, providing the generative model with the data it needs.

[1646] Story Generation Method

[1647] Based on the data received, the generative AI model generates a story from each character's perspective.

[1648] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[1649] Means of receiving generative stories

[1650] The server receives the story data generated by the generative AI model. The received data is divided into perspectives for each character.

[1651] A means of storing story data

[1652] The server categorizes the received story data and stores it in a database.

[1653] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[1654] A way to view stories from different perspectives

[1655] Users use their devices to access the YourSTORY library and view stories from each character's perspective.

[1656] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[1657] Explanation of specific examples

[1658] 1. The user inputs the basic setting of the story "Cinderella" into the device, including the characters "Cinderella," "Stepmother," "Sisters," and "Prince," along with their detailed settings.

[1659] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[1660] 3. The server sends the transformed data to the generative model, which then generates a story from each character's point of view.

[1661] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[1662] 5. Users can access the YourSTORY library using their device, select and view "Cinderella from the Stepmother's Point of View," and understand the story from multiple perspectives.

[1663] This system works by combining these methods to help users understand and learn stories from multiple perspectives.

[1664] The processing flow will be explained below.

[1665] Step 1:

[1666] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[1667] Step 2:

[1668] The terminal sends the data entered by the user to the server. Specifically, the terminal collects the data from the input form and sends it to the server as an HTTP request.

[1669] Step 3:

[1670] The server parses the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into an appropriate data format.

[1671] Step 4:

[1672] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the data.

[1673] Step 5:

[1674] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses its internal algorithm to generate a story from each perspective and returns it as a response.

[1675] Step 6:

[1676] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response, analyzes it, and extracts the story for each perspective.

[1677] Step 7:

[1678] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[1679] Step 8:

[1680] Users access the YourSTORY library using their device and view stories from different perspectives. Specifically, users log in to the YourSTORY library using the browser on their device, select the story from the perspective they want to view, and then perform the necessary operations to display it.

[1681] Step 9:

[1682] In response to a user request, the device retrieves the appropriate story data from the database and displays it on the screen. Specifically, the device sends an HTTP request to the server and displays the story data returned by the server in the browser.

[1683] Example 1

[1684] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1685] Conventional story generation systems require large amounts of data processing and complex procedures when generating stories based on each character's perspective from the basic story and character settings entered by the user, making operation cumbersome. Furthermore, there were not enough systems that allowed users to easily browse stories by perspective. Furthermore, there was a lack of systems that automatically categorized and saved the generated story data. This made it difficult for users to create, manage, and browse stories efficiently and in a unified manner.

[1686] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1687] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the input user information to the server, means for the server to convert the user-input information into a format suitable for the generative model, means for the server to transmit the converted information to the generative AI model, means for the generative AI model to generate a story based on the perspective of each character, means for the server to receive the generated story data, means for the server to categorize and store the received story data, and means for the user to view stories by perspective using a terminal. This enables users to efficiently and intuitively set basic story settings and character settings, and easily generate, manage, and view stories from each character's perspective.

[1688] A "user" is a person who uses the system to input basic story settings and character settings and view the generated story data.

[1689] A "terminal" is an electronic device such as a computer, smartphone, or tablet operated by a user, and is a device for inputting and transmitting story settings and viewing stories from different perspectives.

[1690] The "server" is a central processing unit that receives data entered by the user, sends it to the generative AI model, receives the results, and stores them in a database.

[1691] A "generative AI model" is an artificial intelligence model that generates a story from each character's perspective based on the basic story settings and character settings provided by the user.

[1692] "Basic story setting" refers to information that constitutes the outline of the entire story, such as the story's title and theme.

[1693] "Character settings" refers to information such as the names, roles, and characteristics of the characters that appear in the story.

[1694] A "form" is a set of input fields on a web page that allows a user to enter basic story and character settings.

[1695] An "HTTP request" is an Internet communication protocol used to send user input data to a server.

[1696] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for structuring and representing data.

[1697] A "REST API" is an application programming interface based on Representational State Transfer, a standardized means of sending and receiving data between systems.

[1698] The "database" is an electronic data repository for systematically storing and managing received story data.

[1699] "Categorization" refers to classifying the generated narrative data according to specific perspectives.

[1700] "YourSTORY Library" is a collection of data storage and user interfaces within the system that users access to view narrative data from different perspectives.

[1701] A "prompt sentence" is an instruction sentence that instructs the generative AI model to generate a story, and is a sentence that contains the necessary input data.

[1702] The present invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. The system includes a series of means for appropriately processing the information input by the user and saving and making the generated story data available for viewing.

[1703] The system consists of the following main means:

[1704] 1. Means for inputting and sending story settings

[1705] The user uses the device to input the basic story and character settings (e.g., the story title, the names and roles of the characters). To do this, the user opens a browser and enters the necessary information into a dedicated input form. When the user clicks the "Submit" button, the device asynchronously sends this data to the server as an HTTP POST request.

[1706] 2. Means of converting and transmitting data to the generative model

[1707] The server converts the received user input information into a format suitable for the generative model (for example, JSON format). To do this, the server structures the received data and processes it into a format that is easy for the generative model to understand. After conversion, the server sends this data to the generative AI model as an API call. As a concrete example, we will implement the API call using Python's requests library.

[1708] 3. Narrative Generation Methods

[1709] Based on the data received, the generative AI model generates a story from each character's perspective. Using the story of Cinderella as an example, the generative AI model generates different stories from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective. Stories from each perspective are generated using the generative AI model's prompt sentences.

[1710] Example prompt sentence:

[1711] "Generate a story from Cinderella's point of view: {configuration data}"

[1712] "Generate a story from the stepmother's point of view: {config data}"

[1713] 4. Means of receiving the generative story

[1714] The server receives the story data generated by the generative AI model. The generated data is divided into separate data for each character's perspective, and the server receives this data all at once.

[1715] 5. Storage of story data

[1716] The server categorizes the received story data and stores it in a NoSQL database (e.g., MongoDB). Specifically, the generated story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince" based on each perspective, and each piece of data is saved as a document in the database.

[1717] 6. How to view stories from different perspectives

[1718] Users access the YourSTORY library using their device and view stories from each character's perspective. When the user selects a specific perspective from the displayed list, the device retrieves the necessary story data from the database and displays it on the screen in a format that is easy for the user to view. Specifically, it uses a front-end framework (e.g., Vue.js or React) to asynchronously retrieve data using AJAX or the Fetch API and dynamically updates the screen display.

[1719] In this way, the system of the present invention is configured to allow the user to set basic story and character settings, and to easily create, manage, and view stories from each character's perspective.

[1720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1721] Step 1:

[1722] The user inputs the basic story setting and character settings.

[1723] The user opens a browser on their device and enters details such as the story title, theme, and the names and roles of the characters into a dedicated input form. Once the input is complete, they click the "Submit" button.

[1724] Input: Basic story setting and character information

[1725] Output: Data packet to send (in JSON format)

[1726] Step 2:

[1727] The terminal transmits the input information to the server.

[1728] When the user clicks the "Submit" button, the terminal uses AJAX to send the input data to the server as an HTTP POST request.

[1729] Input: Story setting and character setting information entered by the user

[1730] Output: Data packets sent to the server

[1731] Step 3:

[1732] The server converts the received input data into a format suitable for the generative model.

[1733] The server converts the received data into JSON format, creating a structure that is easy for the generative AI model to understand.

[1734] Input: User input data sent from the terminal

[1735] Output: Structured JSON data to send to a generative AI model

[1736] Step 4:

[1737] The server sends the converted data to the generative AI model.

[1738] The server sends a POST request to an API endpoint, providing the data required for the generative AI model.

[1739] Input: User-supplied data in JSON format

[1740] Output: API call to the generative AI model and its response

[1741] Step 5:

[1742] Based on the data received, the generative AI model generates a story from each character's perspective.

[1743] The generative AI model generates a story from each character's perspective using prompt sentences based on the input data provided.

[1744] For example, the prompt is:

[1745] "Generate a story from Cinderella's point of view: {configuration data}", "Generate a story from the stepmother's point of view: {configuration data}"

[1746] Input: JSON data sent to the generative AI model

[1747] Output: Story data for each character's perspective

[1748] Step 6:

[1749] The server receives the narrative data generated from the generative AI model.

[1750] The server checks the API response and receives the narrative data for each generated perspective.

[1751] Input: Response data from the generative AI model

[1752] Output: Story data stored on the server

[1753] Step 7:

[1754] The server categorizes the received story data and stores it in a database.

[1755] The server classifies the received story data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and stores each piece of data in a NoSQL database.

[1756] Input: Story data divided into perspectives

[1757] Output: Categorized narrative data stored in a database

[1758] Step 8:

[1759] Users use their devices to access the YourSTORY library and browse stories from different perspectives.

[1760] When a user accesses the library and selects a story from a particular perspective from the displayed list, the terminal sends a request to the server to obtain the required data.

[1761] Input: Request information for the viewpoint selected by the user

[1762] Output: Narrative data from a specified point of view

[1763] Step 9:

[1764] In response to a user's request, the terminal retrieves appropriate story data from the database and displays it on the screen.

[1765] The device retrieves data asynchronously using AJAX or the Fetch API, and updates the screen display in a user-friendly format using Vue.js or React.

[1766] Input: Data retrieval request based on user request

[1767] Output: Story data displayed on the user's device

[1768] (Application example 1)

[1769] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1770] There is a need for a system that allows users to easily input basic story settings and character settings, generate stories from multiple perspectives based on that information, and allow users to easily view those stories. However, existing technologies lack the ability to properly process user-input information or manage data received from the generative model, making deployment as a smartphone application particularly difficult. There is also a need for a system that allows the generated story data to be easily saved and managed, and be viewable by perspective.

[1771] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1772] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user-input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for a user to view stories by perspective, means for delivering the story data to a content delivery service, and means for providing the story data as an application that runs on a smartphone. This allows story data generated from multiple perspectives to be efficiently managed and delivered, and allows users to easily access and view it.

[1773] "Story Basics" is information that the user enters to form the framework of the story, such as the story's theme, background, and major events.

[1774] "Character settings" involve the user entering detailed attributes of each character appearing in the story, such as their name, role, personality, and characteristics.

[1775] "User-input information" is a general term for information about the basic story setting and character settings that a user provides to the system.

[1776] A "generative model" is an artificial intelligence model for automatically generating a story based on received user input information, and here it is particularly applicable to generating a story from multiple perspectives.

[1777] "Narrative data" refers to textual data of a story created by a generative model, including multiple versions based on each character's perspective.

[1778] "Categorization" is the act of classifying and organizing received narrative data according to specific criteria.

[1779] "Storage" refers to saving the received story data in a database or storage.

[1780] "Perspective stories" refers to different versions of a story that are generated based on the perspective of each character in the story.

[1781] "Content distribution service" is a general term for online platforms that provide generated story data to users via the Internet.

[1782] "Smartphone-enabled application" refers to a software program that can be installed and executed on a smartphone device, and here means, in particular, one that has story creation and viewing capabilities.

[1783] This invention provides a system that generates stories from multiple perspectives and allows users to view them from different perspectives. Specifically, the system configures a means for users to input basic story settings and character settings, send the data to a generative AI model for processing, and store and distribute the generated story data.

[1784] 1. System Configuration

[1785] The basic components of the system are:

[1786] 1. How to input and submit story settings:

[1787] The user uses the terminal to input the basic story settings and character settings.

[1788] The entered information is sent to the server as an HTTP request.

[1789] 2. Means of sending to the generative model:

[1790] The input data received by the server is converted into JSON format.

[1791] The transformed data is sent to a generative AI model, which may be powered by OpenAI or a similar generative model.

[1792] 3. Narrative generation tools:

[1793] Based on the data received, the generative AI model generates a story from each character's perspective.

[1794] For example, for the story of Cinderella, we generate a story from Cinderella's perspective, her stepmother's perspective, her sisters' perspective, and the prince's perspective.

[1795] 4. Means of receiving the generative story:

[1796] The server receives the narrative data generated from the generative AI model.

[1797] The received data is divided into perspectives for each character.

[1798] 5. Narrative data storage means:

[1799] The server categorizes the received story data and stores it in a database.

[1800] Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and each is stored in a database.

[1801] 6. How to view the story by point of view:

[1802] The user uses a device such as a smartphone to view the story from a different perspective.

[1803] In response to a user's request, the server retrieves the appropriate story data from the database and displays it on the screen.

[1804] 7. Content Delivery Methods:

[1805] The server distributes the generated story data to a platform (content distribution service) that provides it to users via the Internet.

[1806] This allows users to easily access and view stories generated from multiple perspectives.

[1807] 8. Application Delivery Method:

[1808] All of the above functions are implemented as an application for smartphones.

[1809] The application again provides an interface for users to input story settings and view the stories generated by the generative model.

[1810] 2. Program Processing

[1811] The system is built using Python and the Flask framework, and uses the HTTP protocol for data communication, with JSON as the data format.

[1812] 1. Hardware and Software:

[1813] The hardware used includes the user's device (smartphone or computer) and a server.

[1814] The software used includes generative AI models (e.g., OpenAI's GPT-4), frameworks (Flask), and database management systems (e.g., SQLite or MongoDB).

[1815] 2. Data processing and calculation:

[1816] User input data is received by the server and converted to JSON format.

[1817] The converted data is sent to a generative AI model to generate a story.

[1818] The generated story data is received, categorized by character, and stored in a database.

[1819] - Upon user request, story data from a specific character's perspective is retrieved from the database and displayed on the screen.

[1820] 3. Specific Examples

[1821] For example, the user enters the following:

[1822] Title: Cinderella

[1823] character:

[1824] Cinderella: "She has a kind heart"

[1825] Stepmother: "Strict and jealous"

[1826] Older sisters: "Mean personality"

[1827] Prince: "True and brave"

[1828] An example of a prompt for the generative AI model would be, "Please describe the story in detail from Cinderella's point of view." This will enable efficient management and distribution of stories generated from multiple perspectives, making them easily accessible and viewable by users.

[1829] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1830] Step 1:

[1831] The user uses the terminal to input the basic story settings and character settings.

[1832] The entered information (story title, character name, role, personality, etc.) is converted into JSON format within the device application and sent to the server as an HTTP request.

[1833] Input: Data entered by the user for the setting.

[1834] Output: JSON formatted data sent to the server.

[1835] Step 2:

[1836] The server rechecks the received JSON data and converts it into a format suitable for the generative model.

[1837] Validate and format the data as needed, and create prompts to send to the generative AI model.

[1838] Input: JSON formatted data received from the user.

[1839] Output: The prompt sent to the generative AI model.

[1840] Step 3:

[1841] The server sends the prompt sentence to the generative AI model as an API request.

[1842] The generative AI model generates a story from each character's perspective based on the prompt text it receives.

[1843] Input: The prompt sentence sent to the generative AI model.

[1844] Output: Generated narrative text data.

[1845] Step 4:

[1846] The server receives the generated story data as a response from the generative AI model.

[1847] This data is divided into perspectives for each character.

[1848] Input: Narrative data received as a response from a generative AI model.

[1849] Output: Generated narrative data by viewpoint.

[1850] Step 5:

[1851] The server categorizes the received story data by character and stores it in a database.

[1852] When storing, it creates appropriate indexes to facilitate later retrieval and access.

[1853] Input: Narrative data separated by point of view.

[1854] Output: Narrative data stored in a database.

[1855] Step 6:

[1856] The user uses the terminal to request a story from each character's perspective.

[1857] The application on the terminal sends the request to the server.

[1858] Input: A story view request from a user.

[1859] Output: The request data sent to the server.

[1860] Step 7:

[1861] The server retrieves the story data from the relevant character's perspective from the database and sends it to the terminal.

[1862] Here, the appropriate data is retrieved based on the request and a response is sent to the user.

[1863] Input: The browse request sent to the server.

[1864] Output: The narrative data sent back to the terminal.

[1865] Step 8:

[1866] The device displays the received story data to the user.

[1867] Users can read the story from each character's perspective through the device screen.

[1868] Input: Story data sent from the server.

[1869] Output: The story that is displayed to the user.

[1870] Step 9:

[1871] The server distributes the generated story data to a content distribution service via the Internet.

[1872] This is to allow more users to view stories on different devices.

[1873] Input: Generated narrative data.

[1874] Output: Narrative data delivered to a content delivery service.

[1875] Step 10:

[1876] The device is designed to run all of the above functions as smartphone applications.

[1877] The application provides an interface for users to re-enter story settings and view the stories generated by the generative model.

[1878] Input: Various user inputs and data from the server.

[1879] Output: An integrated narrative generation and viewing experience provided to the user.

[1880] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1881] This invention combines an emotion engine with a system in which a user inputs the basic story setting and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[1882] System Program Overview

[1883] The system includes the following means:

[1884] 1. Means for inputting and sending story settings

[1885] 2. Means of sending to the generative model

[1886] 3. Narrative Generation Methods

[1887] 4. Means of receiving the generative story

[1888] 5. Storage of story data

[1889] 6. How to view stories from different perspectives

[1890] 7. Emotion Engine

[1891] 8. Emotion-based narrative adjustment

[1892] A natural language description of the program

[1893] A means of inputting and sending story settings

[1894] The user uses the terminal to input the basic story and character settings, including the story title, the names, roles, and personalities of the characters.

[1895] The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[1896] Sending to the Generative Model

[1897] The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[1898] The server sends the transformed data to the generative model, which is then passed to the model via an API call.

[1899] Story Generation Method

[1900] Based on the data received, the generative AI model generates a story from each character's perspective, for example, the story of Cinderella from multiple characters' perspectives.

[1901] Means of receiving generative stories

[1902] The server receives the response from the generative AI model and the generated story data, which includes story data divided into perspectives for each character.

[1903] A means of storing story data

[1904] The server categorizes the received story data and stores it in a database. Specifically, the story data is classified into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince," and saved in the database.

[1905] A way to view stories from different perspectives

[1906] The user accesses the YourSTORY library using a device and reads stories from each character's perspective. They log in to the library using the device's browser, select the story from the perspective they want to see, and display it.

[1907] Emotion engine and emotion-based story adjustment

[1908] Emotion Engine

[1909] The emotion engine recognizes the user's emotions by analyzing their facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[1910] Emotion-based narrative adjustment

[1911] The server receives the emotion data sent from the emotion engine.

[1912] The generative model dynamically adjusts the story based on the user's emotional data, for example, changing the tone of the story to be more positive if the user is in a happy state.

[1913] The story the user views on the device is dynamically adjusted to correspond to the user's emotional state.

[1914] Explanation of specific examples

[1915] 1. The user inputs the story setting of "Cinderella" on the device, including details of the characters "Cinderella," "Stepmother," "Sisters," and "Prince."

[1916] 2. The device sends this information to the server, which converts it into a format suitable for the generative model.

[1917] 3. The server sends the converted data to the generative model, which then generates a story from each character's perspective.

[1918] 4. The server receives the response from the generative model and categorizes and stores the generated perspective-specific stories in a database.

[1919] 5. The user uses the device to access the YourSTORY library, selects "Cinderella from the Stepmother's Point of View," and views it.

[1920] 6. The emotion engine recognizes the user's emotion, and the server receives this emotion data.

[1921] 7. The generative model dynamically adjusts the story content based on emotional data. For example, if the user is sad, the tone of the story will be changed to be more emotional.

[1922] 8. The stories users view on their devices will respond to their emotional state, providing a more personalized experience.

[1923] In this way, the system generates stories that take the user's emotions into account, allowing the user to have a more multifaceted and emotionally rich story experience.

[1924] The processing flow will be explained below.

[1925] Step 1:

[1926] The user uses the terminal to input basic story and character settings. Specifically, the user enters detailed information such as the story title, characters' names, roles, and personalities into the input form, and then clicks the "Submit" button.

[1927] Step 2:

[1928] The terminal sends the data entered by the user to the server. Specifically, the data in the input form is collected and sent to the server as an HTTP request.

[1929] Step 3:

[1930] The server analyzes the received data and converts it into a format suitable for the generative model (e.g., JSON format). Specifically, the server uses a data format conversion module to convert the input data into the required format.

[1931] Step 4:

[1932] The server calls the API of the generative model and sends the converted data to the generative model. Specifically, the server makes an HTTP POST request to the API endpoint and sends the required data.

[1933] Step 5:

[1934] Based on the data received, the generative AI model generates a story from each character's perspective. Specifically, the generative AI model uses an internal algorithm to generate a story from Cinderella's perspective, the stepmother's perspective, the sisters' perspective, and the prince's perspective.

[1935] Step 6:

[1936] The server receives the response (generated story data) returned from the generative AI model. Specifically, the server receives the HTTP response and analyzes and extracts story data for each perspective.

[1937] Step 7:

[1938] The server categorizes the received story data and stores it in a database. Specifically, the server executes an insert query to the database, saving the data into categories such as "Cinderella," "Stepmother," "Sisters," and "Prince."

[1939] Step 8:

[1940] The user accesses the YourSTORY library using a device and browses stories from different perspectives. Specifically, the user logs into the YourSTORY library using the device's browser, selects the story from the perspective they want to view, and displays it.

[1941] Step 9:

[1942] The emotion engine recognizes the user's emotions by capturing the user's facial expressions and voice through the device's camera and microphone, and then uses an emotion analysis algorithm to determine the user's emotional state.

[1943] Step 10:

[1944] The server receives the emotional data sent from the emotion engine. Specifically, the server receives the analysis results of the emotional data and uses them to adjust the tone and content of the story.

[1945] Step 11:

[1946] The generative model dynamically adjusts the content of the story based on the emotional data. Specifically, the generative model receives emotional data as input and changes the tone and event content of the story according to the user's emotions.

[1947] Step 12:

[1948] The story that the user is viewing on the device is dynamically adjusted according to the user's emotional state. Specifically, if the user is in a happy state, the tone of the story is adjusted to a positive one.

[1949] This series of processes allows users to enjoy a personalized story experience that is tailored to their emotions.

[1950] Example 2

[1951] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1952] Conventional story generation systems generate static stories based on basic settings and character configurations entered by the user, and suffer from a lack of personalization based on the user's emotional state, making it difficult for users to obtain an emotionally rich story experience.

[1953] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1954] In this invention, the server includes means for the user to input basic story settings and character settings, means for transmitting the information input by the user to the generative model, means for generating a story based on the viewpoint of each character, means for receiving the generated story data, means for categorizing and storing the received story data, an emotion engine for recognizing the user's emotions, means for dynamically adjusting the story based on the emotion data from the emotion engine, and means for the user to view stories from different viewpoints, thereby enabling dynamic story generation that corresponds to the user's emotional state.

[1955] A "user" is a person who uses this system to input story settings and character settings.

[1956] "Basic story settings" are information that forms the framework of the story, such as the title of the story, the main storyline, and the setting.

[1957] "Character settings" are detailed information about the characters that appear in the story, such as their names, personalities, and roles.

[1958] A "generative model" is an algorithm or program that generates a story based on information input by a user.

[1959] "Story data" is data containing the content of a story generated by a generative model.

[1960] An "emotion engine" is software or hardware capable of recognizing a user's emotional state and adapting dialogue and output accordingly.

[1961] "Emotion data" is data obtained as a result of the emotion engine analyzing the user's emotions.

[1962] "Dynamic adjustment means" is a function that changes the content of the generated story in real time according to the user's emotional state.

[1963] A "perspective story" is a multiple story told from the perspective of each character in the story.

[1964] This invention combines an emotion engine with a system in which a user inputs basic story settings and character settings, and a generative model generates a story from each character's perspective based on that information. This system recognizes the user's emotions and dynamically adjusts the content of the story based on those emotions, providing a more personalized story experience.

[1965] Hardware and Software Examples

[1966] Devices: PCs, smartphones, tablets, etc.

[1967] Server: Cloud server, web server

[1968] Generative AI models: Generative models using natural language processing (NLP) (e.g., GPT-3)

[1969] Emotion engine: facial expression recognition software, voice analysis software (e.g., Amazon Rekognition, Microsoft Azure Emotion API)

[1970] Specific system configuration

[1971] 1. The user uses a terminal to input the basic story and character settings, including the story title and the names, roles, and personalities of the characters.

[1972] Specifically, the user inputs the story title "Cinderella" and details (personalities and roles) of the characters appearing in the story: "Cinderella," "Prince," "Stepmother," and "Sisters."

[1973] 2. The terminal sends the entered information to the server. The user enters data into the input form and clicks the "Submit" button, which sends the data to the server as an HTTP request.

[1974] 3. The server converts the received input data into a format suitable for the generative model, for example, JSON format.

[1975] 4. The server sends the transformed data to the generative model, which is passed to the model via an API call.

[1976] 5. Based on the received data, the generative AI model generates a story from each character's perspective. For example, the story of Cinderella is generated from the perspectives of multiple characters.

[1977] 6. The server receives the response from the generative AI model and the generated story data, which includes story data separated by each character's perspective.

[1978] 7. The server categorizes the received story data and stores it in the database. Specifically, the story data is classified into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and saved in the database.

[1979] 8. The user accesses the YourSTORY library using a device and browses stories from each character's perspective. The user logs in to the library using the device's browser, selects the story from the perspective they want to view, and displays it.

[1980] 9. The emotion engine recognizes the user's emotions by analyzing the user's facial expressions, voice, or other biometric signals to detect their emotional state. This analysis is performed through the device's camera and microphone.

[1981] 10. The server receives the emotion data sent from the emotion engine.

[1982] 11. The generative model dynamically adjusts the story based on the user's emotional data. For example, if the user is in a happy state, it changes the tone of the story to be more positive.

[1983] 12. The story the user views on their device is dynamically adjusted to correspond to the user's emotional state.

[1984] Specific prompt examples

[1985] Example 1: Generate a story from Cinderella's point of view.

[1986] Example 2: If the user is in a happy state, change the tone of the story to a positive one.

[1987] As described above, the present invention is a system that generates and dynamically adjusts a story based on user input, providing a more personalized story experience.

[1988] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1989] The flow of this system's program processing

[1990] Step 1:

[1991] The user uses a terminal to input the basic setting and character settings of the story.

[1992] Input: The user enters information such as the story title, character names, roles, and personalities into an input form.

[1993] Specific actions: For example, enter the story title "Cinderella" and the names and personalities of "Cinderella," "Prince," "Stepmother," and "Stepsisters" (e.g., Cinderella = kind, Prince = brave).

[1994] Output: The entered information is stored in a data structure within the terminal.

[1995] Step 2:

[1996] The terminal transmits the input information to the server.

[1997] Input: Story and character data entered by the user in Step 1.

[1998] Specific behavior: When the user clicks the "Submit" button, the data is sent to the server as an HTTP request.

[1999] Output: The data sent to the server.

[2000] Step 3:

[2001] The server converts the received data into a format suitable for the generative model.

[2002] Input: Story and character setting data received by the server.

[2003] Specific operation: Converts received data into, for example, JSON format and organizes the data into a fair format.

[2004] Output: Data converted to JSON format.

[2005] Step 4:

[2006] The server sends the transformed data to the generative model.

[2007] Input: Story and characterization data converted to JSON format.

[2008] What it does: Makes an API call and sends data to the appropriate endpoint.

[2009] Output: The data passed to the generative model.

[2010] Step 5:

[2011] Based on the data received, the generative AI model generates a story from each character's perspective.

[2012] Input: Story and characterization data in JSON format.

[2013] How it works: The generative AI model uses algorithms to dynamically generate a story from each character's perspective.

[2014] Output: Narrative data generated for each character.

[2015] Step 6:

[2016] The server receives the response from the generative AI model and receives the generated story data.

[2017] Input: Response data from the generative AI model.

[2018] Specific operation: Analyze the response and save the story data divided by character's perspective on the server.

[2019] Output: Story data from each character's perspective.

[2020] Step 7:

[2021] The server stores the received story data in a database by category.

[2022] Input: Story data from character perspectives.

[2023] Specific operation: For example, classify into categories such as "Cinderella," "Prince," "Stepmother," and "Sisters," and save them in a database.

[2024] Output: Story data in a categorized database.

[2025] Step 8:

[2026] The user uses a terminal to access the YourSTORY library and view stories from each character's perspective.

[2027] Input: Categorized story data.

[2028] Specific operation: Log in to the library using your device's browser, select the story from the perspective you want to see, and display it.

[2029] Output: Narrative content from a user-specified point of view.

[2030] Step 9:

[2031] The emotion engine recognizes the user's emotions.

[2032] Input: The user's facial expressions, voice, and other biometric signals acquired from the device.

[2033] Specific operation: Data is acquired through the camera and microphone, and analyzed to detect emotional state.

[2034] Output: Detected user emotion data.

[2035] Step 10:

[2036] The server receives the emotion data sent from the emotion engine.

[2037] Input: Emotion data sent from the emotion engine.

[2038] Specific operation: The server receives the emotion data and inputs it into the analysis system.

[2039] Output: Emotion data in the server.

[2040] Step 11:

[2041] A generative model dynamically adjusts the narrative based on the user's emotional data.

[2042] Input: User emotion data.

[2043] What it does: The generative model analyzes the emotional data and changes the tone and content of the generated story based on that.

[2044] Output: Dynamically adjusted narrative data that responds to the user's emotions.

[2045] Step 12:

[2046] The story the user views on their device will correspond to the user's emotional state.

[2047] Input: Dynamically adjusted narrative data.

[2048] What it does: When users revisit a story, they will see real-time updates based on sentiment.

[2049] Output: A personalized narrative experience.

[2050] (Application example 2)

[2051] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2052] Conventional story generation systems were able to generate a story from a fixed perspective based on user-entered settings, but lacked the ability to dynamically adjust the story content in response to the user's emotional state. This made it difficult to provide a story optimized for each user's individual emotional experience. Furthermore, there was a lack of an efficient system for generating stories from each character's perspective. This limited the user's ability to enjoy the story by changing their perspective.

[2053] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2054] In this invention, the server includes means for a user to input basic story settings and character settings, means for transmitting the user input information to a generative model, means for generating a story based on the perspective of each character from the generative model, means for receiving the generated story data, means for categorizing and storing the received story data, means for the user to view stories by perspective, means for recognizing the user's emotions, and means for dynamically adjusting the content of the story based on the emotions. This enables a personalized story experience according to the user's emotional state, making it possible to provide a system that allows users to enjoy stories from different perspectives.

[2055] "Means for users to input basic story settings and character settings" refers to the means by which users input the story title, characters' names, roles, personalities, etc.

[2056] "Means for sending user-input information to a generative model" refers to means for sending information on the basic story setting and character settings entered by the user to a generative AI model.

[2057] "Means for generating a story from each character's perspective from a generative model" refers to a means for a generative AI model to generate a story from each character's perspective based on information received from the user.

[2058] "Means for receiving generated story data" refers to means for receiving story data generated from a generative AI model.

[2059] The "means for categorizing and storing received story data" is a means for classifying received story data into specific categories and storing them in a database.

[2060] "Means for users to view stories from different perspectives" refers to means for users to view stories generated from the perspectives of each character.

[2061] "Means for recognizing the user's emotions" refers to a means for analyzing the user's facial expressions, voice, biometric signals, etc. to detect the user's emotional state.

[2062] "Means for dynamically adjusting story content based on emotions" refers to means for adapting and adjusting the content of a generated story in real time based on the recognized emotional state of a user.

[2063] MODE FOR CARRYING OUT THE INVENTION

[2064] System Overview

[2065] This invention is a system in which a user inputs basic story settings and character settings, and a generative AI model generates a story from each character's perspective based on that information. Furthermore, the system has the ability to recognize the user's emotions and dynamically adjust the story content based on those emotions. This system allows users to experience a personalized story from each perspective.

[2066] Hardware and software used

[2067] Hardware: Smartphones, smart glasses, head-mounted displays

[2068] Software: Python 3.8+, Flask (server-side), Emotion Recognition API

[2069] Data processing and data calculation

[2070] Enter and submit story settings

[2071] The user inputs the story title, characters' names, roles, personalities, etc. into a smartphone or other device. The input data is converted into JSON format and sent to the server as an HTTP request, allowing the server to receive the input data from the user.

[2072] Sending to the Generative Model

[2073] The server converts the received user story setting and character setting information into a format suitable for the generative AI model, and then sends the converted data to the generative AI model via an API call.

[2074] Story Generation

[2075] The generative AI model generates a story from each character's perspective based on the received data. For example, it generates the story of the fairy tale "Cinderella" from each character's perspective. This generated story data is sent back to the server.

[2076] Receiving and storing generated stories

[2077] The server receives the story data generated by the generative AI model, categorizes it by each character's perspective, and stores it in a database, improving search efficiency when users later view the story by perspective.

[2078] Viewing stories by point of view

[2079] Users can use their devices to view stories from different points of view, for example, they can select the Cinderella story as "from the stepmother's point of view" and start reading.

[2080] Emotion recognition and dynamic adjustment of narrative

[2081] The user's device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API. This emotional data is sent to the server, which then invokes a generative AI model based on the emotional data to dynamically adjust the content of the story. For example, if the user is in a happy state, the tone of the story will be changed to a more positive one.

[2082] Specific examples

[2083] 1. Enter the story setting

[2084] The user inputs the story setting for "Cinderella" on the device, along with details of the characters: "protagonist," "villain," "rival," and "savior."

[2085] Example prompt sentence:

[2086] Enter the story setting for Cinderella. Characters:

[2087] Name: Cinderella, Role: Protagonist, Personality: Kind

[2088] Name: Stepmother, Role: Antagonist, Character: Ruthless

[2089] Name: Older sisters, Role: Rival, Personality: Jealous

[2090] Name: Prince, Role: Savior, Personality: Sense of Justice

[2091] 2. Send to the generative model

[2092] The server sends the story setting to the generative AI model, which generates a story from each perspective.

[2093] 3. Receiving and storing generated stories

[2094] The generated stories are stored in a database by point of view.

[2095] 4. Emotion recognition

[2096] If the user's emotion is recognized as "happy," the system adjusts the story to a more positive tone.

[2097] 5. Viewing stories from different perspectives

[2098] Users view the adapted story on their device.

[2099] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2100] Step 1:

[2101] The user inputs the story setting.

[2102] Specifically, users use their smartphones or other devices to input the story title, characters' names, roles, personalities, etc. The input data is retrieved from the form and converted into JSON format.

[2103] Input: Basic story setting and character settings

[2104] Output: Story setting data converted to JSON format

[2105] Step 2:

[2106] The terminal transmits story setting data to the server.

[2107] Once the user has finished entering the settings, they press the "Submit" button, which sends an HTTP request from the device to the server, which then checks the received data and converts it into an appropriate format (e.g., JSON).

[2108] Input: Story setting data converted to JSON format

[2109] Output: Story setting data sent to the server

[2110] Step 3:

[2111] The server sends the data to the generative AI model.

[2112] The server verifies the accuracy of the received data, then converts it into a format suitable for the generative AI model, and sends this converted data to the generative AI model via an API call.

[2113] Input: Data converted into a format suitable for generative AI models

[2114] Output: Data sent to the generative AI model

[2115] Step 4:

[2116] A generative AI model generates the story.

[2117] The generative AI model generates a story from each character's perspective based on the received data. This generation process uses natural language processing technology, particularly analyzing prompts to develop the story. The generated story data is organized by each character's perspective and sent back to the server.

[2118] Input: Data sent to the generative AI model

[2119] Output: Narrative data generated by perspective

[2120] Step 5:

[2121] The server receives the generated story data and stores it in a database.

[2122] The server receives the story data sent from the generative AI model, categorizes the received data by perspective, and stores it in a database, which improves future search efficiency.

[2123] Input: Narrative data generated by perspective

[2124] Output: Categorized narrative data stored in a database

[2125] Step 6:

[2126] Users view stories from different perspectives.

[2127] The user uses the terminal to select a story by point of view and begin viewing. The terminal accesses the database and displays the selected story.

[2128] Input: Narrative data stored by point of view

[2129] Output: The story displayed on the user's terminal

[2130] Step 7:

[2131] The device recognizes the user's emotions.

[2132] The device analyzes the user's facial expressions, voice, and biometric signals to detect the user's emotional state using the Emotion Recognition API, and sends the resulting data to the server.

[2133] Input: Emotional data such as user facial expressions, voice, and biometric signals

[2134] Output: Emotion state data analyzed by the Emotion Recognition API

[2135] Step 8:

[2136] The server invokes a generative AI model based on the emotional data and dynamically adjusts the content of the story.

[2137] The server receives the emotional state data and sends prompts to the generative AI model again to adjust the story content, changing the tone and development of the story according to the user's emotional state. The adjusted story data is then regenerated and sent to the user's device.

[2138] Input: Emotion state data sent from the Emotion Recognition API

[2139] Output: Dynamically adjusted narrative data

[2140] Step 9:

[2141] The user views the tailored story.

[2142] The user then views the adjusted story on their device again, providing a story experience optimized for the user's emotional state.

[2143] Input: Dynamically adjusted narrative data

[2144] Output: The adjusted story displayed on the user's terminal

[2145] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2146] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2147] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2148] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2149] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2150] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2151] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2152] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2153] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2154] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2155] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2156] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2157] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2158] 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.

[2159] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2160] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2161] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2162] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2163] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2164] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2165] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2166] The following is further disclosed regarding the above embodiment.

[2167] (Claim 1)

[2168] A means for the user to input basic story settings and character settings;

[2169] a means for transmitting user input information to the generative model;

[2170] A means for generating a story based on each character's perspective from the generative model;

[2171] means for receiving the generated narrative data;

[2172] means for categorizing and storing the received story data;

[2173] A system that includes a means for a user to view a narrative by point of view.

[2174] (Claim 2)

[2175] 10. The system of claim 1, further comprising: means for converting user input information into a format suitable for the generative model.

[2176] (Claim 3)

[2177] 10. The system of claim 1, further comprising means for storing the generated narrative data in a database.

[2178] "Example 1"

[2179] (Claim 1)

[2180] a means for the user to input basic story settings and character settings;

[2181] means for transmitting the input user information to a server;

[2182] A means for the server to convert user input information into a format suitable for the generative model;

[2183] a means for the server to transmit the transformed information to the generative AI model;

[2184] A means for the generative AI model to generate a story based on each character's perspective;

[2185] A means for the server to receive the generated story data;

[2186] A means for the server to categorize and store the received story data;

[2187] A system including a means for a user to view a point-of-view narrative using a terminal.

[2188] (Claim 2)

[2189] 10. The system of claim 1, further comprising means for generating prompt sentences for generating a narrative based on the information received by the generative AI model.

[2190] (Claim 3)

[2191] 10. The system of claim 1, further comprising means for storing the generated narrative data in a database.

[2192] "Application Example 1"

[2193] (Claim 1)

[2194] A means for the user to input basic story settings and character settings;

[2195] a means for transmitting user input information to the generative model;

[2196] A means for generating a story based on each character's perspective from the generative model;

[2197] means for receiving the generated narrative data;

[2198] means for categorizing and storing the received story data;

[2199] A way for users to view stories from different perspectives,

[2200] means for delivering the story data to a content delivery service;

[2201] A means of providing it as an application that runs on a smartphone;

[2202] A system including:

[2203] (Claim 2)

[2204] 10. The system of claim 1, further comprising: means for converting user input information into a format suitable for the generative model.

[2205] (Claim 3)

[2206] 10. The system of claim 1, further comprising means for storing the generated narrative data in a database.

[2207] "Example 2: Combining Emotion Engines"

[2208] (Claim 1)

[2209] a means for a user to input a basic story setting and character settings;

[2210] means for transmitting user-entered information to the generative model;

[2211] A means for the generative model to generate a story based on each character's perspective;

[2212] means for receiving the generated narrative data;

[2213] means for categorizing and storing the received story data;

[2214] a means for a user to view the story from different perspectives;

[2215] an emotion engine that recognizes the user's emotions;

[2216] The system includes a means for dynamically adjusting the narrative based on emotion data from the emotion engine.

[2217] (Claim 2)

[2218] 10. The system of claim 1, further comprising means for converting information input by a user into a format suitable for the generative model.

[2219] (Claim 3)

[2220] 10. The system of claim 1, further comprising means for storing the generated narrative data in a database.

[2221] "Application example 2 when combining emotion engines"

[2222] (Claim 1)

[2223] A means for the user to input basic story settings and character settings;

[2224] a means for transmitting user input information to the generative model;

[2225] A means for generating a story based on each character's perspective from the generative model;

[2226] means for receiving the generated narrative data;

[2227] means for categorizing and storing the received story data;

[2228] A way for users to view stories from different perspectives,

[2229] a means of recognizing a user's emotions;

[2230] A system that includes a means for dynamically adjusting story content based on emotion.

[2231] (Claim 2)

[2232] 10. The system of claim 1, further comprising: means for converting user input information into a format suitable for the generative model.

[2233] (Claim 3)

[2234] 10. The system of claim 1, further comprising means for storing the generated narrative data in a database. [Explanation of symbols]

[2235] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the user to input basic story settings and character settings; a means for transmitting user input information to the generative model; A means for generating a story based on each character's perspective from the generative model; means for receiving the generated narrative data; means for categorizing and storing the received story data; A system that includes a means for a user to view a narrative by point of view.

2. The system of claim 1 , further comprising: means for converting user input information into a format suitable for the generative model.

3. 10. The system of claim 1, further comprising means for storing the generated story data in a database.

Images