System
The system addresses the issue of unfinished stories by using a generative model to predict and format endings for delivery in user-desired formats, effectively completing stories like manga.
Patent Information
- Application Number
- JP2024121611
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2026-02-05
AI Technical Summary
Existing systems lack effective means to provide endings for unfinished stories, particularly manga, due to author illness or accidents, leaving readers unsatisfied and unable to know the story's conclusion.
A system that includes data acquisition, a generative model using machine learning to predict the ending, formatting for text or visual presentation, and data transmission to user terminals, ensuring the ending is delivered in a user-desired format.
The system quickly and accurately generates and delivers the ending of an unfinished story in a user-friendly format, satisfying the demand for story completion.
Smart Images

Figure 2026019863000001_ABST
Abstract
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] Unfinished stories, especially manga, can end publication due to the author's sudden illness or an unforeseen accident. In such cases, many readers often end up never finding out the ending of the story. Furthermore, readers often feel regretful that they will not be able to find out the ending of the story due to their own lifespan. As such, there is a growing demand to know the ending of unfinished stories, but the current situation is that there are not enough solutions to this. [Means for solving the problem]
[0005] In order to solve the above problems, the present invention provides the following means. First, the system includes data acquisition means for acquiring story and character information from existing data. Then, the system provides a generative model means for predicting the ending of an unfinished story based on the acquired information. The system further includes formatting means for formatting the generated ending into a text or visual format. The system also includes data transmission means for providing the ending to a user's terminal, and user interface means for transmitting title information of the unfinished story selected by the user to a server. Additionally, the system includes database acquisition means for acquiring the acquired story and character information from a database, and generative model means using a machine learning model that statistically learns past story data, thereby providing a system that predicts the ending while faithfully reproducing the style of each story and the personalities of its characters.
[0006] "Story information" is detailed data about the development and plot of a story, and refers to the sequence of events and circumstances that lead to the progression of the story.
[0007] "Character information" is detailed data about the personalities, backgrounds, relationships, and behavior patterns of the people and characters that appear in the story.
[0008] "Data acquisition means" refers to a function or device for acquiring story information and character information from a database or external storage.
[0009] A "generative modeling tool" is an algorithm or software that predicts and generates the ending of an unfinished story based on existing story and character information.
[0010] The "formatting means" is a processing system that processes the conclusion generated by the generative model into a text or visual format and displays it in an easy-to-read format.
[0011] "Data transmission means" refers to a communication function or protocol for transmitting the generated outcome data to the user's terminal.
[0012] "User interface means" means an interface through which a user interacts with the system and provides unfinished story title information and other input to the system.
[0013] The "database acquisition means" is a function for extracting necessary data from a database that stores story information and character information.
[0014] A "machine learning model" is an artificial intelligence technology that statistically learns past narrative data and predicts future events and outcomes based on the results of that learning.
[0015] A "user terminal" is an electronic device such as a computer, smartphone, or tablet that a user uses to access the system. [Brief explanation of the drawings]
[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION
[0017] 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.
[0018] First, the terms used in the following description will be explained.
[0019] 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).
[0020] 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.
[0021] 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.
[0022] 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.
[0023] 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."
[0024] [First embodiment]
[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0026] 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.
[0027] 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).
[0028] 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.
[0029] 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.
[0030] 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.
[0031] 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.
[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0033] 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.
[0034] 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.
[0035] 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.
[0036] 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."
[0037] 1. System Overview
[0038] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an unfinished story selected by the user, the server retrieves information from the database, uses the generative model to predict the ending, formats it, and delivers it to the terminal.
[0039] 2. Providing a user interface
[0040] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0041] 3. Data transmission
[0042] When the user selects an unfinished story that interests them and clicks the request button for generating an ending, the terminal sends the title information of the selected manga to the server.
[0043] 4. Acquiring story data
[0044] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[0045] 5. Running the AI model
[0046] The server inputs the acquired story data into a generative model. The generative model uses machine learning techniques to analyze existing story data and character information to predict the ending of an unfinished story. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[0047] 6. Ending tweaks
[0048] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0049] 7. Data Transmission and Display
[0050] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[0051] Specific examples
[0052] 1. Example 1: Textual ending generation
[0053] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0054] The terminal transmits the selected title "Adventure Journey" to the server.
[0055] The server retrieves existing story data for "Adventure Journey" from the database.
[0056] The server inputs the acquired data into a generative model and generates text as the result.
[0057] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[0058] The terminal displays the generated text to the user.
[0059] 2. Example 2: Manga-style ending generation
[0060] The user selects the unfinished story "Magic Forest" from the device's UI.
[0061] The terminal transmits the selected title "Magical Forest" to the server.
[0062] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0063] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[0064] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[0065] The formatted manga format data is sent to the device.
[0066] The terminal displays the generated comic page to the user.
[0067] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0068] The processing flow will be explained below.
[0069] Step 1:
[0070] The terminal provides the user with an interface for selecting an incomplete story title, specifically, a list of available incomplete stories is displayed on the screen.
[0071] Step 2:
[0072] The user selects an unfinished story that they are interested in from the list on the interface and requests the creation of an ending. By clicking the request button, the title information of the selected story is sent.
[0073] Step 3:
[0074] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[0075] Step 4:
[0076] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0077] Step 5:
[0078] The server inputs the acquired story data and character information into a generative model, which uses this data to predict and generate the ending of the unfinished story. AI models and machine learning algorithms are used.
[0079] Step 6:
[0080] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0081] Step 7:
[0082] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[0083] Step 8:
[0084] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[0085] In this way, the system allows the user to find out the ending of an unfinished story.
[0086] Example 1
[0087] 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."
[0088] Conventional technologies have limited means for predicting the ending of an unfinished story and providing it to users. As a result, it has been difficult to quickly and appropriately respond to users' needs to know the ending of the story. In addition, some systems only support either text or visual formats, which means they cannot meet the needs of a wide range of users.
[0089] 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.
[0090] In this invention, the server includes a user interface means for receiving the title of the unfinished story selected by the user, a data acquisition means for acquiring story and character information from existing data, a generative model means including a generative AI model for predicting the ending of the unfinished story based on the acquired information, a formatting means for formatting the generated ending into a text format or a visual format, and a data transmission means for transmitting the formatted ending data to the user's terminal. This makes it possible to quickly generate the ending of the unfinished story and provide it in the text format or visual format desired by the user.
[0091] A "user interface means" is a device or software that provides an interface for a user to interact with the system.
[0092] "Data acquisition means" refers to a device or software for acquiring story and character information from existing data.
[0093] A "generative AI model" is a model that uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story.
[0094] A "generative model means" is a device or software that includes a generative AI model for predicting the outcome of an unfinished story based on acquired information.
[0095] A "formatter" is a device or software for formatting the generated conclusion into textual or visual form.
[0096] The "data transmission means" is a device or software for transmitting formatted conclusion data to the user's terminal.
[0097] The "database acquisition means" is a device or software that allows the server to acquire story and character information from the database.
[0098] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface.
[0099] Hardware and Software Configuration
[0100] Terminal: A device that provides a user interface and receives input from a user. This can be a personal computer, smartphone, tablet, etc. The terminal has UI display software installed, which displays a list of open stories and accepts user selections.
[0101] Server: Acts as the central processing unit, acquiring data, running the generative AI model, formatting and transmitting the data. The server has database connection software and Python scripts installed to run the generative AI model (e.g., GPT-3).
[0102] Database: A data store for story and character information. This is where existing story data and character details are stored.
[0103] Generative AI models: Machine learning models designed to predict the ending of an unfinished story, such as OpenAI's GPT-3, that can analyze existing story data and generate new endings.
[0104] System Operation
[0105] The system operates as follows.
[0106] 1. Providing a user interface
[0107] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0108] 2. Data transmission
[0109] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[0110] 3. Acquiring story data
[0111] The server retrieves related story data and character information from the database based on the received story title information. The server issues a query to the database to retrieve the required data.
[0112] 4. Running the AI model
[0113] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. For example, a prompt sentence such as "The title of the story is 'Adventure Journey'. Please complete the unfinished part of the story" can be input into the generative model.
[0114] 5. Ending tweaks
[0115] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0116] 6. Data transmission and display
[0117] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed in a text viewer, and if it is in manga format, it is displayed in a page viewer.
[0118] Specific examples
[0119] As a concrete example, the following scenario can be considered.
[0120] Example 1: Textual ending generation
[0121] 1. The user selects the unfinished story "Adventure Journey" from the device's UI.
[0122] 2. The terminal sends the selected title "Adventure Journey" to the server.
[0123] 3. The server retrieves existing story data for "Adventure Journey" from the database.
[0124] 4. The server inputs the acquired data into the generative model and generates text as the result.
[0125] 5. Format the generated text, "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions.", and send it to the device.
[0126] 6. The terminal displays the generated text to the user.
[0127] Example 2: Manga-style ending generation
[0128] 1. The user selects the unfinished story "Magic Forest" from the device's UI.
[0129] 2. The device sends the selected title "Magical Forest" to the server.
[0130] 3. The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0131] 4. The server inputs the acquired data into a generative model and generates scenes and dialogues as predicted outcomes.
[0132] 5. Format the generated scenes and dialogues into a comic book format and create page layouts.
[0133] 6. Send the formatted manga data to the device.
[0134] 7. The terminal displays the generated comic page to the user.
[0135] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0137] Step 1: Displaying the User Interface
[0138] The terminal displays an interface for the user to select an incomplete story, specifically, a list of available incomplete stories is displayed on the screen.
[0139] Input: List of unfinished stories in the system
[0140] Output: A list of stories displayed on the device screen
[0141] Specific operation: When the device is initialized, it retrieves the list of unfinished stories from the server and passes that data to the UI component to display the list.
[0142] Step 2: User selects story and submits request
[0143] The user selects an unfinished story of interest from the list and clicks a button to request the creation of an ending for that story.
[0144] The terminal transmits the title information of the selected story to the server.
[0145] Input: User selection and title of selected story
[0146] Output: Sends a request to the server containing the title of the selected story.
[0147] Specific operation: The device catches the user's click event and sends a POST request to the server with the title information of the selected story in JSON format.
[0148] Step 3: Get Story Data
[0149] The server retrieves related story data and character information from the database based on the received story title information.
[0150] Input: Story title information received from the device
[0151] Output: Story data and character information retrieved from the database
[0152] Specific operation: The server executes an SQL query using the story title to retrieve the corresponding story data from the database. For example, it executes the query "SELECT FROM stories WHERE title="Adventure Journey"".
[0153] Step 4: Running the generative AI model
[0154] The server inputs the acquired story data into a generative AI model to predict the ending of the unfinished story.
[0155] Input: Story data and character information retrieved from the database
[0156] Output: Outcome data output from the generative AI model
[0157] Specific operation: The server runs a Python script and inputs story data and a prompt to a generative AI model (e.g., GPT-3). An example of the prompt is "The title of the story is 'Adventure Journey'. Please complete the unfinished parts of the story."
[0158] Step 5: Formatting the outcome data
[0159] The server formats the generated outcome data into a textual or visual format.
[0160] Input: Outcome data output from the generative AI model
[0161] Output: Formatted outcome data (text or visual)
[0162] What it does: The server formats the generated text into HTML or Markdown, edits the scenes and dialogue in the case of manga, and generates the visual data using page layout software.
[0163] Step 6: Send and display the outcome data
[0164] The server sends the formatted outcome data to the user's terminal, which displays the received data to the user.
[0165] Input: Formatted ending data sent from the server
[0166] Output: The outcome data displayed on the user's terminal
[0167] Specific operation: The server sends the formatted ending data in JSON format to the device. The device receives it and displays it to the user in a text viewer or manga viewer.
[0168] (Application example 1)
[0169] 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."
[0170] In recent years, there has been an increasing demand for the ending of unfinished stories, but there are currently no appropriate means to meet this demand. Users cannot obtain automatically generated endings based on existing story data, and must wait a long time for the ending. This makes it difficult to sustain users' interest, and there is a growing demand for early conclusions to stories.
[0171] 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.
[0172] In this invention, the server includes data acquisition means for acquiring story and actor data from existing information, generative model means for predicting the ending of an unfinished story based on the acquired data, formatting means for formatting the generated ending in a text format or a visual format, data transmission means for providing the ending to the user's information terminal, interface means for displaying a list of unfinished stories that the user can select, and request transmission means for transmitting an ending generation request based on the story title selected by the user, thereby enabling the user to quickly obtain the predicted ending of the unfinished story.
[0173] "Data acquisition tools" are functions for collecting story and actor data from existing sources.
[0174] The "generative model means" is a function that automatically predicts the ending of an unfinished story based on acquired story and actor data.
[0175] The "formatting means" is a function for formatting the generated conclusion in a character string format or a visual format so that it can be displayed to the user in an easy-to-understand manner.
[0176] "Data transmission means" is a function for transmitting the generated ending to the user's information terminal.
[0177] The "interface means" is a function that displays a list of incomplete stories that the user can select from and provides an interface for the user to select a story.
[0178] The "request sending means" is a function for sending the title information of the story selected by the user to the server and executing the ending generation request.
[0179] "Database acquisition means" is a function for acquiring story and actor data from a database.
[0180] 1. System Overview
[0181] The system of this invention is designed to allow users to predict the ending of an incomplete story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an incomplete story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, formats it, and delivers it to the terminal.
[0182] 2. Providing a user interface
[0183] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0184] 3. Data transmission
[0185] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[0186] 4. Acquiring story data
[0187] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[0188] 5. Running the AI model
[0189] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. OpenAI's GPT-3 is used as the generative AI model used for prediction. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[0190] 6. Ending tweaks
[0191] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of visual format, the server creates a page layout based on the generated scenes and dialogue, and combines character images.
[0192] 7. Data Transmission and Display
[0193] The server sends the formatted conclusion data to the user's terminal, which displays the received data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[0194] Specific examples
[0195] Example 1: Textual ending generation
[0196] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0197] The terminal transmits the selected title "Adventure Journey" to the server.
[0198] The server retrieves existing story data for "Adventure Journey" from the database.
[0199] The server inputs the acquired data into a generative model and generates text as the result.
[0200] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[0201] The terminal displays the generated text to the user.
[0202] Example 2: Visual Outcome Generation
[0203] The user selects the unfinished story "Magic Forest" from the device's UI.
[0204] The terminal transmits the selected title "Magical Forest" to the server.
[0205] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0206] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[0207] Format the generated scenes and dialogues into a visual format and create a page layout.
[0208] Sends formatted, visually formatted data to the terminal.
[0209] The terminal displays the generated page to the user.
[0210] Prompt Sentence Examples
[0211] Story Data: "The protagonist goes on an adventure to find treasure."
[0212] Prompt: "The protagonist goes on an adventure to find treasure. What is the outcome of this story?"
[0213] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0214] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0215] Step 1:
[0216] The user selects an unfinished story.
[0217] The user selects a story of interest from the displayed list of unfinished stories through the user interface of the terminal. The input is the title of the story based on the user's selection. The output is the title information of the selected story.
[0218] Step 2:
[0219] The terminal transmits the story title information to the server.
[0220] The terminal collects the story title information selected by the user and sends it to the server as a POST request. The input is the story title information selected by the user. The output is the title information received by the server.
[0221] Step 3:
[0222] The server retrieves the story data from the database.
[0223] The server issues a query to the database based on the received story title to retrieve related story data and character information. The input is story title information, and the output is story data and character information.
[0224] Step 4:
[0225] The server inputs story data into a generative model to predict the ending.
[0226] The server inputs the acquired story data and character information into a generative AI model. The generative model (e.g., GPT-3) analyzes the input data, creates a generative prompt to predict the optimal ending, and generates the ending. The input is story data and character information, and the output is the predicted ending data.
[0227] Step 5:
[0228] The server formats the resulting result.
[0229] The server takes the outcome output by the generative model and formats it into a user-readable format (text or visual format). The input is the generated outcome data, and the output is the formatted outcome data.
[0230] Step 6:
[0231] The server transmits the formatted conclusion data to the terminal.
[0232] The server sends the formatted outcome data to the user's terminal. The input is the formatted outcome data, and the output is the outcome data received by the terminal.
[0233] Step 7:
[0234] The terminal displays the received conclusion data to the user.
[0235] The terminal displays the outcome data received from the server to the user through a user interface. The input is the outcome data received from the server, and the output is the outcome information displayed to the user.
[0236] This allows the user to quickly find out the ending of an unfinished story.
[0237] 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.
[0238] 1. System Overview
[0239] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, a user interface, and an emotion engine. For an unfinished story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, and adjusts the ending based on the user's emotions using the emotion engine before delivering it to the terminal.
[0240] 2. Providing a user interface
[0241] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0242] 3. Data transmission
[0243] When a user selects an unfinished story in which they are interested, allows acquisition of emotional data, and clicks a request button for generating an ending, the terminal sends the title information and emotional state information of the selected story to the server.
[0244] 4. Acquiring story data
[0245] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0246] 5. Use of Emotion Engine
[0247] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[0248] 6. Running the AI model
[0249] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[0250] 7. Ending tweaks
[0251] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0252] 8. Data Transmission and Display
[0253] The server sends the formatted conclusion data to the terminal, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[0254] Specific examples
[0255] 1. Example 1: Textual Conclusion and Emotional Adaptation
[0256] The user selects the unfinished story "Adventure Journey" from the device's UI and grants camera permission.
[0257] The terminal transmits the selected title "Adventure Journey" and the emotion data to the server.
[0258] The server retrieves existing story data for "Adventure Journey" from the database.
[0259] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[0260] The server inputs the acquired data into a generative model to generate an outcome based on the emotional state.
[0261] The generated text "The end of the adventure: The protagonist finally finds the treasure and rejoices with his companions." is formatted and sent to the device.
[0262] The terminal displays the generated text to the user.
[0263] 2. Example 2: Manga-style ending and emotional adaptation
[0264] The user selects the unfinished story "Magical Forest" from the device's UI and grants camera permission.
[0265] The terminal transmits the selected title "Magical Forest" and the emotion data to the server.
[0266] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0267] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[0268] The server uses a generative model based on the acquired data to generate scenes and dialogues based on the emotional state.
[0269] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[0270] The formatted manga format data is sent to the device.
[0271] The terminal displays the generated comic page to the user.
[0272] In this way, the system of the present invention generates and provides the user with an ending to an unfinished story while taking into account the user's emotions, providing a more personalized experience.
[0273] The processing flow will be explained below.
[0274] Step 1:
[0275] The terminal provides the user with an interface for selecting an incomplete story title, and the interface displays a list of available incomplete stories.
[0276] Step 2:
[0277] The user selects an unfinished story of interest from a list on the interface, allows emotional data acquisition, and then requests the creation of an ending. By clicking the request button, the title information and emotional state information of the selected story are sent.
[0278] Step 3:
[0279] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[0280] Step 4:
[0281] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0282] Step 5:
[0283] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[0284] Step 6:
[0285] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[0286] Step 7:
[0287] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0288] Step 8:
[0289] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[0290] Step 9:
[0291] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[0292] Example 2
[0293] 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."
[0294] Existing story generation systems often provide a uniform ending without considering the user's emotional state, resulting in low user satisfaction. Furthermore, there is a lack of technology that provides individually tailored endings based on the user's choices and emotions. To address this issue, it is necessary to provide a system that recognizes the user's emotional state in real time and generates and adjusts endings based on that information.
[0295] 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.
[0296] In this invention, the server includes data acquisition means for acquiring information from existing data, generative model means for predicting an ending of an unfinished story based on the acquired information, and emotion adaptation means for adjusting the generated ending based on the user's emotional state, thereby enabling the provision of a personalized ending according to the user's selection and emotional state.
[0297] "Data acquisition means" refers to means for extracting story data and character information from an existing database.
[0298] "Generative model means" refers to a machine learning model for predicting the ending of an unfinished story based on acquired story data and character information.
[0299] A "formatting tool" is a tool for formatting the generated story's ending in text or visual form.
[0300] The "data transmission means" is a communication means for providing the generated ending to the user's terminal after formatting.
[0301] "Emotion engine means" refers to software or hardware for analyzing a user's facial expressions and recognizing the user's emotional state.
[0302] "Emotional adaptation means" are means for adjusting the outcome predicted by the generative model based on the perceived emotional state of the user.
[0303] "User interface means" refers to an operation screen that allows the user to select the title of an unfinished story and transmits that information to the server.
[0304] The "database acquisition means" is a query issuing means for the server to acquire the necessary story data and character information from the database.
[0305] The present invention is a system designed to meet the needs of users who want to know the ending of an unfinished story. The system mainly includes a terminal, a server, a database, a generative AI model, a user interface, and an emotion engine. Below, we will explain in detail how to implement the invention, while specifically showing the hardware and software used.
[0306] 1. Providing a user interface
[0307] The terminal provides the user with an interface for selecting unfinished stories. Specifically, there is an application that runs on a web browser, and the user can select a story of interest from a list of unfinished stories displayed.
[0308] Software used:
[0309] Browser-based UI frameworks (e.g., React, Vue.js)
[0310] Examples:
[0311] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0312] 2. Data transmission
[0313] When the user selects a story, allows acquisition of emotional data, and then clicks the request button, the terminal transmits the selected title and emotional state information to the server.
[0314] Software and hardware used:
[0315] Network communication protocols (e.g. HTTP / HTTPS), camera on user device
[0316] Examples:
[0317] The user selects "Adventure Journey," allows emotion data acquisition, and clicks the request button.
[0318] 3. Acquiring story data
[0319] The server retrieves the relevant story data and character information from the database based on the received story title information, specifically by issuing an SQL query to extract the relevant data.
[0320] Software used:
[0321] Database management systems (e.g., MySQL, PostgreSQL)
[0322] Examples:
[0323] The server issues the query "SELECT FROM stories WHERE title = 'Adventure Journey'" to retrieve story data from the database.
[0324] 4. Use of Emotion Engine
[0325] The device uses a camera to analyze the user's facial expressions and recognizes their emotional state using an emotion engine, and transmits the recognized emotional state information to a server in real time.
[0326] Software used:
[0327] Emotion analysis API (e.g. Emotion API)
[0328] Examples:
[0329] The device uses the Emotion API to analyze the user's facial expression and transmits to the server that the user is "sad."
[0330] 5. Running the generative AI model
[0331] The server inputs the acquired story data, character information, and emotional state information into a generative AI model, which uses machine learning techniques to predict the ending of the unfinished story and adjust it based on the emotional state.
[0332] Software used:
[0333] Generative AI models (e.g., OpenAI GPT-4)
[0334] Examples:
[0335] The server inputs the following prompt into the generative AI model: "The user feels sad about the ending of the story 'Adventure Journey'. Please generate an ending based on this emotion."
[0336] 6. Ending tweaks
[0337] The server formats the generated ending data. In the case of text format, it formats the sentences, and in the case of visual (manga) format, it creates a page layout based on the scenes and dialogues.
[0338] Software used:
[0339] Text processing libraries (e.g., Python's NLTK), visual editing software (e.g., Adobe Photoshop)
[0340] Examples:
[0341] Format the generated text "The end of the adventure: The protagonist ends his journey in sadness." and, in the case of a manga format, create a page layout with scenes and dialogues.
[0342] 7. Data Transmission and Display
[0343] The server sends the formatted outcome data to the terminal, which displays the data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[0344] Software and hardware used:
[0345] Network communication protocol (e.g. HTTP / HTTPS), HTML viewer or dedicated app
[0346] Examples:
[0347] The server sends formatted text data and visual data to the terminal, which displays it to the user.
[0348] The above is a concrete embodiment of the present invention. The system provides a personalized story ending based on the user's choices and emotional state, increasing user satisfaction.
[0349] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0350] Step 1: Display and select the user interface
[0351] Description: The device provides the user with an interface for selecting an incomplete story. The interface displays a list of existing incomplete stories. The user can select a story from the list that interests them.
[0352] Input: A list of unfinished stories on the device
[0353] Output: The specific story title selected by the user
[0354] Specific behavior:
[0355] The device displays a list of unfinished stories as HTML on the browser.
[0356] The user clicks to select "Magic Forest" from the list.
[0357] Step 2: Sending data
[0358] Description: When the user selects a story and clicks the request button after allowing emotional data acquisition, the device sends the selected title and emotional state information to the server.
[0359] Input: User-selected story title, permission to create emotion data
[0360] Output: Story title and emotional state information sent to the server
[0361] Specific behavior:
[0362] The user selects "Magical Forest," allows acquisition of emotion data, and clicks the request button.
[0363] The terminal sends the selected title "Magical Forest" and the user's emotional state information to the server as an HTTP request.
[0364] Step 3: Get Story Data
[0365] Description: The server retrieves related story data and character information from the database based on the received story title information.
[0366] Input: Story title information received by the server
[0367] Output: Story data and character information retrieved from the database
[0368] Specific behavior:
[0369] The server issues the following SQL query to the database: SELECT FROM stories WHERE title = 'Magic Forest'.
[0370] The database returns relevant story data and character information based on the query.
[0371] Step 4: Use the Emotion Engine
[0372] Description: The device uses a camera to analyze the user's facial expressions and utilizes an emotion engine to recognize the user's emotional state. The device transmits the recognized emotional state information to the server in real time.
[0373] Input: A user's face image captured by a camera
[0374] Output: Emotional state information sent to the server
[0375] Specific behavior:
[0376] The device sends the user's facial image to the Emotion API.
[0377] The Emotion API analyzes images and recognizes the user's emotional state as "sad."
[0378] The terminal transmits the recognized emotional state to the server.
[0379] Step 5: Running the generative AI model
[0380] Description: The server inputs the acquired story data, character information, and emotional state information into a generative model. Based on this data, the generative model predicts the ending of the unfinished story and adjusts it based on the user's emotional state.
[0381] Input: Story data, character information, emotional state information
[0382] Output: The generated story ending
[0383] Specific behavior:
[0384] The server inputs this data into a generative AI model.
[0385] A generative AI model (e.g., GPT-4) uses this data to generate a story ending, adjusting it depending on the emotional state.
[0386] The server receives the generated outcome.
[0387] Step 6: Shaping the ending
[0388] Description: The server formats the generated outcome data, either by formatting the sentences in the text format or by creating a page layout based on the scenes and dialogue in the visual format.
[0389] Input: Generated story ending
[0390] Output: Formatted text or visual data
[0391] Specific behavior:
[0392] The server formats the generated text, "The End of the Enchanted Forest: The Protagonist Ends His Journey in Sadness.", to make it easier to read.
[0393] In the manga format, the page layout is created based on the generated scenes and dialogue.
[0394] Step 7: Send and display data
[0395] Description: The server sends the formatted outcome data to the terminal, which displays this data to the user.
[0396] Input: Formatted outcome data
[0397] Output: The outcome displayed on the user's terminal
[0398] Specific behavior:
[0399] The server sends formatted text data and visual data to the terminal.
[0400] The device receives it and displays it to the user, either as text if it is in text format or in a page viewer if it is in visual format.
[0401] (Application example 2)
[0402] 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."
[0403] In recent years, users have increasingly expressed a desire to know the ending of a story in a way that reflects their own emotional state. However, existing systems have difficulty generating endings that reflect the user's emotional state. Furthermore, the generated story endings do not necessarily match the user's emotions, resulting in a uniform user experience.
[0404] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data acquisition means for acquiring story and character information from existing data, generative model means for predicting the ending of an unfinished story based on the acquired information, formatting means for formatting the generated ending into a text format or a visual format, emotion analysis means for analyzing the user's facial expression to acquire emotion data, emotion adjustment means for adjusting the ending using the acquired emotion data, and data transmission means for providing the adjusted ending to the user's terminal. This makes it possible to provide a personalized story ending that corresponds to the user's emotional state.
[0405] "Data acquisition means" refers to a method for acquiring story and character information from existing data.
[0406] A "generative modeling method" is a method for predicting the outcome of an unfinished story based on acquired information.
[0407] A "formatter" is a method for formatting the generated conclusion into textual or visual form.
[0408] The "emotion analysis means" is a method for analyzing the user's facial expression to obtain emotion data.
[0409] "Emotion adjustment means" is a method for adjusting the ending using the acquired emotion data.
[0410] A "data transmission means" is a method for providing a tailored outcome to a user's terminal.
[0411] The "user interface means" is a method for transmitting title information of an unfinished story selected by the user to the server.
[0412] The "database acquisition means" is a method for acquiring acquired story and character information from the database.
[0413] The present invention is a system that uses emotional data to provide a personalized ending to an unfinished story in response to a user's desire to know the ending of the story. This system implements the invention through the following steps.
[0414] 1. System Overview
[0415] The system includes a terminal, a server, a data acquisition means, a generative model means, an emotion analysis means, an emotion adjustment means, a formatting means, a data transmission means, a user interface means, and a database acquisition means. A user uses the terminal to select an unfinished story title and make a request to know the subsequent ending.
[0416] 2. Data Acquisition
[0417] The server uses a database acquisition means to acquire related story data and character information based on the story title information sent by the user. The database stores existing story data and character information, and generates an ending based on this information.
[0418] 3.Emotion analysis
[0419] The device uses a camera to analyze the user's facial expressions and uses an emotion analysis means to recognize the user's emotional state. This emotion analysis means uses facial recognition technology to analyze the user's facial expressions and obtain emotional data such as joy, sadness, and excitement. Libraries such as OpenCV and TensorFlow / Keras are used for this analysis.
[0420] 4. Generative Model
[0421] The server inputs the acquired story data, character information, and emotional state information into a generative modeling means. The generative modeling means uses machine learning technology to analyze existing data and predict the ending of the unfinished story. Furthermore, an emotional adjustment means adjusts the ending according to the user's emotional state.
[0422] 5. Ending tweaks
[0423] The generated ending data is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated content is formatted into easy-to-read sentences, and in the case of the manga format, a page layout is created based on the generated scenes and dialogues, and character drawings are combined to form a manga page.
[0424] 6. Providing an ending
[0425] The formatted conclusion data is sent to the terminal using the data transmission means, and the terminal displays it to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[0426] Specific examples
[0427] 1. Example 1: Textual Conclusion and Emotional Adaptation
[0428] The user selects the unfinished story from the device UI and grants camera permission.
[0429] The terminal transmits the selected title and emotion data to the server.
[0430] The server retrieves existing story data from a database.
[0431] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[0432] The server generates an outcome based on the emotional state, formats it, and sends it to the terminal.
[0433] The terminal displays the generated text to the user.
[0434] 2. Example 2: Manga-style ending and emotional adaptation
[0435] The user selects the unfinished story from the device UI and grants camera permission.
[0436] The terminal transmits the selected title and emotion data to the server.
[0437] The server retrieves existing story data and character information from a database.
[0438] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[0439] The server generates scenes and dialogues based on the emotional state, formats them, and sends them to the device.
[0440] The terminal displays the generated comic page to the user.
[0441] Example prompts for generative AI models
[0442] "The story is set in a fantasy genre. The hero is a hero who is forced to make an important decision during his adventure. An emotion of excitement was detected from the user's facial expression. Please generate the ending of the story."
[0443] As described above, the present invention generates an ending to an unfinished story in a manner that takes into account the user's emotions, thereby providing a personalized content experience.
[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0445] Step 1:
[0446] The user selects the title of an unfinished story using the user interface of the terminal and grants permission to use the camera. The terminal receives input from the user and obtains title information of the selected story.
[0447] Step 2:
[0448] The device captures the user's facial expression along with the acquired story title information with a camera and analyzes the facial expression using an emotion analysis means. The emotion analysis means uses the OpenCV library and TensorFlow / Keras model to identify the user's emotional state (e.g., joy, sadness, excitement) from the facial expression data. The analysis results are output as emotion data.
[0449] Step 3:
[0450] The terminal transmits the title information and emotion data of the selected story to the server. Based on the story title information received from the terminal, the server uses a database acquisition means to acquire related story data and character information. The database stores existing story data and character information.
[0451] Step 4:
[0452] The server inputs the story data, character information, and emotion data acquired by the database acquisition means into the generative model means. The generative model means uses machine learning techniques (TensorFlow / Keras) to predict the ending of the unfinished story. Based on the emotion data, the ending is adjusted to adapt to the user's emotional state.
[0453] Step 5:
[0454] The ending data generated by the generative model means is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated ending is formatted into easy-to-read sentences. In the case of the visual format (manga format), a page layout is created based on the generated scenes and dialogue, and character drawings are combined to format the ending.
[0455] Step 6:
[0456] The server transmits the formatted ending data to the terminal using a data transmission means. The terminal displays the received ending data to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[0457] In this way, a personalized story ending is provided that responds to the user's emotional state.
[0458] 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.
[0459] 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.
[0460] 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.
[0461] [Second embodiment]
[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0463] 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.
[0464] 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).
[0465] 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.
[0466] 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.
[0467] 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).
[0468] 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.
[0469] 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.
[0470] 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.
[0471] 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.
[0472] 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.
[0473] 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."
[0474] 1. System Overview
[0475] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an unfinished story selected by the user, the server retrieves information from the database, uses the generative model to predict the ending, formats it, and delivers it to the terminal.
[0476] 2. Providing a user interface
[0477] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0478] 3. Data transmission
[0479] When the user selects an unfinished story that interests them and clicks the request button for generating an ending, the terminal sends the title information of the selected manga to the server.
[0480] 4. Acquiring story data
[0481] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[0482] 5. Running the AI model
[0483] The server inputs the acquired story data into a generative model. The generative model uses machine learning techniques to analyze existing story data and character information to predict the ending of an unfinished story. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[0484] 6. Ending tweaks
[0485] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0486] 7. Data Transmission and Display
[0487] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[0488] Specific examples
[0489] 1. Example 1: Textual ending generation
[0490] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0491] The terminal transmits the selected title "Adventure Journey" to the server.
[0492] The server retrieves existing story data for "Adventure Journey" from the database.
[0493] The server inputs the acquired data into a generative model and generates text as the result.
[0494] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[0495] The terminal displays the generated text to the user.
[0496] 2. Example 2: Manga-style ending generation
[0497] The user selects the unfinished story "Magic Forest" from the device's UI.
[0498] The terminal transmits the selected title "Magical Forest" to the server.
[0499] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0500] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[0501] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[0502] The formatted manga format data is sent to the device.
[0503] The terminal displays the generated comic page to the user.
[0504] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0505] The processing flow will be explained below.
[0506] Step 1:
[0507] The terminal provides the user with an interface for selecting an incomplete story title, specifically, a list of available incomplete stories is displayed on the screen.
[0508] Step 2:
[0509] The user selects an unfinished story that they are interested in from the list on the interface and requests the creation of an ending. By clicking the request button, the title information of the selected story is sent.
[0510] Step 3:
[0511] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[0512] Step 4:
[0513] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0514] Step 5:
[0515] The server inputs the acquired story data and character information into a generative model, which uses this data to predict and generate the ending of the unfinished story. AI models and machine learning algorithms are used.
[0516] Step 6:
[0517] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0518] Step 7:
[0519] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[0520] Step 8:
[0521] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[0522] In this way, the system allows the user to find out the ending of an unfinished story.
[0523] Example 1
[0524] 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."
[0525] Conventional technologies have limited means for predicting the ending of an unfinished story and providing it to users. As a result, it has been difficult to quickly and appropriately respond to users' needs to know the ending of the story. In addition, some systems only support either text or visual formats, which means they cannot meet the needs of a wide range of users.
[0526] 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.
[0527] In this invention, the server includes a user interface means for receiving the title of the unfinished story selected by the user, a data acquisition means for acquiring story and character information from existing data, a generative model means including a generative AI model for predicting the ending of the unfinished story based on the acquired information, a formatting means for formatting the generated ending into a text format or a visual format, and a data transmission means for transmitting the formatted ending data to the user's terminal. This makes it possible to quickly generate the ending of the unfinished story and provide it in the text format or visual format desired by the user.
[0528] A "user interface means" is a device or software that provides an interface for a user to interact with the system.
[0529] "Data acquisition means" refers to a device or software for acquiring story and character information from existing data.
[0530] A "generative AI model" is a model that uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story.
[0531] A "generative model means" is a device or software that includes a generative AI model for predicting the outcome of an unfinished story based on acquired information.
[0532] A "formatter" is a device or software for formatting the generated conclusion into textual or visual form.
[0533] The "data transmission means" is a device or software for transmitting formatted conclusion data to the user's terminal.
[0534] The "database acquisition means" is a device or software that allows the server to acquire story and character information from the database.
[0535] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface.
[0536] Hardware and Software Configuration
[0537] Terminal: A device that provides a user interface and receives input from a user. This can be a personal computer, smartphone, tablet, etc. The terminal has UI display software installed, which displays a list of open stories and accepts user selections.
[0538] Server: Acts as the central processing unit, acquiring data, running the generative AI model, formatting and transmitting the data. The server has database connection software and Python scripts installed to run the generative AI model (e.g., GPT-3).
[0539] Database: A data store for story and character information. This is where existing story data and character details are stored.
[0540] Generative AI models: Machine learning models designed to predict the ending of an unfinished story, such as OpenAI's GPT-3, that can analyze existing story data and generate new endings.
[0541] System Operation
[0542] The system operates as follows.
[0543] 1. Providing a user interface
[0544] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0545] 2. Data transmission
[0546] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[0547] 3. Acquiring story data
[0548] The server retrieves related story data and character information from the database based on the received story title information. The server issues a query to the database to retrieve the required data.
[0549] 4. Running the AI model
[0550] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. For example, a prompt sentence such as "The title of the story is 'Adventure Journey'. Please complete the unfinished part of the story" can be input into the generative model.
[0551] 5. Ending tweaks
[0552] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0553] 6. Data transmission and display
[0554] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed in a text viewer, and if it is in manga format, it is displayed in a page viewer.
[0555] Specific examples
[0556] As a concrete example, the following scenario can be considered.
[0557] Example 1: Textual ending generation
[0558] 1. The user selects the unfinished story "Adventure Journey" from the device's UI.
[0559] 2. The terminal sends the selected title "Adventure Journey" to the server.
[0560] 3. The server retrieves existing story data for "Adventure Journey" from the database.
[0561] 4. The server inputs the acquired data into the generative model and generates text as the result.
[0562] 5. Format the generated text, "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions.", and send it to the device.
[0563] 6. The terminal displays the generated text to the user.
[0564] Example 2: Manga-style ending generation
[0565] 1. The user selects the unfinished story "Magic Forest" from the device's UI.
[0566] 2. The device sends the selected title "Magical Forest" to the server.
[0567] 3. The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0568] 4. The server inputs the acquired data into a generative model and generates scenes and dialogues as predicted outcomes.
[0569] 5. Format the generated scenes and dialogues into a comic book format and create page layouts.
[0570] 6. Send the formatted manga data to the device.
[0571] 7. The terminal displays the generated comic page to the user.
[0572] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0573] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0574] Step 1: Displaying the User Interface
[0575] The terminal displays an interface for the user to select an incomplete story, specifically, a list of available incomplete stories is displayed on the screen.
[0576] Input: List of unfinished stories in the system
[0577] Output: A list of stories displayed on the device screen
[0578] Specific operation: When the device is initialized, it retrieves the list of unfinished stories from the server and passes that data to the UI component to display the list.
[0579] Step 2: User selects story and submits request
[0580] The user selects an unfinished story of interest from the list and clicks a button to request the creation of an ending for that story.
[0581] The terminal transmits the title information of the selected story to the server.
[0582] Input: User selection and title of selected story
[0583] Output: Sends a request to the server containing the title of the selected story.
[0584] Specific operation: The device catches the user's click event and sends a POST request to the server with the title information of the selected story in JSON format.
[0585] Step 3: Get Story Data
[0586] The server retrieves related story data and character information from the database based on the received story title information.
[0587] Input: Story title information received from the device
[0588] Output: Story data and character information retrieved from the database
[0589] Specific operation: The server executes an SQL query using the story title to retrieve the corresponding story data from the database. For example, it executes the query "SELECT FROM stories WHERE title="Adventure Journey"".
[0590] Step 4: Running the generative AI model
[0591] The server inputs the acquired story data into a generative AI model to predict the ending of the unfinished story.
[0592] Input: Story data and character information retrieved from the database
[0593] Output: Outcome data output from the generative AI model
[0594] Specific operation: The server runs a Python script and inputs story data and a prompt to a generative AI model (e.g., GPT-3). An example of the prompt is "The title of the story is 'Adventure Journey'. Please complete the unfinished parts of the story."
[0595] Step 5: Formatting the outcome data
[0596] The server formats the generated outcome data into a textual or visual format.
[0597] Input: Outcome data output from the generative AI model
[0598] Output: Formatted outcome data (text or visual)
[0599] What it does: The server formats the generated text into HTML or Markdown, edits the scenes and dialogue in the case of manga, and generates the visual data using page layout software.
[0600] Step 6: Send and display the outcome data
[0601] The server sends the formatted outcome data to the user's terminal, which displays the received data to the user.
[0602] Input: Formatted ending data sent from the server
[0603] Output: The outcome data displayed on the user's terminal
[0604] Specific operation: The server sends the formatted ending data in JSON format to the device. The device receives it and displays it to the user in a text viewer or manga viewer.
[0605] (Application example 1)
[0606] 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."
[0607] In recent years, there has been an increasing demand for the ending of unfinished stories, but there are currently no appropriate means to meet this demand. Users cannot obtain automatically generated endings based on existing story data, and must wait a long time for the ending. This makes it difficult to sustain users' interest, and there is a growing demand for early conclusions to stories.
[0608] 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.
[0609] In this invention, the server includes data acquisition means for acquiring story and actor data from existing information, generative model means for predicting the ending of an unfinished story based on the acquired data, formatting means for formatting the generated ending in a text format or a visual format, data transmission means for providing the ending to the user's information terminal, interface means for displaying a list of unfinished stories that the user can select, and request transmission means for transmitting an ending generation request based on the story title selected by the user, thereby enabling the user to quickly obtain the predicted ending of the unfinished story.
[0610] "Data acquisition tools" are functions for collecting story and actor data from existing sources.
[0611] The "generative model means" is a function that automatically predicts the ending of an unfinished story based on acquired story and actor data.
[0612] The "formatting means" is a function for formatting the generated conclusion in a character string format or a visual format so that it can be displayed to the user in an easy-to-understand manner.
[0613] "Data transmission means" is a function for transmitting the generated ending to the user's information terminal.
[0614] The "interface means" is a function that displays a list of incomplete stories that the user can select from and provides an interface for the user to select a story.
[0615] The "request sending means" is a function for sending the title information of the story selected by the user to the server and executing the ending generation request.
[0616] "Database acquisition means" is a function for acquiring story and actor data from a database.
[0617] 1. System Overview
[0618] The system of this invention is designed to allow users to predict the ending of an incomplete story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an incomplete story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, formats it, and delivers it to the terminal.
[0619] 2. Providing a user interface
[0620] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0621] 3. Data transmission
[0622] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[0623] 4. Acquiring story data
[0624] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[0625] 5. Running the AI model
[0626] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. OpenAI's GPT-3 is used as the generative AI model used for prediction. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[0627] 6. Ending tweaks
[0628] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of visual format, the server creates a page layout based on the generated scenes and dialogue, and combines character images.
[0629] 7. Data Transmission and Display
[0630] The server sends the formatted conclusion data to the user's terminal, which displays the received data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[0631] Specific examples
[0632] Example 1: Textual ending generation
[0633] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0634] The terminal transmits the selected title "Adventure Journey" to the server.
[0635] The server retrieves existing story data for "Adventure Journey" from the database.
[0636] The server inputs the acquired data into a generative model and generates text as the result.
[0637] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[0638] The terminal displays the generated text to the user.
[0639] Example 2: Visual Outcome Generation
[0640] The user selects the unfinished story "Magic Forest" from the device's UI.
[0641] The terminal transmits the selected title "Magical Forest" to the server.
[0642] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0643] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[0644] Format the generated scenes and dialogues into a visual format and create a page layout.
[0645] Sends formatted, visually formatted data to the terminal.
[0646] The terminal displays the generated page to the user.
[0647] Prompt Sentence Examples
[0648] Story Data: "The protagonist goes on an adventure to find treasure."
[0649] Prompt: "The protagonist goes on an adventure to find treasure. What is the outcome of this story?"
[0650] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0651] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0652] Step 1:
[0653] The user selects an unfinished story.
[0654] The user selects a story of interest from the displayed list of unfinished stories through the user interface of the terminal. The input is the title of the story based on the user's selection. The output is the title information of the selected story.
[0655] Step 2:
[0656] The terminal transmits the story title information to the server.
[0657] The terminal collects the story title information selected by the user and sends it to the server as a POST request. The input is the story title information selected by the user. The output is the title information received by the server.
[0658] Step 3:
[0659] The server retrieves the story data from the database.
[0660] The server issues a query to the database based on the received story title to retrieve related story data and character information. The input is story title information, and the output is story data and character information.
[0661] Step 4:
[0662] The server inputs story data into a generative model to predict the ending.
[0663] The server inputs the acquired story data and character information into a generative AI model. The generative model (e.g., GPT-3) analyzes the input data, creates a generative prompt to predict the optimal ending, and generates the ending. The input is story data and character information, and the output is the predicted ending data.
[0664] Step 5:
[0665] The server formats the resulting result.
[0666] The server takes the outcome output by the generative model and formats it into a user-readable format (text or visual format). The input is the generated outcome data, and the output is the formatted outcome data.
[0667] Step 6:
[0668] The server transmits the formatted conclusion data to the terminal.
[0669] The server sends the formatted outcome data to the user's terminal. The input is the formatted outcome data, and the output is the outcome data received by the terminal.
[0670] Step 7:
[0671] The terminal displays the received conclusion data to the user.
[0672] The terminal displays the outcome data received from the server to the user through a user interface. The input is the outcome data received from the server, and the output is the outcome information displayed to the user.
[0673] This allows the user to quickly find out the ending of an unfinished story.
[0674] 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.
[0675] 1. System Overview
[0676] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, a user interface, and an emotion engine. For an unfinished story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, and adjusts the ending based on the user's emotions using the emotion engine before delivering it to the terminal.
[0677] 2. Providing a user interface
[0678] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0679] 3. Data transmission
[0680] When a user selects an unfinished story in which they are interested, allows acquisition of emotional data, and clicks a request button for generating an ending, the terminal sends the title information and emotional state information of the selected story to the server.
[0681] 4. Acquiring story data
[0682] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0683] 5. Use of Emotion Engine
[0684] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[0685] 6. Running the AI model
[0686] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[0687] 7. Ending tweaks
[0688] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0689] 8. Data Transmission and Display
[0690] The server sends the formatted conclusion data to the terminal, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[0691] Specific examples
[0692] 1. Example 1: Textual Conclusion and Emotional Adaptation
[0693] The user selects the unfinished story "Adventure Journey" from the device's UI and grants camera permission.
[0694] The terminal transmits the selected title "Adventure Journey" and the emotion data to the server.
[0695] The server retrieves existing story data for "Adventure Journey" from the database.
[0696] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[0697] The server inputs the acquired data into a generative model to generate an outcome based on the emotional state.
[0698] The generated text "The end of the adventure: The protagonist finally finds the treasure and rejoices with his companions." is formatted and sent to the device.
[0699] The terminal displays the generated text to the user.
[0700] 2. Example 2: Manga-style ending and emotional adaptation
[0701] The user selects the unfinished story "Magical Forest" from the device's UI and grants camera permission.
[0702] The terminal transmits the selected title "Magical Forest" and the emotion data to the server.
[0703] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0704] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[0705] The server uses a generative model based on the acquired data to generate scenes and dialogues based on the emotional state.
[0706] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[0707] The formatted manga format data is sent to the device.
[0708] The terminal displays the generated comic page to the user.
[0709] In this way, the system of the present invention generates and provides the user with an ending to an unfinished story while taking into account the user's emotions, providing a more personalized experience.
[0710] The processing flow will be explained below.
[0711] Step 1:
[0712] The terminal provides the user with an interface for selecting an incomplete story title, and the interface displays a list of available incomplete stories.
[0713] Step 2:
[0714] The user selects an unfinished story of interest from a list on the interface, allows emotional data acquisition, and then requests the creation of an ending. By clicking the request button, the title information and emotional state information of the selected story are sent.
[0715] Step 3:
[0716] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[0717] Step 4:
[0718] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0719] Step 5:
[0720] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[0721] Step 6:
[0722] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[0723] Step 7:
[0724] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0725] Step 8:
[0726] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[0727] Step 9:
[0728] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[0729] Example 2
[0730] 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."
[0731] Existing story generation systems often provide a uniform ending without considering the user's emotional state, resulting in low user satisfaction. Furthermore, there is a lack of technology that provides individually tailored endings based on the user's choices and emotions. To address this issue, it is necessary to provide a system that recognizes the user's emotional state in real time and generates and adjusts endings based on that information.
[0732] 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.
[0733] In this invention, the server includes data acquisition means for acquiring information from existing data, generative model means for predicting an ending of an unfinished story based on the acquired information, and emotion adaptation means for adjusting the generated ending based on the user's emotional state, thereby enabling the provision of a personalized ending according to the user's selection and emotional state.
[0734] "Data acquisition means" refers to means for extracting story data and character information from an existing database.
[0735] "Generative model means" refers to a machine learning model for predicting the ending of an unfinished story based on acquired story data and character information.
[0736] A "formatting tool" is a tool for formatting the generated story's ending in text or visual form.
[0737] The "data transmission means" is a communication means for providing the generated ending to the user's terminal after formatting.
[0738] "Emotion engine means" refers to software or hardware for analyzing a user's facial expressions and recognizing the user's emotional state.
[0739] "Emotional adaptation means" are means for adjusting the outcome predicted by the generative model based on the perceived emotional state of the user.
[0740] "User interface means" refers to an operation screen that allows the user to select the title of an unfinished story and transmits that information to the server.
[0741] The "database acquisition means" is a query issuing means for the server to acquire the necessary story data and character information from the database.
[0742] The present invention is a system designed to meet the needs of users who want to know the ending of an unfinished story. The system mainly includes a terminal, a server, a database, a generative AI model, a user interface, and an emotion engine. Below, we will explain in detail how to implement the invention, while specifically showing the hardware and software used.
[0743] 1. Providing a user interface
[0744] The terminal provides the user with an interface for selecting unfinished stories. Specifically, there is an application that runs on a web browser, and the user can select a story of interest from a list of unfinished stories displayed.
[0745] Software used:
[0746] Browser-based UI frameworks (e.g., React, Vue.js)
[0747] Examples:
[0748] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0749] 2. Data transmission
[0750] When the user selects a story, allows acquisition of emotional data, and then clicks the request button, the terminal transmits the selected title and emotional state information to the server.
[0751] Software and hardware used:
[0752] Network communication protocols (e.g. HTTP / HTTPS), camera on user device
[0753] Examples:
[0754] The user selects "Adventure Journey," allows emotion data acquisition, and clicks the request button.
[0755] 3. Acquiring story data
[0756] The server retrieves the relevant story data and character information from the database based on the received story title information, specifically by issuing an SQL query to extract the relevant data.
[0757] Software used:
[0758] Database management systems (e.g., MySQL, PostgreSQL)
[0759] Examples:
[0760] The server issues the query "SELECT FROM stories WHERE title = 'Adventure Journey'" to retrieve story data from the database.
[0761] 4. Use of Emotion Engine
[0762] The device uses a camera to analyze the user's facial expressions and recognizes their emotional state using an emotion engine, and transmits the recognized emotional state information to a server in real time.
[0763] Software used:
[0764] Emotion analysis API (e.g. Emotion API)
[0765] Examples:
[0766] The device uses the Emotion API to analyze the user's facial expression and transmits to the server that the user is "sad."
[0767] 5. Running the generative AI model
[0768] The server inputs the acquired story data, character information, and emotional state information into a generative AI model, which uses machine learning techniques to predict the ending of the unfinished story and adjust it based on the emotional state.
[0769] Software used:
[0770] Generative AI models (e.g., OpenAI GPT-4)
[0771] Examples:
[0772] The server inputs the following prompt into the generative AI model: "The user feels sad about the ending of the story 'Adventure Journey'. Please generate an ending based on this emotion."
[0773] 6. Ending tweaks
[0774] The server formats the generated ending data. In the case of text format, it formats the sentences, and in the case of visual (manga) format, it creates a page layout based on the scenes and dialogues.
[0775] Software used:
[0776] Text processing libraries (e.g., Python's NLTK), visual editing software (e.g., Adobe Photoshop)
[0777] Examples:
[0778] Format the generated text "The end of the adventure: The protagonist ends his journey in sadness." and, in the case of a manga format, create a page layout with scenes and dialogues.
[0779] 7. Data Transmission and Display
[0780] The server sends the formatted outcome data to the terminal, which displays the data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[0781] Software and hardware used:
[0782] Network communication protocol (e.g. HTTP / HTTPS), HTML viewer or dedicated app
[0783] Examples:
[0784] The server sends formatted text data and visual data to the terminal, which displays it to the user.
[0785] The above is a concrete embodiment of the present invention. The system provides a personalized story ending based on the user's choices and emotional state, increasing user satisfaction.
[0786] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0787] Step 1: Display and select the user interface
[0788] Description: The device provides the user with an interface for selecting an incomplete story. The interface displays a list of existing incomplete stories. The user can select a story from the list that interests them.
[0789] Input: A list of unfinished stories on the device
[0790] Output: The specific story title selected by the user
[0791] Specific behavior:
[0792] The device displays a list of unfinished stories as HTML on the browser.
[0793] The user clicks to select "Magic Forest" from the list.
[0794] Step 2: Sending data
[0795] Description: When the user selects a story and clicks the request button after allowing emotional data acquisition, the device sends the selected title and emotional state information to the server.
[0796] Input: User-selected story title, permission to create emotion data
[0797] Output: Story title and emotional state information sent to the server
[0798] Specific behavior:
[0799] The user selects "Magical Forest," allows acquisition of emotion data, and clicks the request button.
[0800] The terminal sends the selected title "Magical Forest" and the user's emotional state information to the server as an HTTP request.
[0801] Step 3: Get Story Data
[0802] Description: The server retrieves related story data and character information from the database based on the received story title information.
[0803] Input: Story title information received by the server
[0804] Output: Story data and character information retrieved from the database
[0805] Specific behavior:
[0806] The server issues the following SQL query to the database: SELECT FROM stories WHERE title = 'Magic Forest'.
[0807] The database returns relevant story data and character information based on the query.
[0808] Step 4: Use the Emotion Engine
[0809] Description: The device uses a camera to analyze the user's facial expressions and utilizes an emotion engine to recognize the user's emotional state. The device transmits the recognized emotional state information to the server in real time.
[0810] Input: A user's face image captured by a camera
[0811] Output: Emotional state information sent to the server
[0812] Specific behavior:
[0813] The device sends the user's facial image to the Emotion API.
[0814] The Emotion API analyzes images and recognizes the user's emotional state as "sad."
[0815] The terminal transmits the recognized emotional state to the server.
[0816] Step 5: Running the generative AI model
[0817] Description: The server inputs the acquired story data, character information, and emotional state information into a generative model. Based on this data, the generative model predicts the ending of the unfinished story and adjusts it based on the user's emotional state.
[0818] Input: Story data, character information, emotional state information
[0819] Output: The generated story ending
[0820] Specific behavior:
[0821] The server inputs this data into a generative AI model.
[0822] A generative AI model (e.g., GPT-4) uses this data to generate a story ending, adjusting it depending on the emotional state.
[0823] The server receives the generated outcome.
[0824] Step 6: Shaping the ending
[0825] Description: The server formats the generated outcome data, either by formatting the sentences in the text format or by creating a page layout based on the scenes and dialogue in the visual format.
[0826] Input: Generated story ending
[0827] Output: Formatted text or visual data
[0828] Specific behavior:
[0829] The server formats the generated text, "The End of the Enchanted Forest: The Protagonist Ends His Journey in Sadness.", to make it easier to read.
[0830] In the manga format, the page layout is created based on the generated scenes and dialogue.
[0831] Step 7: Send and display data
[0832] Description: The server sends the formatted outcome data to the terminal, which displays this data to the user.
[0833] Input: Formatted outcome data
[0834] Output: The outcome displayed on the user's terminal
[0835] Specific behavior:
[0836] The server sends formatted text data and visual data to the terminal.
[0837] The device receives it and displays it to the user, either as text if it is in text format or in a page viewer if it is in visual format.
[0838] (Application example 2)
[0839] 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."
[0840] In recent years, users have increasingly expressed a desire to know the ending of a story in a way that reflects their own emotional state. However, existing systems have difficulty generating endings that reflect the user's emotional state. Furthermore, the generated story endings do not necessarily match the user's emotions, resulting in a uniform user experience.
[0841] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data acquisition means for acquiring story and character information from existing data, generative model means for predicting the ending of an unfinished story based on the acquired information, formatting means for formatting the generated ending into a text format or a visual format, emotion analysis means for analyzing the user's facial expression to acquire emotion data, emotion adjustment means for adjusting the ending using the acquired emotion data, and data transmission means for providing the adjusted ending to the user's terminal. This makes it possible to provide a personalized story ending that corresponds to the user's emotional state.
[0842] "Data acquisition means" refers to a method for acquiring story and character information from existing data.
[0843] A "generative modeling method" is a method for predicting the outcome of an unfinished story based on acquired information.
[0844] A "formatter" is a method for formatting the generated conclusion into textual or visual form.
[0845] The "emotion analysis means" is a method for analyzing the user's facial expression to obtain emotion data.
[0846] "Emotion adjustment means" is a method for adjusting the ending using the acquired emotion data.
[0847] A "data transmission means" is a method for providing a tailored outcome to a user's terminal.
[0848] The "user interface means" is a method for transmitting title information of an unfinished story selected by the user to the server.
[0849] The "database acquisition means" is a method for acquiring acquired story and character information from the database.
[0850] The present invention is a system that uses emotional data to provide a personalized ending to an unfinished story in response to a user's desire to know the ending of the story. This system implements the invention through the following steps.
[0851] 1. System Overview
[0852] The system includes a terminal, a server, a data acquisition means, a generative model means, an emotion analysis means, an emotion adjustment means, a formatting means, a data transmission means, a user interface means, and a database acquisition means. A user uses the terminal to select an unfinished story title and make a request to know the subsequent ending.
[0853] 2. Data Acquisition
[0854] The server uses a database acquisition means to acquire related story data and character information based on the story title information sent by the user. The database stores existing story data and character information, and generates an ending based on this information.
[0855] 3.Emotion analysis
[0856] The device uses a camera to analyze the user's facial expressions and uses an emotion analysis means to recognize the user's emotional state. This emotion analysis means uses facial recognition technology to analyze the user's facial expressions and obtain emotional data such as joy, sadness, and excitement. Libraries such as OpenCV and TensorFlow / Keras are used for this analysis.
[0857] 4. Generative Model
[0858] The server inputs the acquired story data, character information, and emotional state information into a generative modeling means. The generative modeling means uses machine learning technology to analyze existing data and predict the ending of the unfinished story. Furthermore, an emotional adjustment means adjusts the ending according to the user's emotional state.
[0859] 5. Ending tweaks
[0860] The generated ending data is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated content is formatted into easy-to-read sentences, and in the case of the manga format, a page layout is created based on the generated scenes and dialogues, and character drawings are combined to form a manga page.
[0861] 6. Providing an ending
[0862] The formatted conclusion data is sent to the terminal using the data transmission means, and the terminal displays it to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[0863] Specific examples
[0864] 1. Example 1: Textual Conclusion and Emotional Adaptation
[0865] The user selects the unfinished story from the device UI and grants camera permission.
[0866] The terminal transmits the selected title and emotion data to the server.
[0867] The server retrieves existing story data from a database.
[0868] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[0869] The server generates an outcome based on the emotional state, formats it, and sends it to the terminal.
[0870] The terminal displays the generated text to the user.
[0871] 2. Example 2: Manga-style ending and emotional adaptation
[0872] The user selects the unfinished story from the device UI and grants camera permission.
[0873] The terminal transmits the selected title and emotion data to the server.
[0874] The server retrieves existing story data and character information from a database.
[0875] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[0876] The server generates scenes and dialogues based on the emotional state, formats them, and sends them to the device.
[0877] The terminal displays the generated comic page to the user.
[0878] Example prompts for generative AI models
[0879] "The story is set in a fantasy genre. The hero is a hero who is forced to make an important decision during his adventure. An emotion of excitement was detected from the user's facial expression. Please generate the ending of the story."
[0880] As described above, the present invention generates an ending to an unfinished story in a manner that takes into account the user's emotions, thereby providing a personalized content experience.
[0881] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0882] Step 1:
[0883] The user selects the title of an unfinished story using the user interface of the terminal and grants permission to use the camera. The terminal receives input from the user and obtains title information of the selected story.
[0884] Step 2:
[0885] The device captures the user's facial expression along with the acquired story title information with a camera and analyzes the facial expression using an emotion analysis means. The emotion analysis means uses the OpenCV library and TensorFlow / Keras model to identify the user's emotional state (e.g., joy, sadness, excitement) from the facial expression data. The analysis results are output as emotion data.
[0886] Step 3:
[0887] The terminal transmits the title information and emotion data of the selected story to the server. Based on the story title information received from the terminal, the server uses a database acquisition means to acquire related story data and character information. The database stores existing story data and character information.
[0888] Step 4:
[0889] The server inputs the story data, character information, and emotion data acquired by the database acquisition means into the generative model means. The generative model means uses machine learning techniques (TensorFlow / Keras) to predict the ending of the unfinished story. Based on the emotion data, the ending is adjusted to adapt to the user's emotional state.
[0890] Step 5:
[0891] The ending data generated by the generative model means is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated ending is formatted into easy-to-read sentences. In the case of the visual format (manga format), a page layout is created based on the generated scenes and dialogue, and character drawings are combined to format the ending.
[0892] Step 6:
[0893] The server transmits the formatted ending data to the terminal using a data transmission means. The terminal displays the received ending data to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[0894] In this way, a personalized story ending is provided that responds to the user's emotional state.
[0895] 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.
[0896] 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.
[0897] 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.
[0898] [Third embodiment]
[0899] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0900] 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.
[0901] 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).
[0902] 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.
[0903] 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.
[0904] 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).
[0905] 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.
[0906] 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.
[0907] 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.
[0908] 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.
[0909] 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.
[0910] 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."
[0911] 1. System Overview
[0912] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an unfinished story selected by the user, the server retrieves information from the database, uses the generative model to predict the ending, formats it, and delivers it to the terminal.
[0913] 2. Providing a user interface
[0914] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0915] 3. Data transmission
[0916] When the user selects an unfinished story that interests them and clicks the request button for generating an ending, the terminal sends the title information of the selected manga to the server.
[0917] 4. Acquiring story data
[0918] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[0919] 5. Running the AI model
[0920] The server inputs the acquired story data into a generative model. The generative model uses machine learning techniques to analyze existing story data and character information to predict the ending of an unfinished story. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[0921] 6. Ending tweaks
[0922] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0923] 7. Data Transmission and Display
[0924] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[0925] Specific examples
[0926] 1. Example 1: Textual ending generation
[0927] The user selects the unfinished story "Adventure Journey" from the device's UI.
[0928] The terminal transmits the selected title "Adventure Journey" to the server.
[0929] The server retrieves existing story data for "Adventure Journey" from the database.
[0930] The server inputs the acquired data into a generative model and generates text as the result.
[0931] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[0932] The terminal displays the generated text to the user.
[0933] 2. Example 2: Manga-style ending generation
[0934] The user selects the unfinished story "Magic Forest" from the device's UI.
[0935] The terminal transmits the selected title "Magical Forest" to the server.
[0936] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[0937] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[0938] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[0939] The formatted manga format data is sent to the device.
[0940] The terminal displays the generated comic page to the user.
[0941] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[0942] The processing flow will be explained below.
[0943] Step 1:
[0944] The terminal provides the user with an interface for selecting an incomplete story title, specifically, a list of available incomplete stories is displayed on the screen.
[0945] Step 2:
[0946] The user selects an unfinished story that they are interested in from the list on the interface and requests the creation of an ending. By clicking the request button, the title information of the selected story is sent.
[0947] Step 3:
[0948] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[0949] Step 4:
[0950] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[0951] Step 5:
[0952] The server inputs the acquired story data and character information into a generative model, which uses this data to predict and generate the ending of the unfinished story. AI models and machine learning algorithms are used.
[0953] Step 6:
[0954] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0955] Step 7:
[0956] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[0957] Step 8:
[0958] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[0959] In this way, the system allows the user to find out the ending of an unfinished story.
[0960] Example 1
[0961] 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."
[0962] Conventional technologies have limited means for predicting the ending of an unfinished story and providing it to users. As a result, it has been difficult to quickly and appropriately respond to users' needs to know the ending of the story. In addition, some systems only support either text or visual formats, which means they cannot meet the needs of a wide range of users.
[0963] 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.
[0964] In this invention, the server includes a user interface means for receiving the title of the unfinished story selected by the user, a data acquisition means for acquiring story and character information from existing data, a generative model means including a generative AI model for predicting the ending of the unfinished story based on the acquired information, a formatting means for formatting the generated ending into a text format or a visual format, and a data transmission means for transmitting the formatted ending data to the user's terminal. This makes it possible to quickly generate the ending of the unfinished story and provide it in the text format or visual format desired by the user.
[0965] A "user interface means" is a device or software that provides an interface for a user to interact with the system.
[0966] "Data acquisition means" refers to a device or software for acquiring story and character information from existing data.
[0967] A "generative AI model" is a model that uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story.
[0968] A "generative model means" is a device or software that includes a generative AI model for predicting the outcome of an unfinished story based on acquired information.
[0969] A "formatter" is a device or software for formatting the generated conclusion into textual or visual form.
[0970] The "data transmission means" is a device or software for transmitting formatted conclusion data to the user's terminal.
[0971] The "database acquisition means" is a device or software that allows the server to acquire story and character information from the database.
[0972] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface.
[0973] Hardware and Software Configuration
[0974] Terminal: A device that provides a user interface and receives input from a user. This can be a personal computer, smartphone, tablet, etc. The terminal has UI display software installed, which displays a list of open stories and accepts user selections.
[0975] Server: Acts as the central processing unit, acquiring data, running the generative AI model, formatting and transmitting the data. The server has database connection software and Python scripts installed to run the generative AI model (e.g., GPT-3).
[0976] Database: A data store for story and character information. This is where existing story data and character details are stored.
[0977] Generative AI models: Machine learning models designed to predict the ending of an unfinished story, such as OpenAI's GPT-3, that can analyze existing story data and generate new endings.
[0978] System Operation
[0979] The system operates as follows.
[0980] 1. Providing a user interface
[0981] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[0982] 2. Data transmission
[0983] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[0984] 3. Acquiring story data
[0985] The server retrieves related story data and character information from the database based on the received story title information. The server issues a query to the database to retrieve the required data.
[0986] 4. Running the AI model
[0987] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. For example, a prompt sentence such as "The title of the story is 'Adventure Journey'. Please complete the unfinished part of the story" can be input into the generative model.
[0988] 5. Ending tweaks
[0989] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[0990] 6. Data transmission and display
[0991] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed in a text viewer, and if it is in manga format, it is displayed in a page viewer.
[0992] Specific examples
[0993] As a concrete example, the following scenario can be considered.
[0994] Example 1: Textual ending generation
[0995] 1. The user selects the unfinished story "Adventure Journey" from the device's UI.
[0996] 2. The terminal sends the selected title "Adventure Journey" to the server.
[0997] 3. The server retrieves existing story data for "Adventure Journey" from the database.
[0998] 4. The server inputs the acquired data into the generative model and generates text as the result.
[0999] 5. Format the generated text, "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions.", and send it to the device.
[1000] 6. The terminal displays the generated text to the user.
[1001] Example 2: Manga-style ending generation
[1002] 1. The user selects the unfinished story "Magic Forest" from the device's UI.
[1003] 2. The device sends the selected title "Magical Forest" to the server.
[1004] 3. The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1005] 4. The server inputs the acquired data into a generative model and generates scenes and dialogues as predicted outcomes.
[1006] 5. Format the generated scenes and dialogues into a comic book format and create page layouts.
[1007] 6. Send the formatted manga data to the device.
[1008] 7. The terminal displays the generated comic page to the user.
[1009] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[1010] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1011] Step 1: Displaying the User Interface
[1012] The terminal displays an interface for the user to select an incomplete story, specifically, a list of available incomplete stories is displayed on the screen.
[1013] Input: List of unfinished stories in the system
[1014] Output: A list of stories displayed on the device screen
[1015] Specific operation: When the device is initialized, it retrieves the list of unfinished stories from the server and passes that data to the UI component to display the list.
[1016] Step 2: User selects story and submits request
[1017] The user selects an unfinished story of interest from the list and clicks a button to request the creation of an ending for that story.
[1018] The terminal transmits the title information of the selected story to the server.
[1019] Input: User selection and title of selected story
[1020] Output: Sends a request to the server containing the title of the selected story.
[1021] Specific operation: The device catches the user's click event and sends a POST request to the server with the title information of the selected story in JSON format.
[1022] Step 3: Get Story Data
[1023] The server retrieves related story data and character information from the database based on the received story title information.
[1024] Input: Story title information received from the device
[1025] Output: Story data and character information retrieved from the database
[1026] Specific operation: The server executes an SQL query using the story title to retrieve the corresponding story data from the database. For example, it executes the query "SELECT FROM stories WHERE title="Adventure Journey"".
[1027] Step 4: Running the generative AI model
[1028] The server inputs the acquired story data into a generative AI model to predict the ending of the unfinished story.
[1029] Input: Story data and character information retrieved from the database
[1030] Output: Outcome data output from the generative AI model
[1031] Specific operation: The server runs a Python script and inputs story data and a prompt to a generative AI model (e.g., GPT-3). An example of the prompt is "The title of the story is 'Adventure Journey'. Please complete the unfinished parts of the story."
[1032] Step 5: Formatting the outcome data
[1033] The server formats the generated outcome data into a textual or visual format.
[1034] Input: Outcome data output from the generative AI model
[1035] Output: Formatted outcome data (text or visual)
[1036] What it does: The server formats the generated text into HTML or Markdown, edits the scenes and dialogue in the case of manga, and generates the visual data using page layout software.
[1037] Step 6: Send and display the outcome data
[1038] The server sends the formatted outcome data to the user's terminal, which displays the received data to the user.
[1039] Input: Formatted ending data sent from the server
[1040] Output: The outcome data displayed on the user's terminal
[1041] Specific operation: The server sends the formatted ending data in JSON format to the device. The device receives it and displays it to the user in a text viewer or manga viewer.
[1042] (Application example 1)
[1043] 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."
[1044] In recent years, there has been an increasing demand for the ending of unfinished stories, but there are currently no appropriate means to meet this demand. Users cannot obtain automatically generated endings based on existing story data, and must wait a long time for the ending. This makes it difficult to sustain users' interest, and there is a growing demand for early conclusions to stories.
[1045] 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.
[1046] In this invention, the server includes data acquisition means for acquiring story and actor data from existing information, generative model means for predicting the ending of an unfinished story based on the acquired data, formatting means for formatting the generated ending in a text format or a visual format, data transmission means for providing the ending to the user's information terminal, interface means for displaying a list of unfinished stories that the user can select, and request transmission means for transmitting an ending generation request based on the story title selected by the user, thereby enabling the user to quickly obtain the predicted ending of the unfinished story.
[1047] "Data acquisition tools" are functions for collecting story and actor data from existing sources.
[1048] The "generative model means" is a function that automatically predicts the ending of an unfinished story based on acquired story and actor data.
[1049] The "formatting means" is a function for formatting the generated conclusion in a character string format or a visual format so that it can be displayed to the user in an easy-to-understand manner.
[1050] "Data transmission means" is a function for transmitting the generated ending to the user's information terminal.
[1051] The "interface means" is a function that displays a list of incomplete stories that the user can select from and provides an interface for the user to select a story.
[1052] The "request sending means" is a function for sending the title information of the story selected by the user to the server and executing the ending generation request.
[1053] "Database acquisition means" is a function for acquiring story and actor data from a database.
[1054] 1. System Overview
[1055] The system of this invention is designed to allow users to predict the ending of an incomplete story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an incomplete story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, formats it, and delivers it to the terminal.
[1056] 2. Providing a user interface
[1057] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[1058] 3. Data transmission
[1059] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[1060] 4. Acquiring story data
[1061] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[1062] 5. Running the AI model
[1063] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. OpenAI's GPT-3 is used as the generative AI model used for prediction. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[1064] 6. Ending tweaks
[1065] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of visual format, the server creates a page layout based on the generated scenes and dialogue, and combines character images.
[1066] 7. Data Transmission and Display
[1067] The server sends the formatted conclusion data to the user's terminal, which displays the received data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[1068] Specific examples
[1069] Example 1: Textual ending generation
[1070] The user selects the unfinished story "Adventure Journey" from the device's UI.
[1071] The terminal transmits the selected title "Adventure Journey" to the server.
[1072] The server retrieves existing story data for "Adventure Journey" from the database.
[1073] The server inputs the acquired data into a generative model and generates text as the result.
[1074] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[1075] The terminal displays the generated text to the user.
[1076] Example 2: Visual Outcome Generation
[1077] The user selects the unfinished story "Magic Forest" from the device's UI.
[1078] The terminal transmits the selected title "Magical Forest" to the server.
[1079] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1080] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[1081] Format the generated scenes and dialogues into a visual format and create a page layout.
[1082] Sends formatted, visually formatted data to the terminal.
[1083] The terminal displays the generated page to the user.
[1084] Prompt Sentence Examples
[1085] Story Data: "The protagonist goes on an adventure to find treasure."
[1086] Prompt: "The protagonist goes on an adventure to find treasure. What is the outcome of this story?"
[1087] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[1088] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1089] Step 1:
[1090] The user selects an unfinished story.
[1091] The user selects a story of interest from the displayed list of unfinished stories through the user interface of the terminal. The input is the title of the story based on the user's selection. The output is the title information of the selected story.
[1092] Step 2:
[1093] The terminal transmits the story title information to the server.
[1094] The terminal collects the story title information selected by the user and sends it to the server as a POST request. The input is the story title information selected by the user. The output is the title information received by the server.
[1095] Step 3:
[1096] The server retrieves the story data from the database.
[1097] The server issues a query to the database based on the received story title to retrieve related story data and character information. The input is story title information, and the output is story data and character information.
[1098] Step 4:
[1099] The server inputs story data into a generative model to predict the ending.
[1100] The server inputs the acquired story data and character information into a generative AI model. The generative model (e.g., GPT-3) analyzes the input data, creates a generative prompt to predict the optimal ending, and generates the ending. The input is story data and character information, and the output is the predicted ending data.
[1101] Step 5:
[1102] The server formats the resulting result.
[1103] The server takes the outcome output by the generative model and formats it into a user-readable format (text or visual format). The input is the generated outcome data, and the output is the formatted outcome data.
[1104] Step 6:
[1105] The server transmits the formatted conclusion data to the terminal.
[1106] The server sends the formatted outcome data to the user's terminal. The input is the formatted outcome data, and the output is the outcome data received by the terminal.
[1107] Step 7:
[1108] The terminal displays the received conclusion data to the user.
[1109] The terminal displays the outcome data received from the server to the user through a user interface. The input is the outcome data received from the server, and the output is the outcome information displayed to the user.
[1110] This allows the user to quickly find out the ending of an unfinished story.
[1111] 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.
[1112] 1. System Overview
[1113] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, a user interface, and an emotion engine. For an unfinished story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, and adjusts the ending based on the user's emotions using the emotion engine before delivering it to the terminal.
[1114] 2. Providing a user interface
[1115] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[1116] 3. Data transmission
[1117] When a user selects an unfinished story in which they are interested, allows acquisition of emotional data, and clicks a request button for generating an ending, the terminal sends the title information and emotional state information of the selected story to the server.
[1118] 4. Acquiring story data
[1119] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[1120] 5. Use of Emotion Engine
[1121] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[1122] 6. Running the AI model
[1123] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[1124] 7. Ending tweaks
[1125] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1126] 8. Data Transmission and Display
[1127] The server sends the formatted conclusion data to the terminal, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[1128] Specific examples
[1129] 1. Example 1: Textual Conclusion and Emotional Adaptation
[1130] The user selects the unfinished story "Adventure Journey" from the device's UI and grants camera permission.
[1131] The terminal transmits the selected title "Adventure Journey" and the emotion data to the server.
[1132] The server retrieves existing story data for "Adventure Journey" from the database.
[1133] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[1134] The server inputs the acquired data into a generative model to generate an outcome based on the emotional state.
[1135] The generated text "The end of the adventure: The protagonist finally finds the treasure and rejoices with his companions." is formatted and sent to the device.
[1136] The terminal displays the generated text to the user.
[1137] 2. Example 2: Manga-style ending and emotional adaptation
[1138] The user selects the unfinished story "Magical Forest" from the device's UI and grants camera permission.
[1139] The terminal transmits the selected title "Magical Forest" and the emotion data to the server.
[1140] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1141] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[1142] The server uses a generative model based on the acquired data to generate scenes and dialogues based on the emotional state.
[1143] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[1144] The formatted manga format data is sent to the device.
[1145] The terminal displays the generated comic page to the user.
[1146] In this way, the system of the present invention generates and provides the user with an ending to an unfinished story while taking into account the user's emotions, providing a more personalized experience.
[1147] The processing flow will be explained below.
[1148] Step 1:
[1149] The terminal provides the user with an interface for selecting an incomplete story title, and the interface displays a list of available incomplete stories.
[1150] Step 2:
[1151] The user selects an unfinished story of interest from a list on the interface, allows emotional data acquisition, and then requests the creation of an ending. By clicking the request button, the title information and emotional state information of the selected story are sent.
[1152] Step 3:
[1153] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[1154] Step 4:
[1155] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[1156] Step 5:
[1157] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[1158] Step 6:
[1159] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[1160] Step 7:
[1161] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1162] Step 8:
[1163] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[1164] Step 9:
[1165] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[1166] Example 2
[1167] 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."
[1168] Existing story generation systems often provide a uniform ending without considering the user's emotional state, resulting in low user satisfaction. Furthermore, there is a lack of technology that provides individually tailored endings based on the user's choices and emotions. To address this issue, it is necessary to provide a system that recognizes the user's emotional state in real time and generates and adjusts endings based on that information.
[1169] 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.
[1170] In this invention, the server includes data acquisition means for acquiring information from existing data, generative model means for predicting an ending of an unfinished story based on the acquired information, and emotion adaptation means for adjusting the generated ending based on the user's emotional state, thereby enabling the provision of a personalized ending according to the user's selection and emotional state.
[1171] "Data acquisition means" refers to means for extracting story data and character information from an existing database.
[1172] "Generative model means" refers to a machine learning model for predicting the ending of an unfinished story based on acquired story data and character information.
[1173] A "formatting tool" is a tool for formatting the generated story's ending in text or visual form.
[1174] The "data transmission means" is a communication means for providing the generated ending to the user's terminal after formatting.
[1175] "Emotion engine means" refers to software or hardware for analyzing a user's facial expressions and recognizing the user's emotional state.
[1176] "Emotional adaptation means" are means for adjusting the outcome predicted by the generative model based on the perceived emotional state of the user.
[1177] "User interface means" refers to an operation screen that allows the user to select the title of an unfinished story and transmits that information to the server.
[1178] The "database acquisition means" is a query issuing means for the server to acquire the necessary story data and character information from the database.
[1179] The present invention is a system designed to meet the needs of users who want to know the ending of an unfinished story. The system mainly includes a terminal, a server, a database, a generative AI model, a user interface, and an emotion engine. Below, we will explain in detail how to implement the invention, while specifically showing the hardware and software used.
[1180] 1. Providing a user interface
[1181] The terminal provides the user with an interface for selecting unfinished stories. Specifically, there is an application that runs on a web browser, and the user can select a story of interest from a list of unfinished stories displayed.
[1182] Software used:
[1183] Browser-based UI frameworks (e.g., React, Vue.js)
[1184] Examples:
[1185] The user selects the unfinished story "Adventure Journey" from the device's UI.
[1186] 2. Data transmission
[1187] When the user selects a story, allows acquisition of emotional data, and then clicks the request button, the terminal transmits the selected title and emotional state information to the server.
[1188] Software and hardware used:
[1189] Network communication protocols (e.g. HTTP / HTTPS), camera on user device
[1190] Examples:
[1191] The user selects "Adventure Journey," allows emotion data acquisition, and clicks the request button.
[1192] 3. Acquiring story data
[1193] The server retrieves the relevant story data and character information from the database based on the received story title information, specifically by issuing an SQL query to extract the relevant data.
[1194] Software used:
[1195] Database management systems (e.g., MySQL, PostgreSQL)
[1196] Examples:
[1197] The server issues the query "SELECT FROM stories WHERE title = 'Adventure Journey'" to retrieve story data from the database.
[1198] 4. Use of Emotion Engine
[1199] The device uses a camera to analyze the user's facial expressions and recognizes their emotional state using an emotion engine, and transmits the recognized emotional state information to a server in real time.
[1200] Software used:
[1201] Emotion analysis API (e.g. Emotion API)
[1202] Examples:
[1203] The device uses the Emotion API to analyze the user's facial expression and transmits to the server that the user is "sad."
[1204] 5. Running the generative AI model
[1205] The server inputs the acquired story data, character information, and emotional state information into a generative AI model, which uses machine learning techniques to predict the ending of the unfinished story and adjust it based on the emotional state.
[1206] Software used:
[1207] Generative AI models (e.g., OpenAI GPT-4)
[1208] Examples:
[1209] The server inputs the following prompt into the generative AI model: "The user feels sad about the ending of the story 'Adventure Journey'. Please generate an ending based on this emotion."
[1210] 6. Ending tweaks
[1211] The server formats the generated ending data. In the case of text format, it formats the sentences, and in the case of visual (manga) format, it creates a page layout based on the scenes and dialogues.
[1212] Software used:
[1213] Text processing libraries (e.g., Python's NLTK), visual editing software (e.g., Adobe Photoshop)
[1214] Examples:
[1215] Format the generated text "The end of the adventure: The protagonist ends his journey in sadness." and, in the case of a manga format, create a page layout with scenes and dialogues.
[1216] 7. Data Transmission and Display
[1217] The server sends the formatted outcome data to the terminal, which displays the data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[1218] Software and hardware used:
[1219] Network communication protocol (e.g. HTTP / HTTPS), HTML viewer or dedicated app
[1220] Examples:
[1221] The server sends formatted text data and visual data to the terminal, which displays it to the user.
[1222] The above is a concrete embodiment of the present invention. The system provides a personalized story ending based on the user's choices and emotional state, increasing user satisfaction.
[1223] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1224] Step 1: Display and select the user interface
[1225] Description: The device provides the user with an interface for selecting an incomplete story. The interface displays a list of existing incomplete stories. The user can select a story from the list that interests them.
[1226] Input: A list of unfinished stories on the device
[1227] Output: The specific story title selected by the user
[1228] Specific behavior:
[1229] The device displays a list of unfinished stories as HTML on the browser.
[1230] The user clicks to select "Magic Forest" from the list.
[1231] Step 2: Sending data
[1232] Description: When the user selects a story and clicks the request button after allowing emotional data acquisition, the device sends the selected title and emotional state information to the server.
[1233] Input: User-selected story title, permission to create emotion data
[1234] Output: Story title and emotional state information sent to the server
[1235] Specific behavior:
[1236] The user selects "Magical Forest," allows acquisition of emotion data, and clicks the request button.
[1237] The terminal sends the selected title "Magical Forest" and the user's emotional state information to the server as an HTTP request.
[1238] Step 3: Get Story Data
[1239] Description: The server retrieves related story data and character information from the database based on the received story title information.
[1240] Input: Story title information received by the server
[1241] Output: Story data and character information retrieved from the database
[1242] Specific behavior:
[1243] The server issues the following SQL query to the database: SELECT FROM stories WHERE title = 'Magic Forest'.
[1244] The database returns relevant story data and character information based on the query.
[1245] Step 4: Use the Emotion Engine
[1246] Description: The device uses a camera to analyze the user's facial expressions and utilizes an emotion engine to recognize the user's emotional state. The device transmits the recognized emotional state information to the server in real time.
[1247] Input: A user's face image captured by a camera
[1248] Output: Emotional state information sent to the server
[1249] Specific behavior:
[1250] The device sends the user's facial image to the Emotion API.
[1251] The Emotion API analyzes images and recognizes the user's emotional state as "sad."
[1252] The terminal transmits the recognized emotional state to the server.
[1253] Step 5: Running the generative AI model
[1254] Description: The server inputs the acquired story data, character information, and emotional state information into a generative model. Based on this data, the generative model predicts the ending of the unfinished story and adjusts it based on the user's emotional state.
[1255] Input: Story data, character information, emotional state information
[1256] Output: The generated story ending
[1257] Specific behavior:
[1258] The server inputs this data into a generative AI model.
[1259] A generative AI model (e.g., GPT-4) uses this data to generate a story ending, adjusting it depending on the emotional state.
[1260] The server receives the generated outcome.
[1261] Step 6: Shaping the ending
[1262] Description: The server formats the generated outcome data, either by formatting the sentences in the text format or by creating a page layout based on the scenes and dialogue in the visual format.
[1263] Input: Generated story ending
[1264] Output: Formatted text or visual data
[1265] Specific behavior:
[1266] The server formats the generated text, "The End of the Enchanted Forest: The Protagonist Ends His Journey in Sadness.", to make it easier to read.
[1267] In the manga format, the page layout is created based on the generated scenes and dialogue.
[1268] Step 7: Send and display data
[1269] Description: The server sends the formatted outcome data to the terminal, which displays this data to the user.
[1270] Input: Formatted outcome data
[1271] Output: The outcome displayed on the user's terminal
[1272] Specific behavior:
[1273] The server sends formatted text data and visual data to the terminal.
[1274] The device receives it and displays it to the user, either as text if it is in text format or in a page viewer if it is in visual format.
[1275] (Application example 2)
[1276] 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."
[1277] In recent years, users have increasingly expressed a desire to know the ending of a story in a way that reflects their own emotional state. However, existing systems have difficulty generating endings that reflect the user's emotional state. Furthermore, the generated story endings do not necessarily match the user's emotions, resulting in a uniform user experience.
[1278] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data acquisition means for acquiring story and character information from existing data, generative model means for predicting the ending of an unfinished story based on the acquired information, formatting means for formatting the generated ending into a text format or a visual format, emotion analysis means for analyzing the user's facial expression to acquire emotion data, emotion adjustment means for adjusting the ending using the acquired emotion data, and data transmission means for providing the adjusted ending to the user's terminal. This makes it possible to provide a personalized story ending that corresponds to the user's emotional state.
[1279] "Data acquisition means" refers to a method for acquiring story and character information from existing data.
[1280] A "generative modeling method" is a method for predicting the outcome of an unfinished story based on acquired information.
[1281] A "formatter" is a method for formatting the generated conclusion into textual or visual form.
[1282] The "emotion analysis means" is a method for analyzing the user's facial expression to obtain emotion data.
[1283] "Emotion adjustment means" is a method for adjusting the ending using the acquired emotion data.
[1284] A "data transmission means" is a method for providing a tailored outcome to a user's terminal.
[1285] The "user interface means" is a method for transmitting title information of an unfinished story selected by the user to the server.
[1286] The "database acquisition means" is a method for acquiring acquired story and character information from the database.
[1287] The present invention is a system that uses emotional data to provide a personalized ending to an unfinished story in response to a user's desire to know the ending of the story. This system implements the invention through the following steps.
[1288] 1. System Overview
[1289] The system includes a terminal, a server, a data acquisition means, a generative model means, an emotion analysis means, an emotion adjustment means, a formatting means, a data transmission means, a user interface means, and a database acquisition means. A user uses the terminal to select an unfinished story title and make a request to know the subsequent ending.
[1290] 2. Data Acquisition
[1291] The server uses a database acquisition means to acquire related story data and character information based on the story title information sent by the user. The database stores existing story data and character information, and generates an ending based on this information.
[1292] 3.Emotion analysis
[1293] The device uses a camera to analyze the user's facial expressions and uses an emotion analysis means to recognize the user's emotional state. This emotion analysis means uses facial recognition technology to analyze the user's facial expressions and obtain emotional data such as joy, sadness, and excitement. Libraries such as OpenCV and TensorFlow / Keras are used for this analysis.
[1294] 4. Generative Model
[1295] The server inputs the acquired story data, character information, and emotional state information into a generative modeling means. The generative modeling means uses machine learning technology to analyze existing data and predict the ending of the unfinished story. Furthermore, an emotional adjustment means adjusts the ending according to the user's emotional state.
[1296] 5. Ending tweaks
[1297] The generated ending data is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated content is formatted into easy-to-read sentences, and in the case of the manga format, a page layout is created based on the generated scenes and dialogues, and character drawings are combined to form a manga page.
[1298] 6. Providing an ending
[1299] The formatted conclusion data is sent to the terminal using the data transmission means, and the terminal displays it to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[1300] Specific examples
[1301] 1. Example 1: Textual Conclusion and Emotional Adaptation
[1302] The user selects the unfinished story from the device UI and grants camera permission.
[1303] The terminal transmits the selected title and emotion data to the server.
[1304] The server retrieves existing story data from a database.
[1305] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[1306] The server generates an outcome based on the emotional state, formats it, and sends it to the terminal.
[1307] The terminal displays the generated text to the user.
[1308] 2. Example 2: Manga-style ending and emotional adaptation
[1309] The user selects the unfinished story from the device UI and grants camera permission.
[1310] The terminal transmits the selected title and emotion data to the server.
[1311] The server retrieves existing story data and character information from a database.
[1312] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[1313] The server generates scenes and dialogues based on the emotional state, formats them, and sends them to the device.
[1314] The terminal displays the generated comic page to the user.
[1315] Example prompts for generative AI models
[1316] "The story is set in a fantasy genre. The hero is a hero who is forced to make an important decision during his adventure. An emotion of excitement was detected from the user's facial expression. Please generate the ending of the story."
[1317] As described above, the present invention generates an ending to an unfinished story in a manner that takes into account the user's emotions, thereby providing a personalized content experience.
[1318] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1319] Step 1:
[1320] The user selects the title of an unfinished story using the user interface of the terminal and grants permission to use the camera. The terminal receives input from the user and obtains title information of the selected story.
[1321] Step 2:
[1322] The device captures the user's facial expression along with the acquired story title information with a camera and analyzes the facial expression using an emotion analysis means. The emotion analysis means uses the OpenCV library and TensorFlow / Keras model to identify the user's emotional state (e.g., joy, sadness, excitement) from the facial expression data. The analysis results are output as emotion data.
[1323] Step 3:
[1324] The terminal transmits the title information and emotion data of the selected story to the server. Based on the story title information received from the terminal, the server uses a database acquisition means to acquire related story data and character information. The database stores existing story data and character information.
[1325] Step 4:
[1326] The server inputs the story data, character information, and emotion data acquired by the database acquisition means into the generative model means. The generative model means uses machine learning techniques (TensorFlow / Keras) to predict the ending of the unfinished story. Based on the emotion data, the ending is adjusted to adapt to the user's emotional state.
[1327] Step 5:
[1328] The ending data generated by the generative model means is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated ending is formatted into easy-to-read sentences. In the case of the visual format (manga format), a page layout is created based on the generated scenes and dialogue, and character drawings are combined to format the ending.
[1329] Step 6:
[1330] The server transmits the formatted ending data to the terminal using a data transmission means. The terminal displays the received ending data to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[1331] In this way, a personalized story ending is provided that responds to the user's emotional state.
[1332] 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.
[1333] 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.
[1334] 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.
[1335] [Fourth embodiment]
[1336] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1337] 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.
[1338] 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).
[1339] 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.
[1340] 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.
[1341] 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).
[1342] 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.
[1343] 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.
[1344] 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.
[1345] 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.
[1346] 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.
[1347] 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.
[1348] 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."
[1349] 1. System Overview
[1350] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an unfinished story selected by the user, the server retrieves information from the database, uses the generative model to predict the ending, formats it, and delivers it to the terminal.
[1351] 2. Providing a user interface
[1352] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[1353] 3. Data transmission
[1354] When the user selects an unfinished story that interests them and clicks the request button for generating an ending, the terminal sends the title information of the selected manga to the server.
[1355] 4. Acquiring story data
[1356] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[1357] 5. Running the AI model
[1358] The server inputs the acquired story data into a generative model. The generative model uses machine learning techniques to analyze existing story data and character information to predict the ending of an unfinished story. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[1359] 6. Ending tweaks
[1360] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1361] 7. Data Transmission and Display
[1362] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[1363] Specific examples
[1364] 1. Example 1: Textual ending generation
[1365] The user selects the unfinished story "Adventure Journey" from the device's UI.
[1366] The terminal transmits the selected title "Adventure Journey" to the server.
[1367] The server retrieves existing story data for "Adventure Journey" from the database.
[1368] The server inputs the acquired data into a generative model and generates text as the result.
[1369] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[1370] The terminal displays the generated text to the user.
[1371] 2. Example 2: Manga-style ending generation
[1372] The user selects the unfinished story "Magic Forest" from the device's UI.
[1373] The terminal transmits the selected title "Magical Forest" to the server.
[1374] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1375] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[1376] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[1377] The formatted manga format data is sent to the device.
[1378] The terminal displays the generated comic page to the user.
[1379] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[1380] The processing flow will be explained below.
[1381] Step 1:
[1382] The terminal provides the user with an interface for selecting an incomplete story title, specifically, a list of available incomplete stories is displayed on the screen.
[1383] Step 2:
[1384] The user selects an unfinished story that they are interested in from the list on the interface and requests the creation of an ending. By clicking the request button, the title information of the selected story is sent.
[1385] Step 3:
[1386] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[1387] Step 4:
[1388] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[1389] Step 5:
[1390] The server inputs the acquired story data and character information into a generative model, which uses this data to predict and generate the ending of the unfinished story. AI models and machine learning algorithms are used.
[1391] Step 6:
[1392] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1393] Step 7:
[1394] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[1395] Step 8:
[1396] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[1397] In this way, the system allows the user to find out the ending of an unfinished story.
[1398] Example 1
[1399] 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."
[1400] Conventional technologies have limited means for predicting the ending of an unfinished story and providing it to users. As a result, it has been difficult to quickly and appropriately respond to users' needs to know the ending of the story. In addition, some systems only support either text or visual formats, which means they cannot meet the needs of a wide range of users.
[1401] 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.
[1402] In this invention, the server includes a user interface means for receiving the title of the unfinished story selected by the user, a data acquisition means for acquiring story and character information from existing data, a generative model means including a generative AI model for predicting the ending of the unfinished story based on the acquired information, a formatting means for formatting the generated ending into a text format or a visual format, and a data transmission means for transmitting the formatted ending data to the user's terminal. This makes it possible to quickly generate the ending of the unfinished story and provide it in the text format or visual format desired by the user.
[1403] A "user interface means" is a device or software that provides an interface for a user to interact with the system.
[1404] "Data acquisition means" refers to a device or software for acquiring story and character information from existing data.
[1405] A "generative AI model" is a model that uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story.
[1406] A "generative model means" is a device or software that includes a generative AI model for predicting the outcome of an unfinished story based on acquired information.
[1407] A "formatter" is a device or software for formatting the generated conclusion into textual or visual form.
[1408] The "data transmission means" is a device or software for transmitting formatted conclusion data to the user's terminal.
[1409] The "database acquisition means" is a device or software that allows the server to acquire story and character information from the database.
[1410] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, and a user interface.
[1411] Hardware and Software Configuration
[1412] Terminal: A device that provides a user interface and receives input from a user. This can be a personal computer, smartphone, tablet, etc. The terminal has UI display software installed, which displays a list of open stories and accepts user selections.
[1413] Server: Acts as the central processing unit, acquiring data, running the generative AI model, formatting and transmitting the data. The server has database connection software and Python scripts installed to run the generative AI model (e.g., GPT-3).
[1414] Database: A data store for story and character information. This is where existing story data and character details are stored.
[1415] Generative AI models: Machine learning models designed to predict the ending of an unfinished story, such as OpenAI's GPT-3, that can analyze existing story data and generate new endings.
[1416] System Operation
[1417] The system operates as follows.
[1418] 1. Providing a user interface
[1419] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[1420] 2. Data transmission
[1421] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[1422] 3. Acquiring story data
[1423] The server retrieves related story data and character information from the database based on the received story title information. The server issues a query to the database to retrieve the required data.
[1424] 4. Running the AI model
[1425] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. For example, a prompt sentence such as "The title of the story is 'Adventure Journey'. Please complete the unfinished part of the story" can be input into the generative model.
[1426] 5. Ending tweaks
[1427] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1428] 6. Data transmission and display
[1429] The server sends the formatted ending data to the user's device, which then displays the received data to the user. If the data is in text format, it is displayed in a text viewer, and if it is in manga format, it is displayed in a page viewer.
[1430] Specific examples
[1431] As a concrete example, the following scenario can be considered.
[1432] Example 1: Textual ending generation
[1433] 1. The user selects the unfinished story "Adventure Journey" from the device's UI.
[1434] 2. The terminal sends the selected title "Adventure Journey" to the server.
[1435] 3. The server retrieves existing story data for "Adventure Journey" from the database.
[1436] 4. The server inputs the acquired data into the generative model and generates text as the result.
[1437] 5. Format the generated text, "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions.", and send it to the device.
[1438] 6. The terminal displays the generated text to the user.
[1439] Example 2: Manga-style ending generation
[1440] 1. The user selects the unfinished story "Magic Forest" from the device's UI.
[1441] 2. The device sends the selected title "Magical Forest" to the server.
[1442] 3. The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1443] 4. The server inputs the acquired data into a generative model and generates scenes and dialogues as predicted outcomes.
[1444] 5. Format the generated scenes and dialogues into a comic book format and create page layouts.
[1445] 6. Send the formatted manga data to the device.
[1446] 7. The terminal displays the generated comic page to the user.
[1447] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[1448] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1449] Step 1: Displaying the User Interface
[1450] The terminal displays an interface for the user to select an incomplete story, specifically, a list of available incomplete stories is displayed on the screen.
[1451] Input: List of unfinished stories in the system
[1452] Output: A list of stories displayed on the device screen
[1453] Specific operation: When the device is initialized, it retrieves the list of unfinished stories from the server and passes that data to the UI component to display the list.
[1454] Step 2: User selects story and submits request
[1455] The user selects an unfinished story of interest from the list and clicks a button to request the creation of an ending for that story.
[1456] The terminal transmits the title information of the selected story to the server.
[1457] Input: User selection and title of selected story
[1458] Output: Sends a request to the server containing the title of the selected story.
[1459] Specific operation: The device catches the user's click event and sends a POST request to the server with the title information of the selected story in JSON format.
[1460] Step 3: Get Story Data
[1461] The server retrieves related story data and character information from the database based on the received story title information.
[1462] Input: Story title information received from the device
[1463] Output: Story data and character information retrieved from the database
[1464] Specific operation: The server executes an SQL query using the story title to retrieve the corresponding story data from the database. For example, it executes the query "SELECT FROM stories WHERE title="Adventure Journey"".
[1465] Step 4: Running the generative AI model
[1466] The server inputs the acquired story data into a generative AI model to predict the ending of the unfinished story.
[1467] Input: Story data and character information retrieved from the database
[1468] Output: Outcome data output from the generative AI model
[1469] Specific operation: The server runs a Python script and inputs story data and a prompt to a generative AI model (e.g., GPT-3). An example of the prompt is "The title of the story is 'Adventure Journey'. Please complete the unfinished parts of the story."
[1470] Step 5: Formatting the outcome data
[1471] The server formats the generated outcome data into a textual or visual format.
[1472] Input: Outcome data output from the generative AI model
[1473] Output: Formatted outcome data (text or visual)
[1474] What it does: The server formats the generated text into HTML or Markdown, edits the scenes and dialogue in the case of manga, and generates the visual data using page layout software.
[1475] Step 6: Send and display the outcome data
[1476] The server sends the formatted outcome data to the user's terminal, which displays the received data to the user.
[1477] Input: Formatted ending data sent from the server
[1478] Output: The outcome data displayed on the user's terminal
[1479] Specific operation: The server sends the formatted ending data in JSON format to the device. The device receives it and displays it to the user in a text viewer or manga viewer.
[1480] (Application example 1)
[1481] 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."
[1482] In recent years, there has been an increasing demand for the ending of unfinished stories, but there are currently no appropriate means to meet this demand. Users cannot obtain automatically generated endings based on existing story data, and must wait a long time for the ending. This makes it difficult to sustain users' interest, and there is a growing demand for early conclusions to stories.
[1483] 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.
[1484] In this invention, the server includes data acquisition means for acquiring story and actor data from existing information, generative model means for predicting the ending of an unfinished story based on the acquired data, formatting means for formatting the generated ending in a text format or a visual format, data transmission means for providing the ending to the user's information terminal, interface means for displaying a list of unfinished stories that the user can select, and request transmission means for transmitting an ending generation request based on the story title selected by the user, thereby enabling the user to quickly obtain the predicted ending of the unfinished story.
[1485] "Data acquisition tools" are functions for collecting story and actor data from existing sources.
[1486] The "generative model means" is a function that automatically predicts the ending of an unfinished story based on acquired story and actor data.
[1487] The "formatting means" is a function for formatting the generated conclusion in a character string format or a visual format so that it can be displayed to the user in an easy-to-understand manner.
[1488] "Data transmission means" is a function for transmitting the generated ending to the user's information terminal.
[1489] The "interface means" is a function that displays a list of incomplete stories that the user can select from and provides an interface for the user to select a story.
[1490] The "request sending means" is a function for sending the title information of the story selected by the user to the server and executing the ending generation request.
[1491] "Database acquisition means" is a function for acquiring story and actor data from a database.
[1492] 1. System Overview
[1493] The system of this invention is designed to allow users to predict the ending of an incomplete story. The system includes a terminal, a server, a database, a generative model, and a user interface. For an incomplete story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, formats it, and delivers it to the terminal.
[1494] 2. Providing a user interface
[1495] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[1496] 3. Data transmission
[1497] When the user selects an unfinished story that interests them and clicks the request button for ending generation, the terminal sends the title information of the selected story to the server.
[1498] 4. Acquiring story data
[1499] The server retrieves related story data and character information from the database based on the received story title information by issuing a title-based query to the database.
[1500] 5. Running the AI model
[1501] The server inputs the acquired story data into a generative model. The generative model uses machine learning technology to analyze existing story data and character information to predict the ending of an unfinished story. OpenAI's GPT-3 is used as the generative AI model used for prediction. For example, for a story titled "Adventure Journey," the model generates an ending in which the protagonist finds treasure but chooses to bond with his companions.
[1502] 6. Ending tweaks
[1503] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of visual format, the server creates a page layout based on the generated scenes and dialogue, and combines character images.
[1504] 7. Data Transmission and Display
[1505] The server sends the formatted conclusion data to the user's terminal, which displays the received data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[1506] Specific examples
[1507] Example 1: Textual ending generation
[1508] The user selects the unfinished story "Adventure Journey" from the device's UI.
[1509] The terminal transmits the selected title "Adventure Journey" to the server.
[1510] The server retrieves existing story data for "Adventure Journey" from the database.
[1511] The server inputs the acquired data into a generative model and generates text as the result.
[1512] The generated text "The conclusion of the adventure: The protagonist finally finds the treasure, but chooses to bond with his companions." is formatted and sent to the device.
[1513] The terminal displays the generated text to the user.
[1514] Example 2: Visual Outcome Generation
[1515] The user selects the unfinished story "Magic Forest" from the device's UI.
[1516] The terminal transmits the selected title "Magical Forest" to the server.
[1517] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1518] The server uses a generative model based on the acquired data to generate scenes and dialogues as predicted endings.
[1519] Format the generated scenes and dialogues into a visual format and create a page layout.
[1520] Sends formatted, visually formatted data to the terminal.
[1521] The terminal displays the generated page to the user.
[1522] Prompt Sentence Examples
[1523] Story Data: "The protagonist goes on an adventure to find treasure."
[1524] Prompt: "The protagonist goes on an adventure to find treasure. What is the outcome of this story?"
[1525] In this way, the system of the present invention generates the ending of an unfinished story and provides it to the user, thereby satisfying the need to know the ending of the story.
[1526] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1527] Step 1:
[1528] The user selects an unfinished story.
[1529] The user selects a story of interest from the displayed list of unfinished stories through the user interface of the terminal. The input is the title of the story based on the user's selection. The output is the title information of the selected story.
[1530] Step 2:
[1531] The terminal transmits the story title information to the server.
[1532] The terminal collects the story title information selected by the user and sends it to the server as a POST request. The input is the story title information selected by the user. The output is the title information received by the server.
[1533] Step 3:
[1534] The server retrieves the story data from the database.
[1535] The server issues a query to the database based on the received story title to retrieve related story data and character information. The input is story title information, and the output is story data and character information.
[1536] Step 4:
[1537] The server inputs story data into a generative model to predict the ending.
[1538] The server inputs the acquired story data and character information into a generative AI model. The generative model (e.g., GPT-3) analyzes the input data, creates a generative prompt to predict the optimal ending, and generates the ending. The input is story data and character information, and the output is the predicted ending data.
[1539] Step 5:
[1540] The server formats the resulting result.
[1541] The server takes the outcome output by the generative model and formats it into a user-readable format (text or visual format). The input is the generated outcome data, and the output is the formatted outcome data.
[1542] Step 6:
[1543] The server transmits the formatted conclusion data to the terminal.
[1544] The server sends the formatted outcome data to the user's terminal. The input is the formatted outcome data, and the output is the outcome data received by the terminal.
[1545] Step 7:
[1546] The terminal displays the received conclusion data to the user.
[1547] The terminal displays the outcome data received from the server to the user through a user interface. The input is the outcome data received from the server, and the output is the outcome information displayed to the user.
[1548] This allows the user to quickly find out the ending of an unfinished story.
[1549] 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.
[1550] 1. System Overview
[1551] The system of the present invention is designed to meet the needs of users who want to know the ending of an unfinished story. The system includes a terminal, a server, a database, a generative model, a user interface, and an emotion engine. For an unfinished story selected by a user, the server retrieves information from the database, predicts the ending using the generative model, and adjusts the ending based on the user's emotions using the emotion engine before delivering it to the terminal.
[1552] 2. Providing a user interface
[1553] The terminal provides the user with an interface for selecting an unfinished story title. The interface displays a list of available unfinished stories. The user can select an unfinished story of interest from the list.
[1554] 3. Data transmission
[1555] When a user selects an unfinished story in which they are interested, allows acquisition of emotional data, and clicks a request button for generating an ending, the terminal sends the title information and emotional state information of the selected story to the server.
[1556] 4. Acquiring story data
[1557] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[1558] 5. Use of Emotion Engine
[1559] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[1560] 6. Running the AI model
[1561] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[1562] 7. Ending tweaks
[1563] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1564] 8. Data Transmission and Display
[1565] The server sends the formatted conclusion data to the terminal, which then displays the received data to the user. If the data is in text format, it is displayed as easy-to-read text, and if it is in manga format, it is displayed using a page viewer.
[1566] Specific examples
[1567] 1. Example 1: Textual Conclusion and Emotional Adaptation
[1568] The user selects the unfinished story "Adventure Journey" from the device's UI and grants camera permission.
[1569] The terminal transmits the selected title "Adventure Journey" and the emotion data to the server.
[1570] The server retrieves existing story data for "Adventure Journey" from the database.
[1571] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[1572] The server inputs the acquired data into a generative model to generate an outcome based on the emotional state.
[1573] The generated text "The end of the adventure: The protagonist finally finds the treasure and rejoices with his companions." is formatted and sent to the device.
[1574] The terminal displays the generated text to the user.
[1575] 2. Example 2: Manga-style ending and emotional adaptation
[1576] The user selects the unfinished story "Magical Forest" from the device's UI and grants camera permission.
[1577] The terminal transmits the selected title "Magical Forest" and the emotion data to the server.
[1578] The server retrieves existing story data and character information for the "Magical Forest" from the database.
[1579] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[1580] The server uses a generative model based on the acquired data to generate scenes and dialogues based on the emotional state.
[1581] The generated scenes and dialogues are formatted into a comic book format and a page layout is created.
[1582] The formatted manga format data is sent to the device.
[1583] The terminal displays the generated comic page to the user.
[1584] In this way, the system of the present invention generates and provides the user with an ending to an unfinished story while taking into account the user's emotions, providing a more personalized experience.
[1585] The processing flow will be explained below.
[1586] Step 1:
[1587] The terminal provides the user with an interface for selecting an incomplete story title, and the interface displays a list of available incomplete stories.
[1588] Step 2:
[1589] The user selects an unfinished story of interest from a list on the interface, allows emotional data acquisition, and then requests the creation of an ending. By clicking the request button, the title information and emotional state information of the selected story are sent.
[1590] Step 3:
[1591] The terminal sends the title information of the story selected by the user to the server using a communication protocol such as an HTTP request.
[1592] Step 4:
[1593] The server retrieves the relevant story data and character information from the database based on the received story title information. Specifically, it issues a query to the database to retrieve the necessary information.
[1594] Step 5:
[1595] The device analyzes the user's facial expressions with a camera to recognize their emotional state. An emotion engine analyzes the images and identifies their emotional state, such as excitement, joy, or sadness. This information is sent to the server in real time.
[1596] Step 6:
[1597] The server inputs the acquired story data, character information, and emotional state information into a generative model, which uses machine learning techniques to analyze existing story data and character information to predict the ending of the unfinished story and adjust it based on the emotional state.
[1598] Step 7:
[1599] The server formats the generated ending data. In the case of text format, the generated content is formatted as sentences to make it easier to read. In the case of manga format, a page layout is created based on the generated scenes and dialogue, and the character drawings are combined to create the manga pages.
[1600] Step 8:
[1601] The server sends the resulting data to the terminal, where it is formatted and ready to be displayed to the user.
[1602] Step 9:
[1603] The terminal displays the received conclusion data to the user. In the case of text format, it is displayed as easy-to-read sentences, and in the case of manga format, it is displayed using a page viewer.
[1604] Example 2
[1605] 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."
[1606] Existing story generation systems often provide a uniform ending without considering the user's emotional state, resulting in low user satisfaction. Furthermore, there is a lack of technology that provides individually tailored endings based on the user's choices and emotions. To address this issue, it is necessary to provide a system that recognizes the user's emotional state in real time and generates and adjusts endings based on that information.
[1607] 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.
[1608] In this invention, the server includes data acquisition means for acquiring information from existing data, generative model means for predicting an ending of an unfinished story based on the acquired information, and emotion adaptation means for adjusting the generated ending based on the user's emotional state, thereby enabling the provision of a personalized ending according to the user's selection and emotional state.
[1609] "Data acquisition means" refers to means for extracting story data and character information from an existing database.
[1610] "Generative model means" refers to a machine learning model for predicting the ending of an unfinished story based on acquired story data and character information.
[1611] A "formatting tool" is a tool for formatting the generated story's ending in text or visual form.
[1612] The "data transmission means" is a communication means for providing the generated ending to the user's terminal after formatting.
[1613] "Emotion engine means" refers to software or hardware for analyzing a user's facial expressions and recognizing the user's emotional state.
[1614] "Emotional adaptation means" are means for adjusting the outcome predicted by the generative model based on the perceived emotional state of the user.
[1615] "User interface means" refers to an operation screen that allows the user to select the title of an unfinished story and transmits that information to the server.
[1616] The "database acquisition means" is a query issuing means for the server to acquire the necessary story data and character information from the database.
[1617] The present invention is a system designed to meet the needs of users who want to know the ending of an unfinished story. The system mainly includes a terminal, a server, a database, a generative AI model, a user interface, and an emotion engine. Below, we will explain in detail how to implement the invention, while specifically showing the hardware and software used.
[1618] 1. Providing a user interface
[1619] The terminal provides the user with an interface for selecting unfinished stories. Specifically, there is an application that runs on a web browser, and the user can select a story of interest from a list of unfinished stories displayed.
[1620] Software used:
[1621] Browser-based UI frameworks (e.g., React, Vue.js)
[1622] Examples:
[1623] The user selects the unfinished story "Adventure Journey" from the device's UI.
[1624] 2. Data transmission
[1625] When the user selects a story, allows acquisition of emotional data, and then clicks the request button, the terminal transmits the selected title and emotional state information to the server.
[1626] Software and hardware used:
[1627] Network communication protocols (e.g. HTTP / HTTPS), camera on user device
[1628] Examples:
[1629] The user selects "Adventure Journey," allows emotion data acquisition, and clicks the request button.
[1630] 3. Acquiring story data
[1631] The server retrieves the relevant story data and character information from the database based on the received story title information, specifically by issuing an SQL query to extract the relevant data.
[1632] Software used:
[1633] Database management systems (e.g., MySQL, PostgreSQL)
[1634] Examples:
[1635] The server issues the query "SELECT FROM stories WHERE title = 'Adventure Journey'" to retrieve story data from the database.
[1636] 4. Use of Emotion Engine
[1637] The device uses a camera to analyze the user's facial expressions and recognizes their emotional state using an emotion engine, and transmits the recognized emotional state information to a server in real time.
[1638] Software used:
[1639] Emotion analysis API (e.g. Emotion API)
[1640] Examples:
[1641] The device uses the Emotion API to analyze the user's facial expression and transmits to the server that the user is "sad."
[1642] 5. Running the generative AI model
[1643] The server inputs the acquired story data, character information, and emotional state information into a generative AI model, which uses machine learning techniques to predict the ending of the unfinished story and adjust it based on the emotional state.
[1644] Software used:
[1645] Generative AI models (e.g., OpenAI GPT-4)
[1646] Examples:
[1647] The server inputs the following prompt into the generative AI model: "The user feels sad about the ending of the story 'Adventure Journey'. Please generate an ending based on this emotion."
[1648] 6. Ending tweaks
[1649] The server formats the generated ending data. In the case of text format, it formats the sentences, and in the case of visual (manga) format, it creates a page layout based on the scenes and dialogues.
[1650] Software used:
[1651] Text processing libraries (e.g., Python's NLTK), visual editing software (e.g., Adobe Photoshop)
[1652] Examples:
[1653] Format the generated text "The end of the adventure: The protagonist ends his journey in sadness." and, in the case of a manga format, create a page layout with scenes and dialogues.
[1654] 7. Data Transmission and Display
[1655] The server sends the formatted outcome data to the terminal, which displays the data to the user either as easy-to-read text in the case of text format or using a page viewer in the case of visual format.
[1656] Software and hardware used:
[1657] Network communication protocol (e.g. HTTP / HTTPS), HTML viewer or dedicated app
[1658] Examples:
[1659] The server sends formatted text data and visual data to the terminal, which displays it to the user.
[1660] The above is a concrete embodiment of the present invention. The system provides a personalized story ending based on the user's choices and emotional state, increasing user satisfaction.
[1661] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1662] Step 1: Display and select the user interface
[1663] Description: The device provides the user with an interface for selecting an incomplete story. The interface displays a list of existing incomplete stories. The user can select a story from the list that interests them.
[1664] Input: A list of unfinished stories on the device
[1665] Output: The specific story title selected by the user
[1666] Specific behavior:
[1667] The device displays a list of unfinished stories as HTML on the browser.
[1668] The user clicks to select "Magic Forest" from the list.
[1669] Step 2: Sending data
[1670] Description: When the user selects a story and clicks the request button after allowing emotional data acquisition, the device sends the selected title and emotional state information to the server.
[1671] Input: User-selected story title, permission to create emotion data
[1672] Output: Story title and emotional state information sent to the server
[1673] Specific behavior:
[1674] The user selects "Magical Forest," allows acquisition of emotion data, and clicks the request button.
[1675] The terminal sends the selected title "Magical Forest" and the user's emotional state information to the server as an HTTP request.
[1676] Step 3: Get Story Data
[1677] Description: The server retrieves related story data and character information from the database based on the received story title information.
[1678] Input: Story title information received by the server
[1679] Output: Story data and character information retrieved from the database
[1680] Specific behavior:
[1681] The server issues the following SQL query to the database: SELECT FROM stories WHERE title = 'Magic Forest'.
[1682] The database returns relevant story data and character information based on the query.
[1683] Step 4: Use the Emotion Engine
[1684] Description: The device uses a camera to analyze the user's facial expressions and utilizes an emotion engine to recognize the user's emotional state. The device transmits the recognized emotional state information to the server in real time.
[1685] Input: A user's face image captured by a camera
[1686] Output: Emotional state information sent to the server
[1687] Specific behavior:
[1688] The device sends the user's facial image to the Emotion API.
[1689] The Emotion API analyzes images and recognizes the user's emotional state as "sad."
[1690] The terminal transmits the recognized emotional state to the server.
[1691] Step 5: Running the generative AI model
[1692] Description: The server inputs the acquired story data, character information, and emotional state information into a generative model. Based on this data, the generative model predicts the ending of the unfinished story and adjusts it based on the user's emotional state.
[1693] Input: Story data, character information, emotional state information
[1694] Output: The generated story ending
[1695] Specific behavior:
[1696] The server inputs this data into a generative AI model.
[1697] A generative AI model (e.g., GPT-4) uses this data to generate a story ending, adjusting it depending on the emotional state.
[1698] The server receives the generated outcome.
[1699] Step 6: Shaping the ending
[1700] Description: The server formats the generated outcome data, either by formatting the sentences in the text format or by creating a page layout based on the scenes and dialogue in the visual format.
[1701] Input: Generated story ending
[1702] Output: Formatted text or visual data
[1703] Specific behavior:
[1704] The server formats the generated text, "The End of the Enchanted Forest: The Protagonist Ends His Journey in Sadness.", to make it easier to read.
[1705] In the manga format, the page layout is created based on the generated scenes and dialogue.
[1706] Step 7: Send and display data
[1707] Description: The server sends the formatted outcome data to the terminal, which displays this data to the user.
[1708] Input: Formatted outcome data
[1709] Output: The outcome displayed on the user's terminal
[1710] Specific behavior:
[1711] The server sends formatted text data and visual data to the terminal.
[1712] The device receives it and displays it to the user, either as text if it is in text format or in a page viewer if it is in visual format.
[1713] (Application example 2)
[1714] 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."
[1715] In recent years, users have increasingly expressed a desire to know the ending of a story in a way that reflects their own emotional state. However, existing systems have difficulty generating endings that reflect the user's emotional state. Furthermore, the generated story endings do not necessarily match the user's emotions, resulting in a uniform user experience.
[1716] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data acquisition means for acquiring story and character information from existing data, generative model means for predicting the ending of an unfinished story based on the acquired information, formatting means for formatting the generated ending into a text format or a visual format, emotion analysis means for analyzing the user's facial expression to acquire emotion data, emotion adjustment means for adjusting the ending using the acquired emotion data, and data transmission means for providing the adjusted ending to the user's terminal. This makes it possible to provide a personalized story ending that corresponds to the user's emotional state.
[1717] "Data acquisition means" refers to a method for acquiring story and character information from existing data.
[1718] A "generative modeling method" is a method for predicting the outcome of an unfinished story based on acquired information.
[1719] A "formatter" is a method for formatting the generated conclusion into textual or visual form.
[1720] The "emotion analysis means" is a method for analyzing the user's facial expression to obtain emotion data.
[1721] "Emotion adjustment means" is a method for adjusting the ending using the acquired emotion data.
[1722] A "data transmission means" is a method for providing a tailored outcome to a user's terminal.
[1723] The "user interface means" is a method for transmitting title information of an unfinished story selected by the user to the server.
[1724] The "database acquisition means" is a method for acquiring acquired story and character information from the database.
[1725] The present invention is a system that uses emotional data to provide a personalized ending to an unfinished story in response to a user's desire to know the ending of the story. This system implements the invention through the following steps.
[1726] 1. System Overview
[1727] The system includes a terminal, a server, a data acquisition means, a generative model means, an emotion analysis means, an emotion adjustment means, a formatting means, a data transmission means, a user interface means, and a database acquisition means. A user uses the terminal to select an unfinished story title and make a request to know the subsequent ending.
[1728] 2. Data Acquisition
[1729] The server uses a database acquisition means to acquire related story data and character information based on the story title information sent by the user. The database stores existing story data and character information, and generates an ending based on this information.
[1730] 3.Emotion analysis
[1731] The device uses a camera to analyze the user's facial expressions and uses an emotion analysis means to recognize the user's emotional state. This emotion analysis means uses facial recognition technology to analyze the user's facial expressions and obtain emotional data such as joy, sadness, and excitement. Libraries such as OpenCV and TensorFlow / Keras are used for this analysis.
[1732] 4. Generative Model
[1733] The server inputs the acquired story data, character information, and emotional state information into a generative modeling means. The generative modeling means uses machine learning technology to analyze existing data and predict the ending of the unfinished story. Furthermore, an emotional adjustment means adjusts the ending according to the user's emotional state.
[1734] 5. Ending tweaks
[1735] The generated ending data is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated content is formatted into easy-to-read sentences, and in the case of the manga format, a page layout is created based on the generated scenes and dialogues, and character drawings are combined to form a manga page.
[1736] 6. Providing an ending
[1737] The formatted conclusion data is sent to the terminal using the data transmission means, and the terminal displays it to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[1738] Specific examples
[1739] 1. Example 1: Textual Conclusion and Emotional Adaptation
[1740] The user selects the unfinished story from the device UI and grants camera permission.
[1741] The terminal transmits the selected title and emotion data to the server.
[1742] The server retrieves existing story data from a database.
[1743] The device analyzes the user's facial expression and transmits to the server the strong emotion of joy.
[1744] The server generates an outcome based on the emotional state, formats it, and sends it to the terminal.
[1745] The terminal displays the generated text to the user.
[1746] 2. Example 2: Manga-style ending and emotional adaptation
[1747] The user selects the unfinished story from the device UI and grants camera permission.
[1748] The terminal transmits the selected title and emotion data to the server.
[1749] The server retrieves existing story data and character information from a database.
[1750] The device analyzes the user's facial expression and transmits to the server the strong emotion of sadness.
[1751] The server generates scenes and dialogues based on the emotional state, formats them, and sends them to the device.
[1752] The terminal displays the generated comic page to the user.
[1753] Example prompts for generative AI models
[1754] "The story is set in a fantasy genre. The hero is a hero who is forced to make an important decision during his adventure. An emotion of excitement was detected from the user's facial expression. Please generate the ending of the story."
[1755] As described above, the present invention generates an ending to an unfinished story in a manner that takes into account the user's emotions, thereby providing a personalized content experience.
[1756] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1757] Step 1:
[1758] The user selects the title of an unfinished story using the user interface of the terminal and grants permission to use the camera. The terminal receives input from the user and obtains title information of the selected story.
[1759] Step 2:
[1760] The device captures the user's facial expression along with the acquired story title information with a camera and analyzes the facial expression using an emotion analysis means. The emotion analysis means uses the OpenCV library and TensorFlow / Keras model to identify the user's emotional state (e.g., joy, sadness, excitement) from the facial expression data. The analysis results are output as emotion data.
[1761] Step 3:
[1762] The terminal transmits the title information and emotion data of the selected story to the server. Based on the story title information received from the terminal, the server uses a database acquisition means to acquire related story data and character information. The database stores existing story data and character information.
[1763] Step 4:
[1764] The server inputs the story data, character information, and emotion data acquired by the database acquisition means into the generative model means. The generative model means uses machine learning techniques (TensorFlow / Keras) to predict the ending of the unfinished story. Based on the emotion data, the ending is adjusted to adapt to the user's emotional state.
[1765] Step 5:
[1766] The ending data generated by the generative model means is formatted into a text format or a visual format using a formatting means. In the case of the text format, the generated ending is formatted into easy-to-read sentences. In the case of the visual format (manga format), a page layout is created based on the generated scenes and dialogue, and character drawings are combined to format the ending.
[1767] Step 6:
[1768] The server transmits the formatted ending data to the terminal using a data transmission means. The terminal displays the received ending data to the user. If it is in text format, it is displayed as easy-to-read sentences, and if it is in manga format, it is displayed using a page viewer.
[1769] In this way, a personalized story ending is provided that responds to the user's emotional state.
[1770] 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.
[1771] 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.
[1772] 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.
[1773] 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.
[1774] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.
[1775] 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.
[1776] 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).
[1777] 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.
[1778] 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."
[1779] 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.
[1780] 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).
[1781] 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.
[1782] 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.
[1783] 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.
[1784] 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.
[1785] 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.
[1786] 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.
[1787] 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.
[1788] 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.
[1789] 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.
[1790] 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.
[1791] The following is further disclosed regarding the above embodiment.
[1792] (Claim 1)
[1793] A data acquisition method for acquiring story and character information from existing data;
[1794] a generative modeling means for predicting the ending of an unfinished story based on the acquired information;
[1795] formatting means for formatting the generated conclusion into textual or visual form;
[1796] A system including a data transmission means for providing the outcome to a user's terminal.
[1797] (Claim 2)
[1798] 10. The system of claim 1, further comprising user interface means for transmitting title information of an unfinished story selected by the user to the server.
[1799] (Claim 3)
[1800] 10. The system of claim 1, further comprising a database retrieval means for retrieving the retrieved story and character information from a database.
[1801] (Claim 4)
[1802] 2. The system of claim 1, wherein the generative model means uses a machine learning model that statistically learns from past narrative data.
[1803] (Claim 5)
[1804] 10. The system of claim 1, further comprising display means for a user to display the formatted ending.
[1805] "Example 1"
[1806] (Claim 1)
[1807] user interface means for receiving the title of the unfinished story selected by the user;
[1808] A data acquisition method for acquiring story and character information from existing data;
[1809] a generative model means including a generative AI model for predicting the ending of an unfinished story based on the acquired information;
[1810] formatting means for formatting the generated conclusion into textual or visual form;
[1811] The system includes a data transmission means for transmitting the formatted outcome data to a user terminal.
[1812] (Claim 2)
[1813] 10. The system of claim 1, further comprising a data transmission means for transmitting title information of the unfinished story selected by the user to the server.
[1814] (Claim 3)
[1815] 10. The system of claim 1, further comprising a database retrieval means for retrieving the retrieved story and character information from a database.
[1816] "Application Example 1"
[1817] (Claim 1)
[1818] data acquisition methods to obtain story and actor data from existing information;
[1819] a generative modeling means for predicting the ending of an unfinished story based on the acquired data;
[1820] formatting means for formatting the generated conclusion into a textual or visual form;
[1821] data transmission means for providing the conclusion to the user's information terminal;
[1822] interface means for displaying a list of unfinished stories from which a user can select;
[1823] a request sending means for sending an ending generation request based on a story title selected by a user;
[1824] A system including:
[1825] (Claim 2)
[1826] 10. The system of claim 1, further comprising user interface means for transmitting title information of an unfinished story selected by the user to the server.
[1827] (Claim 3)
[1828] 10. The system of claim 1, further comprising a database retrieval means for retrieving the retrieved story and actor data from a database.
[1829] "Example 2: Combining Emotion Engines"
[1830] (Claim 1)
[1831] a data acquisition means for acquiring information from existing data;
[1832] a generative modeling means for predicting the ending of an unfinished story based on the acquired information;
[1833] formatting means for formatting the generated conclusion into textual or visual form;
[1834] data transmission means for providing the outcome to a user's terminal;
[1835] emotion engine means for recognizing an emotional state of a user;
[1836] The system includes an emotional adaptation means for adjusting the generated ending based on the emotional state of the user.
[1837] (Claim 2)
[1838] 10. The system of claim 1, further comprising user interface means for transmitting title information of an unfinished story selected by the user to the server.
[1839] (Claim 3)
[1840] 10. The system of claim 1, further comprising a database retrieval means for retrieving the retrieved information from a database.
[1841] "Application example 2 when combining emotion engines"
[1842] (Claim 1)
[1843] A data acquisition method for acquiring story and character information from existing data;
[1844] a generative modeling means for predicting the ending of an unfinished story based on the acquired information;
[1845] formatting means for formatting the generated conclusion into textual or visual form;
[1846] emotion analysis means for analyzing a user's facial expression to obtain emotion data;
[1847] emotion adjustment means for adjusting the outcome using the acquired emotion data;
[1848] A system including a data transmission means for providing a coordinated outcome to a user's terminal.
[1849] (Claim 2)
[1850] 10. The system of claim 1, further comprising user interface means for transmitting title information of an unfinished story selected by the user to the server.
[1851] (Claim 3)
[1852] 10. The system of claim 1, further comprising a database retrieval means for retrieving the retrieved story and character information from a database. [Explanation of symbols]
[1853] 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 data acquisition method for acquiring story and character information from existing data; a generative modeling means for predicting the ending of an unfinished story based on the acquired information; formatting means for formatting the generated conclusion into textual or visual form; A system including a data transmission means for providing the outcome to a user's terminal.
2. 2. The system of claim 1, further comprising user interface means for transmitting title information of an unfinished story selected by the user to the server.
3. 2. The system of claim 1, further comprising a database retrieval means for retrieving the retrieved story and character information from a database.
4. The system of claim 1 , wherein the generative model means uses a machine learning model that statistically learns from past narrative data.
5. 10. The system of claim 1, further comprising display means for a user to display the formatted ending.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A