System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting a model image; means for inputting a story summary; means for receiving and analyzing the image and story summary; means for automatically generating a continuation of a story using a generation AI; means for generating speech and narration using a text generation AI; means for suggesting a plurality of story developments; means for receiving user development selections; means for generating a final cartoon based on selected developments; and means for displaying the final cartoon to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] Currently, manga production requires high drawing skills, which means that people who have many ideas but cannot draw find it difficult to create their own works. Furthermore, there are many creators who cannot make a living as manga artists, forcing them to give up on their dreams. There is a need to improve this situation and provide a means for anyone to turn their ideas into manga. [Means for solving the problem]

[0006] The present invention allows users without drawing skills to create manga using a system that includes a means for inputting model images, a means for inputting a story outline, a means for receiving and analyzing the images and story outline, a means for automatically generating a continuation of the story using a generation AI, a means for generating dialogue and narration using a text generation AI, a means for proposing multiple story developments, a means for receiving a user's development selection, a means for generating a final manga based on the selected development, and a means for displaying the final manga to the user. Furthermore, by further including a means for presenting multiple genre options based on the story development generated by the generation AI, the system can meet a variety of user needs. Furthermore, by including a means for preprocessing the image and story outline data input by the user, the quality of the input data can be improved, ensuring the quality of the generated manga.

[0007] A "model image" is a basic visual content such as a cartoon character or background that is input by the user.

[0008] A "story outline" is a piece of text that describes the basic plot, setting, scenario, etc. of a manga.

[0009] "Means for receiving and analyzing" refers to the function of obtaining data entered by the user via the network and understanding and processing its contents.

[0010] "Generative AI" refers to algorithms or systems that use artificial intelligence technology to automatically generate the rest of a story based on input data.

[0011] "Text generation AI" refers to algorithms and systems that use artificial intelligence technology to automatically create dialogue and narration that is appropriate for the generated story.

[0012] "Means for suggesting story developments" is a function that allows the user to see multiple scenarios and developments created by the generation AI.

[0013] The "means for receiving a development selection by the user" is a function for acquiring the content selected by the user from among the proposed story developments.

[0014] The "means for generating the final manga" is a function for automatically creating manga pages and panel layouts based on the story development selected by the user.

[0015] "Means for displaying to the user" refers to a function for showing the final generated manga to the user, and is usually displayed on the user's terminal.

[0016] "Preprocessing means" is a function that prepares image data and story summary text data entered by the user into a form that is easy for AI to generate.

[0017] "Means for presenting genre options" is a function that classifies the story developments created by the generation AI into different genres (e.g. comedy, horror, survival, etc.) and presents them to the user as options. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] ---

[0040] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI to automatically generate manga based on data entered by the user. Below, we will explain the program processing of this system in natural language, with specific examples.

[0041] 1. User Input

[0042] First, the user inputs a model image and a summary of the story using a device (such as a PC or smartphone). For example, the user inputs a picture and summary of a story about a cat's adventure in a magical land.

[0043] 2. Data transmission by the terminal

[0044] Next, the device sends the input data (pictures and story outline) to the server via the network.

[0045] 3. Data reception and analysis by the server

[0046] The server receives the data sent from the device and analyzes the image and text data, including preprocessing of the image data (such as resizing and filtering) and text analysis of the story summary.

[0047] 4. Automatic story generation

[0048] The server then uses generative AI to automatically generate the rest of the story based on the model image and story outline entered by the user, for example, generating a scene in which the cat finds the magic key and the adventure begins.

[0049] 5. Automatic generation of dialogue and narration

[0050] After generating the story, the server uses text generation AI to automatically create dialogue and narration that matches the generated story. For example, it generates a scene in which a cat mutters, "What is this?"

[0051] 6. Propose multiple storylines

[0052] The server generates multiple scenarios based on the generated story, categorizes them into genres (such as comedy, horror, survival, etc.), and proposes them to the user. As specific examples, the following scenarios are proposed: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0053] 7. User selection input

[0054] The user selects the most interesting scenario from the multiple proposed scenarios, and this selection data is sent back to the server via the terminal.

[0055] 8. Generating the final manga

[0056] The server generates the final manga based on the user's selection, including details such as character movements, background, panel layout, and dialogue. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[0057] 9. Displaying the generated comic

[0058] Finally, the server transmits the final comic to the terminal, which displays it to the user, allowing the user to view the completed comic.

[0059] In this way, this system can automatically generate manga based on users' ideas, even if they have no drawing skills. This will broaden the scope of creative expression, providing a platform for self-expression for many people who previously could not participate in manga production.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The user uses a terminal to draw a model image (for example, the main character or background) or upload an existing image file, and then inputs the outline of the story and the scenario in text.

[0063] Step 2:

[0064] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[0065] Step 3:

[0066] The server receives the data sent from the device and analyzes the image data and text data. For image data, it performs preprocessing such as resizing and noise removal as necessary.

[0067] Step 4:

[0068] The server launches a generation AI that automatically generates the rest of the story based on the images and story outline entered by the user. At this time, the AI ​​analyzes the input data and determines the character's actions, scene progression, etc.

[0069] Step 5:

[0070] Based on the generated story, the server uses text generation AI to automatically generate dialogue and narration, for example, creating text to describe the words spoken by characters in the generated scenes and the scenery.

[0071] Step 6:

[0072] The server generates multiple storylines (e.g., comedy, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. The suggestions are displayed on the device as options.

[0073] Step 7:

[0074] The user selects the desired scenario from the multiple proposed developments through the terminal and transmits the selection information to the server, which then decides on the story development according to the selection.

[0075] Step 8:

[0076] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. All elements are integrated to create the final manga data.

[0077] Step 9:

[0078] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and, if necessary, make corrections or save it.

[0079] By following the above steps, users can turn their ideas into comics and enjoy multiple storylines, even if they do not have any special drawing skills.

[0080] Example 1

[0081] 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."

[0082] Conventional manga production systems require specialized skills, making it difficult for users without drawing skills to easily create manga. Furthermore, story development and dialogue generation must be done manually, resulting in a time-consuming and labor-intensive production process. Another issue is the lack of systems that automate the proposing of multiple story developments and genres.

[0083] 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.

[0084] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for preprocessing image data and text data and analyzing the data, means for generating prompt sentences, and means for generating various stories using a generation AI model based on the generated prompt sentences and analyzing them. This enables even users without drawing skills to easily create high-quality manga, significantly reducing production time and labor, and automatically proposing multiple story developments and genres.

[0085] "Means for inputting images" refers to a method by which a user provides the system with image data that will serve as a model for the cartoon.

[0086] The "means for inputting a story outline" is a method by which a user provides the system with the general storyline and theme of a manga as text data.

[0087] The "means for receiving and analyzing" refers to a method by which the server receives image data and text data sent from the user and analyzes this data.

[0088] "Generative AI" is an artificial intelligence model that automatically generates new stories and scenes based on input data.

[0089] "Text generation AI" is an artificial intelligence model that automatically generates lines and narration that correspond to generated stories and scenes.

[0090] "Means for proposing multiple story developments" refers to a method of proposing various genres and scenario developments to users based on the story generated by the generation AI.

[0091] The "means for receiving a story development selection" is a method by which the server receives the user's selection from a plurality of proposed story developments.

[0092] The "means for generating the final manga" is a method for automatically generating the final manga, including character movements, backgrounds, dialogue, etc., based on the story development selected by the user.

[0093] "Displaying means" refers to the method by which the server sends the final generated manga to the user's terminal so that the user can view it.

[0094] The "means for preprocessing image data and text data" refers to a method for preprocessing transmitted image data, such as resizing and filtering, and tokenizing text data.

[0095] The "means for generating a prompt sentence" is a method for generating a prompt sentence to give instructions to the generative AI model based on data input by the user.

[0096] "Means for generating various stories using a generative AI model and analyzing them" refers to a method for generating various story developments using a generative AI model and analyzing the results.

[0097] This invention relates to a system that allows users to efficiently create manga even if they do not have drawing skills. This system utilizes a generative AI model and a text generation AI to automatically generate manga based on data entered by the user. The program processing of this system is explained in detail below.

[0098] User Input

[0099] The user uses a device (such as a PC or smartphone) to input a model image and a summary of the story. For example, the user may input an image and a summary of the story based on the theme of "a story about a cat's adventure in a magical land." The image is provided in JPEG or PNG format, and the summary of the story is entered directly into the text box.

[0100] Data transmission by the terminal

[0101] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[0102] Data reception and analysis by the server

[0103] The server receives the data sent from the device. Image data is preprocessed by resizing and filtering. Story data is analyzed using natural language processing (NLP). Specifically, a text analysis library is used to tokenize the text and perform semantic analysis.

[0104] Auto-generation of stories

[0105] The server uses a generative AI model to automatically generate the rest of the story based on the input image and story outline. For example, it generates a scene where the cat finds a magic key and the adventure begins. This process uses the latest AI models such as GPT-4.

[0106] Automatic generation of dialogue and narration

[0107] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[0108] Multiple storyline suggestions

[0109] The server proposes multiple scenarios based on the generated story. Each scenario is classified into a specific genre and proposed to the user. For example, the server can propose the following scenarios: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0110] User selection input

[0111] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[0112] Generating the final manga

[0113] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page containing, for example, an "adventure scene in which a cat makes friends in a magical land" is automatically generated.

[0114] Display of the generated comic

[0115] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[0116] Prompt Sentence Examples

[0117] 1. "Generate a scene in which a cat finds a magic key."

[0118] 2. "Please suggest a storyline that includes a comedy element."

[0119] 3. "Generate dialogue for a scene where a cat fights a monster."

[0120] In this way, this system allows users to automatically generate manga based on their own ideas, even if they do not have drawing skills. This will broaden the scope of creative expression and provide more people with a platform for self-expression.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Processing Steps

[0123] Step 1: User Input

[0124] Users use their device to input a model image and a story summary. Images are provided in JPEG or PNG format, and the story summary is entered directly into the text box.

[0125] Input: Model image file, story summary text

[0126] Output: Image data, story data

[0127] Step 2: Send data by device

[0128] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[0129] Input: User-provided image data and story data

[0130] Output: Data sent to the server

[0131] Step 3: Data reception and analysis by the server

[0132] The server receives the data sent from the device. It performs preprocessing such as resizing and filtering on the image data. It analyzes the story data using natural language processing (NLP). Specifically, it uses a text analysis library to tokenize the text and perform semantic analysis.

[0133] Input: Image data and story data sent from the device

[0134] Output: Preprocessed image data, analyzed story data

[0135] Step 4: Auto-generate stories

[0136] The server uses a generative AI model (e.g., GPT-4) to automatically generate the rest of the story based on the input image and story outline, for example, generating a scene in which the cat finds a magic key and the adventure begins.

[0137] Input: Preprocessed image data, analyzed story data

[0138] Output: The generated continuation of the story

[0139] Step 5: Automatic generation of dialogue and narration

[0140] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[0141] Input: Generated story continuation data

[0142] Output: Generated dialogue, narration

[0143] Step 6: Propose multiple storylines

[0144] The server then proposes multiple scenarios based on the generated story. Each scenario is categorized into a specific genre and suggested to the user. For example, it suggests scenarios such as "making friends in a magical land," "fighting monsters," and "searching for mysterious items."

[0145] Input: Generated story continuation, dialogue, narration

[0146] Output: Multiple storyline scenarios

[0147] Step 7: User Selection Input

[0148] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[0149] Input: Multiple storyline scenarios

[0150] Output: User-selected data

[0151] Step 8: Generate the final comic

[0152] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page is automatically generated, including an "adventure scene in which a cat makes friends in a magical land."

[0153] Input: User-selected data

[0154] Output: The final generated cartoon

[0155] Step 9: Displaying the generated comic

[0156] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[0157] Input: The final generated comic

[0158] Output: Comic displayed on the terminal

[0159] These are the specific processing steps of the system. Through a detailed explanation of the data processed at each step, it becomes clear how the information entered by the user is processed and the final manga is generated.

[0160] (Application example 1)

[0161] 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."

[0162] The challenge is to provide a system that allows users who do not have the advanced skills required for manga creation to easily and automatically generate high-quality manga. Another challenge is to provide a mechanism that allows the generated manga to be shared immediately and to receive interaction and feedback from a wide range of users.

[0163] 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.

[0164] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, and means for displaying the final manga to the user and sharing it on an information distribution service. This enables users without manga creation skills to easily generate high-quality manga and then instantly share the manga.

[0165] A "model image" is an image that is the basis for visual elements such as cartoon characters and backgrounds specified by the user.

[0166] "Story summary" is general information about the basic plot and theme of the manga specified by the user.

[0167] "Generative AI" is artificial intelligence that automatically generates new stories and visuals based on given images and story outlines.

[0168] "Text generation AI" is an artificial intelligence that automatically creates dialogue and narration that is appropriate for the generated story.

[0169] "Multiple storylines" refers to scenarios where different developments of a story are created by the generative AI.

[0170] "User development selection" refers to the act of the user selecting the development that interests them most from among multiple scenarios provided.

[0171] The "final manga" is a manga work completed by the generation AI and text generation AI based on the plot selected by the user.

[0172] An "information distribution service" is a means for sharing the created manga with other users or publishing it on platforms such as social networking sites.

[0173] The present invention provides a system that enables users, even those without drawing skills, to easily create high-quality manga and share the manga through information distribution services. Specific embodiments of the system are described below.

[0174] First, the user accesses the system using a device (such as a smartphone or PC) and inputs a model image and a story outline. This image and story outline are then sent to the server, which then receives the image data and story outline data sent by the user.

[0175] The server then analyzes the image data, which may include resizing and filtering the image, as well as the text data of the story summary. Once the analysis is complete, the server uses generative AI to automatically generate a new story continuation based on this input data.

[0176] Next, a text generation AI is used to automatically generate dialogue and narration that matches the generated story. As a result, multiple development scenarios are created for the story. For example, the following developments may be generated: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0177] The server proposes these multiple scenarios to the user, and the user selects the scenario that interests them most. The selected data is then sent back to the server, which then automatically generates a completed manga based on the scenario selected by the user.

[0178] The generated manga is sent to the user's device and displayed. The user can then share the manga on social media or with friends. This means that even those without manga creation skills can create high-quality manga based on their own ideas and share them instantly.

[0179] Specific examples

[0180] The server performs the above process using the following hardware and software:

[0181] Hardware: Server computer, user's device (smartphone or PC)

[0182] Software: Generative AI, text generation AI, image analysis software, network communication software (e.g., Requests library)

[0183] Usage example

[0184] For example, if a user inputs the prompt "A story about a cat's adventure in a magical land" and provides a corresponding image, the generation AI will generate a scene in which the cat finds a magic key and the adventure begins, and the text generation AI will add a scene in which the cat mutters, "What is this?"

[0185] An example of this prompt is:

[0186] Prompt: "A cat (character) goes on an adventure in a magical land (context)"

[0187] Image path: "path / to / user_image.jpg"

[0188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0189] Step 1:

[0190] The user inputs a model image and a story outline using a terminal. This input data consists of an image file and text data. Consider an example where the user inputs an image and a story outline based on the theme of "a story about a cat's adventure in a magical land."

[0191] Step 2:

[0192] The device sends the input data (image files and text data of the story outline) to the server, which then sends the input data to the specified endpoint on the server via the network.

[0193] Step 3:

[0194] The server analyzes the images and story summaries received from the device. Image data is preprocessed by resizing and filtering, and text data is organized using text analysis tools. Specifically, images are resized using Python's PIL, and text is tokenized using NLTK.

[0195] Step 4:

[0196] The server uses generative AI to automatically generate the rest of the story based on the analyzed model image and the story outline. In this step, a prompt sentence is input into the generative AI model to generate the rest of the story. An example of a generated story is "A scene where a cat finds a magic key and an adventure begins."

[0197] Step 5:

[0198] The server uses a sentence generation AI to generate appropriate dialogue and narration based on the story generated by the generative AI. An example of generated dialogue is a scene in which a cat mutters, "What is this?" This step utilizes a sentence generation model such as GPT-3.

[0199] Step 6:

[0200] The server creates multiple scenarios for the generated story and presents them to the user. Using the prompt and the generated story, the server inputs each scenario into the generation AI and suggests different scenarios, such as "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0201] Step 7:

[0202] The user selects the deployment scenario that interests them most from the multiple deployment scenarios presented. This selection data is then sent back to the server via the device. The data for the selected deployment scenario is sent in JSON format or similar.

[0203] Step 8:

[0204] The server generates the final manga based on the development scenario selected by the user. Here, it integrates images and dialogue, performs paging, and generates manga-format data. The generated manga is saved as an image file for each page.

[0205] Step 9:

[0206] The server then sends the final manga data to the device, where the user can view the manga. Additionally, the server provides a link and a button to share the manga with friends or on social media via an information distribution service.

[0207] This allows users to create high-quality manga and share them instantly, even if they have no manga creation skills.

[0208] 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.

[0209] ---

[0210] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI, and also combines an emotion engine that recognizes the user's emotions, to automatically generate manga based on input data and emotion data. Below, the program processing of this system is explained in natural language, with specific examples.

[0211] 1. User Input

[0212] The user inputs a model image and a summary of the story using a device (such as a PC or smartphone). Specifically, the user inputs a picture and summary based on the theme of "a story about a cat's adventure in a magical land."

[0213] 2. Data Transmission

[0214] The device sends the user's input data (images and story summary) to a server, which then transmits the data over the Internet and stores it on the server using a secure protocol.

[0215] 3. Data Analysis

[0216] The server receives the data sent from the device and analyzes the image and text data. The image data is preprocessed as needed, such as by resizing or removing noise. The story summary text data is also preprocessed in the same way.

[0217] 4. Emotion Recognition by Emotion Engine

[0218] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device and inputs information. For example, emotional data such as whether the user is happy or sad can be extracted.

[0219] 5. Automatic story generation

[0220] The server uses the AI ​​to automatically generate the rest of the story based on the data (images and story summary) and emotional data entered by the user. For example, when generating a scene in which the cat finds the magic key and the adventure begins, if the user is having fun, a bright and cheerful development will be selected, and if the user is sad, a more moving development will be selected.

[0221] 6. Automatic generation of dialogue and narration

[0222] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, in a scene where a cat mutters, "What is this?", it generates high-energy or somber lines that match the user's emotions.

[0223] 7. Story Development Suggestion

[0224] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[0225] 8. User Selection

[0226] The user selects a desired scenario from multiple proposed scenarios through the terminal, and the selected data is sent to the server through the terminal.

[0227] 9. Generating the final manga

[0228] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, dialogue placement, etc. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[0229] 10. Display of manga

[0230] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and enjoy the work that matches their emotions.

[0231] In this way, even if the user does not have drawing skills, this system can automatically generate manga based on the user's ideas, and by incorporating an emotion engine, it can provide story development and dialogue that responds to the user's emotions, broadening the scope of creative expression and further enriching the user's experience.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] The user uses the device to draw a model image (for example, the main character or background) or upload an existing image file, and also enters the story outline and scenario in text.

[0235] Step 2:

[0236] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[0237] Step 3:

[0238] The server receives the data sent from the device and analyzes the image data and text data. For example, preprocessing such as resizing and noise removal is performed on the image data, and text cleansing is performed on the text data.

[0239] Step 4:

[0240] The device captures facial expressions and voices as the user uses the device and inputs data. The device then sends the collected facial and voice data to an emotion analysis algorithm to recognize the user's emotions.

[0241] Step 5:

[0242] The server uses an emotion engine to analyze the facial expression and voice data sent from the device and extract the user's emotional data. For example, it recognizes emotions such as happiness, sadness, and excitement from the user's facial expression and tone of voice.

[0243] Step 6:

[0244] The server uses AI to automatically generate the rest of the story based on the image, story summary, and emotional data entered by the user. For example, when generating a scene in which a cat finds a magic key and the adventure begins, if the user is excited, it will generate an action-packed story, but if the user is calm, it will generate an exploration-focused story.

[0245] Step 7:

[0246] Based on the generated story, the server uses text generation AI to create dialogue and narration. For example, in a scene where a cat says, "What is this?", it can generate a surprised or calm tone to match the user's emotions.

[0247] Step 8:

[0248] Based on the generated story and dialogue, the server generates multiple different story developments (e.g., comedy, horror, survival, etc.) using emotional data and suggests them to the user. These suggestions are displayed on the device.

[0249] Step 9:

[0250] The user selects a desired scenario from multiple proposed story developments through the terminal, and this selection information is sent to the server through the terminal.

[0251] Step 10:

[0252] The server generates the final manga based on the user's selections, including character movements, backgrounds, panel layouts, and dialogue placement. For example, it automatically generates a final manga page that details the scene where a cat makes friends in a magical land.

[0253] Step 11:

[0254] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and make corrections or save it as needed.

[0255] By following these steps, users can embody their ideas as manga and enjoy story development that matches their emotions, even if they do not have any special drawing skills.

[0256] Example 2

[0257] 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."

[0258] Conventional manga generation systems require users to have drawing skills, and it is difficult to generate content that reflects emotions. This means that users cannot get the story development or dialogue they expect, limiting the scope of creative expression.

[0259] 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.

[0260] In this invention, the server includes means for inputting model data, means for inputting a story outline, means for receiving and analyzing the data and the story outline, means for pre-processing the data, means for recognizing a user's emotions, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a sentence generation AI, means for proposing multiple story developments, means for receiving a development selection by the user, means for generating final content based on the selected development, and means for displaying the final content to the user. This makes it possible to provide story developments and dialogue that correspond to emotions without requiring the user to have drawing skills.

[0261] "Model data" refers to data that represents the original images or information in the system.

[0262] The "story summary" is text data entered by the user that describes the basic content and setting of the story.

[0263] "Preprocessing" refers to data processing such as resizing and noise removal that the system performs before analyzing the data.

[0264] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions and voice data to identify their emotional state in real time.

[0265] "Generative AI" is an artificial intelligence technology that automatically generates new stories and content based on input data.

[0266] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration that fit specific scenes and stories.

[0267] "Story development proposal" is the process in which the system presents the user with multiple story progression scenarios.

[0268] "Receiving a storyline selection" refers to the user selecting one of the proposed storylines and the system receiving that selection.

[0269] "Final content" is the completed comic or story that the system ultimately generates based on the user's input and selections.

[0270] "Means for displaying to the user" refers to the technology for transmitting the final content generated by the system to the user's terminal and making it viewable.

[0271] The present invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes a generation AI and a text generation AI, and combines it with an emotion engine that recognizes the user's emotions, and automatically generates manga based on input data and emotion data. The following describes in detail the embodiments of the present invention.

[0272] User Input

[0273] Users use a device (such as a PC or smartphone) to input model data and a story outline. The model data includes image files, and the story outline includes the basic setting of the story. For example, a user can input a theme such as "A story about a cat's adventures in a magical land."

[0274] Data transmission

[0275] The device sends the user's input data to the server, which receives and stores it using the Internet and a secure protocol (e.g., HTTPS).

[0276] Data analysis and preprocessing

[0277] The server receives the data sent from the device and analyzes the image and text data. The image data undergoes preprocessing, such as resizing and noise removal. The story summary text data is also preprocessed using natural language processing techniques to extract keywords and check grammar.

[0278] Emotion recognition by emotion engine

[0279] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device to input data. The emotion engine analyzes the user's facial expressions and voice and extracts emotional data such as whether they are happy or sad. This is done using facial recognition software.

[0280] Auto-generation of stories

[0281] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input and emotional data. For example, when generating a scene in which the cat finds a magic key and the adventure begins, if the user is enjoying themselves, a bright and cheerful development will be generated.

[0282] Automatic generation of dialogue and narration

[0283] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, a scene in which a cat mutters, "What is this?" can be generated as high-energy or somber lines that match the user's emotions.

[0284] Story development suggestions

[0285] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[0286] User Selection

[0287] The user selects the desired scenario from the proposed multiple scenarios through the terminal and sends it to the server, which then reflects this selection data in the next process.

[0288] Generating the final manga

[0289] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. For example, it automatically generates a manga page containing the scene "A cat makes friends in a magical land."

[0290] Cartoon Display

[0291] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[0292] Examples and prompts

[0293] For example, suppose a user is looking for a story about a cat's adventures in a magical land and enters the following data:

[0294] Image: Cat character illustration

[0295] Story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[0296] If the emotion engine recognizes that the person is having fun, the generative AI will generate the following continuation of the story:

[0297] "A cat finds a magic key and an adventure begins."

[0298] Text generation AI generates dialogue:

[0299] "The cat excitedly mutters, 'What is this?'"

[0300] Server proposes multiple deployments:

[0301] Gag development: "The cat meets one interesting character after another."

[0302] Adventure: "A cat overcomes challenges and searches for treasure."

[0303] Heartwarming story: "A cat meets a new friend and a friendship blossoms."

[0304] Example prompt sentence:

[0305] User-provided story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[0306] User sentiment: Enjoying it

[0307] The rest of the story to be printed:

[0308] This invention allows users without drawing skills to automatically generate manga based on their own ideas, and also utilizes an emotion engine to provide story developments and dialogue that match the emotions, thereby broadening the scope of creative expression and enriching the user experience.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1: User Input

[0311] Specific actions

[0312] The user uses a device (PC or smartphone) to input image data and a summary of the story. The user opens the device's browser or a dedicated app, uploads an image file from the input form, and writes a summary of the story in the text box. For example, the user might enter a theme such as "A story about a cat's adventures in a magical land."

[0313] Input: Image data (e.g., cat character illustration), story summary (e.g., "A cat character goes on an adventure to find lost treasure in a magical land")

[0314] Output: The user's input data is saved to the device.

[0315] Step 2: Send data

[0316] Specific actions

[0317] The device sends the user's input data to the server, which uses the Internet and a secure protocol (e.g., HTTPS). After transmission, the server receives and stores this data.

[0318] Input: User input data (image data, story outline)

[0319] Output: Data is stored on the server.

[0320] Step 3: Data analysis and preprocessing

[0321] Specific actions

[0322] The server analyzes the data received from the device. First, it performs preprocessing such as resizing and noise removal on the image data. Next, it preprocesses the text data of the story summary using natural language processing techniques. This includes extracting story keywords and checking grammar.

[0323] Input: Image data and text data on the server

[0324] Output: Preprocessed data

[0325] Step 4: Emotion Recognition with the Emotion Engine

[0326] Specific actions

[0327] The emotion engine analyzes facial expressions and voice data in real time as users input data using the device. It uses the device's camera and microphone to capture the user's facial expressions and voice and identify their emotional state (e.g., happy, sad). This analysis is performed using facial recognition software and voice analysis tools.

[0328] Input: User's facial expression data and voice data

[0329] Output: User's emotion data (e.g., having fun)

[0330] Step 5: Auto-generate stories

[0331] Specific actions

[0332] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input data and emotional data. A prompt is input into the generative AI model, which generates a scenario based on the user's emotions. For example, it outputs a fun-filled scene in which "the cat finds a magic key and the adventure begins."

[0333] Input: Preprocessed data, emotion data

[0334] Output: The generated story (e.g. "The cat finds the magic key and the adventure begins")

[0335] Step 6: Automatic generation of dialogue and narration

[0336] Specific actions

[0337] The server uses text generation AI to automatically create lines and narration that fit the generated story. Based on the generative AI model, it generates lines such as "The cat mutters 'What is this?'" that match the user's emotions.

[0338] Input: Generated stories

[0339] Output: Generated dialogue or narration (e.g., "The cat excitedly murmurs, 'What is this? It looks so interesting!'")

[0340] Step 7: Propose a storyline

[0341] Specific actions

[0342] The server generates multiple scenarios (e.g., comedy, horror, survival) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide the optimal option.

[0343] Input: Generated story, dialogue, and emotion data

[0344] Output: Proposal of multiple scenarios (e.g. comedy, adventure, emotional)

[0345] Step 8: User Selection

[0346] Specific actions

[0347] The user selects the desired scenario from the multiple proposed scenarios through the terminal. The scenario is selected on the terminal's UI interface, and the "Decide" button is clicked. The selected data is sent to the server.

[0348] Input: Proposed deployment scenario

[0349] Output: User-selected data

[0350] Step 9: Generate the final cartoon

[0351] Specific actions

[0352] The server generates the final manga based on the user's selections. It automatically designs the character movements, background, panel layout, and dialogue placement. For example, it generates a manga page containing a scene based on the selection, "A cat makes friends in a magical land."

[0353] Input: User-selected data

[0354] Output: The final generated comic page

[0355] Step 10: Displaying the comic

[0356] Specific actions

[0357] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[0358] Input: The final generated comic page

[0359] Output: Comic displayed on the device

[0360] Through these steps, this system can automatically generate manga based on a user's ideas, even if the user has no drawing skills, and can also provide story development and dialogue that matches the user's emotions.

[0361] (Application example 2)

[0362] 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."

[0363] Conventional manga creation systems do not provide story development or product recommendations that are in line with the user's emotions, making it difficult to improve the quality of the user experience. Furthermore, in physical stores, there is a lack of means to recognize customer emotions in real time and make appropriate product recommendations, making it difficult to improve customer satisfaction.

[0364] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0365] In this invention, the server includes means for inputting a model image, means for inputting a story outline, means for receiving and analyzing the image and the story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for recommending products based on the user's field, means for automatically generating storytelling related to the recommended products, and means for recognizing the user's emotions in real time, thereby enabling story developments and product recommendations that are in line with the user's emotions.

[0366] A "model image" is visual data of an object input by the user, and is the basis for the system's analysis and use.

[0367] The "story summary" is the plot and theme information of the story entered by the user, and is the information that the system uses to develop the story.

[0368] "Generative AI" refers to software that uses artificial intelligence techniques to automatically generate stories and other creative content.

[0369] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration based on input data.

[0370] "Multiple storylines" are different scenario options automatically generated by the generative AI.

[0371] "User development selection" refers to the act of the user selecting one of the proposed story developments.

[0372] "Final comic" refers to the completed comic, including the storyline selected by the user and the dialogue and narration generated by the user.

[0373] A "means for recommending products based on a user's field" is a method or technology for presenting appropriate products based on a user's interests and hobbies.

[0374] The "means for automatically generating storytelling related to a recommended product" refers to a method or technology for generating a story to convey the appeal of a recommended product.

[0375] "Means for recognizing a user's emotions in real time" refers to technology that uses a camera and microphone to analyze the user's emotional state from their facial expressions and voice.

[0376] The present invention is a system for creating manga that utilizes generation AI and text generation AI, and combines it with an emotion engine that recognizes the user's emotions in real time to improve the user experience. The system of the present invention is configured as follows.

[0377] Hardware and Software Use

[0378] Servers and devices are used as the primary hardware. In particular, smart glasses (e.g., Google Glass, Microsoft HoloLens), high-resolution cameras, and highly sensitive microphones are used for real-time emotion recognition. Facial expression recognition software (e.g., Affectiva) and voice emotion analysis software (e.g., IBM Watson Tone Analyzer) are used for emotion recognition. Generative AI models (e.g., OpenAI's GPT) and AR display libraries (e.g., Vuforia, ARKit) also play important roles.

[0379] System Details

[0380] User Input

[0381] The user inputs a model image and a summary of the story using a device (smartphone or PC). For example, they input an image and summary based on the theme of "a story about a cat's adventure in a magical land."

[0382] Data transmission and analysis

[0383] The device sends the user's input data (images and story outline) to the server, which analyzes the data and performs preprocessing such as resizing and noise removal. The story outline is also preprocessed in the same way.

[0384] Emotion recognition by emotion engine

[0385] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial and voice data and analyzes emotions in real time. Emotional data is extracted using Affectiva and IBM Watson APIs.

[0386] Automatic story generation and product recommendation

[0387] The server uses generative AI to automatically generate the rest of the story based on the data and emotional data entered by the user. It also recommends products based on the user's field and automatically generates storytelling related to the recommended products. For example, if the user is having fun, it will choose a bright and cheerful development.

[0388] Automatic generation and presentation of dialogue and narration

[0389] The server uses text generation AI to automatically create lines and narration that fit the generated story, generating high-energy or somber lines to match the user's emotions.

[0390] Generate and display the final manga

[0391] After the user selects multiple storylines, the server generates the final manga, including character movements, background details, panel layout, and dialogue placement. The generated final manga data is sent to the device, which displays it to the user.

[0392] Examples of concrete examples and prompts

[0393] In a specific scenario, when a user wears smart glasses and enters a store, the glasses analyze the user's emotions in real time and recommend products based on that. For example, if the glasses determine that the user is having fun, they will input the following prompt sentence into the generation AI:

[0394] "Generate a compelling story about Product A. For example, what kind of adventurer used this item?"

[0395] When a customer comes in front of a designated product, an automatically generated storytelling is displayed on the smart glasses display.

[0396] In this way, the present invention can realize story development and product recommendations that are in line with the user's emotions, thereby improving the quality of the user experience.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] The user uses the device to input a model image and a summary of the story. The input image and text data are acquired as the initial input for the system. Specifically, the user inputs an image and a summary based on the theme of "a story about a cat's adventure in a magical land." The input data is temporarily saved in the device.

[0400] Step 2:

[0401] The device sends the user's input data to the server, which then transmits the input data (images and story outline) over the Internet using a secure protocol, where the received data is stored.

[0402] Step 3:

[0403] The server analyzes the image and text data it receives. The image data undergoes preprocessing such as resizing and noise removal, and the text data undergoes preprocessing such as grammar checks and removal of unnecessary symbols. The preprocessed data becomes the input data for story generation.

[0404] Step 4:

[0405] The device uses a camera and microphone to capture the user's facial expressions and voice data, and sends it to the server in real time. The server uses this data to analyze the user's emotions using an emotion engine (e.g., Affectiva, IBM Watson). The analysis results are saved as the user's emotional state.

[0406] Step 5:

[0407] The server uses a generative AI model (e.g., OpenAI's GPT) to automatically generate the rest of the story based on the story summary and emotional data entered by the user. Based on the input data and emotional data, the generative AI generates the rest of the story. For example, it generates a scene in which the cat finds the magic key and the adventure begins, with a bright and fun development that matches the user's emotions.

[0408] Step 6:

[0409] The server uses text generation AI to automatically generate lines and narration that fit the generated story. Using the generated story as input, lines and narration that match the user's emotions are output. For example, a scene in which a cat mutters, "What is this?" is generated as a high-energy line.

[0410] Step 7:

[0411] The server recommends products based on the user's field. A generative AI model is used to recommend products based on sentiment data and past purchase history. The user expresses interest in the displayed products.

[0412] Step 8:

[0413] The server generates storytelling related to the recommended product. Using the recommended product and the user's emotional data as input, the generation AI is prompted with the prompt "Generate an engaging story for Product A. For example, what kind of adventurer used this item?", and the storytelling is obtained as output. The generated story is displayed on the device.

[0414] Step 9:

[0415] The terminal displays the final manga data sent from the server. The user can browse the displayed manga and enjoy the emotionally relevant story and product recommendations.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] In the smart glasses 214, 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.

[0431] 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."

[0432] ---

[0433] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI to automatically generate manga based on data entered by the user. Below, we will explain the program processing of this system in natural language, with specific examples.

[0434] 1. User Input

[0435] First, the user inputs a model image and a summary of the story using a device (such as a PC or smartphone). For example, the user inputs a picture and summary of a story about a cat's adventure in a magical land.

[0436] 2. Data transmission by the terminal

[0437] Next, the device sends the input data (pictures and story outline) to the server via the network.

[0438] 3. Data reception and analysis by the server

[0439] The server receives the data sent from the device and analyzes the image and text data, including preprocessing of the image data (such as resizing and filtering) and text analysis of the story summary.

[0440] 4. Automatic story generation

[0441] The server then uses generative AI to automatically generate the rest of the story based on the model image and story outline entered by the user, for example, generating a scene in which the cat finds the magic key and the adventure begins.

[0442] 5. Automatic generation of dialogue and narration

[0443] After generating the story, the server uses text generation AI to automatically create dialogue and narration that matches the generated story. For example, it generates a scene in which a cat mutters, "What is this?"

[0444] 6. Propose multiple storylines

[0445] The server generates multiple scenarios based on the generated story, categorizes them into genres (such as comedy, horror, survival, etc.), and proposes them to the user. As specific examples, the following scenarios are proposed: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0446] 7. User selection input

[0447] The user selects the most interesting scenario from the multiple proposed scenarios, and this selection data is sent back to the server via the terminal.

[0448] 8. Generating the final manga

[0449] The server generates the final manga based on the user's selection, including details such as character movements, background, panel layout, and dialogue. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[0450] 9. Displaying the generated comic

[0451] Finally, the server transmits the final comic to the terminal, which displays it to the user, allowing the user to view the completed comic.

[0452] In this way, this system can automatically generate manga based on users' ideas, even if they have no drawing skills. This will broaden the scope of creative expression, providing a platform for self-expression for many people who previously could not participate in manga production.

[0453] The processing flow will be explained below.

[0454] Step 1:

[0455] The user uses a terminal to draw a model image (for example, the main character or background) or upload an existing image file, and then inputs the outline of the story and the scenario in text.

[0456] Step 2:

[0457] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[0458] Step 3:

[0459] The server receives the data sent from the device and analyzes the image data and text data. For image data, it performs preprocessing such as resizing and noise removal as necessary.

[0460] Step 4:

[0461] The server launches a generation AI that automatically generates the rest of the story based on the images and story outline entered by the user. At this time, the AI ​​analyzes the input data and determines the character's actions, scene progression, etc.

[0462] Step 5:

[0463] Based on the generated story, the server uses text generation AI to automatically generate dialogue and narration, for example, creating text to describe the words spoken by characters in the generated scenes and the scenery.

[0464] Step 6:

[0465] The server generates multiple storylines (e.g., comedy, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. The suggestions are displayed on the device as options.

[0466] Step 7:

[0467] The user selects the desired scenario from the multiple proposed developments through the terminal and transmits the selection information to the server, which then decides on the story development according to the selection.

[0468] Step 8:

[0469] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. All elements are integrated to create the final manga data.

[0470] Step 9:

[0471] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and, if necessary, make corrections or save it.

[0472] By following the above steps, users can turn their ideas into comics and enjoy multiple storylines, even if they do not have any special drawing skills.

[0473] Example 1

[0474] 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."

[0475] Conventional manga production systems require specialized skills, making it difficult for users without drawing skills to easily create manga. Furthermore, story development and dialogue generation must be done manually, resulting in a time-consuming and labor-intensive production process. Another issue is the lack of systems that automate the proposing of multiple story developments and genres.

[0476] 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.

[0477] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for preprocessing image data and text data and analyzing the data, means for generating prompt sentences, and means for generating various stories using a generation AI model based on the generated prompt sentences and analyzing them. This enables even users without drawing skills to easily create high-quality manga, significantly reducing production time and labor, and automatically proposing multiple story developments and genres.

[0478] "Means for inputting images" refers to a method by which a user provides the system with image data that will serve as a model for the cartoon.

[0479] The "means for inputting a story outline" is a method by which a user provides the system with the general storyline and theme of a manga as text data.

[0480] The "means for receiving and analyzing" refers to a method by which the server receives image data and text data sent from the user and analyzes this data.

[0481] "Generative AI" is an artificial intelligence model that automatically generates new stories and scenes based on input data.

[0482] "Text generation AI" is an artificial intelligence model that automatically generates lines and narration that correspond to generated stories and scenes.

[0483] "Means for proposing multiple story developments" refers to a method of proposing various genres and scenario developments to users based on the story generated by the generation AI.

[0484] The "means for receiving a story development selection" is a method by which the server receives the user's selection from a plurality of proposed story developments.

[0485] The "means for generating the final manga" is a method for automatically generating the final manga, including character movements, backgrounds, dialogue, etc., based on the story development selected by the user.

[0486] "Displaying means" refers to the method by which the server sends the final generated manga to the user's terminal so that the user can view it.

[0487] The "means for preprocessing image data and text data" refers to a method for preprocessing transmitted image data, such as resizing and filtering, and tokenizing text data.

[0488] The "means for generating a prompt sentence" is a method for generating a prompt sentence to give instructions to the generative AI model based on data input by the user.

[0489] "Means for generating various stories using a generative AI model and analyzing them" refers to a method for generating various story developments using a generative AI model and analyzing the results.

[0490] This invention relates to a system that allows users to efficiently create manga even if they do not have drawing skills. This system utilizes a generative AI model and a text generation AI to automatically generate manga based on data entered by the user. The program processing of this system is explained in detail below.

[0491] User Input

[0492] The user uses a device (such as a PC or smartphone) to input a model image and a summary of the story. For example, the user may input an image and a summary of the story based on the theme of "a story about a cat's adventure in a magical land." The image is provided in JPEG or PNG format, and the summary of the story is entered directly into the text box.

[0493] Data transmission by the terminal

[0494] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[0495] Data reception and analysis by the server

[0496] The server receives the data sent from the device. Image data is preprocessed by resizing and filtering. Story data is analyzed using natural language processing (NLP). Specifically, a text analysis library is used to tokenize the text and perform semantic analysis.

[0497] Auto-generation of stories

[0498] The server uses a generative AI model to automatically generate the rest of the story based on the input image and story outline. For example, it generates a scene where the cat finds a magic key and the adventure begins. This process uses the latest AI models such as GPT-4.

[0499] Automatic generation of dialogue and narration

[0500] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[0501] Multiple storyline suggestions

[0502] The server proposes multiple scenarios based on the generated story. Each scenario is classified into a specific genre and proposed to the user. For example, the server can propose the following scenarios: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0503] User selection input

[0504] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[0505] Generating the final manga

[0506] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page containing, for example, an "adventure scene in which a cat makes friends in a magical land" is automatically generated.

[0507] Display of the generated comic

[0508] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[0509] Prompt Sentence Examples

[0510] 1. "Generate a scene in which a cat finds a magic key."

[0511] 2. "Please suggest a storyline that includes a comedy element."

[0512] 3. "Generate dialogue for a scene where a cat fights a monster."

[0513] In this way, this system allows users to automatically generate manga based on their own ideas, even if they do not have drawing skills. This will broaden the scope of creative expression and provide more people with a platform for self-expression.

[0514] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0515] Processing Steps

[0516] Step 1: User Input

[0517] Users use their device to input a model image and a story summary. Images are provided in JPEG or PNG format, and the story summary is entered directly into the text box.

[0518] Input: Model image file, story summary text

[0519] Output: Image data, story data

[0520] Step 2: Send data by device

[0521] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[0522] Input: User-provided image data and story data

[0523] Output: Data sent to the server

[0524] Step 3: Data reception and analysis by the server

[0525] The server receives the data sent from the device. It performs preprocessing such as resizing and filtering on the image data. It analyzes the story data using natural language processing (NLP). Specifically, it uses a text analysis library to tokenize the text and perform semantic analysis.

[0526] Input: Image data and story data sent from the device

[0527] Output: Preprocessed image data, analyzed story data

[0528] Step 4: Auto-generate stories

[0529] The server uses a generative AI model (e.g., GPT-4) to automatically generate the rest of the story based on the input image and story outline, for example, generating a scene in which the cat finds a magic key and the adventure begins.

[0530] Input: Preprocessed image data, analyzed story data

[0531] Output: The generated continuation of the story

[0532] Step 5: Automatic generation of dialogue and narration

[0533] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[0534] Input: Generated story continuation data

[0535] Output: Generated dialogue, narration

[0536] Step 6: Propose multiple storylines

[0537] The server then proposes multiple scenarios based on the generated story. Each scenario is categorized into a specific genre and suggested to the user. For example, it suggests scenarios such as "making friends in a magical land," "fighting monsters," and "searching for mysterious items."

[0538] Input: Generated story continuation, dialogue, narration

[0539] Output: Multiple storyline scenarios

[0540] Step 7: User Selection Input

[0541] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[0542] Input: Multiple storyline scenarios

[0543] Output: User-selected data

[0544] Step 8: Generate the final comic

[0545] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page is automatically generated, including an "adventure scene in which a cat makes friends in a magical land."

[0546] Input: User-selected data

[0547] Output: The final generated cartoon

[0548] Step 9: Displaying the generated comic

[0549] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[0550] Input: The final generated comic

[0551] Output: Comic displayed on the terminal

[0552] These are the specific processing steps of the system. Through a detailed explanation of the data processed at each step, it becomes clear how the information entered by the user is processed and the final manga is generated.

[0553] (Application example 1)

[0554] 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."

[0555] The challenge is to provide a system that allows users who do not have the advanced skills required for manga creation to easily and automatically generate high-quality manga. Another challenge is to provide a mechanism that allows the generated manga to be shared immediately and to receive interaction and feedback from a wide range of users.

[0556] 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.

[0557] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, and means for displaying the final manga to the user and sharing it on an information distribution service. This enables users without manga creation skills to easily generate high-quality manga and then instantly share the manga.

[0558] A "model image" is an image that is the basis for visual elements such as cartoon characters and backgrounds specified by the user.

[0559] "Story summary" is general information about the basic plot and theme of the manga specified by the user.

[0560] "Generative AI" is artificial intelligence that automatically generates new stories and visuals based on given images and story outlines.

[0561] "Text generation AI" is an artificial intelligence that automatically creates dialogue and narration that is appropriate for the generated story.

[0562] "Multiple storylines" refers to scenarios where different developments of a story are created by the generative AI.

[0563] "User development selection" refers to the act of the user selecting the development that interests them most from among multiple scenarios provided.

[0564] The "final manga" is a manga work completed by the generation AI and text generation AI based on the plot selected by the user.

[0565] An "information distribution service" is a means for sharing the created manga with other users or publishing it on platforms such as social networking sites.

[0566] The present invention provides a system that enables users, even those without drawing skills, to easily create high-quality manga and share the manga through information distribution services. Specific embodiments of the system are described below.

[0567] First, the user accesses the system using a device (such as a smartphone or PC) and inputs a model image and a story outline. This image and story outline are then sent to the server, which then receives the image data and story outline data sent by the user.

[0568] The server then analyzes the image data, which may include resizing and filtering the image, as well as the text data of the story summary. Once the analysis is complete, the server uses generative AI to automatically generate a new story continuation based on this input data.

[0569] Next, a text generation AI is used to automatically generate dialogue and narration that matches the generated story. As a result, multiple development scenarios are created for the story. For example, the following developments may be generated: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0570] The server proposes these multiple scenarios to the user, and the user selects the scenario that interests them most. The selected data is then sent back to the server, which then automatically generates a completed manga based on the scenario selected by the user.

[0571] The generated manga is sent to the user's device and displayed. The user can then share the manga on social media or with friends. This means that even those without manga creation skills can create high-quality manga based on their own ideas and share them instantly.

[0572] Specific examples

[0573] The server performs the above process using the following hardware and software:

[0574] Hardware: Server computer, user's device (smartphone or PC)

[0575] Software: Generative AI, text generation AI, image analysis software, network communication software (e.g., Requests library)

[0576] Usage example

[0577] For example, if a user inputs the prompt "A story about a cat's adventure in a magical land" and provides a corresponding image, the generation AI will generate a scene in which the cat finds a magic key and the adventure begins, and the text generation AI will add a scene in which the cat mutters, "What is this?"

[0578] An example of this prompt is:

[0579] Prompt: "A cat (character) goes on an adventure in a magical land (context)"

[0580] Image path: "path / to / user_image.jpg"

[0581] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0582] Step 1:

[0583] The user inputs a model image and a story outline using a terminal. This input data consists of an image file and text data. Consider an example where the user inputs an image and a story outline based on the theme of "a story about a cat's adventure in a magical land."

[0584] Step 2:

[0585] The device sends the input data (image files and text data of the story outline) to the server, which then sends the input data to the specified endpoint on the server via the network.

[0586] Step 3:

[0587] The server analyzes the images and story summaries received from the device. Image data is preprocessed by resizing and filtering, and text data is organized using text analysis tools. Specifically, images are resized using Python's PIL, and text is tokenized using NLTK.

[0588] Step 4:

[0589] The server uses generative AI to automatically generate the rest of the story based on the analyzed model image and the story outline. In this step, a prompt sentence is input into the generative AI model to generate the rest of the story. An example of a generated story is "A scene where a cat finds a magic key and an adventure begins."

[0590] Step 5:

[0591] The server uses a sentence generation AI to generate appropriate dialogue and narration based on the story generated by the generative AI. An example of generated dialogue is a scene in which a cat mutters, "What is this?" This step utilizes a sentence generation model such as GPT-3.

[0592] Step 6:

[0593] The server creates multiple scenarios for the generated story and presents them to the user. Using the prompt and the generated story, the server inputs each scenario into the generation AI and suggests different scenarios, such as "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0594] Step 7:

[0595] The user selects the deployment scenario that interests them most from the multiple deployment scenarios presented. This selection data is then sent back to the server via the device. The data for the selected deployment scenario is sent in JSON format or similar.

[0596] Step 8:

[0597] The server generates the final manga based on the development scenario selected by the user. Here, it integrates images and dialogue, performs paging, and generates manga-format data. The generated manga is saved as an image file for each page.

[0598] Step 9:

[0599] The server then sends the final manga data to the device, where the user can view the manga. Additionally, the server provides a link and a button to share the manga with friends or on social media via an information distribution service.

[0600] This allows users to create high-quality manga and share them instantly, even if they have no manga creation skills.

[0601] 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.

[0602] ---

[0603] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI, and also combines an emotion engine that recognizes the user's emotions, to automatically generate manga based on input data and emotion data. Below, the program processing of this system is explained in natural language, with specific examples.

[0604] 1. User Input

[0605] The user inputs a model image and a summary of the story using a device (such as a PC or smartphone). Specifically, the user inputs a picture and summary based on the theme of "a story about a cat's adventure in a magical land."

[0606] 2. Data Transmission

[0607] The device sends the user's input data (images and story summary) to a server, which then transmits the data over the Internet and stores it on the server using a secure protocol.

[0608] 3. Data Analysis

[0609] The server receives the data sent from the device and analyzes the image and text data. The image data is preprocessed as needed, such as by resizing or removing noise. The story summary text data is also preprocessed in the same way.

[0610] 4. Emotion Recognition by Emotion Engine

[0611] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device and inputs information. For example, emotional data such as whether the user is happy or sad can be extracted.

[0612] 5. Automatic story generation

[0613] The server uses the AI ​​to automatically generate the rest of the story based on the data (images and story summary) and emotional data entered by the user. For example, when generating a scene in which the cat finds the magic key and the adventure begins, if the user is having fun, a bright and cheerful development will be selected, and if the user is sad, a more moving development will be selected.

[0614] 6. Automatic generation of dialogue and narration

[0615] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, in a scene where a cat mutters, "What is this?", it generates high-energy or somber lines that match the user's emotions.

[0616] 7. Story Development Suggestion

[0617] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[0618] 8. User Selection

[0619] The user selects a desired scenario from multiple proposed scenarios through the terminal, and the selected data is sent to the server through the terminal.

[0620] 9. Generating the final manga

[0621] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, dialogue placement, etc. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[0622] 10. Display of manga

[0623] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and enjoy the work that matches their emotions.

[0624] In this way, even if the user does not have drawing skills, this system can automatically generate manga based on the user's ideas, and by incorporating an emotion engine, it can provide story development and dialogue that responds to the user's emotions, broadening the scope of creative expression and further enriching the user's experience.

[0625] The processing flow will be explained below.

[0626] Step 1:

[0627] The user uses the device to draw a model image (for example, the main character or background) or upload an existing image file, and also enters the story outline and scenario in text.

[0628] Step 2:

[0629] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[0630] Step 3:

[0631] The server receives the data sent from the device and analyzes the image data and text data. For example, preprocessing such as resizing and noise removal is performed on the image data, and text cleansing is performed on the text data.

[0632] Step 4:

[0633] The device captures facial expressions and voices as the user uses the device and inputs data. The device then sends the collected facial and voice data to an emotion analysis algorithm to recognize the user's emotions.

[0634] Step 5:

[0635] The server uses an emotion engine to analyze the facial expression and voice data sent from the device and extract the user's emotional data. For example, it recognizes emotions such as happiness, sadness, and excitement from the user's facial expression and tone of voice.

[0636] Step 6:

[0637] The server uses AI to automatically generate the rest of the story based on the image, story summary, and emotional data entered by the user. For example, when generating a scene in which a cat finds a magic key and the adventure begins, if the user is excited, it will generate an action-packed story, but if the user is calm, it will generate an exploration-focused story.

[0638] Step 7:

[0639] Based on the generated story, the server uses text generation AI to create dialogue and narration. For example, in a scene where a cat says, "What is this?", it can generate a surprised or calm tone to match the user's emotions.

[0640] Step 8:

[0641] Based on the generated story and dialogue, the server generates multiple different story developments (e.g., comedy, horror, survival, etc.) using emotional data and suggests them to the user. These suggestions are displayed on the device.

[0642] Step 9:

[0643] The user selects a desired scenario from multiple proposed story developments through the terminal, and this selection information is sent to the server through the terminal.

[0644] Step 10:

[0645] The server generates the final manga based on the user's selections, including character movements, backgrounds, panel layouts, and dialogue placement. For example, it automatically generates a final manga page that details the scene where a cat makes friends in a magical land.

[0646] Step 11:

[0647] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and make corrections or save it as needed.

[0648] By following these steps, users can embody their ideas as manga and enjoy story development that matches their emotions, even if they do not have any special drawing skills.

[0649] Example 2

[0650] 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."

[0651] Conventional manga generation systems require users to have drawing skills, and it is difficult to generate content that reflects emotions. This means that users cannot get the story development or dialogue they expect, limiting the scope of creative expression.

[0652] 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.

[0653] In this invention, the server includes means for inputting model data, means for inputting a story outline, means for receiving and analyzing the data and the story outline, means for pre-processing the data, means for recognizing a user's emotions, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a sentence generation AI, means for proposing multiple story developments, means for receiving a development selection by the user, means for generating final content based on the selected development, and means for displaying the final content to the user. This makes it possible to provide story developments and dialogue that correspond to emotions without requiring the user to have drawing skills.

[0654] "Model data" refers to data that represents the original images or information in the system.

[0655] The "story summary" is text data entered by the user that describes the basic content and setting of the story.

[0656] "Preprocessing" refers to data processing such as resizing and noise removal that the system performs before analyzing the data.

[0657] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions and voice data to identify their emotional state in real time.

[0658] "Generative AI" is an artificial intelligence technology that automatically generates new stories and content based on input data.

[0659] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration that fit specific scenes and stories.

[0660] "Story development proposal" is the process in which the system presents the user with multiple story progression scenarios.

[0661] "Receiving a storyline selection" refers to the user selecting one of the proposed storylines and the system receiving that selection.

[0662] "Final content" is the completed comic or story that the system ultimately generates based on the user's input and selections.

[0663] "Means for displaying to the user" refers to the technology for transmitting the final content generated by the system to the user's terminal and making it viewable.

[0664] The present invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes a generation AI and a text generation AI, and combines it with an emotion engine that recognizes the user's emotions, and automatically generates manga based on input data and emotion data. The following describes in detail the embodiments of the present invention.

[0665] User Input

[0666] Users use a device (such as a PC or smartphone) to input model data and a story outline. The model data includes image files, and the story outline includes the basic setting of the story. For example, a user can input a theme such as "A story about a cat's adventures in a magical land."

[0667] Data transmission

[0668] The device sends the user's input data to the server, which receives and stores it using the Internet and a secure protocol (e.g., HTTPS).

[0669] Data analysis and preprocessing

[0670] The server receives the data sent from the device and analyzes the image and text data. The image data undergoes preprocessing, such as resizing and noise removal. The story summary text data is also preprocessed using natural language processing techniques to extract keywords and check grammar.

[0671] Emotion recognition by emotion engine

[0672] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device to input data. The emotion engine analyzes the user's facial expressions and voice and extracts emotional data such as whether they are happy or sad. This is done using facial recognition software.

[0673] Auto-generation of stories

[0674] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input and emotional data. For example, when generating a scene in which the cat finds a magic key and the adventure begins, if the user is enjoying themselves, a bright and cheerful development will be generated.

[0675] Automatic generation of dialogue and narration

[0676] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, a scene in which a cat mutters, "What is this?" can be generated as high-energy or somber lines that match the user's emotions.

[0677] Story development suggestions

[0678] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[0679] User Selection

[0680] The user selects the desired scenario from the proposed multiple scenarios through the terminal and sends it to the server, which then reflects this selection data in the next process.

[0681] Generating the final manga

[0682] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. For example, it automatically generates a manga page containing the scene "A cat makes friends in a magical land."

[0683] Cartoon Display

[0684] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[0685] Examples and prompts

[0686] For example, suppose a user is looking for a story about a cat's adventures in a magical land and enters the following data:

[0687] Image: Cat character illustration

[0688] Story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[0689] If the emotion engine recognizes that the person is having fun, the generative AI will generate the following continuation of the story:

[0690] "A cat finds a magic key and an adventure begins."

[0691] Text generation AI generates dialogue:

[0692] "The cat excitedly mutters, 'What is this?'"

[0693] Server proposes multiple deployments:

[0694] Gag development: "The cat meets one interesting character after another."

[0695] Adventure: "A cat overcomes challenges and searches for treasure."

[0696] Heartwarming story: "A cat meets a new friend and a friendship blossoms."

[0697] Example prompt sentence:

[0698] User-provided story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[0699] User sentiment: Enjoying it

[0700] The rest of the story to be printed:

[0701] This invention allows users without drawing skills to automatically generate manga based on their own ideas, and also utilizes an emotion engine to provide story developments and dialogue that match the emotions, thereby broadening the scope of creative expression and enriching the user experience.

[0702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0703] Step 1: User Input

[0704] Specific actions

[0705] The user uses a device (PC or smartphone) to input image data and a summary of the story. The user opens the device's browser or a dedicated app, uploads an image file from the input form, and writes a summary of the story in the text box. For example, the user might enter a theme such as "A story about a cat's adventures in a magical land."

[0706] Input: Image data (e.g., cat character illustration), story summary (e.g., "A cat character goes on an adventure to find lost treasure in a magical land")

[0707] Output: The user's input data is saved to the device.

[0708] Step 2: Send data

[0709] Specific actions

[0710] The device sends the user's input data to the server, which uses the Internet and a secure protocol (e.g., HTTPS). After transmission, the server receives and stores this data.

[0711] Input: User input data (image data, story outline)

[0712] Output: Data is stored on the server.

[0713] Step 3: Data analysis and preprocessing

[0714] Specific actions

[0715] The server analyzes the data received from the device. First, it performs preprocessing such as resizing and noise removal on the image data. Next, it preprocesses the text data of the story summary using natural language processing techniques. This includes extracting story keywords and checking grammar.

[0716] Input: Image data and text data on the server

[0717] Output: Preprocessed data

[0718] Step 4: Emotion Recognition with the Emotion Engine

[0719] Specific actions

[0720] The emotion engine analyzes facial expressions and voice data in real time as users input data using the device. It uses the device's camera and microphone to capture the user's facial expressions and voice and identify their emotional state (e.g., happy, sad). This analysis is performed using facial recognition software and voice analysis tools.

[0721] Input: User's facial expression data and voice data

[0722] Output: User's emotion data (e.g., having fun)

[0723] Step 5: Auto-generate stories

[0724] Specific actions

[0725] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input data and emotional data. A prompt is input into the generative AI model, which generates a scenario based on the user's emotions. For example, it outputs a fun-filled scene in which "the cat finds a magic key and the adventure begins."

[0726] Input: Preprocessed data, emotion data

[0727] Output: The generated story (e.g. "The cat finds the magic key and the adventure begins")

[0728] Step 6: Automatic generation of dialogue and narration

[0729] Specific actions

[0730] The server uses text generation AI to automatically create lines and narration that fit the generated story. Based on the generative AI model, it generates lines such as "The cat mutters 'What is this?'" that match the user's emotions.

[0731] Input: Generated stories

[0732] Output: Generated dialogue or narration (e.g., "The cat excitedly murmurs, 'What is this? It looks so interesting!'")

[0733] Step 7: Propose a storyline

[0734] Specific actions

[0735] The server generates multiple scenarios (e.g., comedy, horror, survival) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide the optimal option.

[0736] Input: Generated story, dialogue, and emotion data

[0737] Output: Proposal of multiple scenarios (e.g. comedy, adventure, emotional)

[0738] Step 8: User Selection

[0739] Specific actions

[0740] The user selects the desired scenario from the multiple proposed scenarios through the terminal. The scenario is selected on the terminal's UI interface, and the "Decide" button is clicked. The selected data is sent to the server.

[0741] Input: Proposed deployment scenario

[0742] Output: User-selected data

[0743] Step 9: Generate the final cartoon

[0744] Specific actions

[0745] The server generates the final manga based on the user's selections. It automatically designs the character movements, background, panel layout, and dialogue placement. For example, it generates a manga page containing a scene based on the selection, "A cat makes friends in a magical land."

[0746] Input: User-selected data

[0747] Output: The final generated comic page

[0748] Step 10: Displaying the comic

[0749] Specific actions

[0750] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[0751] Input: The final generated comic page

[0752] Output: Comic displayed on the device

[0753] Through these steps, this system can automatically generate manga based on a user's ideas, even if the user has no drawing skills, and can also provide story development and dialogue that matches the user's emotions.

[0754] (Application example 2)

[0755] 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."

[0756] Conventional manga creation systems do not provide story development or product recommendations that are in line with the user's emotions, making it difficult to improve the quality of the user experience. Furthermore, in physical stores, there is a lack of means to recognize customer emotions in real time and make appropriate product recommendations, making it difficult to improve customer satisfaction.

[0757] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0758] In this invention, the server includes means for inputting a model image, means for inputting a story outline, means for receiving and analyzing the image and the story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for recommending products based on the user's field, means for automatically generating storytelling related to the recommended products, and means for recognizing the user's emotions in real time, thereby enabling story developments and product recommendations that are in line with the user's emotions.

[0759] A "model image" is visual data of an object input by the user, and is the basis for the system's analysis and use.

[0760] The "story summary" is the plot and theme information of the story entered by the user, and is the information that the system uses to develop the story.

[0761] "Generative AI" refers to software that uses artificial intelligence techniques to automatically generate stories and other creative content.

[0762] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration based on input data.

[0763] "Multiple storylines" are different scenario options automatically generated by the generative AI.

[0764] "User development selection" refers to the act of the user selecting one of the proposed story developments.

[0765] "Final comic" refers to the completed comic, including the storyline selected by the user and the dialogue and narration generated by the user.

[0766] A "means for recommending products based on a user's field" is a method or technology for presenting appropriate products based on a user's interests and hobbies.

[0767] The "means for automatically generating storytelling related to a recommended product" refers to a method or technology for generating a story to convey the appeal of a recommended product.

[0768] "Means for recognizing a user's emotions in real time" refers to technology that uses a camera and microphone to analyze the user's emotional state from their facial expressions and voice.

[0769] The present invention is a system for creating manga that utilizes generation AI and text generation AI, and combines it with an emotion engine that recognizes the user's emotions in real time to improve the user experience. The system of the present invention is configured as follows.

[0770] Hardware and Software Use

[0771] Servers and devices are used as the primary hardware. In particular, smart glasses (e.g., Google Glass, Microsoft HoloLens), high-resolution cameras, and highly sensitive microphones are used for real-time emotion recognition. Facial expression recognition software (e.g., Affectiva) and voice emotion analysis software (e.g., IBM Watson Tone Analyzer) are used for emotion recognition. Generative AI models (e.g., OpenAI's GPT) and AR display libraries (e.g., Vuforia, ARKit) also play important roles.

[0772] System Details

[0773] User Input

[0774] The user inputs a model image and a summary of the story using a device (smartphone or PC). For example, they input an image and summary based on the theme of "a story about a cat's adventure in a magical land."

[0775] Data transmission and analysis

[0776] The device sends the user's input data (images and story outline) to the server, which analyzes the data and performs preprocessing such as resizing and noise removal. The story outline is also preprocessed in the same way.

[0777] Emotion recognition by emotion engine

[0778] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial and voice data and analyzes emotions in real time. Emotional data is extracted using Affectiva and IBM Watson APIs.

[0779] Automatic story generation and product recommendation

[0780] The server uses generative AI to automatically generate the rest of the story based on the data and emotional data entered by the user. It also recommends products based on the user's field and automatically generates storytelling related to the recommended products. For example, if the user is having fun, it will choose a bright and cheerful development.

[0781] Automatic generation and presentation of dialogue and narration

[0782] The server uses text generation AI to automatically create lines and narration that fit the generated story, generating high-energy or somber lines to match the user's emotions.

[0783] Generate and display the final manga

[0784] After the user selects multiple storylines, the server generates the final manga, including character movements, background details, panel layout, and dialogue placement. The generated final manga data is sent to the device, which displays it to the user.

[0785] Examples of concrete examples and prompts

[0786] In a specific scenario, when a user wears smart glasses and enters a store, the glasses analyze the user's emotions in real time and recommend products based on that. For example, if the glasses determine that the user is having fun, they will input the following prompt sentence into the generation AI:

[0787] "Generate a compelling story about Product A. For example, what kind of adventurer used this item?"

[0788] When a customer comes in front of a designated product, an automatically generated storytelling is displayed on the smart glasses display.

[0789] In this way, the present invention can realize story development and product recommendations that are in line with the user's emotions, thereby improving the quality of the user experience.

[0790] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0791] Step 1:

[0792] The user uses the device to input a model image and a summary of the story. The input image and text data are acquired as the initial input for the system. Specifically, the user inputs an image and a summary based on the theme of "a story about a cat's adventure in a magical land." The input data is temporarily saved in the device.

[0793] Step 2:

[0794] The device sends the user's input data to the server, which then transmits the input data (images and story outline) over the Internet using a secure protocol, where the received data is stored.

[0795] Step 3:

[0796] The server analyzes the image and text data it receives. The image data undergoes preprocessing such as resizing and noise removal, and the text data undergoes preprocessing such as grammar checks and removal of unnecessary symbols. The preprocessed data becomes the input data for story generation.

[0797] Step 4:

[0798] The device uses a camera and microphone to capture the user's facial expressions and voice data, and sends it to the server in real time. The server uses this data to analyze the user's emotions using an emotion engine (e.g., Affectiva, IBM Watson). The analysis results are saved as the user's emotional state.

[0799] Step 5:

[0800] The server uses a generative AI model (e.g., OpenAI's GPT) to automatically generate the rest of the story based on the story summary and emotional data entered by the user. Based on the input data and emotional data, the generative AI generates the rest of the story. For example, it generates a scene in which the cat finds the magic key and the adventure begins, with a bright and fun development that matches the user's emotions.

[0801] Step 6:

[0802] The server uses text generation AI to automatically generate lines and narration that fit the generated story. Using the generated story as input, lines and narration that match the user's emotions are output. For example, a scene in which a cat mutters, "What is this?" is generated as a high-energy line.

[0803] Step 7:

[0804] The server recommends products based on the user's field. A generative AI model is used to recommend products based on sentiment data and past purchase history. The user expresses interest in the displayed products.

[0805] Step 8:

[0806] The server generates storytelling related to the recommended product. Using the recommended product and the user's emotional data as input, the generation AI is prompted with the prompt "Generate an engaging story for Product A. For example, what kind of adventurer used this item?", and the storytelling is obtained as output. The generated story is displayed on the device.

[0807] Step 9:

[0808] The terminal displays the final manga data sent from the server. The user can browse the displayed manga and enjoy the emotionally relevant story and product recommendations.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] [Third embodiment]

[0813] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0814] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0815] 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).

[0816] 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.

[0817] 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.

[0818] 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).

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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."

[0825] ---

[0826] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI to automatically generate manga based on data entered by the user. Below, we will explain the program processing of this system in natural language, with specific examples.

[0827] 1. User Input

[0828] First, the user inputs a model image and a summary of the story using a device (such as a PC or smartphone). For example, the user inputs a picture and summary of a story about a cat's adventure in a magical land.

[0829] 2. Data transmission by the terminal

[0830] Next, the device sends the input data (pictures and story outline) to the server via the network.

[0831] 3. Data reception and analysis by the server

[0832] The server receives the data sent from the device and analyzes the image and text data, including preprocessing of the image data (such as resizing and filtering) and text analysis of the story summary.

[0833] 4. Automatic story generation

[0834] The server then uses generative AI to automatically generate the rest of the story based on the model image and story outline entered by the user, for example, generating a scene in which the cat finds the magic key and the adventure begins.

[0835] 5. Automatic generation of dialogue and narration

[0836] After generating the story, the server uses text generation AI to automatically create dialogue and narration that matches the generated story. For example, it generates a scene in which a cat mutters, "What is this?"

[0837] 6. Propose multiple storylines

[0838] The server generates multiple scenarios based on the generated story, categorizes them into genres (such as comedy, horror, survival, etc.), and proposes them to the user. As specific examples, the following scenarios are proposed: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0839] 7. User selection input

[0840] The user selects the most interesting scenario from the multiple proposed scenarios, and this selection data is sent back to the server via the terminal.

[0841] 8. Generating the final manga

[0842] The server generates the final manga based on the user's selection, including details such as character movements, background, panel layout, and dialogue. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[0843] 9. Displaying the generated comic

[0844] Finally, the server transmits the final comic to the terminal, which displays it to the user, allowing the user to view the completed comic.

[0845] In this way, this system can automatically generate manga based on users' ideas, even if they have no drawing skills. This will broaden the scope of creative expression, providing a platform for self-expression for many people who previously could not participate in manga production.

[0846] The processing flow will be explained below.

[0847] Step 1:

[0848] The user uses a terminal to draw a model image (for example, the main character or background) or upload an existing image file, and then inputs the outline of the story and the scenario in text.

[0849] Step 2:

[0850] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[0851] Step 3:

[0852] The server receives the data sent from the device and analyzes the image data and text data. For image data, it performs preprocessing such as resizing and noise removal as necessary.

[0853] Step 4:

[0854] The server launches a generation AI that automatically generates the rest of the story based on the images and story outline entered by the user. At this time, the AI ​​analyzes the input data and determines the character's actions, scene progression, etc.

[0855] Step 5:

[0856] Based on the generated story, the server uses text generation AI to automatically generate dialogue and narration, for example, creating text to describe the words spoken by characters in the generated scenes and the scenery.

[0857] Step 6:

[0858] The server generates multiple storylines (e.g., comedy, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. The suggestions are displayed on the device as options.

[0859] Step 7:

[0860] The user selects the desired scenario from the multiple proposed developments through the terminal and transmits the selection information to the server, which then decides on the story development according to the selection.

[0861] Step 8:

[0862] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. All elements are integrated to create the final manga data.

[0863] Step 9:

[0864] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and, if necessary, make corrections or save it.

[0865] By following the above steps, users can turn their ideas into comics and enjoy multiple storylines, even if they do not have any special drawing skills.

[0866] Example 1

[0867] 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."

[0868] Conventional manga production systems require specialized skills, making it difficult for users without drawing skills to easily create manga. Furthermore, story development and dialogue generation must be done manually, resulting in a time-consuming and labor-intensive production process. Another issue is the lack of systems that automate the proposing of multiple story developments and genres.

[0869] 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.

[0870] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for preprocessing image data and text data and analyzing the data, means for generating prompt sentences, and means for generating various stories using a generation AI model based on the generated prompt sentences and analyzing them. This enables even users without drawing skills to easily create high-quality manga, significantly reducing production time and labor, and automatically proposing multiple story developments and genres.

[0871] "Means for inputting images" refers to a method by which a user provides the system with image data that will serve as a model for the cartoon.

[0872] The "means for inputting a story outline" is a method by which a user provides the system with the general storyline and theme of a manga as text data.

[0873] The "means for receiving and analyzing" refers to a method by which the server receives image data and text data sent from the user and analyzes this data.

[0874] "Generative AI" is an artificial intelligence model that automatically generates new stories and scenes based on input data.

[0875] "Text generation AI" is an artificial intelligence model that automatically generates lines and narration that correspond to generated stories and scenes.

[0876] "Means for proposing multiple story developments" refers to a method of proposing various genres and scenario developments to users based on the story generated by the generation AI.

[0877] The "means for receiving a story development selection" is a method by which the server receives the user's selection from a plurality of proposed story developments.

[0878] The "means for generating the final manga" is a method for automatically generating the final manga, including character movements, backgrounds, dialogue, etc., based on the story development selected by the user.

[0879] "Displaying means" refers to the method by which the server sends the final generated manga to the user's terminal so that the user can view it.

[0880] The "means for preprocessing image data and text data" refers to a method for preprocessing transmitted image data, such as resizing and filtering, and tokenizing text data.

[0881] The "means for generating a prompt sentence" is a method for generating a prompt sentence to give instructions to the generative AI model based on data input by the user.

[0882] "Means for generating various stories using a generative AI model and analyzing them" refers to a method for generating various story developments using a generative AI model and analyzing the results.

[0883] This invention relates to a system that allows users to efficiently create manga even if they do not have drawing skills. This system utilizes a generative AI model and a text generation AI to automatically generate manga based on data entered by the user. The program processing of this system is explained in detail below.

[0884] User Input

[0885] The user uses a device (such as a PC or smartphone) to input a model image and a summary of the story. For example, the user may input an image and a summary of the story based on the theme of "a story about a cat's adventure in a magical land." The image is provided in JPEG or PNG format, and the summary of the story is entered directly into the text box.

[0886] Data transmission by the terminal

[0887] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[0888] Data reception and analysis by the server

[0889] The server receives the data sent from the device. Image data is preprocessed by resizing and filtering. Story data is analyzed using natural language processing (NLP). Specifically, a text analysis library is used to tokenize the text and perform semantic analysis.

[0890] Auto-generation of stories

[0891] The server uses a generative AI model to automatically generate the rest of the story based on the input image and story outline. For example, it generates a scene where the cat finds a magic key and the adventure begins. This process uses the latest AI models such as GPT-4.

[0892] Automatic generation of dialogue and narration

[0893] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[0894] Multiple storyline suggestions

[0895] The server proposes multiple scenarios based on the generated story. Each scenario is classified into a specific genre and proposed to the user. For example, the server can propose the following scenarios: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0896] User selection input

[0897] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[0898] Generating the final manga

[0899] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page containing, for example, an "adventure scene in which a cat makes friends in a magical land" is automatically generated.

[0900] Display of the generated comic

[0901] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[0902] Prompt Sentence Examples

[0903] 1. "Generate a scene in which a cat finds a magic key."

[0904] 2. "Please suggest a storyline that includes a comedy element."

[0905] 3. "Generate dialogue for a scene where a cat fights a monster."

[0906] In this way, this system allows users to automatically generate manga based on their own ideas, even if they do not have drawing skills. This will broaden the scope of creative expression and provide more people with a platform for self-expression.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Processing Steps

[0909] Step 1: User Input

[0910] Users use their device to input a model image and a story summary. Images are provided in JPEG or PNG format, and the story summary is entered directly into the text box.

[0911] Input: Model image file, story summary text

[0912] Output: Image data, story data

[0913] Step 2: Send data by device

[0914] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[0915] Input: User-provided image data and story data

[0916] Output: Data sent to the server

[0917] Step 3: Data reception and analysis by the server

[0918] The server receives the data sent from the device. It performs preprocessing such as resizing and filtering on the image data. It analyzes the story data using natural language processing (NLP). Specifically, it uses a text analysis library to tokenize the text and perform semantic analysis.

[0919] Input: Image data and story data sent from the device

[0920] Output: Preprocessed image data, analyzed story data

[0921] Step 4: Auto-generate stories

[0922] The server uses a generative AI model (e.g., GPT-4) to automatically generate the rest of the story based on the input image and story outline, for example, generating a scene in which the cat finds a magic key and the adventure begins.

[0923] Input: Preprocessed image data, analyzed story data

[0924] Output: The generated continuation of the story

[0925] Step 5: Automatic generation of dialogue and narration

[0926] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[0927] Input: Generated story continuation data

[0928] Output: Generated dialogue, narration

[0929] Step 6: Propose multiple storylines

[0930] The server then proposes multiple scenarios based on the generated story. Each scenario is categorized into a specific genre and suggested to the user. For example, it suggests scenarios such as "making friends in a magical land," "fighting monsters," and "searching for mysterious items."

[0931] Input: Generated story continuation, dialogue, narration

[0932] Output: Multiple storyline scenarios

[0933] Step 7: User Selection Input

[0934] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[0935] Input: Multiple storyline scenarios

[0936] Output: User-selected data

[0937] Step 8: Generate the final comic

[0938] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page is automatically generated, including an "adventure scene in which a cat makes friends in a magical land."

[0939] Input: User-selected data

[0940] Output: The final generated cartoon

[0941] Step 9: Displaying the generated comic

[0942] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[0943] Input: The final generated comic

[0944] Output: Comic displayed on the terminal

[0945] These are the specific processing steps of the system. Through a detailed explanation of the data processed at each step, it becomes clear how the information entered by the user is processed and the final manga is generated.

[0946] (Application example 1)

[0947] 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."

[0948] The challenge is to provide a system that allows users who do not have the advanced skills required for manga creation to easily and automatically generate high-quality manga. Another challenge is to provide a mechanism that allows the generated manga to be shared immediately and to receive interaction and feedback from a wide range of users.

[0949] 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.

[0950] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, and means for displaying the final manga to the user and sharing it on an information distribution service. This enables users without manga creation skills to easily generate high-quality manga and then instantly share the manga.

[0951] A "model image" is an image that is the basis for visual elements such as cartoon characters and backgrounds specified by the user.

[0952] "Story summary" is general information about the basic plot and theme of the manga specified by the user.

[0953] "Generative AI" is artificial intelligence that automatically generates new stories and visuals based on given images and story outlines.

[0954] "Text generation AI" is an artificial intelligence that automatically creates dialogue and narration that is appropriate for the generated story.

[0955] "Multiple storylines" refers to scenarios where different developments of a story are created by the generative AI.

[0956] "User development selection" refers to the act of the user selecting the development that interests them most from among multiple scenarios provided.

[0957] The "final manga" is a manga work completed by the generation AI and text generation AI based on the plot selected by the user.

[0958] An "information distribution service" is a means for sharing the created manga with other users or publishing it on platforms such as social networking sites.

[0959] The present invention provides a system that enables users, even those without drawing skills, to easily create high-quality manga and share the manga through information distribution services. Specific embodiments of the system are described below.

[0960] First, the user accesses the system using a device (such as a smartphone or PC) and inputs a model image and a story outline. This image and story outline are then sent to the server, which then receives the image data and story outline data sent by the user.

[0961] The server then analyzes the image data, which may include resizing and filtering the image, as well as the text data of the story summary. Once the analysis is complete, the server uses generative AI to automatically generate a new story continuation based on this input data.

[0962] Next, a text generation AI is used to automatically generate dialogue and narration that matches the generated story. As a result, multiple development scenarios are created for the story. For example, the following developments may be generated: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0963] The server proposes these multiple scenarios to the user, and the user selects the scenario that interests them most. The selected data is then sent back to the server, which then automatically generates a completed manga based on the scenario selected by the user.

[0964] The generated manga is sent to the user's device and displayed. The user can then share the manga on social media or with friends. This means that even those without manga creation skills can create high-quality manga based on their own ideas and share them instantly.

[0965] Specific examples

[0966] The server performs the above process using the following hardware and software:

[0967] Hardware: Server computer, user's device (smartphone or PC)

[0968] Software: Generative AI, text generation AI, image analysis software, network communication software (e.g., Requests library)

[0969] Usage example

[0970] For example, if a user inputs the prompt "A story about a cat's adventure in a magical land" and provides a corresponding image, the generation AI will generate a scene in which the cat finds a magic key and the adventure begins, and the text generation AI will add a scene in which the cat mutters, "What is this?"

[0971] An example of this prompt is:

[0972] Prompt: "A cat (character) goes on an adventure in a magical land (context)"

[0973] Image path: "path / to / user_image.jpg"

[0974] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0975] Step 1:

[0976] The user inputs a model image and a story outline using a terminal. This input data consists of an image file and text data. Consider an example where the user inputs an image and a story outline based on the theme of "a story about a cat's adventure in a magical land."

[0977] Step 2:

[0978] The device sends the input data (image files and text data of the story outline) to the server, which then sends the input data to the specified endpoint on the server via the network.

[0979] Step 3:

[0980] The server analyzes the images and story summaries received from the device. Image data is preprocessed by resizing and filtering, and text data is organized using text analysis tools. Specifically, images are resized using Python's PIL, and text is tokenized using NLTK.

[0981] Step 4:

[0982] The server uses generative AI to automatically generate the rest of the story based on the analyzed model image and the story outline. In this step, a prompt sentence is input into the generative AI model to generate the rest of the story. An example of a generated story is "A scene where a cat finds a magic key and an adventure begins."

[0983] Step 5:

[0984] The server uses a sentence generation AI to generate appropriate dialogue and narration based on the story generated by the generative AI. An example of generated dialogue is a scene in which a cat mutters, "What is this?" This step utilizes a sentence generation model such as GPT-3.

[0985] Step 6:

[0986] The server creates multiple scenarios for the generated story and presents them to the user. Using the prompt and the generated story, the server inputs each scenario into the generation AI and suggests different scenarios, such as "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[0987] Step 7:

[0988] The user selects the deployment scenario that interests them most from the multiple deployment scenarios presented. This selection data is then sent back to the server via the device. The data for the selected deployment scenario is sent in JSON format or similar.

[0989] Step 8:

[0990] The server generates the final manga based on the development scenario selected by the user. Here, it integrates images and dialogue, performs paging, and generates manga-format data. The generated manga is saved as an image file for each page.

[0991] Step 9:

[0992] The server then sends the final manga data to the device, where the user can view the manga. Additionally, the server provides a link and a button to share the manga with friends or on social media via an information distribution service.

[0993] This allows users to create high-quality manga and share them instantly, even if they have no manga creation skills.

[0994] 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.

[0995] ---

[0996] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI, and also combines an emotion engine that recognizes the user's emotions, to automatically generate manga based on input data and emotion data. Below, the program processing of this system is explained in natural language, with specific examples.

[0997] 1. User Input

[0998] The user inputs a model image and a summary of the story using a device (such as a PC or smartphone). Specifically, the user inputs a picture and summary based on the theme of "a story about a cat's adventure in a magical land."

[0999] 2. Data Transmission

[1000] The device sends the user's input data (images and story summary) to a server, which then transmits the data over the Internet and stores it on the server using a secure protocol.

[1001] 3. Data Analysis

[1002] The server receives the data sent from the device and analyzes the image and text data. The image data is preprocessed as needed, such as by resizing or removing noise. The story summary text data is also preprocessed in the same way.

[1003] 4. Emotion Recognition by Emotion Engine

[1004] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device and inputs information. For example, emotional data such as whether the user is happy or sad can be extracted.

[1005] 5. Automatic story generation

[1006] The server uses the AI ​​to automatically generate the rest of the story based on the data (images and story summary) and emotional data entered by the user. For example, when generating a scene in which the cat finds the magic key and the adventure begins, if the user is having fun, a bright and cheerful development will be selected, and if the user is sad, a more moving development will be selected.

[1007] 6. Automatic generation of dialogue and narration

[1008] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, in a scene where a cat mutters, "What is this?", it generates high-energy or somber lines that match the user's emotions.

[1009] 7. Story Development Suggestion

[1010] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[1011] 8. User Selection

[1012] The user selects a desired scenario from multiple proposed scenarios through the terminal, and the selected data is sent to the server through the terminal.

[1013] 9. Generating the final manga

[1014] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, dialogue placement, etc. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[1015] 10. Display of manga

[1016] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and enjoy the work that matches their emotions.

[1017] In this way, even if the user does not have drawing skills, this system can automatically generate manga based on the user's ideas, and by incorporating an emotion engine, it can provide story development and dialogue that responds to the user's emotions, broadening the scope of creative expression and further enriching the user's experience.

[1018] The processing flow will be explained below.

[1019] Step 1:

[1020] The user uses the device to draw a model image (for example, the main character or background) or upload an existing image file, and also enters the story outline and scenario in text.

[1021] Step 2:

[1022] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[1023] Step 3:

[1024] The server receives the data sent from the device and analyzes the image data and text data. For example, preprocessing such as resizing and noise removal is performed on the image data, and text cleansing is performed on the text data.

[1025] Step 4:

[1026] The device captures facial expressions and voices as the user uses the device and inputs data. The device then sends the collected facial and voice data to an emotion analysis algorithm to recognize the user's emotions.

[1027] Step 5:

[1028] The server uses an emotion engine to analyze the facial expression and voice data sent from the device and extract the user's emotional data. For example, it recognizes emotions such as happiness, sadness, and excitement from the user's facial expression and tone of voice.

[1029] Step 6:

[1030] The server uses AI to automatically generate the rest of the story based on the image, story summary, and emotional data entered by the user. For example, when generating a scene in which a cat finds a magic key and the adventure begins, if the user is excited, it will generate an action-packed story, but if the user is calm, it will generate an exploration-focused story.

[1031] Step 7:

[1032] Based on the generated story, the server uses text generation AI to create dialogue and narration. For example, in a scene where a cat says, "What is this?", it can generate a surprised or calm tone to match the user's emotions.

[1033] Step 8:

[1034] Based on the generated story and dialogue, the server generates multiple different story developments (e.g., comedy, horror, survival, etc.) using emotional data and suggests them to the user. These suggestions are displayed on the device.

[1035] Step 9:

[1036] The user selects a desired scenario from multiple proposed story developments through the terminal, and this selection information is sent to the server through the terminal.

[1037] Step 10:

[1038] The server generates the final manga based on the user's selections, including character movements, backgrounds, panel layouts, and dialogue placement. For example, it automatically generates a final manga page that details the scene where a cat makes friends in a magical land.

[1039] Step 11:

[1040] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and make corrections or save it as needed.

[1041] By following these steps, users can embody their ideas as manga and enjoy story development that matches their emotions, even if they do not have any special drawing skills.

[1042] Example 2

[1043] 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."

[1044] Conventional manga generation systems require users to have drawing skills, and it is difficult to generate content that reflects emotions. This means that users cannot get the story development or dialogue they expect, limiting the scope of creative expression.

[1045] 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.

[1046] In this invention, the server includes means for inputting model data, means for inputting a story outline, means for receiving and analyzing the data and the story outline, means for pre-processing the data, means for recognizing a user's emotions, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a sentence generation AI, means for proposing multiple story developments, means for receiving a development selection by the user, means for generating final content based on the selected development, and means for displaying the final content to the user. This makes it possible to provide story developments and dialogue that correspond to emotions without requiring the user to have drawing skills.

[1047] "Model data" refers to data that represents the original images or information in the system.

[1048] The "story summary" is text data entered by the user that describes the basic content and setting of the story.

[1049] "Preprocessing" refers to data processing such as resizing and noise removal that the system performs before analyzing the data.

[1050] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions and voice data to identify their emotional state in real time.

[1051] "Generative AI" is an artificial intelligence technology that automatically generates new stories and content based on input data.

[1052] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration that fit specific scenes and stories.

[1053] "Story development proposal" is the process in which the system presents the user with multiple story progression scenarios.

[1054] "Receiving a storyline selection" refers to the user selecting one of the proposed storylines and the system receiving that selection.

[1055] "Final content" is the completed comic or story that the system ultimately generates based on the user's input and selections.

[1056] "Means for displaying to the user" refers to the technology for transmitting the final content generated by the system to the user's terminal and making it viewable.

[1057] The present invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes a generation AI and a text generation AI, and combines it with an emotion engine that recognizes the user's emotions, and automatically generates manga based on input data and emotion data. The following describes in detail the embodiments of the present invention.

[1058] User Input

[1059] Users use a device (such as a PC or smartphone) to input model data and a story outline. The model data includes image files, and the story outline includes the basic setting of the story. For example, a user can input a theme such as "A story about a cat's adventures in a magical land."

[1060] Data transmission

[1061] The device sends the user's input data to the server, which receives and stores it using the Internet and a secure protocol (e.g., HTTPS).

[1062] Data analysis and preprocessing

[1063] The server receives the data sent from the device and analyzes the image and text data. The image data undergoes preprocessing, such as resizing and noise removal. The story summary text data is also preprocessed using natural language processing techniques to extract keywords and check grammar.

[1064] Emotion recognition by emotion engine

[1065] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device to input data. The emotion engine analyzes the user's facial expressions and voice and extracts emotional data such as whether they are happy or sad. This is done using facial recognition software.

[1066] Auto-generation of stories

[1067] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input and emotional data. For example, when generating a scene in which the cat finds a magic key and the adventure begins, if the user is enjoying themselves, a bright and cheerful development will be generated.

[1068] Automatic generation of dialogue and narration

[1069] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, a scene in which a cat mutters, "What is this?" can be generated as high-energy or somber lines that match the user's emotions.

[1070] Story development suggestions

[1071] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[1072] User Selection

[1073] The user selects the desired scenario from the proposed multiple scenarios through the terminal and sends it to the server, which then reflects this selection data in the next process.

[1074] Generating the final manga

[1075] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. For example, it automatically generates a manga page containing the scene "A cat makes friends in a magical land."

[1076] Cartoon Display

[1077] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[1078] Examples and prompts

[1079] For example, suppose a user is looking for a story about a cat's adventures in a magical land and enters the following data:

[1080] Image: Cat character illustration

[1081] Story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[1082] If the emotion engine recognizes that the person is having fun, the generative AI will generate the following continuation of the story:

[1083] "A cat finds a magic key and an adventure begins."

[1084] Text generation AI generates dialogue:

[1085] "The cat excitedly mutters, 'What is this?'"

[1086] Server proposes multiple deployments:

[1087] Gag development: "The cat meets one interesting character after another."

[1088] Adventure: "A cat overcomes challenges and searches for treasure."

[1089] Heartwarming story: "A cat meets a new friend and a friendship blossoms."

[1090] Example prompt sentence:

[1091] User-provided story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[1092] User sentiment: Enjoying it

[1093] The rest of the story to be printed:

[1094] This invention allows users without drawing skills to automatically generate manga based on their own ideas, and also utilizes an emotion engine to provide story developments and dialogue that match the emotions, thereby broadening the scope of creative expression and enriching the user experience.

[1095] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1096] Step 1: User Input

[1097] Specific actions

[1098] The user uses a device (PC or smartphone) to input image data and a summary of the story. The user opens the device's browser or a dedicated app, uploads an image file from the input form, and writes a summary of the story in the text box. For example, the user might enter a theme such as "A story about a cat's adventures in a magical land."

[1099] Input: Image data (e.g., cat character illustration), story summary (e.g., "A cat character goes on an adventure to find lost treasure in a magical land")

[1100] Output: The user's input data is saved to the device.

[1101] Step 2: Send data

[1102] Specific actions

[1103] The device sends the user's input data to the server, which uses the Internet and a secure protocol (e.g., HTTPS). After transmission, the server receives and stores this data.

[1104] Input: User input data (image data, story outline)

[1105] Output: Data is stored on the server.

[1106] Step 3: Data analysis and preprocessing

[1107] Specific actions

[1108] The server analyzes the data received from the device. First, it performs preprocessing such as resizing and noise removal on the image data. Next, it preprocesses the text data of the story summary using natural language processing techniques. This includes extracting story keywords and checking grammar.

[1109] Input: Image data and text data on the server

[1110] Output: Preprocessed data

[1111] Step 4: Emotion Recognition with the Emotion Engine

[1112] Specific actions

[1113] The emotion engine analyzes facial expressions and voice data in real time as users input data using the device. It uses the device's camera and microphone to capture the user's facial expressions and voice and identify their emotional state (e.g., happy, sad). This analysis is performed using facial recognition software and voice analysis tools.

[1114] Input: User's facial expression data and voice data

[1115] Output: User's emotion data (e.g., having fun)

[1116] Step 5: Auto-generate stories

[1117] Specific actions

[1118] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input data and emotional data. A prompt is input into the generative AI model, which generates a scenario based on the user's emotions. For example, it outputs a fun-filled scene in which "the cat finds a magic key and the adventure begins."

[1119] Input: Preprocessed data, emotion data

[1120] Output: The generated story (e.g. "The cat finds the magic key and the adventure begins")

[1121] Step 6: Automatic generation of dialogue and narration

[1122] Specific actions

[1123] The server uses text generation AI to automatically create lines and narration that fit the generated story. Based on the generative AI model, it generates lines such as "The cat mutters 'What is this?'" that match the user's emotions.

[1124] Input: Generated stories

[1125] Output: Generated dialogue or narration (e.g., "The cat excitedly murmurs, 'What is this? It looks so interesting!'")

[1126] Step 7: Propose a storyline

[1127] Specific actions

[1128] The server generates multiple scenarios (e.g., comedy, horror, survival) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide the optimal option.

[1129] Input: Generated story, dialogue, and emotion data

[1130] Output: Proposal of multiple scenarios (e.g. comedy, adventure, emotional)

[1131] Step 8: User Selection

[1132] Specific actions

[1133] The user selects the desired scenario from the multiple proposed scenarios through the terminal. The scenario is selected on the terminal's UI interface, and the "Decide" button is clicked. The selected data is sent to the server.

[1134] Input: Proposed deployment scenario

[1135] Output: User-selected data

[1136] Step 9: Generate the final cartoon

[1137] Specific actions

[1138] The server generates the final manga based on the user's selections. It automatically designs the character movements, background, panel layout, and dialogue placement. For example, it generates a manga page containing a scene based on the selection, "A cat makes friends in a magical land."

[1139] Input: User-selected data

[1140] Output: The final generated comic page

[1141] Step 10: Displaying the comic

[1142] Specific actions

[1143] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[1144] Input: The final generated comic page

[1145] Output: Comic displayed on the device

[1146] Through these steps, this system can automatically generate manga based on a user's ideas, even if the user has no drawing skills, and can also provide story development and dialogue that matches the user's emotions.

[1147] (Application example 2)

[1148] 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."

[1149] Conventional manga creation systems do not provide story development or product recommendations that are in line with the user's emotions, making it difficult to improve the quality of the user experience. Furthermore, in physical stores, there is a lack of means to recognize customer emotions in real time and make appropriate product recommendations, making it difficult to improve customer satisfaction.

[1150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1151] In this invention, the server includes means for inputting a model image, means for inputting a story outline, means for receiving and analyzing the image and the story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for recommending products based on the user's field, means for automatically generating storytelling related to the recommended products, and means for recognizing the user's emotions in real time, thereby enabling story developments and product recommendations that are in line with the user's emotions.

[1152] A "model image" is visual data of an object input by the user, and is the basis for the system's analysis and use.

[1153] The "story summary" is the plot and theme information of the story entered by the user, and is the information that the system uses to develop the story.

[1154] "Generative AI" refers to software that uses artificial intelligence techniques to automatically generate stories and other creative content.

[1155] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration based on input data.

[1156] "Multiple storylines" are different scenario options automatically generated by the generative AI.

[1157] "User development selection" refers to the act of the user selecting one of the proposed story developments.

[1158] "Final comic" refers to the completed comic, including the storyline selected by the user and the dialogue and narration generated by the user.

[1159] A "means for recommending products based on a user's field" is a method or technology for presenting appropriate products based on a user's interests and hobbies.

[1160] The "means for automatically generating storytelling related to a recommended product" refers to a method or technology for generating a story to convey the appeal of a recommended product.

[1161] "Means for recognizing a user's emotions in real time" refers to technology that uses a camera and microphone to analyze the user's emotional state from their facial expressions and voice.

[1162] The present invention is a system for creating manga that utilizes generation AI and text generation AI, and combines it with an emotion engine that recognizes the user's emotions in real time to improve the user experience. The system of the present invention is configured as follows.

[1163] Hardware and Software Use

[1164] Servers and devices are used as the primary hardware. In particular, smart glasses (e.g., Google Glass, Microsoft HoloLens), high-resolution cameras, and highly sensitive microphones are used for real-time emotion recognition. Facial expression recognition software (e.g., Affectiva) and voice emotion analysis software (e.g., IBM Watson Tone Analyzer) are used for emotion recognition. Generative AI models (e.g., OpenAI's GPT) and AR display libraries (e.g., Vuforia, ARKit) also play important roles.

[1165] System Details

[1166] User Input

[1167] The user inputs a model image and a summary of the story using a device (smartphone or PC). For example, they input an image and summary based on the theme of "a story about a cat's adventure in a magical land."

[1168] Data transmission and analysis

[1169] The device sends the user's input data (images and story outline) to the server, which analyzes the data and performs preprocessing such as resizing and noise removal. The story outline is also preprocessed in the same way.

[1170] Emotion recognition by emotion engine

[1171] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial and voice data and analyzes emotions in real time. Emotional data is extracted using Affectiva and IBM Watson APIs.

[1172] Automatic story generation and product recommendation

[1173] The server uses generative AI to automatically generate the rest of the story based on the data and emotional data entered by the user. It also recommends products based on the user's field and automatically generates storytelling related to the recommended products. For example, if the user is having fun, it will choose a bright and cheerful development.

[1174] Automatic generation and presentation of dialogue and narration

[1175] The server uses text generation AI to automatically create lines and narration that fit the generated story, generating high-energy or somber lines to match the user's emotions.

[1176] Generate and display the final manga

[1177] After the user selects multiple storylines, the server generates the final manga, including character movements, background details, panel layout, and dialogue placement. The generated final manga data is sent to the device, which displays it to the user.

[1178] Examples of concrete examples and prompts

[1179] In a specific scenario, when a user wears smart glasses and enters a store, the glasses analyze the user's emotions in real time and recommend products based on that. For example, if the glasses determine that the user is having fun, they will input the following prompt sentence into the generation AI:

[1180] "Generate a compelling story about Product A. For example, what kind of adventurer used this item?"

[1181] When a customer comes in front of a designated product, an automatically generated storytelling is displayed on the smart glasses display.

[1182] In this way, the present invention can realize story development and product recommendations that are in line with the user's emotions, thereby improving the quality of the user experience.

[1183] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1184] Step 1:

[1185] The user uses the device to input a model image and a summary of the story. The input image and text data are acquired as the initial input for the system. Specifically, the user inputs an image and a summary based on the theme of "a story about a cat's adventure in a magical land." The input data is temporarily saved in the device.

[1186] Step 2:

[1187] The device sends the user's input data to the server, which then transmits the input data (images and story outline) over the Internet using a secure protocol, where the received data is stored.

[1188] Step 3:

[1189] The server analyzes the image and text data it receives. The image data undergoes preprocessing such as resizing and noise removal, and the text data undergoes preprocessing such as grammar checks and removal of unnecessary symbols. The preprocessed data becomes the input data for story generation.

[1190] Step 4:

[1191] The device uses a camera and microphone to capture the user's facial expressions and voice data, and sends it to the server in real time. The server uses this data to analyze the user's emotions using an emotion engine (e.g., Affectiva, IBM Watson). The analysis results are saved as the user's emotional state.

[1192] Step 5:

[1193] The server uses a generative AI model (e.g., OpenAI's GPT) to automatically generate the rest of the story based on the story summary and emotional data entered by the user. Based on the input data and emotional data, the generative AI generates the rest of the story. For example, it generates a scene in which the cat finds the magic key and the adventure begins, with a bright and fun development that matches the user's emotions.

[1194] Step 6:

[1195] The server uses text generation AI to automatically generate lines and narration that fit the generated story. Using the generated story as input, lines and narration that match the user's emotions are output. For example, a scene in which a cat mutters, "What is this?" is generated as a high-energy line.

[1196] Step 7:

[1197] The server recommends products based on the user's field. A generative AI model is used to recommend products based on sentiment data and past purchase history. The user expresses interest in the displayed products.

[1198] Step 8:

[1199] The server generates storytelling related to the recommended product. Using the recommended product and the user's emotional data as input, the generation AI is prompted with the prompt "Generate an engaging story for Product A. For example, what kind of adventurer used this item?", and the storytelling is obtained as output. The generated story is displayed on the device.

[1200] Step 9:

[1201] The terminal displays the final manga data sent from the server. The user can browse the displayed manga and enjoy the emotionally relevant story and product recommendations.

[1202] 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.

[1203] 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.

[1204] 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.

[1205] [Fourth embodiment]

[1206] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1207] 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.

[1208] 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).

[1209] 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.

[1210] 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.

[1211] 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).

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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."

[1219] ---

[1220] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI to automatically generate manga based on data entered by the user. Below, we will explain the program processing of this system in natural language, with specific examples.

[1221] 1. User Input

[1222] First, the user inputs a model image and a summary of the story using a device (such as a PC or smartphone). For example, the user inputs a picture and summary of a story about a cat's adventure in a magical land.

[1223] 2. Data transmission by the terminal

[1224] Next, the device sends the input data (pictures and story outline) to the server via the network.

[1225] 3. Data reception and analysis by the server

[1226] The server receives the data sent from the device and analyzes the image and text data, including preprocessing of the image data (such as resizing and filtering) and text analysis of the story summary.

[1227] 4. Automatic story generation

[1228] The server then uses generative AI to automatically generate the rest of the story based on the model image and story outline entered by the user, for example, generating a scene in which the cat finds the magic key and the adventure begins.

[1229] 5. Automatic generation of dialogue and narration

[1230] After generating the story, the server uses text generation AI to automatically create dialogue and narration that matches the generated story. For example, it generates a scene in which a cat mutters, "What is this?"

[1231] 6. Propose multiple storylines

[1232] The server generates multiple scenarios based on the generated story, categorizes them into genres (such as comedy, horror, survival, etc.), and proposes them to the user. As specific examples, the following scenarios are proposed: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[1233] 7. User selection input

[1234] The user selects the most interesting scenario from the multiple proposed scenarios, and this selection data is sent back to the server via the terminal.

[1235] 8. Generating the final manga

[1236] The server generates the final manga based on the user's selection, including details such as character movements, background, panel layout, and dialogue. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[1237] 9. Displaying the generated comic

[1238] Finally, the server transmits the final comic to the terminal, which displays it to the user, allowing the user to view the completed comic.

[1239] In this way, this system can automatically generate manga based on users' ideas, even if they have no drawing skills. This will broaden the scope of creative expression, providing a platform for self-expression for many people who previously could not participate in manga production.

[1240] The processing flow will be explained below.

[1241] Step 1:

[1242] The user uses a terminal to draw a model image (for example, the main character or background) or upload an existing image file, and then inputs the outline of the story and the scenario in text.

[1243] Step 2:

[1244] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[1245] Step 3:

[1246] The server receives the data sent from the device and analyzes the image data and text data. For image data, it performs preprocessing such as resizing and noise removal as necessary.

[1247] Step 4:

[1248] The server launches a generation AI that automatically generates the rest of the story based on the images and story outline entered by the user. At this time, the AI ​​analyzes the input data and determines the character's actions, scene progression, etc.

[1249] Step 5:

[1250] Based on the generated story, the server uses text generation AI to automatically generate dialogue and narration, for example, creating text to describe the words spoken by characters in the generated scenes and the scenery.

[1251] Step 6:

[1252] The server generates multiple storylines (e.g., comedy, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. The suggestions are displayed on the device as options.

[1253] Step 7:

[1254] The user selects the desired scenario from the multiple proposed developments through the terminal and transmits the selection information to the server, which then decides on the story development according to the selection.

[1255] Step 8:

[1256] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. All elements are integrated to create the final manga data.

[1257] Step 9:

[1258] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and, if necessary, make corrections or save it.

[1259] By following the above steps, users can turn their ideas into comics and enjoy multiple storylines, even if they do not have any special drawing skills.

[1260] Example 1

[1261] 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."

[1262] Conventional manga production systems require specialized skills, making it difficult for users without drawing skills to easily create manga. Furthermore, story development and dialogue generation must be done manually, resulting in a time-consuming and labor-intensive production process. Another issue is the lack of systems that automate the proposing of multiple story developments and genres.

[1263] 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.

[1264] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for preprocessing image data and text data and analyzing the data, means for generating prompt sentences, and means for generating various stories using a generation AI model based on the generated prompt sentences and analyzing them. This enables even users without drawing skills to easily create high-quality manga, significantly reducing production time and labor, and automatically proposing multiple story developments and genres.

[1265] "Means for inputting images" refers to a method by which a user provides the system with image data that will serve as a model for the cartoon.

[1266] The "means for inputting a story outline" is a method by which a user provides the system with the general storyline and theme of a manga as text data.

[1267] The "means for receiving and analyzing" refers to a method by which the server receives image data and text data sent from the user and analyzes this data.

[1268] "Generative AI" is an artificial intelligence model that automatically generates new stories and scenes based on input data.

[1269] "Text generation AI" is an artificial intelligence model that automatically generates lines and narration that correspond to generated stories and scenes.

[1270] "Means for proposing multiple story developments" refers to a method of proposing various genres and scenario developments to users based on the story generated by the generation AI.

[1271] The "means for receiving a story development selection" is a method by which the server receives the user's selection from a plurality of proposed story developments.

[1272] The "means for generating the final manga" is a method for automatically generating the final manga, including character movements, backgrounds, dialogue, etc., based on the story development selected by the user.

[1273] "Displaying means" refers to the method by which the server sends the final generated manga to the user's terminal so that the user can view it.

[1274] The "means for preprocessing image data and text data" refers to a method for preprocessing transmitted image data, such as resizing and filtering, and tokenizing text data.

[1275] The "means for generating a prompt sentence" is a method for generating a prompt sentence to give instructions to the generative AI model based on data input by the user.

[1276] "Means for generating various stories using a generative AI model and analyzing them" refers to a method for generating various story developments using a generative AI model and analyzing the results.

[1277] This invention relates to a system that allows users to efficiently create manga even if they do not have drawing skills. This system utilizes a generative AI model and a text generation AI to automatically generate manga based on data entered by the user. The program processing of this system is explained in detail below.

[1278] User Input

[1279] The user uses a device (such as a PC or smartphone) to input a model image and a summary of the story. For example, the user may input an image and a summary of the story based on the theme of "a story about a cat's adventure in a magical land." The image is provided in JPEG or PNG format, and the summary of the story is entered directly into the text box.

[1280] Data transmission by the terminal

[1281] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[1282] Data reception and analysis by the server

[1283] The server receives the data sent from the device. Image data is preprocessed by resizing and filtering. Story data is analyzed using natural language processing (NLP). Specifically, a text analysis library is used to tokenize the text and perform semantic analysis.

[1284] Auto-generation of stories

[1285] The server uses a generative AI model to automatically generate the rest of the story based on the input image and story outline. For example, it generates a scene where the cat finds a magic key and the adventure begins. This process uses the latest AI models such as GPT-4.

[1286] Automatic generation of dialogue and narration

[1287] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[1288] Multiple storyline suggestions

[1289] The server proposes multiple scenarios based on the generated story. Each scenario is classified into a specific genre and proposed to the user. For example, the server can propose the following scenarios: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[1290] User selection input

[1291] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[1292] Generating the final manga

[1293] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page containing, for example, an "adventure scene in which a cat makes friends in a magical land" is automatically generated.

[1294] Display of the generated comic

[1295] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[1296] Prompt Sentence Examples

[1297] 1. "Generate a scene in which a cat finds a magic key."

[1298] 2. "Please suggest a storyline that includes a comedy element."

[1299] 3. "Generate dialogue for a scene where a cat fights a monster."

[1300] In this way, this system allows users to automatically generate manga based on their own ideas, even if they do not have drawing skills. This will broaden the scope of creative expression and provide more people with a platform for self-expression.

[1301] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1302] Processing Steps

[1303] Step 1: User Input

[1304] Users use their device to input a model image and a story summary. Images are provided in JPEG or PNG format, and the story summary is entered directly into the text box.

[1305] Input: Model image file, story summary text

[1306] Output: Image data, story data

[1307] Step 2: Send data by device

[1308] The device sends the input image and story summary data to the server using the HTTP protocol. Specifically, the image file is sent in binary format, and the story data is sent as text data in JSON format.

[1309] Input: User-provided image data and story data

[1310] Output: Data sent to the server

[1311] Step 3: Data reception and analysis by the server

[1312] The server receives the data sent from the device. It performs preprocessing such as resizing and filtering on the image data. It analyzes the story data using natural language processing (NLP). Specifically, it uses a text analysis library to tokenize the text and perform semantic analysis.

[1313] Input: Image data and story data sent from the device

[1314] Output: Preprocessed image data, analyzed story data

[1315] Step 4: Auto-generate stories

[1316] The server uses a generative AI model (e.g., GPT-4) to automatically generate the rest of the story based on the input image and story outline, for example, generating a scene in which the cat finds a magic key and the adventure begins.

[1317] Input: Preprocessed image data, analyzed story data

[1318] Output: The generated continuation of the story

[1319] Step 5: Automatic generation of dialogue and narration

[1320] After the story is generated, the server uses text generation AI to automatically generate dialogue and narration that fits the generated story. For example, it generates dialogue that corresponds to the scene where the cat mutters, "What is this?"

[1321] Input: Generated story continuation data

[1322] Output: Generated dialogue, narration

[1323] Step 6: Propose multiple storylines

[1324] The server then proposes multiple scenarios based on the generated story. Each scenario is categorized into a specific genre and suggested to the user. For example, it suggests scenarios such as "making friends in a magical land," "fighting monsters," and "searching for mysterious items."

[1325] Input: Generated story continuation, dialogue, narration

[1326] Output: Multiple storyline scenarios

[1327] Step 7: User Selection Input

[1328] The user selects the scenario that interests them from the multiple scenarios proposed and sends the data to the server via their terminal.

[1329] Input: Multiple storyline scenarios

[1330] Output: User-selected data

[1331] Step 8: Generate the final comic

[1332] The server generates the final manga based on the storyline selected by the user. This generation process involves creating an overall storyline including character movements, backgrounds, panel layouts, dialogue, etc. In this step, a manga page is automatically generated, including an "adventure scene in which a cat makes friends in a magical land."

[1333] Input: User-selected data

[1334] Output: The final generated cartoon

[1335] Step 9: Displaying the generated comic

[1336] The server sends the completed manga data to the device, which displays it, and the user can then view, save, and share the final manga.

[1337] Input: The final generated comic

[1338] Output: Comic displayed on the terminal

[1339] These are the specific processing steps of the system. Through a detailed explanation of the data processed at each step, it becomes clear how the information entered by the user is processed and the final manga is generated.

[1340] (Application example 1)

[1341] 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."

[1342] The challenge is to provide a system that allows users who do not have the advanced skills required for manga creation to easily and automatically generate high-quality manga. Another challenge is to provide a mechanism that allows the generated manga to be shared immediately and to receive interaction and feedback from a wide range of users.

[1343] 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.

[1344] In this invention, the server includes means for inputting model images, means for inputting a story outline, means for receiving and analyzing the images and story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, and means for displaying the final manga to the user and sharing it on an information distribution service. This enables users without manga creation skills to easily generate high-quality manga and then instantly share the manga.

[1345] A "model image" is an image that is the basis for visual elements such as cartoon characters and backgrounds specified by the user.

[1346] "Story summary" is general information about the basic plot and theme of the manga specified by the user.

[1347] "Generative AI" is artificial intelligence that automatically generates new stories and visuals based on given images and story outlines.

[1348] "Text generation AI" is an artificial intelligence that automatically creates dialogue and narration that is appropriate for the generated story.

[1349] "Multiple storylines" refers to scenarios where different developments of a story are created by the generative AI.

[1350] "User development selection" refers to the act of the user selecting the development that interests them most from among multiple scenarios provided.

[1351] The "final manga" is a manga work completed by the generation AI and text generation AI based on the plot selected by the user.

[1352] An "information distribution service" is a means for sharing the created manga with other users or publishing it on platforms such as social networking sites.

[1353] The present invention provides a system that enables users, even those without drawing skills, to easily create high-quality manga and share the manga through information distribution services. Specific embodiments of the system are described below.

[1354] First, the user accesses the system using a device (such as a smartphone or PC) and inputs a model image and a story outline. This image and story outline are then sent to the server, which then receives the image data and story outline data sent by the user.

[1355] The server then analyzes the image data, which may include resizing and filtering the image, as well as the text data of the story summary. Once the analysis is complete, the server uses generative AI to automatically generate a new story continuation based on this input data.

[1356] Next, a text generation AI is used to automatically generate dialogue and narration that matches the generated story. As a result, multiple development scenarios are created for the story. For example, the following developments may be generated: "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[1357] The server proposes these multiple scenarios to the user, and the user selects the scenario that interests them most. The selected data is then sent back to the server, which then automatically generates a completed manga based on the scenario selected by the user.

[1358] The generated manga is sent to the user's device and displayed. The user can then share the manga on social media or with friends. This means that even those without manga creation skills can create high-quality manga based on their own ideas and share them instantly.

[1359] Specific examples

[1360] The server performs the above process using the following hardware and software:

[1361] Hardware: Server computer, user's device (smartphone or PC)

[1362] Software: Generative AI, text generation AI, image analysis software, network communication software (e.g., Requests library)

[1363] Usage example

[1364] For example, if a user inputs the prompt "A story about a cat's adventure in a magical land" and provides a corresponding image, the generation AI will generate a scene in which the cat finds a magic key and the adventure begins, and the text generation AI will add a scene in which the cat mutters, "What is this?"

[1365] An example of this prompt is:

[1366] Prompt: "A cat (character) goes on an adventure in a magical land (context)"

[1367] Image path: "path / to / user_image.jpg"

[1368] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1369] Step 1:

[1370] The user inputs a model image and a story outline using a terminal. This input data consists of an image file and text data. Consider an example where the user inputs an image and a story outline based on the theme of "a story about a cat's adventure in a magical land."

[1371] Step 2:

[1372] The device sends the input data (image files and text data of the story outline) to the server, which then sends the input data to the specified endpoint on the server via the network.

[1373] Step 3:

[1374] The server analyzes the images and story summaries received from the device. Image data is preprocessed by resizing and filtering, and text data is organized using text analysis tools. Specifically, images are resized using Python's PIL, and text is tokenized using NLTK.

[1375] Step 4:

[1376] The server uses generative AI to automatically generate the rest of the story based on the analyzed model image and the story outline. In this step, a prompt sentence is input into the generative AI model to generate the rest of the story. An example of a generated story is "A scene where a cat finds a magic key and an adventure begins."

[1377] Step 5:

[1378] The server uses a sentence generation AI to generate appropriate dialogue and narration based on the story generated by the generative AI. An example of generated dialogue is a scene in which a cat mutters, "What is this?" This step utilizes a sentence generation model such as GPT-3.

[1379] Step 6:

[1380] The server creates multiple scenarios for the generated story and presents them to the user. Using the prompt and the generated story, the server inputs each scenario into the generation AI and suggests different scenarios, such as "1. Make friends in a magical land," "2. Fight monsters," and "3. Search for mysterious items."

[1381] Step 7:

[1382] The user selects the deployment scenario that interests them most from the multiple deployment scenarios presented. This selection data is then sent back to the server via the device. The data for the selected deployment scenario is sent in JSON format or similar.

[1383] Step 8:

[1384] The server generates the final manga based on the development scenario selected by the user. Here, it integrates images and dialogue, performs paging, and generates manga-format data. The generated manga is saved as an image file for each page.

[1385] Step 9:

[1386] The server then sends the final manga data to the device, where the user can view the manga. Additionally, the server provides a link and a button to share the manga with friends or on social media via an information distribution service.

[1387] This allows users to create high-quality manga and share them instantly, even if they have no manga creation skills.

[1388] 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.

[1389] ---

[1390] This invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes generation AI and text generation AI, and also combines an emotion engine that recognizes the user's emotions, to automatically generate manga based on input data and emotion data. Below, the program processing of this system is explained in natural language, with specific examples.

[1391] 1. User Input

[1392] The user inputs a model image and a summary of the story using a device (such as a PC or smartphone). Specifically, the user inputs a picture and summary based on the theme of "a story about a cat's adventure in a magical land."

[1393] 2. Data Transmission

[1394] The device sends the user's input data (images and story summary) to a server, which then transmits the data over the Internet and stores it on the server using a secure protocol.

[1395] 3. Data Analysis

[1396] The server receives the data sent from the device and analyzes the image and text data. The image data is preprocessed as needed, such as by resizing or removing noise. The story summary text data is also preprocessed in the same way.

[1397] 4. Emotion Recognition by Emotion Engine

[1398] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device and inputs information. For example, emotional data such as whether the user is happy or sad can be extracted.

[1399] 5. Automatic story generation

[1400] The server uses the AI ​​to automatically generate the rest of the story based on the data (images and story summary) and emotional data entered by the user. For example, when generating a scene in which the cat finds the magic key and the adventure begins, if the user is having fun, a bright and cheerful development will be selected, and if the user is sad, a more moving development will be selected.

[1401] 6. Automatic generation of dialogue and narration

[1402] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, in a scene where a cat mutters, "What is this?", it generates high-energy or somber lines that match the user's emotions.

[1403] 7. Story Development Suggestion

[1404] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[1405] 8. User Selection

[1406] The user selects a desired scenario from multiple proposed scenarios through the terminal, and the selected data is sent to the server through the terminal.

[1407] 9. Generating the final manga

[1408] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, dialogue placement, etc. For example, it automatically generates a manga page containing a scene based on the selection "A cat makes friends in a magical land."

[1409] 10. Display of manga

[1410] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and enjoy the work that matches their emotions.

[1411] In this way, even if the user does not have drawing skills, this system can automatically generate manga based on the user's ideas, and by incorporating an emotion engine, it can provide story development and dialogue that responds to the user's emotions, broadening the scope of creative expression and further enriching the user's experience.

[1412] The processing flow will be explained below.

[1413] Step 1:

[1414] The user uses the device to draw a model image (for example, the main character or background) or upload an existing image file, and also enters the story outline and scenario in text.

[1415] Step 2:

[1416] The device sends the user's input data (images and story outline) to the server via the Internet, and the data is stored on a cloud server.

[1417] Step 3:

[1418] The server receives the data sent from the device and analyzes the image data and text data. For example, preprocessing such as resizing and noise removal is performed on the image data, and text cleansing is performed on the text data.

[1419] Step 4:

[1420] The device captures facial expressions and voices as the user uses the device and inputs data. The device then sends the collected facial and voice data to an emotion analysis algorithm to recognize the user's emotions.

[1421] Step 5:

[1422] The server uses an emotion engine to analyze the facial expression and voice data sent from the device and extract the user's emotional data. For example, it recognizes emotions such as happiness, sadness, and excitement from the user's facial expression and tone of voice.

[1423] Step 6:

[1424] The server uses AI to automatically generate the rest of the story based on the image, story summary, and emotional data entered by the user. For example, when generating a scene in which a cat finds a magic key and the adventure begins, if the user is excited, it will generate an action-packed story, but if the user is calm, it will generate an exploration-focused story.

[1425] Step 7:

[1426] Based on the generated story, the server uses text generation AI to create dialogue and narration. For example, in a scene where a cat says, "What is this?", it can generate a surprised or calm tone to match the user's emotions.

[1427] Step 8:

[1428] Based on the generated story and dialogue, the server generates multiple different story developments (e.g., comedy, horror, survival, etc.) using emotional data and suggests them to the user. These suggestions are displayed on the device.

[1429] Step 9:

[1430] The user selects a desired scenario from multiple proposed story developments through the terminal, and this selection information is sent to the server through the terminal.

[1431] Step 10:

[1432] The server generates the final manga based on the user's selections, including character movements, backgrounds, panel layouts, and dialogue placement. For example, it automatically generates a final manga page that details the scene where a cat makes friends in a magical land.

[1433] Step 11:

[1434] The server sends the generated final manga data to the terminal, which displays it to the user. The user can view the completed manga and make corrections or save it as needed.

[1435] By following these steps, users can embody their ideas as manga and enjoy story development that matches their emotions, even if they do not have any special drawing skills.

[1436] Example 2

[1437] 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."

[1438] Conventional manga generation systems require users to have drawing skills, and it is difficult to generate content that reflects emotions. This means that users cannot get the story development or dialogue they expect, limiting the scope of creative expression.

[1439] 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.

[1440] In this invention, the server includes means for inputting model data, means for inputting a story outline, means for receiving and analyzing the data and the story outline, means for pre-processing the data, means for recognizing a user's emotions, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a sentence generation AI, means for proposing multiple story developments, means for receiving a development selection by the user, means for generating final content based on the selected development, and means for displaying the final content to the user. This makes it possible to provide story developments and dialogue that correspond to emotions without requiring the user to have drawing skills.

[1441] "Model data" refers to data that represents the original images or information in the system.

[1442] The "story summary" is text data entered by the user that describes the basic content and setting of the story.

[1443] "Preprocessing" refers to data processing such as resizing and noise removal that the system performs before analyzing the data.

[1444] "Means for recognizing emotions" refers to technology that analyzes a user's facial expressions and voice data to identify their emotional state in real time.

[1445] "Generative AI" is an artificial intelligence technology that automatically generates new stories and content based on input data.

[1446] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration that fit specific scenes and stories.

[1447] "Story development proposal" is the process in which the system presents the user with multiple story progression scenarios.

[1448] "Receiving a storyline selection" refers to the user selecting one of the proposed storylines and the system receiving that selection.

[1449] "Final content" is the completed comic or story that the system ultimately generates based on the user's input and selections.

[1450] "Means for displaying to the user" refers to the technology for transmitting the final content generated by the system to the user's terminal and making it viewable.

[1451] The present invention relates to a system that allows users to efficiently create manga even if they have no drawing skills. This system utilizes a generation AI and a text generation AI, and combines it with an emotion engine that recognizes the user's emotions, and automatically generates manga based on input data and emotion data. The following describes in detail the embodiments of the present invention.

[1452] User Input

[1453] Users use a device (such as a PC or smartphone) to input model data and a story outline. The model data includes image files, and the story outline includes the basic setting of the story. For example, a user can input a theme such as "A story about a cat's adventures in a magical land."

[1454] Data transmission

[1455] The device sends the user's input data to the server, which receives and stores it using the Internet and a secure protocol (e.g., HTTPS).

[1456] Data analysis and preprocessing

[1457] The server receives the data sent from the device and analyzes the image and text data. The image data undergoes preprocessing, such as resizing and noise removal. The story summary text data is also preprocessed using natural language processing techniques to extract keywords and check grammar.

[1458] Emotion recognition by emotion engine

[1459] The emotion engine recognizes the user's emotions in real time based on facial expressions and voice data when the user uses the device to input data. The emotion engine analyzes the user's facial expressions and voice and extracts emotional data such as whether they are happy or sad. This is done using facial recognition software.

[1460] Auto-generation of stories

[1461] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input and emotional data. For example, when generating a scene in which the cat finds a magic key and the adventure begins, if the user is enjoying themselves, a bright and cheerful development will be generated.

[1462] Automatic generation of dialogue and narration

[1463] The server uses text generation AI to automatically create lines and narration that fit the generated story. For example, a scene in which a cat mutters, "What is this?" can be generated as high-energy or somber lines that match the user's emotions.

[1464] Story development suggestions

[1465] The server generates multiple scenarios (gag, horror, survival, etc.) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide options that are more in line with their emotions.

[1466] User Selection

[1467] The user selects the desired scenario from the proposed multiple scenarios through the terminal and sends it to the server, which then reflects this selection data in the next process.

[1468] Generating the final manga

[1469] The server generates the final manga based on the user's selections, including character movements, background details, panel layout, and dialogue placement. For example, it automatically generates a manga page containing the scene "A cat makes friends in a magical land."

[1470] Cartoon Display

[1471] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[1472] Examples and prompts

[1473] For example, suppose a user is looking for a story about a cat's adventures in a magical land and enters the following data:

[1474] Image: Cat character illustration

[1475] Story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[1476] If the emotion engine recognizes that the person is having fun, the generative AI will generate the following continuation of the story:

[1477] "A cat finds a magic key and an adventure begins."

[1478] Text generation AI generates dialogue:

[1479] "The cat excitedly mutters, 'What is this?'"

[1480] Server proposes multiple deployments:

[1481] Gag development: "The cat meets one interesting character after another."

[1482] Adventure: "A cat overcomes challenges and searches for treasure."

[1483] Heartwarming story: "A cat meets a new friend and a friendship blossoms."

[1484] Example prompt sentence:

[1485] User-provided story summary: "A cat character goes on an adventure to find lost treasure in a magical land."

[1486] User sentiment: Enjoying it

[1487] The rest of the story to be printed:

[1488] This invention allows users without drawing skills to automatically generate manga based on their own ideas, and also utilizes an emotion engine to provide story developments and dialogue that match the emotions, thereby broadening the scope of creative expression and enriching the user experience.

[1489] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1490] Step 1: User Input

[1491] Specific actions

[1492] The user uses a device (PC or smartphone) to input image data and a summary of the story. The user opens the device's browser or a dedicated app, uploads an image file from the input form, and writes a summary of the story in the text box. For example, the user might enter a theme such as "A story about a cat's adventures in a magical land."

[1493] Input: Image data (e.g., cat character illustration), story summary (e.g., "A cat character goes on an adventure to find lost treasure in a magical land")

[1494] Output: The user's input data is saved to the device.

[1495] Step 2: Send data

[1496] Specific actions

[1497] The device sends the user's input data to the server, which uses the Internet and a secure protocol (e.g., HTTPS). After transmission, the server receives and stores this data.

[1498] Input: User input data (image data, story outline)

[1499] Output: Data is stored on the server.

[1500] Step 3: Data analysis and preprocessing

[1501] Specific actions

[1502] The server analyzes the data received from the device. First, it performs preprocessing such as resizing and noise removal on the image data. Next, it preprocesses the text data of the story summary using natural language processing techniques. This includes extracting story keywords and checking grammar.

[1503] Input: Image data and text data on the server

[1504] Output: Preprocessed data

[1505] Step 4: Emotion Recognition with the Emotion Engine

[1506] Specific actions

[1507] The emotion engine analyzes facial expressions and voice data in real time as users input data using the device. It uses the device's camera and microphone to capture the user's facial expressions and voice and identify their emotional state (e.g., happy, sad). This analysis is performed using facial recognition software and voice analysis tools.

[1508] Input: User's facial expression data and voice data

[1509] Output: User's emotion data (e.g., having fun)

[1510] Step 5: Auto-generate stories

[1511] Specific actions

[1512] The server uses a generative AI model (e.g., GPT-3) to automatically generate the rest of the story based on the user's input data and emotional data. A prompt is input into the generative AI model, which generates a scenario based on the user's emotions. For example, it outputs a fun-filled scene in which "the cat finds a magic key and the adventure begins."

[1513] Input: Preprocessed data, emotion data

[1514] Output: The generated story (e.g. "The cat finds the magic key and the adventure begins")

[1515] Step 6: Automatic generation of dialogue and narration

[1516] Specific actions

[1517] The server uses text generation AI to automatically create lines and narration that fit the generated story. Based on the generative AI model, it generates lines such as "The cat mutters 'What is this?'" that match the user's emotions.

[1518] Input: Generated stories

[1519] Output: Generated dialogue or narration (e.g., "The cat excitedly murmurs, 'What is this? It looks so interesting!'")

[1520] Step 7: Propose a storyline

[1521] Specific actions

[1522] The server generates multiple scenarios (e.g., comedy, horror, survival) based on the generated story and dialogue, and suggests them to the user. It also takes into account the user's emotional data to provide the optimal option.

[1523] Input: Generated story, dialogue, and emotion data

[1524] Output: Proposal of multiple scenarios (e.g. comedy, adventure, emotional)

[1525] Step 8: User Selection

[1526] Specific actions

[1527] The user selects the desired scenario from the multiple proposed scenarios through the terminal. The scenario is selected on the terminal's UI interface, and the "Decide" button is clicked. The selected data is sent to the server.

[1528] Input: Proposed deployment scenario

[1529] Output: User-selected data

[1530] Step 9: Generate the final cartoon

[1531] Specific actions

[1532] The server generates the final manga based on the user's selections. It automatically designs the character movements, background, panel layout, and dialogue placement. For example, it generates a manga page containing a scene based on the selection, "A cat makes friends in a magical land."

[1533] Input: User-selected data

[1534] Output: The final generated comic page

[1535] Step 10: Displaying the comic

[1536] Specific actions

[1537] The server sends the generated final manga data to the terminal and displays it to the user, who can then view and enjoy the completed manga on the terminal screen.

[1538] Input: The final generated comic page

[1539] Output: Comic displayed on the device

[1540] Through these steps, this system can automatically generate manga based on a user's ideas, even if the user has no drawing skills, and can also provide story development and dialogue that matches the user's emotions.

[1541] (Application example 2)

[1542] 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."

[1543] Conventional manga creation systems do not provide story development or product recommendations that are in line with the user's emotions, making it difficult to improve the quality of the user experience. Furthermore, in physical stores, there is a lack of means to recognize customer emotions in real time and make appropriate product recommendations, making it difficult to improve customer satisfaction.

[1544] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1545] In this invention, the server includes means for inputting a model image, means for inputting a story outline, means for receiving and analyzing the image and the story outline, means for automatically generating a continuation of the story using a generation AI, means for generating dialogue and narration using a text generation AI, means for proposing multiple story developments, means for receiving a development selection by a user, means for generating a final manga based on the selected development, means for displaying the final manga to the user, means for recommending products based on the user's field, means for automatically generating storytelling related to the recommended products, and means for recognizing the user's emotions in real time, thereby enabling story developments and product recommendations that are in line with the user's emotions.

[1546] A "model image" is visual data of an object input by the user, and is the basis for the system's analysis and use.

[1547] The "story summary" is the plot and theme information of the story entered by the user, and is the information that the system uses to develop the story.

[1548] "Generative AI" refers to software that uses artificial intelligence techniques to automatically generate stories and other creative content.

[1549] "Text generation AI" is an artificial intelligence technology that automatically generates lines and narration based on input data.

[1550] "Multiple storylines" are different scenario options automatically generated by the generative AI.

[1551] "User development selection" refers to the act of the user selecting one of the proposed story developments.

[1552] "Final comic" refers to the completed comic, including the storyline selected by the user and the dialogue and narration generated by the user.

[1553] A "means for recommending products based on a user's field" is a method or technology for presenting appropriate products based on a user's interests and hobbies.

[1554] The "means for automatically generating storytelling related to a recommended product" refers to a method or technology for generating a story to convey the appeal of a recommended product.

[1555] "Means for recognizing a user's emotions in real time" refers to technology that uses a camera and microphone to analyze the user's emotional state from their facial expressions and voice.

[1556] The present invention is a system for creating manga that utilizes generation AI and text generation AI, and combines it with an emotion engine that recognizes the user's emotions in real time to improve the user experience. The system of the present invention is configured as follows.

[1557] Hardware and Software Use

[1558] Servers and devices are used as the primary hardware. In particular, smart glasses (e.g., Google Glass, Microsoft HoloLens), high-resolution cameras, and highly sensitive microphones are used for real-time emotion recognition. Facial expression recognition software (e.g., Affectiva) and voice emotion analysis software (e.g., IBM Watson Tone Analyzer) are used for emotion recognition. Generative AI models (e.g., OpenAI's GPT) and AR display libraries (e.g., Vuforia, ARKit) also play important roles.

[1559] System Details

[1560] User Input

[1561] The user inputs a model image and a summary of the story using a device (smartphone or PC). For example, they input an image and summary based on the theme of "a story about a cat's adventure in a magical land."

[1562] Data transmission and analysis

[1563] The device sends the user's input data (images and story outline) to the server, which analyzes the data and performs preprocessing such as resizing and noise removal. The story outline is also preprocessed in the same way.

[1564] Emotion recognition by emotion engine

[1565] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial and voice data and analyzes emotions in real time. Emotional data is extracted using Affectiva and IBM Watson APIs.

[1566] Automatic story generation and product recommendation

[1567] The server uses generative AI to automatically generate the rest of the story based on the data and emotional data entered by the user. It also recommends products based on the user's field and automatically generates storytelling related to the recommended products. For example, if the user is having fun, it will choose a bright and cheerful development.

[1568] Automatic generation and presentation of dialogue and narration

[1569] The server uses text generation AI to automatically create lines and narration that fit the generated story, generating high-energy or somber lines to match the user's emotions.

[1570] Generate and display the final manga

[1571] After the user selects multiple storylines, the server generates the final manga, including character movements, background details, panel layout, and dialogue placement. The generated final manga data is sent to the device, which displays it to the user.

[1572] Examples of concrete examples and prompts

[1573] In a specific scenario, when a user wears smart glasses and enters a store, the glasses analyze the user's emotions in real time and recommend products based on that. For example, if the glasses determine that the user is having fun, they will input the following prompt sentence into the generation AI:

[1574] "Generate a compelling story about Product A. For example, what kind of adventurer used this item?"

[1575] When a customer comes in front of a designated product, an automatically generated storytelling is displayed on the smart glasses display.

[1576] In this way, the present invention can realize story development and product recommendations that are in line with the user's emotions, thereby improving the quality of the user experience.

[1577] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1578] Step 1:

[1579] The user uses the device to input a model image and a summary of the story. The input image and text data are acquired as the initial input for the system. Specifically, the user inputs an image and a summary based on the theme of "a story about a cat's adventure in a magical land." The input data is temporarily saved in the device.

[1580] Step 2:

[1581] The device sends the user's input data to the server, which then transmits the input data (images and story outline) over the Internet using a secure protocol, where the received data is stored.

[1582] Step 3:

[1583] The server analyzes the image and text data it receives. The image data undergoes preprocessing such as resizing and noise removal, and the text data undergoes preprocessing such as grammar checks and removal of unnecessary symbols. The preprocessed data becomes the input data for story generation.

[1584] Step 4:

[1585] The device uses a camera and microphone to capture the user's facial expressions and voice data, and sends it to the server in real time. The server uses this data to analyze the user's emotions using an emotion engine (e.g., Affectiva, IBM Watson). The analysis results are saved as the user's emotional state.

[1586] Step 5:

[1587] The server uses a generative AI model (e.g., OpenAI's GPT) to automatically generate the rest of the story based on the story summary and emotional data entered by the user. Based on the input data and emotional data, the generative AI generates the rest of the story. For example, it generates a scene in which the cat finds the magic key and the adventure begins, with a bright and fun development that matches the user's emotions.

[1588] Step 6:

[1589] The server uses text generation AI to automatically generate lines and narration that fit the generated story. Using the generated story as input, lines and narration that match the user's emotions are output. For example, a scene in which a cat mutters, "What is this?" is generated as a high-energy line.

[1590] Step 7:

[1591] The server recommends products based on the user's field. A generative AI model is used to recommend products based on sentiment data and past purchase history. The user expresses interest in the displayed products.

[1592] Step 8:

[1593] The server generates storytelling related to the recommended product. Using the recommended product and the user's emotional data as input, the generation AI is prompted with the prompt "Generate an engaging story for Product A. For example, what kind of adventurer used this item?", and the storytelling is obtained as output. The generated story is displayed on the device.

[1594] Step 9:

[1595] The terminal displays the final manga data sent from the server. The user can browse the displayed manga and enjoy the emotionally relevant story and product recommendations.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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).

[1603] 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.

[1604] 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."

[1605] 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.

[1606] 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).

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] The following is further disclosed regarding the above embodiment.

[1618] (Claim 1)

[1619] A means for inputting a model image;

[1620] a means for inputting a story outline;

[1621] means for receiving and analyzing said images and story summary;

[1622] A means to automatically generate the continuation of the story using generative AI,

[1623] A means of generating lines and narration using text generation AI,

[1624] A means of proposing multiple storylines,

[1625] means for receiving a deployment selection by a user;

[1626] means for generating a final cartoon based on the selected developments;

[1627] means for displaying the final cartoon to a user;

[1628] A system including:

[1629] (Claim 2)

[1630] The system according to claim 1, further comprising means for presenting a selection of multiple genres based on the story development generated by the generation AI.

[1631] (Claim 3)

[1632] 10. The system of claim 1, further comprising means for pre-processing the user-entered image and story summary data.

[1633] "Example 1"

[1634] (Claim 1)

[1635] A means for inputting a model image;

[1636] a means for inputting a story outline;

[1637] means for receiving and analyzing said images and story summary;

[1638] A means to automatically generate the continuation of the story using generative AI,

[1639] A means of generating lines and narration using text generation AI,

[1640] A means of proposing multiple storylines,

[1641] means for receiving a deployment selection by a user;

[1642] means for generating a final cartoon based on the selected developments;

[1643] means for displaying the final cartoon to a user;

[1644] means for preprocessing image data and text data and analyzing the data;

[1645] a means for generating a prompt sentence;

[1646] A method for generating various stories using a generative AI model based on the generated prompt sentences and analyzing them;

[1647] A system including:

[1648] (Claim 2)

[1649] The system of claim 1, which presents multiple genre options based on the story development generated by the generation AI.

[1650] (Claim 3)

[1651] 10. The system of claim 1, further comprising means for pre-processing the user-entered image and story summary data.

[1652] "Application Example 1"

[1653] (Claim 1)

[1654] A means for inputting a model image;

[1655] a means for inputting a story outline;

[1656] means for receiving and analyzing said images and story summary;

[1657] A means to automatically generate the continuation of the story using generative AI,

[1658] A means of generating lines and narration using text generation AI,

[1659] A means of proposing multiple storylines,

[1660] means for receiving a deployment selection by a user;

[1661] means for generating a final cartoon based on the selected developments;

[1662] means for displaying the final comic to users and sharing it on an information distribution service;

[1663] A system including:

[1664] (Claim 2)

[1665] The system according to claim 1, further comprising means for presenting a selection of multiple genres based on the story development generated by the generation AI.

[1666] (Claim 3)

[1667] 10. The system of claim 1, further comprising means for pre-processing the user-entered image and story summary data.

[1668] "Example 2: Combining Emotion Engines"

[1669] (Claim 1)

[1670] A means of inputting model data;

[1671] a means for inputting a story outline;

[1672] means for receiving and analyzing said data and story summary;

[1673] means for pre-processing the data;

[1674] means for recognizing a user's emotion;

[1675] A means to automatically generate the continuation of the story using generative AI,

[1676] A means of generating lines and narration using text generation AI,

[1677] A means of proposing multiple storylines,

[1678] means for receiving a deployment selection by a user;

[1679] means for generating final content based on the selected expansion;

[1680] means for displaying the final content to a user;

[1681] A system including:

[1682] (Claim 2)

[1683] The system according to claim 1, further comprising means for presenting a selection of multiple genres based on the story development generated by the generation AI.

[1684] (Claim 3)

[1685] 2. The system according to claim 1, wherein the emotion recognition means uses a terminal to collect and analyze emotion data of the user.

[1686] "Application example 2 when combining emotion engines"

[1687] (Claim 1)

[1688] A means for inputting a model image;

[1689] a means for inputting a story outline;

[1690] means for receiving and analyzing said images and story summary;

[1691] A means to automatically generate the continuation of the story using generative AI,

[1692] A means of generating lines and narration using text generation AI,

[1693] A means of proposing multiple storylines,

[1694] means for receiving a deployment selection by a user;

[1695] means for generating a final cartoon based on the selected developments;

[1696] means for displaying the final cartoon to a user;

[1697] means for recommending products based on a user's field;

[1698] means for automatically generating storytelling related to the recommended products;

[1699] means for recognizing the user's emotions in real time;

[1700] A system including:

[1701] (Claim 2)

[1702] The system according to claim 1, further comprising means for presenting a selection of multiple genres based on the story development generated by the generation AI.

[1703] (Claim 3)

[1704] 10. The system of claim 1, further comprising means for pre-processing the user-entered image and story summary data. [Explanation of symbols]

[1705] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for inputting a model image; a means for inputting a story outline; means for receiving and analyzing said images and story summary; A means to automatically generate the continuation of the story using generative AI, A means of generating lines and narration using text generation AI, A means of proposing multiple storylines, means for receiving a deployment selection by a user; means for generating a final cartoon based on the selected developments; means for displaying the final cartoon to a user; A system including:

2. The system according to claim 1 , further comprising means for presenting a selection of a plurality of genres based on the story development generated by the generation AI.

3. 10. The system of claim 1, further comprising means for pre-processing said user-entered image and story summary data.

Images