System
The system uses generative AI to assist users in creating original picture books by generating stories and illustrations based on user input, addressing the challenges of creativity and skill barriers, allowing for easy and efficient digital book creation.
Patent Information
- Application Number
- JP2024133433
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2026-02-20
AI Technical Summary
Parents face challenges in creating original picture books due to the difficulty in coming up with stories and drawing pictures, high costs, and the need for specialized skills, making it difficult for average users to create personalized books.
A system that allows users to input data for creating a picture book, which includes character information and a story outline, using generative AI to automatically generate a story and illustrations, and integrate them into a digital book, which can be distributed to a user terminal.
Enables users to easily and efficiently create original digital picture books that reflect their intentions, reducing the barriers of time, effort, and skill requirements.
Smart Images

Figure 2026030450000001_ABST
Abstract
Description
[Technical Field]
[0001] The technology of the present disclosure relates to a system. [Background technology]
[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]
[0004] Many parents want to create original picture books for their children, but coming up with a story and drawing the pictures is difficult, and the high cost and minimum print run requirements are obstacles. Furthermore, these tasks often require specialized skills, making them difficult for average users. The purpose of this invention is to use generative AI to lower these hurdles and enable anyone to easily create original picture books. [Means for solving the problem]
[0005] The present invention solves the problems by a system including a means for a user to input data for creating an original picture book, a means for transmitting the user's input data to a server, a means by which the server generates a story based on the input data, a means by which the server generates illustrations based on the story, a means for creating a digital picture book by integrating the generated story and illustrations, and a means for distributing the digital picture book to a user terminal. In particular, the data input by the user includes character information and a story outline, and the illustrations generated by the server can be customized based on photos provided by the user, making it easy to create an original picture book that reflects the user's own intentions.
[0006] "User" refers to ordinary consumers who wish to use the system to create original picture books.
[0007] "Data" refers to information entered by the user for creating a picture book, and specifically includes information about characters and a story outline.
[0008] "Server" refers to the computer system that receives user input data and generates the story and illustrations using generative AI.
[0009] "Story" refers to the content of the story that the characters in a picture book unfold.
[0010] "Illustrations" are images within a picture book that are generated based on the story and are used as a visual representation of the story.
[0011] "Generative AI" refers to artificial intelligence algorithms that perform natural language processing and image generation based on input data.
[0012] A "digital picture book" refers to an electronic picture book that includes a story and illustrations created by generative AI based on data entered by the user.
[0013] "Delivery" refers to the transmission of the digital picture book generated by the server to the user's terminal.
[0014] "Terminal" refers to an electronic device such as a smartphone, tablet, or PC that a user uses to operate the system and view the generated digital picture book. [Brief explanation of the drawings]
[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION
[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.
[0017] First, the terms used in the following description will be explained.
[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).
[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.
[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.
[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.
[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."
[0023] [First embodiment]
[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.
[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.
[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.
[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.
[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.
[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0036] This invention is a system in which a user inputs data to create an original picture book, automatically generates a story and illustrations using generation AI, and finally provides the user with a digital picture book.
[0037] System Overview
[0038] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story.
[0039] The information entered through the device is sent to a server, where a generation AI on the server uses it to generate a story and illustrations. Natural language processing technology is used to generate the story, and image generation technology is used to generate the illustrations. The generated story and illustrations are integrated by the server and assembled into a digital picture book. The picture book is then distributed to the device, allowing the user to view it in digital format.
[0040] Specific processing of the program
[0041] The user enters a request
[0042] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0043] The device sends the data to the server
[0044] The data entered by the user is sent from the device to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0045] The server generates the story
[0046] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, Mike finds himself in a magical forest..." The story is customized based on the character traits of the characters and photos provided by the user.
[0047] The server generates the illustrations
[0048] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided photos and specific character attributes. For example, it creates an illustration of a cat based on a photo of Mike.
[0049] The server assembles the picture book data
[0050] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the picture book is properly positioned.
[0051] The server delivers the picture book to the user
[0052] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0053] Specific examples
[0054] Example 1: Creating a picture book for preschoolers
[0055] The user inputs, "I want to write an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "One day, Yuuta meets a mysterious creature in the forest..." and creates illustrations with Yuuta as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the picture book on their smartphone.
[0056] Example 2: Creating an educational picture book for a specific theme
[0057] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "Sakura gets on a spaceship and sets off on a planetary exploration..." and creates illustrations featuring Sakura as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the book on their PC.
[0058] As described above, the system of the present invention provides a means for users to easily create original picture books and view them in digital format.
[0059] The processing flow will be explained below.
[0060] Processing Steps
[0061] Step 1:
[0062] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[0063] Step 2:
[0064] The user enters basic information. The user accesses a form to enter the picture book title, target age, story theme, etc., and fills in each item.
[0065] Step 3:
[0066] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[0067] Step 4:
[0068] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[0069] Step 5:
[0070] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[0071] Step 6:
[0072] The server generates the story. The server analyzes the received data and uses the generation AI to automatically generate a detailed story. For example, if the user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[0073] Step 7:
[0074] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[0075] Step 8:
[0076] The server assembles the picture book data, combines the story and illustrations into a single file, and creates a digital picture book with the appropriate layout. It then applies a layout algorithm to adjust the placement of each page.
[0077] Step 9:
[0078] The server generates the picture book file, exports the completed picture book data in PDF format or a dedicated app display format, and generates the final file.
[0079] Step 10:
[0080] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[0081] Step 11:
[0082] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[0083] This step allows users to easily create and view original digital picture books.
[0084] Example 1
[0085] 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."
[0086] Conventional original picture book creation systems require users to manually create text and illustrations, which takes a lot of time and effort. It is also difficult to consistently create stories and illustrations that fit a specific theme, which can result in a lack of originality and cohesion as intended by the user. Therefore, there is a need for a system that allows users to create original picture books more easily and efficiently.
[0087] 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.
[0088] In this invention, the server includes means for a user to input data for creating an original digital book, means for transmitting the user's input data from a communication device to a computer, means for the computer to generate a story based on the input data, means for the computer to generate images based on the story, means for integrating the generated story and images to create a digital digital book, and means for delivering the digital digital book to the user's communication device, thereby enabling users to easily and efficiently create and view original digital picture books.
[0089] "User" refers to a person who inputs the data necessary to create an original electronic book.
[0090] "Communication devices" are devices for sending and receiving data, including smartphones and personal computers.
[0091] "Computer" refers to a device that includes a server and processor for generating stories and images from data and creating digital e-books.
[0092] A "story" is a collection of textual information created by a generative AI model, and is text data containing the story content.
[0093] "Images" are visual data created by generative AI models, and are illustrations or pictures corresponding to each scene in the story.
[0094] "Digital e-book" refers to a book that integrates generated narrative and images and is created in a digital format, including PDF and dedicated app formats.
[0095] "Input data" refers to information that a user inputs using a communication device, and includes information about characters appearing in the game and an outline of the story.
[0096] "Generative AI model" refers to an artificial intelligence algorithm used to generate stories and images based on prompts entered by a user.
[0097] The present invention is a system that allows users to create original e-books. Specifically, the system allows users to input data, automatically generates stories and images using a generative AI model, and ultimately provides the results to users as a digital e-book.
[0098] System configuration
[0099] Users access the "Picture Book Maker" application using a communication device such as a smartphone or personal computer. In the application, users enter information to create an original e-book tailored to their child or a specific theme. This information includes information about the characters (such as name, age, gender, and photo) and a summary of the story.
[0100] The information entered by the terminal is securely transmitted to the computer (server) using the HTTPS protocol, and the transmitted data is encoded in an appropriate format, such as JSON.
[0101] Specific examples of processing
[0102] The server receives and analyzes the data sent by the user. Based on the analyzed data, a generative AI model (e.g., GPT-4) is used to automatically generate a detailed story. An example of a specific prompt is "Create a story about the adventures of Takeshi the cat." Using this prompt as input, the generative AI generates a specific story such as "One day, Takeshi found himself in a magical forest..."
[0103] Next, the server generates images corresponding to each scene in the story. The illustrations are generated using a generative AI model (e.g., DALL-E or Stable Diffusion). Based on the character photos and characteristics provided by the user, the server automatically creates images appropriate for each scene in the story. For example, an illustration of a scene in which a cat named "Takeshi" is in a magical forest is generated.
[0104] The generated story and illustrations are then integrated by a server and assembled into a digital e-book with the appropriate page layout, using HTML5, CSS3, and JavaScript, before being exported to PDF or a dedicated app.
[0105] The completed digital e-book is then distributed from the server to the user's communication device, where the user can easily view the digital e-book on, for example, a smartphone or personal computer.
[0106] Specific use cases
[0107] Example 1: Creating an e-book for preschoolers
[0108] The user enters, "I want to create an adventure story for my 4-year-old son. The main character will be a character using a photo of my son, named Takeshi, 5 years old," and uploads a related photo. The data is sent from the device to the server. The server uses generative AI to generate a story—"One day, Takeshi meets a mysterious creature in the forest..."—and creates illustrations based on the photos provided by the user. The final e-book can be viewed on a smartphone.
[0109] Example 2: Creating an educational e-book on a specific topic
[0110] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story: "Sakura gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Sakura as the main character based on the photo provided by the user. The final e-book can be viewed on a personal computer.
[0111] As described above, the system of the present invention allows users to easily and efficiently create and view original digital electronic books.
[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0113] Step 1:
[0114] The user prepares input data for creating an original electronic book.
[0115] Specifically, the user launches the "Picture Book Maker" application and enters character information (such as name, age, gender, and photo) and a summary of the story into the input form. After entering this information, the user clicks the "Generate" button to complete the request.
[0116] Input: Character information (e.g., name "Takeshi", age "6 years old", gender "male", photo), story summary (e.g., "A story about the adventures of Takeshi the cat")
[0117] Output: The input data is temporarily saved in the terminal in JSON format.
[0118] Step 2:
[0119] The terminal transmits the user's input data to the server.
[0120] Specifically, the device encodes the input data into JSON format and sends it to the server using the HTTPS protocol. For security reasons, the data is encrypted before transmission.
[0121] Input: User data in JSON format
[0122] Output: The input data sent to the server
[0123] Step 3:
[0124] The server analyzes the received data and generates a story.
[0125] Specifically, the server analyzes the received JSON data and uses a generative AI model (e.g., GPT-4) to automatically generate a detailed story based on the prompt (e.g., "Create a story about the adventures of Takeshi the cat"). The generated story is then stored on the server.
[0126] Input: User data (JSON format), prompt statement
[0127] Output: Generated story (text format)
[0128] Step 4:
[0129] The server generates illustrations for the generated story.
[0130] Specifically, the server uses a generative AI model (e.g., DALL-E or Stable Diffusion) to generate illustrations for each scene in the story. It generates appropriate images based on the character photos and attributes provided by the user.
[0131] Input: Generated story, character photos
[0132] Output: Generated illustration (image format)
[0133] Step 5:
[0134] The server combines the story and illustrations to create a digital e-book.
[0135] Specifically, the server integrates the generated story and illustrations, assembles them into a digital e-book with the appropriate layout for each page using HTML5, CSS3, and JavaScript, and finally exports it to PDF format or a dedicated app display format.
[0136] Input: Generated story, generated illustrations
[0137] Output: Integrated digital e-book (PDF or app format)
[0138] Step 6:
[0139] The server distributes the completed digital e-book to the user.
[0140] Specifically, the server delivers the completed digital e-book to the user's communication device. Delivery methods include sending a download link or allowing the user to view the e-book directly within the app. Users can then view the e-book on their smartphone or personal computer.
[0141] Input: Integrated digital e-book
[0142] Output: Digital e-book delivered to the user's communication device
[0143] (Application example 1)
[0144] 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."
[0145] In conventional picture book creation systems, users are limited to simply viewing the created picture book on a digital device, making it difficult to share the experience in real time. Furthermore, there is a lack of a way to enjoy a personalized experience while actually seeing the background and story of the product in a physical store, making it difficult to attract customers' interest.
[0146] 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.
[0147] In this invention, the server includes a means for a user to input data for creating an original picture book, a means for transmitting the user's input data to the server, a means for the server to generate a story based on the input data, a means for the server to generate illustrations based on the story, a means for integrating the generated story and illustrations to create a digital picture book, and a means for delivering the digital picture book to a visual device and enabling in-store browsing. This makes it possible to provide customers in a physical store with personalized stories related to products in real time and allow them to instantly experience them through their visual device.
[0148] A "user terminal" is a device used by a user to input data, and includes a smartphone, tablet, personal computer, etc.
[0149] The "server" is a central processing unit that receives data sent from user terminals and generates stories and illustrations.
[0150] "Means for inputting data" refers to an input device or interface that receives information entered by a user, including a keyboard, touch screen, voice recognition, etc.
[0151] "Means for transmitting data" refers to the communication functions and protocols for transmitting data input from the user terminal to the server.
[0152] "Means for generating a story" refers to algorithms or generative AI that automatically create story content based on input data.
[0153] "Means for generating illustrations" refers to image generation algorithms or generative AI that create visual illustrations based on the generated story.
[0154] "Digital picture books" refer to picture books that integrate generated stories and illustrations and are provided in digital format.
[0155] A "visual device" is a device that allows a user to visually view a digital picture book, and includes smart glasses, head-mounted displays, and the like.
[0156] "In-store browsing" refers to the act of viewing product information and related stories in real time using visual devices in a physical store.
[0157] System Overview
[0158] This invention is a system that allows users to input data to create original picture books, automatically generates stories and illustrations using generative AI, and finally provides the users with a digital picture book. This system mainly utilizes visual devices such as smart glasses to provide a real-time experience in a physical store.
[0159] Specific processing of the program
[0160] The user enters a request
[0161] The user launches the "Smart Picture Book Maker" application through the smart glasses and inputs basic information about the picture book, information about the characters, and a summary of the story. For example, the user can input the character's name, age, and gender, and then enter details of the story's plot and key events. After completing the input, the user clicks the "Generate" button, and the data is sent to the server.
[0162] The device sends the data to the server
[0163] The data entered by the user is sent from the smart glasses to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol (e.g., HTTPS).
[0164] The server generates the story
[0165] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about a cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, the cat steps into a magical forest..." The generation AI uses natural language processing technology.
[0166] The server generates the illustrations
[0167] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided images and specific character attributes. For example, a prompt such as "Draw a cat based on a photo of the character" can be used to generate a new image.
[0168] The server assembles the picture book data
[0169] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the digital picture book is properly positioned.
[0170] The server delivers the picture book to the user
[0171] The completed digital storybook is then delivered to a visual device, where users can view it through smart glasses.
[0172] Specific use cases
[0173] Example 1: Creating a picture book for preschoolers
[0174] The user inputs, "I want to create an adventure story for a 3-year-old child. The main character will be a character using a child's photo, named Taro, 4 years old." The data is sent from the smart glasses to the server. The server uses a generative AI to generate a story such as, "One day, Taro meets a mysterious creature in the forest..." and creates illustrations featuring Taro as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by wearing the smart glasses.
[0175] Example 2: Creating an educational picture book for a specific theme
[0176] The user inputs, "I want to create a story that will teach children in the early grades of elementary school about space. The main character will be a character using a child's photo, named Hanako, 7 years old." The data is sent from the smart glasses to the server. The server uses a generation AI to generate a story such as "Hanako gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Hanako as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by putting on the smart glasses.
[0177] Prompt Sentence Examples
[0178] "I want to write a story about an adventure in the forest for my four-year-old son. The main character is a character made from a photo of my son, named Taro, who is five years old."
[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0180] Step 1:
[0181] The user puts on the smart glasses and launches the "Smart Picture Book Maker" application. The user enters character information and a story outline for the original picture book through the application's input screen. For example, the user enters information such as the character's name, age, gender, and related images into the form, followed by a detailed description of the story's plot and important events. When the user clicks the "Generate" button, this data is prepared.
[0182] Input: Character information (name, age, gender, image), story summary
[0183] Output: A data object in JSON format
[0184] Step 2:
[0185] The device (smart glasses) sends the data entered by the user to the server. The device encodes the entered data into JSON format and sends it to the server using a secure communication protocol (e.g., HTTPS).
[0186] Input: A JSON formatted data object
[0187] Output: Send data to the server
[0188] Step 3:
[0189] The server analyzes the received data and automatically generates a detailed story based on the generative AI model. Natural language processing technology is used to generate the story, and the development of the story is determined based on the input data. For example, if the generative AI receives the prompt "A cat goes on an adventure," it will generate a storyline like "One day, a cat steps into a magical forest..."
[0190] Input: A JSON formatted data object
[0191] Output: Generated story (text data)
[0192] Step 4:
[0193] The server generates illustrations for each scene in the generated story. The AI uses built-in image generation technology to create customized illustrations based on user-provided images and character attributes. For example, images are generated according to specific instructions, such as "draw a cat based on a photo of the character."
[0194] Input: Generated story (text data), character information (images)
[0195] Output: Generated illustration (image data)
[0196] Step 5:
[0197] The server integrates the generated story and illustrations and creates a digital picture book based on an appropriate layout algorithm. The story text and illustrations are arranged appropriately for each page, creating a digital picture book format. The book can then be exported in PDF format or a dedicated app display format.
[0198] Input: Generated story (text data), generated illustrations (image data)
[0199] Output: Digital picture book (PDF format or dedicated app format)
[0200] Step 6:
[0201] The server delivers the completed digital picture book to a visual device (smart glasses), and the user can view the received digital picture book through the smart glasses.
[0202] Input: Digital picture book (PDF format or dedicated app format)
[0203] Output: Delivery to smart glasses, user viewing of digital picture books
[0204] 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.
[0205] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[0206] System Overview
[0207] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[0208] The device sends the input information and analyzed emotional data to the server, where the server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing users to view it digitally.
[0209] Specific processing of the program
[0210] The user enters a request
[0211] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0212] Emotion recognition by emotion engine
[0213] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[0214] The device sends the data to the server
[0215] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0216] The server generates the story and illustrations
[0217] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[0218] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[0219] The server assembles the picture book data
[0220] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0221] The server delivers the picture book to the user
[0222] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0223] Specific examples
[0224] Example 1: Creating a picture book for preschoolers
[0225] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[0226] Example 2: Creating an educational picture book
[0227] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[0228] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[0229] The processing flow will be explained below.
[0230] Processing Steps
[0231] Step 1:
[0232] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[0233] Step 2:
[0234] The user enters basic information. The user accesses a form to enter the book title, target age group, story theme, etc., and fills in each item.
[0235] Step 3:
[0236] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[0237] Step 4:
[0238] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[0239] Step 5:
[0240] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[0241] Step 6:
[0242] The device collects the user's emotional data. It uses the device's camera and microphone to collect the user's facial expression data and voice data.
[0243] Step 7:
[0244] The device transmits the collected emotion data to the server, which then encodes the data in an appropriate format and transmits it to the server using a secure communication protocol.
[0245] Step 8:
[0246] The server generates the story. The server analyzes the received user data and emotional data, and uses the generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[0247] Step 9:
[0248] The server adjusts the tone of the story based on the emotion data. The server adjusts the tone of the story (e.g., fun, moving, suspenseful) according to the user's emotion.
[0249] Step 10:
[0250] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[0251] Step 11:
[0252] The server adjusts the facial expressions of the illustrations based on the emotional data, and adjusts the character's facial expressions and the tone of the environment based on the user's emotional data.
[0253] Step 12:
[0254] The server assembles the picture book data. The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0255] Step 13:
[0256] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[0257] Step 14:
[0258] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[0259] This step allows users to easily create original digital picture books and enjoy content customized to their emotions.
[0260] Example 2
[0261] 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."
[0262] Conventional digital picture book creation systems lack support for users to easily create original stories and illustrations, making it difficult to provide personalized content that reflects the user's emotions. Furthermore, the lack of a customization function based on the user's emotions makes it difficult to create picture books optimized for individual users.
[0263] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input data for creating an original picture book; means for a terminal to acquire and transmit the user's input data and emotional data; a server that receives the input data and emotional data; means by the server that generates a story based on the input data and emotional data; means by the server that generates illustrations based on the story; means for creating a digital picture book by integrating the generated story and illustrations; and means for delivering the digital picture book to a user terminal. This makes it possible to easily create and deliver an original digital picture book that is individually optimized while reflecting the user's emotions.
[0264] "User" refers to a person who uses the system to create an original picture book.
[0265] An "original picture book" refers to a picture book that includes a unique story and illustrations generated based on data and emotional data entered by the user.
[0266] "Data" refers to the information that users input into the system, including character information and story outlines.
[0267] "Emotional data" refers to information about the emotional state obtained by analyzing the user's facial expressions and voice.
[0268] "Terminal" refers to a device that allows a user to input and send data, and specifically includes smartphones and PCs.
[0269] The term "server" refers to a computer device that receives data and emotional data sent by users, generates stories and illustrations, and integrates picture books.
[0270] "Generative AI" refers to artificial intelligence technology that automatically generates stories based on user input data and emotional data.
[0271] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to obtain emotional data.
[0272] "Story" refers to the content of the story generated by the generative AI.
[0273] "Illustrations" refers to illustrations created by the server based on the generated story.
[0274] "Digital picture book" refers to a picture book created in digital format that integrates generated stories and illustrations.
[0275] "Distribution" refers to the process of sending the completed digital picture book to the user's terminal.
[0276] The present invention is a system that allows users to input data for creating an original picture book, automatically generates a story and illustrations using a generative AI model and an emotion engine, and finally provides the user with a digital picture book. This system is characterized by its ability to recognize the user's emotions and customize the content accordingly. A specific embodiment of this system is described below.
[0277] System Overview
[0278] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and image) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and during use.
[0279] The device sends the input information and analyzed emotional data to the server, where the generative AI model and emotion engine on the server generate a story and illustrations based on the information. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[0280] Specific program description
[0281] The user enters a request
[0282] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into a form, and then enters details of the story's plot and important events. The input data is confirmed by clicking the "Generate" button.
[0283] Emotion recognition by emotion engine
[0284] When a user inputs information, the device captures emotion data from the user's facial expressions and voice via the camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state. This emotion data is sent to the server along with the input data. The emotion engine can use, for example, Microsoft's Azure Emotion API.
[0285] The device sends the data to the server
[0286] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format such as JSON and sent using a secure communication protocol such as HTTPS. The device can be a smartphone or a PC.
[0287] The server generates the story and illustrations
[0288] The server analyzes the received data and automatically generates a detailed story using a generative AI model (e.g., OpenAI's GPT-3). The generated story can be adjusted in tone and content based on emotions recognized by an emotion engine. For example, if the user expresses positive emotions, the server can generate an upbeat and fun story.
[0289] The server also reflects the data from the emotion engine when generating illustrations. For example, based on the image provided by the user, the facial expression and background of the generated character will change according to the user's emotional state. This means that if the user provides an image of a smiling character, the character will also be drawn smiling.
[0290] The server assembles the picture book data
[0291] The generated story and illustrations are then integrated by a server, which then assembles the digital picture book into a suitable layout. The server uses a layout algorithm (e.g., Adobe InDesign Server) to determine the placement of each page, resulting in a beautiful and coherent digital picture book.
[0292] The server delivers the picture book to the user
[0293] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server protects the user's privacy by transmitting data using a secure communication protocol. Users receive the digital picture book on their smartphone or PC and can view it using a dedicated app or PDF reader.
[0294] Examples of prompt statements
[0295] "I want to create an adventure story for my 4-year-old son. The main character is a character made using a photo of my son, named Yuuta, who is 5 years old. The story will have a cheerful and fun adventure theme. The generated character's expressions and environment will be based on positive emotions."
[0296] The above is a specific embodiment for implementing the system of the present invention, which allows users to easily create and view original digital picture books.
[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0298] System program processing flow
[0299] Step 1: User enters request
[0300] Step 2: Emotion recognition by the emotion engine
[0301] Step 3: The device sends the data to the server
[0302] Step 4: The server generates the story and illustrations
[0303] Step 5: The server assembles the picture book data
[0304] Step 6: The server delivers the picture book to the user
[0305] Specific explanation of each processing step
[0306] Step 1: User enters request
[0307] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into the form, followed by details about the story's plot and important events. Clicking the "Generate" button finalizes the input data. The input data is saved on the device and used in the next step.
[0308] Input: Character information (name, age, gender, image), story summary
[0309] Output: Confirmed input data
[0310] Step 2: Emotion recognition by the emotion engine
[0311] When the user enters information, the device collects the user's facial expressions and voice through the camera and microphone. An emotion engine (e.g., Microsoft's Azure Emotion API) analyzes this data and recognizes the user's current emotional state. The analysis results are stored on the device and used in the next step.
[0312] Input: facial expression data, voice data
[0313] Output: Parsed emotion data
[0314] Step 3: The device sends the data to the server
[0315] The device sends the confirmed input data and analyzed emotion data to the server. This data is encoded in JSON format and securely transmitted using HTTPS. The server stores the received data for analysis.
[0316] Input: Confirmed input data, analyzed emotion data
[0317] Output: Data sent to the server
[0318] Step 4: The server generates the story and illustrations
[0319] The server analyzes the input data and emotional data it receives and automatically generates a story using a generative AI model (e.g., OpenAI's GPT-3). The tone and content of the generated story are adjusted based on the emotional data. The server then generates illustrations in a similar manner. The illustrations are customized based on the images and emotional data provided by the user.
[0320] Input: Input data, emotion data
[0321] Output: Generated story and illustrations
[0322] Step 5: The server assembles the picture book data
[0323] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. The server uses a layout algorithm (e.g., Adobe InDesign server) to set the layout of each page, and the story and illustrations are beautifully arranged.
[0324] Input: Generated story, illustrations
[0325] Output: Digital picture book data
[0326] Step 6: The server delivers the picture book to the user
[0327] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server securely transmits data using HTTPS, and the user can receive and view the digital picture book on their smartphone or PC.
[0328] Input: Digital picture book data
[0329] Output: Digital picture book delivered to the user's device
[0330] These are the specific processing steps of the program for this system, which allows users to easily create and view original digital picture books.
[0331] (Application example 2)
[0332] 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."
[0333] Conventional digital picture book generation systems have struggled to provide an individualized experience that reflects the user's emotions. In certain situations, the story and illustrations are not adjusted based on the user's emotions, resulting in a lack of personalized content. Furthermore, the lack of technology to acquire user emotion data in real time and apply it to picture book production makes it difficult to generate picture books that appeal to the user's desired emotions.
[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input data for creating an original picture book, means for transmitting the user's input data to the server, means for the server to generate a story based on the input data, means for the server to generate illustrations based on the story, means for integrating the generated story and illustrations to create a digital picture book, means for delivering the digital picture book to a user terminal, and means having an emotion engine that acquires and analyzes emotion data and adjusting the tone and content of the story and illustrations based on the emotion data. This makes it possible to generate a personalized digital picture book that matches the user's emotions.
[0335] "User input data" refers to data such as character information and story outlines that are input by the user to create an original picture book.
[0336] A "server" is a computer system that receives user input data and generates stories and illustrations to create a digital picture book.
[0337] "Story generation means" refers to a means by which the server automatically creates a story based on user input data.
[0338] The "illustration generating means" is a means for creating illustrations based on the story generated by the server.
[0339] The "digital picture book creation means" is a means for creating a digital picture book by integrating the generated story and illustrations.
[0340] "Distribution means" refers to a means for transmitting the completed digital picture book to the user terminal.
[0341] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice data and recognizes their emotional state.
[0342] "Emotion data" is data that indicates the user's emotional state, obtained as a result of analysis by the emotion engine.
[0343] "Customization" refers to adjusting the content and tone of the story and illustrations based on user-provided photographs and emotional data.
[0344] "User terminal" refers to devices such as smartphones, tablets, and PCs used for creating and viewing picture books.
[0345] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[0346] System Overview
[0347] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[0348] The device sends the input information and analyzed emotional data to the server. The server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[0349] Specific processing of the program
[0350] The user enters a request
[0351] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0352] Emotion recognition by emotion engine
[0353] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[0354] The device sends the data to the server
[0355] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0356] The server generates the story and illustrations
[0357] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[0358] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[0359] The server assembles the picture book data
[0360] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0361] The server delivers the picture book to the user
[0362] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0363] Specific examples
[0364] Example 1: Creating a picture book for preschoolers
[0365] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[0366] Example 2: Creating an educational picture book
[0367] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[0368] Example of input prompt for generative AI model
[0369] User information: Character name is "Yuta", age is 5, gender is male. Story summary is "One day, Yuuta encounters a mysterious creature in the forest."
[0370] Emotion data: The user is smiling when typing, and positive emotions are detected.
[0371] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[0372] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0373] Step 1:
[0374] The user starts the "Picture Book Maker" application and inputs character information and a story outline. Specifically, the user fills in a dedicated input form with the character's name, age, gender, photo, story summary, etc. This generates user input data.
[0375] Step 2:
[0376] After the user completes the input data, the device will use the camera and microphone to collect the user's facial expressions and voice. These emotion data will be sent to the emotion engine and used to analyze the user's emotional state. Emotion data will be generated as a result of the analysis.
[0377] Step 3:
[0378] The device encodes user input data and emotion data in JSON format and sends it to the server using a secure communication protocol. The input data is the user input data and emotion data, and the output is the data sent to the server.
[0379] Step 4:
[0380] The server analyzes the received user input data and emotional data. Specifically, it uses generative AI to automatically generate a detailed story based on the user input data. The emotional engine analyzes the emotional data and adjusts the tone and content of the story. For example, if positive emotions are detected, a fun adventure story will be generated. The input data are user input data and emotional data, and the output is the generated story.
[0381] Step 5:
[0382] The server generates illustrations based on the story it generates. Characters are customized based on photos provided by the user, and backgrounds and other visual elements are generated using a generative AI model. Emotional data is also taken into account during this process, and the illustrations are adjusted to be more emotionally appealing. The input data are the story, user photos, and emotional data, and the output is the generated illustration.
[0383] Step 6:
[0384] The server integrates the generated story and illustrations and assembles them into a digital picture book. It applies a layout algorithm to properly position each page and create the final digital picture book file. The input data are the generated story and illustrations, and the output is the digital picture book data.
[0385] Step 7:
[0386] The server exports the completed digital picture book data in PDF format or a dedicated app format and distributes it to the user's device. The user receives this and views the digital picture book on their smartphone or PC. The input data is the digital picture book data, and the output is a digital picture book distributed to the user's device.
[0387] 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.
[0388] 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.
[0389] 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.
[0390] [Second embodiment]
[0391] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0392] 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.
[0393] 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).
[0394] 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.
[0395] 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.
[0396] 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).
[0397] 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.
[0398] 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.
[0399] 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.
[0400] 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.
[0401] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0402] 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."
[0403] This invention is a system in which a user inputs data to create an original picture book, automatically generates a story and illustrations using generation AI, and finally provides the user with a digital picture book.
[0404] System Overview
[0405] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story.
[0406] The information entered through the device is sent to a server, where a generation AI on the server uses it to generate a story and illustrations. Natural language processing technology is used to generate the story, and image generation technology is used to generate the illustrations. The generated story and illustrations are integrated by the server and assembled into a digital picture book. The picture book is then distributed to the device, allowing the user to view it in digital format.
[0407] Specific processing of the program
[0408] The user enters a request
[0409] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0410] The device sends the data to the server
[0411] The data entered by the user is sent from the device to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0412] The server generates the story
[0413] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, Mike finds himself in a magical forest..." The story is customized based on the character traits of the characters and photos provided by the user.
[0414] The server generates the illustrations
[0415] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided photos and specific character attributes. For example, it creates an illustration of a cat based on a photo of Mike.
[0416] The server assembles the picture book data
[0417] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the picture book is properly positioned.
[0418] The server delivers the picture book to the user
[0419] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0420] Specific examples
[0421] Example 1: Creating a picture book for preschoolers
[0422] The user inputs, "I want to write an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "One day, Yuuta meets a mysterious creature in the forest..." and creates illustrations with Yuuta as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the picture book on their smartphone.
[0423] Example 2: Creating an educational picture book for a specific theme
[0424] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "Sakura gets on a spaceship and sets off on a planetary exploration..." and creates illustrations featuring Sakura as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the book on their PC.
[0425] As described above, the system of the present invention provides a means for users to easily create original picture books and view them in digital format.
[0426] The processing flow will be explained below.
[0427] Processing Steps
[0428] Step 1:
[0429] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[0430] Step 2:
[0431] The user enters basic information. The user accesses a form to enter the picture book title, target age, story theme, etc., and fills in each item.
[0432] Step 3:
[0433] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[0434] Step 4:
[0435] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[0436] Step 5:
[0437] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[0438] Step 6:
[0439] The server generates the story. The server analyzes the received data and uses the generation AI to automatically generate a detailed story. For example, if the user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[0440] Step 7:
[0441] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[0442] Step 8:
[0443] The server assembles the picture book data, combines the story and illustrations into a single file, and creates a digital picture book with the appropriate layout. It then applies a layout algorithm to adjust the placement of each page.
[0444] Step 9:
[0445] The server generates the picture book file, exports the completed picture book data in PDF format or a dedicated app display format, and generates the final file.
[0446] Step 10:
[0447] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[0448] Step 11:
[0449] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[0450] This step allows users to easily create and view original digital picture books.
[0451] Example 1
[0452] 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."
[0453] Conventional original picture book creation systems require users to manually create text and illustrations, which takes a lot of time and effort. It is also difficult to consistently create stories and illustrations that fit a specific theme, which can result in a lack of originality and cohesion as intended by the user. Therefore, there is a need for a system that allows users to create original picture books more easily and efficiently.
[0454] 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.
[0455] In this invention, the server includes means for a user to input data for creating an original digital book, means for transmitting the user's input data from a communication device to a computer, means for the computer to generate a story based on the input data, means for the computer to generate images based on the story, means for integrating the generated story and images to create a digital digital book, and means for delivering the digital digital book to the user's communication device, thereby enabling users to easily and efficiently create and view original digital picture books.
[0456] "User" refers to a person who inputs the data necessary to create an original electronic book.
[0457] "Communication devices" are devices for sending and receiving data, including smartphones and personal computers.
[0458] "Computer" refers to a device that includes a server and processor for generating stories and images from data and creating digital e-books.
[0459] A "story" is a collection of textual information created by a generative AI model, and is text data containing the story content.
[0460] "Images" are visual data created by generative AI models, and are illustrations or pictures corresponding to each scene in the story.
[0461] "Digital e-book" refers to a book that integrates generated narrative and images and is created in a digital format, including PDF and dedicated app formats.
[0462] "Input data" refers to information that a user inputs using a communication device, and includes information about characters appearing in the game and an outline of the story.
[0463] "Generative AI model" refers to an artificial intelligence algorithm used to generate stories and images based on prompts entered by a user.
[0464] The present invention is a system that allows users to create original e-books. Specifically, the system allows users to input data, automatically generates stories and images using a generative AI model, and ultimately provides the results to users as a digital e-book.
[0465] System configuration
[0466] Users access the "Picture Book Maker" application using a communication device such as a smartphone or personal computer. In the application, users enter information to create an original e-book tailored to their child or a specific theme. This information includes information about the characters (such as name, age, gender, and photo) and a summary of the story.
[0467] The information entered by the terminal is securely transmitted to the computer (server) using the HTTPS protocol, and the transmitted data is encoded in an appropriate format, such as JSON.
[0468] Specific examples of processing
[0469] The server receives and analyzes the data sent by the user. Based on the analyzed data, a generative AI model (e.g., GPT-4) is used to automatically generate a detailed story. An example of a specific prompt is "Create a story about the adventures of Takeshi the cat." Using this prompt as input, the generative AI generates a specific story such as "One day, Takeshi found himself in a magical forest..."
[0470] Next, the server generates images corresponding to each scene in the story. The illustrations are generated using a generative AI model (e.g., DALL-E or Stable Diffusion). Based on the character photos and characteristics provided by the user, the server automatically creates images appropriate for each scene in the story. For example, an illustration of a scene in which a cat named "Takeshi" is in a magical forest is generated.
[0471] The generated story and illustrations are then integrated by a server and assembled into a digital e-book with the appropriate page layout, using HTML5, CSS3, and JavaScript, before being exported to PDF or a dedicated app.
[0472] The completed digital e-book is then distributed from the server to the user's communication device, where the user can easily view the digital e-book on, for example, a smartphone or personal computer.
[0473] Specific use cases
[0474] Example 1: Creating an e-book for preschoolers
[0475] The user enters, "I want to create an adventure story for my 4-year-old son. The main character will be a character using a photo of my son, named Takeshi, 5 years old," and uploads a related photo. The data is sent from the device to the server. The server uses generative AI to generate a story—"One day, Takeshi meets a mysterious creature in the forest..."—and creates illustrations based on the photos provided by the user. The final e-book can be viewed on a smartphone.
[0476] Example 2: Creating an educational e-book on a specific topic
[0477] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story: "Sakura gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Sakura as the main character based on the photo provided by the user. The final e-book can be viewed on a personal computer.
[0478] As described above, the system of the present invention allows users to easily and efficiently create and view original digital electronic books.
[0479] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0480] Step 1:
[0481] The user prepares input data for creating an original electronic book.
[0482] Specifically, the user launches the "Picture Book Maker" application and enters character information (such as name, age, gender, and photo) and a summary of the story into the input form. After entering this information, the user clicks the "Generate" button to complete the request.
[0483] Input: Character information (e.g., name "Takeshi", age "6 years old", gender "male", photo), story summary (e.g., "A story about the adventures of Takeshi the cat")
[0484] Output: The input data is temporarily saved in the terminal in JSON format.
[0485] Step 2:
[0486] The terminal transmits the user's input data to the server.
[0487] Specifically, the device encodes the input data into JSON format and sends it to the server using the HTTPS protocol. For security reasons, the data is encrypted before transmission.
[0488] Input: User data in JSON format
[0489] Output: The input data sent to the server
[0490] Step 3:
[0491] The server analyzes the received data and generates a story.
[0492] Specifically, the server analyzes the received JSON data and uses a generative AI model (e.g., GPT-4) to automatically generate a detailed story based on the prompt (e.g., "Create a story about the adventures of Takeshi the cat"). The generated story is then stored on the server.
[0493] Input: User data (JSON format), prompt statement
[0494] Output: Generated story (text format)
[0495] Step 4:
[0496] The server generates illustrations for the generated story.
[0497] Specifically, the server uses a generative AI model (e.g., DALL-E or Stable Diffusion) to generate illustrations for each scene in the story. It generates appropriate images based on the character photos and attributes provided by the user.
[0498] Input: Generated story, character photos
[0499] Output: Generated illustration (image format)
[0500] Step 5:
[0501] The server combines the story and illustrations to create a digital e-book.
[0502] Specifically, the server integrates the generated story and illustrations, assembles them into a digital e-book with the appropriate layout for each page using HTML5, CSS3, and JavaScript, and finally exports it to PDF format or a dedicated app display format.
[0503] Input: Generated story, generated illustrations
[0504] Output: Integrated digital e-book (PDF or app format)
[0505] Step 6:
[0506] The server distributes the completed digital e-book to the user.
[0507] Specifically, the server delivers the completed digital e-book to the user's communication device. Delivery methods include sending a download link or allowing the user to view the e-book directly within the app. Users can then view the e-book on their smartphone or personal computer.
[0508] Input: Integrated digital e-book
[0509] Output: Digital e-book delivered to the user's communication device
[0510] (Application example 1)
[0511] 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."
[0512] In conventional picture book creation systems, users are limited to simply viewing the created picture book on a digital device, making it difficult to share the experience in real time. Furthermore, there is a lack of a way to enjoy a personalized experience while actually seeing the background and story of the product in a physical store, making it difficult to attract customers' interest.
[0513] 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.
[0514] In this invention, the server includes a means for a user to input data for creating an original picture book, a means for transmitting the user's input data to the server, a means for the server to generate a story based on the input data, a means for the server to generate illustrations based on the story, a means for integrating the generated story and illustrations to create a digital picture book, and a means for delivering the digital picture book to a visual device and enabling in-store browsing. This makes it possible to provide customers in a physical store with personalized stories related to products in real time and allow them to instantly experience them through their visual device.
[0515] A "user terminal" is a device used by a user to input data, and includes a smartphone, tablet, personal computer, etc.
[0516] The "server" is a central processing unit that receives data sent from user terminals and generates stories and illustrations.
[0517] "Means for inputting data" refers to an input device or interface that receives information entered by a user, including a keyboard, touch screen, voice recognition, etc.
[0518] "Means for transmitting data" refers to the communication functions and protocols for transmitting data input from the user terminal to the server.
[0519] "Means for generating a story" refers to algorithms or generative AI that automatically create story content based on input data.
[0520] "Means for generating illustrations" refers to image generation algorithms or generative AI that create visual illustrations based on the generated story.
[0521] "Digital picture books" refer to picture books that integrate generated stories and illustrations and are provided in digital format.
[0522] A "visual device" is a device that allows a user to visually view a digital picture book, and includes smart glasses, head-mounted displays, and the like.
[0523] "In-store browsing" refers to the act of viewing product information and related stories in real time using visual devices in a physical store.
[0524] System Overview
[0525] This invention is a system that allows users to input data to create original picture books, automatically generates stories and illustrations using generative AI, and finally provides the users with a digital picture book. This system mainly utilizes visual devices such as smart glasses to provide a real-time experience in a physical store.
[0526] Specific processing of the program
[0527] The user enters a request
[0528] The user launches the "Smart Picture Book Maker" application through the smart glasses and inputs basic information about the picture book, information about the characters, and a summary of the story. For example, the user can input the character's name, age, and gender, and then enter details of the story's plot and key events. After completing the input, the user clicks the "Generate" button, and the data is sent to the server.
[0529] The device sends the data to the server
[0530] The data entered by the user is sent from the smart glasses to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol (e.g., HTTPS).
[0531] The server generates the story
[0532] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about a cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, the cat steps into a magical forest..." The generation AI uses natural language processing technology.
[0533] The server generates the illustrations
[0534] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided images and specific character attributes. For example, a prompt such as "Draw a cat based on a photo of the character" can be used to generate a new image.
[0535] The server assembles the picture book data
[0536] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the digital picture book is properly positioned.
[0537] The server delivers the picture book to the user
[0538] The completed digital storybook is then delivered to a visual device, where users can view it through smart glasses.
[0539] Specific use cases
[0540] Example 1: Creating a picture book for preschoolers
[0541] The user inputs, "I want to create an adventure story for a 3-year-old child. The main character will be a character using a child's photo, named Taro, 4 years old." The data is sent from the smart glasses to the server. The server uses a generative AI to generate a story such as, "One day, Taro meets a mysterious creature in the forest..." and creates illustrations featuring Taro as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by wearing the smart glasses.
[0542] Example 2: Creating an educational picture book for a specific theme
[0543] The user inputs, "I want to create a story that will teach children in the early grades of elementary school about space. The main character will be a character using a child's photo, named Hanako, 7 years old." The data is sent from the smart glasses to the server. The server uses a generation AI to generate a story such as "Hanako gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Hanako as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by putting on the smart glasses.
[0544] Prompt Sentence Examples
[0545] "I want to write a story about an adventure in the forest for my four-year-old son. The main character is a character made from a photo of my son, named Taro, who is five years old."
[0546] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0547] Step 1:
[0548] The user puts on the smart glasses and launches the "Smart Picture Book Maker" application. The user enters character information and a story outline for the original picture book through the application's input screen. For example, the user enters information such as the character's name, age, gender, and related images into the form, followed by a detailed description of the story's plot and important events. When the user clicks the "Generate" button, this data is prepared.
[0549] Input: Character information (name, age, gender, image), story summary
[0550] Output: A data object in JSON format
[0551] Step 2:
[0552] The device (smart glasses) sends the data entered by the user to the server. The device encodes the entered data into JSON format and sends it to the server using a secure communication protocol (e.g., HTTPS).
[0553] Input: A JSON formatted data object
[0554] Output: Send data to the server
[0555] Step 3:
[0556] The server analyzes the received data and automatically generates a detailed story based on the generative AI model. Natural language processing technology is used to generate the story, and the development of the story is determined based on the input data. For example, if the generative AI receives the prompt "A cat goes on an adventure," it will generate a storyline like "One day, a cat steps into a magical forest..."
[0557] Input: A JSON formatted data object
[0558] Output: Generated story (text data)
[0559] Step 4:
[0560] The server generates illustrations for each scene in the generated story. The AI uses built-in image generation technology to create customized illustrations based on user-provided images and character attributes. For example, images are generated according to specific instructions, such as "draw a cat based on a photo of the character."
[0561] Input: Generated story (text data), character information (images)
[0562] Output: Generated illustration (image data)
[0563] Step 5:
[0564] The server integrates the generated story and illustrations and creates a digital picture book based on an appropriate layout algorithm. The story text and illustrations are arranged appropriately for each page, creating a digital picture book format. The book can then be exported in PDF format or a dedicated app display format.
[0565] Input: Generated story (text data), generated illustrations (image data)
[0566] Output: Digital picture book (PDF format or dedicated app format)
[0567] Step 6:
[0568] The server delivers the completed digital picture book to a visual device (smart glasses), and the user can view the received digital picture book through the smart glasses.
[0569] Input: Digital picture book (PDF format or dedicated app format)
[0570] Output: Delivery to smart glasses, user viewing of digital picture books
[0571] 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.
[0572] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[0573] System Overview
[0574] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[0575] The device sends the input information and analyzed emotional data to the server, where the server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing users to view it digitally.
[0576] Specific processing of the program
[0577] The user enters a request
[0578] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0579] Emotion recognition by emotion engine
[0580] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[0581] The device sends the data to the server
[0582] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0583] The server generates the story and illustrations
[0584] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[0585] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[0586] The server assembles the picture book data
[0587] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0588] The server delivers the picture book to the user
[0589] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0590] Specific examples
[0591] Example 1: Creating a picture book for preschoolers
[0592] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[0593] Example 2: Creating an educational picture book
[0594] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[0595] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[0596] The processing flow will be explained below.
[0597] Processing Steps
[0598] Step 1:
[0599] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[0600] Step 2:
[0601] The user enters basic information. The user accesses a form to enter the book title, target age group, story theme, etc., and fills in each item.
[0602] Step 3:
[0603] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[0604] Step 4:
[0605] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[0606] Step 5:
[0607] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[0608] Step 6:
[0609] The device collects the user's emotional data. It uses the device's camera and microphone to collect the user's facial expression data and voice data.
[0610] Step 7:
[0611] The device transmits the collected emotion data to the server, which then encodes the data in an appropriate format and transmits it to the server using a secure communication protocol.
[0612] Step 8:
[0613] The server generates the story. The server analyzes the received user data and emotional data, and uses the generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[0614] Step 9:
[0615] The server adjusts the tone of the story based on the emotion data. The server adjusts the tone of the story (e.g., fun, moving, suspenseful) according to the user's emotion.
[0616] Step 10:
[0617] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[0618] Step 11:
[0619] The server adjusts the facial expressions of the illustrations based on the emotional data, and adjusts the character's facial expressions and the tone of the environment based on the user's emotional data.
[0620] Step 12:
[0621] The server assembles the picture book data. The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0622] Step 13:
[0623] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[0624] Step 14:
[0625] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[0626] This step allows users to easily create original digital picture books and enjoy content customized to their emotions.
[0627] Example 2
[0628] 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."
[0629] Conventional digital picture book creation systems lack support for users to easily create original stories and illustrations, making it difficult to provide personalized content that reflects the user's emotions. Furthermore, the lack of a customization function based on the user's emotions makes it difficult to create picture books optimized for individual users.
[0630] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input data for creating an original picture book; means for a terminal to acquire and transmit the user's input data and emotional data; a server that receives the input data and emotional data; means by the server that generates a story based on the input data and emotional data; means by the server that generates illustrations based on the story; means for creating a digital picture book by integrating the generated story and illustrations; and means for delivering the digital picture book to a user terminal. This makes it possible to easily create and deliver an original digital picture book that is individually optimized while reflecting the user's emotions.
[0631] "User" refers to a person who uses the system to create an original picture book.
[0632] An "original picture book" refers to a picture book that includes a unique story and illustrations generated based on data and emotional data entered by the user.
[0633] "Data" refers to the information that users input into the system, including character information and story outlines.
[0634] "Emotional data" refers to information about the emotional state obtained by analyzing the user's facial expressions and voice.
[0635] "Terminal" refers to a device that allows a user to input and send data, and specifically includes smartphones and PCs.
[0636] The term "server" refers to a computer device that receives data and emotional data sent by users, generates stories and illustrations, and integrates picture books.
[0637] "Generative AI" refers to artificial intelligence technology that automatically generates stories based on user input data and emotional data.
[0638] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to obtain emotional data.
[0639] "Story" refers to the content of the story generated by the generative AI.
[0640] "Illustrations" refers to illustrations created by the server based on the generated story.
[0641] "Digital picture book" refers to a picture book created in digital format that integrates generated stories and illustrations.
[0642] "Distribution" refers to the process of sending the completed digital picture book to the user's terminal.
[0643] The present invention is a system that allows users to input data for creating an original picture book, automatically generates a story and illustrations using a generative AI model and an emotion engine, and finally provides the user with a digital picture book. This system is characterized by its ability to recognize the user's emotions and customize the content accordingly. A specific embodiment of this system is described below.
[0644] System Overview
[0645] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and image) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and during use.
[0646] The device sends the input information and analyzed emotional data to the server, where the generative AI model and emotion engine on the server generate a story and illustrations based on the information. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[0647] Specific program description
[0648] The user enters a request
[0649] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into a form, and then enters details of the story's plot and important events. The input data is confirmed by clicking the "Generate" button.
[0650] Emotion recognition by emotion engine
[0651] When a user inputs information, the device captures emotion data from the user's facial expressions and voice via the camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state. This emotion data is sent to the server along with the input data. The emotion engine can use, for example, Microsoft's Azure Emotion API.
[0652] The device sends the data to the server
[0653] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format such as JSON and sent using a secure communication protocol such as HTTPS. The device can be a smartphone or a PC.
[0654] The server generates the story and illustrations
[0655] The server analyzes the received data and automatically generates a detailed story using a generative AI model (e.g., OpenAI's GPT-3). The generated story can be adjusted in tone and content based on emotions recognized by an emotion engine. For example, if the user expresses positive emotions, the server can generate an upbeat and fun story.
[0656] The server also reflects the data from the emotion engine when generating illustrations. For example, based on the image provided by the user, the facial expression and background of the generated character will change according to the user's emotional state. This means that if the user provides an image of a smiling character, the character will also be drawn smiling.
[0657] The server assembles the picture book data
[0658] The generated story and illustrations are then integrated by a server, which then assembles the digital picture book into a suitable layout. The server uses a layout algorithm (e.g., Adobe InDesign Server) to determine the placement of each page, resulting in a beautiful and coherent digital picture book.
[0659] The server delivers the picture book to the user
[0660] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server protects the user's privacy by transmitting data using a secure communication protocol. Users receive the digital picture book on their smartphone or PC and can view it using a dedicated app or PDF reader.
[0661] Examples of prompt statements
[0662] "I want to create an adventure story for my 4-year-old son. The main character is a character made using a photo of my son, named Yuuta, who is 5 years old. The story will have a cheerful and fun adventure theme. The generated character's expressions and environment will be based on positive emotions."
[0663] The above is a specific embodiment for implementing the system of the present invention, which allows users to easily create and view original digital picture books.
[0664] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0665] System program processing flow
[0666] Step 1: User enters request
[0667] Step 2: Emotion recognition by the emotion engine
[0668] Step 3: The device sends the data to the server
[0669] Step 4: The server generates the story and illustrations
[0670] Step 5: The server assembles the picture book data
[0671] Step 6: The server delivers the picture book to the user
[0672] Specific explanation of each processing step
[0673] Step 1: User enters request
[0674] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into the form, followed by details about the story's plot and important events. Clicking the "Generate" button finalizes the input data. The input data is saved on the device and used in the next step.
[0675] Input: Character information (name, age, gender, image), story summary
[0676] Output: Confirmed input data
[0677] Step 2: Emotion recognition by the emotion engine
[0678] When the user enters information, the device collects the user's facial expressions and voice through the camera and microphone. An emotion engine (e.g., Microsoft's Azure Emotion API) analyzes this data and recognizes the user's current emotional state. The analysis results are stored on the device and used in the next step.
[0679] Input: facial expression data, voice data
[0680] Output: Parsed emotion data
[0681] Step 3: The device sends the data to the server
[0682] The device sends the confirmed input data and analyzed emotion data to the server. This data is encoded in JSON format and securely transmitted using HTTPS. The server stores the received data for analysis.
[0683] Input: Confirmed input data, analyzed emotion data
[0684] Output: Data sent to the server
[0685] Step 4: The server generates the story and illustrations
[0686] The server analyzes the input data and emotional data it receives and automatically generates a story using a generative AI model (e.g., OpenAI's GPT-3). The tone and content of the generated story are adjusted based on the emotional data. The server then generates illustrations in a similar manner. The illustrations are customized based on the images and emotional data provided by the user.
[0687] Input: Input data, emotion data
[0688] Output: Generated story and illustrations
[0689] Step 5: The server assembles the picture book data
[0690] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. The server uses a layout algorithm (e.g., Adobe InDesign server) to set the layout of each page, and the story and illustrations are beautifully arranged.
[0691] Input: Generated story, illustrations
[0692] Output: Digital picture book data
[0693] Step 6: The server delivers the picture book to the user
[0694] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server securely transmits data using HTTPS, and the user can receive and view the digital picture book on their smartphone or PC.
[0695] Input: Digital picture book data
[0696] Output: Digital picture book delivered to the user's device
[0697] These are the specific processing steps of the program for this system, which allows users to easily create and view original digital picture books.
[0698] (Application example 2)
[0699] 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."
[0700] Conventional digital picture book generation systems have struggled to provide an individualized experience that reflects the user's emotions. In certain situations, the story and illustrations are not adjusted based on the user's emotions, resulting in a lack of personalized content. Furthermore, the lack of technology to acquire user emotion data in real time and apply it to picture book production makes it difficult to generate picture books that appeal to the user's desired emotions.
[0701] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input data for creating an original picture book, means for transmitting the user's input data to the server, means for the server to generate a story based on the input data, means for the server to generate illustrations based on the story, means for integrating the generated story and illustrations to create a digital picture book, means for delivering the digital picture book to a user terminal, and means having an emotion engine that acquires and analyzes emotion data and adjusting the tone and content of the story and illustrations based on the emotion data. This makes it possible to generate a personalized digital picture book that matches the user's emotions.
[0702] "User input data" refers to data such as character information and story outlines that are input by the user to create an original picture book.
[0703] A "server" is a computer system that receives user input data and generates stories and illustrations to create a digital picture book.
[0704] "Story generation means" refers to a means by which the server automatically creates a story based on user input data.
[0705] The "illustration generating means" is a means for creating illustrations based on the story generated by the server.
[0706] The "digital picture book creation means" is a means for creating a digital picture book by integrating the generated story and illustrations.
[0707] "Distribution means" refers to a means for transmitting the completed digital picture book to the user terminal.
[0708] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice data and recognizes their emotional state.
[0709] "Emotion data" is data that indicates the user's emotional state, obtained as a result of analysis by the emotion engine.
[0710] "Customization" refers to adjusting the content and tone of the story and illustrations based on user-provided photographs and emotional data.
[0711] "User terminal" refers to devices such as smartphones, tablets, and PCs used for creating and viewing picture books.
[0712] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[0713] System Overview
[0714] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[0715] The device sends the input information and analyzed emotional data to the server. The server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[0716] Specific processing of the program
[0717] The user enters a request
[0718] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0719] Emotion recognition by emotion engine
[0720] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[0721] The device sends the data to the server
[0722] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0723] The server generates the story and illustrations
[0724] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[0725] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[0726] The server assembles the picture book data
[0727] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0728] The server delivers the picture book to the user
[0729] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0730] Specific examples
[0731] Example 1: Creating a picture book for preschoolers
[0732] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[0733] Example 2: Creating an educational picture book
[0734] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[0735] Example of input prompt for generative AI model
[0736] User information: Character name is "Yuta", age is 5, gender is male. Story summary is "One day, Yuuta encounters a mysterious creature in the forest."
[0737] Emotion data: The user is smiling when typing, and positive emotions are detected.
[0738] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[0739] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0740] Step 1:
[0741] The user starts the "Picture Book Maker" application and inputs character information and a story outline. Specifically, the user fills in a dedicated input form with the character's name, age, gender, photo, story summary, etc. This generates user input data.
[0742] Step 2:
[0743] After the user completes the input data, the device will use the camera and microphone to collect the user's facial expressions and voice. These emotion data will be sent to the emotion engine and used to analyze the user's emotional state. Emotion data will be generated as a result of the analysis.
[0744] Step 3:
[0745] The device encodes user input data and emotion data in JSON format and sends it to the server using a secure communication protocol. The input data is the user input data and emotion data, and the output is the data sent to the server.
[0746] Step 4:
[0747] The server analyzes the received user input data and emotional data. Specifically, it uses generative AI to automatically generate a detailed story based on the user input data. The emotional engine analyzes the emotional data and adjusts the tone and content of the story. For example, if positive emotions are detected, a fun adventure story will be generated. The input data are user input data and emotional data, and the output is the generated story.
[0748] Step 5:
[0749] The server generates illustrations based on the story it generates. Characters are customized based on photos provided by the user, and backgrounds and other visual elements are generated using a generative AI model. Emotional data is also taken into account during this process, and the illustrations are adjusted to be more emotionally appealing. The input data are the story, user photos, and emotional data, and the output is the generated illustration.
[0750] Step 6:
[0751] The server integrates the generated story and illustrations and assembles them into a digital picture book. It applies a layout algorithm to properly position each page and create the final digital picture book file. The input data are the generated story and illustrations, and the output is the digital picture book data.
[0752] Step 7:
[0753] The server exports the completed digital picture book data in PDF format or a dedicated app format and distributes it to the user's device. The user receives this and views the digital picture book on their smartphone or PC. The input data is the digital picture book data, and the output is a digital picture book distributed to the user's device.
[0754] 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.
[0755] 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.
[0756] 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.
[0757] [Third embodiment]
[0758] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0759] 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.
[0760] 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).
[0761] 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.
[0762] 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.
[0763] 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).
[0764] 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.
[0765] 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.
[0766] 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.
[0767] 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.
[0768] 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.
[0769] 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."
[0770] This invention is a system in which a user inputs data to create an original picture book, automatically generates a story and illustrations using generation AI, and finally provides the user with a digital picture book.
[0771] System Overview
[0772] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story.
[0773] The information entered through the device is sent to a server, where a generation AI on the server uses it to generate a story and illustrations. Natural language processing technology is used to generate the story, and image generation technology is used to generate the illustrations. The generated story and illustrations are integrated by the server and assembled into a digital picture book. The picture book is then distributed to the device, allowing the user to view it in digital format.
[0774] Specific processing of the program
[0775] The user enters a request
[0776] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0777] The device sends the data to the server
[0778] The data entered by the user is sent from the device to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0779] The server generates the story
[0780] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, Mike finds himself in a magical forest..." The story is customized based on the character traits of the characters and photos provided by the user.
[0781] The server generates the illustrations
[0782] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided photos and specific character attributes. For example, it creates an illustration of a cat based on a photo of Mike.
[0783] The server assembles the picture book data
[0784] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the picture book is properly positioned.
[0785] The server delivers the picture book to the user
[0786] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0787] Specific examples
[0788] Example 1: Creating a picture book for preschoolers
[0789] The user inputs, "I want to write an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "One day, Yuuta meets a mysterious creature in the forest..." and creates illustrations with Yuuta as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the picture book on their smartphone.
[0790] Example 2: Creating an educational picture book for a specific theme
[0791] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "Sakura gets on a spaceship and sets off on a planetary exploration..." and creates illustrations featuring Sakura as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the book on their PC.
[0792] As described above, the system of the present invention provides a means for users to easily create original picture books and view them in digital format.
[0793] The processing flow will be explained below.
[0794] Processing Steps
[0795] Step 1:
[0796] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[0797] Step 2:
[0798] The user enters basic information. The user accesses a form to enter the picture book title, target age, story theme, etc., and fills in each item.
[0799] Step 3:
[0800] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[0801] Step 4:
[0802] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[0803] Step 5:
[0804] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[0805] Step 6:
[0806] The server generates the story. The server analyzes the received data and uses the generation AI to automatically generate a detailed story. For example, if the user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[0807] Step 7:
[0808] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[0809] Step 8:
[0810] The server assembles the picture book data, combines the story and illustrations into a single file, and creates a digital picture book with the appropriate layout. It then applies a layout algorithm to adjust the placement of each page.
[0811] Step 9:
[0812] The server generates the picture book file, exports the completed picture book data in PDF format or a dedicated app display format, and generates the final file.
[0813] Step 10:
[0814] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[0815] Step 11:
[0816] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[0817] This step allows users to easily create and view original digital picture books.
[0818] Example 1
[0819] 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."
[0820] Conventional original picture book creation systems require users to manually create text and illustrations, which takes a lot of time and effort. It is also difficult to consistently create stories and illustrations that fit a specific theme, which can result in a lack of originality and cohesion as intended by the user. Therefore, there is a need for a system that allows users to create original picture books more easily and efficiently.
[0821] 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.
[0822] In this invention, the server includes means for a user to input data for creating an original digital book, means for transmitting the user's input data from a communication device to a computer, means for the computer to generate a story based on the input data, means for the computer to generate images based on the story, means for integrating the generated story and images to create a digital digital book, and means for delivering the digital digital book to the user's communication device, thereby enabling users to easily and efficiently create and view original digital picture books.
[0823] "User" refers to a person who inputs the data necessary to create an original electronic book.
[0824] "Communication devices" are devices for sending and receiving data, including smartphones and personal computers.
[0825] "Computer" refers to a device that includes a server and processor for generating stories and images from data and creating digital e-books.
[0826] A "story" is a collection of textual information created by a generative AI model, and is text data containing the story content.
[0827] "Images" are visual data created by generative AI models, and are illustrations or pictures corresponding to each scene in the story.
[0828] "Digital e-book" refers to a book that integrates generated narrative and images and is created in a digital format, including PDF and dedicated app formats.
[0829] "Input data" refers to information that a user inputs using a communication device, and includes information about characters appearing in the game and an outline of the story.
[0830] "Generative AI model" refers to an artificial intelligence algorithm used to generate stories and images based on prompts entered by a user.
[0831] The present invention is a system that allows users to create original e-books. Specifically, the system allows users to input data, automatically generates stories and images using a generative AI model, and ultimately provides the results to users as a digital e-book.
[0832] System configuration
[0833] Users access the "Picture Book Maker" application using a communication device such as a smartphone or personal computer. In the application, users enter information to create an original e-book tailored to their child or a specific theme. This information includes information about the characters (such as name, age, gender, and photo) and a summary of the story.
[0834] The information entered by the terminal is securely transmitted to the computer (server) using the HTTPS protocol, and the transmitted data is encoded in an appropriate format, such as JSON.
[0835] Specific examples of processing
[0836] The server receives and analyzes the data sent by the user. Based on the analyzed data, a generative AI model (e.g., GPT-4) is used to automatically generate a detailed story. An example of a specific prompt is "Create a story about the adventures of Takeshi the cat." Using this prompt as input, the generative AI generates a specific story such as "One day, Takeshi found himself in a magical forest..."
[0837] Next, the server generates images corresponding to each scene in the story. The illustrations are generated using a generative AI model (e.g., DALL-E or Stable Diffusion). Based on the character photos and characteristics provided by the user, the server automatically creates images appropriate for each scene in the story. For example, an illustration of a scene in which a cat named "Takeshi" is in a magical forest is generated.
[0838] The generated story and illustrations are then integrated by a server and assembled into a digital e-book with the appropriate page layout, using HTML5, CSS3, and JavaScript, before being exported to PDF or a dedicated app.
[0839] The completed digital e-book is then distributed from the server to the user's communication device, where the user can easily view the digital e-book on, for example, a smartphone or personal computer.
[0840] Specific use cases
[0841] Example 1: Creating an e-book for preschoolers
[0842] The user enters, "I want to create an adventure story for my 4-year-old son. The main character will be a character using a photo of my son, named Takeshi, 5 years old," and uploads a related photo. The data is sent from the device to the server. The server uses generative AI to generate a story—"One day, Takeshi meets a mysterious creature in the forest..."—and creates illustrations based on the photos provided by the user. The final e-book can be viewed on a smartphone.
[0843] Example 2: Creating an educational e-book on a specific topic
[0844] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story: "Sakura gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Sakura as the main character based on the photo provided by the user. The final e-book can be viewed on a personal computer.
[0845] As described above, the system of the present invention allows users to easily and efficiently create and view original digital electronic books.
[0846] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0847] Step 1:
[0848] The user prepares input data for creating an original electronic book.
[0849] Specifically, the user launches the "Picture Book Maker" application and enters character information (such as name, age, gender, and photo) and a summary of the story into the input form. After entering this information, the user clicks the "Generate" button to complete the request.
[0850] Input: Character information (e.g., name "Takeshi", age "6 years old", gender "male", photo), story summary (e.g., "A story about the adventures of Takeshi the cat")
[0851] Output: The input data is temporarily saved in the terminal in JSON format.
[0852] Step 2:
[0853] The terminal transmits the user's input data to the server.
[0854] Specifically, the device encodes the input data into JSON format and sends it to the server using the HTTPS protocol. For security reasons, the data is encrypted before transmission.
[0855] Input: User data in JSON format
[0856] Output: The input data sent to the server
[0857] Step 3:
[0858] The server analyzes the received data and generates a story.
[0859] Specifically, the server analyzes the received JSON data and uses a generative AI model (e.g., GPT-4) to automatically generate a detailed story based on the prompt (e.g., "Create a story about the adventures of Takeshi the cat"). The generated story is then stored on the server.
[0860] Input: User data (JSON format), prompt statement
[0861] Output: Generated story (text format)
[0862] Step 4:
[0863] The server generates illustrations for the generated story.
[0864] Specifically, the server uses a generative AI model (e.g., DALL-E or Stable Diffusion) to generate illustrations for each scene in the story. It generates appropriate images based on the character photos and attributes provided by the user.
[0865] Input: Generated story, character photos
[0866] Output: Generated illustration (image format)
[0867] Step 5:
[0868] The server combines the story and illustrations to create a digital e-book.
[0869] Specifically, the server integrates the generated story and illustrations, assembles them into a digital e-book with the appropriate layout for each page using HTML5, CSS3, and JavaScript, and finally exports it to PDF format or a dedicated app display format.
[0870] Input: Generated story, generated illustrations
[0871] Output: Integrated digital e-book (PDF or app format)
[0872] Step 6:
[0873] The server distributes the completed digital e-book to the user.
[0874] Specifically, the server delivers the completed digital e-book to the user's communication device. Delivery methods include sending a download link or allowing the user to view the e-book directly within the app. Users can then view the e-book on their smartphone or personal computer.
[0875] Input: Integrated digital e-book
[0876] Output: Digital e-book delivered to the user's communication device
[0877] (Application example 1)
[0878] 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."
[0879] In conventional picture book creation systems, users are limited to simply viewing the created picture book on a digital device, making it difficult to share the experience in real time. Furthermore, there is a lack of a way to enjoy a personalized experience while actually seeing the background and story of the product in a physical store, making it difficult to attract customers' interest.
[0880] 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.
[0881] In this invention, the server includes a means for a user to input data for creating an original picture book, a means for transmitting the user's input data to the server, a means for the server to generate a story based on the input data, a means for the server to generate illustrations based on the story, a means for integrating the generated story and illustrations to create a digital picture book, and a means for delivering the digital picture book to a visual device and enabling in-store browsing. This makes it possible to provide customers in a physical store with personalized stories related to products in real time and allow them to instantly experience them through their visual device.
[0882] A "user terminal" is a device used by a user to input data, and includes a smartphone, tablet, personal computer, etc.
[0883] The "server" is a central processing unit that receives data sent from user terminals and generates stories and illustrations.
[0884] "Means for inputting data" refers to an input device or interface that receives information entered by a user, including a keyboard, touch screen, voice recognition, etc.
[0885] "Means for transmitting data" refers to the communication functions and protocols for transmitting data input from the user terminal to the server.
[0886] "Means for generating a story" refers to algorithms or generative AI that automatically create story content based on input data.
[0887] "Means for generating illustrations" refers to image generation algorithms or generative AI that create visual illustrations based on the generated story.
[0888] "Digital picture books" refer to picture books that integrate generated stories and illustrations and are provided in digital format.
[0889] A "visual device" is a device that allows a user to visually view a digital picture book, and includes smart glasses, head-mounted displays, and the like.
[0890] "In-store browsing" refers to the act of viewing product information and related stories in real time using visual devices in a physical store.
[0891] System Overview
[0892] This invention is a system that allows users to input data to create original picture books, automatically generates stories and illustrations using generative AI, and finally provides the users with a digital picture book. This system mainly utilizes visual devices such as smart glasses to provide a real-time experience in a physical store.
[0893] Specific processing of the program
[0894] The user enters a request
[0895] The user launches the "Smart Picture Book Maker" application through the smart glasses and inputs basic information about the picture book, information about the characters, and a summary of the story. For example, the user can input the character's name, age, and gender, and then enter details of the story's plot and key events. After completing the input, the user clicks the "Generate" button, and the data is sent to the server.
[0896] The device sends the data to the server
[0897] The data entered by the user is sent from the smart glasses to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol (e.g., HTTPS).
[0898] The server generates the story
[0899] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about a cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, the cat steps into a magical forest..." The generation AI uses natural language processing technology.
[0900] The server generates the illustrations
[0901] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided images and specific character attributes. For example, a prompt such as "Draw a cat based on a photo of the character" can be used to generate a new image.
[0902] The server assembles the picture book data
[0903] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the digital picture book is properly positioned.
[0904] The server delivers the picture book to the user
[0905] The completed digital storybook is then delivered to a visual device, where users can view it through smart glasses.
[0906] Specific use cases
[0907] Example 1: Creating a picture book for preschoolers
[0908] The user inputs, "I want to create an adventure story for a 3-year-old child. The main character will be a character using a child's photo, named Taro, 4 years old." The data is sent from the smart glasses to the server. The server uses a generative AI to generate a story such as, "One day, Taro meets a mysterious creature in the forest..." and creates illustrations featuring Taro as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by wearing the smart glasses.
[0909] Example 2: Creating an educational picture book for a specific theme
[0910] The user inputs, "I want to create a story that will teach children in the early grades of elementary school about space. The main character will be a character using a child's photo, named Hanako, 7 years old." The data is sent from the smart glasses to the server. The server uses a generation AI to generate a story such as "Hanako gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Hanako as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by putting on the smart glasses.
[0911] Prompt Sentence Examples
[0912] "I want to write a story about an adventure in the forest for my four-year-old son. The main character is a character made from a photo of my son, named Taro, who is five years old."
[0913] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0914] Step 1:
[0915] The user puts on the smart glasses and launches the "Smart Picture Book Maker" application. The user enters character information and a story outline for the original picture book through the application's input screen. For example, the user enters information such as the character's name, age, gender, and related images into the form, followed by a detailed description of the story's plot and important events. When the user clicks the "Generate" button, this data is prepared.
[0916] Input: Character information (name, age, gender, image), story summary
[0917] Output: A data object in JSON format
[0918] Step 2:
[0919] The device (smart glasses) sends the data entered by the user to the server. The device encodes the entered data into JSON format and sends it to the server using a secure communication protocol (e.g., HTTPS).
[0920] Input: A JSON formatted data object
[0921] Output: Send data to the server
[0922] Step 3:
[0923] The server analyzes the received data and automatically generates a detailed story based on the generative AI model. Natural language processing technology is used to generate the story, and the development of the story is determined based on the input data. For example, if the generative AI receives the prompt "A cat goes on an adventure," it will generate a storyline like "One day, a cat steps into a magical forest..."
[0924] Input: A JSON formatted data object
[0925] Output: Generated story (text data)
[0926] Step 4:
[0927] The server generates illustrations for each scene in the generated story. The AI uses built-in image generation technology to create customized illustrations based on user-provided images and character attributes. For example, images are generated according to specific instructions, such as "draw a cat based on a photo of the character."
[0928] Input: Generated story (text data), character information (images)
[0929] Output: Generated illustration (image data)
[0930] Step 5:
[0931] The server integrates the generated story and illustrations and creates a digital picture book based on an appropriate layout algorithm. The story text and illustrations are arranged appropriately for each page, creating a digital picture book format. The book can then be exported in PDF format or a dedicated app display format.
[0932] Input: Generated story (text data), generated illustrations (image data)
[0933] Output: Digital picture book (PDF format or dedicated app format)
[0934] Step 6:
[0935] The server delivers the completed digital picture book to a visual device (smart glasses), and the user can view the received digital picture book through the smart glasses.
[0936] Input: Digital picture book (PDF format or dedicated app format)
[0937] Output: Delivery to smart glasses, user viewing of digital picture books
[0938] 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.
[0939] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[0940] System Overview
[0941] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[0942] The device sends the input information and analyzed emotional data to the server, where the server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing users to view it digitally.
[0943] Specific processing of the program
[0944] The user enters a request
[0945] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[0946] Emotion recognition by emotion engine
[0947] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[0948] The device sends the data to the server
[0949] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[0950] The server generates the story and illustrations
[0951] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[0952] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[0953] The server assembles the picture book data
[0954] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0955] The server delivers the picture book to the user
[0956] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[0957] Specific examples
[0958] Example 1: Creating a picture book for preschoolers
[0959] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[0960] Example 2: Creating an educational picture book
[0961] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[0962] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[0963] The processing flow will be explained below.
[0964] Processing Steps
[0965] Step 1:
[0966] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[0967] Step 2:
[0968] The user enters basic information. The user accesses a form to enter the book title, target age group, story theme, etc., and fills in each item.
[0969] Step 3:
[0970] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[0971] Step 4:
[0972] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[0973] Step 5:
[0974] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[0975] Step 6:
[0976] The device collects the user's emotional data. It uses the device's camera and microphone to collect the user's facial expression data and voice data.
[0977] Step 7:
[0978] The device transmits the collected emotion data to the server, which then encodes the data in an appropriate format and transmits it to the server using a secure communication protocol.
[0979] Step 8:
[0980] The server generates the story. The server analyzes the received user data and emotional data, and uses the generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[0981] Step 9:
[0982] The server adjusts the tone of the story based on the emotion data. The server adjusts the tone of the story (e.g., fun, moving, suspenseful) according to the user's emotion.
[0983] Step 10:
[0984] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[0985] Step 11:
[0986] The server adjusts the facial expressions of the illustrations based on the emotional data, and adjusts the character's facial expressions and the tone of the environment based on the user's emotional data.
[0987] Step 12:
[0988] The server assembles the picture book data. The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[0989] Step 13:
[0990] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[0991] Step 14:
[0992] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[0993] This step allows users to easily create original digital picture books and enjoy content customized to their emotions.
[0994] Example 2
[0995] 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."
[0996] Conventional digital picture book creation systems lack support for users to easily create original stories and illustrations, making it difficult to provide personalized content that reflects the user's emotions. Furthermore, the lack of a customization function based on the user's emotions makes it difficult to create picture books optimized for individual users.
[0997] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input data for creating an original picture book; means for a terminal to acquire and transmit the user's input data and emotional data; a server that receives the input data and emotional data; means by the server that generates a story based on the input data and emotional data; means by the server that generates illustrations based on the story; means for creating a digital picture book by integrating the generated story and illustrations; and means for delivering the digital picture book to a user terminal. This makes it possible to easily create and deliver an original digital picture book that is individually optimized while reflecting the user's emotions.
[0998] "User" refers to a person who uses the system to create an original picture book.
[0999] An "original picture book" refers to a picture book that includes a unique story and illustrations generated based on data and emotional data entered by the user.
[1000] "Data" refers to the information that users input into the system, including character information and story outlines.
[1001] "Emotional data" refers to information about the emotional state obtained by analyzing the user's facial expressions and voice.
[1002] "Terminal" refers to a device that allows a user to input and send data, and specifically includes smartphones and PCs.
[1003] The term "server" refers to a computer device that receives data and emotional data sent by users, generates stories and illustrations, and integrates picture books.
[1004] "Generative AI" refers to artificial intelligence technology that automatically generates stories based on user input data and emotional data.
[1005] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to obtain emotional data.
[1006] "Story" refers to the content of the story generated by the generative AI.
[1007] "Illustrations" refers to illustrations created by the server based on the generated story.
[1008] "Digital picture book" refers to a picture book created in digital format that integrates generated stories and illustrations.
[1009] "Distribution" refers to the process of sending the completed digital picture book to the user's terminal.
[1010] The present invention is a system that allows users to input data for creating an original picture book, automatically generates a story and illustrations using a generative AI model and an emotion engine, and finally provides the user with a digital picture book. This system is characterized by its ability to recognize the user's emotions and customize the content accordingly. A specific embodiment of this system is described below.
[1011] System Overview
[1012] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and image) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and during use.
[1013] The device sends the input information and analyzed emotional data to the server, where the generative AI model and emotion engine on the server generate a story and illustrations based on the information. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[1014] Specific program description
[1015] The user enters a request
[1016] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into a form, and then enters details of the story's plot and important events. The input data is confirmed by clicking the "Generate" button.
[1017] Emotion recognition by emotion engine
[1018] When a user inputs information, the device captures emotion data from the user's facial expressions and voice via the camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state. This emotion data is sent to the server along with the input data. The emotion engine can use, for example, Microsoft's Azure Emotion API.
[1019] The device sends the data to the server
[1020] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format such as JSON and sent using a secure communication protocol such as HTTPS. The device can be a smartphone or a PC.
[1021] The server generates the story and illustrations
[1022] The server analyzes the received data and automatically generates a detailed story using a generative AI model (e.g., OpenAI's GPT-3). The generated story can be adjusted in tone and content based on emotions recognized by an emotion engine. For example, if the user expresses positive emotions, the server can generate an upbeat and fun story.
[1023] The server also reflects the data from the emotion engine when generating illustrations. For example, based on the image provided by the user, the facial expression and background of the generated character will change according to the user's emotional state. This means that if the user provides an image of a smiling character, the character will also be drawn smiling.
[1024] The server assembles the picture book data
[1025] The generated story and illustrations are then integrated by a server, which then assembles the digital picture book into a suitable layout. The server uses a layout algorithm (e.g., Adobe InDesign Server) to determine the placement of each page, resulting in a beautiful and coherent digital picture book.
[1026] The server delivers the picture book to the user
[1027] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server protects the user's privacy by transmitting data using a secure communication protocol. Users receive the digital picture book on their smartphone or PC and can view it using a dedicated app or PDF reader.
[1028] Examples of prompt statements
[1029] "I want to create an adventure story for my 4-year-old son. The main character is a character made using a photo of my son, named Yuuta, who is 5 years old. The story will have a cheerful and fun adventure theme. The generated character's expressions and environment will be based on positive emotions."
[1030] The above is a specific embodiment for implementing the system of the present invention, which allows users to easily create and view original digital picture books.
[1031] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1032] System program processing flow
[1033] Step 1: User enters request
[1034] Step 2: Emotion recognition by the emotion engine
[1035] Step 3: The device sends the data to the server
[1036] Step 4: The server generates the story and illustrations
[1037] Step 5: The server assembles the picture book data
[1038] Step 6: The server delivers the picture book to the user
[1039] Specific explanation of each processing step
[1040] Step 1: User enters request
[1041] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into the form, followed by details about the story's plot and important events. Clicking the "Generate" button finalizes the input data. The input data is saved on the device and used in the next step.
[1042] Input: Character information (name, age, gender, image), story summary
[1043] Output: Confirmed input data
[1044] Step 2: Emotion recognition by the emotion engine
[1045] When the user enters information, the device collects the user's facial expressions and voice through the camera and microphone. An emotion engine (e.g., Microsoft's Azure Emotion API) analyzes this data and recognizes the user's current emotional state. The analysis results are stored on the device and used in the next step.
[1046] Input: facial expression data, voice data
[1047] Output: Parsed emotion data
[1048] Step 3: The device sends the data to the server
[1049] The device sends the confirmed input data and analyzed emotion data to the server. This data is encoded in JSON format and securely transmitted using HTTPS. The server stores the received data for analysis.
[1050] Input: Confirmed input data, analyzed emotion data
[1051] Output: Data sent to the server
[1052] Step 4: The server generates the story and illustrations
[1053] The server analyzes the input data and emotional data it receives and automatically generates a story using a generative AI model (e.g., OpenAI's GPT-3). The tone and content of the generated story are adjusted based on the emotional data. The server then generates illustrations in a similar manner. The illustrations are customized based on the images and emotional data provided by the user.
[1054] Input: Input data, emotion data
[1055] Output: Generated story and illustrations
[1056] Step 5: The server assembles the picture book data
[1057] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. The server uses a layout algorithm (e.g., Adobe InDesign server) to set the layout of each page, and the story and illustrations are beautifully arranged.
[1058] Input: Generated story, illustrations
[1059] Output: Digital picture book data
[1060] Step 6: The server delivers the picture book to the user
[1061] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server securely transmits data using HTTPS, and the user can receive and view the digital picture book on their smartphone or PC.
[1062] Input: Digital picture book data
[1063] Output: Digital picture book delivered to the user's device
[1064] These are the specific processing steps of the program for this system, which allows users to easily create and view original digital picture books.
[1065] (Application example 2)
[1066] 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."
[1067] Conventional digital picture book generation systems have struggled to provide an individualized experience that reflects the user's emotions. In certain situations, the story and illustrations are not adjusted based on the user's emotions, resulting in a lack of personalized content. Furthermore, the lack of technology to acquire user emotion data in real time and apply it to picture book production makes it difficult to generate picture books that appeal to the user's desired emotions.
[1068] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input data for creating an original picture book, means for transmitting the user's input data to the server, means for the server to generate a story based on the input data, means for the server to generate illustrations based on the story, means for integrating the generated story and illustrations to create a digital picture book, means for delivering the digital picture book to a user terminal, and means having an emotion engine that acquires and analyzes emotion data and adjusting the tone and content of the story and illustrations based on the emotion data. This makes it possible to generate a personalized digital picture book that matches the user's emotions.
[1069] "User input data" refers to data such as character information and story outlines that are input by the user to create an original picture book.
[1070] A "server" is a computer system that receives user input data and generates stories and illustrations to create a digital picture book.
[1071] "Story generation means" refers to a means by which the server automatically creates a story based on user input data.
[1072] The "illustration generating means" is a means for creating illustrations based on the story generated by the server.
[1073] The "digital picture book creation means" is a means for creating a digital picture book by integrating the generated story and illustrations.
[1074] "Distribution means" refers to a means for transmitting the completed digital picture book to the user terminal.
[1075] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice data and recognizes their emotional state.
[1076] "Emotion data" is data that indicates the user's emotional state, obtained as a result of analysis by the emotion engine.
[1077] "Customization" refers to adjusting the content and tone of the story and illustrations based on user-provided photographs and emotional data.
[1078] "User terminal" refers to devices such as smartphones, tablets, and PCs used for creating and viewing picture books.
[1079] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[1080] System Overview
[1081] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[1082] The device sends the input information and analyzed emotional data to the server. The server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[1083] Specific processing of the program
[1084] The user enters a request
[1085] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[1086] Emotion recognition by emotion engine
[1087] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[1088] The device sends the data to the server
[1089] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[1090] The server generates the story and illustrations
[1091] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[1092] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[1093] The server assembles the picture book data
[1094] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[1095] The server delivers the picture book to the user
[1096] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[1097] Specific examples
[1098] Example 1: Creating a picture book for preschoolers
[1099] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[1100] Example 2: Creating an educational picture book
[1101] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[1102] Example of input prompt for generative AI model
[1103] User information: Character name is "Yuta", age is 5, gender is male. Story summary is "One day, Yuuta encounters a mysterious creature in the forest."
[1104] Emotion data: The user is smiling when typing, and positive emotions are detected.
[1105] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[1106] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1107] Step 1:
[1108] The user starts the "Picture Book Maker" application and inputs character information and a story outline. Specifically, the user fills in a dedicated input form with the character's name, age, gender, photo, story summary, etc. This generates user input data.
[1109] Step 2:
[1110] After the user completes the input data, the device will use the camera and microphone to collect the user's facial expressions and voice. These emotion data will be sent to the emotion engine and used to analyze the user's emotional state. Emotion data will be generated as a result of the analysis.
[1111] Step 3:
[1112] The device encodes user input data and emotion data in JSON format and sends it to the server using a secure communication protocol. The input data is the user input data and emotion data, and the output is the data sent to the server.
[1113] Step 4:
[1114] The server analyzes the received user input data and emotional data. Specifically, it uses generative AI to automatically generate a detailed story based on the user input data. The emotional engine analyzes the emotional data and adjusts the tone and content of the story. For example, if positive emotions are detected, a fun adventure story will be generated. The input data are user input data and emotional data, and the output is the generated story.
[1115] Step 5:
[1116] The server generates illustrations based on the story it generates. Characters are customized based on photos provided by the user, and backgrounds and other visual elements are generated using a generative AI model. Emotional data is also taken into account during this process, and the illustrations are adjusted to be more emotionally appealing. The input data are the story, user photos, and emotional data, and the output is the generated illustration.
[1117] Step 6:
[1118] The server integrates the generated story and illustrations and assembles them into a digital picture book. It applies a layout algorithm to properly position each page and create the final digital picture book file. The input data are the generated story and illustrations, and the output is the digital picture book data.
[1119] Step 7:
[1120] The server exports the completed digital picture book data in PDF format or a dedicated app format and distributes it to the user's device. The user receives this and views the digital picture book on their smartphone or PC. The input data is the digital picture book data, and the output is a digital picture book distributed to the user's device.
[1121] 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.
[1122] 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.
[1123] 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.
[1124] [Fourth embodiment]
[1125] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1126] 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.
[1127] 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).
[1128] 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.
[1129] 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.
[1130] 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).
[1131] 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.
[1132] 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.
[1133] 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.
[1134] 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.
[1135] 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.
[1136] 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.
[1137] 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."
[1138] This invention is a system in which a user inputs data to create an original picture book, automatically generates a story and illustrations using generation AI, and finally provides the user with a digital picture book.
[1139] System Overview
[1140] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story.
[1141] The information entered through the device is sent to a server, where a generation AI on the server uses it to generate a story and illustrations. Natural language processing technology is used to generate the story, and image generation technology is used to generate the illustrations. The generated story and illustrations are integrated by the server and assembled into a digital picture book. The picture book is then distributed to the device, allowing the user to view it in digital format.
[1142] Specific processing of the program
[1143] The user enters a request
[1144] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[1145] The device sends the data to the server
[1146] The data entered by the user is sent from the device to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[1147] The server generates the story
[1148] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, Mike finds himself in a magical forest..." The story is customized based on the character traits of the characters and photos provided by the user.
[1149] The server generates the illustrations
[1150] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided photos and specific character attributes. For example, it creates an illustration of a cat based on a photo of Mike.
[1151] The server assembles the picture book data
[1152] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the picture book is properly positioned.
[1153] The server delivers the picture book to the user
[1154] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[1155] Specific examples
[1156] Example 1: Creating a picture book for preschoolers
[1157] The user inputs, "I want to write an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "One day, Yuuta meets a mysterious creature in the forest..." and creates illustrations with Yuuta as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the picture book on their smartphone.
[1158] Example 2: Creating an educational picture book for a specific theme
[1159] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story such as, "Sakura gets on a spaceship and sets off on a planetary exploration..." and creates illustrations featuring Sakura as the main character based on the photos provided by the user. The completed picture book data is sent to the device, and the user can view the book on their PC.
[1160] As described above, the system of the present invention provides a means for users to easily create original picture books and view them in digital format.
[1161] The processing flow will be explained below.
[1162] Processing Steps
[1163] Step 1:
[1164] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[1165] Step 2:
[1166] The user enters basic information. The user accesses a form to enter the picture book title, target age, story theme, etc., and fills in each item.
[1167] Step 3:
[1168] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[1169] Step 4:
[1170] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[1171] Step 5:
[1172] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[1173] Step 6:
[1174] The server generates the story. The server analyzes the received data and uses the generation AI to automatically generate a detailed story. For example, if the user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[1175] Step 7:
[1176] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[1177] Step 8:
[1178] The server assembles the picture book data, combines the story and illustrations into a single file, and creates a digital picture book with the appropriate layout. It then applies a layout algorithm to adjust the placement of each page.
[1179] Step 9:
[1180] The server generates the picture book file, exports the completed picture book data in PDF format or a dedicated app display format, and generates the final file.
[1181] Step 10:
[1182] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[1183] Step 11:
[1184] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[1185] This step allows users to easily create and view original digital picture books.
[1186] Example 1
[1187] 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."
[1188] Conventional original picture book creation systems require users to manually create text and illustrations, which takes a lot of time and effort. It is also difficult to consistently create stories and illustrations that fit a specific theme, which can result in a lack of originality and cohesion as intended by the user. Therefore, there is a need for a system that allows users to create original picture books more easily and efficiently.
[1189] 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.
[1190] In this invention, the server includes means for a user to input data for creating an original digital book, means for transmitting the user's input data from a communication device to a computer, means for the computer to generate a story based on the input data, means for the computer to generate images based on the story, means for integrating the generated story and images to create a digital digital book, and means for delivering the digital digital book to the user's communication device, thereby enabling users to easily and efficiently create and view original digital picture books.
[1191] "User" refers to a person who inputs the data necessary to create an original electronic book.
[1192] "Communication devices" are devices for sending and receiving data, including smartphones and personal computers.
[1193] "Computer" refers to a device that includes a server and processor for generating stories and images from data and creating digital e-books.
[1194] A "story" is a collection of textual information created by a generative AI model, and is text data containing the story content.
[1195] "Images" are visual data created by generative AI models, and are illustrations or pictures corresponding to each scene in the story.
[1196] "Digital e-book" refers to a book that integrates generated narrative and images and is created in a digital format, including PDF and dedicated app formats.
[1197] "Input data" refers to information that a user inputs using a communication device, and includes information about characters appearing in the game and an outline of the story.
[1198] "Generative AI model" refers to an artificial intelligence algorithm used to generate stories and images based on prompts entered by a user.
[1199] The present invention is a system that allows users to create original e-books. Specifically, the system allows users to input data, automatically generates stories and images using a generative AI model, and ultimately provides the results to users as a digital e-book.
[1200] System configuration
[1201] Users access the "Picture Book Maker" application using a communication device such as a smartphone or personal computer. In the application, users enter information to create an original e-book tailored to their child or a specific theme. This information includes information about the characters (such as name, age, gender, and photo) and a summary of the story.
[1202] The information entered by the terminal is securely transmitted to the computer (server) using the HTTPS protocol, and the transmitted data is encoded in an appropriate format, such as JSON.
[1203] Specific examples of processing
[1204] The server receives and analyzes the data sent by the user. Based on the analyzed data, a generative AI model (e.g., GPT-4) is used to automatically generate a detailed story. An example of a specific prompt is "Create a story about the adventures of Takeshi the cat." Using this prompt as input, the generative AI generates a specific story such as "One day, Takeshi found himself in a magical forest..."
[1205] Next, the server generates images corresponding to each scene in the story. The illustrations are generated using a generative AI model (e.g., DALL-E or Stable Diffusion). Based on the character photos and characteristics provided by the user, the server automatically creates images appropriate for each scene in the story. For example, an illustration of a scene in which a cat named "Takeshi" is in a magical forest is generated.
[1206] The generated story and illustrations are then integrated by a server and assembled into a digital e-book with the appropriate page layout, using HTML5, CSS3, and JavaScript, before being exported to PDF or a dedicated app.
[1207] The completed digital e-book is then distributed from the server to the user's communication device, where the user can easily view the digital e-book on, for example, a smartphone or personal computer.
[1208] Specific use cases
[1209] Example 1: Creating an e-book for preschoolers
[1210] The user enters, "I want to create an adventure story for my 4-year-old son. The main character will be a character using a photo of my son, named Takeshi, 5 years old," and uploads a related photo. The data is sent from the device to the server. The server uses generative AI to generate a story—"One day, Takeshi meets a mysterious creature in the forest..."—and creates illustrations based on the photos provided by the user. The final e-book can be viewed on a smartphone.
[1211] Example 2: Creating an educational e-book on a specific topic
[1212] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using a photo of my daughter, named Sakura, and she's 7 years old." The data is sent from the device to the server. The server uses a generation AI to generate a story: "Sakura gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Sakura as the main character based on the photo provided by the user. The final e-book can be viewed on a personal computer.
[1213] As described above, the system of the present invention allows users to easily and efficiently create and view original digital electronic books.
[1214] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1215] Step 1:
[1216] The user prepares input data for creating an original electronic book.
[1217] Specifically, the user launches the "Picture Book Maker" application and enters character information (such as name, age, gender, and photo) and a summary of the story into the input form. After entering this information, the user clicks the "Generate" button to complete the request.
[1218] Input: Character information (e.g., name "Takeshi", age "6 years old", gender "male", photo), story summary (e.g., "A story about the adventures of Takeshi the cat")
[1219] Output: The input data is temporarily saved in the terminal in JSON format.
[1220] Step 2:
[1221] The terminal transmits the user's input data to the server.
[1222] Specifically, the device encodes the input data into JSON format and sends it to the server using the HTTPS protocol. For security reasons, the data is encrypted before transmission.
[1223] Input: User data in JSON format
[1224] Output: The input data sent to the server
[1225] Step 3:
[1226] The server analyzes the received data and generates a story.
[1227] Specifically, the server analyzes the received JSON data and uses a generative AI model (e.g., GPT-4) to automatically generate a detailed story based on the prompt (e.g., "Create a story about the adventures of Takeshi the cat"). The generated story is then stored on the server.
[1228] Input: User data (JSON format), prompt statement
[1229] Output: Generated story (text format)
[1230] Step 4:
[1231] The server generates illustrations for the generated story.
[1232] Specifically, the server uses a generative AI model (e.g., DALL-E or Stable Diffusion) to generate illustrations for each scene in the story. It generates appropriate images based on the character photos and attributes provided by the user.
[1233] Input: Generated story, character photos
[1234] Output: Generated illustration (image format)
[1235] Step 5:
[1236] The server combines the story and illustrations to create a digital e-book.
[1237] Specifically, the server integrates the generated story and illustrations, assembles them into a digital e-book with the appropriate layout for each page using HTML5, CSS3, and JavaScript, and finally exports it to PDF format or a dedicated app display format.
[1238] Input: Generated story, generated illustrations
[1239] Output: Integrated digital e-book (PDF or app format)
[1240] Step 6:
[1241] The server distributes the completed digital e-book to the user.
[1242] Specifically, the server delivers the completed digital e-book to the user's communication device. Delivery methods include sending a download link or allowing the user to view the e-book directly within the app. Users can then view the e-book on their smartphone or personal computer.
[1243] Input: Integrated digital e-book
[1244] Output: Digital e-book delivered to the user's communication device
[1245] (Application example 1)
[1246] 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."
[1247] In conventional picture book creation systems, users are limited to simply viewing the created picture book on a digital device, making it difficult to share the experience in real time. Furthermore, there is a lack of a way to enjoy a personalized experience while actually seeing the background and story of the product in a physical store, making it difficult to attract customers' interest.
[1248] 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.
[1249] In this invention, the server includes a means for a user to input data for creating an original picture book, a means for transmitting the user's input data to the server, a means for the server to generate a story based on the input data, a means for the server to generate illustrations based on the story, a means for integrating the generated story and illustrations to create a digital picture book, and a means for delivering the digital picture book to a visual device and enabling in-store browsing. This makes it possible to provide customers in a physical store with personalized stories related to products in real time and allow them to instantly experience them through their visual device.
[1250] A "user terminal" is a device used by a user to input data, and includes a smartphone, tablet, personal computer, etc.
[1251] The "server" is a central processing unit that receives data sent from user terminals and generates stories and illustrations.
[1252] "Means for inputting data" refers to an input device or interface that receives information entered by a user, including a keyboard, touch screen, voice recognition, etc.
[1253] "Means for transmitting data" refers to the communication functions and protocols for transmitting data input from the user terminal to the server.
[1254] "Means for generating a story" refers to algorithms or generative AI that automatically create story content based on input data.
[1255] "Means for generating illustrations" refers to image generation algorithms or generative AI that create visual illustrations based on the generated story.
[1256] "Digital picture books" refer to picture books that integrate generated stories and illustrations and are provided in digital format.
[1257] A "visual device" is a device that allows a user to visually view a digital picture book, and includes smart glasses, head-mounted displays, and the like.
[1258] "In-store browsing" refers to the act of viewing product information and related stories in real time using visual devices in a physical store.
[1259] System Overview
[1260] This invention is a system that allows users to input data to create original picture books, automatically generates stories and illustrations using generative AI, and finally provides the users with a digital picture book. This system mainly utilizes visual devices such as smart glasses to provide a real-time experience in a physical store.
[1261] Specific processing of the program
[1262] The user enters a request
[1263] The user launches the "Smart Picture Book Maker" application through the smart glasses and inputs basic information about the picture book, information about the characters, and a summary of the story. For example, the user can input the character's name, age, and gender, and then enter details of the story's plot and key events. After completing the input, the user clicks the "Generate" button, and the data is sent to the server.
[1264] The device sends the data to the server
[1265] The data entered by the user is sent from the smart glasses to the server, where it is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol (e.g., HTTPS).
[1266] The server generates the story
[1267] The server analyzes the received data and uses a generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about a cat going on an adventure," the generation AI will generate a specific storyline such as, "One day, the cat steps into a magical forest..." The generation AI uses natural language processing technology.
[1268] The server generates the illustrations
[1269] The generative AI generates illustrations for each scene in the story, customizing them based on user-provided images and specific character attributes. For example, a prompt such as "Draw a cat based on a photo of the character" can be used to generate a new image.
[1270] The server assembles the picture book data
[1271] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to ensure that each page of the digital picture book is properly positioned.
[1272] The server delivers the picture book to the user
[1273] The completed digital storybook is then delivered to a visual device, where users can view it through smart glasses.
[1274] Specific use cases
[1275] Example 1: Creating a picture book for preschoolers
[1276] The user inputs, "I want to create an adventure story for a 3-year-old child. The main character will be a character using a child's photo, named Taro, 4 years old." The data is sent from the smart glasses to the server. The server uses a generative AI to generate a story such as, "One day, Taro meets a mysterious creature in the forest..." and creates illustrations featuring Taro as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by wearing the smart glasses.
[1277] Example 2: Creating an educational picture book for a specific theme
[1278] The user inputs, "I want to create a story that will teach children in the early grades of elementary school about space. The main character will be a character using a child's photo, named Hanako, 7 years old." The data is sent from the smart glasses to the server. The server uses a generation AI to generate a story such as "Hanako gets on a spaceship and sets off to explore the planet..." and creates illustrations featuring Hanako as the main character based on the photos provided by the user. The completed picture book data is sent to a visual device, and the user can view the picture book by putting on the smart glasses.
[1279] Prompt Sentence Examples
[1280] "I want to write a story about an adventure in the forest for my four-year-old son. The main character is a character made from a photo of my son, named Taro, who is five years old."
[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1282] Step 1:
[1283] The user puts on the smart glasses and launches the "Smart Picture Book Maker" application. The user enters character information and a story outline for the original picture book through the application's input screen. For example, the user enters information such as the character's name, age, gender, and related images into the form, followed by a detailed description of the story's plot and important events. When the user clicks the "Generate" button, this data is prepared.
[1284] Input: Character information (name, age, gender, image), story summary
[1285] Output: A data object in JSON format
[1286] Step 2:
[1287] The device (smart glasses) sends the data entered by the user to the server. The device encodes the entered data into JSON format and sends it to the server using a secure communication protocol (e.g., HTTPS).
[1288] Input: A JSON formatted data object
[1289] Output: Send data to the server
[1290] Step 3:
[1291] The server analyzes the received data and automatically generates a detailed story based on the generative AI model. Natural language processing technology is used to generate the story, and the development of the story is determined based on the input data. For example, if the generative AI receives the prompt "A cat goes on an adventure," it will generate a storyline like "One day, a cat steps into a magical forest..."
[1292] Input: A JSON formatted data object
[1293] Output: Generated story (text data)
[1294] Step 4:
[1295] The server generates illustrations for each scene in the generated story. The AI uses built-in image generation technology to create customized illustrations based on user-provided images and character attributes. For example, images are generated according to specific instructions, such as "draw a cat based on a photo of the character."
[1296] Input: Generated story (text data), character information (images)
[1297] Output: Generated illustration (image data)
[1298] Step 5:
[1299] The server integrates the generated story and illustrations and creates a digital picture book based on an appropriate layout algorithm. The story text and illustrations are arranged appropriately for each page, creating a digital picture book format. The book can then be exported in PDF format or a dedicated app display format.
[1300] Input: Generated story (text data), generated illustrations (image data)
[1301] Output: Digital picture book (PDF format or dedicated app format)
[1302] Step 6:
[1303] The server delivers the completed digital picture book to a visual device (smart glasses), and the user can view the received digital picture book through the smart glasses.
[1304] Input: Digital picture book (PDF format or dedicated app format)
[1305] Output: Delivery to smart glasses, user viewing of digital picture books
[1306] 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.
[1307] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[1308] System Overview
[1309] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[1310] The device sends the input information and analyzed emotional data to the server, where the server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing users to view it digitally.
[1311] Specific processing of the program
[1312] The user enters a request
[1313] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[1314] Emotion recognition by emotion engine
[1315] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[1316] The device sends the data to the server
[1317] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[1318] The server generates the story and illustrations
[1319] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[1320] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[1321] The server assembles the picture book data
[1322] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[1323] The server delivers the picture book to the user
[1324] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[1325] Specific examples
[1326] Example 1: Creating a picture book for preschoolers
[1327] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[1328] Example 2: Creating an educational picture book
[1329] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[1330] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[1331] The processing flow will be explained below.
[1332] Processing Steps
[1333] Step 1:
[1334] The user launches the "Picture Book Maker" application. The user opens the application on their smartphone or PC and logs in.
[1335] Step 2:
[1336] The user enters basic information. The user accesses a form to enter the book title, target age group, story theme, etc., and fills in each item.
[1337] Step 3:
[1338] The user registers information about the character. The user accesses a form to enter the character's name, role, age, gender, photo, etc., and fills in each item.
[1339] Step 4:
[1340] The user enters a story summary: The user enters the plot summary and important events in detail and clicks the "Submit" button.
[1341] Step 5:
[1342] The device sends the user's input data to the server, which then encodes the data in an appropriate format, such as JSON, and sends it to the server using a secure communication protocol.
[1343] Step 6:
[1344] The device collects the user's emotional data. It uses the device's camera and microphone to collect the user's facial expression data and voice data.
[1345] Step 7:
[1346] The device transmits the collected emotion data to the server, which then encodes the data in an appropriate format and transmits it to the server using a secure communication protocol.
[1347] Step 8:
[1348] The server generates the story. The server analyzes the received user data and emotional data, and uses the generation AI to automatically generate a detailed story. For example, if a user inputs, "I want to create a story about Mike the cat going on an adventure," the generation AI will generate a story such as, "One day, Mike finds himself in a magical forest..."
[1349] Step 9:
[1350] The server adjusts the tone of the story based on the emotion data. The server adjusts the tone of the story (e.g., fun, moving, suspenseful) according to the user's emotion.
[1351] Step 10:
[1352] The server generates illustrations. The server uses an image generation algorithm to generate illustrations that correspond to each scene in the story. Customized illustrations are generated based on user-provided photos and character attributes.
[1353] Step 11:
[1354] The server adjusts the facial expressions of the illustrations based on the emotional data, and adjusts the character's facial expressions and the tone of the environment based on the user's emotional data.
[1355] Step 12:
[1356] The server assembles the picture book data. The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[1357] Step 13:
[1358] The server sends the picture book data to the terminal, sends the generated digital picture book file to the user's terminal, and notifies the user that data delivery has been completed.
[1359] Step 14:
[1360] The device displays the picture book. The device displays the received digital picture book data, allowing users to view the picture book on their smartphone or PC.
[1361] This step allows users to easily create original digital picture books and enjoy content customized to their emotions.
[1362] Example 2
[1363] 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."
[1364] Conventional digital picture book creation systems lack support for users to easily create original stories and illustrations, making it difficult to provide personalized content that reflects the user's emotions. Furthermore, the lack of a customization function based on the user's emotions makes it difficult to create picture books optimized for individual users.
[1365] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input data for creating an original picture book; means for a terminal to acquire and transmit the user's input data and emotional data; a server that receives the input data and emotional data; means by the server that generates a story based on the input data and emotional data; means by the server that generates illustrations based on the story; means for creating a digital picture book by integrating the generated story and illustrations; and means for delivering the digital picture book to a user terminal. This makes it possible to easily create and deliver an original digital picture book that is individually optimized while reflecting the user's emotions.
[1366] "User" refers to a person who uses the system to create an original picture book.
[1367] An "original picture book" refers to a picture book that includes a unique story and illustrations generated based on data and emotional data entered by the user.
[1368] "Data" refers to the information that users input into the system, including character information and story outlines.
[1369] "Emotional data" refers to information about the emotional state obtained by analyzing the user's facial expressions and voice.
[1370] "Terminal" refers to a device that allows a user to input and send data, and specifically includes smartphones and PCs.
[1371] The term "server" refers to a computer device that receives data and emotional data sent by users, generates stories and illustrations, and integrates picture books.
[1372] "Generative AI" refers to artificial intelligence technology that automatically generates stories based on user input data and emotional data.
[1373] "Emotion engine" refers to technology that analyzes a user's facial expressions and voice data to obtain emotional data.
[1374] "Story" refers to the content of the story generated by the generative AI.
[1375] "Illustrations" refers to illustrations created by the server based on the generated story.
[1376] "Digital picture book" refers to a picture book created in digital format that integrates generated stories and illustrations.
[1377] "Distribution" refers to the process of sending the completed digital picture book to the user's terminal.
[1378] The present invention is a system that allows users to input data for creating an original picture book, automatically generates a story and illustrations using a generative AI model and an emotion engine, and finally provides the user with a digital picture book. This system is characterized by its ability to recognize the user's emotions and customize the content accordingly. A specific embodiment of this system is described below.
[1379] System Overview
[1380] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and image) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and during use.
[1381] The device sends the input information and analyzed emotional data to the server, where the generative AI model and emotion engine on the server generate a story and illustrations based on the information. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[1382] Specific program description
[1383] The user enters a request
[1384] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into a form, and then enters details of the story's plot and important events. The input data is confirmed by clicking the "Generate" button.
[1385] Emotion recognition by emotion engine
[1386] When a user inputs information, the device captures emotion data from the user's facial expressions and voice via the camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state. This emotion data is sent to the server along with the input data. The emotion engine can use, for example, Microsoft's Azure Emotion API.
[1387] The device sends the data to the server
[1388] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format such as JSON and sent using a secure communication protocol such as HTTPS. The device can be a smartphone or a PC.
[1389] The server generates the story and illustrations
[1390] The server analyzes the received data and automatically generates a detailed story using a generative AI model (e.g., OpenAI's GPT-3). The generated story can be adjusted in tone and content based on emotions recognized by an emotion engine. For example, if the user expresses positive emotions, the server can generate an upbeat and fun story.
[1391] The server also reflects the data from the emotion engine when generating illustrations. For example, based on the image provided by the user, the facial expression and background of the generated character will change according to the user's emotional state. This means that if the user provides an image of a smiling character, the character will also be drawn smiling.
[1392] The server assembles the picture book data
[1393] The generated story and illustrations are then integrated by a server, which then assembles the digital picture book into a suitable layout. The server uses a layout algorithm (e.g., Adobe InDesign Server) to determine the placement of each page, resulting in a beautiful and coherent digital picture book.
[1394] The server delivers the picture book to the user
[1395] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server protects the user's privacy by transmitting data using a secure communication protocol. Users receive the digital picture book on their smartphone or PC and can view it using a dedicated app or PDF reader.
[1396] Examples of prompt statements
[1397] "I want to create an adventure story for my 4-year-old son. The main character is a character made using a photo of my son, named Yuuta, who is 5 years old. The story will have a cheerful and fun adventure theme. The generated character's expressions and environment will be based on positive emotions."
[1398] The above is a specific embodiment for implementing the system of the present invention, which allows users to easily create and view original digital picture books.
[1399] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1400] System program processing flow
[1401] Step 1: User enters request
[1402] Step 2: Emotion recognition by the emotion engine
[1403] Step 3: The device sends the data to the server
[1404] Step 4: The server generates the story and illustrations
[1405] Step 5: The server assembles the picture book data
[1406] Step 6: The server delivers the picture book to the user
[1407] Specific explanation of each processing step
[1408] Step 1: User enters request
[1409] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story outline. For example, the user enters the character's name, age, gender, and related images into the form, followed by details about the story's plot and important events. Clicking the "Generate" button finalizes the input data. The input data is saved on the device and used in the next step.
[1410] Input: Character information (name, age, gender, image), story summary
[1411] Output: Confirmed input data
[1412] Step 2: Emotion recognition by the emotion engine
[1413] When the user enters information, the device collects the user's facial expressions and voice through the camera and microphone. An emotion engine (e.g., Microsoft's Azure Emotion API) analyzes this data and recognizes the user's current emotional state. The analysis results are stored on the device and used in the next step.
[1414] Input: facial expression data, voice data
[1415] Output: Parsed emotion data
[1416] Step 3: The device sends the data to the server
[1417] The device sends the confirmed input data and analyzed emotion data to the server. This data is encoded in JSON format and securely transmitted using HTTPS. The server stores the received data for analysis.
[1418] Input: Confirmed input data, analyzed emotion data
[1419] Output: Data sent to the server
[1420] Step 4: The server generates the story and illustrations
[1421] The server analyzes the input data and emotional data it receives and automatically generates a story using a generative AI model (e.g., OpenAI's GPT-3). The tone and content of the generated story are adjusted based on the emotional data. The server then generates illustrations in a similar manner. The illustrations are customized based on the images and emotional data provided by the user.
[1422] Input: Input data, emotion data
[1423] Output: Generated story and illustrations
[1424] Step 5: The server assembles the picture book data
[1425] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. The server uses a layout algorithm (e.g., Adobe InDesign server) to set the layout of each page, and the story and illustrations are beautifully arranged.
[1426] Input: Generated story, illustrations
[1427] Output: Digital picture book data
[1428] Step 6: The server delivers the picture book to the user
[1429] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device. The server securely transmits data using HTTPS, and the user can receive and view the digital picture book on their smartphone or PC.
[1430] Input: Digital picture book data
[1431] Output: Digital picture book delivered to the user's device
[1432] These are the specific processing steps of the program for this system, which allows users to easily create and view original digital picture books.
[1433] (Application example 2)
[1434] 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."
[1435] Conventional digital picture book generation systems have struggled to provide an individualized experience that reflects the user's emotions. In certain situations, the story and illustrations are not adjusted based on the user's emotions, resulting in a lack of personalized content. Furthermore, the lack of technology to acquire user emotion data in real time and apply it to picture book production makes it difficult to generate picture books that appeal to the user's desired emotions.
[1436] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input data for creating an original picture book, means for transmitting the user's input data to the server, means for the server to generate a story based on the input data, means for the server to generate illustrations based on the story, means for integrating the generated story and illustrations to create a digital picture book, means for delivering the digital picture book to a user terminal, and means having an emotion engine that acquires and analyzes emotion data and adjusting the tone and content of the story and illustrations based on the emotion data. This makes it possible to generate a personalized digital picture book that matches the user's emotions.
[1437] "User input data" refers to data such as character information and story outlines that are input by the user to create an original picture book.
[1438] A "server" is a computer system that receives user input data and generates stories and illustrations to create a digital picture book.
[1439] "Story generation means" refers to a means by which the server automatically creates a story based on user input data.
[1440] The "illustration generating means" is a means for creating illustrations based on the story generated by the server.
[1441] The "digital picture book creation means" is a means for creating a digital picture book by integrating the generated story and illustrations.
[1442] "Distribution means" refers to a means for transmitting the completed digital picture book to the user terminal.
[1443] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice data and recognizes their emotional state.
[1444] "Emotion data" is data that indicates the user's emotional state, obtained as a result of analysis by the emotion engine.
[1445] "Customization" refers to adjusting the content and tone of the story and illustrations based on user-provided photographs and emotional data.
[1446] "User terminal" refers to devices such as smartphones, tablets, and PCs used for creating and viewing picture books.
[1447] This invention is a system that allows users to input data to create an original picture book, automatically generates a story and illustrations using a generative AI and emotion engine, and finally provides the user with a digital picture book. This system is particularly characterized by its ability to recognize the user's emotions and customize the content accordingly.
[1448] System Overview
[1449] Users access the "Picture Book Maker" application using a device such as a smartphone or PC and enter information to create an original picture book tailored to their child or a specific theme. Specifically, users enter information about the characters that appear in the picture book (such as name, age, gender, and photo) and a summary of the story. The emotion engine also analyzes the user's emotions based on facial expression and voice data when the user enters information and while using the app.
[1450] The device sends the input information and analyzed emotional data to the server. The server's generative AI and emotion engine use this information to generate a story and illustrations. The server then integrates the generated story and illustrations and assembles them into a digital picture book. The book is then distributed to the device, allowing the user to view it digitally.
[1451] Specific processing of the program
[1452] The user enters a request
[1453] The user launches the "Picture Book Maker" application and enters basic information about the picture book, information about the characters, and a story summary. For example, the user enters the character's name, age, gender, and relevant photos into the form, and then enters details of the story's plot and important events. The input data is completed by clicking the "Generate" button.
[1454] Emotion recognition by emotion engine
[1455] When a user inputs information, the device captures emotional data from the user's facial expressions and voice via a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state.
[1456] The device sends the data to the server
[1457] The data entered by the user and the emotional data analyzed by the emotion engine are sent from the device to the server. The data is encoded in an appropriate format, such as JSON, and transmitted using a secure communication protocol.
[1458] The server generates the story and illustrations
[1459] The server analyzes the received data and automatically generates a detailed story using generative AI. The generated story's tone and content are adjusted based on the emotions recognized by the emotion engine. For example, if the user expresses positive emotions, the generated story will be full of fun and adventure.
[1460] The server also uses data from the emotion engine to generate illustrations. For example, based on a user-provided photo, the generated character's facial expression and environment can be changed according to the user's emotional state.
[1461] The server assembles the picture book data
[1462] The generated story and illustrations are integrated by the server and assembled into a digital picture book with an appropriate layout. A layout algorithm is applied to adjust the placement of each page.
[1463] The server delivers the picture book to the user
[1464] The completed digital picture book is exported in PDF format or a dedicated app display format and delivered to the user's device, where the user can receive it and view it on their smartphone or PC.
[1465] Specific examples
[1466] Example 1: Creating a picture book for preschoolers
[1467] The user inputs, "I want to create an adventure story for my 4-year-old son. The main character will be a character using my son's photo, named Yuuta, 5 years old." As data is sent from the device to the server, the user's facial expressions and voice data are analyzed by the emotion engine. Using the generative AI and emotion engine, the server generates a story—"One day, Yuuta meets a mysterious creature in the forest..."—and illustrations based on the user's emotion data. A picture book with a fun, adventurous atmosphere is completed, and the user can view it on their smartphone.
[1468] Example 2: Creating an educational picture book
[1469] The user inputs, "I want to create a story for my 6-year-old daughter that will teach her about space. The main character will be a character using my daughter's photo, named Sakura, and she's 7 years old." The data is sent from the device to the server, where an emotion engine analyzes the user's emotions. The server uses generative AI to generate a story—"Sakura gets on a spaceship and sets off to explore the planet..."—and illustrations in bright colors based on positive emotions. The completed picture book data is sent to the device, where the user can view it on their PC.
[1470] Example of input prompt for generative AI model
[1471] User information: Character name is "Yuta", age is 5, gender is male. Story summary is "One day, Yuuta encounters a mysterious creature in the forest."
[1472] Emotion data: The user is smiling when typing, and positive emotions are detected.
[1473] As described above, the system of the present invention provides a means for easily creating and viewing an original digital picture book that reflects the user's emotions.
[1474] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1475] Step 1:
[1476] The user starts the "Picture Book Maker" application and inputs character information and a story outline. Specifically, the user fills in a dedicated input form with the character's name, age, gender, photo, story summary, etc. This generates user input data.
[1477] Step 2:
[1478] After the user completes the input data, the device will use the camera and microphone to collect the user's facial expressions and voice. These emotion data will be sent to the emotion engine and used to analyze the user's emotional state. Emotion data will be generated as a result of the analysis.
[1479] Step 3:
[1480] The device encodes user input data and emotion data in JSON format and sends it to the server using a secure communication protocol. The input data is the user input data and emotion data, and the output is the data sent to the server.
[1481] Step 4:
[1482] The server analyzes the received user input data and emotional data. Specifically, it uses generative AI to automatically generate a detailed story based on the user input data. The emotional engine analyzes the emotional data and adjusts the tone and content of the story. For example, if positive emotions are detected, a fun adventure story will be generated. The input data are user input data and emotional data, and the output is the generated story.
[1483] Step 5:
[1484] The server generates illustrations based on the story it generates. Characters are customized based on photos provided by the user, and backgrounds and other visual elements are generated using a generative AI model. Emotional data is also taken into account during this process, and the illustrations are adjusted to be more emotionally appealing. The input data are the story, user photos, and emotional data, and the output is the generated illustration.
[1485] Step 6:
[1486] The server integrates the generated story and illustrations and assembles them into a digital picture book. It applies a layout algorithm to properly position each page and create the final digital picture book file. The input data are the generated story and illustrations, and the output is the digital picture book data.
[1487] Step 7:
[1488] The server exports the completed digital picture book data in PDF format or a dedicated app format and distributes it to the user's device. The user receives this and views the digital picture book on their smartphone or PC. The input data is the digital picture book data, and the output is a digital picture book distributed to the user's device.
[1489] 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.
[1490] 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.
[1491] 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.
[1492] 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.
[1493] 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.
[1494] 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.
[1495] 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).
[1496] 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.
[1497] 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."
[1498] 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.
[1499] 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).
[1500] 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.
[1501] 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.
[1502] 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.
[1503] 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.
[1504] 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.
[1505] 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.
[1506] 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.
[1507] 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.
[1508] 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.
[1509] 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.
[1510] The following is further disclosed regarding the above embodiment.
[1511] (Claim 1)
[1512] A means for a user to input data for creating an original picture book;
[1513] means for transmitting the user input data to a server;
[1514] means for the server to generate a story based on the input data;
[1515] means for the server to generate illustrations based on the story;
[1516] a means for integrating the generated stories and illustrations to create a digital picture book;
[1517] means for distributing the digital picture book to a user terminal;
[1518] A system including:
[1519] (Claim 2)
[1520] The data entered by the user includes character information and a story summary.
[1521] 10. The system of claim 1.
[1522] (Claim 3)
[1523] The illustrations generated by the server include customization based on user-provided photographs.
[1524] 10. The system of claim 1.
[1525] "Example 1"
[1526] (Claim 1)
[1527] A means for a user to input data for creating an original electronic book;
[1528] means for transmitting the user input data from a communication device to a computer;
[1529] means for the computer to generate a story based on the input data;
[1530] means for the computer to generate images based on the story;
[1531] a means of integrating the generated narrative and images to create a digital e-book;
[1532] means for delivering said digital electronic book to a user's communication device;
[1533] A system including:
[1534] (Claim 2)
[1535] The data entered by the user includes character information and a story summary.
[1536] 10. The system of claim 1.
[1537] (Claim 3)
[1538] the computer-generated image includes customization based on a user-provided photograph;
[1539] 10. The system of claim 1.
[1540] "Application Example 1"
[1541] Claiming a new invention
[1542] (Claim 1)
[1543] A means for a user to input data for creating an original picture book;
[1544] means for transmitting the user input data to a server;
[1545] means for the server to generate a story based on the input data;
[1546] means for the server to generate illustrations based on the story;
[1547] a means for integrating the generated stories and illustrations to create a digital picture book;
[1548] means for delivering said digital picture book to a visual device to enable in-store browsing;
[1549] A system including:
[1550] (Claim 2)
[1551] The data entered by the user includes character information and a story summary.
[1552] 10. The system of claim 1.
[1553] (Claim 3)
[1554] The illustrations generated by the server include customization based on user-provided images.
[1555] 10. The system of claim 1.
[1556] "Example 2: Combining Emotion Engines"
[1557] (Claim 1)
[1558] A means for a user to input data for creating an original picture book;
[1559] means for acquiring and transmitting the user's input data and emotion data by the terminal;
[1560] a server that receives the input data and emotion data;
[1561] a means for generating a story based on the input data and emotion data by the server;
[1562] means for the server to generate illustrations based on the story;
[1563] a means for integrating the generated stories and illustrations to create a digital picture book;
[1564] means for distributing the digital picture book to a user terminal;
[1565] A system including:
[1566] (Claim 2)
[1567] The data input by the user includes character information, a story outline, and emotion data.
[1568] 10. The system of claim 1.
[1569] (Claim 3)
[1570] The illustrations generated by the server include customization based on user-provided images.
[1571] 10. The system of claim 1.
[1572] "Application example 2 when combining emotion engines"
[1573] (Claim 1)
[1574] A means for a user to input data for creating an original picture book;
[1575] means for transmitting the user input data to a server;
[1576] means for the server to generate a story based on the input data;
[1577] means for the server to generate illustrations based on the story;
[1578] a means for integrating the generated stories and illustrations to create a digital picture book;
[1579] means for distributing the digital picture book to a user terminal;
[1580] an emotion engine for acquiring and analyzing emotion data, and means for adjusting the tone and content of the story and illustrations based on the emotion data;
[1581] A system including:
[1582] (Claim 2)
[1583] The data entered by the user includes character information and a story summary.
[1584] The emotion engine analyzes the user's facial expressions and voice data to generate emotion data.
[1585] 10. The system of claim 1.
[1586] (Claim 3)
[1587] The illustrations generated by the server include customization based on user-provided photographs.
[1588] adjusting the generated story and illustrations in response to the emotion data;
[1589] 10. The system of claim 1. [Explanation of symbols]
[1590] 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 a user to input data for creating an original picture book; means for transmitting the user input data to a server; means for the server to generate a story based on the input data; means for the server to generate illustrations based on the story; a means for integrating the generated stories and illustrations to create a digital picture book; means for distributing the digital picture book to a user terminal; A system including:
2. The data entered by the user includes character information and a story summary. The system of claim 1 .
3. The illustrations generated by the server include customization based on user-provided photographs. The system of claim 1 .
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A