System

Abstract

To provide a system.SOLUTION: A system comprises: means for inputting a main character in a story inputted by a user and a setting for the story; an emotion engine for recognizing the user's emotion; generation means for generating a story plot by inputting, in a generative AI model, prompt sentences proposing to the user a personalized story on the basis of the story and the setting, and for generating an original story based on the setting on the basis of the plot; and means for outputting the story generated in the generation means. The generation means adjusts the original story's tone and theme on the basis of the user's emotion.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional picture books and stories generally use fixed stories and characters, making it difficult to customize them to meet the needs and circumstances of individual users. In particular, creating stories in which children are the main characters requires time and effort, making it a difficult task for ordinary parents and educators. [Means for solving the problem]

[0005] As a means for solving this problem, the system of the present invention includes a means for inputting a protagonist appearing in a story input by a user and a setting of the story, an emotion engine that recognizes the emotions of the user, a generation means for generating a story plot by inputting prompt sentences that suggest a personalized story to the user based on the story and the setting into a generative AI model, and generating an original story based on the setting based on the plot, and a means for outputting the story generated by the generation means, wherein the generation means adjusts the tone and theme of the original story based on the emotions of the user. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, a system is provided that includes an interface through which a user inputs a protagonist and setting. Specifically, the user inputs information such as the protagonist's name, gender, age, likes, dislikes, etc., on a website or application. The user also selects or inputs the setting, theme, location, etc. of the story.

[0029] "Example 2"

[0030] Based on the input information, the AI ​​generates an original story. Based on the information input by the user, the AI ​​creates a story plot and generates a story based on that. The generated story is output in a format that the user can read. Specifically, it is output in text or PDF format, and the user can download and read it.

[0031] "Example 3"

[0032] In addition, a means is provided to generate original illustrations based on the AI-generated story. Specifically, the AI ​​analyzes the content of the story and generates illustrations that correspond to appropriate scenes. The generated illustrations are output together with the story, allowing users to enjoy the story visually.

[0033] "Example 4"

[0034] In addition, a means is provided to convert the AI-generated story into audio and read it aloud. Specifically, the AI ​​converts the generated story from text to audio and outputs it in a format that the user can listen to. This is convenient for users who have difficulty reading visually or who want to do other tasks while listening to the story.

[0035] The process flow of each embodiment will be described below.

[0036] "Example 1"

[0037] Step 1: A user opens a website or application and enters some information about the main character, such as their name, gender, age, likes, and dislikes.

[0038] Step 2: The user selects or inputs the setting, theme, location, etc. of the story.

[0039] "Example 2"

[0040] Step 1: The AI ​​creates a story plot based on information input by the user.

[0041] Step 2: Generate a story based on the plot created by the AI.

[0042] Step 3: The generated story is output in a format that the user can read. Specifically, it is output in text format or PDF format, and the user can download it and read it.

[0043] "Example 3"

[0044] Step 1: Analyze the content of the AI-generated story.

[0045] Step 2: The AI ​​generates illustrations that correspond to appropriate scenes based on the content of the story.

[0046] Step 3: The generated illustrations are output together with the story, allowing users to enjoy the story visually.

[0047] "Example 4"

[0048] Step 1: The AI ​​converts the generated story from text to audio.

[0049] Step 2: The converted audio is output in a format that the user can hear, which is convenient for users who have visual impairments or who want to continue with other tasks while listening to the story.

[0050] Example 1

[0051] Next, a description will be given of Example 1 of the embodiment 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".

[0052] Conventional story generation systems often fail to fully reflect the user's intentions and detailed settings when generating original stories based on information input by the user. They also lack the means to quickly and effectively provide the generated stories to users. Furthermore, they lack the ability to generate illustrations and audio based on the generated stories, limiting the user experience.

[0053] 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.

[0054] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for transmitting the input information to the server, a means for generating a prompt sentence based on the information received by the server, a means for inputting the generated prompt sentence to the generative AI model, a means for returning a story generated by the generative AI model to the server, a means for the server to transmit the generated story to the terminal, and a means for displaying the story received by the terminal to the user. This makes it possible to quickly and effectively generate an original story that reflects the user's detailed settings and provide it to the user.

[0055] A "user" is an individual or group that uses the system to input the protagonist and story settings.

[0056] The "protagonist" is the character at the center of the story, and is the person for whom the user enters information such as name, gender, and age.

[0057] "Setting" refers to information such as the background, theme, and location of the story, and is an element selected or input by the user.

[0058] The "server" is a computer system that receives information sent by a user and inputs prompt sentences into the generative AI model.

[0059] "Terminal" means a device through which a user can input information and display the generated story, including a web browser and dedicated applications.

[0060] A "prompt sentence" is text that is generated based on information entered by the user and is input into a generative AI model.

[0061] A "generative AI model" is an artificial intelligence algorithm that generates a story based on a prompt sentence, using natural language processing technology, for example.

[0062] A "story" is text that a generative AI model generates based on a prompt, and is an original story provided to the user.

[0063] "Illustrations" are illustrations that are drawn based on the generated story and provide a visual complement to the story.

[0064] "Speech" is the process of converting the generated story into audio data for reading aloud.

[0065] This invention is a system in which a user inputs the protagonist and story settings, and a generative AI model generates an original story based on that information and provides it to the user. A specific embodiment of this system will be described below.

[0066] Users input information into a website or application, such as the main character's name, gender, age, likes, dislikes, setting, theme, location, etc. For example, a user might input the following information:

[0067] Main character's name: Taro

[0068] Gender: Male

[0069] Age: 25

[0070] Likes: Adventure

[0071] Dislikes: Boredom

[0072] Story setting: Fantasy

[0073] Theme: Friendship

[0074] Location: Magical Forest

[0075] The device receives the information entered by the user and sends it to the server. To do this, the device uses a web browser or a dedicated application to send data to the server using an HTTP request.

[0076] The server receives the information sent from the device and generates a prompt sentence to input to the generative AI model. Specifically, it generates the following prompt sentence:

[0077] "The main character's name is Taro, a 25-year-old man. He loves adventure and hates boredom. The story is set in a fantasy world, the theme is friendship, and the location is a magical forest."

[0078] The server inputs the generated prompt sentence into the generative AI model. For example, OpenAI's GPT-3 (registered trademark) is used as the generative AI model. The server sends the prompt sentence using an API request.

[0079] The generative AI model generates a story based on the prompt received from the server and returns the result to the server. An example of the generated story is as follows:

[0080] "Taro is a 25-year-old adventurous young man who hates boredom. One day, he meets new friends in a magical forest and together they embark on a great adventure."

[0081] The server receives the story returned by the generative AI model and sends it to the device. The server sends the data using an HTTP response.

[0082] The device displays the story received from the server to the user, using a web browser or an application UI.

[0083] This system allows users to quickly and effectively generate and enjoy original stories that reflect detailed settings. The user experience can be further improved by adding the functionality to generate illustrations and audio based on the generated stories.

[0084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0085] Step 1:

[0086] Users input information such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, and location on a website or application. Specifically, they input information such as "Taro, male, 25 years old, adventure, boredom, fantasy, friendship, magical forest" into an input form. The input data is stored on the device in JSON format.

[0087] Step 2:

[0088] The terminal receives the information entered by the user and sends it to the server. Specifically, the terminal uses an HTTP POST request to send the entered JSON data to the server. The input data is sent to the server, and the server receives it.

[0089] Step 3:

[0090] The server receives the information sent from the device and generates a prompt to input to the generative AI model. Specifically, it analyzes the received JSON data and generates a prompt like the following:

[0091] "The main character's name is Taro, a 25-year-old man. He loves adventure and hates boredom. The story is set in a fantasy world, the theme is friendship, and the location is a magical forest."

[0092] The generated prompt sentences are input into a generative AI model.

[0093] Step 4:

[0094] The server inputs the generated prompt sentence into the generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. Specifically, the prompt sentence is sent using an API request. The input data is the prompt sentence, and the output data is the generated story.

[0095] Step 5:

[0096] The generative AI model generates a story based on the prompt received from the server and returns the result to the server. Specifically, the generative AI model generates a story using natural language processing technology and returns the generated text data to the server as an API response. The output data is the generated story.

[0097] Step 6:

[0098] The server receives the story returned from the generative AI model and sends it to the terminal. Specifically, it sends the generated story to the terminal using an HTTP response. The input data is the generated story, and the output data is the story to be sent to the terminal.

[0099] Step 7:

[0100] The terminal displays the story received from the server to the user. Specifically, the story is displayed using a web browser or an application UI. The input data is the story received from the server, and the output data is the story displayed to the user.

[0101] (Application example 1)

[0102] Next, a description will be given of Application Example 1 of Form 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."

[0103] Conventional story generation systems can generate stories based on information entered by the user, but the generated stories may not meet the user's expectations. In addition, the story generation process is a black box, making it difficult for users to understand how the story is generated. Furthermore, there are limited ways to enjoy the generated story visually or aurally, which limits the user experience.

[0104] 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.

[0105] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for outputting the generated story, a means for generating a prompt sentence to be passed to the generative AI model, and a means for displaying the generated story to the user. This allows a high-quality story to be generated based on the information input by the user, and allows the user to enjoy the story visually and aurally.

[0106] A "user" is an individual or group that uses the system to generate a story.

[0107] The "protagonist" is the character at the center of the story, and is the subject for which the user enters information such as name, gender, and age.

[0108] "Setting" refers to information such as the background, theme, and location of a story, and is an element that affects the content of the story when entered by the user.

[0109] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on information entered by the user.

[0110] A "narrative" is a text-based story generated by a generative AI model and constructed based on information input by a user.

[0111] A "prompt sentence" is an input sentence to be passed to a generative AI model, and is generated based on information entered by the user.

[0112] "Output" is the act or means of providing the generated narrative to a user.

[0113] "Display" is the act or means of visually presenting the generated narrative to a user.

[0114] A system for implementing this invention includes a means for a user to input a protagonist and setting and for a generative AI model to generate an original story based on the input, a means for outputting the generated story, a means for generating a prompt sentence to be passed to the generative AI model, and a means for displaying the generated story to the user.

[0115] System Configuration

[0116] The system consists of the following main components:

[0117] 1. User Interface: The interface through which the user inputs the main character and settings. This is implemented as a smartphone application.

[0118] 2. Generative AI model: An artificial intelligence model that generates a story based on information input by the user. Specifically, we use OpenAI's GPT-3.

[0119] 3. Prompt generation module: A module that generates a prompt sentence to be passed to the generative AI model based on the information entered by the user.

[0120] 4. Story display module: A module that visually displays the generated story to the user.

[0121] Program Processing

[0122] The server receives information input by the user through the user interface, such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, location, etc. This information is passed to the prompt generation module, which generates a prompt sentence suitable for the generative AI model.

[0123] The generated prompt sentences are passed to a generative AI model to generate an original story, which is then displayed to the user through a story display module.

[0124] Hardware and Software Used

[0125] Hardware: Smartphone

[0126] Software: Python, OpenAI API

[0127] Examples

[0128] If the user enters the following information:

[0129] Name: Taro

[0130] Gender: Male

[0131] Age: 10

[0132] Likes: Adventure

[0133] Dislikes: Boredom

[0134] Story Setting: Future city

[0135] Theme: Friendship

[0136] Location: Japan

[0137] An example of a prompt that can be generated based on this information is:

[0138] Main character's name: Taro

[0139] Gender: Male

[0140] Age: 10

[0141] Likes: Adventure

[0142] Dislikes: Boredom

[0143] Story Setting: Future city

[0144] Theme: Friendship

[0145] Location: Japan

[0146] Using this information, generate a story like the one below.

[0147] By passing this prompt to a generative AI model, a personalized story is generated for the user, which is then displayed on the smartphone screen for the user to enjoy visually.

[0148] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0149] Step 1:

[0150] The user starts the smartphone application and inputs information about the protagonist and the setting. Specifically, the user inputs information such as the protagonist's name, gender, age, likes and dislikes, story setting, theme, location, etc. through the application's interface. The input information is then sent to the server.

[0151] Input: Main character's name, gender, age, likes, dislikes, story setting, theme, location

[0152] Output: User input data

[0153] Step 2:

[0154] The server passes the received user input data to the prompt generation module. The prompt generation module generates a prompt sentence to be passed to the generative AI model based on the user input data. The prompt sentence is in text format that contains the information entered by the user.

[0155] Input: User-entered data

[0156] Output: Prompt statement

[0157] Step 3:

[0158] The server passes the generated prompt sentence to the generative AI model. The generative AI model generates an original story based on the prompt sentence. OpenAI's GPT-3 is used as the generative AI model.

[0159] Input: Prompt statement

[0160] Output: The generated story

[0161] Step 4:

[0162] The server passes the generated story to a story display module. The story display module displays the generated story on the user's smartphone. The user can visually enjoy the generated story through the screen of the smartphone.

[0163] Input: A generated story

[0164] Output: Story displayed on a smartphone

[0165] Step 5:

[0166] The user can read and enjoy the generated story, and if desired, can change the settings again and generate a new story.

[0167] Input: A story displayed on a smartphone

[0168] Output: User experience and feedback

[0169] Example 2

[0170] Next, a second embodiment of the second embodiment will be described. 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."

[0171] Conventional story generation systems have been lacking in quality and speed when generating original stories based on information entered by users. In addition, there are limited ways to provide the generated stories in a format that is easy for users to read, resulting in a poor user experience. Furthermore, there is a lack of functionality to add illustrations and audio to stories, which makes it difficult to fully bring out the appeal of the stories.

[0172] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0173] In this invention, the server includes a means for a user to input a theme, characters, and setting, a means for transmitting the input information to the server, a means for the server to input a prompt sentence to the generative AI model, a means for the generative AI model to generate a plot of the story, a means for the server to generate a detailed story based on the plot, a means for the server to convert the story into a text format or a PDF format, a means for the server to transmit the generated story to the user's terminal, and a means for the user to download and read the story. This makes it possible to quickly generate a high-quality original story based on the information input by the user and provide it in an easy-to-read format. In addition, the inclusion of a function to add illustrations and audio to the story can further enhance the appeal of the story.

[0174] A "user" is an individual or group that uses the system to input information such as theme, characters, and setting in order to generate a story.

[0175] "Theme" refers to the main subject or genre of the story, and is information entered by the user to specify the direction of the story.

[0176] "Characters" refers to characters who appear in a story, and is information that a user inputs to specify characters who play important roles in the story.

[0177] "Setting" refers to the setting or background of a story, and is information that the user inputs to specify the environment and time period of the story.

[0178] A "Terminal" is a device (e.g., PC, smartphone, tablet) that a User uses to access the System and input information.

[0179] "Server" means a computer system for receiving information submitted by a user, generating a story using a generative AI model, and finally providing the story to the user.

[0180] A "generative AI model" is an artificial intelligence model that generates story plots and detailed text based on information entered by the user.

[0181] A "prompt" is a sentence that is input into a generative AI model based on information such as theme, characters, and setting entered by the user.

[0182] A "plot" is a summary of a story's main components (introduction, development, climax, and conclusion) that is generated by a generative AI model.

[0183] The "text format" is a format in which the generated story is saved as textual information and is provided to the user in a manner that is easy to read.

[0184] "PDF Format" refers to a format in which the generated story is saved in Portable Document Format and provided to users for easy reading.

[0185] "Illustrations" are illustrations generated based on the content of the story and are used to enhance the visual appeal of the story.

[0186] "Speech" is the process of converting the generated story into audio data so that the user can enjoy it aurally.

[0187] The "means for reading aloud" is a function for playing the generated story as audio so that the user can listen to the story.

[0188] This invention is a system that generates an original story using a generative AI model based on a user's input of a theme, characters, and setting, and provides the story to the user. A specific embodiment of this system will be described below.

[0189] A user accesses the system using a terminal (e.g., a PC, a smartphone, or a tablet). The user opens a web browser and accesses the system's web page. The user enters information such as theme, characters, and setting into the input form, and clicks the "Generate" button. For example, if a user wants to generate "a story about a hero slaying a dragon in a fantasy world," the user enters "fantasy" as the theme, "hero, dragon, wizard" as the characters, and "medieval kingdom" as the setting.

[0190] The terminal sends the information entered by the user to the server in JSON format. The server generates a prompt sentence based on the received information and inputs it into a generative AI model (for example, OpenAI's GPT-4 (registered trademark)). The prompt sentence is in a format that includes an outline of the story and the setting. For example, the following prompt sentence is generated:

[0191] Theme: Fantasy

[0192] Characters: Hero, Dragon, Wizard

[0193] Setting: Medieval Kingdom

[0194] Summary of the story: A hero sets out on a journey to defeat a dragon. Along the way, he meets a wizard and together they defeat the dragon.

[0195] The generative AI model analyzes the prompt sentence and generates a story plot. The plot includes the main components of a story (introduction, development, climax, and conclusion). For example, the following plot is generated:

[0196] 1. The hero learns of the threat of the dragon.

[0197] 2. The hero decides to go on a journey.

[0198] 3. Along the way, you meet a wizard and get his help.

[0199] 4. A hero and a wizard face off against a dragon.

[0200] 5. The dragon is defeated and peace returns to the kingdom.

[0201] The server generates a detailed story based on the generated plot. The generative AI model converts the plot into detailed sentences and completes the entire story. For example, the following story is generated.

[0202] Once upon a time, there lived a hero in a medieval kingdom. One day, a dragon appeared in the kingdom and terrorized the people. The hero set out on a journey to defeat the dragon. Along the way, he met a wizard, and together they succeeded in defeating the dragon. Peace returned to the kingdom, and the hero was celebrated as a hero.

[0203] The server converts the generated story into a format that is easy for the user to read, such as text or PDF. For example, a Python library is used to generate the PDF file.

[0204] The server sends the converted story to the user's device. The user receives an email with a download link or sees a download link on a web page. The user can click the download link to download and read the story. The user can open the downloaded file and enjoy the story. For example, open the PDF file using a PDF reader.

[0205] The system allows users to quickly generate high-quality original stories based on the information they input, delivered in an easy-to-read format, and includes the ability to add illustrations and audio to the stories to enhance their appeal.

[0206] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0207] Step 1:

[0208] The user inputs the theme, characters, and setting.

[0209] A user uses a terminal to access the system's web page and inputs information such as theme, characters, and setting into an input form. For example, the user inputs the theme "fantasy," the characters "heroes, dragons, and wizards," and the setting "medieval kingdom." The input information becomes the basis of prompt sentences for generating a story.

[0210] Step 2:

[0211] The terminal transmits the input information to the server.

[0212] The terminal sends the information entered by the user to the server in JSON format. Specifically, the data in the input form is converted to JSON format and sent to the server using an HTTP request. The server analyzes the received data and uses it to generate a prompt text.

[0213] Step 3:

[0214] The server inputs a prompt sentence into the generative AI model.

[0215] The server generates a prompt based on the received information. For example, it generates the following prompt:

[0216] Theme: Fantasy

[0217] Characters: Hero, Dragon, Wizard

[0218] Setting: Medieval Kingdom

[0219] Summary of the story: A hero sets out on a journey to defeat a dragon. Along the way, he meets a wizard and together they defeat the dragon.

[0220] The generated prompt sentences are input into a generative AI model.

[0221] Step 4:

[0222] A generative AI model generates the story plot.

[0223] The generative AI model analyzes the input prompt sentence and generates a story plot. The plot includes the main components of a story (introduction, development, climax, and conclusion). For example, the following plot is generated:

[0224] 1. The hero learns of the threat of the dragon.

[0225] 2. The hero decides to go on a journey.

[0226] 3. Along the way, you meet a wizard and get his help.

[0227] 4. A hero and a wizard face off against a dragon.

[0228] 5. The dragon is defeated and peace returns to the kingdom.

[0229] The generated plot is returned to the server.

[0230] Step 5:

[0231] The server generates a detailed story based on the plot.

[0232] The server generates a detailed story based on the generated plot. The generative AI model converts the plot into detailed sentences and completes the entire story. For example, the following story is generated.

[0233] Once upon a time, there lived a hero in a medieval kingdom. One day, a dragon appeared in the kingdom and terrorized the people. The hero set out on a journey to defeat the dragon. Along the way, he met a wizard, and together they succeeded in defeating the dragon. Peace returned to the kingdom, and the hero was celebrated as a hero.

[0234] The generated stories are stored on a server.

[0235] Step 6:

[0236] The server converts the stories into text or PDF format.

[0237] The server converts the generated story into a format that is easy for users to read, such as text or PDF. For example, a Python library is used to generate PDF files. The converted files are then stored on the server.

[0238] Step 7:

[0239] The server transmits the generated story to the terminal.

[0240] The server sends the converted story to the user's device. The user receives an email containing a download link or sees a download link on a web page. The user clicks on the download link to download the story.

[0241] Step 8:

[0242] The user downloads and reads the story.

[0243] The user can use the device to download and read the story. The user can then open the downloaded file and enjoy the story, for example by opening the PDF file using a PDF reader.

[0244] (Application example 2)

[0245] Next, a description will be given of Application Example 2 of Form 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."

[0246] Conventional story generation systems can generate stories based on information entered by the user, but they lack the functionality to output and save the generated stories in a variety of formats. They also lack illustrations to enjoy the generated stories visually, and audio functions to enjoy them audibly. This limits the user's experience and restricts the way the story can be enjoyed.

[0247] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for a user to input a protagonist and a setting, and an AI to generate an original story based on the input, a means for outputting the generated story in a text format or a PDF format, and a means for saving the generated story. This allows the user to output and save the generated story in various formats. In addition, by further including a means for generating original illustrations based on the story generated by the AI, the story can be enjoyed visually. In addition, by further including a means for converting the story generated by the AI ​​into audio and reading it aloud, the story can be enjoyed auditorily.

[0248] A "user" is an individual or organization that uses the system to request the generation of a story.

[0249] The "protagonist" is the central character of the story and is part of the information entered by the user.

[0250] "Setting" refers to information such as the background of the story, the environment, time period, and location in which the story takes place, and is part of the information entered by the user.

[0251] "AI" stands for artificial intelligence, a technology that generates stories based on information entered by the user.

[0252] A "story" is an AI-generated text that contains a sequence of events and character actions.

[0253] A "text format" is a digital document format that is composed only of text information.

[0254] "PDF format" is an abbreviation for Portable Document Format, and is a standard file format for electronically storing documents.

[0255] "Output" refers to providing the generated narrative in a form viewable by a user.

[0256] "Preservation" refers to recording the generated stories in a digital format so that they can be reused at a later time.

[0257] "Illustrations" are illustrations or images that visually complement the content of the story.

[0258] "Speech" refers to the conversion of a textual narrative into audio data.

[0259] "Storytelling" refers to playing an audio version of a story to the user.

[0260] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on the input, means for outputting the generated story in text or PDF format, and means for saving the generated story.

[0261] System Configuration

[0262] The system uses the following hardware and software:

[0263] Hardware:

[0264] Smartphone

[0265] software:

[0266] Python

[0267] OpenAI API

[0268] FPDF Library

[0269] Processing flow

[0270] 1. Getting user input:

[0271] Through a smartphone application, users input information about the story, such as the theme, characters, and setting, which allows the system to generate a story according to the user's wishes.

[0272] 2. Generate prompt:

[0273] The server generates a prompt based on the information entered by the user, which contains instructions for the generative AI model to generate a story.

[0274] Example prompt:

[0275] Theme: Adventure

[0276] Characters: Hero, Wizard

[0277] Setting: Medieval fantasy world

[0278] Generate a story based on this information.

[0279] 3. Narrative generation:

[0280] The server uses OpenAI's API to input a prompt sentence into a generative AI model (e.g., GPT-3) to generate a story. The generated story is obtained in text format.

[0281] 4. Output and save the story:

[0282] The server outputs the generated stories in text and PDF formats for users to download, and also allows users to save the generated stories for later reuse.

[0283] Examples

[0284] If the user inputs an "adventure" theme, characters that are a "hero" and a "wizard," and a medieval fantasy world as the setting, the following prompt text will be generated:

[0285] Example prompt:

[0286] Theme: Adventure

[0287] Characters: Hero, Wizard

[0288] Setting: Medieval fantasy world

[0289] Generate a story based on this information.

[0290] By inputting this prompt into a generative AI model, an original adventure story is generated. The generated story is saved in PDF format and users can download it to read.

[0291] In this way, users can easily create original stories that fit their own desires and enjoy them in a variety of formats.

[0292] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0293] Step 1:

[0294] A user starts the smartphone application and inputs information such as the theme, characters, and setting of the story. The input information is sent to the server. The input data includes the theme (e.g., adventure), characters (e.g., hero, wizard), and setting (e.g., a medieval fantasy world).

[0295] Step 2:

[0296] The server receives the input data sent by the user and generates a prompt sentence. Specifically, it creates the following prompt sentence based on the input data.

[0297] Theme: Adventure

[0298] Characters: Hero, Wizard

[0299] Setting: Medieval fantasy world

[0300] Generate a story based on this information.

[0301] The generated prompt text is used in the next step.

[0302] Step 3:

[0303] The server sends the generated prompt sentence to the OpenAI API and generates a story using a generative AI model (e.g. GPT-3). The generative AI model takes the prompt sentence as input and outputs the text of the story. The output story is stored on the server.

[0304] Step 4:

[0305] The server outputs the generated stories in text and PDF formats. Specifically, it converts the stories into PDF format using the FPDF library. The converted PDF files are stored on the server for users to download.

[0306] Step 5:

[0307] Users download and view the stories generated through a smartphone application. Users can choose to download stories in text or PDF format. Downloaded stories are stored on the user's device and can be viewed at any time.

[0308] In this way, users can easily create original stories that fit their own desires and enjoy them in a variety of formats.

[0309] Example 3

[0310] Next, a third embodiment of the third embodiment will be described. 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."

[0311] Conventional story generation systems only generate stories based on settings entered by the user, making it difficult to provide visual and auditory enjoyment. In addition, they do not adequately address users who have difficulty reading visually or who want to do other tasks while listening to a story. This limits the user's experience and restricts how they can enjoy a story.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0313] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for analyzing the generated story, a means for generating illustrations based on the analysis results, a means for converting the generated story into audio, and a means for outputting the generated story, illustrations, and audio files, thereby enabling the user to enjoy the story both visually and aurally.

[0314] A "user" is an entity that uses the system to generate and output a story.

[0315] "Protagonist and setting" refers to details of the characters and scenario that the user enters as information necessary to generate the story.

[0316] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on information entered by the user.

[0317] A "narrative" is a story in text form generated by a generative AI model.

[0318] "Means of analysis" refers to the process of analyzing the content of the generated story and extracting important scenes and events.

[0319] An "illustration" is an image created to visually represent a particular scene or event in the story.

[0320] A "convert-to-speech means" is a process that converts the generated narrative text into audio data.

[0321] "Output means" is the process that provides the generated story, illustrations, and audio files to the user.

[0322] This invention is a system in which a generative AI model generates an original story based on a prompt sentence entered by a user, analyzes the story to generate illustrations, and converts the story into audio for output. A specific embodiment of this system will be described below.

[0323] First, the user accesses the system interface using a terminal (e.g., a PC or a smartphone). The user inputs a prompt that indicates the theme and setting of the story. For example, the user might input "Adventure in the Magical Forest."

[0324] Next, the server receives the prompt sentence entered by the user and passes it to a generative AI model (e.g., GPT-4). The generative AI model generates a story based on the prompt sentence. The generated story is saved in text format on the server.

[0325] The server then analyzes the content of the generated story, specifically extracting scenes and important events from the story, and uses the results of this analysis for subsequent illustration generation and audio generation.

[0326] Next, the server generates illustrations using an image generation AI model (e.g., DALL-E) based on the results of the story analysis. Illustrations corresponding to each scene are generated and stored together with the story text.

[0327] The server then converts the generated story into audio using text-to-speech software (e.g., Google® Text-to-Speech API). The generated audio file is saved in a format that can be heard by the user.

[0328] Finally, the server provides the generated stories, illustrations, and audio files to the user, who can then view and enjoy these contents through their terminals.

[0329] As a concrete example, if the user enters the prompt "Adventure in the magical forest", the server will perform the following process:

[0330] 1. The server generates a story based on "Adventure in the Magical Forest" using a generative AI model (GPT-4).

[0331] 2. The server analyzes the content of the generated story and uses DALL-E to generate illustrations corresponding to each scene in the story.

[0332] 3. The server converts the story into audio using the Google Text-to-Speech API.

[0333] 4. The server provides the generated story, illustrations and audio files to the user.

[0334] This allows the user to enjoy the story both visually and aurally. The flow of the specific process in the third embodiment will be described with reference to FIG.

[0335] Step 1:

[0336] The user enters a prompt.

[0337] A user uses a terminal to access the system's interface and inputs a prompt that indicates the theme and setting of the story, for example, "An adventure in a magical forest." The input prompt is then sent to the server.

[0338] Input: The prompt text entered by the user.

[0339] Output: The prompt text sent to the server.

[0340] Step 2:

[0341] The server generates the story using a generative AI model

[0342] The server receives the prompt sentence entered by the user and passes it to a generative AI model (e.g., GPT-4). The generative AI model generates a story based on the prompt sentence. The generated story is saved in text format on the server.

[0343] Input: Prompt statement

[0344] Output: Generated story (in text format)

[0345] Step 3:

[0346] The server parses the generated story

[0347] The server analyzes the generated story content, specifically extracting scenes and important events from the story using natural language processing (NLP) algorithms, and the analysis results are used for subsequent illustration generation and audio generation.

[0348] Input: Generated story (in text format)

[0349] Output: Story analysis results (extraction of scenes and events)

[0350] Step 4:

[0351] The server generates the illustrations.

[0352] The server generates illustrations using an image generation AI model (e.g., DALL-E) based on the results of the story analysis. Illustrations corresponding to each scene are generated and stored together with the story text.

[0353] Input: Story analysis results

[0354] Output: The generated illustration

[0355] Step 5:

[0356] The server converts the story into audio.

[0357] The server converts the generated story into audio using text-to-speech software (e.g., Google Text-to-Speech API), and the generated audio file is saved in a format that can be heard by the user.

[0358] Input: Generated story (in text format)

[0359] Output: The generated audio file.

[0360] Step 6:

[0361] The server serves the generated story, illustrations, and audio files to the user.

[0362] The server provides the generated stories, illustrations, and audio files to the users, who can then view and enjoy these contents through their terminals.

[0363] Input: Generated story, illustrations, and audio files

[0364] Output: The content provided to the user (story, illustrations, audio files)

[0365] (Application example 3)

[0366] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0367] Conventional story generation systems can generate stories based on settings entered by the user, but they lack the means to enjoy the story visually and aurally. This is also inconvenient for users who have difficulty reading visually or who want to do other tasks while listening to the story. Furthermore, there is no way to automatically generate illustrations suitable for the story, which means that the appeal of the story cannot be fully brought out.

[0368] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0369] In this invention, the server includes a means for allowing a user to input a protagonist and setting and for an AI to generate an original story based on the input, a means for generating original illustrations based on the generated story, a means for converting the generated story into audio and reading it aloud, a means for displaying the generated illustrations and displaying the story as text, and a means for reading the generated story aloud, thereby enabling the user to enjoy the story both visually and aurally.

[0370] A "user" is an entity that uses the system to generate stories, display illustrations, and read aloud.

[0371] The "protagonist" is the character at the center of the story and can be set by the user.

[0372] "Setting" refers to information entered by the user, such as the story's background, characters, and scenario.

[0373] "AI" stands for artificial intelligence, a technology that generates stories, creates illustrations, and translates audio based on information entered by the user.

[0374] An "original story" is a story that is newly generated by AI based on settings entered by the user.

[0375] An "illustration" is a visual image generated based on the content of a story, and visually represents a scene from the story.

[0376] "Speech" is the process of converting a textual narrative into audio.

[0377] "Means for reading aloud" is a function for playing the generated story aloud and letting the user listen.

[0378] "Means of display" refers to the functionality for visually presenting the generated illustrations and narrative text to the user.

[0379] "Means for reading aloud" is a function for playing the generated story aloud and allowing the user to listen.

[0380] A system for implementing this invention includes means for a user to input a main character and setting and for an AI to generate an original story based on the input, means for generating original illustrations based on the generated story, means for converting the generated story into audio and reading it aloud, means for displaying the generated illustrations and displaying the story as text, and means for reading the generated story aloud.

[0381] System Programming

[0382] The system includes the following programs:

[0383] 1. Story generation: The server generates a story using the OpenAI API based on the prompt entered by the user. For example, if the user enters the prompt "Once upon a time in a faraway land...", the AI ​​generates a story based on this prompt.

[0384] 2. Illustration generation: The server analyzes the content of the generated story and calls the OpenAI image generation API to generate appropriate illustrations. For example, it generates an illustration for the scene "A beautiful castle on a hill."

[0385] 3. Text-to-speech: The server uses the pyttsx3 library to convert the generated story from text to speech, so that the story can be read aloud.

[0386] 4. Display and reading: The device displays the generated illustrations, displays the story as text, and reads it aloud.

[0387] Hardware and Software Used

[0388] Hardware: Servers, user devices (smartphones, tablets, etc.)

[0389] Software: OpenAI API, pyttsx3 library, image display library (e.g. PIL)

[0390] Examples

[0391] When the user enters the prompt "Once upon a time in a faraway land...", the server does the following:

[0392] 1. Story generation: Use OpenAI's API to generate a story based on a prompt.

[0393] 2. Illustration generation: Analyze the content of the generated story and generate illustrations for a scene such as "A beautiful castle on a hill."

[0394] 3. Text-to-speech: The generated story is converted into audio using the pyttsx3 library and read to the user.

[0395] 4. Display and read aloud: The generated illustrations are displayed on the user's device, and the story is displayed as text and read aloud.

[0396] Example prompt:

[0397] "Once upon a time in a faraway land, there was a beautiful castle on a hill. The castle was home to a kind king and queen who loved their people dearly..."

[0398] In this way, users can enjoy the story both visually and aurally.

[0399] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0400] Step 1:

[0401] The user enters a prompt at the terminal.

[0402] Input: The prompt text that the user types (e.g., "Once upon a time in a faraway land...")

[0403] Output: The prompt text is sent to the server.

[0404] Step 2:

[0405] The server calls the OpenAI API based on the received prompt text and generates a story.

[0406] Input: Prompt statement

[0407] Data processing: Use the OpenAI API to generate a story based on the prompt.

[0408] Output: Text data of the generated story

[0409] Step 3:

[0410] The server analyzes the text data of the generated story and calls OpenAI's image generation API to generate appropriate illustrations.

[0411] Input: Text data of the generated story

[0412] Data processing: Analyze the content of the story and generate appropriate illustrations using an illustration generation API.

[0413] Output: Image data of the generated illustration

[0414] Step 4:

[0415] The server converts the text data of the generated story into audio data using the pyttsx3 library.

[0416] Input: Text data of the generated story

[0417] Data processing: Convert text data into audio data using the pyttsx3 library.

[0418] Output: Audio data of the generated story

[0419] Step 5:

[0420] The server transmits image data of the generated illustrations, text data of the story, and audio data to the terminal.

[0421] Input: Image data of the generated illustrations, text data of the story, and audio data

[0422] Output: Image data of illustrations, text data of the story, and audio data are sent to the terminal.

[0423] Step 6:

[0424] The terminal displays the received image data of the illustrations, displays the text data of the story, and plays back the audio data.

[0425] Input: Image data of illustrations, text data of the story, audio data

[0426] Specific operations: Display illustrations, display text, and play audio on the device screen.

[0427] Output: The user can enjoy the story visually and aurally.

[0428] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0429] "Example 1"

[0430] In one embodiment of the present invention, the user inputs the protagonist and setting, and the AI ​​generates an original story based on that input. At this time, an emotion engine that recognizes the user's emotions is built in. Specifically, when the user inputs information for story generation, the emotion engine recognizes the user's emotions from the user's facial expressions, tone of voice, input speed, etc.

[0431] "Example 2"

[0432] The AI ​​adjusts the story generation based on the user's emotions as recognized by the emotion engine. For example, if the user expresses happiness, the AI ​​will generate a story with a light theme that reflects that emotion. Conversely, if the user expresses sadness, the AI ​​will generate a story with a dark theme that reflects that emotion.

[0433] "Example 3"

[0434] In addition, the emotion engine adjusts the output format of the generated story based on the user's emotions. For example, if the user is surprised, the AI ​​will audio-read the story with suspenseful music that reflects that emotion. On the other hand, if the user is relaxed, the AI ​​will audio-read the story with calming music that reflects that emotion.

[0435] "Example 4"

[0436] In one embodiment of the present invention, original illustrations are generated based on the AI-generated story. In this case, the color tone and style of the generated illustrations are adjusted based on the user's emotions recognized by the emotion engine. For example, if the user expresses an emotion of joy, the AI ​​generates illustrations in light colors that reflect that emotion. Conversely, if the user expresses an emotion of sadness, the AI ​​generates illustrations in dark colors that reflect that emotion.

[0437] The process flow of each embodiment will be described below.

[0438] "Example 1"

[0439] Step 1: The user enters information about the protagonist, setting, etc. into the system.

[0440] Step 2: The emotion engine recognizes the user's emotions from their facial expressions, tone of voice, typing speed, etc.

[0441] Step 3: The AI ​​generates an original story based on user input and emotional information from the emotion engine.

[0442] "Example 2"

[0443] Step 1: The emotion engine recognizes the user's emotion.

[0444] Step 2: The AI ​​adjusts the story theme based on the emotional information from the emotion engine.

[0445] Step 3: Generate an original story based on the AI-tuned themes.

[0446] "Example 3"

[0447] Step 1: The emotion engine recognizes the user's emotion.

[0448] Step 2: The AI ​​adjusts the narrative output format based on the emotional information from the emotion engine.

[0449] Step 3: Output the story based on the output format adjusted by the AI.

[0450] "Example 4"

[0451] Step 1: Generate original illustrations based on the AI-generated story.

[0452] Step 2: The emotion engine recognizes the user's emotion.

[0453] Step 3: The AI ​​adjusts the color tone and style of the generated illustration based on the emotional information from the emotion engine.

[0454] Example 1

[0455] Next, a description will be given of Example 1 of the embodiment 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".

[0456] Conventional story generation systems only generate stories based on information entered by the user, and have the problem of not being able to generate stories that take into account the user's emotions and input circumstances. In addition, there are cases where the generated stories do not meet the user's expectations, which results in a lack of improvement in the user experience.

[0457] 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.

[0458] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for transmitting the input information to the server, a means for the server to analyze the information received, a means for the server to analyze the user's emotions using an emotion engine, a means for the server to generate a prompt sentence based on the analysis result and transmit it to the generative AI model, a means for the generative AI model to generate an original story based on the prompt sentence, a means for the server to transmit the generated story to the user's terminal, and a means for the user to receive the generated story. This enables story generation that takes into account the user's emotions and input situation, improving the user experience.

[0459] A "user" is a person who uses the system to input the protagonist and setting and generate a story.

[0460] The "protagonist" is the central character of the story entered by the user.

[0461] "Setting" refers to information such as the background, theme, and location of a story.

[0462] A "server" is a computer system that receives and analyzes information sent by a user, and sends prompts to the generative AI model.

[0463] An "emotion engine" is software that analyzes a user's emotions from their facial expressions, tone of voice, typing speed, etc.

[0464] A "generative AI model" is an artificial intelligence model that generates an original story based on a prompt text.

[0465] A "prompt" is text sent to the generative AI model that is generated based on information entered by the user and the results of analysis by the emotion engine.

[0466] A "story" is a story that a generative AI model generates based on a prompt.

[0467] "Terminal" means a device through which a User accesses the system, inputs information, and receives generated stories.

[0468] This invention is a system in which the user inputs the protagonist and setting, and a generative AI model generates an original story based on that input. The system incorporates an emotion engine that analyzes the user's emotions, making it possible to generate a story that takes the user's emotions into account.

[0469] Hardware and Software Used

[0470] Hardware

[0471] Device: The device (e.g. computer, smartphone, tablet) through which the User enters information and receives the generated story.

[0472] Server: A computer system that receives and analyzes information sent by the user and sends prompts to the generative AI model.

[0473] Camera and microphone: Devices used to capture a user's facial expressions and tone of voice.

[0474] software

[0475] Emotion engine: Software that analyzes emotions from a user's facial expressions, tone of voice, typing speed, etc. (e.g. Microsoft® Azure® Emotion API).

[0476] Generative AI model: An artificial intelligence model that generates an original story based on a prompt (e.g., OpenAI's GPT-4).

[0477] Data processing and calculation

[0478] The user enters information

[0479] A user visits a website or application and fills in a form displayed in the interface with information about the protagonist, such as their name, gender, age, likes, dislikes, setting, theme, location, etc. For example, a user might enter "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, enchanted forest."

[0480] The server receives the information

[0481] When the user completes the input and presses the send button, the terminal sends the input information to the server, which receives the information and stores it in a database.

[0482] The server analyzes the user's emotions using an emotion engine.

[0483] The server uses the device's camera and microphone to capture facial expressions, tone of voice, and input speed when the user enters information. This data is then sent to the emotion engine to analyze the user's emotions. For example, if the user is excited, that information is obtained as the analysis result.

[0484] The server sends a prompt to the generative AI model.

[0485] The server generates a prompt based on the information entered by the user and the analysis results of the emotion engine. For example, it generates a prompt like this: "The main character's name is Alice, her gender is female, and her age is 25. Alice loves adventure and hates boredom. The story is set in fantasy, the theme is friendship, and the location is a magical forest. Please generate a story in which Alice meets new friends in the magical forest and goes on an adventure together," and sends it to the generative AI model.

[0486] A generative AI model generates the story.

[0487] The generative AI model generates an original story based on the prompt sent from the server. For example, it generates a story about Alice meeting new friends in a magical forest and going on an adventure together.

[0488] The server transmits the generated story to the user.

[0489] The server receives the story generated by the generative AI model and sends it to the user's device. The server sends the story in an appropriate format (e.g., text format).

[0490] The user receives the story.

[0491] The user can receive the story generated on the device and read the story displayed on the interface. For example, the user reads "A story about Alice meeting new friends in a magical forest and going on adventures together."

[0492] The above is an embodiment of the present invention.

[0493] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0494] Step 1:

[0495] The user enters the information.

[0496] A user accesses a website or application and enters information such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, and location into a form displayed on the interface. The entered information is sent from the terminal to the server. A specific action is when the user enters "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, magical forest."

[0497] Step 2:

[0498] The server receives the information.

[0499] The server receives the information sent by the user and saves it in the database. It checks the consistency of the input data and verifies that it does not contain any invalid data. In concrete terms, the server receives the information "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, magical forest" and saves it in the database.

[0500] Step 3:

[0501] The server analyzes the user's emotions using an emotion engine.

[0502] The server uses the device's camera and microphone to capture the user's facial expressions, tone of voice, and input speed when entering information. This data is then sent to the emotion engine to analyze the user's emotions. Specifically, the server captures the user's facial expressions and voice through the camera and microphone and sends them to the emotion engine. The emotion engine returns the user's excitement state as the analysis result.

[0503] Step 4:

[0504] The server sends a prompt to the generative AI model.

[0505] The server generates a prompt sentence based on the information entered by the user and the analysis results of the emotion engine. The generated prompt sentence is sent to the generative AI model. Specifically, the server generates a prompt sentence that reads, "The main character's name is Alice, her gender is female, and her age is 25. Alice loves adventure and hates boredom. The story is set in fantasy, the theme is friendship, and the location is a magical forest. Please generate a story in which Alice meets new friends in the magical forest and goes on an adventure together." and sends it to the generative AI model.

[0506] Step 5:

[0507] A generative AI model generates the story.

[0508] The generative AI model generates an original story based on the prompt sent from the server. In concrete terms, the generative AI model generates a story in which Alice meets new friends in a magical forest and goes on an adventure together.

[0509] Step 6:

[0510] The server transmits the generated story to the user.

[0511] The server receives the story generated by the generative AI model and transmits it to the user's terminal. The server transmits the story in an appropriate format (e.g., text format). As a specific operation, the server transmits the generated story in text format to the user's terminal.

[0512] Step 7:

[0513] The user receives the story.

[0514] The user can receive the story generated on the terminal and read the story displayed on the interface. In a specific operation, the user reads "a story about Alice meeting new friends in a magical forest and going on an adventure together."

[0515] (Application example 1)

[0516] Next, a description will be given of Application Example 1 of Form 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."

[0517] Conventional story generation systems can generate stories based on user input, but they cannot generate personalized stories that take into account the user's emotions. As a result, they cannot provide stories that correspond to the user's emotions, limiting the user experience. They also lack illustrations and voice reading functions to make the generated stories more appealing.

[0518] 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.

[0519] In this invention, the server includes a means for a user to input a protagonist and setting and an AI to generate an original story based on the input, an emotion recognition means for recognizing emotions from the user's facial expressions, tone of voice, input speed, etc., a means for generating a story based on the emotions recognized by the emotion recognition means, and a means for outputting the generated story. This makes it possible to generate a personalized story according to the user's emotions.

[0520] A "user" is an individual or group that uses the system to generate a story.

[0521] The "protagonist" is a character who is central to the story, and whose information, such as name, gender, and age, is set by the user.

[0522] "Setting" refers to information such as the background, theme, and location of the story, and is selected or entered by the user.

[0523] "AI" stands for artificial intelligence, a technology that generates original stories based on user input.

[0524] A "story" is a story generated by user input and AI, and output in text format.

[0525] "Emotion recognition means" is a technology that recognizes emotions from a user's facial expressions, tone of voice, input speed, etc.

[0526] "Emotion" indicates the user's psychological state and is analyzed by the emotion recognition means.

[0527] "Output means" refers to the means for providing the generated story to the user, including formats such as text display and voice reading.

[0528] "Illustrations" are illustrations generated based on the content of the story and visually complement the story.

[0529] "Speech" is a technology that outputs the generated story as audio, and is a means of reading the story aloud to the user.

[0530] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on the input, emotion recognition means for recognizing emotions from the user's facial expressions, tone of voice, input speed, etc., means for generating a story based on the emotions recognized by the emotion recognition means, and means for outputting the generated story.

[0531] Hardware and Software Used

[0532] Hardware: Smartphone camera, smartphone microphone

[0533] Software: OpenCV (for emotion recognition), SpeechRecognition (for voice recognition), transformers (for generative AI models)

[0534] Data processing and calculation

[0535] 1. Emotion recognition:

[0536] The system analyzes images captured by the smartphone camera using OpenCV and determines the user's emotions using an emotion recognition model. Specifically, the system preprocesses the image data captured by the camera and inputs it into the emotion recognition model to estimate the user's emotions from their facial expressions.

[0537] 2. Voice Recognition:

[0538] Speech captured by a smartphone microphone is converted to text using SpeechRecognition. Specifically, the speech data is preprocessed and input into a speech recognition engine to convert the speech to text data.

[0539] 3. Narrative Generation:

[0540] Using the user's input text and emotions as prompts, the GPT-3 model is used to generate an original story. Specifically, a prompt sentence is generated that combines the user's input and emotion information, and the story is generated by inputting the prompt sentence into the GPT-3 model.

[0541] Examples

[0542] If a user enters, "Please create a story about a brave knight who fights a dragon," and the emotion engine recognizes "excitement," the story it generates will be, "An adventure story about a brave knight who engages in a fierce battle with a dragon."

[0543] Examples of prompt statements

[0544] User Input: Create a story about a brave knight who battles a dragon.

[0545] User Sentiment: Excitement

[0546] story:

[0547] In this way, a more personalized narrative can be generated based on the user's emotions and input.

[0548] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0549] Step 1:

[0550] The user launches the smartphone application and inputs the main character and story settings.

[0551] Input: Text data entered by the user (e.g., the protagonist's name, gender, age, story theme, etc.)

[0552] Output: User input data

[0553] Specific operation: The user enters the required information into the application's input form and presses the submit button.

[0554] Step 2:

[0555] The device captures the user's facial expressions using the smartphone camera and recognizes emotions using OpenCV.

[0556] Input: Image data acquired from the camera

[0557] Output: Recognized emotion data (e.g. excitement, sadness, happiness, etc.)

[0558] Specific operation: The camera takes a picture of the user's face, preprocesses the image data, and inputs it into an emotion recognition model to estimate emotions.

[0559] Step 3:

[0560] The device uses the smartphone's microphone to capture the user's voice and converts it into text using SpeechRecognition.

[0561] Input: Audio data obtained from the microphone

[0562] Output: Text data converted by speech recognition

[0563] Specific operation: The user's voice is recorded using a microphone, the voice data is preprocessed, input into a speech recognition engine, and converted into text data.

[0564] Step 4:

[0565] The server generates a prompt sentence based on the user's input data and the recognized emotion data.

[0566] Input: User input data, recognized emotion data

[0567] Output: Generated prompt statement

[0568] Specific operation: The user's input data and emotion data are combined to create a prompt sentence for narrative generation.

[0569] Step 5:

[0570] The server inputs the generated prompt sentences into the GPT-3 model to generate an original story.

[0571] Input: Generated prompt text

[0572] Output: Generated narrative text

[0573] Specific operations: Input the prompt sentence into the GPT-3 model and obtain the narrative text generated by the model.

[0574] Step 6:

[0575] The terminal displays the generated story text to the user, using a text-to-speech function if necessary.

[0576] Input: Generated narrative text

[0577] Output: Story text displayed to the user, voice reading data

[0578] Specific behavior: The generated story text is displayed on the application screen and the story is played aloud using the text-to-speech function.

[0579] Example 2

[0580] Next, a second embodiment of the second embodiment will be described. 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."

[0581] Conventional story generation systems generate stories without considering the user's emotions, making it difficult to provide a story that matches the user's emotions. In addition, there are limited ways to output the generated story in an easy-to-read format, which reduces user convenience.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0583] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for an emotion recognition engine to recognize the emotion of the user, a means for generating a prompt sentence for the generative AI model based on the user's input information and the recognized emotion, a means for the generative AI model to generate an original story based on the prompt sentence, and a means for outputting the generated story in text or PDF format. This makes it possible to generate a story that matches the emotion of the user and output it in a format that is easy for the user to read.

[0584] A "user" is an individual or organization that uses the system to request the generation of a story.

[0585] The "protagonist" is the character at the center of the story and the main character defined by the user.

[0586] "Setting" refers to detailed information about the story's background, environment, time period, location, etc., and is an element entered by the user.

[0587] An "emotion recognition engine" is software or hardware that analyzes data such as the user's facial expressions and voice to recognize the user's emotions.

[0588] A "generative AI model" is an artificial intelligence algorithm that generates an original story based on an input prompt.

[0589] A "prompt" is text that provides instructions to a generative AI model based on user input and recognized emotions.

[0590] A "narrative" is a piece of text containing a sequence of events and character descriptions generated by a generative AI model.

[0591] A "text format" is a digital format for storing and displaying the generated story as character data.

[0592] "PDF Format" means a digital format for storing and displaying the generated story in Portable Document Format.

[0593] "Output" is the process of providing the generated narrative in a user-accessible form.

[0594] This invention is a system in which a generative AI model generates an original story based on information input by a user and emotions recognized by an emotion recognition engine, and outputs the story in a format that is easy for the user to read. A specific embodiment of this system will be described below.

[0595] Hardware and Software Used

[0596] Hardware: Servers, user devices (PCs, smartphones, etc.)

[0597] Software: Generative AI models (e.g. GPT-4), emotion recognition engines (e.g. Affectiva SDK)

[0598] Program Processing

[0599] 1. Collecting user input information

[0600] A user uses a terminal to input information needed to generate a story, such as details about the story's theme, characters, setting, etc.

[0601] Example: A user opens a web browser and types "I'd like to read medieval fantasy stories" into the system's input form.

[0602] 2. Emotion recognition using emotion engine

[0603] When a user provides input, the emotion recognition engine recognizes the user's emotions from their facial expressions and voice.

[0604] Example: When a user uses the camera and microphone to input, an emotion recognition engine analyzes the user's facial expressions and tone of voice to recognize the emotion "excitement."

[0605] 3. Prompt generation

[0606] The server generates a prompt sentence for the generative AI model based on the user's input information and the emotions recognized by the emotion recognition engine.

[0607] Example: The server generates a prompt saying "Generate a medieval fantasy story. The story should include an exciting adventure" based on the input information "I want to read a medieval fantasy story" and the emotion "excitement."

[0608] 4. Narrative Creation

[0609] The server inputs prompt sentences into the generative AI model and generates a story.

[0610] Example: A server inputs the following prompt to a generative AI model (e.g., GPT-4): "Generate a medieval fantasy story. The story should include an exciting adventure."

[0611] 5. Story output

[0612] The generated story is output in a user-friendly format.

[0613] Example: A server generates a generated story in text and / or PDF format and provides a link for the user to download it.

[0614] Examples

[0615] User input: "I want to read a medieval fantasy story."

[0616] Emotion recognition engine recognition result: "Excited"

[0617] Prompt for generative AI model: "Generate a medieval fantasy story that contains exciting adventures."

[0618] When this prompt is fed into a generative AI model, the model generates a story like this:

[0619] A snippet from the generated story: "In a medieval kingdom, a young knight embarks on an adventure to slay a dragon. He overcomes many challenges and ultimately becomes the hero who saves the kingdom."

[0620] Users can download and read the story in text or PDF format.

[0621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] The user uses the terminal to input the information needed to generate the story.

[0624] Specifically, a user opens a web browser and fills in the system's input form with details about the story's theme, characters, setting, etc.

[0625] Input: Details of the story, such as theme, characters, setting, etc.

[0626] Output: User input is sent to the server

[0627] Step 2:

[0628] When a user provides input, the emotion recognition engine recognizes the user's emotions from their facial expressions and voice.

[0629] Specifically, when a user makes input using the camera and microphone, the emotion recognition engine analyzes the user's facial expressions and tone of voice.

[0630] Input: User's facial expression data, voice data

[0631] Output: The recognized emotion data is sent to the server.

[0632] Step 3:

[0633] The server generates a prompt sentence for the generative AI model based on the user's input information and the emotions recognized by the emotion recognition engine.

[0634] Specifically, the server generates a prompt sentence saying, "Please generate a medieval fantasy story. The story should include an exciting adventure," based on the input information "I want to read a medieval fantasy story" and the emotion "excitement."

[0635] Input: User input information, recognized emotion data

[0636] Output: Generated prompt statement

[0637] Step 4:

[0638] The server inputs prompt sentences into the generative AI model and generates a story.

[0639] Specifically, the server inputs a prompt to the generative AI model (e.g., GPT-4): "Generate a medieval fantasy story. The story should include an exciting adventure."

[0640] Input: Generated prompt text

[0641] Output: The generated story

[0642] Step 5:

[0643] The generated story is output in a user-friendly format.

[0644] Specifically, the server generates the generated story in text or PDF format and provides a link for the user to download it.

[0645] Input: A generated story

[0646] Output: Story file in text and PDF format, download link

[0647] (Application example 2)

[0648] Next, a description will be given of Application Example 2 of Form 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."

[0649] Conventional story generation systems were unable to generate stories that reflected the user's emotions, making it difficult to provide a story experience that corresponded to the user's emotions. In addition, there was a lack of means to save the generated stories in various formats, which resulted in low user convenience.

[0650] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0651] In this invention, the server includes a means for a user to input a protagonist and a setting and an AI to generate an original story based on the input, a means for outputting the generated story, a means for an emotion recognition engine to recognize the user's emotion and adjust the tone and theme of the story based on the emotion, and a means for saving the generated story in text or PDF format. This makes it possible to provide a story experience according to the user's emotion and to save the generated story in a variety of formats.

[0652] A "user" is an individual or group that uses the system to generate a story.

[0653] The "protagonist" is the character at the center of the story and can be set by the user.

[0654] "Setting" refers to detailed information about the story, such as the background, situation, and characters, which can be entered by the user.

[0655] "AI" stands for artificial intelligence, a technology that generates original stories based on user input.

[0656] A "narrative" is a piece of text that contains a series of events or episodes generated by AI.

[0657] "Output" refers to providing the generated narrative in a form that can be viewed by a user.

[0658] An "emotion recognition engine" is a technology that recognizes the user's emotions in real time and adjusts the tone and theme of the story based on that information.

[0659] "Tone" refers to the overall mood or emotional tone of a story.

[0660] A "theme" is the central subject or message of a story.

[0661] "Text format" is a data format in which data is saved as character information.

[0662] "PDF format" is an abbreviation for Portable Document Format, and is a standard file format for electronically storing documents.

[0663] "Saving" refers to keeping the generated story as data so that it can be viewed at a later date.

[0664] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on that input, means for outputting the generated story, means for an emotion recognition engine to recognize the user's emotions and adjust the tone and theme of the story based on the emotions, and means for saving the generated story in text or PDF format.

[0665] System Configuration

[0666] The system uses the following hardware and software:

[0667] Hardware: Smartphones, servers

[0668] Software: Python, OpenAI API, pdfkit, EmotionRecognizer

[0669] Program processing explanation

[0670] The server uses OpenAI's generative AI model to generate a story based on the protagonist and setting entered by the user. As the user enters the input via their smartphone, the data is sent to the server. The server uses an emotion recognition engine (EmotionRecognizer) to recognize the user's emotions in real time and adjusts the tone and theme of the story based on the emotional information.

[0671] The generated stories are saved in text or PDF format and made available for download by users. Specifically, the generated stories are converted to PDF format using pdfkit and saved on the server.

[0672] Examples

[0673] For example, if the user inputs the theme "adventure" and the emotion recognition engine recognizes "joy," the server will send the following prompt to the generative AI model:

[0674] User Sentiment: Delight

[0675] User Input: Adventure

[0676] Generate a story.

[0677] Based on this prompt, the generative AI model generates a light-hearted and fun adventure story, which is then converted to PDF format using pdfkit and saved on the server for users to download.

[0678] In this way, a system is realized that generates original stories based on the user's emotions and input, and allows users to save and view the stories in a variety of formats.

[0679] The flow of the identification process in the application example 2 will be described with reference to FIG.

[0680] Step 1:

[0681] Users use their smartphones to input the theme and keywords of the story.

[0682] Input: Themes or keywords entered by the user (e.g. "adventure")

[0683] Output: User input data

[0684] Specific actions: The user opens the smartphone application, enters information into text boxes for the story's theme and keywords, and presses the send button.

[0685] Step 2:

[0686] The server receives the user's input data and recognizes the user's emotions in real time using an emotion recognition engine.

[0687] Input: User input data

[0688] Output: User emotion data (e.g. "happy")

[0689] Specific operation: The server receives the user's input data, analyzes the user's emotions using EmotionRecognizer, and generates emotion data.

[0690] Step 3:

[0691] The server generates a prompt sentence based on the user's input data and emotion data and sends it to the generative AI model.

[0692] Input: User input data, user emotion data

[0693] Output: Prompt text (e.g. "User emotion: Joy\nUser input: Adventure\nGenerate a story.")

[0694] Specific operation: The server combines the user's input data and emotion data to generate a prompt sentence and sends it to OpenAI's generative AI model.

[0695] Step 4:

[0696] The generative AI model generates an original story based on the prompt and sends it back to the server.

[0697] Input: Prompt statement

[0698] Output: A generated story (e.g. "One day, a joyous adventure began...")

[0699] Specific operation: The generative AI model analyzes the prompt sentence, generates an appropriate story and sends it back to the server.

[0700] Step 5:

[0701] The server stores the generated stories in text and PDF formats and makes them available for users to download.

[0702] Input: A generated story

[0703] Output: Story file in text and PDF format

[0704] Specific behavior: The server converts the generated story to PDF format using pdfkit and saves it on the server. The user can download the story file by clicking the download link.

[0705] Step 6:

[0706] Users can download and view the generated stories.

[0707] Input: Story file in text or PDF format

[0708] Output: The story the user sees

[0709] Specific operations: The user clicks on the download link via the smartphone application, downloads the generated story, and views it.

[0710] Example 3

[0711] Next, a third embodiment of the third embodiment will be described. 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."

[0712] Conventional story generation systems can generate stories based on prompts entered by users, but they lack the means to enjoy the story visually and aurally. They also lack the ability to adjust the story output format according to the user's emotions. This limits the user experience and reduces the immersiveness of the story.

[0713] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0714] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for analyzing the generated story and generating illustrations corresponding to appropriate scenes, a means for recognizing the user's emotions using an emotion engine and adjusting the color tone and style of the generated illustrations, a means for converting the generated story from text to audio and adding background music based on the user's emotions, and a means for outputting the generated story, illustrations, and audio to the user. This allows the user to enjoy the story visually and audibly, and furthermore, the output format of the story is adjusted according to the user's emotions, enabling a more immersive experience.

[0715] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on prompts entered by the user.

[0716] A "prompt" is text that a user enters to direct the generation of a story.

[0717] "Illustrations" are images generated to visually represent the content of a story.

[0718] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's output based on those emotions.

[0719] "Tone" is an element that refers to the brightness and saturation of the colors in an illustration.

[0720] "Style" is an element that refers to the characteristics of the illustration's design and art.

[0721] "Text-to-speech" is a technique for converting text data into speech data.

[0722] "Background music" is music that is played in conjunction with the audio output of the story.

[0723] "User emotion" refers to the emotional state exhibited by the user, such as happiness, surprise, relaxation, etc.

[0724] "Output format" is the form in which the content is presented to the user, such as narrative, illustrations, audio, etc.

[0725] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0726] The present invention is a system that generates a story based on a prompt sentence input by a user, and allows the user to enjoy the story visually and aurally. A specific embodiment of the system will be described below.

[0727] System Configuration

[0728] Hardware and Software Configuration

[0729] 1. Server

[0730] Generative AI models are used to generate narratives, specifically using natural language generation models such as OpenAI's GPT-4.

[0731] Image generation AI: Used to generate illustrations. Specifically, it uses image generation models such as DALL-E.

[0732] Emotion Engine: Used to recognize the user's emotions. Specifically, it uses Affectiva's emotion recognition technology.

[0733] Text-to-speech technology: Used to convert the story into audio, specifically using technologies such as Google Text-to-Speech.

[0734] 2. Terminal

[0735] Provides an interface for the user to enter a prompt.

[0736] Displays and plays stories, illustrations, and audio sent from the server.

[0737] System Operation

[0738] User Actions

[0739] The user types a story prompt into an input field on the device, for example, "A story about a boy who one day encounters a mysterious creature in the woods."

[0740] Server Processing

[0741] 1. Narrative Creation

[0742] The server receives the prompt text entered by the user and inputs it into the generative AI model. The generative AI model generates a story based on the prompt text. For example, it generates a story like, "One day, the boy met a mysterious creature in the forest. The creature could talk and told the boy the secret of the forest."

[0743] 2. Illustration Generation

[0744] The server analyzes the generated story and identifies important scenes. It then uses image generation AI to generate illustrations that correspond to the identified scenes. For example, it generates an illustration of a scene where a boy encounters a mysterious creature.

[0745] 3. Emotion Recognition

[0746] The server uses an emotion engine to recognize emotions from the user's facial expressions and voice, for example, to determine whether the user is expressing an emotion of joy.

[0747] 4. Adjusting illustrations

[0748] The server adjusts the color tone and style of the generated illustration based on the user's recognized emotion, for example generating a bright-colored illustration if the user is expressing an emotion of joy.

[0749] 5. Audio version of the story

[0750] The server uses text-to-speech technology to convert the generated story into audio. For example, it will convert a story like this: "One day, a boy met a mysterious creature in the forest. The creature could speak and told the boy the secrets of the forest."

[0751] 6. Add background music

[0752] The server adds appropriate background music to the spoken story based on the recognized user emotion, for example, if the user shows a relaxed emotion, it adds calm music in the background.

[0753] Display of terminal

[0754] The device displays and plays the received story, illustrations, and audio to the user, allowing the user to enjoy the story both visually and aurally.

[0755] In this way, a system is realized that allows the user to enjoy a consistent experience from the creation of a story to the visual and audio experience. The flow of the specific process in the third embodiment will be described with reference to FIG.

[0756] Step 1:

[0757] The user enters a prompt sentence.

[0758] Input: The user types a story prompt into the device's input field, for example, "A story about a boy who one day encounters a mysterious creature in the woods."

[0759] Output: The prompt text entered is sent to the server.

[0760] Step 2:

[0761] The server generates a story using a generative AI model.

[0762] Input: The server receives the prompt sent by the user.

[0763] Data processing: The server inputs prompt text into a generative AI model (e.g., GPT-4) to generate a story.

[0764] Output: The generated story is stored in the server. For example, a story like "One day, the boy met a mysterious creature in the forest. The creature could talk and told the boy the secret of the forest."

[0765] Step 3:

[0766] The server analyzes the generated story and generates illustrations.

[0767] Input: The server receives the generated story.

[0768] Data processing: The server analyzes the story and identifies important scenes. Then, it uses an image generation AI (e.g., DALL-E) to generate illustrations that correspond to the identified scenes.

[0769] Output: The generated illustrations are stored in the server. For example, an illustration of a scene where a boy encounters a mysterious creature is generated.

[0770] Step 4:

[0771] The server recognizes the user's emotions using an emotion engine.

[0772] Input: The server receives the user's facial and voice data.

[0773] Data processing: The server uses an emotion engine (e.g., Affectiva's emotion recognition technology) to analyze the user's emotions.

[0774] Output: The user's emotional state is recognized, e.g., the user is recognized to be exhibiting the emotion of happiness.

[0775] Step 5:

[0776] The server adjusts the color tone and style of the illustration based on the user's emotions.

[0777] Input: The server receives the recognized emotional state of the user and the generated illustration.

[0778] Data processing: The server adjusts the color tone and style of the illustration based on the user's emotion. For example, if the user expresses happiness, the server adjusts the color tone of the illustration to a brighter color.

[0779] Output: The adjusted illustrations are kept on the server.

[0780] Step 6:

[0781] The server vocalizes the generated story.

[0782] Input: The server receives the generated story.

[0783] Data processing: The server converts the story into audio using text-to-speech technology (e.g., Google Text-to-Speech).

[0784] Output: The voiced story is stored in the server. For example, a story like "One day, a boy met a mysterious creature in the forest. The creature could talk and told the boy the secret of the forest." is voiced.

[0785] Step 7:

[0786] The server adds background music to the voiced story based on the user's emotions.

[0787] Input: The server receives the recognized emotional state of the user and the spoken narrative.

[0788] Data processing: The server selects appropriate background music based on the user's emotion and adds it to the spoken story. For example, if the user is showing a relaxed emotion, a calm music will be added to the background.

[0789] Output: The audio version of the story with added background music is kept on the server.

[0790] Step 8:

[0791] The server transmits the final story, illustrations, and audio to the device.

[0792] Input: The server receives a voiced story with adjusted illustrations and background music.

[0793] Data processing: The server puts these data together into a single package.

[0794] Output: The final story, illustrations and audio are sent to the device.

[0795] Step 9:

[0796] The device displays and plays the story, illustrations and audio to the user.

[0797] Input: The device receives the final story, illustrations, and audio sent by the server.

[0798] Data processing: The device properly displays and plays back this data.

[0799] Output: The user can enjoy the story both visually and aurally.

[0800] (Application example 3)

[0801] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0802] Conventional story generation systems have difficulty adjusting the output format according to the user's emotions and providing visual and auditory enjoyment. In addition, the system lacks the ability to generate illustrations based on the content of the story and adjust the voice output based on emotions, limiting the user experience. This is inconvenient for users who have difficulty reading visually or who want to do other tasks while listening to a story.

[0803] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0804] In this invention, the server includes a means for a user to input a protagonist and a setting, and an AI to generate an original story based on the input, a means for outputting the generated story, a means for an emotion engine to recognize the user's emotion and adjust the output format of the story based on the emotion, a means for converting the generated story from text to audio and reading it aloud, and a means for generating original illustrations based on the generated story and adjusting the color tone and style of the illustrations based on the user's emotion. This enables visual and audio output of the story according to the user's emotion, and makes it possible to provide a system that is convenient for users who have difficulty reading visually and users who want to do other tasks while listening to the story.

[0805] A "user" is an individual or organization that uses the system to generate and output stories.

[0806] The "protagonist" is the character at the center of the story and can be set by the user.

[0807] "Setting" refers to the background of the story and details of the scenario, and is information entered by the user.

[0808] "AI" stands for artificial intelligence, a technology that generates stories based on user input.

[0809] A "narrative" is a piece of text that contains a series of events or episodes generated by AI.

[0810] "Output" is the act of providing the generated story and illustrations to the user.

[0811] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's output based on those emotions.

[0812] "Illustrations" are visual images or illustrations generated based on the content of the story.

[0813] "Color tone" refers to the brightness and vividness of the colors in an illustration, and is adjusted according to the user's emotions.

[0814] "Style" refers to the design and expression of the illustrations, and is adjusted according to the user's emotions.

[0815] "Speech" is the process of converting text into speech.

[0816] "Reading aloud" is the act of conveying the generated story to the user through audio.

[0817] "Speed" refers to the speed at which the audio version of the story is read out, and is adjusted according to the user's emotions.

[0818] "Music" refers to the background music played when the story is being spoken, and is selected based on the user's emotions.

[0819] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on that input, means for outputting the generated story, means for an emotion engine to recognize the user's emotions and adjust the output format of the story based on the emotions, means for converting the generated story from text to speech and reading it aloud, and means for generating original illustrations based on the generated story and adjusting the color tone and style of the illustrations based on the user's emotions.

[0820] System Configuration

[0821] 1. User Input:

[0822] The user inputs the protagonist and setting using a device such as a smartphone or a head-mounted display, for example by entering a prompt sentence such as "Once upon a time in a faraway land...".

[0823] 2. Narrative Generation:

[0824] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate a story based on the prompts entered by the user, and the story is stored in text format on the server.

[0825] 3. Emotion recognition:

[0826] The user's emotions are recognized using an emotion engine (e.g., emotion_recognition library), which analyzes the user's facial expressions and voice to determine emotions, and sends the results to the server.

[0827] 4. Illustration Generation:

[0828] The server generates illustrations based on the content of the generated story. The illustrations are created using PIL (Python Imaging Library) and their color tone and style are adjusted based on the user's emotion. For example, if the user indicates the emotion "happy," a bright colored illustration is generated.

[0829] 5. Vocalization:

[0830] The server uses the pyttsx3 library to convert the generated story from text to speech, adjusting the speech speed and background music based on the user's emotions. For example, if the user expresses the emotion "happy," a faster, more upbeat music will play.

[0831] Examples

[0832] When a user enters the prompt phrase "Once upon a time in a faraway land...", the server uses a generative AI model to generate a story. If the emotion engine recognizes the user's emotion as "happy", the generated illustrations are adjusted to brighter tones and the voice is set to a faster speed. Users can enjoy the story visually and aurally through their smartphone or head-mounted display.

[0833] This system makes it possible to output a story visually and aurally according to the user's emotions, providing a convenient system for users who have difficulty reading visually or who wish to perform other tasks while listening to a story.

[0834] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0835] Step 1:

[0836] The user uses a terminal to input the main character and setting. The input prompt (e.g., "Once upon a time in a faraway land...") is sent from the terminal to the server. The input data is in text format, and the server receives it.

[0837] Step 2:

[0838] The server generates a story using a generative AI model (e.g., OpenAI's GPT-3) based on the received prompt sentence. The generative AI model takes the prompt sentence as input and outputs the text of the story. The generated story is stored on the server.

[0839] Step 3:

[0840] The server uses an emotion engine (e.g., emotion_recognition library) to recognize the user's emotions. The emotion engine receives the user's facial expressions and voice data as input, and outputs the emotion analysis results. The analysis results are sent to the server.

[0841] Step 4:

[0842] The server generates illustrations based on the content of the generated story. It uses PIL (Python Imaging Library) to draw the story text into an image. The color tone and style of the illustration are adjusted based on the user's emotion. For example, if the emotion is "happy," an illustration with a bright color tone is generated. The generated illustrations are stored on the server.

[0843] Step 5:

[0844] The server uses the pyttsx3 library to convert the generated story from text to audio. It takes the story text as input and outputs audio data. Based on the user's emotion, the audio speed and background music are adjusted. For example, if the emotion is "happy," a faster, more upbeat music is played. The generated audio data is stored on the server.

[0845] Step 6:

[0846] The server transmits the generated story, illustrations, and audio data to the terminal. The terminal receives the data and provides it visually and audibly to the user. The user can enjoy the story through the terminal.

[0847] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0848] The data generation model 58 is a so-called generative AI (Artificial Intelligence) model. An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0849] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0850] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0851] [Second embodiment]

[0852] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0853] 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.

[0854] 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 wide area network (WAN) and / or a local area network (LAN).

[0855] 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.

[0856] 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 the voice according to instructions from the processor 46.

[0857] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0858] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0859] Fig. 4 shows an example of 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0864] "Example 1"

[0865] In one embodiment of the present invention, a system is provided that includes an interface through which a user inputs a protagonist and setting. Specifically, the user inputs information such as the protagonist's name, gender, age, likes, dislikes, etc., on a website or application. The user also selects or inputs the setting, theme, location, etc. of the story.

[0866] "Example 2"

[0867] Based on the input information, the AI ​​generates an original story. Based on the information input by the user, the AI ​​creates a story plot and generates a story based on that. The generated story is output in a format that the user can read. Specifically, it is output in text or PDF format, and the user can download and read it.

[0868] "Example 3"

[0869] In addition, a means is provided to generate original illustrations based on the AI-generated story. Specifically, the AI ​​analyzes the content of the story and generates illustrations that correspond to appropriate scenes. The generated illustrations are output together with the story, allowing users to enjoy the story visually.

[0870] "Example 4"

[0871] In addition, a means is provided to convert the AI-generated story into audio and read it aloud. Specifically, the AI ​​converts the generated story from text to audio and outputs it in a format that the user can listen to. This is convenient for users who have difficulty reading visually or who want to do other tasks while listening to the story.

[0872] The process flow of each embodiment will be described below.

[0873] "Example 1"

[0874] Step 1: A user opens a website or application and enters some information about the main character, such as their name, gender, age, likes, and dislikes.

[0875] Step 2: The user selects or inputs the setting, theme, location, etc. of the story.

[0876] "Example 2"

[0877] Step 1: The AI ​​creates a story plot based on information input by the user.

[0878] Step 2: Generate a story based on the plot created by the AI.

[0879] Step 3: The generated story is output in a form that can be read by the user.

[0880] The output is in text or PDF format, which users can download and read.

[0881] "Example 3"

[0882] Step 1: Analyze the content of the AI-generated story.

[0883] Step 2: The AI ​​generates illustrations that correspond to appropriate scenes based on the content of the story.

[0884] Step 3: The generated illustrations are output together with the story, allowing users to enjoy the story visually.

[0885] "Example 4"

[0886] Step 1: The AI ​​converts the generated story from text to audio.

[0887] Step 2: The converted audio is output in a format that the user can hear, which is convenient for users who have visual impairments or who want to continue with other tasks while listening to the story.

[0888] Example 1

[0889] Next, a description will be given of Example 1 of Form 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".

[0890] Conventional story generation systems often fail to fully reflect the user's intentions and detailed settings when generating original stories based on information entered by the user. They also lack a means to quickly and effectively provide the generated stories to users. Furthermore, the lack of a function to generate illustrations and audio based on the generated stories limits the user experience.

[0891] 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.

[0892] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for transmitting the input information to the server, a means for generating a prompt sentence based on the information received by the server, a means for inputting the generated prompt sentence to the generative AI model, a means for returning a story generated by the generative AI model to the server, a means for the server to transmit the generated story to the terminal, and a means for displaying the story received by the terminal to the user. This makes it possible to quickly and effectively generate an original story that reflects the user's detailed settings and provide it to the user.

[0893] A "user" is an individual or group that uses the system to input the protagonist and story settings.

[0894] The "protagonist" is the character at the center of the story, and is the person for whom the user enters information such as name, gender, and age.

[0895] "Setting" refers to information such as the background, theme, and location of the story, and is an element selected or input by the user.

[0896] The "server" is a computer system that receives information sent by a user and inputs prompt sentences into the generative AI model.

[0897] "Terminal" means a device through which a user can input information and display the generated story, including a web browser and dedicated applications.

[0898] A "prompt sentence" is text that is generated based on information entered by the user and is input into a generative AI model.

[0899] A "generative AI model" is an artificial intelligence algorithm that generates a story based on a prompt sentence, using natural language processing technology, for example.

[0900] A "story" is text that a generative AI model generates based on a prompt, and is an original story provided to the user.

[0901] "Illustrations" are illustrations that are drawn based on the generated story and provide a visual complement to the story.

[0902] "Speech" is the process of converting the generated story into audio data for reading aloud.

[0903] This invention is a system in which a user inputs the protagonist and story settings, and a generative AI model generates an original story based on that information and provides it to the user. A specific embodiment of this system will be described below.

[0904] Users input information into a website or application, such as the main character's name, gender, age, likes, dislikes, setting, theme, location, etc. For example, a user might input the following information:

[0905] Main character's name: Taro

[0906] Gender: Male

[0907] Age: 25

[0908] Likes: Adventure

[0909] Dislikes: Boredom

[0910] Story setting: Fantasy

[0911] Theme: Friendship

[0912] Location: Magical Forest

[0913] The device receives the information entered by the user and sends it to the server. To do this, the device uses a web browser or a dedicated application to send data to the server using an HTTP request.

[0914] The server receives the information sent from the device and generates a prompt sentence to input to the generative AI model. Specifically, it generates the following prompt sentence:

[0915] "The main character's name is Taro, a 25-year-old man. He loves adventure and hates boredom. The story is set in a fantasy world, the theme is friendship, and the location is a magical forest."

[0916] The server inputs the generated prompt sentence into a generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. The server sends the prompt sentence using an API request.

[0917] The generative AI model generates a story based on the prompt received from the server and returns the result to the server. An example of the generated story is as follows:

[0918] "Taro is a 25-year-old adventurous young man who hates boredom. One day, he meets new friends in a magical forest and together they embark on a great adventure."

[0919] The server receives the story returned by the generative AI model and sends it to the device. The server sends the data using an HTTP response.

[0920] The device displays the story received from the server to the user, using a web browser or an application UI.

[0921] This system allows users to quickly and effectively generate and enjoy original stories that reflect detailed settings. The user experience can be further improved by adding the functionality to generate illustrations and audio based on the generated stories.

[0922] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0923] Step 1:

[0924] Users input information such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, and location on a website or application. Specifically, they input information such as "Taro, male, 25 years old, adventure, boredom, fantasy, friendship, magical forest" into an input form. The input data is stored on the device in JSON format.

[0925] Step 2:

[0926] The terminal receives the information entered by the user and sends it to the server. Specifically, the terminal uses an HTTP POST request to send the entered JSON data to the server. The input data is sent to the server, and the server receives it.

[0927] Step 3:

[0928] The server receives the information sent from the device and generates a prompt to input to the generative AI model. Specifically, it analyzes the received JSON data and generates a prompt like the following:

[0929] "The main character's name is Taro, a 25-year-old man. He loves adventure and hates boredom. The story is set in a fantasy world, the theme is friendship, and the location is a magical forest."

[0930] The generated prompt sentences are input into a generative AI model.

[0931] Step 4:

[0932] The server inputs the generated prompt sentence into the generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. Specifically, the prompt sentence is sent using an API request. The input data is the prompt sentence, and the output data is the generated story.

[0933] Step 5:

[0934] The generative AI model generates a story based on the prompt received from the server and returns the result to the server. Specifically, the generative AI model generates a story using natural language processing technology and returns the generated text data to the server as an API response. The output data is the generated story.

[0935] Step 6:

[0936] The server receives the story returned from the generative AI model and sends it to the terminal. Specifically, it sends the generated story to the terminal using an HTTP response. The input data is the generated story, and the output data is the story to be sent to the terminal.

[0937] Step 7:

[0938] The terminal displays the story received from the server to the user. Specifically, the story is displayed using a web browser or an application UI. The input data is the story received from the server, and the output data is the story displayed to the user.

[0939] (Application example 1)

[0940] Next, a description will be given of Application Example 1 of Form 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".

[0941] Conventional story generation systems can generate stories based on information entered by the user, but the generated stories may not meet the user's expectations. In addition, the story generation process is a black box, making it difficult for users to understand how the story is generated. Furthermore, there are limited ways to enjoy the generated story visually or aurally, which limits the user experience.

[0942] 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.

[0943] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for outputting the generated story, a means for generating a prompt sentence to be passed to the generative AI model, and a means for displaying the generated story to the user. This allows a high-quality story to be generated based on the information input by the user, and allows the user to enjoy the story visually and aurally.

[0944] A "user" is an individual or group that uses the system to generate a story.

[0945] The "protagonist" is the character at the center of the story, and is the subject for which the user enters information such as name, gender, and age.

[0946] "Setting" refers to information such as the background, theme, and location of a story, and is an element that affects the content of the story when entered by the user.

[0947] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on information entered by the user.

[0948] A "narrative" is a text-based story generated by a generative AI model and constructed based on information input by a user.

[0949] A "prompt sentence" is an input sentence to be passed to a generative AI model, and is generated based on information entered by the user.

[0950] "Output" is the act or means of providing the generated narrative to a user.

[0951] "Display" is the act or means of visually presenting the generated narrative to a user.

[0952] A system for implementing this invention includes a means for a user to input a protagonist and setting and for a generative AI model to generate an original story based on the input, a means for outputting the generated story, a means for generating a prompt sentence to be passed to the generative AI model, and a means for displaying the generated story to the user.

[0953] System Configuration

[0954] The system consists of the following main components:

[0955] 1. User Interface: The interface through which the user inputs the main character and settings. This is implemented as a smartphone application.

[0956] 2. Generative AI model: An artificial intelligence model that generates a story based on information input by the user. Specifically, we use OpenAI's GPT-3.

[0957] 3. Prompt generation module: A module that generates a prompt sentence to be passed to the generative AI model based on the information entered by the user.

[0958] 4. Story display module: A module that visually displays the generated story to the user.

[0959] Program Processing

[0960] The server receives information input by the user through the user interface, such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, location, etc. This information is passed to the prompt generation module, which generates a prompt sentence suitable for the generative AI model.

[0961] The generated prompt sentences are passed to a generative AI model to generate an original story, which is then displayed to the user through a story display module.

[0962] Hardware and Software Used

[0963] Hardware: Smartphone

[0964] Software: Python, OpenAI API

[0965] Examples

[0966] If the user enters the following information:

[0967] Name: Taro

[0968] Gender: Male

[0969] Age: 10

[0970] Likes: Adventure

[0971] Dislikes: Boredom

[0972] Story Setting: Future city

[0973] Theme: Friendship

[0974] Location: Japan

[0975] An example of a prompt that can be generated based on this information is:

[0976] Main character's name: Taro

[0977] Gender: Male

[0978] Age: 10

[0979] Likes: Adventure

[0980] Dislikes: Boredom

[0981] Story Setting: Future city

[0982] Theme: Friendship

[0983] Location: Japan

[0984] Using this information, generate a story like the one below.

[0985] By passing this prompt to a generative AI model, a personalized story is generated for the user, which is then displayed on the smartphone screen for the user to enjoy visually.

[0986] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0987] Step 1:

[0988] The user starts the smartphone application and inputs information about the protagonist and the setting. Specifically, the user inputs information such as the protagonist's name, gender, age, likes and dislikes, story setting, theme, location, etc. through the application's interface. The input information is then sent to the server.

[0989] Input: Main character's name, gender, age, likes, dislikes, story setting, theme, location

[0990] Output: User input data

[0991] Step 2:

[0992] The server passes the received user input data to the prompt generation module. The prompt generation module generates a prompt sentence to be passed to the generative AI model based on the user input data. The prompt sentence is in text format that contains the information entered by the user.

[0993] Input: User-entered data

[0994] Output: Prompt statement

[0995] Step 3:

[0996] The server passes the generated prompt sentence to the generative AI model. The generative AI model generates an original story based on the prompt sentence. OpenAI's GPT-3 is used as the generative AI model.

[0997] Input: Prompt statement

[0998] Output: The generated story

[0999] Step 4:

[1000] The server passes the generated story to a story display module. The story display module displays the generated story on the user's smartphone. The user can visually enjoy the generated story through the screen of the smartphone.

[1001] Input: A generated story

[1002] Output: Story displayed on a smartphone

[1003] Step 5:

[1004] The user can read and enjoy the generated story, and if desired, can change the settings again and generate a new story.

[1005] Input: A story displayed on a smartphone

[1006] Output: User experience and feedback

[1007] Example 2

[1008] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1009] Conventional story generation systems were lacking in the quality and speed of generating original stories based on information entered by the user. In addition, there were limited ways to provide the generated stories in a format that was easy for users to read, resulting in a poor user experience. Furthermore, there was a lack of functionality to add illustrations and audio to the stories, which made it difficult to fully bring out the appeal of the stories.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1011] In this invention, the server includes a means for a user to input a theme, characters, and setting, a means for transmitting the input information to the server, a means for the server to input a prompt sentence to the generative AI model, a means for the generative AI model to generate a plot of the story, a means for the server to generate a detailed story based on the plot, a means for the server to convert the story into a text format or a PDF format, a means for the server to transmit the generated story to the user's terminal, and a means for the user to download and read the story. This makes it possible to quickly generate a high-quality original story based on the information input by the user and provide it in an easy-to-read format. In addition, the inclusion of a function to add illustrations and audio to the story can further enhance the appeal of the story.

[1012] A "user" is an individual or group that uses the system to input information such as theme, characters, and setting in order to generate a story.

[1013] "Theme" refers to the main subject or genre of the story, and is information entered by the user to specify the direction of the story.

[1014] "Characters" refers to characters who appear in a story, and is information that a user inputs to specify characters who play important roles in the story.

[1015] "Setting" refers to the setting or background of a story, and is information that the user inputs to specify the environment and time period of the story.

[1016] A "Terminal" is a device (e.g., PC, smartphone, tablet) that a User uses to access the System and input information.

[1017] "Server" means a computer system for receiving information submitted by a user, generating a story using a generative AI model, and finally providing the story to the user.

[1018] A "generative AI model" is an artificial intelligence model that generates story plots and detailed text based on information entered by the user.

[1019] A "prompt" is a sentence that is input into a generative AI model based on information such as theme, characters, and setting entered by the user.

[1020] A "plot" is a summary of a story's main components (introduction, development, climax, and conclusion) that is generated by a generative AI model.

[1021] The "text format" is a format in which the generated story is saved as textual information and is provided to the user in a manner that is easy to read.

[1022] "PDF Format" refers to a format in which the generated story is saved in Portable Document Format and provided to users for easy reading.

[1023] "Illustrations" are illustrations generated based on the content of the story and are used to enhance the visual appeal of the story.

[1024] "Speech" is the process of converting the generated story into audio data so that the user can enjoy it aurally.

[1025] The "means for reading aloud" is a function for playing the generated story as audio so that the user can listen to the story.

[1026] This invention is a system that generates an original story using a generative AI model based on a user's input of a theme, characters, and setting, and provides the story to the user. A specific embodiment of this system will be described below.

[1027] A user accesses the system using a terminal (e.g., a PC, a smartphone, or a tablet). The user opens a web browser and accesses the system's web page. The user enters information such as theme, characters, and setting into the input form, and clicks the "Generate" button. For example, if a user wants to generate "a story about a hero slaying a dragon in a fantasy world," the user enters "fantasy" as the theme, "hero, dragon, wizard" as the characters, and "medieval kingdom" as the setting.

[1028] The terminal sends the information entered by the user in JSON format to the server. The server generates a prompt sentence based on the received information and inputs it into a generative AI model (for example, OpenAI's GPT-4). The prompt sentence is in a format that includes an outline of the story and the setting. For example, the following prompt sentence is generated:

[1029] Theme: Fantasy

[1030] Characters: Hero, Dragon, Wizard

[1031] Setting: Medieval Kingdom

[1032] Summary of the story: A hero sets out on a journey to defeat a dragon. Along the way, he meets a wizard and together they defeat the dragon.

[1033] The generative AI model analyzes the prompt sentence and generates a story plot. The plot includes the main components of a story (introduction, development, climax, and conclusion). For example, the following plot is generated:

[1034] 1. The hero learns of the threat of the dragon.

[1035] 2. The hero decides to go on a journey.

[1036] 3. Along the way, you meet a wizard and get his help.

[1037] 4. A hero and a wizard face off against a dragon.

[1038] 5. The dragon is defeated and peace returns to the kingdom.

[1039] The server generates a detailed story based on the generated plot. The generative AI model converts the plot into detailed sentences and completes the entire story. For example, the following story is generated.

[1040] Once upon a time, there lived a hero in a medieval kingdom. One day, a dragon appeared in the kingdom and terrorized the people. The hero set out on a journey to defeat the dragon. Along the way, he met a wizard, and together they succeeded in defeating the dragon. Peace returned to the kingdom, and the hero was celebrated as a hero.

[1041] The server converts the generated story into a format that is easy for the user to read, such as text or PDF. For example, a Python library is used to generate the PDF file.

[1042] The server sends the converted story to the user's device. The user receives an email with a download link or sees a download link on a web page. The user can click the download link to download and read the story. The user can open the downloaded file and enjoy the story. For example, open the PDF file using a PDF reader.

[1043] The system allows users to quickly generate high-quality original stories based on the information they input, delivered in an easy-to-read format, and includes the ability to add illustrations and audio to the stories to enhance their appeal.

[1044] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1045] Step 1:

[1046] The user inputs the theme, characters, and setting.

[1047] A user uses a terminal to access the system's web page and inputs information such as theme, characters, and setting into an input form. For example, the user inputs the theme "fantasy," the characters "heroes, dragons, and wizards," and the setting "medieval kingdom." The input information becomes the basis of prompt sentences for generating a story.

[1048] Step 2:

[1049] The terminal transmits the input information to the server.

[1050] The terminal sends the information entered by the user to the server in JSON format. Specifically, the data in the input form is converted to JSON format and sent to the server using an HTTP request. The server analyzes the received data and uses it to generate a prompt text.

[1051] Step 3:

[1052] The server inputs a prompt sentence into the generative AI model.

[1053] The server generates a prompt based on the received information. For example, it generates the following prompt:

[1054] Theme: Fantasy

[1055] Characters: Hero, Dragon, Wizard

[1056] Setting: Medieval Kingdom

[1057] Summary of the story: A hero sets out on a journey to defeat a dragon. Along the way, he meets a wizard and together they defeat the dragon.

[1058] The generated prompt sentences are input into a generative AI model.

[1059] Step 4:

[1060] A generative AI model generates the story plot.

[1061] The generative AI model analyzes the input prompt sentence and generates a story plot. The plot includes the main components of a story (introduction, development, climax, and conclusion). For example, the following plot is generated:

[1062] 1. The hero learns of the threat of the dragon.

[1063] 2. The hero decides to go on a journey.

[1064] 3. Along the way, you meet a wizard and get his help.

[1065] 4. A hero and a wizard face off against a dragon.

[1066] 5. The dragon is defeated and peace returns to the kingdom.

[1067] The generated plot is returned to the server.

[1068] Step 5:

[1069] The server generates a detailed story based on the plot.

[1070] The server generates a detailed story based on the generated plot. The generative AI model converts the plot into detailed sentences and completes the entire story. For example, the following story is generated.

[1071] Once upon a time, there lived a hero in a medieval kingdom. One day, a dragon appeared in the kingdom and terrorized the people. The hero set out on a journey to defeat the dragon. Along the way, he met a wizard, and together they succeeded in defeating the dragon. Peace returned to the kingdom, and the hero was celebrated as a hero.

[1072] The generated stories are stored on a server.

[1073] Step 6:

[1074] The server converts the stories into text or PDF format.

[1075] The server converts the generated story into a format that is easy for users to read, such as text or PDF. For example, a Python library is used to generate PDF files. The converted files are then stored on the server.

[1076] Step 7:

[1077] The server transmits the generated story to the terminal.

[1078] The server sends the converted story to the user's device. The user receives an email containing a download link or sees a download link on a web page. The user clicks on the download link to download the story.

[1079] Step 8:

[1080] The user downloads and reads the story.

[1081] The user can use the device to download and read the story. The user can then open the downloaded file and enjoy the story, for example by opening the PDF file using a PDF reader.

[1082] (Application example 2)

[1083] Next, a description will be given of Application Example 2 of Form 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".

[1084] Conventional story generation systems can generate stories based on information entered by the user, but they lack the functionality to output and save the generated stories in a variety of formats. They also lack illustrations to enjoy the generated stories visually, and audio functions to enjoy them audibly. This limits the user's experience and restricts the way the story can be enjoyed.

[1085] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for a user to input a protagonist and a setting, and an AI to generate an original story based on the input, a means for outputting the generated story in a text format or a PDF format, and a means for saving the generated story. This allows the user to output and save the generated story in various formats. In addition, by further including a means for generating original illustrations based on the story generated by the AI, the story can be enjoyed visually. In addition, by further including a means for converting the story generated by the AI ​​into audio and reading it aloud, the story can be enjoyed auditorily.

[1086] A "user" is an individual or organization that uses the system to request the generation of a story.

[1087] The "protagonist" is the central character of the story and is part of the information entered by the user.

[1088] "Setting" refers to information such as the background of the story, the environment, time period, and location in which the story takes place, and is part of the information entered by the user.

[1089] "AI" stands for artificial intelligence, a technology that generates stories based on information entered by the user.

[1090] A "story" is an AI-generated text that contains a sequence of events and character actions.

[1091] A "text format" is a digital document format that is composed only of text information.

[1092] "PDF format" is an abbreviation for Portable Document Format, and is a standard file format for electronically storing documents.

[1093] "Output" refers to providing the generated narrative in a form viewable by a user.

[1094] "Preservation" refers to recording the generated stories in a digital format so that they can be reused at a later time.

[1095] "Illustrations" are illustrations or images that visually complement the content of the story.

[1096] "Speech" refers to the conversion of a textual narrative into audio data.

[1097] "Storytelling" refers to playing an audio version of a story to the user.

[1098] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on the input, means for outputting the generated story in text or PDF format, and means for saving the generated story.

[1099] System Configuration

[1100] The system uses the following hardware and software:

[1101] Hardware:

[1102] Smartphone

[1103] software:

[1104] Python

[1105] OpenAI API

[1106] FPDF Library

[1107] Processing flow

[1108] 1. Getting user input:

[1109] Through a smartphone application, users input information about the story, such as the theme, characters, and setting, which allows the system to generate a story according to the user's wishes.

[1110] 2. Generate prompt:

[1111] The server generates a prompt based on the information entered by the user, which contains instructions for the generative AI model to generate a story.

[1112] Example prompt:

[1113] Theme: Adventure

[1114] Characters: Hero, Wizard

[1115] Setting: Medieval fantasy world

[1116] Generate a story based on this information.

[1117] 3. Narrative generation:

[1118] The server uses OpenAI's API to input a prompt sentence into a generative AI model (e.g., GPT-3) to generate a story. The generated story is obtained in text format.

[1119] 4. Output and save the story:

[1120] The server outputs the generated stories in text and PDF formats for users to download, and also allows users to save the generated stories for later reuse.

[1121] Examples

[1122] If the user inputs an "adventure" theme, characters that are a "hero" and a "wizard," and a medieval fantasy world as the setting, the following prompt text will be generated:

[1123] Example prompt:

[1124] Theme: Adventure

[1125] Characters: Hero, Wizard

[1126] Setting: Medieval fantasy world

[1127] Generate a story based on this information.

[1128] By inputting this prompt into a generative AI model, an original adventure story is generated. The generated story is saved in PDF format and users can download it to read.

[1129] In this way, users can easily create original stories that fit their own desires and enjoy them in a variety of formats.

[1130] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1131] Step 1:

[1132] A user starts the smartphone application and inputs information such as the theme, characters, and setting of the story. The input information is sent to the server. The input data includes the theme (e.g., adventure), characters (e.g., hero, wizard), and setting (e.g., a medieval fantasy world).

[1133] Step 2:

[1134] The server receives the input data sent by the user and generates a prompt sentence. Specifically, it creates the following prompt sentence based on the input data.

[1135] Theme: Adventure

[1136] Characters: Hero, Wizard

[1137] Setting: Medieval fantasy world

[1138] Generate a story based on this information.

[1139] The generated prompt text is used in the next step.

[1140] Step 3:

[1141] The server sends the generated prompt sentence to the OpenAI API and generates a story using a generative AI model (e.g. GPT-3). The generative AI model takes the prompt sentence as input and outputs the text of the story. The output story is stored on the server.

[1142] Step 4:

[1143] The server outputs the generated stories in text and PDF formats. Specifically, it converts the stories into PDF format using the FPDF library. The converted PDF files are stored on the server for users to download.

[1144] Step 5:

[1145] Users download and view the stories generated through a smartphone application. Users can choose to download stories in text or PDF format. Downloaded stories are stored on the user's device and can be viewed at any time.

[1146] In this way, users can easily create original stories that fit their own desires and enjoy them in a variety of formats.

[1147] Example 3

[1148] Next, a third embodiment of the third embodiment will be described. 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".

[1149] Conventional story generation systems only generate stories based on settings entered by the user, making it difficult to provide visual and auditory enjoyment. In addition, they do not adequately address users who have difficulty reading visually or who want to do other tasks while listening to a story. This limits the user's experience and restricts how they can enjoy a story.

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

[1151] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for analyzing the generated story, a means for generating illustrations based on the analysis results, a means for converting the generated story into audio, and a means for outputting the generated story, illustrations, and audio files, thereby enabling the user to enjoy the story both visually and aurally.

[1152] A "user" is an entity that uses the system to generate and output a story.

[1153] "Protagonist and setting" refers to details of the characters and scenario that the user enters as information necessary to generate the story.

[1154] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on information entered by the user.

[1155] A "narrative" is a story in text form generated by a generative AI model.

[1156] "Means of analysis" refers to the process of analyzing the content of the generated story and extracting important scenes and events.

[1157] An "illustration" is an image created to visually represent a particular scene or event in the story.

[1158] A "convert-to-speech means" is a process that converts the generated narrative text into audio data.

[1159] "Output means" is the process that provides the generated story, illustrations, and audio files to the user.

[1160] This invention is a system in which a generative AI model generates an original story based on a prompt sentence entered by a user, analyzes the story to generate illustrations, and converts the story into audio for output. A specific embodiment of this system will be described below.

[1161] First, the user accesses the system interface using a terminal (e.g., a PC or a smartphone). The user inputs a prompt that indicates the theme and setting of the story. For example, the user might input "Adventure in the Magical Forest."

[1162] Next, the server receives the prompt sentence entered by the user and passes it to a generative AI model (e.g., GPT-4). The generative AI model generates a story based on the prompt sentence. The generated story is saved in text format on the server.

[1163] The server then analyzes the content of the generated story, specifically extracting scenes and important events from the story, and uses the results of this analysis for subsequent illustration generation and audio generation.

[1164] Next, the server generates illustrations using an image generation AI model (e.g., DALL-E) based on the results of the story analysis. Illustrations corresponding to each scene are generated and stored together with the story text.

[1165] The server then converts the generated story into audio using text-to-speech software (e.g., Google Text-to-Speech API), and the generated audio file is saved in a format that can be heard by the user.

[1166] Finally, the server provides the generated stories, illustrations, and audio files to the user, who can then view and enjoy these contents through their terminals.

[1167] As a concrete example, if the user enters the prompt "Adventure in the magical forest", the server will perform the following process:

[1168] 1. The server generates a story based on "Adventure in the Magical Forest" using a generative AI model (GPT-4).

[1169] 2. The server analyzes the content of the generated story and uses DALL-E to generate illustrations corresponding to each scene in the story.

[1170] 3. The server converts the story into audio using the Google Text-to-Speech API.

[1171] 4. The server provides the generated story, illustrations and audio files to the user.

[1172] This allows the user to enjoy the story both visually and aurally. The flow of the specific process in the third embodiment will be described with reference to FIG.

[1173] Step 1:

[1174] The user enters a prompt.

[1175] A user uses a terminal to access the system's interface and inputs a prompt that indicates the theme and setting of the story, for example, "An adventure in a magical forest." The input prompt is then sent to the server.

[1176] Input: The prompt text entered by the user.

[1177] Output: The prompt text sent to the server.

[1178] Step 2:

[1179] The server generates the story using a generative AI model

[1180] The server receives the prompt sentence entered by the user and passes it to a generative AI model (e.g., GPT-4). The generative AI model generates a story based on the prompt sentence. The generated story is saved in text format on the server.

[1181] Input: Prompt statement

[1182] Output: Generated story (in text format)

[1183] Step 3:

[1184] The server parses the generated story

[1185] The server analyzes the generated story content, specifically extracting scenes and important events from the story using natural language processing (NLP) algorithms, and the analysis results are used for subsequent illustration generation and audio generation.

[1186] Input: Generated story (in text format)

[1187] Output: Story analysis results (extraction of scenes and events)

[1188] Step 4:

[1189] The server generates the illustrations.

[1190] The server generates illustrations using an image generation AI model (e.g., DALL-E) based on the results of the story analysis. Illustrations corresponding to each scene are generated and stored together with the story text.

[1191] Input: Story analysis results

[1192] Output: The generated illustration

[1193] Step 5:

[1194] The server converts the story into audio.

[1195] The server converts the generated story into audio using text-to-speech software (e.g., Google Text-to-Speech API), and the generated audio file is saved in a format that can be heard by the user.

[1196] Input: Generated story (in text format)

[1197] Output: The generated audio file.

[1198] Step 6:

[1199] The server serves the generated story, illustrations, and audio files to the user.

[1200] The server provides the generated stories, illustrations, and audio files to the users, who can then view and enjoy these contents through their terminals.

[1201] Input: Generated story, illustrations, and audio files

[1202] Output: The content provided to the user (story, illustrations, audio files)

[1203] (Application example 3)

[1204] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1205] Conventional story generation systems can generate stories based on settings entered by the user, but they lack the means to enjoy the story visually and aurally. This is also inconvenient for users who have difficulty reading visually or who want to do other tasks while listening to the story. Furthermore, there is no way to automatically generate illustrations suitable for the story, which means that the appeal of the story cannot be fully brought out.

[1206] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1207] In this invention, the server includes a means for allowing a user to input a protagonist and setting and for an AI to generate an original story based on the input, a means for generating original illustrations based on the generated story, a means for converting the generated story into audio and reading it aloud, a means for displaying the generated illustrations and displaying the story as text, and a means for reading the generated story aloud, thereby enabling the user to enjoy the story both visually and aurally.

[1208] A "user" is an entity that uses the system to generate stories, display illustrations, and read aloud.

[1209] The "protagonist" is the character at the center of the story and can be set by the user.

[1210] "Setting" refers to information entered by the user, such as the story's background, characters, and scenario.

[1211] "AI" stands for artificial intelligence, a technology that generates stories, creates illustrations, and translates audio based on information entered by the user.

[1212] An "original story" is a story that is newly generated by AI based on settings entered by the user.

[1213] An "illustration" is a visual image generated based on the content of a story, and visually represents a scene from the story.

[1214] "Speech" is the process of converting a textual narrative into audio.

[1215] "Means for reading aloud" is a function for playing the generated story aloud and letting the user listen.

[1216] "Means of display" refers to the functionality for visually presenting the generated illustrations and narrative text to the user.

[1217] "Means for reading aloud" is a function for playing the generated story aloud and allowing the user to listen.

[1218] A system for implementing this invention includes means for a user to input a main character and setting and for an AI to generate an original story based on the input, means for generating original illustrations based on the generated story, means for converting the generated story into audio and reading it aloud, means for displaying the generated illustrations and displaying the story as text, and means for reading the generated story aloud.

[1219] System Programming

[1220] The system includes the following programs:

[1221] 1. Story generation: The server generates a story using the OpenAI API based on the prompt entered by the user. For example, if the user enters the prompt "Once upon a time in a faraway land...", the AI ​​generates a story based on this prompt.

[1222] 2. Illustration generation: The server analyzes the content of the generated story and calls the OpenAI image generation API to generate appropriate illustrations. For example, it generates an illustration for the scene "A beautiful castle on a hill."

[1223] 3. Text-to-speech: The server uses the pyttsx3 library to convert the generated story from text to speech, so that the story can be read aloud.

[1224] 4. Display and reading: The device displays the generated illustrations, displays the story as text, and reads it aloud.

[1225] Hardware and Software Used

[1226] Hardware: Servers, user devices (smartphones, tablets, etc.)

[1227] Software: OpenAI API, pyttsx3 library, image display library (e.g. PIL)

[1228] Examples

[1229] When the user enters the prompt "Once upon a time in a faraway land...", the server does the following:

[1230] 1. Story generation: Use OpenAI's API to generate a story based on a prompt.

[1231] 2. Illustration generation: Analyze the content of the generated story and generate illustrations for a scene such as "A beautiful castle on a hill."

[1232] 3. Text-to-speech: The generated story is converted into audio using the pyttsx3 library and read to the user.

[1233] 4. Display and read aloud: The generated illustrations are displayed on the user's device, and the story is displayed as text and read aloud.

[1234] Example prompt:

[1235] "Once upon a time in a faraway land, there was a beautiful castle on a hill. The castle was home to a kind king and queen who loved their people dearly..."

[1236] In this way, users can enjoy the story both visually and aurally.

[1237] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1238] Step 1:

[1239] The user enters a prompt at the terminal.

[1240] Input: The prompt text that the user types (e.g., "Once upon a time in a faraway land...")

[1241] Output: The prompt text is sent to the server.

[1242] Step 2:

[1243] The server calls the OpenAI API based on the received prompt text and generates a story.

[1244] Input: Prompt statement

[1245] Data processing: Use the OpenAI API to generate a story based on the prompt.

[1246] Output: Text data of the generated story

[1247] Step 3:

[1248] The server analyzes the text data of the generated story and calls OpenAI's image generation API to generate appropriate illustrations.

[1249] Input: Text data of the generated story

[1250] Data processing: Analyze the content of the story and generate appropriate illustrations using an illustration generation API.

[1251] Output: Image data of the generated illustration

[1252] Step 4:

[1253] The server converts the text data of the generated story into audio data using the pyttsx3 library.

[1254] Input: Text data of the generated story

[1255] Data processing: Convert text data into audio data using the pyttsx3 library.

[1256] Output: Audio data of the generated story

[1257] Step 5:

[1258] The server transmits image data of the generated illustrations, text data of the story, and audio data to the terminal.

[1259] Input: Image data of the generated illustrations, text data of the story, and audio data

[1260] Output: Image data of illustrations, text data of the story, and audio data are sent to the terminal.

[1261] Step 6:

[1262] The terminal displays the received image data of the illustrations, displays the text data of the story, and plays back the audio data.

[1263] Input: Image data of illustrations, text data of the story, audio data

[1264] Specific operations: Display illustrations, display text, and play audio on the device screen.

[1265] Output: The user can enjoy the story visually and aurally.

[1266] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[1267] "Example 1"

[1268] In one embodiment of the present invention, the user inputs the protagonist and setting, and the AI ​​generates an original story based on that input. At this time, an emotion engine that recognizes the user's emotions is built in. Specifically, when the user inputs information for story generation, the emotion engine recognizes the user's emotions from the user's facial expressions, tone of voice, input speed, etc.

[1269] "Example 2"

[1270] The AI ​​adjusts the story generation based on the user's emotions as recognized by the emotion engine. For example, if the user expresses happiness, the AI ​​will generate a story with a light theme that reflects that emotion. Conversely, if the user expresses sadness, the AI ​​will generate a story with a dark theme that reflects that emotion.

[1271] "Example 3"

[1272] In addition, the emotion engine adjusts the output format of the generated story based on the user's emotions. For example, if the user is surprised, the AI ​​will audio-read the story with suspenseful music that reflects that emotion. On the other hand, if the user is relaxed, the AI ​​will audio-read the story with calming music that reflects that emotion.

[1273] "Example 4"

[1274] In one embodiment of the present invention, original illustrations are generated based on the AI-generated story. In this case, the color tone and style of the generated illustrations are adjusted based on the user's emotions recognized by the emotion engine. For example, if the user expresses an emotion of joy, the AI ​​generates illustrations in light colors that reflect that emotion. Conversely, if the user expresses an emotion of sadness, the AI ​​generates illustrations in dark colors that reflect that emotion.

[1275] The process flow of each embodiment will be described below.

[1276] "Example 1"

[1277] Step 1: The user enters information about the protagonist, setting, etc. into the system.

[1278] Step 2: The emotion engine recognizes the user's emotions from their facial expressions, tone of voice, typing speed, etc.

[1279] Step 3: The AI ​​generates an original story based on user input and emotional information from the emotion engine.

[1280] "Example 2"

[1281] Step 1: The emotion engine recognizes the user's emotion.

[1282] Step 2: The AI ​​adjusts the story theme based on the emotional information from the emotion engine.

[1283] Step 3: Generate an original story based on the AI-tuned themes.

[1284] "Example 3"

[1285] Step 1: The emotion engine recognizes the user's emotion.

[1286] Step 2: The AI ​​adjusts the narrative output format based on the emotional information from the emotion engine.

[1287] Step 3: Output the story based on the output format adjusted by the AI.

[1288] "Example 4"

[1289] Step 1: Generate original illustrations based on the AI-generated story.

[1290] Step 2: The emotion engine recognizes the user's emotion.

[1291] Step 3: The AI ​​adjusts the color tone and style of the generated illustration based on the emotional information from the emotion engine.

[1292] Example 1

[1293] Next, a description will be given of Example 1 of Form 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".

[1294] Conventional story generation systems only generate stories based on information entered by the user, and have the problem of not being able to generate stories that take into account the user's emotions and input circumstances. In addition, there are cases where the generated stories do not meet the user's expectations, which results in a lack of improvement in the user experience.

[1295] 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.

[1296] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for transmitting the input information to the server, a means for the server to analyze the information received, a means for the server to analyze the user's emotions using an emotion engine, a means for the server to generate a prompt sentence based on the analysis result and transmit it to the generative AI model, a means for the generative AI model to generate an original story based on the prompt sentence, a means for the server to transmit the generated story to the user's terminal, and a means for the user to receive the generated story. This enables story generation that takes into account the user's emotions and input situation, improving the user experience.

[1297] A "user" is a person who uses the system to input the protagonist and setting and generate a story.

[1298] The "protagonist" is the central character of the story entered by the user.

[1299] "Setting" refers to information such as the background, theme, and location of a story.

[1300] A "server" is a computer system that receives and analyzes information sent by a user, and sends prompts to the generative AI model.

[1301] An "emotion engine" is software that analyzes a user's emotions from their facial expressions, tone of voice, typing speed, etc.

[1302] A "generative AI model" is an artificial intelligence model that generates an original story based on a prompt text.

[1303] A "prompt" is text sent to the generative AI model that is generated based on information entered by the user and the results of analysis by the emotion engine.

[1304] A "story" is a story that a generative AI model generates based on a prompt.

[1305] "Terminal" means a device through which a User accesses the system, inputs information, and receives generated stories.

[1306] This invention is a system in which the user inputs the protagonist and setting, and a generative AI model generates an original story based on that input. The system incorporates an emotion engine that analyzes the user's emotions, making it possible to generate a story that takes the user's emotions into account.

[1307] Hardware and Software Used

[1308] Hardware

[1309] Device: The device (e.g. computer, smartphone, tablet) through which the User enters information and receives the generated story.

[1310] Server: A computer system that receives and analyzes information sent by the user and sends prompts to the generative AI model.

[1311] Camera and microphone: Devices used to capture a user's facial expressions and tone of voice.

[1312] software

[1313] Emotion engine: Software that analyzes emotions from a user's facial expressions, tone of voice, typing speed, etc. (e.g. Microsoft Azure's Emotion API).

[1314] Generative AI model: An artificial intelligence model that generates an original story based on a prompt (e.g., OpenAI's GPT-4).

[1315] Data processing and calculation

[1316] The user enters information

[1317] A user visits a website or application and fills in a form displayed in the interface with information about the protagonist, such as their name, gender, age, likes, dislikes, setting, theme, location, etc. For example, a user might enter "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, enchanted forest."

[1318] The server receives the information

[1319] When the user completes the input and presses the send button, the terminal sends the input information to the server, which receives the information and stores it in a database.

[1320] The server analyzes the user's emotions using an emotion engine.

[1321] The server uses the device's camera and microphone to capture facial expressions, tone of voice, and input speed when the user enters information. This data is then sent to the emotion engine to analyze the user's emotions. For example, if the user is excited, that information is obtained as the analysis result.

[1322] The server sends a prompt to the generative AI model.

[1323] The server generates a prompt based on the information entered by the user and the analysis results of the emotion engine. For example, it generates a prompt like this: "The main character's name is Alice, her gender is female, and her age is 25. Alice loves adventure and hates boredom. The story is set in fantasy, the theme is friendship, and the location is a magical forest. Please generate a story in which Alice meets new friends in the magical forest and goes on an adventure together," and sends it to the generative AI model.

[1324] Generative AI models generate stories

[1325] The generative AI model generates an original story based on the prompt sent from the server. For example, it generates a story about Alice meeting new friends in a magical forest and going on an adventure together.

[1326] The server sends the generated story to the user.

[1327] The server receives the story generated by the generative AI model and sends it to the user's device. The server sends the story in an appropriate format (e.g., text format).

[1328] User receives the story

[1329] The user can receive the story generated on the device and read the story displayed on the interface. For example, the user reads "A story about Alice meeting new friends in a magical forest and going on adventures together."

[1330] The above is an embodiment of the present invention.

[1331] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1332] Step 1:

[1333] The user enters information

[1334] A user accesses a website or application and enters information such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, and location into a form displayed on the interface. The entered information is sent from the terminal to the server. A specific action is when the user enters "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, magical forest."

[1335] Step 2:

[1336] The server receives the information

[1337] The server receives the information sent by the user and saves it in the database. It checks the consistency of the input data and verifies that it does not contain any invalid data. In concrete terms, the server receives the information "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, magical forest" and saves it in the database.

[1338] Step 3:

[1339] The server analyzes the user's emotions using an emotion engine.

[1340] The server uses the device's camera and microphone to capture the user's facial expressions, tone of voice, and input speed when entering information. This data is then sent to the emotion engine to analyze the user's emotions. Specifically, the server captures the user's facial expressions and voice through the camera and microphone and sends them to the emotion engine. The emotion engine returns the user's excitement state as the analysis result.

[1341] Step 4:

[1342] The server sends a prompt to the generative AI model.

[1343] The server generates a prompt sentence based on the information entered by the user and the analysis results of the emotion engine. The generated prompt sentence is sent to the generative AI model. Specifically, the server generates a prompt sentence that reads, "The main character's name is Alice, her gender is female, and her age is 25. Alice loves adventure and hates boredom. The story is set in fantasy, the theme is friendship, and the location is a magical forest. Please generate a story in which Alice meets new friends in the magical forest and goes on an adventure together." and sends it to the generative AI model.

[1344] Step 5:

[1345] Generative AI models generate stories

[1346] The generative AI model generates an original story based on the prompt sent from the server. In concrete terms, the generative AI model generates a story in which Alice meets new friends in a magical forest and goes on an adventure together.

[1347] Step 6:

[1348] The server sends the generated story to the user.

[1349] The server receives the story generated by the generative AI model and transmits it to the user's terminal. The server transmits the story in an appropriate format (e.g., text format). As a specific operation, the server transmits the generated story in text format to the user's terminal.

[1350] Step 7:

[1351] User receives the story

[1352] The user can receive the story generated on the terminal and read the story displayed on the interface. In a specific operation, the user reads "a story about Alice meeting new friends in a magical forest and going on an adventure together."

[1353] (Application example 1)

[1354] Next, a description will be given of Application Example 1 of Form 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".

[1355] Conventional story generation systems can generate stories based on user input, but they cannot generate personalized stories that take into account the user's emotions. As a result, they cannot provide stories that correspond to the user's emotions, limiting the user experience. They also lack illustrations and voice reading functions to make the generated stories more appealing.

[1356] 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.

[1357] In this invention, the server includes a means for a user to input a protagonist and setting and an AI to generate an original story based on the input, an emotion recognition means for recognizing emotions from the user's facial expressions, tone of voice, input speed, etc., a means for generating a story based on the emotions recognized by the emotion recognition means, and a means for outputting the generated story. This makes it possible to generate a personalized story according to the user's emotions.

[1358] A "user" is an individual or group that uses the system to generate a story.

[1359] The "protagonist" is a character who is central to the story, and whose information, such as name, gender, and age, is set by the user.

[1360] "Setting" refers to information such as the background, theme, and location of the story, and is selected or entered by the user.

[1361] "AI" stands for artificial intelligence, a technology that generates original stories based on user input.

[1362] A "story" is a story generated by user input and AI, and output in text format.

[1363] "Emotion recognition means" is a technology that recognizes emotions from a user's facial expressions, tone of voice, input speed, etc.

[1364] "Emotion" indicates the user's psychological state and is analyzed by the emotion recognition means.

[1365] "Output means" refers to the means for providing the generated story to the user, including formats such as text display and voice reading.

[1366] "Illustrations" are illustrations generated based on the content of the story and visually complement the story.

[1367] "Speech" is a technology that outputs the generated story as audio, and is a means of reading the story aloud to the user.

[1368] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on the input, emotion recognition means for recognizing emotions from the user's facial expressions, tone of voice, input speed, etc., means for generating a story based on the emotions recognized by the emotion recognition means, and means for outputting the generated story.

[1369] Hardware and Software Used

[1370] Hardware: Smartphone camera, smartphone microphone

[1371] Software: OpenCV (for emotion recognition), SpeechRecognition (for voice recognition), transformers (for generative AI models)

[1372] Data processing and calculation

[1373] 1. Emotion recognition:

[1374] The system analyzes images captured by the smartphone camera using OpenCV and determines the user's emotions using an emotion recognition model. Specifically, the system preprocesses the image data captured by the camera and inputs it into the emotion recognition model to estimate the user's emotions from their facial expressions.

[1375] 2. Voice Recognition:

[1376] Speech captured by a smartphone microphone is converted to text using SpeechRecognition. Specifically, the speech data is preprocessed and input into a speech recognition engine to convert the speech to text data.

[1377] 3. Narrative Generation:

[1378] Using the user's input text and emotions as prompts, the GPT-3 model is used to generate an original story. Specifically, a prompt sentence is generated that combines the user's input and emotion information, and the story is generated by inputting the prompt sentence into the GPT-3 model.

[1379] Examples

[1380] If a user enters, "Please create a story about a brave knight who fights a dragon," and the emotion engine recognizes "excitement," the story it generates will be, "An adventure story about a brave knight who engages in a fierce battle with a dragon."

[1381] Examples of prompt statements

[1382] User input: Create a story about a brave knight who fights a dragon.

[1383] User Sentiment: Excitement

[1384] story:

[1385] In this way, a more personalized narrative can be generated based on the user's emotions and input.

[1386] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1387] Step 1:

[1388] The user launches the smartphone application and inputs the main character and story settings.

[1389] Input: Text data entered by the user (e.g., the protagonist's name, gender, age, story theme, etc.)

[1390] Output: User input data

[1391] Specific operation: The user enters the required information into the application's input form and presses the submit button.

[1392] Step 2:

[1393] The device captures the user's facial expressions using the smartphone camera and recognizes emotions using OpenCV.

[1394] Input: Image data acquired from the camera

[1395] Output: Recognized emotion data (e.g. excitement, sadness, happiness, etc.)

[1396] Specific operation: The camera takes a picture of the user's face, preprocesses the image data, and inputs it into an emotion recognition model to estimate emotions.

[1397] Step 3:

[1398] The device uses the smartphone's microphone to capture the user's voice and converts it into text using SpeechRecognition.

[1399] Input: Audio data obtained from the microphone

[1400] Output: Text data converted by speech recognition

[1401] Specific operation: The user's voice is recorded using a microphone, the voice data is preprocessed, input into a speech recognition engine, and converted into text data.

[1402] Step 4:

[1403] The server generates a prompt sentence based on the user's input data and the recognized emotion data.

[1404] Input: User input data, recognized emotion data

[1405] Output: Generated prompt statement

[1406] Specific operation: The user's input data and emotion data are combined to create a prompt sentence for narrative generation.

[1407] Step 5:

[1408] The server inputs the generated prompt sentences into the GPT-3 model to generate an original story.

[1409] Input: Generated prompt text

[1410] Output: Generated narrative text

[1411] Specific operations: Input the prompt sentence into the GPT-3 model and obtain the narrative text generated by the model.

[1412] Step 6:

[1413] The terminal displays the generated story text to the user, using a text-to-speech function if necessary.

[1414] Input: Generated narrative text

[1415] Output: Story text displayed to the user, voice reading data

[1416] Specific behavior: The generated story text is displayed on the application screen and the story is played aloud using the text-to-speech function.

[1417] Example 2

[1418] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1419] Conventional story generation systems generate stories without considering the user's emotions, making it difficult to provide a story that matches the user's emotions. In addition, there are limited ways to output the generated story in a format that is easy for the user to read, which reduces user convenience.

[1420] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1421] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for an emotion recognition engine to recognize the emotion of the user, a means for generating a prompt sentence for the generative AI model based on the user's input information and the recognized emotion, a means for the generative AI model to generate an original story based on the prompt sentence, and a means for outputting the generated story in text or PDF format. This makes it possible to generate a story that matches the emotion of the user and output it in a format that is easy for the user to read.

[1422] A "user" is an individual or organization that uses the system to request the generation of a story.

[1423] The "protagonist" is the character at the center of the story and the main character defined by the user.

[1424] "Setting" refers to detailed information about the story's background, environment, time period, location, etc., and is an element entered by the user.

[1425] An "emotion recognition engine" is software or hardware that analyzes data such as the user's facial expressions and voice to recognize the user's emotions.

[1426] A "generative AI model" is an artificial intelligence algorithm that generates an original story based on an input prompt.

[1427] A "prompt" is text that provides instructions to a generative AI model based on user input and recognized emotions.

[1428] A "narrative" is a piece of text containing a sequence of events and character descriptions generated by a generative AI model.

[1429] A "text format" is a digital format for storing and displaying the generated story as character data.

[1430] "PDF Format" means a digital format for storing and displaying the generated story in Portable Document Format.

[1431] "Output" is the process of providing the generated narrative in a user-accessible form.

[1432] This invention is a system in which a generative AI model generates an original story based on information input by a user and emotions recognized by an emotion recognition engine, and outputs the story in a format that is easy for the user to read. A specific embodiment of this system will be described below.

[1433] Hardware and Software Used

[1434] Hardware: Servers, user devices (PCs, smartphones, etc.)

[1435] Software: Generative AI models (e.g. GPT-4), emotion recognition engines (e.g. Affectiva SDK)

[1436] Program Processing

[1437] 1. Collecting user input information

[1438] A user uses a terminal to input information needed to generate a story, such as details about the story's theme, characters, setting, etc.

[1439] Example: A user opens a web browser and types "I'd like to read medieval fantasy stories" into the system's input form.

[1440] 2. Emotion recognition using emotion engine

[1441] When a user provides input, the emotion recognition engine recognizes the user's emotions from their facial expressions and voice.

[1442] Example: When a user uses the camera and microphone to input, an emotion recognition engine analyzes the user's facial expressions and tone of voice to recognize the emotion "excitement."

[1443] 3. Prompt generation

[1444] The server generates a prompt sentence for the generative AI model based on the user's input information and the emotions recognized by the emotion recognition engine.

[1445] Example: The server generates a prompt saying "Generate a medieval fantasy story. The story should include an exciting adventure" based on the input information "I want to read a medieval fantasy story" and the emotion "excitement."

[1446] 4. Narrative Creation

[1447] The server inputs prompt sentences into the generative AI model and generates a story.

[1448] Example: A server inputs the following prompt to a generative AI model (e.g., GPT-4): "Generate a medieval fantasy story. The story should include an exciting adventure."

[1449] 5. Story output

[1450] The generated story is output in a user-friendly format.

[1451] Example: A server generates a generated story in text and / or PDF format and provides a link for the user to download it.

[1452] Examples

[1453] User input: "I want to read a medieval fantasy story."

[1454] Emotion recognition engine recognition result: "Excited"

[1455] Prompt for generative AI model: "Generate a medieval fantasy story that contains exciting adventures."

[1456] When this prompt is fed into a generative AI model, the model generates a story like this:

[1457] A snippet from the generated story: "In a medieval kingdom, a young knight embarks on an adventure to slay a dragon. He overcomes many challenges and ultimately becomes the hero who saves the kingdom."

[1458] Users can download and read the story in text or PDF format.

[1459] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1460] Step 1:

[1461] The user uses the terminal to input the information needed to generate the story.

[1462] Specifically, a user opens a web browser and fills in the system's input form with details about the story's theme, characters, setting, etc.

[1463] Input: Details of the story, such as theme, characters, setting, etc.

[1464] Output: User input is sent to the server

[1465] Step 2:

[1466] When a user provides input, the emotion recognition engine recognizes the user's emotions from their facial expressions and voice.

[1467] Specifically, when a user makes input using the camera and microphone, the emotion recognition engine analyzes the user's facial expressions and tone of voice.

[1468] Input: User's facial expression data, voice data

[1469] Output: The recognized emotion data is sent to the server.

[1470] Step 3:

[1471] The server generates a prompt sentence for the generative AI model based on the user's input information and the emotions recognized by the emotion recognition engine.

[1472] Specifically, the server generates a prompt sentence saying, "Please generate a medieval fantasy story. The story should include an exciting adventure," based on the input information "I want to read a medieval fantasy story" and the emotion "excitement."

[1473] Input: User input information, recognized emotion data

[1474] Output: Generated prompt statement

[1475] Step 4:

[1476] The server inputs prompt sentences into the generative AI model and generates a story.

[1477] Specifically, the server inputs a prompt to the generative AI model (e.g., GPT-4): "Generate a medieval fantasy story. The story should include an exciting adventure."

[1478] Input: Generated prompt text

[1479] Output: The generated story

[1480] Step 5:

[1481] The generated story is output in a user-friendly format.

[1482] Specifically, the server generates the generated story in text or PDF format and provides a link for the user to download it.

[1483] Input: A generated story

[1484] Output: Story file in text and PDF format, download link

[1485] (Application example 2)

[1486] Next, a description will be given of Application Example 2 of Form 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".

[1487] Conventional story generation systems are unable to generate stories that reflect the user's emotions, making it difficult to provide a story experience that responds to the user's emotions. In addition, there is a lack of means to save the generated stories in various formats, which makes it less convenient for users.

[1488] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1489] In this invention, the server includes a means for a user to input a protagonist and a setting and an AI to generate an original story based on the input, a means for outputting the generated story, a means for an emotion recognition engine to recognize the user's emotion and adjust the tone and theme of the story based on the emotion, and a means for saving the generated story in text or PDF format. This makes it possible to provide a story experience according to the user's emotion and to save the generated story in a variety of formats.

[1490] A "user" is an individual or group that uses the system to generate a story.

[1491] The "protagonist" is the character at the center of the story and can be set by the user.

[1492] "Setting" refers to detailed information about the story, such as the background, situation, and characters, which can be entered by the user.

[1493] "AI" stands for artificial intelligence, a technology that generates original stories based on user input.

[1494] A "narrative" is a piece of text that contains a series of events or episodes generated by AI.

[1495] "Output" refers to providing the generated narrative in a form that can be viewed by a user.

[1496] An "emotion recognition engine" is a technology that recognizes the user's emotions in real time and adjusts the tone and theme of the story based on that information.

[1497] "Tone" refers to the overall mood or emotional tone of a story.

[1498] A "theme" is the central subject or message of a story.

[1499] "Text format" is a data format in which data is saved as character information.

[1500] "PDF format" is an abbreviation for Portable Document Format, and is a standard file format for electronically storing documents.

[1501] "Saving" refers to keeping the generated story as data so that it can be viewed at a later date.

[1502] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on that input, means for outputting the generated story, means for an emotion recognition engine to recognize the user's emotions and adjust the tone and theme of the story based on the emotions, and means for saving the generated story in text or PDF format.

[1503] System Configuration

[1504] The system uses the following hardware and software:

[1505] Hardware: Smartphones, servers

[1506] Software: Python, OpenAI API, pdfkit, EmotionRecognizer

[1507] Program processing explanation

[1508] The server uses OpenAI's generative AI model to generate a story based on the protagonist and setting entered by the user. As the user enters the input via their smartphone, the data is sent to the server. The server uses an emotion recognition engine (EmotionRecognizer) to recognize the user's emotions in real time and adjusts the tone and theme of the story based on the emotional information.

[1509] The generated stories are saved in text or PDF format and made available for download by users. Specifically, the generated stories are converted to PDF format using pdfkit and saved on the server.

[1510] Examples

[1511] For example, if the user inputs the theme "adventure" and the emotion recognition engine recognizes "joy," the server will send the following prompt to the generative AI model:

[1512] User Sentiment: Delight

[1513] User Input: Adventure

[1514] Generate a story.

[1515] Based on this prompt, the generative AI model generates a light-hearted and fun adventure story, which is then converted to PDF format using pdfkit and saved on the server for users to download.

[1516] In this way, a system is realized that generates original stories based on the user's emotions and input, and allows users to save and view the stories in a variety of formats.

[1517] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1518] Step 1:

[1519] Users use their smartphones to input the theme and keywords of the story.

[1520] Input: Themes or keywords entered by the user (e.g. "adventure")

[1521] Output: User input data

[1522] Specific actions: The user opens the smartphone application, enters information into text boxes for the story's theme and keywords, and presses the send button.

[1523] Step 2:

[1524] The server receives the user's input data and recognizes the user's emotions in real time using an emotion recognition engine.

[1525] Input: User input data

[1526] Output: User emotion data (e.g. "happy")

[1527] Specific operation: The server receives the user's input data, analyzes the user's emotions using EmotionRecognizer, and generates emotion data.

[1528] Step 3:

[1529] The server generates a prompt sentence based on the user's input data and emotion data and sends it to the generative AI model.

[1530] Input: User input data, user emotion data

[1531] Output: Prompt text (e.g. "User emotion: Joy\nUser input: Adventure\nGenerate a story.")

[1532] Specific operation: The server combines the user's input data and emotion data to generate a prompt sentence and sends it to OpenAI's generative AI model.

[1533] Step 4:

[1534] The generative AI model generates an original story based on the prompt and sends it back to the server.

[1535] Input: Prompt statement

[1536] Output: A generated story (e.g. "One day, a joyous adventure began...")

[1537] Specific operation: The generative AI model analyzes the prompt sentence, generates an appropriate story and sends it back to the server.

[1538] Step 5:

[1539] The server stores the generated stories in text and PDF formats and makes them available for users to download.

[1540] Input: A generated story

[1541] Output: Story file in text and PDF format

[1542] Specific behavior: The server converts the generated story to PDF format using pdfkit and saves it on the server. The user can download the story file by clicking the download link.

[1543] Step 6:

[1544] Users can download and view the generated stories.

[1545] Input: Story file in text or PDF format

[1546] Output: The story the user sees

[1547] Specific operations: The user clicks on the download link via the smartphone application, downloads the generated story, and views it.

[1548] Example 3

[1549] Next, a third embodiment of the third embodiment will be described. 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".

[1550] Conventional story generation systems can generate stories based on prompts entered by users, but they lack the means to enjoy the story visually and aurally. They also lack the ability to adjust the story output format according to the user's emotions. This limits the user experience and reduces the immersiveness of the story.

[1551] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1552] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for analyzing the generated story and generating illustrations corresponding to appropriate scenes, a means for recognizing the user's emotions using an emotion engine and adjusting the color tone and style of the generated illustrations, a means for converting the generated story from text to audio and adding background music based on the user's emotions, and a means for outputting the generated story, illustrations, and audio to the user. This allows the user to enjoy the story visually and audibly, and furthermore, the output format of the story is adjusted according to the user's emotions, enabling a more immersive experience.

[1553] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on prompts entered by the user.

[1554] A "prompt" is text that a user enters to direct the generation of a story.

[1555] "Illustrations" are images generated to visually represent the content of a story.

[1556] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's output based on those emotions.

[1557] "Tone" is an element that refers to the brightness and saturation of the colors in an illustration.

[1558] "Style" is an element that refers to the characteristics of the illustration's design and art.

[1559] "Text-to-speech" is a technique for converting text data into speech data.

[1560] "Background music" is music that is played in conjunction with the audio output of the story.

[1561] "User emotion" refers to the emotional state exhibited by the user, such as happiness, surprise, relaxation, etc.

[1562] "Output format" is the form in which the content is presented to the user, such as narrative, illustrations, audio, etc.

[1563] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1564] The present invention is a system that generates a story based on a prompt sentence input by a user, and allows the user to enjoy the story visually and aurally. A specific embodiment of the system will be described below.

[1565] System Configuration

[1566] Hardware and Software Configuration

[1567] 1. Server

[1568] Generative AI models are used to generate narratives, specifically using natural language generation models such as OpenAI's GPT-4.

[1569] Image generation AI: Used to generate illustrations. Specifically, it uses image generation models such as DALL-E.

[1570] Emotion Engine: Used to recognize the user's emotions. Specifically, it uses Affectiva's emotion recognition technology.

[1571] Text-to-speech technology: Used to convert the story into audio, specifically using technologies such as Google Text-to-Speech.

[1572] 2. Terminal

[1573] Provides an interface for the user to enter a prompt.

[1574] Displays and plays stories, illustrations, and audio sent from the server.

[1575] System Operation

[1576] User Actions

[1577] The user types a story prompt into an input field on the device, for example, "A story about a boy who one day encounters a mysterious creature in the woods."

[1578] Server Processing

[1579] 1. Narrative Creation

[1580] The server receives the prompt text entered by the user and inputs it into the generative AI model. The generative AI model generates a story based on the prompt text. For example, it generates a story like, "One day, the boy met a mysterious creature in the forest. The creature could talk and told the boy the secret of the forest."

[1581] 2. Illustration Generation

[1582] The server analyzes the generated story and identifies important scenes. It then uses image generation AI to generate illustrations that correspond to the identified scenes. For example, it generates an illustration of a scene where a boy encounters a mysterious creature.

[1583] 3. Emotion Recognition

[1584] The server uses an emotion engine to recognize emotions from the user's facial expressions and voice, for example, to determine whether the user is expressing an emotion of joy.

[1585] 4. Adjusting illustrations

[1586] The server adjusts the color tone and style of the generated illustration based on the user's recognized emotion, for example generating a bright-colored illustration if the user is expressing an emotion of joy.

[1587] 5. Audio version of the story

[1588] The server uses text-to-speech technology to convert the generated story into audio. For example, it will convert a story like this: "One day, a boy met a mysterious creature in the forest. The creature could speak and told the boy the secrets of the forest."

[1589] 6. Add background music

[1590] The server adds appropriate background music to the spoken story based on the recognized user emotion, for example, if the user shows a relaxed emotion, it adds calm music in the background.

[1591] Display of terminal

[1592] The device displays and plays the received story, illustrations, and audio to the user, allowing the user to enjoy the story both visually and aurally.

[1593] In this way, a system is realized that allows the user to enjoy a consistent experience from the creation of a story to the visual and audio experience. The flow of the specific process in the third embodiment will be described with reference to FIG.

[1594] Step 1:

[1595] The user enters a prompt sentence.

[1596] Input: The user types a story prompt into the device's input field, for example, "A story about a boy who one day encounters a mysterious creature in the woods."

[1597] Output: The prompt text entered is sent to the server.

[1598] Step 2:

[1599] The server generates a story using a generative AI model.

[1600] Input: The server receives the prompt sent by the user.

[1601] Data processing: The server inputs prompt text into a generative AI model (e.g., GPT-4) to generate a story.

[1602] Output: The generated story is stored in the server. For example, a story like "One day, the boy met a mysterious creature in the forest. The creature could talk and told the boy the secret of the forest."

[1603] Step 3:

[1604] The server analyzes the generated story and generates illustrations.

[1605] Input: The server receives the generated story.

[1606] Data processing: The server analyzes the story and identifies important scenes. Then, it uses an image generation AI (e.g., DALL-E) to generate illustrations that correspond to the identified scenes.

[1607] Output: The generated illustrations are stored in the server. For example, an illustration of a scene where a boy encounters a mysterious creature is generated.

[1608] Step 4:

[1609] The server recognizes the user's emotions using an emotion engine.

[1610] Input: The server receives the user's facial and voice data.

[1611] Data processing: The server uses an emotion engine (e.g., Affectiva's emotion recognition technology) to analyze the user's emotions.

[1612] Output: The user's emotional state is recognized, e.g., the user is recognized to be exhibiting the emotion of happiness.

[1613] Step 5:

[1614] The server adjusts the color tone and style of the illustration based on the user's emotions.

[1615] Input: The server receives the recognized emotional state of the user and the generated illustration.

[1616] Data processing: The server adjusts the color tone and style of the illustration based on the user's emotion. For example, if the user expresses happiness, the server adjusts the color tone of the illustration to a brighter color.

[1617] Output: The adjusted illustrations are kept on the server.

[1618] Step 6:

[1619] The server vocalizes the generated story.

[1620] Input: The server receives the generated story.

[1621] Data processing: The server converts the story into audio using text-to-speech technology (e.g., Google Text-to-Speech).

[1622] Output: The voiced story is stored in the server. For example, a story like "One day, a boy met a mysterious creature in the forest. The creature could talk and told the boy the secret of the forest." is voiced.

[1623] Step 7:

[1624] The server adds background music to the voiced story based on the user's emotions.

[1625] Input: The server receives the recognized emotional state of the user and the spoken narrative.

[1626] Data processing: The server selects appropriate background music based on the user's emotion and adds it to the spoken story. For example, if the user is showing a relaxed emotion, a calm music will be added to the background.

[1627] Output: The audio version of the story with added background music is kept on the server.

[1628] Step 8:

[1629] The server transmits the final story, illustrations, and audio to the device.

[1630] Input: The server receives a voiced story with adjusted illustrations and background music.

[1631] Data processing: The server puts these data together into a single package.

[1632] Output: The final story, illustrations and audio are sent to the device.

[1633] Step 9:

[1634] The device displays and plays the story, illustrations and audio to the user.

[1635] Input: The device receives the final story, illustrations, and audio sent by the server.

[1636] Data processing: The device properly displays and plays back this data.

[1637] Output: The user can enjoy the story both visually and aurally.

[1638] (Application example 3)

[1639] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1640] Conventional story generation systems have difficulty adjusting the output format according to the user's emotions and providing visual and auditory enjoyment. In addition, the system lacks the ability to generate illustrations based on the content of the story and adjust the voice output based on emotions, limiting the user experience. This is inconvenient for users who have difficulty reading visually or who want to do other tasks while listening to a story.

[1641] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1642] In this invention, the server includes a means for a user to input a protagonist and a setting, and an AI to generate an original story based on the input, a means for outputting the generated story, a means for an emotion engine to recognize the user's emotion and adjust the output format of the story based on the emotion, a means for converting the generated story from text to audio and reading it aloud, and a means for generating original illustrations based on the generated story and adjusting the color tone and style of the illustrations based on the user's emotion. This enables visual and audio output of the story according to the user's emotion, and makes it possible to provide a system that is convenient for users who have difficulty reading visually and users who want to do other tasks while listening to the story.

[1643] A "user" is an individual or organization that uses the system to generate and output stories.

[1644] The "protagonist" is the character at the center of the story and can be set by the user.

[1645] "Setting" refers to the background of the story and details of the scenario, and is information entered by the user.

[1646] "AI" stands for artificial intelligence, a technology that generates stories based on user input.

[1647] A "narrative" is a piece of text that contains a series of events or episodes generated by AI.

[1648] "Output" is the act of providing the generated story and illustrations to the user.

[1649] An "emotion engine" is a technology that recognizes the user's emotions and adjusts the system's output based on those emotions.

[1650] "Illustrations" are visual images or illustrations generated based on the content of the story.

[1651] "Color tone" refers to the brightness and vividness of the colors in an illustration, and is adjusted according to the user's emotions.

[1652] "Style" refers to the design and expression of the illustrations, and is adjusted according to the user's emotions.

[1653] "Speech" is the process of converting text into speech.

[1654] "Reading aloud" is the act of conveying the generated story to the user through audio.

[1655] "Speed" refers to the speed at which the audio version of the story is read out, and is adjusted according to the user's emotions.

[1656] "Music" refers to the background music played when the story is being spoken, and is selected based on the user's emotions.

[1657] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on that input, means for outputting the generated story, means for an emotion engine to recognize the user's emotions and adjust the output format of the story based on the emotions, means for converting the generated story from text to speech and reading it aloud, and means for generating original illustrations based on the generated story and adjusting the color tone and style of the illustrations based on the user's emotions.

[1658] System Configuration

[1659] 1. User Input:

[1660] The user inputs the protagonist and setting using a device such as a smartphone or a head-mounted display, for example by entering a prompt sentence such as "Once upon a time in a faraway land...".

[1661] 2. Narrative Generation:

[1662] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate a story based on the prompts entered by the user, and the story is stored in text format on the server.

[1663] 3. Emotion recognition:

[1664] The user's emotions are recognized using an emotion engine (e.g., emotion_recognition library), which analyzes the user's facial expressions and voice to determine emotions, and sends the results to the server.

[1665] 4. Illustration Generation:

[1666] The server generates illustrations based on the content of the generated story. The illustrations are created using PIL (Python Imaging Library) and their color tone and style are adjusted based on the user's emotion. For example, if the user indicates the emotion "happy," a bright colored illustration is generated.

[1667] 5. Vocalization:

[1668] The server uses the pyttsx3 library to convert the generated story from text to speech, adjusting the speech speed and background music based on the user's emotions. For example, if the user expresses the emotion "happy," a faster, more upbeat music will play.

[1669] Examples

[1670] When a user enters the prompt phrase "Once upon a time in a faraway land...", the server uses a generative AI model to generate a story. If the emotion engine recognizes the user's emotion as "happy", the generated illustrations are adjusted to brighter tones and the voice is set to a faster speed. Users can enjoy the story visually and aurally through their smartphone or head-mounted display.

[1671] This system makes it possible to output a story visually and aurally according to the user's emotions, providing a convenient system for users who have difficulty reading visually or who wish to perform other tasks while listening to a story.

[1672] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1673] Step 1:

[1674] The user uses a terminal to input the main character and setting. The input prompt (e.g., "Once upon a time in a faraway land...") is sent from the terminal to the server. The input data is in text format, and the server receives it.

[1675] Step 2:

[1676] The server generates a story using a generative AI model (e.g., OpenAI's GPT-3) based on the received prompt sentence. The generative AI model takes the prompt sentence as input and outputs the text of the story. The generated story is stored on the server.

[1677] Step 3:

[1678] The server uses an emotion engine (e.g., emotion_recognition library) to recognize the user's emotions. The emotion engine receives the user's facial expressions and voice data as input, and outputs the emotion analysis results. The analysis results are sent to the server.

[1679] Step 4:

[1680] The server generates illustrations based on the content of the generated story. It uses PIL (Python Imaging Library) to draw the story text into an image. The color tone and style of the illustration are adjusted based on the user's emotion. For example, if the emotion is "happy," an illustration with a bright color tone is generated. The generated illustrations are stored on the server.

[1681] Step 5:

[1682] The server uses the pyttsx3 library to convert the generated story from text to audio. It takes the story text as input and outputs audio data. Based on the user's emotion, the audio speed and background music are adjusted. For example, if the emotion is "happy," a faster, more upbeat music is played. The generated audio data is stored on the server.

[1683] Step 6:

[1684] The server transmits the generated story, illustrations, and audio data to the terminal. The terminal receives the data and provides it visually and audibly to the user. The user can enjoy the story through the terminal.

[1685] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1686] The data generation model 58 is a so-called generative AI (Artificial Intelligence) model. An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1687] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1688] 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 smart glasses 214.

[1689] [Third embodiment]

[1690] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1691] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1692] 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 wide area network (WAN) and / or a local area network (LAN).

[1693] 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.

[1694] 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 the voice according to instructions from the processor 46.

[1695] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1696] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1697] Fig. 6 shows an example of 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.

[1698] 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.

[1699] 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.

[1700] In the headset type terminal 314, 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.

[1701] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1702] "Example 1"

[1703] As one embodiment of the present invention, a system is provided that includes an interface for a user to input a protagonist and a setting. Specifically, the user inputs information such as the protagonist's name, gender, age, likes, dislikes, etc., on a website or application.

[1704] You also select or input the setting, theme, and location of the story.

[1705] "Example 2"

[1706] Based on the input information, the AI ​​generates an original story. Based on the information input by the user, the AI ​​creates a story plot and generates a story based on that. The generated story is output in a format that the user can read. Specifically, it is output in text or PDF format, and the user can download and read it.

[1707] "Example 3"

[1708] In addition, a means is provided to generate original illustrations based on the AI-generated story. Specifically, the AI ​​analyzes the content of the story and generates illustrations that correspond to appropriate scenes. The generated illustrations are output together with the story, allowing users to enjoy the story visually.

[1709] "Example 4"

[1710] In addition, a means is provided to convert the AI-generated story into audio and read it aloud. Specifically, the AI ​​converts the generated story from text to audio and outputs it in a format that the user can listen to. This is convenient for users who have difficulty reading visually or who want to do other tasks while listening to the story.

[1711] The process flow of each embodiment will be described below.

[1712] "Example 1"

[1713] Step 1: A user opens a website or application and enters some information about the main character, such as their name, gender, age, likes, and dislikes.

[1714] Step 2: The user selects or inputs the setting, theme, location, etc. of the story.

[1715] "Example 2"

[1716] Step 1: The AI ​​creates a story plot based on information input by the user.

[1717] Step 2: Generate a story based on the plot created by the AI.

[1718] Step 3: The generated story is output in a format that the user can read. Specifically, it is output in text format or PDF format, and the user can download it and read it.

[1719] "Example 3"

[1720] Step 1: Analyze the content of the AI-generated story.

[1721] Step 2: The AI ​​generates illustrations that correspond to appropriate scenes based on the content of the story.

[1722] Step 3: The generated illustrations are output together with the story, allowing users to enjoy the story visually.

[1723] "Example 4"

[1724] Step 1: The AI ​​converts the generated story from text to audio.

[1725] Step 2: The converted audio is output in a format that the user can hear, which is convenient for users who have visual impairments or who want to continue with other tasks while listening to the story.

[1726] Example 1

[1727] Next, a description will be given of Example 1 of the embodiment 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".

[1728] Conventional story generation systems often fail to fully reflect the user's intentions and detailed settings when generating original stories based on information entered by the user. They also lack a means to quickly and effectively provide the generated stories to users. Furthermore, the lack of a function to generate illustrations and audio based on the generated stories limits the user experience.

[1729] 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.

[1730] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for transmitting the input information to the server, a means for generating a prompt sentence based on the information received by the server, a means for inputting the generated prompt sentence to the generative AI model, a means for returning a story generated by the generative AI model to the server, a means for the server to transmit the generated story to the terminal, and a means for displaying the story received by the terminal to the user. This makes it possible to quickly and effectively generate an original story that reflects the user's detailed settings and provide it to the user.

[1731] A "user" is an individual or group that uses the system to input the protagonist and story settings.

[1732] The "protagonist" is the character at the center of the story, and is the person for whom the user enters information such as name, gender, and age.

[1733] "Setting" refers to information such as the background, theme, and location of the story, and is an element selected or input by the user.

[1734] The "server" is a computer system that receives information sent by a user and inputs prompt sentences into the generative AI model.

[1735] "Terminal" means a device through which a user can input information and display the generated story, including a web browser and dedicated applications.

[1736] A "prompt sentence" is text that is generated based on information entered by the user and is input into a generative AI model.

[1737] A "generative AI model" is an artificial intelligence algorithm that generates a story based on a prompt sentence, using natural language processing technology, for example.

[1738] A "story" is text that a generative AI model generates based on a prompt, and is an original story provided to the user.

[1739] "Illustrations" are illustrations that are drawn based on the generated story and provide a visual complement to the story.

[1740] "Speech" is the process of converting the generated story into audio data for reading aloud.

[1741] This invention is a system in which a user inputs the protagonist and story settings, and a generative AI model generates an original story based on that information and provides it to the user. A specific embodiment of this system will be described below.

[1742] Users input information into a website or application, such as the main character's name, gender, age, likes, dislikes, setting, theme, location, etc. For example, a user might input the following information:

[1743] Main character's name: Taro

[1744] Gender: Male

[1745] Age: 25

[1746] Likes: Adventure

[1747] Dislikes: Boredom

[1748] Story setting: Fantasy

[1749] Theme: Friendship

[1750] Location: Magical Forest

[1751] The device receives the information entered by the user and sends it to the server. To do this, the device uses a web browser or a dedicated application to send data to the server using an HTTP request.

[1752] The server receives the information sent from the device and generates a prompt sentence to input to the generative AI model. Specifically, it generates the following prompt sentence:

[1753] "The main character's name is Taro, a 25-year-old man. He loves adventure and hates boredom. The story is set in a fantasy world, the theme is friendship, and the location is a magical forest."

[1754] The server inputs the generated prompt sentence into a generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. The server sends the prompt sentence using an API request.

[1755] The generative AI model generates a story based on the prompt received from the server and returns the result to the server. An example of the generated story is as follows:

[1756] "Taro is a 25-year-old adventurous young man who hates boredom. One day, he meets new friends in a magical forest and together they embark on a great adventure."

[1757] The server receives the story returned by the generative AI model and sends it to the device. The server sends the data using an HTTP response.

[1758] The device displays the story received from the server to the user, using a web browser or an application UI.

[1759] This system allows users to quickly and effectively generate and enjoy original stories that reflect detailed settings. The user experience can be further improved by adding the functionality to generate illustrations and audio based on the generated stories.

[1760] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1761] Step 1:

[1762] Users input information such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, and location on a website or application. Specifically, they input information such as "Taro, male, 25 years old, adventure, boredom, fantasy, friendship, magical forest" into an input form. The input data is stored on the device in JSON format.

[1763] Step 2:

[1764] The terminal receives the information entered by the user and sends it to the server. Specifically, the terminal uses an HTTP POST request to send the entered JSON data to the server. The input data is sent to the server, and the server receives it.

[1765] Step 3:

[1766] The server receives the information sent from the device and generates a prompt to input to the generative AI model. Specifically, it analyzes the received JSON data and generates a prompt like the following:

[1767] "The main character's name is Taro, a 25-year-old man. He loves adventure and hates boredom. The story is set in a fantasy world, the theme is friendship, and the location is a magical forest."

[1768] The generated prompt sentences are input into a generative AI model.

[1769] Step 4:

[1770] The server inputs the generated prompt sentence into the generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. Specifically, the prompt sentence is sent using an API request. The input data is the prompt sentence, and the output data is the generated story.

[1771] Step 5:

[1772] The generative AI model generates a story based on the prompt received from the server and returns the result to the server. Specifically, the generative AI model generates a story using natural language processing technology and returns the generated text data to the server as an API response. The output data is the generated story.

[1773] Step 6:

[1774] The server receives the story returned from the generative AI model and sends it to the terminal. Specifically, it sends the generated story to the terminal using an HTTP response. The input data is the generated story, and the output data is the story to be sent to the terminal.

[1775] Step 7:

[1776] The terminal displays the story received from the server to the user. Specifically, the story is displayed using a web browser or an application UI. The input data is the story received from the server, and the output data is the story displayed to the user.

[1777] (Application example 1)

[1778] Next, a description will be given of Application Example 1 of Form 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".

[1779] Conventional story generation systems can generate stories based on information entered by the user, but the generated stories may not meet the user's expectations. In addition, the story generation process is a black box, making it difficult for users to understand how the story is generated. Furthermore, there are limited ways to enjoy the generated story visually or aurally, which limits the user experience.

[1780] 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.

[1781] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for outputting the generated story, a means for generating a prompt sentence to be passed to the generative AI model, and a means for displaying the generated story to the user. This allows a high-quality story to be generated based on the information input by the user, and allows the user to enjoy the story visually and aurally.

[1782] A "user" is an individual or group that uses the system to generate a story.

[1783] The "protagonist" is the character at the center of the story, and is the subject for which the user enters information such as name, gender, and age.

[1784] "Setting" refers to information such as the background, theme, and location of a story, and is an element that affects the content of the story when entered by the user.

[1785] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on information entered by the user.

[1786] A "narrative" is a text-based story generated by a generative AI model and constructed based on information input by a user.

[1787] A "prompt sentence" is an input sentence to be passed to a generative AI model, and is generated based on information entered by the user.

[1788] "Output" is the act or means of providing the generated narrative to a user.

[1789] "Display" is the act or means of visually presenting the generated narrative to a user.

[1790] A system for implementing this invention includes a means for a user to input a protagonist and setting and for a generative AI model to generate an original story based on the input, a means for outputting the generated story, a means for generating a prompt sentence to be passed to the generative AI model, and a means for displaying the generated story to the user.

[1791] System Configuration

[1792] The system consists of the following main components:

[1793] 1. User Interface: The interface through which the user inputs the main character and settings. This is implemented as a smartphone application.

[1794] 2. Generative AI model: An artificial intelligence model that generates a story based on information input by the user. Specifically, we use OpenAI's GPT-3.

[1795] 3. Prompt generation module: A module that generates a prompt sentence to be passed to the generative AI model based on the information entered by the user.

[1796] 4. Story display module: A module that visually displays the generated story to the user.

[1797] Program Processing

[1798] The server receives information input by the user through the user interface, such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, location, etc. This information is passed to the prompt generation module, which generates a prompt sentence suitable for the generative AI model.

[1799] The generated prompt sentences are passed to a generative AI model to generate an original story, which is then displayed to the user through a story display module.

[1800] Hardware and Software Used

[1801] Hardware: Smartphone

[1802] Software: Python, OpenAI API

[1803] Examples

[1804] If the user enters the following information:

[1805] Name: Taro

[1806] Gender: Male

[1807] Age: 10

[1808] Likes: Adventure

[1809] Dislikes: Boredom

[1810] Story Setting: Future city

[1811] Theme: Friendship

[1812] Location: Japan

[1813] An example of a prompt that can be generated based on this information is:

[1814] Main character's name: Taro

[1815] Gender: Male

[1816] Age: 10

[1817] Likes: Adventure

[1818] Dislikes: Boredom

[1819] Story Setting: Future city

[1820] Theme: Friendship

[1821] Location: Japan

[1822] Using this information, generate a story like the one below.

[1823] By passing this prompt to a generative AI model, a personalized story is generated for the user, which is then displayed on the smartphone screen for the user to enjoy visually.

[1824] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1825] Step 1:

[1826] The user starts the smartphone application and inputs information about the protagonist and the setting. Specifically, the user inputs information such as the protagonist's name, gender, age, likes and dislikes, story setting, theme, location, etc. through the application's interface. The input information is then sent to the server.

[1827] Input: Main character's name, gender, age, likes, dislikes, story setting, theme, location

[1828] Output: User input data

[1829] Step 2:

[1830] The server passes the received user input data to the prompt generation module. The prompt generation module generates a prompt sentence to be passed to the generative AI model based on the user input data. The prompt sentence is in text format that contains the information entered by the user.

[1831] Input: User-entered data

[1832] Output: Prompt statement

[1833] Step 3:

[1834] The server passes the generated prompt sentence to the generative AI model. The generative AI model generates an original story based on the prompt sentence. OpenAI's GPT-3 is used as the generative AI model.

[1835] Input: Prompt statement

[1836] Output: The generated story

[1837] Step 4:

[1838] The server passes the generated story to a story display module. The story display module displays the generated story on the user's smartphone. The user can visually enjoy the generated story through the screen of the smartphone.

[1839] Input: A generated story

[1840] Output: Story displayed on a smartphone

[1841] Step 5:

[1842] The user can read and enjoy the generated story, and if desired, can change the settings again and generate a new story.

[1843] Input: A story displayed on a smartphone

[1844] Output: User experience and feedback

[1845] Example 2

[1846] Next, a second embodiment of the second form will be described. 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".

[1847] Conventional story generation systems were lacking in the quality and speed of generating original stories based on information entered by the user. In addition, there were limited ways to provide the generated stories in a format that was easy for users to read, resulting in a poor user experience. Furthermore, there was a lack of functionality to add illustrations and audio to the stories, which made it difficult to fully bring out the appeal of the stories.

[1848] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1849] In this invention, the server includes a means for a user to input a theme, characters, and setting, a means for transmitting the input information to the server, a means for the server to input a prompt sentence to the generative AI model, a means for the generative AI model to generate a plot of the story, a means for the server to generate a detailed story based on the plot, a means for the server to convert the story into a text format or a PDF format, a means for the server to transmit the generated story to the user's terminal, and a means for the user to download and read the story. This makes it possible to quickly generate a high-quality original story based on the information input by the user and provide it in an easy-to-read format. In addition, the inclusion of a function to add illustrations and audio to the story can further enhance the appeal of the story.

[1850] A "user" is an individual or group that uses the system to input information such as theme, characters, and setting in order to generate a story.

[1851] "Theme" refers to the main subject or genre of the story, and is information entered by the user to specify the direction of the story.

[1852] "Characters" refers to characters who appear in a story, and is information that a user inputs to specify characters who play important roles in the story.

[1853] "Setting" refers to the setting or background of a story, and is information that the user inputs to specify the environment and time period of the story.

[1854] A "Terminal" is a device (e.g., PC, smartphone, tablet) that a User uses to access the System and input information.

[1855] "Server" means a computer system for receiving information submitted by a user, generating a story using a generative AI model, and finally providing the story to the user.

[1856] A "generative AI model" is an artificial intelligence model that generates story plots and detailed text based on information entered by the user.

[1857] A "prompt" is a sentence that is input into a generative AI model based on information such as theme, characters, and setting entered by the user.

[1858] A "plot" is a summary of a story's main components (introduction, development, climax, and conclusion) that is generated by a generative AI model.

[1859] The "text format" is a format in which the generated story is saved as textual information and is provided to the user in a manner that is easy to read.

[1860] "PDF Format" refers to a format in which the generated story is saved in Portable Document Format and provided to users for easy reading.

[1861] "Illustrations" are illustrations generated based on the content of the story and are used to enhance the visual appeal of the story.

[1862] "Speech" is the process of converting the generated story into audio data so that the user can enjoy it aurally.

[1863] The "means for reading aloud" is a function for playing the generated story as audio so that the user can listen to the story.

[1864] This invention is a system that generates an original story using a generative AI model based on a user's input of a theme, characters, and setting, and provides the story to the user. A specific embodiment of this system will be described below.

[1865] A user accesses the system using a terminal (e.g., a PC, a smartphone, or a tablet). The user opens a web browser and accesses the system's web page. The user enters information such as theme, characters, and setting into the input form, and clicks the "Generate" button. For example, if a user wants to generate "a story about a hero slaying a dragon in a fantasy world," the user enters "fantasy" as the theme, "hero, dragon, wizard" as the characters, and "medieval kingdom" as the setting.

[1866] The terminal sends the information entered by the user in JSON format to the server. The server generates a prompt sentence based on the received information and inputs it into a generative AI model (for example, OpenAI's GPT-4). The prompt sentence is in a format that includes an outline of the story and the setting. For example, the following prompt sentence is generated:

[1867] Theme: Fantasy

[1868] Characters: Hero, Dragon, Wizard

[1869] Setting: Medieval Kingdom

[1870] Summary of the story: A hero sets out on a journey to defeat a dragon. Along the way, he meets a wizard and together they defeat the dragon.

[1871] The generative AI model analyzes the prompt sentence and generates a story plot. The plot includes the main components of a story (introduction, development, climax, and conclusion). For example, the following plot is generated:

[1872] 1. The hero learns of the threat of the dragon.

[1873] 2. The hero decides to go on a journey.

[1874] 3. Along the way, you meet a wizard and get his help.

[1875] 4. A hero and a wizard face off against a dragon.

[1876] 5. The dragon is defeated and peace returns to the kingdom.

[1877] The server generates a detailed story based on the generated plot. The generative AI model converts the plot into detailed sentences and completes the entire story. For example, the following story is generated.

[1878] Once upon a time, there lived a hero in a medieval kingdom. One day, a dragon appeared in the kingdom and terrorized the people. The hero set out on a journey to defeat the dragon. Along the way, he met a wizard, and together they succeeded in defeating the dragon. Peace returned to the kingdom, and the hero was celebrated as a hero.

[1879] The server converts the generated story into a format that is easy for the user to read, such as text or PDF. For example, a Python library is used to generate the PDF file.

[1880] The server sends the converted story to the user's device. The user receives an email with a download link or sees a download link on a web page. The user can click the download link to download and read the story. The user can open the downloaded file and enjoy the story. For example, open the PDF file using a PDF reader.

[1881] The system allows users to quickly generate high-quality original stories based on the information they input, delivered in an easy-to-read format, and includes the ability to add illustrations and audio to the stories to enhance their appeal.

[1882] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1883] Step 1:

[1884] The user inputs the theme, characters, and setting.

[1885] A user uses a terminal to access the system's web page and inputs information such as theme, characters, and setting into an input form. For example, the user inputs the theme "fantasy," the characters "heroes, dragons, and wizards," and the setting "medieval kingdom." The input information becomes the basis of prompt sentences for generating a story.

[1886] Step 2:

[1887] The terminal transmits the input information to the server.

[1888] The terminal sends the information entered by the user to the server in JSON format. Specifically, the data in the input form is converted to JSON format and sent to the server using an HTTP request. The server analyzes the received data and uses it to generate a prompt text.

[1889] Step 3:

[1890] The server inputs a prompt sentence into the generative AI model.

[1891] The server generates a prompt based on the received information. For example, it generates the following prompt:

[1892] Theme: Fantasy

[1893] Characters: Hero, Dragon, Wizard

[1894] Setting: Medieval Kingdom

[1895] Summary of the story: A hero sets out on a journey to defeat a dragon. Along the way, he meets a wizard and together they defeat the dragon.

[1896] The generated prompt sentences are input into a generative AI model.

[1897] Step 4:

[1898] A generative AI model generates the story plot.

[1899] The generative AI model analyzes the input prompt sentence and generates a story plot. The plot includes the main components of a story (introduction, development, climax, and conclusion). For example, the following plot is generated:

[1900] 1. The hero learns of the threat of the dragon.

[1901] 2. The hero decides to go on a journey.

[1902] 3. Along the way, you meet a wizard and get his help.

[1903] 4. A hero and a wizard face off against a dragon.

[1904] 5. The dragon is defeated and peace returns to the kingdom.

[1905] The generated plot is returned to the server.

[1906] Step 5:

[1907] The server generates a detailed story based on the plot.

[1908] The server generates a detailed story based on the generated plot. The generative AI model converts the plot into detailed sentences and completes the entire story. For example, the following story is generated.

[1909] Once upon a time, there lived a hero in a medieval kingdom. One day, a dragon appeared in the kingdom and terrorized the people. The hero set out on a journey to defeat the dragon. Along the way, he met a wizard, and together they succeeded in defeating the dragon. Peace returned to the kingdom, and the hero was celebrated as a hero.

[1910] The generated stories are stored on a server.

[1911] Step 6:

[1912] The server converts the stories into text or PDF format.

[1913] The server converts the generated story into a format that is easy for users to read, such as text or PDF. For example, a Python library is used to generate PDF files. The converted files are then stored on the server.

[1914] Step 7:

[1915] The server transmits the generated story to the terminal.

[1916] The server sends the converted story to the user's device. The user receives an email containing a download link or sees a download link on a web page. The user clicks on the download link to download the story.

[1917] Step 8:

[1918] The user downloads and reads the story.

[1919] The user can use the device to download and read the story. The user can then open the downloaded file and enjoy the story, for example by opening the PDF file using a PDF reader.

[1920] (Application example 2)

[1921] Next, a description will be given of Application Example 2 of Form 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".

[1922] Conventional story generation systems can generate stories based on information entered by the user, but they lack the functionality to output and save the generated stories in a variety of formats. They also lack illustrations to enjoy the generated stories visually, and audio functions to enjoy them audibly. This limits the user's experience and restricts the way the story can be enjoyed.

[1923] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for a user to input a protagonist and a setting, and an AI to generate an original story based on the input, a means for outputting the generated story in a text format or a PDF format, and a means for saving the generated story. This allows the user to output and save the generated story in various formats. In addition, by further including a means for generating original illustrations based on the story generated by the AI, the story can be enjoyed visually. In addition, by further including a means for converting the story generated by the AI ​​into audio and reading it aloud, the story can be enjoyed auditorily.

[1924] A "user" is an individual or organization that uses the system to request the generation of a story.

[1925] The "protagonist" is the central character of the story and is part of the information entered by the user.

[1926] "Setting" refers to information such as the background of the story, the environment, time period, and location in which the story takes place, and is part of the information entered by the user.

[1927] "AI" stands for artificial intelligence, a technology that generates stories based on information entered by the user.

[1928] A "story" is an AI-generated text that contains a sequence of events and character actions.

[1929] A "text format" is a digital document format that is composed only of text information.

[1930] "PDF format" is an abbreviation for Portable Document Format, and is a standard file format for electronically storing documents.

[1931] "Output" refers to providing the generated narrative in a form viewable by a user.

[1932] "Preservation" refers to recording the generated stories in a digital format so that they can be reused at a later time.

[1933] "Illustrations" are illustrations or images that visually complement the content of the story.

[1934] "Speech" refers to the conversion of a textual narrative into audio data.

[1935] "Storytelling" refers to playing an audio version of a story to the user.

[1936] A system for implementing this invention includes means for a user to input a protagonist and setting and for an AI to generate an original story based on the input, means for outputting the generated story in text or PDF format, and means for saving the generated story.

[1937] System Configuration

[1938] The system uses the following hardware and software:

[1939] Hardware:

[1940] Smartphone

[1941] software:

[1942] Python

[1943] OpenAI API

[1944] FPDF Library

[1945] Processing flow

[1946] 1. Getting user input:

[1947] Through a smartphone application, users input information about the story, such as the theme, characters, and setting, which allows the system to generate a story according to the user's wishes.

[1948] 2. Generate prompt:

[1949] The server generates a prompt based on the information entered by the user, which contains instructions for the generative AI model to generate a story.

[1950] Example prompt:

[1951] Theme: Adventure

[1952] Characters: Hero, Wizard

[1953] Setting: Medieval fantasy world

[1954] Generate a story based on this information.

[1955] 3. Narrative generation:

[1956] The server uses OpenAI's API to input a prompt sentence into a generative AI model (e.g., GPT-3) to generate a story. The generated story is obtained in text format.

[1957] 4. Output and save the story:

[1958] The server outputs the generated stories in text and PDF formats for users to download, and also allows users to save the generated stories for later reuse.

[1959] Examples

[1960] If the user inputs an "adventure" theme, characters that are a "hero" and a "wizard," and a medieval fantasy world as the setting, the following prompt text will be generated:

[1961] Example prompt:

[1962] Theme: Adventure

[1963] Characters: Hero, Wizard

[1964] Setting: Medieval fantasy world

[1965] Generate a story based on this information.

[1966] By inputting this prompt into a generative AI model, an original adventure story is generated. The generated story is saved in PDF format and users can download it to read.

[1967] In this way, users can easily create original stories that fit their own desires and enjoy them in a variety of formats.

[1968] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1969] Step 1:

[1970] A user starts the smartphone application and inputs information such as the theme, characters, and setting of the story. The input information is sent to the server. The input data includes the theme (e.g., adventure), characters (e.g., hero, wizard), and setting (e.g., a medieval fantasy world).

[1971] Step 2:

[1972] The server receives the input data sent by the user and generates a prompt sentence. Specifically, it creates the following prompt sentence based on the input data.

[1973] Theme: Adventure

[1974] Characters: Hero, Wizard

[1975] Setting: Medieval fantasy world

[1976] Generate a story based on this information.

[1977] The generated prompt text is used in the next step.

[1978] Step 3:

[1979] The server sends the generated prompt sentence to the OpenAI API and generates a story using a generative AI model (e.g. GPT-3). The generative AI model takes the prompt sentence as input and outputs the text of the story. The output story is stored on the server.

[1980] Step 4:

[1981] The server outputs the generated stories in text and PDF formats. Specifically, it converts the stories into PDF format using the FPDF library. The converted PDF files are stored on the server for users to download.

[1982] Step 5:

[1983] Users download and view the stories generated through a smartphone application. Users can choose to download stories in text or PDF format. Downloaded stories are stored on the user's device and can be viewed at any time.

[1984] In this way, users can easily create original stories that fit their own desires and enjoy them in a variety of formats.

[1985] Example 3

[1986] Next, a third embodiment of the third embodiment will be described. 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".

[1987] Conventional story generation systems only generate stories based on settings entered by the user, making it difficult to provide visual and auditory enjoyment. In addition, they do not adequately address users who have difficulty reading visually or who want to do other tasks while listening to a story. This limits the user's experience and restricts how they can enjoy a story.

[1988] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1989] In this invention, the server includes a means for a user to input a protagonist and a setting, and a generative AI model to generate an original story based on the input, a means for analyzing the generated story, a means for generating illustrations based on the analysis results, a means for converting the generated story into audio, and a means for outputting the generated story, illustrations, and audio files, thereby enabling the user to enjoy the story both visually and aurally.

[1990] A "user" is an entity that uses the system to generate and output a story.

[1991] "Protagonist and setting" refers to details of the characters and scenario that the user enters as information necessary to generate the story.

[1992] A "generative AI model" is an artificial intelligence algorithm that generates original stories based on information entered by the user.

[1993] A "narrative" is a story in text form generated by a generative AI model.

[1994] "Means of analysis" refers to the process of analyzing the content of the generated story and extracting important scenes and events.

[1995] An "illustration" is an image created to visually represent a particular scene or event in the story.

[1996] A "convert-to-speech means" is a process that converts the generated narrative text into audio data.

[1997] "Output means" is the process that provides the generated story, illustrations, and audio files to the user.

[1998] This invention is a system in which a generative AI model generates an original story based on a prompt sentence entered by a user, analyzes the story to generate illustrations, and converts the story into audio for output. A specific embodiment of this system will be described below.

[1999] First, the user accesses the system interface using a terminal (e.g., a PC or a smartphone). The user inputs a prompt that indicates the theme and setting of the story. For example, the user might input "Adventure in the Magical Forest."

[2000] Next, the server receives the prompt sentence entered by the user and passes it to a generative AI model (e.g., GPT-4). The generative AI model generates a story based on the prompt sentence. The generated story is saved in text format on the server.

[2001] The server then analyzes the content of the generated story, specifically extracting scenes and important events from the story, and uses the results of this analysis for subsequent illustration generation and audio generation.

[2002] Next, the server generates illustrations using an image generation AI model (e.g., DALL-E) based on the results of the story analysis. Illustrations corresponding to each scene are generated and stored together with the story text.

[2003] The server then converts the generated story into audio using text-to-speech software (e.g., Google Text-to-Speech API), and the generated audio file is saved in a format that can be heard by the user.

[2004] Finally, the server provides the generated stories, illustrations, and audio files to the user, who can then view and enjoy these contents through their terminals.

[2005] As a concrete example, if the user enters the prompt "Adventure in the magical forest", the server will perform the following process:

[2006] 1. The server generates a story based on "Adventure in the Magical Forest" using a generative AI model (GPT-4).

[2007] 2. The server analyzes the content of the generated story and uses DALL-E to generate illustrations corresponding to each scene in the story.

[2008] 3. The server converts the story into audio using the Google Text-to-Speech API.

[2009] 4. The server provides the generated story, illustrations and audio files to the user.

[2010] This allows the user to enjoy the story both visually and aurally. The flow of the specific process in the third embodiment will be described with reference to FIG.

[2011] Step 1:

[2012] The user enters a prompt.

[2013] A user uses a terminal to access the system's interface and inputs a prompt that indicates the theme and setting of the story, for example, "An adventure in a magical forest." The input prompt is then sent to the server.

[2014] Input: The prompt text entered by the user.

[2015] Output: The prompt text sent to the server.

[2016] Step 2:

[2017] The server generates the story using a generative AI model

[2018] The server receives the prompt sentence entered by the user and passes it to a generative AI model (e.g., GPT-4). The generative AI model generates a story based on the prompt sentence. The generated story is saved in text format on the server.

[2019] Input: Prompt statement

[2020] Output: Generated story (in text format)

[2021] Step 3:

[2022] The server parses the generated story

[2023] The server analyzes the generated story content, specifically extracting scenes and important events from the story using natural language processing (NLP) algorithms, and the analysis results are used for subsequent illustration generation and audio generation.

[2024] Input: Generated story (in text format)

[2025] Output: Story analysis results (extraction of scenes and events)

[2026] Step 4:

[2027] The server generates the illustrations.

[2028] The server generates illustrations using an image generation AI model (e.g., DALL-E) based on the results of the story analysis. Illustrations corresponding to each scene are generated and stored together with the story text.

[2029] Input: Story analysis results

[2030] Output: The generated illustration

[2031] Step 5:

[2032] The server converts the story into audio.

[2033] The server converts the generated story into audio using text-to-speech software (e.g., Google Text-to-Speech API), and the generated audio file is saved in a format that can be heard by the user.

[2034] Input: Generated story (in text format)

[2035] Output: The generated audio file.

[2036] Step 6:

[2037] The server serves the generated story, illustrations, and audio files to the user.

[2038] The server provides the generated stories, illustrations, and audio files to the users, who can then view and enjoy these contents through their terminals.

[2039] Input: Generated story, illustrations, and audio files

[2040] Output: The content provided to the user (story, illustrations, audio files)

[2041] (Application example 3)

[2042] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[2043] Conventional story generation systems can generate stories based on settings entered by the user, but they lack the means to enjoy the story visually and aurally. This is also inconvenient for users who have difficulty reading visually or who want to do other tasks while listening to the story. Furthermore, there is no way to automatically generate illustrations suitable for the story, which means that the appeal of the story cannot be fully brought out.

[2044] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[2045] In this invention, the server includes a means for allowing a user to input a protagonist and setting and for an AI to generate an original story based on the input, a means for generating original illustrations based on the generated story, a means for converting the generated story into audio and reading it aloud, a means for displaying the generated illustrations and displaying the story as text, and a means for reading the generated story aloud, thereby enabling the user to enjoy the story both visually and aurally.

[2046] A "user" is an entity that uses the system to generate stories, display illustrations, and read aloud.

[2047] The "protagonist" is the character at the center of the story and can be set by the user.

[2048] "Setting" refers to information entered by the user, such as the story's background, characters, and scenario.

[2049] "AI" stands for artificial intelligence, a technology that generates stories, creates illustrations, and translates audio based on information entered by the user.

[2050] An "original story" is a story that is newly generated by AI based on settings entered by the user.

[2051] An "illustration" is a visual image generated based on the content of a story, and visually represents a scene from the story.

[2052] "Speech" is the process of converting a textual narrative into audio.

[2053] "Means for reading aloud" is a function for playing the generated story aloud and letting the user listen.

[2054] "Means of display" refers to the functionality for visually presenting the generated illustrations and narrative text to the user.

[2055] "Means for reading aloud" is a function for playing the generated story aloud and allowing the user to listen.

[2056] A system for implementing this invention includes means for a user to input a main character and setting and for an AI to generate an original story based on the input, means for generating original illustrations based on the generated story, means for converting the generated story into audio and reading it aloud, means for displaying the generated illustrations and displaying the story as text, and means for reading the generated story aloud.

[2057] System Programming

[2058] The system includes the following programs:

[2059] 1. Story generation: The server generates a story using the OpenAI API based on the prompt entered by the user. For example, if the user enters the prompt "Once upon a time in a faraway land...", the AI ​​generates a story based on this prompt.

[2060] 2. Illustration generation: The server analyzes the content of the generated story and calls the OpenAI image generation API to generate appropriate illustrations. For example, it generates an illustration for the scene "A beautiful castle on a hill."

[2061] 3. Text-to-speech: The server uses the pyttsx3 library to convert the generated story from text to speech, so that the story can be read aloud.

[2062] 4. Display and reading: The device displays the generated illustrations, displays the story as text, and reads it aloud.

[2063] Hardware and Software Used

[2064] Hardware: Servers, user devices (smartphones, tablets, etc.)

[2065] Software: OpenAI API, pyttsx3 library, image display library (e.g. PIL)

[2066] Examples

[2067] When the user enters the prompt "Once upon a time in a faraway land...", the server does the following:

[2068] 1. Story generation: Use OpenAI's API to generate a story based on a prompt.

[2069] 2. Illustration generation: Analyze the content of the generated story and generate illustrations for a scene such as "A beautiful castle on a hill."

[2070] 3. Text-to-speech: The generated story is converted into audio using the pyttsx3 library and read to the user.

[2071] 4. Display and read aloud: The generated illustrations are displayed on the user's device, and the story is displayed as text and read aloud.

[2072] Example prompt:

[2073] "Once upon a time in a faraway land, there was a beautiful castle on a hill. The castle was home to a kind king and queen who loved their people dearly..."

[2074] In this way, users can enjoy the story both visually and aurally.

[2075] The flow of the specific process in the application example 3 will be described with reference to FIG.

[2076] Step 1:

[2077] The user enters a prompt at the terminal.

[2078] Input: The prompt text that the user types (e.g., "Once upon a time in a faraway land...")

[2079] Output: The prompt text is sent to the server.

[2080] Step 2:

[2081] The server calls the OpenAI API based on the received prompt text and generates a story.

[2082] Input: Prompt statement

[2083] Data processing: Use the OpenAI API to generate a story based on the prompt.

[2084] Output: Text data of the generated story

[2085] Step 3:

[2086] The server analyzes the text data of the generated story and calls OpenAI's image generation API to generate appropriate illustrations.

[2087] Input: Text data of the generated story

[2088] Data processing: Analyze the content of the story and generate appropriate illustrations using an illustration generation API.

[2089] Output: Image data of the generated illustration

[2090] Step 4:

[2091] The server converts the text data of the generated story into audio data using the pyttsx3 library.

[2092] Input: Text data of the generated story

[2093] Data processing: Convert text data into audio data using the pyttsx3 library.

[2094] Output: Audio data of the generated story

[2095] Step 5:

[2096] The server transmits image data of the generated illustrations, text data of the story, and audio data to the terminal.

[2097] Input: Image data of the generated illustrations, text data of the story, and audio data

[2098] Output: Image data of illustrations, text data of the story, and audio data are sent to the terminal.

[2099] Step 6:

[2100] The terminal displays the received image data of the illustrations, displays the text data of the story, and plays back the audio data.

[2101] Input: Image data of illustrations, text data of the story, audio data

[2102] Specific operations: Display illustrations, display text, and play audio on the device screen.

[2103] Output: The user can enjoy the story visually and aurally.

[2104] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[2105] "Example 1"

[2106] In one embodiment of the present invention, the user inputs the protagonist and setting, and the AI ​​generates an original story based on that input. At this time, an emotion engine that recognizes the user's emotions is built in. Specifically, when the user inputs information for story generation, the emotion engine recognizes the user's emotions from the user's facial expressions, tone of voice, input speed, etc.

[2107] "Example 2"

[2108] The AI ​​adjusts the story generation based on the user's emotions recognized by the emotion engine.

[2109] For example, if the user expresses an emotion of joy, the AI ​​will generate a story with a light theme that reflects that emotion, and conversely, if the user expresses an emotion of sadness, the AI ​​will generate a story with a dark theme that reflects that emotion.

[2110] "Example 3"

[2111] In addition, the emotion engine adjusts the output format of the generated story based on the user's emotions. For example, if the user is surprised, the AI ​​will audio-read the story with suspenseful music that reflects that emotion. On the other hand, if the user is relaxed, the AI ​​will audio-read the story with calming music that reflects that emotion.

[2112] "Example 4"

[2113] In one embodiment of the present invention, original illustrations are generated based on the AI-generated story. In this case, the color tone and style of the generated illustrations are adjusted based on the user's emotions recognized by the emotion engine. For example, if the user expresses an emotion of joy, the AI ​​generates illustrations in light colors that reflect that emotion. Conversely, if the user expresses an emotion of sadness, the AI ​​generates illustrations in dark colors that reflect that emotion.

[2114] The process flow of each embodiment will be described below.

[2115] "Example 1"

[2116] Step 1: The user enters information about the protagonist, setting, etc. into the system.

[2117] Step 2: The emotion engine recognizes the user's emotions from their facial expressions, tone of voice, typing speed, etc.

[2118] Step 3: The AI ​​generates an original story based on user input and emotional information from the emotion engine.

[2119] "Example 2"

[2120] Step 1: The emotion engine recognizes the user's emotion.

[2121] Step 2: The AI ​​adjusts the story theme based on the emotional information from the emotion engine.

[2122] Step 3: Generate an original story based on the AI-tuned themes.

[2123] "Example 3"

[2124] Step 1: The emotion engine recognizes the user's emotion.

[2125] Step 2: The AI ​​adjusts the narrative output format based on the emotional information from the emotion engine.

[2126] Step 3: Output the story based on the output format adjusted by the AI.

[2127] "Example 4"

[2128] Step 1: Generate original illustrations based on the AI-generated story.

[2129] Step 2: The emotion engine recognizes the user's emotion.

[2130] Step 3: The AI ​​adjusts the color tone and style of the generated illustration based on the emotional information from the emotion engine.

[2131] Example 1

[2132] Next, a description will be given of Example 1 of the embodiment 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".

[2133] Conventional story generation systems only generate stories based on information entered by the user, and have the problem of not being able to generate stories that take into account the user's emotions and input circumstances. In addition, there are cases where the generated stories do not meet the user's expectations, which results in a lack of improvement in the user experience.

[2134] 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.

[2135] In this invention, the server includes a means for a user to input a protagonist and a setting, a means for transmitting the input information to the server, a means for the server to analyze the information received, a means for the server to analyze the user's emotions using an emotion engine, a means for the server to generate a prompt sentence based on the analysis result and transmit it to the generative AI model, a means for the generative AI model to generate an original story based on the prompt sentence, a means for the server to transmit the generated story to the user's terminal, and a means for the user to receive the generated story. This enables story generation that takes into account the user's emotions and input situation, improving the user experience.

[2136] A "user" is a person who uses the system to input the protagonist and setting and generate a story.

[2137] The "protagonist" is the central character of the story entered by the user.

[2138] "Setting" refers to information such as the background, theme, and location of a story.

[2139] A "server" is a computer system that receives and analyzes information sent by a user, and sends prompts to the generative AI model.

[2140] An "emotion engine" is software that analyzes a user's emotions from their facial expressions, tone of voice, typing speed, etc.

[2141] A "generative AI model" is an artificial intelligence model that generates an original story based on a prompt text.

[2142] A "prompt" is text sent to the generative AI model that is generated based on information entered by the user and the results of analysis by the emotion engine.

[2143] A "story" is a story that a generative AI model generates based on a prompt.

[2144] "Terminal" means a device through which a User accesses the system, inputs information, and receives generated stories.

[2145] This invention is a system in which the user inputs the protagonist and setting, and a generative AI model generates an original story based on that input. The system incorporates an emotion engine that analyzes the user's emotions, making it possible to generate a story that takes the user's emotions into account.

[2146] Hardware and Software Used

[2147] Hardware

[2148] Device: The device (e.g. computer, smartphone, tablet) through which the User enters information and receives the generated story.

[2149] Server: A computer system that receives and analyzes information sent by the user and sends prompts to the generative AI model.

[2150] Camera and microphone: Devices used to capture a user's facial expressions and tone of voice.

[2151] software

[2152] Emotion engine: Software that analyzes emotions from a user's facial expressions, tone of voice, typing speed, etc. (e.g. Microsoft Azure's Emotion API).

[2153] Generative AI model: An artificial intelligence model that generates an original story based on a prompt (e.g., OpenAI's GPT-4).

[2154] Data processing and calculation

[2155] The user enters information

[2156] A user visits a website or application and fills in a form displayed in the interface with information about the protagonist, such as their name, gender, age, likes, dislikes, setting, theme, location, etc. For example, a user might enter "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, enchanted forest."

[2157] The server receives the information

[2158] When the user completes the input and presses the send button, the terminal sends the input information to the server, which receives the information and stores it in a database.

[2159] The server analyzes the user's emotions using an emotion engine.

[2160] The server uses the device's camera and microphone to capture facial expressions, tone of voice, and input speed when the user enters information. This data is then sent to the emotion engine to analyze the user's emotions. For example, if the user is excited, that information is obtained as the analysis result.

[2161] The server sends a prompt to the generative AI model.

[2162] The server generates a prompt based on the information entered by the user and the analysis results of the emotion engine. For example, it generates a prompt like this: "The main character's name is Alice, her gender is female, and her age is 25. Alice loves adventure and hates boredom. The story is set in fantasy, the theme is friendship, and the location is a magical forest. Please generate a story in which Alice meets new friends in the magical forest and goes on an adventure together," and sends it to the generative AI model.

[2163] Generative AI models generate stories

[2164] The generative AI model generates an original story based on the prompt sent from the server. For example, it generates a story about Alice meeting new friends in a magical forest and going on an adventure together.

[2165] The server sends the generated story to the user.

[2166] The server receives the story generated by the generative AI model and sends it to the user's device. The server sends the story in an appropriate format (e.g., text format).

[2167] User receives the story

[2168] The user can receive the story generated on the device and read the story displayed on the interface. For example, the user reads "A story about Alice meeting new friends in a magical forest and going on adventures together."

[2169] The above is an embodiment of the present invention.

[2170] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2171] Step 1:

[2172] The user enters information

[2173] A user accesses a website or application and enters information such as the protagonist's name, gender, age, likes, dislikes, story setting, theme, and location into a form displayed on the interface. The entered information is sent from the terminal to the server. A specific action is when the user enters "Alice, female, 25 years old, adventure, boredom, fantasy, friendship, magical forest."

[2174] Step 2:

[2175] The server receives the information 【21...

Claims

1. A means for inputting a protagonist appearing in a story input by a user and a setting of the story; an emotion engine that recognizes the emotion of the user; A generating means for generating a plot of a story by inputting a prompt sentence that proposes a personalized story to the user based on the story and the setting into a generating AI model, and generating an original story based on the setting based on the plot; A means for outputting the story generated by the generating means; Including, The generating means adjusts the tone and theme of the original story based on the user's emotions.

2. The system of claim 1 further comprising means for generating original illustrations based on the original story generated by said generating means.

3. The system of claim 1 further comprising means for vocalizing and reading the original story generated by said generating means.

Images