system

Abstract

Provide a system. 【Solution means】 Input means for receiving keywords and themes input from a user, Generation means for generating the overall composition of a story based on the keywords and themes, First generation means for sequentially generating each chapter of the story based on the generated composition, Proposal means for proposing the next development to the user at the end of each chapter, Update means for updating the story based on the development selected by the user, AI means for generating a story by utilizing a generation AI model, Presentation means for presenting editing of the composition and publication options of the work, Publication means for automatically performing the publication procedure, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern busy lives, many people are interested in reading and creative activities, but those who have the time and skills to devise and write their own stories are limited. Also, although there are those who want to publish their creative works, the procedures are complicated and are a hurdle for many people. Furthermore, conventional automatic generation systems may not fully reflect the intentions of users, and there has been a problem that individual creativity is difficult to be exerted. It is desired to improve such a situation and provide an environment in which anyone can easily create an original novel and publish it as they wish.

Means for Solving the Problems

[0005] This invention provides a system that automatically generates a novel plot based on keywords and themes entered by the user, and then sequentially generates the story chapter by chapter based on that plot. The user can advance the story at their own discretion by selecting the next development from multiple options presented at the end of each chapter. Furthermore, this system presents options for editing and publishing the novel, and includes a procedure for automatically publishing it as an ebook, making it easy for users to publish and sell their works. This solves conventional problems and creates an environment where more people can participate in creative activities.

[0006] An "input method" is an interface for receiving keywords and themes entered by the user.

[0007] A "generation device" is a device that has the function of automatically creating a novel plot based on received keywords and themes.

[0008] The "first generation means" is a device that has the function of sequentially generating each chapter of a novel based on the generated plot.

[0009] A "proposal device" is a device that has the function of presenting the next development to the user at the end of each chapter.

[0010] An "update mechanism" is a device that has the function of updating the story based on the development selected by the user.

[0011] A "presentation means" is a device that has the function of presenting the user with editing options for the generated plot and publishing the work.

[0012] A "publishing device" is a device that automates the publishing process and has the function of distributing works.

[0013] The "second generation means" is a device that has the function of generating the next chapter based on the user's selection from a plurality of proposed options.

[0014] "Distribution method" refers to a device that has the function of distributing novels in ebook format to a designated platform. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

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

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

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

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

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

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

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio 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 audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0036] This invention is a system that generates an original novel from keywords and themes specified by the user and allows the story to progress interactively. Specific embodiments are described below.

[0037] First, the user inputs keywords and themes for the novel via their device. This information is sent from the device to the server. The server uses the received keywords and themes to run an AI generation model and create the overall plot of the novel. After the plot is generated, the server sequentially develops the story chapter by chapter, suggesting multiple story developments so that the user can choose the next development at the end of each chapter.

[0038] The user selects one of the suggested story developments on their device, and this selection is sent back to the server. Based on the user's selection, the server generates the next chapter of the novel and updates the story. This allows the user to actively participate in the progression of the narrative and enjoy a personalized reading experience.

[0039] For example, if a user selects a theme such as "science fiction" or "adventure," the server can generate a plot for "future planetary exploration." Then, if the user selects "encounter with unknown life forms" from the suggested scenarios, the server will depict the next chapter based on that selection.

[0040] Finally, once all chapters have been generated and the novel is complete, the server will present the user with options for publishing the novel. These options include setting the selling price and sales region, and publishing in ebook format. If the user chooses to publish, the server will automatically handle the process and publish the work on the specified platform.

[0041] In this way, the system based on the present invention provides an environment in which users can easily generate and publish original novels.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user uses their device to input keywords and themes for the novel. This input interface allows the user to freely enter keywords, and also provides a dropdown menu for selecting themes.

[0045] Step 2:

[0046] The terminal sends user input as data to the server. The input information is structured in a format that includes at least keywords and themes.

[0047] Step 3:

[0048] The server processes the received keywords and themes and uses an AI model to generate the overall plot. The plot automatically creates the basic storyline of the narrative.

[0049] Step 4:

[0050] The server then develops the story for the first chapter based on the generated plot. It generates elements such as main events and characters in text form, describing the beginning of the story.

[0051] Step 5:

[0052] Upon reaching the end of a chapter, the server generates several options suggesting the next development. Each of these options suggests a different storyline.

[0053] Step 6:

[0054] The terminal displays the user with options suggested by the server. The user then selects and confirms the next story development they wish to pursue from the displayed options.

[0055] Step 7:

[0056] After the device sends the user's selection to the server, the server generates the next chapter based on the selected development. This process allows for story updates that reflect the user's intent.

[0057] Step 8:

[0058] This process is repeated until all chapters are generated, at which point the entire novel is complete. The server then formats the generated novel into its final form.

[0059] Step 9:

[0060] The server presents the user with publishing options for the completed novel. These include selecting the sales price and sales region, and specifying the distribution platform.

[0061] Step 10:

[0062] Once the user selects their desired options from the presented choices, the server automatically executes the publishing process and publishes the novel on the specified platform.

[0063] (Example 1)

[0064] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] Traditional story generation systems have limited opportunities for users to directly participate in the story's themes and progression, making it difficult to provide a personalized storytelling experience. Furthermore, there is a lack of efficient means for publishing and distributing the generated stories, creating a barrier for users to widely share their own creations.

[0066] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0067] In this invention, the server includes a receiving means for receiving words and themes input by a user, a structure generation means for generating the overall structure of a story based on the words and themes, and a chapter generation means for sequentially generating each chapter of the story based on the generated overall structure. This provides an environment in which users can actively participate in the progression of the story and easily enjoy a personalized story experience, and further enables the efficient publication of the generated story.

[0068] "Reception means" refers to a device or system that has the function of receiving words and topics entered by a user.

[0069] "Structure generation means" refers to a device or system that has the function of generating the overall structure of a story based on words and themes entered by the user.

[0070] A "chapter generation means" is a device or system that has the function of sequentially generating each chapter of a story based on the generated overall structure.

[0071] A "development suggestion means" is a device or system that has the function of suggesting the next development of the story to the user at the end of each chapter.

[0072] A "story updating means" is a device or system that has the function of updating the story based on the development selected by the user.

[0073] An "option presentation means" is a device or system that has the function of presenting users with options for editing the overall structure of the story and publishing the work.

[0074] "Publication means" refers to a device or system that has the function of automatically performing the procedure of distributing a story in electronic book format to a designated information and communication infrastructure.

[0075] This system provides an environment for users to generate and publish original stories. Users input words and themes via a terminal. This input information is sent from the terminal to the server. The server has a mechanism to receive words and themes through a reception system.

[0076] The server utilizes a generative AI model based on the received words and subject matter to generate the overall structure of the story. This process employs natural language generation models such as OpenAI's GPT-3. The generated overall structure is then formed by a structure generation means.

[0077] Subsequently, the server uses a chapter generation mechanism to sequentially generate each chapter based on the overall structure. Upon completion of each chapter, a development suggestion mechanism is used to propose the next development to the user, who can choose one of the options presented on their terminal. This selection is sent back to the server, and the story is updated by a story update mechanism.

[0078] Ultimately, the server provides the user with an option to publish the story through an option presentation mechanism. If the user chooses to publish, the publishing mechanism is activated, and the story is delivered to the specified information and communication infrastructure in ebook format.

[0079] For example, if a user inputs the themes of "fantasy" and "friendship," the server will generate an overall structure such as "Two friends embark on an adventure in a medieval kingdom." Users can communicate the direction of the story to the server by providing prompts, for example, "Generate the beginning of a novel with the themes of fantasy and friendship. Imagine a scene where the main characters step into a mystical forest and an unknown adventure begins." This allows users to generate and publish individually customized stories.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The user uses a device to input specific words and topics. This defines the general theme and content of the story the user desires. The entered information is temporarily stored as digital data on the device and later prepared for transmission to the server.

[0083] Step 2:

[0084] The terminal sends the entered words and topics to the server. The transmitted data is received by the server's receiving mechanism. This data is treated as basic information for subsequent processes and is appropriately stored in the database.

[0085] Step 3:

[0086] The server runs a generative AI model based on the received words and subject matter. During this process, prompt sentences are supplied to the generative AI model, which then generates the overall structure of the story. The generated overall structure is then saved to the server in a digital format.

[0087] Step 4:

[0088] The server utilizes the overall configuration to sequentially create individual chapters via a chapter generation mechanism. At this stage, the first version of each chapter is generated. An AI model generates text based on the content of the constructed story, and the created chapters are stored on the server as digital data.

[0089] Step 5:

[0090] At the end of each chapter, the server uses a development presentation mechanism to offer the user choices for the next development of the story. The choices are sent to the user's terminal, and the user can choose the next development from the presented options. The selected option is then sent back to the server from the terminal.

[0091] Step 6:

[0092] The server updates the story using a narrative update mechanism based on the selection information sent by the user. Specifically, it reruns the generative AI model based on the selected development, and generates the next chapter. This update ensures that the story includes new developments that correspond to the user's selection.

[0093] Step 7:

[0094] Once the story is complete, the server presents the user with publishing options through an options presentation system. These include the publishing format, pricing, and platform selection. Based on the user's selection, the server automatically adjusts to the most suitable publishing option.

[0095] Step 8:

[0096] In the final step, the server uses a publishing mechanism to distribute the story to the designated information and communication infrastructure. During this process, the story is converted into an electronic book format and distributed to the selected platform. Once publication is complete, users can verify that the work is accessible worldwide.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] There is a need for a novel generation system that allows users to easily enjoy individual story experiences and interactively advance the narrative through their own choices. Furthermore, a challenge lies in providing a system that allows for the easy publication and sharing of these generated stories as ebooks.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes an input means for receiving keywords and themes entered by a user, a first generation means for sequentially generating each chapter of a story based on the generated structure, and an AI means for generating a story using a generation AI model. This allows users to enjoy a story experience based on individual themes and publish and share it as an electronic document.

[0102] "Keywords" are important words or concepts that users input to concretize the content or theme of a story.

[0103] A "theme" is the main topic or subject matter that runs throughout the entire story, and it is a factor that determines the direction of the narrative.

[0104] "The overall structure of the story" refers to the framework of the narrative generated based on information provided by the user, and includes a consistent plot that encompasses the flow of chapters and episodes.

[0105] "Generative means" refers to a technical method that concretizes the story based on the overall structure and derives the next development in response to the user's interactive input.

[0106] The "first generation means" is a device or method for sequentially creating each chapter based on the overall structure of the generated story.

[0107] A "suggestion method" is a technique that presents the user with multiple options at the end of each chapter of a story, allowing them to choose the next development.

[0108] "AI methods" refer to techniques that use generative AI models to automatically generate story structures and chapters.

[0109] "Delivery means" refers to a device or method that has the function of delivering a completed story in the form of an electronic document to a desired base or platform.

[0110] This invention relates to a story generation system consisting of a user terminal and a server, which provides a function that allows users to interactively generate stories and publish them as ebooks.

[0111] First, the user inputs the theme and keywords of the novel via a device such as a smartphone. This information is sent to a server via the network. Based on the received keywords and themes, the server uses a generative AI model to create the overall structure of the story. This AI model might use, for example, the OpenAI API. The AI ​​analyzes the input information and constructs a coherent framework for the story.

[0112] The generated overall structure is further broken down on the server, and each chapter is generated sequentially. At the end of each chapter, the user can choose the next development from the suggested options. In this way, the story is customized according to the user's choices. Through this communication, the user can become deeply involved in the story and enjoy a personalized experience. The selected development is sent back to the server, and the next chapter is generated.

[0113] The server also has the means to deliver the generated stories in electronic document format to a specified platform. This allows users to automatically share their created stories with others as ebooks. For example, if a user selects the themes "fantasy" and "magic revolution," and then chooses the plot "adventuring for ancient treasures," the AI ​​will describe how the next chapter will unfold based on that information.

[0114] Examples of prompt statements include the following:

[0115] Create a fantasy novel plot based on the following theme: "Magic Revolution".

[0116] Start the story with the main plot point as an adventure to discover ancient treasures.

[0117] Thus, the system of the present invention provides an environment in which users can easily visualize stories and generate their own unique narrative experiences.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The user uses a terminal to input the novel's theme and keywords. The entered information is processed as text data and sent to the server over the network.

[0121] Step 2:

[0122] The server analyzes the received theme and keywords. Based on this, it forms a prompt message and sends it to the generating AI model. This prompt message contains instructions for generating the overall structure of the story.

[0123] Step 3:

[0124] The generative AI model generates the overall structure of the story based on the prompt messages received from the server. The generated structure is returned to the server as data containing the storyline and key plot elements.

[0125] Step 4:

[0126] The server then concretizes each chapter of the story based on the overall structure returned by the AI ​​model. It breaks down the story chapter by chapter and generates sub-plans for each chapter. The results are processed sequentially and sent to the user as choices for the next chapter.

[0127] Step 5:

[0128] The user reviews and selects from the options presented on their device for the next development. This selection information is then sent back to the server and used as data input for the next story development.

[0129] Step 6:

[0130] The server updates the chapter based on the user's selection. The newly obtained selection is converted back into a prompt and sent to the generating AI model to prepare the basic data for generating the next chapter.

[0131] Step 7:

[0132] Once all chapters have been generated, the server compiles the completed story into an electronic document and delivers it to the designated distribution platform. This output is in a publicly shareable format, allowing users to share the story with others.

[0133] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0134] The present invention is a system that generates an original novel from keywords and themes specified by the user, and interactively advances the story, and further includes an emotion engine that recognizes the user's emotions and adjusts the story's development and tone.

[0135] First, the user inputs keywords and themes for the novel using their device. This information is sent from the device to the server. The server runs an AI generation model based on the received keywords and themes to create the overall plot of the novel. After the plot is generated, the server generates the story chapter by chapter and suggests the next development to the user at the end of each chapter. At this time, the emotion engine detects the user's emotions and customizes the suggested developments based on that information.

[0136] When a user selects a scenario from those presented on their device, that selection is sent to the server, which can then generate the next chapter based on the user's selection and emotional state. For example, if the user chooses "fantasy" and "adventure" as their themes, the server can generate a plot for "an adventure story in a magical land." If the user then selects the scenario "encountering a dragon," and the emotion engine determines that the user is excited, the server will generate an action-packed chapter that reflects that excitement.

[0137] Furthermore, once all chapters have been generated and the story is complete, the server presents the user with publishing options for their novel. The emotion engine suggests a promotional strategy tailored to the user's emotional state, which is also reflected in the sales strategy for the work. Finally, the server automatically handles the publishing process according to the user's selected options and publishes the work on the designated platform.

[0138] In this way, users can obtain a personalized creative experience through a system that allows for emotionally-driven story customization and easy publishing.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] Users input keywords and themes for their novels through their devices. The input screen is designed for intuitive use and allows for the combination of multiple themes and keywords.

[0142] Step 2:

[0143] The terminal sends user input information to the server. This information is registered in a database and used in subsequent processes.

[0144] Step 3:

[0145] The server uses the received keywords and themes to activate an AI generation model and generate the overall plot. During plot creation, settings and characters appropriate to the theme are automatically generated.

[0146] Step 4:

[0147] The server generates the first chapter. The generated chapter includes the introduction to the story and the main characters, and the story unfolds based on this.

[0148] Step 5:

[0149] At the end of the generated chapter, the server presents the user with options for the next development. Here, the emotion engine analyzes the user's emotions and customizes and sets the options accordingly.

[0150] Step 6:

[0151] The terminal displays suggested options received from the server to the user. The user selects the storyline that interests them most and confirms their choice.

[0152] Step 7:

[0153] The user's selection is sent from the terminal to the server. The server takes that selection and the results of the emotion engine's analysis into consideration and generates the next chapter. This process is repeated until the story is completed.

[0154] Step 8:

[0155] Once all chapters of the story are complete, the server automatically edits the novel and checks for consistency throughout.

[0156] Step 9:

[0157] The server presents the user with publishing options. The sentiment engine is also used here to suggest a promotional strategy based on the user's emotions.

[0158] Step 10:

[0159] When a user selects a publishing option, the server automatically executes the publishing process and publishes the novel in ebook format to the specified platform.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] In recent years, there has been a growing demand for personalized content tailored to individual user preferences. However, there is a lack of systems that can generate stories based on user-specified themes and keywords, while also considering the user's emotional state. Furthermore, there is a need for efficient means of publishing these generated works. This invention aims to solve these problems by interactively generating stories that reflect the user's intentions and emotions, and automatically publishing them.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes receiving means for receiving instructions and themes input by the user, generating means for generating a story outline based on the instructions and themes, and chapter generating means for sequentially generating each chapter of the story based on the generated outline. This makes it possible to generate interactive novels that reflect the individual preferences and emotional states of the user, and to effectively publish the resulting works.

[0165] "Receiving means" refers to the part of the system that has communication functions to receive instructions and topics from the user and process them within the system.

[0166] The "generative means" refers to the part that constructs the framework based on the received instructions and theme, and has the function of outlining the basic flow and outline of the story.

[0167] The "chapter generation mechanism" is the part that sequentially forms each chapter based on the generated outline, thereby detailing the story.

[0168] "Suggestion mechanism" refers to the part of the story that presents the next development to the user and offers them choices.

[0169] The "adjustment mechanism" refers to the part that dynamically updates the story's development based on user choices and emotional data, and has the function of adapting the tone and flow of the story.

[0170] "Display means" refers to the part that has an interface function to present the generated outline and publication options to the user.

[0171] "Automation means" refers to the part that has the function of executing a process to efficiently carry out the publishing process of the generated story and provide it to a designated platform.

[0172] The "emotional response generation mechanism" is a component that has the function of adjusting the content and development of the story based on the user's emotional state, and plays a role in supporting the individualization of the story.

[0173] "Means of delivery" refers to the part that has communication and distribution functions for transmitting the completed story to an external platform in electronic publishing format.

[0174] This invention is a system that allows users to generate original stories and easily publish them. This system mainly consists of a server and terminals, and dynamically generates stories based on user input and customizes the story according to the user's emotional state.

[0175] First, the user uses a terminal to input the instructions and theme of their desired story. This input is sent from the terminal to the server via a secure communication method (e.g., HTTPS). On the server, a generative AI model (for example, GPT-3 is a common model) is used to construct the story's framework based on the received instructions and theme. This generative AI model has advanced natural language processing capabilities and is capable of generating a wide variety of stories.

[0176] Next, the server uses a chapter generation mechanism based on the generated framework to detail the story chapter by chapter. At the end of each chapter, the server presents the user with a choice (prompt) to select the next course of action. For example, "You begin a new adventure in the land of magic. Choose one of the following options: 1. Confront the dragon, 2. Enter the Cave of Wisdom, 3. Explore the Magic Tree."

[0177] In this process, the server utilizes an emotion engine to detect the user's emotions. It analyzes data obtained from the camera and microphone connected to the device to understand the user's emotional state (for example, whether they are excited or not). Based on this information, an emotion response generation mechanism works to adjust and generate the content and tone of the next chapter.

[0178] When the story is complete, the server uses automated means to present the user with publishing options. Based on the option selected by the user, the service provider delivers the story in electronic publishing format to an external platform (e.g., an ebook store).

[0179] As described above, users can use this system to create and effectively distribute interactive, personalized stories. The system can provide a seamless and flexible process from story generation to publication.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The user uses a terminal to input the story's instructions and theme. This input is captured as text data, and the terminal prepares this data for transmission to the server. The input data is used as the requirements for generating the story.

[0183] Step 2:

[0184] The terminal sends instructions and subject data to the server. The HTTPS protocol is used for communication, ensuring security. The transmitted data is stored in a database on the server side and becomes input data for the generated AI model.

[0185] Step 3:

[0186] The server runs a generative AI model and generates a story outline based on the received instructions and theme. Here, machine learning algorithms are used to process the data and generate the text data of the outline. This generated outline will be refined in the next step.

[0187] Step 4:

[0188] The server operates the chapter generation mechanism based on the framework, generating the story chapter by chapter. Each chapter is constructed individually as text data, gradually assembling the entire story. The output is the text of each chapter.

[0189] Step 5:

[0190] At the end of each chapter, the server presents the user with a prompt (a choice of the next step). Once the user makes a choice, that selection is sent to the server. The prompt is text designed to visualize the progression of the story.

[0191] Step 6:

[0192] The server uses an emotion engine to analyze emotional data sent from the terminal. Specifically, it uses data obtained from the camera and microphone to analyze the user's facial expressions and tone of voice, and quantifies their emotional state. The analyzed emotional data is used as adjustment data for the story.

[0193] Step 7:

[0194] The server generates the next chapter based on selection data and emotion data. Utilizing emotion-responsive generation methods, it adjusts the tone and content of the story according to the user's emotions, generating chapters based on the user's choices. The output is the adjusted chapter text.

[0195] Step 8:

[0196] Once the story is complete, the server uses automated mechanisms to present the user with publishing options. Based on the user's selection, preparations are made to distribute the story to external platforms through the provided means. The user's choice is crucial in determining the publishing format.

[0197] Step 9:

[0198] The server provides the story to an external platform in electronic publishing format according to the selected publishing option. This process automatically handles conversion to the ebook file format and uploading to the publishing platform. The output is a published ebook.

[0199] (Application Example 2)

[0200] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0201] Providing personalized experiences based on user input is challenging in story generation. Furthermore, there is a need to enhance user satisfaction by dynamically changing the story in response to user emotions. Additionally, there is a lack of automated processes for easily publishing generated stories.

[0202] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0203] In this invention, the server includes a receiving means, a story framework generation means, and an emotion recognition means. This enables the generation and automatic publication of personalized stories that correspond to the user's emotional state based on user input.

[0204] A "receiving means" is a device that has the function of accurately receiving data and subject matter entered by the user.

[0205] The "first generation means" is a device that has the function of forming the framework of a story based on the received data and theme.

[0206] The "second generation means" is a device that has the function of sequentially generating each part of the story based on the generated framework.

[0207] A "presentation method" is a device that has the function of suggesting the next development to the user at the end of each part of the story.

[0208] An "emotion recognition means" is a device that detects the user's emotional state and has the function of adjusting the story's progression accordingly.

[0209] An "update mechanism" is a function that updates the story based on the user's chosen plot developments and emotional state.

[0210] "Selection options" refers to a function that presents users with options for editing the story's framework and publishing the work.

[0211] "Distribution method" refers to a device that has the function of transmitting the generated story in electronic format to a specified medium.

[0212] The system for realizing this invention consists of a user terminal and a server. The user uses a smartphone or other computer device to input keywords and themes into the terminal's interface. This information is transmitted from the terminal to the server.

[0213] The server first receives data and a subject from the user via a "receiving means." Then, using a "first generation means," it generates the framework of a story based on the received information. Specifically, a generation AI model processes prompt sentences and automatically generates the basic structure of the story. For example, OpenAI's GPT-3 can be used as the AI ​​model.

[0214] Next, the "second generation means" sequentially generates each part of the story chapter by chapter based on the generated framework. During this process, the "emotion recognition means" detects emotions in real time using the user's device camera and sends the data to the server. Software such as Microsoft® Azure® Face API can be used for emotion recognition. Through this process, the story's development and tone are adjusted according to the user's emotions.

[0215] When a user selects the next development based on the "presentation method" presented at the end of each chapter, that information is sent back to the server. The "update method" then generates the next part of the story based on that selection and emotional data.

[0216] Furthermore, the "Selection Method" presents the user with editing and publishing options once the story is complete. If the user selects a specific publishing option, the story is automatically distributed to the specified medium in electronic format via the "Distribution Method."

[0217] For example, if a user enters "I want to enjoy an adventure story in a magical land" as a prompt themed around "fantasy" and "adventure," the system will generate a dynamic fantasy story based on that information. If the system recognizes that the user is excited, the story will unfold with action and surprises.

[0218] Example of a prompt:

[0219] "The theme is 'adventure.' The keywords are 'dragons' and 'magic.' Start creating a fantasy story that incorporates emotionally engaging plot development."

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] The user enters keywords and themes into the interface via their device. The device sends this information to the server as a prompt. The entered prompt includes themes and keywords such as "adventure" or "magic."

[0223] Step 2:

[0224] The server receives prompt messages sent by the user via its "receiving mechanism." Based on the received prompt messages, it performs analysis and stores them as information that forms the basis of the story.

[0225] Step 3:

[0226] Based on the information received by the server's "first generation means," a generative AI model is used to generate the framework of the story. Specifically, prompt text is input to a generative AI model such as GPT-3, and the basic structure of the story is output. At this time, appropriate settings and characters are automatically created based on keywords and themes.

[0227] Step 4:

[0228] The server's "second generation mechanism" sequentially generates chapters for each story based on the generated framework. At this time, the AI ​​model materializes the framework into a detailed storyline and constructs the story development for each chapter.

[0229] Step 5:

[0230] At the end of each chapter's generation, the server uses a "presentation mechanism" to offer the user options for the next development. The terminal receives the output from the generated AI model and presents the user with multiple choices.

[0231] Step 6:

[0232] The user selects from the options presented on the device. Furthermore, the device's camera analyzes the user's emotions in real time, and emotion data is acquired using an emotion recognition API. The device then sends the user's selection and emotion data to the server.

[0233] Step 7:

[0234] The server's "emotion recognition" and "update" mechanisms receive user selections and emotional data, and generate the next chapter based on the new data. The story's development and tone are adjusted based on the emotional data.

[0235] Step 8:

[0236] Once the entire story has been generated, the server presents the user with editing and publishing options through a "selection mechanism." The terminal displays this information to the user and asks for their choice.

[0237] Step 9:

[0238] When the user selects the distribution or publication option, the server's "distribution method" automatically distributes the story in electronic format to the specified platform. The terminal is notified when the entire process is complete.

[0239] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0240] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0241] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0242] [Second Embodiment]

[0243] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0244] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0245] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0246] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0247] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0248] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0249] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0250] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0251] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0252] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0253] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0254] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0255] This invention is a system that generates an original novel from keywords and themes specified by the user and allows the story to progress interactively. Specific embodiments are described below.

[0256] First, the user inputs keywords and themes for the novel via their device. This information is sent from the device to the server. The server uses the received keywords and themes to run an AI generation model and create the overall plot of the novel. After the plot is generated, the server sequentially develops the story chapter by chapter, suggesting multiple story developments so that the user can choose the next development at the end of each chapter.

[0257] The user selects one of the suggested story developments on their device, and this selection is sent back to the server. Based on the user's selection, the server generates the next chapter of the novel and updates the story. This allows the user to actively participate in the progression of the narrative and enjoy a personalized reading experience.

[0258] For example, if a user selects a theme such as "science fiction" or "adventure," the server can generate a plot for "future planetary exploration." Then, if the user selects "encounter with unknown life forms" from the suggested scenarios, the server will depict the next chapter based on that selection.

[0259] Finally, once all chapters have been generated and the novel is complete, the server will present the user with options for publishing the novel. These options include setting the selling price and sales region, and publishing in ebook format. If the user chooses to publish, the server will automatically handle the process and publish the work on the specified platform.

[0260] In this way, the system based on the present invention provides an environment in which users can easily generate and publish original novels.

[0261] The following describes the processing flow.

[0262] Step 1:

[0263] The user uses their device to input keywords and themes for the novel. This input interface allows the user to freely enter keywords, and also provides a dropdown menu for selecting themes.

[0264] Step 2:

[0265] The terminal sends user input as data to the server. The input information is structured in a format that includes at least keywords and themes.

[0266] Step 3:

[0267] The server processes the received keywords and themes and uses an AI model to generate the overall plot. The plot automatically creates the basic storyline of the narrative.

[0268] Step 4:

[0269] The server then develops the story for the first chapter based on the generated plot. It generates elements such as main events and characters in text form, describing the beginning of the story.

[0270] Step 5:

[0271] Upon reaching the end of a chapter, the server generates several options suggesting the next development. Each of these options suggests a different storyline.

[0272] Step 6:

[0273] The terminal displays the user with options suggested by the server. The user then selects and confirms the next story development they wish to pursue from the displayed options.

[0274] Step 7:

[0275] After the device sends the user's selection to the server, the server generates the next chapter based on the selected development. This process allows for story updates that reflect the user's intent.

[0276] Step 8:

[0277] This process is repeated until all chapters are generated, completing the entire novel. The server then refines the generated novel into its final form.

[0278] Step 9:

[0279] The server presents the user with the publication options for the completed novel. This includes the selection of the selling price, the sales region, and the specification of the distribution platform.

[0280] Step 10:

[0281] When the user selects the desired items from the presented options, the server automatically executes the publication procedure and publishes the novel on the specified platform.

[0282] (Example 1)

[0283] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] In a conventional story generation system, there is a problem that the opportunity for the user to directly participate in the theme and progress of the story is limited, and it is difficult to provide a personalized story experience. In addition, there is a lack of means to efficiently publish and distribute the generated story, which has become an obstacle for the user to widely publish their own story.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0286] In this invention, the server includes a reception means for receiving the words and themes input from the user, a configuration generation means for generating the overall configuration of the story based on the words and themes, and a chapter generation means for sequentially generating each chapter of the story based on the generated overall configuration. Thereby, an environment is provided in which the user can actively participate in the progress of the story and easily enjoy a personalized story experience, and furthermore, the generated story can be efficiently published.

[0287] "Reception means" refers to a device or system that has the function of receiving words and topics entered by a user.

[0288] "Structure generation means" refers to a device or system that has the function of generating the overall structure of a story based on words and themes entered by the user.

[0289] A "chapter generation means" is a device or system that has the function of sequentially generating each chapter of a story based on the generated overall structure.

[0290] A "development suggestion means" is a device or system that has the function of suggesting the next development of the story to the user at the end of each chapter.

[0291] A "story updating means" is a device or system that has the function of updating the story based on the development selected by the user.

[0292] An "option presentation means" is a device or system that has the function of presenting users with options for editing the overall structure of the story and publishing the work.

[0293] "Publication means" refers to a device or system that has the function of automatically performing the procedure of distributing a story in electronic book format to a designated information and communication infrastructure.

[0294] This system provides an environment for users to generate and publish original stories. Users input words and themes via a terminal. This input information is sent from the terminal to the server. The server has a mechanism to receive words and themes through a reception system.

[0295] The server utilizes a generative AI model based on the received words and subject matter to generate the overall structure of the story. This process employs natural language generation models such as OpenAI's GPT-3. The generated overall structure is then formed by a structure generation mechanism.

[0296] Subsequently, the server uses a chapter generation mechanism to sequentially generate each chapter based on the overall structure. Upon completion of each chapter, a development suggestion mechanism is used to propose the next development to the user, who can choose one of the options presented on their terminal. This selection is sent back to the server, and the story is updated by a story update mechanism.

[0297] Ultimately, the server provides the user with an option to publish the story through an option presentation mechanism. If the user chooses to publish, the publishing mechanism is activated, and the story is delivered to the specified information and communication infrastructure in ebook format.

[0298] For example, if a user inputs the themes of "fantasy" and "friendship," the server will generate an overall structure such as "Two friends embark on an adventure in a medieval kingdom." Users can communicate the direction of the story to the server by providing prompts, for example, "Generate the beginning of a novel with the themes of fantasy and friendship. Imagine a scene where the main characters step into a mystical forest and an unknown adventure begins." This allows users to generate and publish individually customized stories.

[0299] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0300] Step 1:

[0301] The user uses a device to input specific words and topics. This defines the general theme and content of the story the user desires. The entered information is temporarily stored as digital data on the device and later prepared for transmission to the server.

[0302] Step 2:

[0303] The terminal sends the entered words and topics to the server. The transmitted data is received by the server's receiving mechanism. This data is treated as basic information for subsequent processes and is appropriately stored in the database.

[0304] Step 3:

[0305] The server executes the generation AI model based on the received words and themes. In this process, the prompt sentence is supplied to the generation AI model, and the model generates the overall composition of the story. The generated overall composition is saved in the server in digital format.

[0306] Step 4:

[0307] The server utilizes the overall composition and sequentially creates individual chapters through the chapter generation means. At this stage, the first version of each chapter is generated. The AI model generates articles based on the content of the constructed story, and the created chapters are saved in the server as digital data.

[0308] Step 5:

[0309] When each chapter ends, the server uses the development presentation means to provide the user with options for the next development of the story. The options are sent to the user's terminal, and the user can choose the next development from the presented options. The selected option is sent back to the server from the terminal.

[0310] Step 6:

[0311] The server updates the story using the story update means based on the selection information sent from the user. Specifically, the generation AI model is re-executed based on the selected development, and the next chapter is generated. This update causes the story to include a new development according to the user's selection.

[0312] Step 7:

[0313] When the story is completed, the server presents the story's publishing options to the user through the option presentation means. This includes the story's publishing format, price, and platform selection. According to the user's selection, the optimal publishing option is automatically adjusted by the server.

[0314] Step 8:

[0315] In the final step, the server uses a publishing mechanism to distribute the story to the designated information and communication infrastructure. During this process, the story is converted into an electronic book format and distributed to the selected platform. Once publication is complete, users can verify that the work is accessible worldwide.

[0316] (Application Example 1)

[0317] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0318] There is a need for a novel generation system that allows users to easily enjoy individual story experiences and interactively advance the narrative through their own choices. Furthermore, a challenge lies in providing a system that allows for the easy publication and sharing of these generated stories as ebooks.

[0319] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0320] In this invention, the server includes an input means for receiving keywords and themes entered by a user, a first generation means for sequentially generating each chapter of a story based on the generated structure, and an AI means for generating a story using a generation AI model. This allows users to enjoy a story experience based on individual themes and publish and share it as an electronic document.

[0321] "Keywords" are important words or concepts that users input to concretize the content or theme of a story.

[0322] A "theme" is the main topic or subject matter that runs throughout the entire story, and it is a factor that determines the direction of the narrative.

[0323] "The overall structure of the story" refers to the framework of the narrative generated based on information provided by the user, and includes a consistent plot that encompasses the flow of chapters and episodes.

[0324] "Generative means" refers to a technical method that concretizes the story based on the overall structure and derives the next development in response to the user's interactive input.

[0325] The "first generation means" is a device or method for sequentially creating each chapter based on the overall structure of the generated story.

[0326] A "suggestion method" is a technique that presents the user with multiple options at the end of each chapter of a story, allowing them to choose the next development.

[0327] "AI methods" refer to techniques that use generative AI models to automatically generate story structures and chapters.

[0328] "Delivery means" refers to a device or method that has the function of delivering a completed story in the form of an electronic document to a desired base or platform.

[0329] This invention relates to a story generation system consisting of a user terminal and a server, which provides a function that allows users to interactively generate stories and publish them as ebooks.

[0330] First, the user inputs the theme and keywords of the novel via a device such as a smartphone. This information is sent to a server via the network. Based on the received keywords and themes, the server uses a generative AI model to create the overall structure of the story. This AI model might use, for example, the OpenAI API. The AI ​​analyzes the input information and constructs a coherent framework for the story.

[0331] The generated overall structure is further broken down on the server, and each chapter is generated sequentially. At the end of each chapter, the user can choose the next development from the suggested options. In this way, the story is customized according to the user's choices. Through this communication, the user can become deeply involved in the story and enjoy a personalized experience. The selected development is sent back to the server, and the next chapter is generated.

[0332] The server also has the means to deliver the generated stories in electronic document format to a specified platform. This allows users to automatically share their created stories with others as ebooks. For example, if a user selects the themes "fantasy" and "magic revolution," and then chooses the plot "adventuring for ancient treasures," the AI ​​will describe how the next chapter will unfold based on that information.

[0333] Examples of prompt statements include the following:

[0334] Create a fantasy novel plot based on the following theme: "Magic Revolution".

[0335] Start the story with the main plot point as an adventure to discover ancient treasures.

[0336] Thus, the system of the present invention provides an environment in which users can easily visualize stories and generate their own unique narrative experiences.

[0337] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0338] Step 1:

[0339] The user uses a terminal to input the novel's theme and keywords. The entered information is processed as text data and sent to the server over the network.

[0340] Step 2:

[0341] The server analyzes the received theme and keywords. Based on this, it forms a prompt message and sends it to the generating AI model. This prompt message contains instructions for generating the overall structure of the story.

[0342] Step 3:

[0343] The generative AI model generates the overall structure of the story based on the prompt messages received from the server. The generated structure is returned to the server as data containing the storyline and key plot elements.

[0344] Step 4:

[0345] The server then concretizes each chapter of the story based on the overall structure returned by the AI ​​model. It breaks down the story chapter by chapter and generates sub-plans for each chapter. The results are processed sequentially and sent to the user as choices for the next chapter.

[0346] Step 5:

[0347] The user reviews and selects from the options presented on their device for the next development. This selection information is then sent back to the server and used as data input for the next story development.

[0348] Step 6:

[0349] The server updates the chapter based on the user's selection. The newly obtained selection is converted back into a prompt and sent to the generating AI model to prepare the basic data for generating the next chapter.

[0350] Step 7:

[0351] Once all chapters have been generated, the server compiles the completed story into an electronic document and delivers it to the designated distribution platform. This output is in a publicly shareable format, allowing users to share the story with others.

[0352] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0353] The present invention is a system that generates an original novel from keywords and themes specified by the user, and interactively advances the story, and further includes an emotion engine that recognizes the user's emotions and adjusts the story's development and tone.

[0354] First, the user inputs keywords and themes for the novel using their device. This information is sent from the device to the server. The server runs an AI generation model based on the received keywords and themes to create the overall plot of the novel. After the plot is generated, the server generates the story chapter by chapter and suggests the next development to the user at the end of each chapter. At this time, the emotion engine detects the user's emotions and customizes the suggested developments based on that information.

[0355] When a user selects a scenario from those presented on their device, that selection is sent to the server, which can then generate the next chapter based on the user's selection and emotional state. For example, if the user chooses "fantasy" and "adventure" as their themes, the server can generate a plot for "an adventure story in a magical land." If the user then selects the scenario "encountering a dragon," and the emotion engine determines that the user is excited, the server will generate an action-packed chapter that reflects that excitement.

[0356] Furthermore, once all chapters have been generated and the story is complete, the server presents the user with publishing options for their novel. The emotion engine suggests a promotional strategy tailored to the user's emotional state, which is also reflected in the sales strategy for the work. Finally, the server automatically handles the publishing process according to the user's selected options and publishes the work on the designated platform.

[0357] In this way, users can obtain a personalized creative experience through a system that allows for emotionally-driven story customization and easy publishing.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] Users input keywords and themes for their novels through their devices. The input screen is designed for intuitive use and allows for the combination of multiple themes and keywords.

[0361] Step 2:

[0362] The terminal sends user input information to the server. This information is registered in a database and used in subsequent processes.

[0363] Step 3:

[0364] The server uses the received keywords and themes to activate an AI generation model and generate the overall plot. During plot creation, settings and characters appropriate to the theme are automatically generated.

[0365] Step 4:

[0366] The server generates the first chapter. The generated chapter includes the introduction to the story and the main characters, and the story unfolds based on this.

[0367] Step 5:

[0368] At the end of the generated chapter, the server presents the user with options for the next development. Here, the emotion engine analyzes the user's emotions and customizes and sets the options accordingly.

[0369] Step 6:

[0370] The terminal displays suggested options received from the server to the user. The user selects the storyline that interests them most and confirms their choice.

[0371] Step 7:

[0372] The user's selection is sent from the terminal to the server. The server takes that selection and the results of the emotion engine's analysis into consideration and generates the next chapter. This process is repeated until the story is completed.

[0373] Step 8:

[0374] Once all chapters of the story are complete, the server automatically edits the novel and checks for consistency throughout.

[0375] Step 9:

[0376] The server presents the user with publishing options. The sentiment engine is also used here to suggest a promotional strategy based on the user's emotions.

[0377] Step 10:

[0378] When a user selects a publishing option, the server automatically executes the publishing process and publishes the novel in ebook format to the specified platform.

[0379] (Example 2)

[0380] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0381] In recent years, there has been a growing demand for personalized content tailored to individual user preferences. However, there is a lack of systems that can generate stories based on user-specified themes and keywords, while also considering the user's emotional state. Furthermore, there is a need for efficient means of publishing these generated works. This invention aims to solve these problems by interactively generating stories that reflect the user's intentions and emotions, and automatically publishing them.

[0382] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0383] In this invention, the server includes receiving means for receiving instructions and themes input by the user, generating means for generating a story outline based on the instructions and themes, and chapter generating means for sequentially generating each chapter of the story based on the generated outline. This makes it possible to generate interactive novels that reflect the individual preferences and emotional states of the user, and to effectively publish the resulting works.

[0384] "Receiving means" refers to the part of the system that has communication functions to receive instructions and topics from the user and process them within the system.

[0385] The "generative means" refers to the part that constructs the framework based on the received instructions and theme, and has the function of outlining the basic flow and outline of the story.

[0386] The "chapter generation mechanism" is the part that sequentially forms each chapter based on the generated outline, thereby detailing the story.

[0387] "Suggestion mechanism" refers to the part of the story that presents the next development to the user and offers them choices.

[0388] The "adjustment mechanism" refers to the part that dynamically updates the story's development based on user choices and emotional data, and has the function of adapting the tone and flow of the story.

[0389] "Display means" refers to the part that has an interface function to present the generated outline and publication options to the user.

[0390] "Automation means" refers to the part that has the function of executing a process to efficiently carry out the publishing process of the generated story and provide it to a designated platform.

[0391] The "emotional response generation mechanism" is a component that has the function of adjusting the content and development of the story based on the user's emotional state, and plays a role in supporting the individualization of the story.

[0392] "Means of delivery" refers to the part that has communication and distribution functions for transmitting the completed story to an external platform in electronic publishing format.

[0393] This invention is a system that allows users to generate original stories and easily publish them. This system mainly consists of a server and terminals, and dynamically generates stories based on user input and customizes the story according to the user's emotional state.

[0394] First, the user uses a terminal to input the instructions and theme of their desired story. This input is sent from the terminal to the server via a secure communication method (e.g., HTTPS). On the server, a generative AI model (for example, GPT-3 is a common model) is used to construct the story's framework based on the received instructions and theme. This generative AI model has advanced natural language processing capabilities and is capable of generating a wide variety of stories.

[0395] Next, the server uses a chapter generation mechanism based on the generated framework to detail the story chapter by chapter. At the end of each chapter, the server presents the user with a choice (prompt) to select the next course of action. For example, "You begin a new adventure in the land of magic. Choose one of the following options: 1. Confront the dragon, 2. Enter the Cave of Wisdom, 3. Explore the Magic Tree."

[0396] In this process, the server utilizes an emotion engine to detect the user's emotions. It analyzes data obtained from the camera and microphone connected to the device to understand the user's emotional state (for example, whether they are excited or not). Based on this information, an emotion response generation mechanism works to adjust and generate the content and tone of the next chapter.

[0397] When the story is complete, the server uses automated means to present the user with publishing options. Based on the option selected by the user, the service provider delivers the story in electronic publishing format to an external platform (e.g., an ebook store).

[0398] As described above, users can use this system to create and effectively distribute interactive, personalized stories. The system can provide a seamless and flexible process from story generation to publication.

[0399] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0400] Step 1:

[0401] The user uses a terminal to input the story's instructions and theme. This input is captured as text data, and the terminal prepares this data for transmission to the server. The input data is used as the requirements for generating the story.

[0402] Step 2:

[0403] The terminal sends instructions and subject data to the server. The HTTPS protocol is used for communication, ensuring security. The transmitted data is stored in a database on the server side and becomes input data for the generated AI model.

[0404] Step 3:

[0405] The server runs a generative AI model and generates a story outline based on the received instructions and theme. Here, machine learning algorithms are used to process the data and generate the text data of the outline. This generated outline will be refined in the next step.

[0406] Step 4:

[0407] The server operates the chapter generation mechanism based on the framework, generating the story chapter by chapter. Each chapter is constructed individually as text data, gradually assembling the entire story. The output is the text of each chapter.

[0408] Step 5:

[0409] At the end of each chapter, the server presents the user with a prompt (a choice of the next step). Once the user makes a choice, that selection is sent to the server. The prompt is text designed to visualize the progression of the story.

[0410] Step 6:

[0411] The server uses an emotion engine to analyze emotional data sent from the terminal. Specifically, it uses data obtained from the camera and microphone to analyze the user's facial expressions and tone of voice, and quantifies their emotional state. The analyzed emotional data is used as adjustment data for the story.

[0412] Step 7:

[0413] The server generates the next chapter based on selection data and emotion data. Utilizing emotion-responsive generation methods, it adjusts the tone and content of the story according to the user's emotions, generating chapters based on the user's choices. The output is the adjusted chapter text.

[0414] Step 8:

[0415] Once the story is complete, the server uses automated mechanisms to present the user with publishing options. Based on the user's selection, preparations are made to distribute the story to external platforms through the provided means. The user's choice is crucial in determining the publishing format.

[0416] Step 9:

[0417] The server provides the story to an external platform in electronic publishing format according to the selected publishing option. This process automatically handles conversion to the ebook file format and uploading to the publishing platform. The output is a published ebook.

[0418] (Application Example 2)

[0419] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0420] Providing personalized experiences based on user input is challenging in story generation. Furthermore, there is a need to enhance user satisfaction by dynamically changing the story in response to user emotions. Additionally, there is a lack of automated processes for easily publishing generated stories.

[0421] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0422] In this invention, the server includes a receiving means, a story framework generation means, and an emotion recognition means. This enables the generation and automatic publication of personalized stories that correspond to the user's emotional state based on user input.

[0423] A "receiving means" is a device that has the function of accurately receiving data and subject matter entered by the user.

[0424] The "first generation means" is a device that has the function of forming the framework of a story based on the received data and theme.

[0425] The "second generation means" is a device that has the function of sequentially generating each part of the story based on the generated framework.

[0426] A "presentation method" is a device that has the function of suggesting the next development to the user at the end of each part of the story.

[0427] An "emotion recognition means" is a device that detects the user's emotional state and has the function of adjusting the story's progression accordingly.

[0428] An "update mechanism" is a function that updates the story based on the user's chosen plot developments and emotional state.

[0429] "Selection options" refers to a function that presents users with options for editing the story's framework and publishing the work.

[0430] "Distribution method" refers to a device that has the function of transmitting the generated story in electronic format to a specified medium.

[0431] The system for realizing this invention consists of a user terminal and a server. The user uses a smartphone or other computer device to input keywords and themes into the terminal's interface. This information is transmitted from the terminal to the server.

[0432] The server first receives data and a subject from the user via a "receiving means." Then, using a "first generation means," it generates the framework of a story based on the received information. Specifically, a generation AI model processes prompt sentences and automatically generates the basic structure of the story. For example, OpenAI's GPT-3 can be used as the AI ​​model.

[0433] Next, the "second generation means" sequentially generates each part of the story chapter by chapter based on the generated framework. During this process, the "emotion recognition means" uses the user's device camera to detect emotions in real time and sends the data to the server. Software such as Microsoft Azure's Face API can be used for emotion recognition. Through this process, the story's development and tone are adjusted according to the user's emotions.

[0434] When a user selects the next development based on the "presentation method" presented at the end of each chapter, that information is sent back to the server. The "update method" then generates the next part of the story based on that selection and emotional data.

[0435] Furthermore, the "Selection Method" presents the user with editing and publishing options once the story is complete. If the user selects a specific publishing option, the story is automatically distributed to the specified medium in electronic format via the "Distribution Method."

[0436] For example, if a user enters "I want to enjoy an adventure story in a magical land" as a prompt themed around "fantasy" and "adventure," the system will generate a dynamic fantasy story based on that information. If the system recognizes that the user is excited, the story will unfold with action and surprises.

[0437] Example of a prompt:

[0438] "The theme is 'adventure.' The keywords are 'dragons' and 'magic.' Start creating a fantasy story that incorporates emotionally engaging plot development."

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The user enters keywords and themes into the interface via their device. The device sends this information to the server as a prompt. The entered prompt includes themes and keywords such as "adventure" or "magic."

[0442] Step 2:

[0443] The server receives prompt messages sent by the user via its "receiving mechanism." Based on the received prompt messages, it performs analysis and stores them as information that forms the basis of the story.

[0444] Step 3:

[0445] Based on the information received by the server's "first generation means," a generative AI model is used to generate the framework of the story. Specifically, prompt text is input to a generative AI model such as GPT-3, and the basic structure of the story is output. At this time, appropriate settings and characters are automatically created based on keywords and themes.

[0446] Step 4:

[0447] The server's "second generation mechanism" sequentially generates chapters for each story based on the generated framework. At this time, the AI ​​model materializes the framework into a detailed storyline and constructs the story development for each chapter.

[0448] Step 5:

[0449] At the end of each chapter's generation, the server uses a "presentation mechanism" to offer the user options for the next development. The terminal receives the output from the generated AI model and presents the user with multiple choices.

[0450] Step 6:

[0451] The user selects from the options presented on the device. Furthermore, the device's camera analyzes the user's emotions in real time, and emotion data is acquired using an emotion recognition API. The device then sends the user's selection and emotion data to the server.

[0452] Step 7:

[0453] The server's "emotion recognition" and "update" mechanisms receive user selections and emotional data, and generate the next chapter based on the new data. The story's development and tone are adjusted based on the emotional data.

[0454] Step 8:

[0455] Once the entire story has been generated, the server presents the user with editing and publishing options through a "selection mechanism." The terminal displays this information to the user and asks for their choice.

[0456] Step 9:

[0457] When the user selects the distribution or publication option, the server's "distribution method" automatically distributes the story in electronic format to the specified platform. The terminal is notified when the entire process is complete.

[0458] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0459] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0460] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0461] [Third Embodiment]

[0462] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0463] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0464] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0465] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0466] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0467] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0468] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0469] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0470] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0471] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0472] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0473] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0474] This invention is a system that generates an original novel from keywords and themes specified by the user and allows the story to progress interactively. Specific embodiments are described below.

[0475] First, the user inputs keywords and themes for the novel via their device. This information is sent from the device to the server. The server uses the received keywords and themes to run an AI generation model and create the overall plot of the novel. After the plot is generated, the server sequentially develops the story chapter by chapter, suggesting multiple story developments so that the user can choose the next development at the end of each chapter.

[0476] The user selects one of the suggested story developments on their device, and this selection is sent back to the server. Based on the user's selection, the server generates the next chapter of the novel and updates the story. This allows the user to actively participate in the progression of the narrative and enjoy a personalized reading experience.

[0477] For example, if a user selects a theme such as "science fiction" or "adventure," the server can generate a plot for "future planetary exploration." Then, if the user selects "encounter with unknown life forms" from the suggested scenarios, the server will depict the next chapter based on that selection.

[0478] Finally, once all chapters have been generated and the novel is complete, the server will present the user with options for publishing the novel. These options include setting the selling price and sales region, and publishing in ebook format. If the user chooses to publish, the server will automatically handle the process and publish the work on the specified platform.

[0479] In this way, the system based on the present invention provides an environment in which users can easily generate and publish original novels.

[0480] The following describes the processing flow.

[0481] Step 1:

[0482] The user uses their device to input keywords and themes for the novel. This input interface allows the user to freely enter keywords, and also provides a dropdown menu for selecting themes.

[0483] Step 2:

[0484] The terminal sends user input as data to the server. The input information is structured in a format that includes at least keywords and themes.

[0485] Step 3:

[0486] The server processes the received keywords and themes and uses an AI model to generate the overall plot. The plot automatically creates the basic storyline of the narrative.

[0487] Step 4:

[0488] The server then develops the story for the first chapter based on the generated plot. It generates elements such as main events and characters in text form, describing the beginning of the story.

[0489] Step 5:

[0490] Upon reaching the end of a chapter, the server generates several options suggesting the next development. Each of these options suggests a different storyline.

[0491] Step 6:

[0492] The terminal displays the user with options suggested by the server. The user then selects and confirms the next story development they wish to pursue from the displayed options.

[0493] Step 7:

[0494] After the device sends the user's selection to the server, the server generates the next chapter based on the selected development. This process allows for story updates that reflect the user's intent.

[0495] Step 8:

[0496] This process is repeated until all chapters are generated, completing the entire novel. The server then refines the generated novel into its final form.

[0497] Step 9:

[0498] The server presents the user with publishing options for the completed novel. These include selecting the sales price and sales region, and specifying the distribution platform.

[0499] Step 10:

[0500] Once the user selects their desired options from the presented choices, the server automatically executes the publishing process and publishes the novel on the specified platform.

[0501] (Example 1)

[0502] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0503] Traditional story generation systems have limited opportunities for users to directly participate in the story's themes and progression, making it difficult to provide a personalized storytelling experience. Furthermore, there is a lack of efficient means for publishing and distributing the generated stories, creating a barrier for users to widely share their own creations.

[0504] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0505] In this invention, the server includes a receiving means for receiving words and themes input by a user, a structure generation means for generating the overall structure of a story based on the words and themes, and a chapter generation means for sequentially generating each chapter of the story based on the generated overall structure. This provides an environment in which users can actively participate in the progression of the story and easily enjoy a personalized story experience, and further enables the efficient publication of the generated story.

[0506] "Reception means" refers to a device or system that has the function of receiving words and topics entered by a user.

[0507] "Structure generation means" refers to a device or system that has the function of generating the overall structure of a story based on words and themes entered by the user.

[0508] A "chapter generation means" is a device or system that has the function of sequentially generating each chapter of a story based on the generated overall structure.

[0509] A "development suggestion means" is a device or system that has the function of suggesting the next development of the story to the user at the end of each chapter.

[0510] A "story updating means" is a device or system that has the function of updating the story based on the development selected by the user.

[0511] An "option presentation means" is a device or system that has the function of presenting users with options for editing the overall structure of the story and publishing the work.

[0512] "Publication means" refers to a device or system that has the function of automatically performing the procedure of distributing a story in electronic book format to a designated information and communication infrastructure.

[0513] This system provides an environment for users to generate and publish original stories. Users input words and themes via a terminal. This input information is sent from the terminal to the server. The server has a mechanism to receive words and themes through a reception system.

[0514] The server utilizes a generative AI model based on the received words and subject matter to generate the overall structure of the story. This process employs natural language generation models such as OpenAI's GPT-3. The generated overall structure is then formed by a structure generation mechanism.

[0515] Subsequently, the server uses a chapter generation mechanism to sequentially generate each chapter based on the overall structure. Upon completion of each chapter, a development suggestion mechanism is used to propose the next development to the user, who can choose one of the options presented on their terminal. This selection is sent back to the server, and the story is updated by a story update mechanism.

[0516] Ultimately, the server provides the user with an option to publish the story through an option presentation mechanism. If the user chooses to publish, the publishing mechanism is activated, and the story is delivered to the specified information and communication infrastructure in ebook format.

[0517] For example, if a user inputs the themes of "fantasy" and "friendship," the server will generate an overall structure such as "Two friends embark on an adventure in a medieval kingdom." Users can communicate the direction of the story to the server by providing prompts, for example, "Generate the beginning of a novel with the themes of fantasy and friendship. Imagine a scene where the main characters step into a mystical forest and an unknown adventure begins." This allows users to generate and publish individually customized stories.

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] Step 1:

[0520] The user uses a device to input specific words and topics. This defines the general theme and content of the story the user desires. The entered information is temporarily stored as digital data on the device and later prepared for transmission to the server.

[0521] Step 2:

[0522] The terminal sends the entered words and topics to the server. The transmitted data is received by the server's receiving mechanism. This data is treated as basic information for subsequent processes and is appropriately stored in the database.

[0523] Step 3:

[0524] The server runs a generative AI model based on the received words and subject matter. During this process, prompt sentences are supplied to the generative AI model, which then generates the overall structure of the story. The generated overall structure is then saved to the server in a digital format.

[0525] Step 4:

[0526] The server utilizes the overall configuration to sequentially create individual chapters via a chapter generation mechanism. At this stage, the first version of each chapter is generated. An AI model generates text based on the content of the constructed story, and the created chapters are stored on the server as digital data.

[0527] Step 5:

[0528] At the end of each chapter, the server uses a development presentation mechanism to offer the user choices for the next development of the story. The choices are sent to the user's terminal, and the user can choose the next development from the presented options. The selected option is then sent back to the server from the terminal.

[0529] Step 6:

[0530] The server updates the story using a narrative update mechanism based on the selection information sent by the user. Specifically, it reruns the generative AI model based on the selected development, and generates the next chapter. This update ensures that the story includes new developments that correspond to the user's selection.

[0531] Step 7:

[0532] Once the story is complete, the server presents the user with publishing options through an options presentation system. These include the publishing format, pricing, and platform selection. Based on the user's selection, the server automatically adjusts to the most suitable publishing option.

[0533] Step 8:

[0534] In the final step, the server uses a publishing mechanism to distribute the story to the designated information and communication infrastructure. During this process, the story is converted into an electronic book format and distributed to the selected platform. Once publication is complete, users can verify that the work is accessible worldwide.

[0535] (Application Example 1)

[0536] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0537] There is a need for a novel generation system that allows users to easily enjoy individual story experiences and interactively advance the narrative through their own choices. Furthermore, a challenge lies in providing a system that allows for the easy publication and sharing of these generated stories as ebooks.

[0538] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0539] In this invention, the server includes an input means for receiving keywords and themes entered by a user, a first generation means for sequentially generating each chapter of a story based on the generated structure, and an AI means for generating a story using a generation AI model. This allows users to enjoy a story experience based on individual themes and publish and share it as an electronic document.

[0540] "Keywords" are important words or concepts that users input to concretize the content or theme of a story.

[0541] A "theme" is the main topic or subject matter that runs throughout the entire story, and it is a factor that determines the direction of the narrative.

[0542] "The overall structure of the story" refers to the framework of the narrative generated based on information provided by the user, and includes a consistent plot that encompasses the flow of chapters and episodes.

[0543] "Generative means" refers to a technical method that concretizes the story based on the overall structure and derives the next development in response to the user's interactive input.

[0544] The "first generation means" is a device or method for sequentially creating each chapter based on the overall structure of the generated story.

[0545] A "suggestion method" is a technique that presents the user with multiple options at the end of each chapter of a story, allowing them to choose the next development.

[0546] "AI methods" refer to techniques that use generative AI models to automatically generate story structures and chapters.

[0547] "Delivery means" refers to a device or method that has the function of delivering a completed story in the form of an electronic document to a desired base or platform.

[0548] This invention relates to a story generation system consisting of a user terminal and a server, which provides a function that allows users to interactively generate stories and publish them as ebooks.

[0549] First, the user inputs the theme and keywords of the novel via a device such as a smartphone. This information is sent to a server via the network. Based on the received keywords and themes, the server uses a generative AI model to create the overall structure of the story. This AI model might use, for example, the OpenAI API. The AI ​​analyzes the input information and constructs a coherent framework for the story.

[0550] The generated overall structure is further broken down on the server, and each chapter is generated sequentially. At the end of each chapter, the user can choose the next development from the suggested options. In this way, the story is customized according to the user's choices. Through this communication, the user can become deeply involved in the story and enjoy a personalized experience. The selected development is sent back to the server, and the next chapter is generated.

[0551] The server also has the means to deliver the generated stories in electronic document format to a specified platform. This allows users to automatically share their created stories with others as ebooks. For example, if a user selects the themes "fantasy" and "magic revolution," and then chooses the plot "adventuring for ancient treasures," the AI ​​will describe how the next chapter will unfold based on that information.

[0552] Examples of prompt statements include the following:

[0553] Create a fantasy novel plot based on the following theme: "Magic Revolution".

[0554] Start the story with the main plot point as an adventure to discover ancient treasures.

[0555] Thus, the system of the present invention provides an environment in which users can easily visualize stories and generate their own unique narrative experiences.

[0556] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0557] Step 1:

[0558] The user uses a terminal to input the novel's theme and keywords. The entered information is processed as text data and sent to the server over the network.

[0559] Step 2:

[0560] The server analyzes the received theme and keywords. Based on this, it forms a prompt message and sends it to the generating AI model. This prompt message contains instructions for generating the overall structure of the story.

[0561] Step 3:

[0562] The generative AI model generates the overall structure of the story based on the prompt messages received from the server. The generated structure is returned to the server as data containing the storyline and key plot elements.

[0563] Step 4:

[0564] The server then concretizes each chapter of the story based on the overall structure returned by the AI ​​model. It breaks down the story chapter by chapter and generates sub-plans for each chapter. The results are processed sequentially and sent to the user as choices for the next chapter.

[0565] Step 5:

[0566] The user reviews and selects from the next development options presented on their device. This selection information is then sent back to the server and used as data input for the next story development.

[0567] Step 6:

[0568] The server updates the chapter based on the user's selection. The newly obtained selection is converted back into a prompt and sent to the generating AI model to prepare the basic data for generating the next chapter.

[0569] Step 7:

[0570] Once all chapters have been generated, the server compiles the completed story into an electronic document and delivers it to the designated distribution platform. This output is in a publicly shareable format, allowing users to share the story with others.

[0571] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0572] This invention is a system that generates an original novel from keywords and themes specified by the user, and interactively advances the story, and further includes an emotion engine that recognizes the user's emotions and adjusts the story's development and tone.

[0573] First, the user inputs keywords and themes for the novel using their device. This information is sent from the device to the server. The server runs an AI generation model based on the received keywords and themes to create the overall plot of the novel. After the plot is generated, the server generates the story chapter by chapter and suggests the next development to the user at the end of each chapter. At this time, the emotion engine detects the user's emotions and customizes the suggested developments based on that information.

[0574] When a user selects a scenario from those presented on their device, that selection is sent to the server, which can then generate the next chapter based on the user's selection and emotional state. For example, if the user chooses "fantasy" and "adventure" as their themes, the server can generate a plot for "an adventure story in a magical land." If the user then selects the scenario "encountering a dragon," and the emotion engine determines that the user is excited, the server will generate an action-packed chapter that reflects that excitement.

[0575] Furthermore, once all chapters have been generated and the story is complete, the server presents the user with publishing options for their novel. The emotion engine suggests a promotional strategy tailored to the user's emotional state, which is also reflected in the sales strategy for the work. Finally, the server automatically handles the publishing process according to the user's selected options and publishes the work on the designated platform.

[0576] In this way, users can obtain a personalized creative experience through a system that allows for emotionally-driven story customization and easy publishing.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] Users input keywords and themes for their novels through their devices. The input screen is designed for intuitive use and allows for the combination of multiple themes and keywords.

[0580] Step 2:

[0581] The terminal sends user input information to the server. This information is registered in a database and used in subsequent processes.

[0582] Step 3:

[0583] The server uses the received keywords and themes to activate an AI generation model and generate the overall plot. During plot creation, settings and characters appropriate to the theme are automatically generated.

[0584] Step 4:

[0585] The server generates the first chapter. The generated chapter includes the introduction to the story and the main characters, and the story unfolds based on this.

[0586] Step 5:

[0587] At the end of the generated chapter, the server presents the user with options for the next development. Here, the emotion engine analyzes the user's emotions and customizes and sets the options accordingly.

[0588] Step 6:

[0589] The terminal displays suggested options received from the server to the user. The user selects the storyline that interests them most and confirms their choice.

[0590] Step 7:

[0591] The user's selection is sent from the terminal to the server. The server takes that selection and the results of the emotion engine's analysis into consideration and generates the next chapter. This process is repeated until the story is completed.

[0592] Step 8:

[0593] Once all chapters of the story are complete, the server automatically edits the novel and checks for consistency throughout.

[0594] Step 9:

[0595] The server presents the user with publishing options. The sentiment engine is also used here to suggest a promotional strategy based on the user's emotions.

[0596] Step 10:

[0597] When a user selects a publishing option, the server automatically executes the publishing process and publishes the novel in ebook format to the specified platform.

[0598] (Example 2)

[0599] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0600] In recent years, there has been a growing demand for personalized content tailored to individual user preferences. However, there is a lack of systems that can generate stories based on user-specified themes and keywords, while also considering the user's emotional state. Furthermore, there is a need for efficient means of publishing these generated works. This invention aims to solve these problems by interactively generating stories that reflect the user's intentions and emotions, and automatically publishing them.

[0601] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0602] In this invention, the server includes receiving means for receiving instructions and themes input by the user, generating means for generating a story outline based on the instructions and themes, and chapter generating means for sequentially generating each chapter of the story based on the generated outline. This makes it possible to generate interactive novels that reflect the individual preferences and emotional states of the user, and to effectively publish the resulting works.

[0603] "Receiving means" refers to the part of the system that has communication functions to receive instructions and topics from the user and process them within the system.

[0604] The "generative means" refers to the part that constructs the framework based on the received instructions and theme, and has the function of outlining the basic flow and outline of the story.

[0605] The "chapter generation mechanism" is the part that sequentially forms each chapter based on the generated outline, thereby detailing the story.

[0606] "Suggestion mechanism" refers to the part of the story that presents the next development to the user and offers them choices.

[0607] The "adjustment mechanism" refers to the part that dynamically updates the story's development based on user choices and emotional data, and has the function of adapting the tone and flow of the story.

[0608] "Display means" refers to the part that has an interface function to present the generated outline and publication options to the user.

[0609] "Automation means" refers to the part that has the function of executing a process to efficiently carry out the publishing process of the generated story and provide it to a designated platform.

[0610] The "emotional response generation mechanism" is a component that has the function of adjusting the content and development of the story based on the user's emotional state, and plays a role in supporting the individualization of the story.

[0611] "Means of delivery" refers to the part that has communication and distribution functions for transmitting the completed story to an external platform in electronic publishing format.

[0612] This invention is a system that allows users to generate original stories and easily publish them. This system mainly consists of a server and terminals, and dynamically generates stories based on user input and customizes the story according to the user's emotional state.

[0613] First, the user uses a terminal to input the instructions and theme of their desired story. This input is sent from the terminal to the server via a secure communication method (e.g., HTTPS). On the server, a generative AI model (for example, GPT-3 is a common model) is used to construct the story's framework based on the received instructions and theme. This generative AI model has advanced natural language processing capabilities and is capable of generating a wide variety of stories.

[0614] Next, the server uses a chapter generation mechanism based on the generated framework to detail the story chapter by chapter. At the end of each chapter, the server presents the user with a choice (prompt) to select the next course of action. For example, "You begin a new adventure in the land of magic. Choose one of the following options: 1. Confront the dragon, 2. Enter the Cave of Wisdom, 3. Explore the Magic Tree."

[0615] In this process, the server utilizes an emotion engine to detect the user's emotions. It analyzes data obtained from the camera and microphone connected to the device to understand the user's emotional state (for example, whether they are excited or not). Based on this information, an emotion response generation mechanism works to adjust and generate the content and tone of the next chapter.

[0616] When the story is complete, the server uses automated means to present the user with publishing options. Based on the option selected by the user, the service provider delivers the story in electronic publishing format to an external platform (e.g., an ebook store).

[0617] As described above, users can use this system to create and effectively distribute interactive, personalized stories. The system can provide a seamless and flexible process from story generation to publication.

[0618] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0619] Step 1:

[0620] The user uses a terminal to input the story's instructions and theme. This input is captured as text data, and the terminal prepares this data for transmission to the server. The input data is used as the requirements for generating the story.

[0621] Step 2:

[0622] The terminal sends instructions and subject data to the server. The HTTPS protocol is used for communication, ensuring security. The transmitted data is stored in a database on the server side and becomes input data for the generated AI model.

[0623] Step 3:

[0624] The server runs a generative AI model and generates a story outline based on the received instructions and theme. Here, machine learning algorithms are used to process the data and generate the text data of the outline. This generated outline will be refined in the next step.

[0625] Step 4:

[0626] The server operates the chapter generation mechanism based on the framework, generating the story chapter by chapter. Each chapter is constructed individually as text data, gradually putting the whole story together. The output is the text of each chapter.

[0627] Step 5:

[0628] At the end of each chapter, the server presents the user with a prompt (a choice of the next step). Once the user makes a choice, that selection is sent to the server. The prompt is text designed to visualize the progression of the story.

[0629] Step 6:

[0630] The server uses an emotion engine to analyze emotional data sent from the terminal. Specifically, it uses data obtained from the camera and microphone to analyze the user's facial expressions and tone of voice, and quantifies their emotional state. The analyzed emotional data is used as adjustment data for the story.

[0631] Step 7:

[0632] The server generates the next chapter based on selection data and emotion data. Utilizing emotion-responsive generation methods, it adjusts the tone and content of the story according to the user's emotions, generating chapters based on the user's choices. The output is the adjusted chapter text.

[0633] Step 8:

[0634] Once the story is complete, the server uses automated mechanisms to present the user with publishing options. Based on the user's selection, preparations are made to distribute the story to external platforms through the provided means. The user's choice is crucial in determining the publishing format.

[0635] Step 9:

[0636] The server provides the story to an external platform in electronic publishing format according to the selected publishing option. This process automatically handles conversion to the ebook file format and uploading to the publishing platform. The output is a published ebook.

[0637] (Application Example 2)

[0638] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0639] Providing personalized experiences based on user input is challenging in story generation. Furthermore, there is a need to enhance user satisfaction by dynamically changing the story in response to user emotions. Additionally, there is a lack of automated processes for easily publishing generated stories.

[0640] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0641] In this invention, the server includes a receiving means, a story framework generation means, and an emotion recognition means. This enables the generation of personalized stories that correspond to the user's emotional state based on user input, and their automatic publication.

[0642] A "receiving means" is a device that has the function of accurately receiving data and subject matter entered by the user.

[0643] The "first generation means" is a device that has the function of forming the framework of a story based on the received data and theme.

[0644] The "second generation means" is a device that has the function of sequentially generating each part of the story based on the generated framework.

[0645] A "presentation method" is a device that has the function of suggesting the next development to the user at the end of each part of the story.

[0646] An "emotion recognition means" is a device that detects the user's emotional state and has the function of adjusting the story's progression accordingly.

[0647] An "update mechanism" is a function that updates the story based on the user's chosen plot developments and emotional state.

[0648] "Selection options" refers to a function that presents users with options for editing the story's framework and publishing the work.

[0649] "Distribution method" refers to a device that has the function of transmitting the generated story in electronic format to a specified medium.

[0650] The system for realizing this invention consists of a user terminal and a server. The user uses a smartphone or other computer device to input keywords and themes into the terminal's interface. This information is transmitted from the terminal to the server.

[0651] The server first receives data and a subject from the user via a "receiving means." Then, using a "first generation means," it generates the framework of a story based on the received information. Specifically, a generation AI model processes prompt sentences and automatically generates the basic structure of the story. For example, OpenAI's GPT-3 can be used as the AI ​​model.

[0652] Next, the "second generation means" sequentially generates each part of the story chapter by chapter based on the generated framework. During this process, the "emotion recognition means" uses the user's device camera to detect emotions in real time and sends the data to the server. Software such as Microsoft Azure's Face API can be used for emotion recognition. Through this process, the story's development and tone are adjusted according to the user's emotions.

[0653] When a user selects the next development based on the "presentation method" presented at the end of each chapter, that information is sent back to the server. The "update method" then generates the next part of the story based on that selection and emotional data.

[0654] Furthermore, the "Selection Method" presents the user with editing and publishing options once the story is complete. If the user selects a specific publishing option, the story is automatically distributed to the specified medium in electronic format via the "Distribution Method."

[0655] For example, if a user enters "I want to enjoy an adventure story in a magical land" as a prompt themed around "fantasy" and "adventure," the system will generate a dynamic fantasy story based on that information. If the system recognizes that the user is excited, the story will unfold with action and surprises.

[0656] Example of a prompt:

[0657] "The theme is 'adventure.' The keywords are 'dragons' and 'magic.' Start creating a fantasy story that incorporates emotionally engaging plot development."

[0658] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0659] Step 1:

[0660] The user enters keywords and themes into the interface via their device. The device sends this information to the server as a prompt. The entered prompt includes themes and keywords such as "adventure" or "magic."

[0661] Step 2:

[0662] The server receives prompt messages sent by the user via its "receiving mechanism." Based on the received prompt messages, it performs analysis and stores them as information that forms the basis of the story.

[0663] Step 3:

[0664] Based on the information received by the server's "first generation means," a generative AI model is used to generate the framework of the story. Specifically, prompt text is input to a generative AI model such as GPT-3, and the basic structure of the story is output. At this time, appropriate settings and characters are automatically created based on keywords and themes.

[0665] Step 4:

[0666] The server's "second generation mechanism" sequentially generates chapters for each story based on the generated framework. At this time, the AI ​​model materializes the framework into a detailed storyline and constructs the story development for each chapter.

[0667] Step 5:

[0668] At the end of each chapter's generation, the server uses a "presentation mechanism" to offer the user options for the next development. The terminal receives the output from the generated AI model and presents the user with multiple choices.

[0669] Step 6:

[0670] The user selects from the options presented on the device. Furthermore, the device's camera analyzes the user's emotions in real time, and emotion data is acquired using an emotion recognition API. The device then sends the user's selection and emotion data to the server.

[0671] Step 7:

[0672] The server's "emotion recognition" and "update" mechanisms receive user selections and emotional data, and generate the next chapter based on the new data. The story's development and tone are adjusted based on the emotional data.

[0673] Step 8:

[0674] Once the entire story has been generated, the server presents the user with editing and publishing options through a "selection mechanism." The terminal displays this information to the user and asks for their choice.

[0675] Step 9:

[0676] When the user selects the distribution or publication option, the server's "distribution method" automatically distributes the story in electronic format to the specified platform. The terminal is notified when the entire process is complete.

[0677] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0678] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0679] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0680] [Fourth Embodiment]

[0681] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0682] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0683] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0684] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0685] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0686] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0687] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0688] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0689] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0690] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0691] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0692] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0693] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0694] This invention is a system that generates an original novel from keywords and themes specified by the user and allows the story to progress interactively. Specific embodiments are described below.

[0695] First, the user inputs keywords and themes for the novel via their device. This information is sent from the device to the server. The server uses the received keywords and themes to run an AI generation model and create the overall plot of the novel. After the plot is generated, the server sequentially develops the story chapter by chapter, suggesting multiple story developments so that the user can choose the next development at the end of each chapter.

[0696] The user selects one of the suggested story developments on their device, and this selection is sent back to the server. Based on the user's selection, the server generates the next chapter of the novel and updates the story. This allows the user to actively participate in the progression of the narrative and enjoy a personalized reading experience.

[0697] For example, if a user selects a theme such as "science fiction" or "adventure," the server can generate a plot for "future planetary exploration." Then, if the user selects "encounter with unknown life forms" from the suggested scenarios, the server will depict the next chapter based on that selection.

[0698] Finally, once all chapters have been generated and the novel is complete, the server will present the user with options for publishing the novel. These options include setting the selling price and sales region, and publishing in ebook format. If the user chooses to publish, the server will automatically handle the process and publish the work on the specified platform.

[0699] In this way, the system based on the present invention provides an environment in which users can easily generate and publish original novels.

[0700] The following describes the processing flow.

[0701] Step 1:

[0702] The user uses their device to input keywords and themes for the novel. This input interface allows the user to freely enter keywords, and also provides a dropdown menu for selecting themes.

[0703] Step 2:

[0704] The terminal sends user input as data to the server. The input information is structured in a format that includes at least keywords and themes.

[0705] Step 3:

[0706] The server processes the received keywords and themes and uses an AI model to generate the overall plot. The plot automatically creates the basic storyline of the narrative.

[0707] Step 4:

[0708] The server then develops the story for the first chapter based on the generated plot. It generates elements such as main events and characters in text form, describing the beginning of the story.

[0709] Step 5:

[0710] Upon reaching the end of a chapter, the server generates several options suggesting the next development. Each of these options suggests a different storyline.

[0711] Step 6:

[0712] The terminal displays the user with options suggested by the server. The user then selects and confirms the next story development they wish to pursue from the displayed options.

[0713] Step 7:

[0714] After the device sends the user's selection to the server, the server generates the next chapter based on the selected development. This process allows for story updates that reflect the user's intent.

[0715] Step 8:

[0716] This process is repeated until all chapters are generated, completing the entire novel. The server then refines the generated novel into its final form.

[0717] Step 9:

[0718] The server presents the user with publishing options for the completed novel. These include selecting the sales price and sales region, and specifying the distribution platform.

[0719] Step 10:

[0720] Once the user selects their desired options from the presented choices, the server automatically executes the publishing process and publishes the novel on the specified platform.

[0721] (Example 1)

[0722] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0723] Traditional story generation systems have limited opportunities for users to directly participate in the story's themes and progression, making it difficult to provide a personalized storytelling experience. Furthermore, there is a lack of efficient means for publishing and distributing the generated stories, creating a barrier for users to widely share their own creations.

[0724] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0725] In this invention, the server includes a receiving means for receiving words and themes input by a user, a structure generation means for generating the overall structure of a story based on the words and themes, and a chapter generation means for sequentially generating each chapter of the story based on the generated overall structure. This provides an environment in which users can actively participate in the progression of the story and easily enjoy a personalized story experience, and further enables the efficient publication of the generated story.

[0726] "Reception means" refers to a device or system that has the function of receiving words and topics entered by a user.

[0727] "Structure generation means" refers to a device or system that has the function of generating the overall structure of a story based on words and themes entered by the user.

[0728] A "chapter generation means" is a device or system that has the function of sequentially generating each chapter of a story based on the generated overall structure.

[0729] A "development suggestion means" is a device or system that has the function of suggesting the next development of the story to the user at the end of each chapter.

[0730] A "story updating means" is a device or system that has the function of updating the story based on the development selected by the user.

[0731] An "option presentation means" is a device or system that has the function of presenting users with options for editing the overall structure of the story and publishing the work.

[0732] "Publication means" refers to a device or system that has the function of automatically performing the procedure of distributing a story in electronic book format to a designated information and communication infrastructure.

[0733] This system provides an environment for users to generate and publish original stories. Users input words and themes via a terminal. This input information is sent from the terminal to the server. The server has a mechanism to receive words and themes through a reception system.

[0734] The server utilizes a generative AI model based on the received words and subject matter to generate the overall structure of the story. This process employs natural language generation models such as OpenAI's GPT-3. The generated overall structure is then formed by a structure generation mechanism.

[0735] Subsequently, the server uses a chapter generation mechanism to sequentially generate each chapter based on the overall structure. Upon completion of each chapter, a development suggestion mechanism is used to propose the next development to the user, who can choose one of the options presented on their terminal. This selection is sent back to the server, and the story is updated by a story update mechanism.

[0736] Ultimately, the server provides the user with an option to publish the story through an option presentation mechanism. If the user chooses to publish, the publishing mechanism is activated, and the story is delivered to the specified information and communication infrastructure in ebook format.

[0737] For example, if a user inputs the themes of "fantasy" and "friendship," the server will generate an overall structure such as "Two friends embark on an adventure in a medieval kingdom." Users can communicate the direction of the story to the server by providing prompts, for example, "Generate the beginning of a novel with the themes of fantasy and friendship. Imagine a scene where the main characters step into a mystical forest and an unknown adventure begins." This allows users to generate and publish individually customized stories.

[0738] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0739] Step 1:

[0740] The user uses a device to input specific words and topics. This defines the general theme and content of the story the user desires. The entered information is temporarily stored as digital data on the device and later prepared for transmission to the server.

[0741] Step 2:

[0742] The terminal sends the entered words and topics to the server. The transmitted data is received by the server's receiving mechanism. This data is treated as basic information for subsequent processes and is appropriately stored in the database.

[0743] Step 3:

[0744] The server runs a generative AI model based on the received words and subject matter. During this process, prompt sentences are supplied to the generative AI model, which then generates the overall structure of the story. The generated overall structure is then saved to the server in a digital format.

[0745] Step 4:

[0746] The server utilizes the overall configuration to sequentially create individual chapters via a chapter generation mechanism. At this stage, the first version of each chapter is generated. An AI model generates text based on the content of the constructed story, and the created chapters are stored on the server as digital data.

[0747] Step 5:

[0748] At the end of each chapter, the server uses a development presentation mechanism to offer the user choices for the next development of the story. The choices are sent to the user's terminal, and the user can choose the next development from the presented options. The selected option is then sent back to the server from the terminal.

[0749] Step 6:

[0750] The server updates the story using a narrative update mechanism based on the selection information sent by the user. Specifically, it reruns the generative AI model based on the selected development, and generates the next chapter. This update ensures that the story includes new developments that correspond to the user's selection.

[0751] Step 7:

[0752] Once the story is complete, the server presents the user with publishing options through an options presentation system. These include the publishing format, pricing, and platform selection. Based on the user's selection, the server automatically adjusts to the most suitable publishing option.

[0753] Step 8:

[0754] In the final step, the server uses a publishing mechanism to distribute the story to the designated information and communication infrastructure. During this process, the story is converted into an electronic book format and distributed to the selected platform. Once publication is complete, users can verify that the work is accessible worldwide.

[0755] (Application Example 1)

[0756] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0757] There is a need for a novel generation system that allows users to easily enjoy individual story experiences and interactively advance the narrative through their own choices. Furthermore, a challenge lies in providing a system that allows for the easy publication and sharing of these generated stories as ebooks.

[0758] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0759] In this invention, the server includes an input means for receiving keywords and themes entered by a user, a first generation means for sequentially generating each chapter of a story based on the generated structure, and an AI means for generating a story using a generation AI model. This allows users to enjoy a story experience based on individual themes and publish and share it as an electronic document.

[0760] "Keywords" are important words or concepts that users input to concretize the content or theme of a story.

[0761] A "theme" is the main topic or subject matter that runs throughout the entire story, and it is a factor that determines the direction of the narrative.

[0762] "The overall structure of the story" refers to the framework of the narrative generated based on information provided by the user, and includes a consistent plot that encompasses the flow of chapters and episodes.

[0763] "Generative means" refers to a technical method that concretizes the story based on the overall structure and derives the next development in response to the user's interactive input.

[0764] The "first generation means" is a device or method for sequentially creating each chapter based on the overall structure of the generated story.

[0765] A "suggestion method" is a technique that presents the user with multiple options at the end of each chapter of a story, allowing them to choose the next development.

[0766] "AI methods" refer to techniques that use generative AI models to automatically generate story structures and chapters.

[0767] "Delivery means" refers to a device or method that has the function of delivering a completed story in the form of an electronic document to a desired base or platform.

[0768] This invention relates to a story generation system consisting of a user terminal and a server, which provides a function that allows users to interactively generate stories and publish them as ebooks.

[0769] First, the user inputs the theme and keywords of the novel via a device such as a smartphone. This information is sent to a server via the network. Based on the received keywords and themes, the server uses a generative AI model to create the overall structure of the story. This AI model might use, for example, the OpenAI API. The AI ​​analyzes the input information and constructs a coherent framework for the story.

[0770] The generated overall structure is further broken down on the server, and each chapter is generated sequentially. At the end of each chapter, the user can choose the next development from the suggested options. In this way, the story is customized according to the user's choices. Through this communication, the user can become deeply involved in the story and enjoy a personalized experience. The selected development is sent back to the server, and the next chapter is generated.

[0771] The server also has the means to deliver the generated stories in electronic document format to a specified platform. This allows users to automatically share their created stories with others as ebooks. For example, if a user selects the themes "fantasy" and "magic revolution," and then chooses the plot "adventuring for ancient treasures," the AI ​​will describe how the next chapter will unfold based on that information.

[0772] Examples of prompt statements include the following:

[0773] Create a fantasy novel plot based on the following theme: "Magic Revolution".

[0774] Start the story with the main plot point as an adventure to discover ancient treasures.

[0775] Thus, the system of the present invention provides an environment in which users can easily visualize stories and generate their own unique narrative experiences.

[0776] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0777] Step 1:

[0778] The user uses a terminal to input the novel's theme and keywords. The entered information is processed as text data and sent to the server over the network.

[0779] Step 2:

[0780] The server analyzes the received theme and keywords. Based on this, it forms a prompt message and sends it to the generating AI model. This prompt message contains instructions for generating the overall structure of the story.

[0781] Step 3:

[0782] The generative AI model generates the overall structure of the story based on the prompt messages received from the server. The generated structure is returned to the server as data containing the storyline and key plot elements.

[0783] Step 4:

[0784] The server then concretizes each chapter of the story based on the overall structure returned by the AI ​​model. It breaks down the story chapter by chapter and generates sub-plans for each chapter. The results are processed sequentially and sent to the user as choices for the next chapter.

[0785] Step 5:

[0786] The user reviews and selects from the next development options presented on their device. This selection information is then sent back to the server and used as data input for the next story development.

[0787] Step 6:

[0788] The server updates the chapter based on the user's selection. The newly obtained selection is converted back into a prompt and sent to the generating AI model to prepare the basic data for generating the next chapter.

[0789] Step 7:

[0790] Once all chapters have been generated, the server compiles the completed story into an electronic document and delivers it to the designated distribution platform. This output is in a publicly shareable format, allowing users to share the story with others.

[0791] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0792] This invention is a system that generates an original novel from keywords and themes specified by the user, and interactively advances the story, and further includes an emotion engine that recognizes the user's emotions and adjusts the story's development and tone.

[0793] First, the user inputs keywords and themes for the novel using their device. This information is sent from the device to the server. The server runs an AI generation model based on the received keywords and themes to create the overall plot of the novel. After the plot is generated, the server generates the story chapter by chapter and suggests the next development to the user at the end of each chapter. At this time, the emotion engine detects the user's emotions and customizes the suggested developments based on that information.

[0794] When a user selects a scenario from those presented on their device, that selection is sent to the server, which can then generate the next chapter based on the user's selection and emotional state. For example, if the user chooses "fantasy" and "adventure" as their themes, the server can generate a plot for "an adventure story in a magical land." If the user then selects the scenario "encountering a dragon," and the emotion engine determines that the user is excited, the server will generate an action-packed chapter that reflects that excitement.

[0795] Furthermore, once all chapters have been generated and the story is complete, the server presents the user with publishing options for their novel. The emotion engine suggests a promotional strategy tailored to the user's emotional state, which is also reflected in the sales strategy for the work. Finally, the server automatically handles the publishing process according to the user's selected options and publishes the work on the designated platform.

[0796] In this way, users can obtain a personalized creative experience through a system that allows for emotionally-driven story customization and easy publishing.

[0797] The following describes the processing flow.

[0798] Step 1:

[0799] Users input keywords and themes for their novels through their devices. The input screen is designed for intuitive use and allows for the combination of multiple themes and keywords.

[0800] Step 2:

[0801] The terminal sends user input information to the server. This information is registered in a database and used in subsequent processes.

[0802] Step 3:

[0803] The server uses the received keywords and themes to activate an AI generation model and generate the overall plot. During plot creation, settings and characters appropriate to the theme are automatically generated.

[0804] Step 4:

[0805] The server generates the first chapter. The generated chapter includes the introduction to the story and the main characters, and the story unfolds based on this.

[0806] Step 5:

[0807] At the end of the generated chapter, the server presents the user with options for the next development. Here, the emotion engine analyzes the user's emotions and customizes and sets the options accordingly.

[0808] Step 6:

[0809] The terminal displays suggested options received from the server to the user. The user selects the storyline that interests them most and confirms their choice.

[0810] Step 7:

[0811] The user's selection is sent from the terminal to the server. The server takes that selection and the results of the emotion engine's analysis into consideration and generates the next chapter. This process is repeated until the story is completed.

[0812] Step 8:

[0813] Once all chapters of the story are complete, the server automatically edits the novel and checks for consistency throughout.

[0814] Step 9:

[0815] The server presents the user with publishing options. The sentiment engine is also used here to suggest a promotional strategy based on the user's emotions.

[0816] Step 10:

[0817] When a user selects a publishing option, the server automatically executes the publishing process and publishes the novel in ebook format to the specified platform.

[0818] (Example 2)

[0819] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0820] In recent years, there has been a growing demand for personalized content tailored to individual user preferences. However, there is a lack of systems that can generate stories based on user-specified themes and keywords, while also considering the user's emotional state. Furthermore, there is a need for efficient means of publishing these generated works. This invention aims to solve these problems by interactively generating stories that reflect the user's intentions and emotions, and automatically publishing them.

[0821] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0822] In this invention, the server includes receiving means for receiving instructions and themes input by the user, generating means for generating a story outline based on the instructions and themes, and chapter generating means for sequentially generating each chapter of the story based on the generated outline. This makes it possible to generate interactive novels that reflect the individual preferences and emotional states of the user, and to effectively publish the resulting works.

[0823] "Receiving means" refers to the part of the system that has communication functions to receive instructions and topics from the user and process them within the system.

[0824] The "generative means" refers to the part that constructs the framework based on the received instructions and theme, and has the function of outlining the basic flow and outline of the story.

[0825] The "chapter generation mechanism" is the part that sequentially forms each chapter based on the generated outline, thereby detailing the story.

[0826] "Suggestion mechanism" refers to the part of the story that presents the next development to the user and offers them choices.

[0827] The "adjustment mechanism" refers to the part that dynamically updates the story's development based on user choices and emotional data, and has the function of adapting the tone and flow of the story.

[0828] "Display means" refers to the part that has an interface function to present the generated outline and publication options to the user.

[0829] "Automation means" refers to the part that has the function of executing a process to efficiently carry out the publishing process of the generated story and provide it to a designated platform.

[0830] The "emotional response generation mechanism" is a component that has the function of adjusting the content and development of the story based on the user's emotional state, and plays a role in supporting the individualization of the story.

[0831] "Means of delivery" refers to the part that has communication and distribution functions for transmitting the completed story to an external platform in electronic publishing format.

[0832] This invention is a system that allows users to generate original stories and easily publish them. This system mainly consists of a server and terminals, and dynamically generates stories based on user input and customizes the story according to the user's emotional state.

[0833] First, the user uses a terminal to input the instructions and theme of their desired story. This input is sent from the terminal to the server via a secure communication method (e.g., HTTPS). On the server, a generative AI model (for example, GPT-3 is a common model) is used to construct the story's framework based on the received instructions and theme. This generative AI model has advanced natural language processing capabilities and is capable of generating a wide variety of stories.

[0834] Next, the server uses a chapter generation mechanism based on the generated framework to detail the story chapter by chapter. At the end of each chapter, the server presents the user with a choice (prompt) to select the next course of action. For example, "You begin a new adventure in the land of magic. Choose one of the following options: 1. Confront the dragon, 2. Enter the Cave of Wisdom, 3. Explore the Magic Tree."

[0835] In this process, the server utilizes an emotion engine to detect the user's emotions. It analyzes data obtained from the camera and microphone connected to the device to understand the user's emotional state (for example, whether they are excited or not). Based on this information, an emotion response generation mechanism works to adjust and generate the content and tone of the next chapter.

[0836] When the story is complete, the server uses automated means to present the user with publishing options. Based on the option selected by the user, the service provider delivers the story in electronic publishing format to an external platform (e.g., an ebook store).

[0837] As described above, users can use this system to create and effectively distribute interactive, personalized stories. The system can provide a seamless and flexible process from story generation to publication.

[0838] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0839] Step 1:

[0840] The user uses a terminal to input the story's instructions and theme. This input is captured as text data, and the terminal prepares this data for transmission to the server. The input data is used as the requirements for generating the story.

[0841] Step 2:

[0842] The terminal sends instructions and subject data to the server. The HTTPS protocol is used for communication, ensuring security. The transmitted data is stored in a database on the server side and becomes input data for the generated AI model.

[0843] Step 3:

[0844] The server runs a generative AI model and generates a story outline based on the received instructions and theme. Here, machine learning algorithms are used to process the data and generate the text data of the outline. This generated outline will be refined in the next step.

[0845] Step 4:

[0846] The server operates the chapter generation mechanism based on the framework, generating the story chapter by chapter. Each chapter is constructed individually as text data, gradually putting the whole story together. The output is the text of each chapter.

[0847] Step 5:

[0848] At the end of each chapter, the server presents the user with a prompt (a choice of the next step). Once the user makes a choice, that selection is sent to the server. The prompt is text designed to visualize the progression of the story.

[0849] Step 6:

[0850] The server uses an emotion engine to analyze emotional data sent from the terminal. Specifically, it uses data obtained from the camera and microphone to analyze the user's facial expressions and tone of voice, and quantifies their emotional state. The analyzed emotional data is used as adjustment data for the story.

[0851] Step 7:

[0852] The server generates the next chapter based on selection data and emotion data. Utilizing emotion-responsive generation methods, it adjusts the tone and content of the story according to the user's emotions, generating chapters based on the user's choices. The output is the adjusted chapter text.

[0853] Step 8:

[0854] Once the story is complete, the server uses automated mechanisms to present the user with publishing options. Based on the user's selection, preparations are made to distribute the story to external platforms through the provided means. The user's choice is crucial in determining the publishing format.

[0855] Step 9:

[0856] The server provides the story to an external platform in electronic publishing format according to the selected publishing option. This process automatically handles conversion to the ebook file format and uploading to the publishing platform. The output is a published ebook.

[0857] (Application Example 2)

[0858] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0859] Providing personalized experiences based on user input is challenging in story generation. Furthermore, there is a need to enhance user satisfaction by dynamically changing the story in response to user emotions. Additionally, there is a lack of automated processes for easily publishing generated stories.

[0860] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0861] In this invention, the server includes a receiving means, a story framework generation means, and an emotion recognition means. This enables the generation of personalized stories that correspond to the user's emotional state based on user input, and their automatic publication.

[0862] A "receiving means" is a device that has the function of accurately receiving data and subject matter entered by the user.

[0863] The "first generation means" is a device that has the function of forming the framework of a story based on the received data and theme.

[0864] The "second generation means" is a device that has the function of sequentially generating each part of the story based on the generated framework.

[0865] A "presentation method" is a device that has the function of suggesting the next development to the user at the end of each part of the story.

[0866] An "emotion recognition means" is a device that detects the user's emotional state and has the function of adjusting the story's progression accordingly.

[0867] An "update mechanism" is a function that updates the story based on the user's chosen plot developments and emotional state.

[0868] "Selection options" refers to a function that presents users with options for editing the story's framework and publishing the work.

[0869] "Distribution method" refers to a device that has the function of transmitting the generated story in electronic format to a specified medium.

[0870] The system for realizing this invention consists of a user terminal and a server. The user uses a smartphone or other computer device to input keywords and themes into the terminal's interface. This information is transmitted from the terminal to the server.

[0871] The server first receives data and a subject from the user via a "receiving means." Then, using a "first generation means," it generates the framework of a story based on the received information. Specifically, a generation AI model processes prompt sentences and automatically generates the basic structure of the story. For example, OpenAI's GPT-3 can be used as the AI ​​model.

[0872] Next, the "second generation means" sequentially generates each part of the story chapter by chapter based on the generated framework. During this process, the "emotion recognition means" uses the user's device camera to detect emotions in real time and sends the data to the server. Software such as Microsoft Azure's Face API can be used for emotion recognition. Through this process, the story's development and tone are adjusted according to the user's emotions.

[0873] When a user selects the next development based on the "presentation method" presented at the end of each chapter, that information is sent back to the server. The "update method" then generates the next part of the story based on that selection and emotional data.

[0874] Furthermore, the "Selection Method" presents the user with editing and publishing options once the story is complete. If the user selects a specific publishing option, the story is automatically distributed to the specified medium in electronic format via the "Distribution Method."

[0875] For example, if a user enters "I want to enjoy an adventure story in a magical land" as a prompt themed around "fantasy" and "adventure," the system will generate a dynamic fantasy story based on that information. If the system recognizes that the user is excited, the story will unfold with action and surprises.

[0876] Example of a prompt:

[0877] "The theme is 'adventure.' The keywords are 'dragons' and 'magic.' Start creating a fantasy story that incorporates emotionally engaging plot development."

[0878] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0879] Step 1:

[0880] The user enters keywords and themes into the interface via their device. The device sends this information to the server as a prompt. The entered prompt includes themes and keywords such as "adventure" or "magic."

[0881] Step 2:

[0882] The server receives prompt messages sent by the user via its "receiving mechanism." Based on the received prompt messages, it performs analysis and stores them as information that forms the basis of the story.

[0883] Step 3:

[0884] Based on the information received by the server's "first generation means," a generative AI model is used to generate the framework of the story. Specifically, prompt text is input to a generative AI model such as GPT-3, and the basic structure of the story is output. At this time, appropriate settings and characters are automatically created based on keywords and themes.

[0885] Step 4:

[0886] The server's "second generation mechanism" sequentially generates chapters for each story based on the generated framework. At this time, the AI ​​model materializes the framework into a detailed storyline and constructs the story development for each chapter.

[0887] Step 5:

[0888] At the end of each chapter's generation, the server uses a "presentation mechanism" to offer the user options for the next development. The terminal receives the output from the generated AI model and presents the user with multiple choices.

[0889] Step 6:

[0890] The user selects from the options presented on the device. Furthermore, the device's camera analyzes the user's emotions in real time, and emotion data is acquired using an emotion recognition API. The device then sends the user's selection and emotion data to the server.

[0891] Step 7:

[0892] The server's "emotion recognition" and "update" mechanisms receive user selections and emotional data, and generate the next chapter based on the new data. The story's development and tone are adjusted based on the emotional data.

[0893] Step 8:

[0894] Once the entire story has been generated, the server presents the user with editing and publishing options through a "selection mechanism." The terminal displays this information to the user and asks for their choice.

[0895] Step 9:

[0896] When the user selects the distribution or publication option, the server's "distribution method" automatically distributes the story in electronic format to the specified platform. The terminal is notified when the entire process is complete.

[0897] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0898] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0899] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0900] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0901] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0902] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0903] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0904] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0905] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0906] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0907] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0908] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0909] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0910] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0911] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0912] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0913] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0914] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0915] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0916] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0917] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0918] The following is further disclosed regarding the embodiments described above.

[0919] (Claim 1)

[0920] An input means for receiving keywords and themes entered by the user,

[0921] A generation means for generating a novel plot based on the aforementioned keywords and themes,

[0922] A first generation means that sequentially generates each chapter of the novel based on the generated plot,

[0923] A suggestion mechanism that proposes the next development to the user at the end of each chapter,

[0924] An update method that updates the story based on the development selected by the user,

[0925] A presentation means for presenting the editing of the plot and options for publishing the work,

[0926] A publishing method that automates the publishing process,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, characterized in that the proposed means includes a second generating means that presents a plurality of options to the user and generates the next chapter based on the user's selection.

[0930] (Claim 3)

[0931] The system according to claim 1, characterized in that the publishing means includes distribution means for distributing a novel in ebook format to a designated platform.

[0932] "Example 1"

[0933] (Claim 1)

[0934] A receiving means for receiving words and topics entered by the user,

[0935] A structure generation means for generating the overall structure of a story based on the aforementioned words and themes,

[0936] A chapter generation means that sequentially generates each chapter of the story based on the generated overall structure,

[0937] A means of presenting the next development to the user at the end of each chapter,

[0938] A story update method that updates the story based on the development selected by the user,

[0939] An option presentation means that presents options for editing the overall structure and publishing the work,

[0940] A means of publishing that automates the publishing process,

[0941] A system that includes this.

[0942] (Claim 2)

[0943] The system according to claim 1, characterized in that the development presentation means includes a chapter generation function that presents a plurality of options to the user and generates the next chapter based on the user's selection.

[0944] (Claim 3)

[0945] The system according to claim 1, characterized in that the publishing means includes a distribution function for distributing a story in electronic book format to a designated information and communication infrastructure.

[0946] "Application Example 1"

[0947] (Claim 1)

[0948] An input means for receiving keywords and themes entered by the user,

[0949] A generation means for generating the overall structure of a story based on the aforementioned keywords and themes,

[0950] A first generation means that sequentially generates each chapter of the story based on the generated structure,

[0951] A suggestion mechanism that proposes the next development to the user at the end of each chapter,

[0952] An update mechanism that updates the story based on the developments chosen by the user,

[0953] AI methods that generate stories using generative AI models,

[0954] A presentation means that presents options for editing the aforementioned configuration and publishing the work,

[0955] A means of publishing that automates the publishing process,

[0956] A system that includes this.

[0957] (Claim 2)

[0958] The system according to claim 1, characterized in that the proposed means includes a second generating means that presents a plurality of options to the user and generates the next chapter based on the user's selection.

[0959] (Claim 3)

[0960] The system according to claim 1, characterized in that the publishing means includes a publishing means for publishing the story in the form of an electronic document to a designated platform.

[0961] "Example 2 of combining an emotion engine"

[0962] (Claim 1)

[0963] A receiving means for receiving instructions and topics input by the user,

[0964] A generation means for generating the outline of a story based on the aforementioned instructions and theme,

[0965] A chapter generation means that sequentially generates each chapter of the story based on the generated outline,

[0966] A suggestion mechanism that proposes the next development to the user upon completion of each chapter,

[0967] A means of adjusting the story based on the development selected by the user and the emotions detected,

[0968] A display means that presents options for editing the aforementioned outline and publishing the work,

[0969] Automation methods for performing the publication procedure automatically,

[0970] A system that includes this.

[0971] (Claim 2)

[0972] The system according to claim 1, characterized in that the proposed means includes emotion response generation means that presents a user with multiple options and generates the next chapter based on the user's selection and emotions.

[0973] (Claim 3)

[0974] The system according to claim 1, characterized in that the automation means includes a means for providing a story in electronic publishing format to a specified platform.

[0975] "Application example 2 when combining with an emotional engine"

[0976] (Claim 1)

[0977] A receiving means for receiving data and subject matter entered by the user,

[0978] A first generation means for generating the framework of a story based on the aforementioned data and theme,

[0979] A second generation means that sequentially generates each part of the story based on the generated framework,

[0980] A presentation mechanism that suggests the next development to the user at the end of each section,

[0981] An emotion recognition means that detects the user's emotional state and adjusts the story's development based on it,

[0982] An update mechanism that updates the story based on the development and emotions selected by the user,

[0983] A selection means that presents options for editing the aforementioned framework and publishing the work,

[0984] A distribution method that automates the publication process,

[0985] A system that includes this.

[0986] (Claim 2)

[0987] The system according to claim 1, characterized in that the presentation means includes a third generation means that presents a plurality of options to the user and generates the next part based on the user's selection and feelings.

[0988] (Claim 3)

[0989] The system according to claim 1, characterized in that the distribution means includes a transmission means for distributing a story in electronic format to a designated medium. [Explanation of Symbols]

[0990] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An input means for receiving keywords and themes entered by the user, A generation means for generating the overall structure of a story based on the aforementioned keywords and themes, A first generation means that sequentially generates each chapter of the story based on the generated structure, A suggestion mechanism that proposes the next development to the user at the end of each chapter, An update mechanism that updates the story based on the developments chosen by the user, AI methods that generate stories using generative AI models, A presentation means that presents options for editing the aforementioned configuration and publishing the work, A means of publishing that automates the publishing process, A system that includes this.

2. The system according to claim 1, characterized in that the proposed means includes a second generating means that presents a plurality of options to the user and generates the next chapter based on the user's selection.

3. The system according to claim 1, characterized in that the publishing means includes a distribution means for distributing the story in the form of an electronic document to a designated base.

Images