System
A system facilitating generative AI creators to register prompts and generate game content addresses the skill gap in game production, enhancing efficiency and creativity by allowing AI to produce and manage high-quality game content.
Patent Information
- Application Number
- JP2024122721
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2026-02-10
AI Technical Summary
Game production requires diverse skills that individuals or small organizations often lack, limiting the efficiency and creativity of content generation.
A system that allows generative AI creators to register prompts based on their drawing style, enabling game creators to input situations and characters, with the AI generating illustrations and music, and storing the content in a database for efficient management and provision.
Enables individuals and small organizations to efficiently generate and manage high-quality game content, promoting collaboration and reducing the time and effort required for content creation.
Smart Images

Figure 2026021039000001_ABST
Abstract
Description
[Technical Field]
[0001] The technology of the present disclosure relates to a system. [Background technology]
[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]
[0004] Game production requires a diverse skill set (e.g., graphic design, music production, character modeling), but it is difficult for individuals or small organizations to possess all of these skills. Furthermore, while the spread of generative artificial intelligence has given rise to new creators, opportunities for them to utilize their skill sets are limited. This current situation reduces the efficiency of content production and tends to restrict creative activities. This calls for the creation of an environment in which creators can freely generate and use high-quality content. [Means for solving the problem]
[0005] The present invention first provides a means for a generative AI creator to register prompts related to their drawing style. Next, it provides a means for the game creator to input an outline of the situation and characters based on the prompts. Furthermore, it provides a means for the generative AI to generate illustrations and music based on the input information, and provides a means for storing the generated content in a database. Finally, it constructs a system that includes a means for providing the generated content to the game creator. This realizes an environment in which even individuals or small organizations can efficiently generate and manage high-quality game content.
[0006] A "generative AI creator" is a person or entity with the skills to generate content (e.g., illustrations, music, 3D models, etc.) using artificial intelligence.
[0007] A "drawing style" is a characteristic method or pattern used by an individual creator to draw content using their own unique techniques and methods of expression.
[0008] A "prompt" is an instruction or condition provided by a generative AI creator to specify the characteristics or content of the content to be generated.
[0009] A "game creator" is a person or team involved in the development and design of a game, and is in a position to generate and use content.
[0010] A "situation" refers to a specific scene or situation within the game, including character behavior and background settings.
[0011] "Character Overview" is information that comprehensively describes the appearance, personality, role, etc. of the characters that appear in the game.
[0012] "Generative artificial intelligence" refers to algorithms or systems that automatically generate content such as images or music based on specified prompts or input information.
[0013] The "database" is a system for centrally storing and managing information such as generated content and registered prompts.
[0014] An "interface" is a means, such as a screen or input form, that allows a user to interact with a system and makes operation easier.
[0015] "Real-time" refers to processing that responds almost immediately to user input or operations, and is a characteristic that provides results without delay. [Brief explanation of the drawings]
[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION
[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.
[0018] First, the terms used in the following description will be explained.
[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).
[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.
[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.
[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.
[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."
[0024] [First embodiment]
[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.
[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.
[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.
[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.
[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.
[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0037] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[0038] overview
[0039] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[0040] Program processing
[0041] 1. Generative AI creator registers a prompt
[0042] User (generative AI creator)
[0043] Fill in the prompts based on your drawing style through a web form.
[0044] The form has a text entry field where creators can describe their prompt in detail.
[0045] Terminal
[0046] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[0047] server
[0048] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[0049] 2. Game creators use prompts to generate content
[0050] User (game creator)
[0051] Select the prompt you want to generate from the prompt list and access the input form to specify character details and the situation.
[0052] Enter the required information and click the Generate button to send a generation request to the server.
[0053] Terminal
[0054] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[0055] server
[0056] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[0057] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[0058] The generated content is temporarily stored and the generation results are returned to the game creator.
[0059] 3. Store and manage generated content
[0060] User (game creator)
[0061] You can check the generated content displayed on the screen and save it by clicking the save button.
[0062] It can also be modified and regenerated as needed.
[0063] Terminal
[0064] When the save button is clicked, the generated content is sent to the server API in JSON format.
[0065] server
[0066] The received generated content is saved in a database and a response indicating success is returned to the client.
[0067] Supports the management and provision of generated content, making it easily accessible to game creators.
[0068] Specific examples
[0069] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[0070] 1. Generative AI Creator
[0071] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[0072] 2. Game Creator
[0073] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[0074] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[0075] 3. Generated results
[0076] Illustrations generated by AI are provided to game creators via a server.
[0077] The game creator checks the generated content and saves it.
[0078] This will promote collaboration between generative AI creators and game creators, and create a system that provides an environment in which even individuals and small organizations can efficiently generate and manage high-quality game content.
[0079] The processing flow will be explained below.
[0080] Step 1:
[0081] The user (generative AI creator) accesses a web form and fills in prompts based on their own drawing style.
[0082] Step 2:
[0083] The device captures the web form submit event and retrieves the input prompt in JavaScript.
[0084] Step 3:
[0085] The device converts the prompt into JSON format and sends it to the server's API endpoint.
[0086] Step 4:
[0087] The server saves the received prompt data in the database and generates a response indicating that the save was successful.
[0088] Step 5:
[0089] The server returns a successful save response to the device.
[0090] Step 6:
[0091] The user (game creator) accesses the prompt list page and selects the prompt they want to create.
[0092] Step 7:
[0093] Based on the prompt selected by the user (game creator), the necessary information is entered into an input form for entering character details and the situation.
[0094] Step 8:
[0095] The terminal captures the form submit event and obtains the selected prompt ID and the user's input.
[0096] Step 9:
[0097] The device converts the prompt ID and the user's input into JSON format and sends it to the server's API endpoint.
[0098] Step 10:
[0099] The server retrieves the corresponding prompt from the database based on the prompt ID received and the user input.
[0100] Step 11:
[0101] The server passes the obtained prompt and user input information to the AI generation service, instructing it to generate content.
[0102] Step 12:
[0103] The server receives the generated content from the AI generation service and temporarily stores it.
[0104] Step 13:
[0105] The server returns the generated results to the terminal.
[0106] Step 14:
[0107] The device displays the generated results on the user's (game creator's) screen so that they can be checked.
[0108] Step 15:
[0109] The user (game creator) clicks the save button for the generated content.
[0110] Step 16:
[0111] The device captures the click event of the save button, converts the generated content into JSON format, and sends it to the server's API endpoint.
[0112] Step 17:
[0113] The server saves the received generated content in the database and generates a response indicating that saving was successful.
[0114] Step 18:
[0115] The server returns a successful save response to the device.
[0116] Step 19:
[0117] The device displays a message indicating successful saving on the user's (game creator's) screen.
[0118] The above is the specific operational flow of each processing step in the present invention. This will realize an environment in which AI creators and game creators can work together to efficiently generate and manage high-quality game content.
[0119] Example 1
[0120] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0121] Previous game content generation systems had issues such as creators being unable to effectively use prompts based on their own drawing style, and the time and effort required to check, modify, and regenerate generated content. Furthermore, there was a lack of a way to display generated content in real time and easily save it.
[0122] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[0123] In this invention, the server includes a means for a generation AI creator to register prompts regarding their drawing style, a means for a game creator to input an outline of a situation or character, a means for the generation AI to generate illustrations and music, a means for saving the generated content in a database, a means for the game creator to check, modify, regenerate, and save the generated content, and a means for displaying the generated content in real time and processing save requests, thereby enabling creators to efficiently generate high-quality content and instantly check, modify, and save it.
[0124] A "generative AI creator" is a creator who creates and registers prompts based on their own drawing style.
[0125] A "prompt" is a text description of instructions and conditions for generating content such as illustrations and music.
[0126] A "game creator" is a creator whose role is to input an outline of the situation and characters based on prompts and instruct the generation of game content.
[0127] A "situation" is a specific description of a scene or situation within the game.
[0128] "Character Overview" is information that describes the character's appearance, personality, behavior, etc.
[0129] "Generative AI" is AI that automatically generates content such as illustrations and music based on input information.
[0130] A "database" is a system that permanently stores and manages data such as generated content and prompts.
[0131] An "interface" is a screen or tool that provides an input means for a user to register a prompt or enter information.
[0132] A "generation request" is a request that a game creator inputs detailed information about the content to be generated based on a prompt and sends to the server.
[0133] A "storage request" is a request sent to a server to store generated content in a database.
[0134] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[0135] overview
[0136] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[0137] Additionally, generated content can be easily reviewed, modified, regenerated, and saved, and creation and saving requests are handled in real time.
[0138] Program processing
[0139] Generative AI creator registers prompts
[0140] User (generative AI creator)
[0141] Through a web form, users enter prompts based on their drawing style, such as "fantasy character, young wizard in blue robes, with a magical tower in the background."
[0142] Terminal
[0143] When the form is submitted, JavaScript takes the prompt content, converts it to JSON format, and sends it to the server's API.
[0144] server
[0145] The server saves the received prompt data in a database and returns a response indicating that the save was successful to the client.
[0146] Game creators use prompts to generate content
[0147] User (game creator)
[0148] The user selects the prompt they want to generate from a list of prompts, enters details about the character, such as "A young wizard undergoes trials to become a full-fledged wizard," and clicks the Generate button to send a generation request to the server.
[0149] Terminal
[0150] JavaScript gets the selected prompt ID and the user's input, converts it into JSON format, and sends it to the server's API.
[0151] server
[0152] The server retrieves the prompt from the database and calls the AI generation service along with the user's input information. The AI generation service is used to automatically generate content such as a scene in which a young wizard in a blue robe is put to the test in front of a magical tower. The generated content is temporarily saved and the results are returned to the game creator.
[0153] Store and manage generated content
[0154] User (game creator)
[0155] The user can check the generated content displayed on the screen, and modify or regenerate it as necessary. The generated content is saved by clicking the Save button.
[0156] Terminal
[0157] When the save button is clicked, the generated content is sent to the server API in JSON format.
[0158] server
[0159] The server stores the generated content in a database and returns a successful save response to the client. This system enables creators to efficiently generate high-quality content and instantly check, modify, and save it.
[0160] For example, a generative AI creator can register a prompt to draw a fantasy character, and a game creator can generate a brave young wizard. By using this system, creators can efficiently generate and manage high-quality game content.
[0161] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0162] Step 1:
[0163] User (generative AI creator)
[0164] Input: Enter a prompt into a web form, such as "Fantasy character, young wizard in blue robes, with a magical tower in the background."
[0165] How it works: A generative AI creator visits a specific web form and fills in text fields with prompts that reflect their drawing style.
[0166] Output: The prompt text entered.
[0167] Step 2:
[0168] Terminal
[0169] Input: The prompt text entered into the web form.
[0170] How it works: When the submit button on the form is clicked, a JavaScript is triggered that retrieves the prompt text that was entered.
[0171] Data processing: Convert the obtained prompt text into JSON format.
[0172] Output: Prompt data in JSON format.
[0173] Step 3:
[0174] server
[0175] Input: Prompt data sent from the terminal in JSON format.
[0176] Operation: The server stores the received prompt data in a database.
[0177] Output: Save result (success or failure response) to database.
[0178] Step 4:
[0179] User (game creator)
[0180] Input: A request to generate content based on a saved prompt. Specifically, you select a prompt and enter character details and a situation, such as "A young wizard undergoes trials to become a full wizard."
[0181] How it works: The game creator selects the prompt they want to generate from the prompt list screen and enters character details and the situation.
[0182] Output: The generated request and associated input information.
[0183] Step 5:
[0184] Terminal
[0185] Input: The generated request and prompt ID entered by the user.
[0186] What it does: JavaScript takes the generated request and prompt ID and converts it to JSON format.
[0187] Data processing: The generation request and prompt ID converted to JSON format are sent to the server API.
[0188] Output: Generated request data in JSON format.
[0189] Step 6:
[0190] server
[0191] Input: The generated request data in JSON format sent from the terminal.
[0192] How it works: The server retrieves prompt data from the database based on the prompt ID, then passes the prompt data and a generation request to the AI generation service.
[0193] Data Computing: AI generation services auto-generate content such as illustrations and music based on prompts and generation requests.
[0194] Output: The generated content and the generated result (success or failure response).
[0195] Step 7:
[0196] server
[0197] Input: Generated content from an AI-generated service.
[0198] How it works: The server temporarily stores the generated content and returns the generated results to the game creator.
[0199] Output: The URL or file path of the generated content.
[0200] Step 8:
[0201] User (game creator)
[0202] Input: The URL or file path of the generated content.
[0203] Action: The game creator reviews the generated content displayed, modifies it or regenerates it as needed, and clicks the Save button if they wish to save it.
[0204] Output: Save request.
[0205] Step 9:
[0206] Terminal
[0207] Input: Save request and generated content.
[0208] What it does: JavaScript converts the save request and generated content into JSON format.
[0209] Data processing: The save request and generated content converted into JSON format are sent to the server's API.
[0210] Output: Save request data in JSON format.
[0211] Step 10:
[0212] server
[0213] Input: Save request data sent from the device in JSON format.
[0214] Operation: The server stores the received save request data in a database.
[0215] Output: Save result (success or failure response) to database.
[0216] (Application example 1)
[0217] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0218] With conventional content generation systems, collaboration between general users and professional creators was difficult, making it difficult to quickly and efficiently materialize users' ideas. Furthermore, the storage and management of generated content was also inefficient, resulting in problems such as a decline in content quality and productivity.
[0219] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0220] In this invention, the server includes means for a generating AI creator to register prompts related to their drawing style, means for a content creator to input an outline of a situation or character, means for the generating AI to generate illustrations, music, and video, means for saving the generated content in a database, means for providing the generated content to the content creator, means for providing an interface for the generating AI creator to register prompts, and means for displaying content generated in real time based on the outline of a situation or character input by the content creator. This enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality.
[0221] A "generative AI creator" refers to an AI that registers prompts related to one's drawing style and contributes to content generation based on those prompts.
[0222] A "prompt" is a piece of text or keyword that provides instructions or guidelines for a generative AI model to generate a particular depiction or situation.
[0223] "Content creators" refer to users who input a situation or character outline based on prompts and use or edit the content generated by the generative AI.
[0224] A "situation" is information that describes a specific scene or setting, providing the background or environment for a generative AI model to generate content.
[0225] "Character Description" refers to text describing the characteristics and details of a character used in content generation.
[0226] "Generative AI" refers to AI that has the technology to automatically generate content such as illustrations, music, and video based on prompts and additional input information.
[0227] "Content" refers to digital works such as illustrations, music, and video created by generative AI models.
[0228] "Database" refers to a digital storage system for storing and managing Generated Content.
[0229] "Interface" means the web form or application user interface for entering and registering a Student Configuration Prompt.
[0230] "Real-time" refers to the system's ability to respond almost immediately to input information and quickly display generated content.
[0231] This embodiment of the present invention relates to a system in which a user generates content using a generative AI model, stores the content in a database, and provides it to other users. In this system, a server, a terminal, and users (generative AI creators and content creators) work together to perform processing.
[0232] Overall processing overview of the program
[0233] 1. Generative AI creator registers prompt
[0234] user:
[0235] Generative AI creators use a dedicated web form to enter prompts based on their drawing style, such as specific drawing guidelines like "underwater city, futuristic design, adventurer adventure scene."
[0236] Device:
[0237] The prompt information entered into the form by the artificial intelligence creator is obtained using JavaScript and sent to the server's API in JSON format.
[0238] server:
[0239] The received prompt data is saved in the database and a response indicating successful saving is returned to the client (user).
[0240] 2. Content creators use prompts to generate content
[0241] user:
[0242] Content creators select a prompt they want to generate from a list of prompts and enter a brief description of the characters and situation, such as "a scene in which an adventurer finds treasure in a futuristic underwater city."
[0243] Device:
[0244] Obtain the selected prompt ID and detailed information about the character and situation, and send it in JSON format to the server's API.
[0245] server:
[0246] The system retrieves a prompt from the database and calls an AI generation service (e.g., OpenAI GPT-4 or Stable Diffusion) along with the user's input. The AI generation service automatically generates content such as illustrations, music, and video based on the specified prompt and input. The generated content is then temporarily stored and returned to the content creator.
[0247] 3. Store and manage generated content
[0248] user:
[0249] The content creator can review the generated content and, if satisfied, press the "Save" button to save the content to the database. It can also be modified or regenerated as needed.
[0250] Device:
[0251] Once the save button is clicked, the generated content is sent to the server API in JSON format.
[0252] server:
[0253] It stores the received generated content in a database and returns a successful save response to the client, making it easier to manage and serve generated content and make it easily accessible to content creators.
[0254] Specific step-by-step instructions
[0255] Server Roles and Configuration
[0256] The server includes the following means:
[0257] A means for generative AI creators to register prompts.
[0258] A way for content creators to input situations and character descriptions.
[0259] A means for generative AI to generate illustrations, music, and video.
[0260] A means of storing generated content in a database.
[0261] A means of providing generated content to content creators.
[0262] A means to provide an interface for generative AI creators to register prompts.
[0263] A means of displaying content generated in real time based on situations and character descriptions entered by content creators.
[0264] This will enable efficient collaboration between general users and professional creators, and will enable users' ideas to be realized quickly and with high quality. Below are some examples of prompt sentences:
[0265] Prompt: Underwater city, futuristic design, adventurer adventure scene
[0266] Details: Underwater city features transparent domes, alien colonies, and hidden treasure
[0267] In this way, the present invention realizes a system that allows users to register prompts based on their own ideas and visual and auditory instructions, and efficiently manage, store, and use the generated content.
[0268] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0269] Step 1:
[0270] This is the stage where the user (generative AI creator) registers a prompt. The user enters a prompt based on their own drawing style into a dedicated web form. The entered prompt is converted into JSON format using JavaScript. The device sends this JSON data to the server's API. The server saves the received prompt data in a database and returns a successful save response to the client (user). For example, a prompt such as "underwater city, futuristic design, scene of adventurers on an adventure" can be entered here.
[0271] Input: User input for prompt (text)
[0272] Output: JSON format prompt data, save success response
[0273] Step 2:
[0274] The server retrieves the saved prompt data from the database. The user (content creator) selects the prompt they want to generate from the prompt list and enters a summary of the situation and character. This detailed information is also converted into JSON format and sent from the device to the server's API. The server retrieves the corresponding prompt from the database based on the received data.
[0275] Input: Prompt ID, situation, character summary (text)
[0276] Output: Prompts and detailed information from the database
[0277] Step 3:
[0278] The server calls the AI generation service using the obtained prompt and the input situation and character summary. It sends the prompt and detailed information to the AI generation service (e.g., OpenAI GPT-4, Stable Diffusion). The AI generation service generates content such as illustrations, music, and video based on this information. This generated content is temporarily stored on the server.
[0279] Input: Prompt, Situation, Character Summary (Text)
[0280] Output: Generated content such as illustrations, music, and videos
[0281] Step 4:
[0282] The server provides the generated content to the content creator. The user (content creator) can review the provided content and make further corrections or additions. An interface displaying the generated content in real time is displayed on the terminal. The content creator can request regeneration as needed.
[0283] Input: Generated content, corrections and additional input (text)
[0284] Output: Display of content updated in real time
[0285] Step 5:
[0286] If the content creator is satisfied with the generated content, they press the save button to save it to the server. When the save button is pressed, the device converts the generated content into JSON format and sends it to the server's API. The server saves the received generated content in its database and returns a successful save response to the client.
[0287] Input: Press the save button, generated content (JSON format)
[0288] Output: Content saved to database, save success response
[0289] In this way, the system enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality, while the generated content is efficiently managed, stored, and used.
[0290] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.
[0291] This invention is an improvement to a system in which a generative AI creator registers prompts related to their drawing style, and a game creator generates the necessary content based on those prompts, by combining it with an emotion engine that recognizes the user's emotions and adjusts the generated content to match the user's emotions. In this system, the server, terminal, and user (generative AI creator, game creator) work together to perform processing and improve the quality of the generated content.
[0292] overview
[0293] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on the prompts, (3) the AI generates content based on the input, (4) the emotion engine recognizes the user's emotions and adjusts the generated content, (5) the generated content is saved and managed, and (6) it is provided to the game creator.
[0294] Program processing
[0295] 1. Generative AI creator registers a prompt
[0296] User (generative AI creator)
[0297] Access a web form and fill out prompts based on your drawing style.
[0298] The form has a text entry field where creators can describe their prompt in detail.
[0299] Terminal
[0300] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[0301] server
[0302] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[0303] 2. Game creators use prompts to generate content
[0304] User (game creator)
[0305] Select the prompt you want to generate from the prompt list and enter the required information in the input form to specify the character details and situation.
[0306] Enter the required information and click the Generate button to send a generation request to the server.
[0307] Terminal
[0308] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[0309] server
[0310] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[0311] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[0312] The generated content is temporarily stored and the generation results are returned to the game creator.
[0313] 3. Tuning the emotion engine and generated content
[0314] Terminal
[0315] When game creators check the generated content, sensors such as cameras and microphones are activated to recognize the user's emotions.
[0316] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates emotion data.
[0317] server
[0318] Based on the emotion data sent from the emotion engine, the generated content is evaluated to see if it matches the user's emotion.
[0319] Run a regeneration and tweak process to adjust the content as needed.
[0320] 4. Store and manage generated content
[0321] User (game creator)
[0322] You can check the generated content displayed on the screen and save it by clicking the save button.
[0323] It can also be modified and regenerated as needed.
[0324] Terminal
[0325] When the save button is clicked, the generated content is sent to the server API in JSON format.
[0326] server
[0327] The received generated content is saved in a database and a response indicating success is returned to the client.
[0328] Supports the management and provision of generated content, making it easily accessible to game creators.
[0329] Specific examples
[0330] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[0331] 1. Generative AI Creator
[0332] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[0333] 2. Game Creator
[0334] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[0335] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[0336] 3. Emotion Engine
[0337] Analyze game creators' emotions in real time to ensure the generated content meets expectations.
[0338] If the emotion does not match, it instructs the AI generation service to regenerate it.
[0339] 4. Generated results
[0340] Illustrations generated by AI are provided to game creators via a server.
[0341] Optimized content is provided based on the results confirmed through the emotion engine.
[0342] The game creator checks the generated content and saves it.
[0343] This will enable collaboration between generative AI creators, game creators, and emotion engines, providing an environment in which high-quality game content that matches user emotions can be efficiently generated and managed.
[0344] The processing flow will be explained below.
[0345] Step 1:
[0346] The user (generative AI creator) accesses a web form and enters a prompt based on their drawing style. The form includes a text input field where the creator can further describe the prompt.
[0347] Step 2:
[0348] The device captures the submit event of the web form, gets the prompt entered in JavaScript, converts the input into JSON format, and sends it to the server's API endpoint.
[0349] Step 3:
[0350] The server saves the received prompt data in the database. After the save process is complete, it generates a save success response and returns it to the client.
[0351] Step 4:
[0352] The user (game creator) accesses the prompt list page and selects the prompt they want to create. Based on the selected prompt, they enter the necessary information into the input form to specify the character details and situation.
[0353] Step 5:
[0354] The terminal captures the form submission event, obtains the selected prompt ID and the user's input, converts it to JSON format, and sends it to the server's API endpoint.
[0355] Step 6:
[0356] The server retrieves the corresponding prompt from the database based on the received prompt ID and user input, passes the retrieved prompt and user input information to the AI generation service, and instructs it to generate content.
[0357] Step 7:
[0358] The server receives the generated content from the AI generation service, temporarily stores it, and returns the generated results to the game creator.
[0359] Step 8:
[0360] The device displays the generated content on the user's (game creator's) screen. When the user checks the generated content, sensors such as the device's camera and microphone are activated to collect emotional data.
[0361] Step 9:
[0362] The emotion engine analyzes the user's facial expressions and tone of voice in real time to generate emotion data, which is then sent to the server.
[0363] Step 10:
[0364] The server evaluates whether the generated content matches the user's emotions based on the emotion data received from the emotion engine. Based on the evaluation results, the content is regenerated or fine-tuned as necessary.
[0365] Step 11:
[0366] The server returns the adjusted generated content to the device, and the user (game creator) checks the generated content again.
[0367] Step 12:
[0368] When the user (game creator) is satisfied with the generated content, they click the save button. The device then captures the save button click event, converts the generated content into JSON format, and sends it to the server's API endpoint.
[0369] Step 13:
[0370] The server saves the generated content it receives in the database. After the save process is complete, it generates a save success response and returns it to the client.
[0371] Step 14:
[0372] The device displays a message indicating successful saving on the user's (game creator's) screen.
[0373] The above is the specific flow of operation for each processing step in this invention. This allows AI creators and game creators to work together, and by introducing an emotion engine, an environment is realized in which high-quality game content that matches the user's emotions can be efficiently generated and managed.
[0374] Example 2
[0375] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0376] Current content generation systems using generative AI do not take user emotions into account, so the generated content may not necessarily match the user's expectations or emotions. This poses challenges in improving the user experience and optimizing the quality of generated content.
[0377] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0378] In this invention, the server includes means for a generation device creator to register instructions regarding his or her drawing style, means for a developer to input an outline of the situation and characters based on the instructions, means for the generation device to generate video and audio based on the input information, means for saving the generated content in a data storage device, means for providing the generated content to the developer, means for acquiring user emotions using a sensing device and analyzing them with an emotion engine, and means for adjusting the generated content based on the analysis results, thereby making it possible to generate and provide high-quality content that matches the user's emotions.
[0379] A "generator creator" is a user who is responsible for registering instructions based on their own drawing style and concept into the system.
[0380] "Instructions" are information that details the style and specific elements of the content to be generated.
[0381] The "developer" is a user who inputs details about the situation and characters based on the generated prompts, and then generates and checks the final content.
[0382] "Context" is information that indicates a specific situation or background of the generated content.
[0383] "Characters" refers to information that refers to the characters and character details that appear in the generated content.
[0384] A "generation device" is an artificial intelligence system that automatically generates content such as video and audio based on information entered by the user.
[0385] "Video" is a form of visual content, including illustrations, animations, and videos.
[0386] "Audio" refers to a form of auditory content, including music, sound effects, narration, etc.
[0387] A "data store" is a physical or virtual storage system for storing generated content.
[0388] A "sensing device" is a device used to acquire emotional data of a user, and includes a camera, a microphone, and the like.
[0389] The "emotion engine" is a software component that analyzes acquired emotion data and evaluates the user's emotional state.
[0390] The "analysis results" are information about the user's emotional state obtained by the emotion engine.
[0391] "Tuning" is the process of modifying or regenerating generated content to match the user's emotional state.
[0392] "Content" refers to content such as video and audio automatically created by a generating device.
[0393] This invention is a system in which a generator creator registers instructions (prompts) based on their own drawing style and concept into the system, and a developer uses the prompts to input details of the situation and characters, and the generator generates content such as video and audio. This generated content is adjusted by acquiring the user's emotions using a sensing device and analyzing them with an emotion engine, providing high-quality content that matches the user's emotions.
[0394] Specifically, the system is implemented according to the following steps: First, the creator of the generator accesses the web interface and describes in detail their drawing style and the characteristics of their work. The input prompt is obtained by JavaScript on the device, converted into JSON format, and sent to the server's API. The server saves this prompt data in a data storage device and returns a response to the device indicating that the save was successful.
[0395] Next, the developer selects the desired prompt from a list of prompts and enters a summary of the situation and character. For example, the developer selects "Fantasy character, young wizard in blue robes, against a magical tower background" as the prompt and enters "Young wizard undergoes trials to become a full wizard" as the character details. This input is captured on the device and sent back to the server's API in JSON format.
[0396] The server then passes prompts and additional information to the AI generation service based on the received data. The AI generation service then automatically generates content such as video and audio based on this information. The generated content is temporarily stored in a data storage device, and the generated results are returned to the developer.
[0397] When the developer checks the generated content, sensing devices (cameras and microphones) are activated to capture the user's emotional data in real time. The emotion engine analyzes this data, evaluates whether the generated content matches the user's emotions, and regenerates or fine-tunes it as necessary.
[0398] For example, consider a scenario where a developer wants to generate a scene depicting a young wizard undergoing a trial using a prompt registered by a generator creator: "Fantasy character, young wizard in blue robes, with a magical tower in the background." The generator uses this information to generate the corresponding video and evaluates and adjusts the generated content using a sensing device and emotion engine. Ultimately, high-quality content that matches the user's emotions is provided, and the developer can save the content.
[0399] In this way, the present invention realizes efficient generation and management of high-quality content that reflects the user's emotions through collaboration between generation device creators, developers, sensing devices, and emotion engines.
[0400] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0401] Step 1:
[0402] The user (generator creator) accesses a web interface and inputs instructions (prompts) describing their drawing style and the characteristics of their work. For example, they might input "a fantasy character, a young wizard in a blue robe, with a magical tower as the background." The input instructions are retrieved using JavaScript on the device. Input: The prompt text entered by the user into the web form. Output: The prompt text is converted to JSON format.
[0403] Step 2:
[0404] The terminal converts the prompt text into JSON format and sends it as a POST request to the server's API. At this time, by sending data to a specific endpoint, the server prepares to receive the instruction data. Input: Prompt text in JSON format. Output: POST request sent to the server.
[0405] Step 3:
[0406] The server parses the received JSON data and validates the contents before saving it to the database. If the validation is successful, the data is saved to the database and a response indicating successful saving is returned to the terminal. Input: Prompt text in JSON format sent to the server. Output: Prompt text is saved to the database and a response indicating successful saving is returned.
[0407] Step 4:
[0408] The user (developer) selects the desired prompt from the prompt list and enters details of the situation and characters. For example, "A young wizard undergoes the trials to become a full-fledged wizard." Input: The prompt ID selected from the prompt list and additional information from the user. Output: The generation request converted to JSON format.
[0409] Step 5:
[0410] The terminal converts the selected prompt ID and additional information into JSON format and sends it to the server's API. Input: Prompt ID and user's additional information. Output: Sends a generation request to the server.
[0411] Step 6:
[0412] The server receives the generation request, retrieves a prompt from the database, and then passes the prompt and additional information to the AI generation service. The AI generation service uses this information to generate content such as video and audio. The generated content is stored in a temporary storage area on the server. Input: Generation request sent to the server. Output: Generated content.
[0413] Step 7:
[0414] The server stores the generated content in a temporary storage area and returns the generated result to the end user. Input: Generated content. Output: Return of generated result to the end user.
[0415] Step 8:
[0416] When a user (developer) checks the generated content, sensing devices (camera and microphone) connected to the device collect the user's emotional data. For example, the camera detects the user's facial expressions, and the microphone detects the tone of voice. Input: Generated content and user's emotional data. Output: Collected emotional data.
[0417] Step 9:
[0418] The device sends the collected emotion data to the server in real time. Input: Collected emotion data. Output: Sending emotion data to the server.
[0419] Step 10:
[0420] The server passes emotional data to the emotion engine for analysis. Based on the analysis results, it evaluates how well the generated content matches the user's emotions and regenerates or fine-tunes it as necessary. Input: Emotion data passed to the emotion engine. Output: Analysis results and adjustment instructions.
[0421] Step 11:
[0422] The server finally provides the adjusted generated content to the end user, allowing the user to review the content. Input: Adjusted generated content. Output: Provided to the end user.
[0423] Step 12:
[0424] The user (developer) checks the generated content displayed on the screen and saves it by clicking the save button. It is also possible to modify or regenerate the content as needed. Input: User actions on the generated content. Output: The final saved content.
[0425] (Application example 2)
[0426] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0427] Conventional content generation systems using generative artificial intelligence have had difficulty generating content that matches the user's emotions. In the entertainment field in particular, there is a demand for content that responds to the user's emotions and reactions. Therefore, there is a need for technology that can recognize user emotions in real time and adjust and optimize content based on those emotions.
[0428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[0429] In this invention, the server includes means for the generating AI creator to register prompts related to his / her drawing style, means for the game creator to input an outline of the situation and characters, means for the generating AI to generate illustrations and music based on the input information, means for saving the generated content in a database, means for providing the generated content to the game creator, means for adjusting the generated content using an emotion engine that recognizes the user's emotions, and means for providing the adjusted content to the user, thereby enabling the generation of content that matches the user's emotions.
[0430] The "generative AI creator" is an AI that is responsible for registering prompts based on its own drawing style.
[0431] A "prompt" is a sentence or keyword that a generative AI model uses as an instruction to generate content.
[0432] A "game creator" is a user whose role is to input a summary of the situation and characters based on prompts.
[0433] "Situation" refers to the specific scene or situation in which a character is placed within a game.
[0434] "Character Overview" refers to the basic characteristics and background information of characters that appear in the game.
[0435] "Generative AI" is AI that generates content such as illustrations and music based on input information.
[0436] A "database" is a system that stores generated content and makes it accessible as needed.
[0437] The "emotion engine" is a system that recognizes the user's emotions in real time and acquires that data.
[0438] "Adjustment" refers to the process of making changes to the generated content based on the user's emotions as recognized by the emotion engine.
[0439] "Means" refers to a device, method, or composition of matter employed to accomplish a particular purpose.
[0440] This embodiment describes a system for generating and providing entertainment content that matches a user's emotions. This system features a generative AI creator registering prompts, a game creator using the prompts to generate content, and an emotion engine adjusting the generated content based on the user's emotions.
[0441] Hardware and software used
[0442] Hardware
[0443] Smartphone or head-mounted display (HMD)
[0444] Camera and microphone for emotion recognition by the emotion engine
[0445] software
[0446] JavaScript (front-end data processing)
[0447] Python (server-side script)
[0448] TensorFlow (a machine learning framework for emotion recognition)
[0449] OpenAI API (generative AI models for content generation)
[0450] Detailed process description
[0451] 1. Prompt registration by generative AI creator
[0452] Users, or generative AI creators, submit prompts based on their drawing style through a web form, such as "a fantasy character, a young wizard in blue robes, with a magical tower in the background."
[0453] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[0454] The server stores the received prompt data in a database and returns a response indicating successful storage to the client.
[0455] 2. Content generation by game creators
[0456] The user, the game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and the situation, such as "a scene in which a young wizard is put to the test."
[0457] On the terminal, the selected prompt ID and the user's input are sent to the server API in JSON format.
[0458] The server retrieves prompts from the database and calls the OpenAI API based on the user's input. The AI generates content such as illustrations and music based on the specified prompts and input.
[0459] 3. Content adjustment using emotion engines
[0460] When a user checks the content generated on the device, the camera and microphone are activated to recognize emotions. Facial expressions and tone of voice are analyzed in real time to obtain emotional data.
[0461] The server evaluates whether the generated content matches the user's emotion based on the emotion data sent from the emotion engine. If the emotion does not match, it instructs the AI generation service to regenerate the content.
[0462] 4. Storing and Managing Generated Content
[0463] The user can review the generated content and save it by clicking the save button, and can also regenerate or fine-tune it as needed.
[0464] 5. Specific Examples
[0465] Example prompt from a generative AI creator: "A quiet street lit by streetlights on a new moon night."
[0466] Example input from a game creator: "A scene in which the main character walks through a quiet street."
[0467] These operations enable the generation and provision of high-quality game content that responds to the user's emotions.
[0468] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0469] Step 1:
[0470] The user, a generative AI creator, registers prompts based on their drawing style through a web form.
[0471] Input: The prompt text entered by the user into the web form
[0472] Specific Action: A user accesses a web form, enters text based on their drawing style, and clicks the submit button.
[0473] Step 2:
[0474] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[0475] Input: Prompt text taken from a web form
[0476] Data processing: Convert the input text into JSON format
[0477] Output: API request to the server
[0478] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[0479] Step 3:
[0480] The server saves the prompt data received in the database and returns a response indicating success to the client.
[0481] Input: Prompt data in JSON format
[0482] Data processing: Convert prompt data into database format
[0483] Output: Save successful response
[0484] What happens: The server-side script opens a database connection, saves the prompt data, and returns a response to the client if successful.
[0485] Step 4:
[0486] The user, a game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and situation.
[0487] Input: Prompt ID, character details, situation text
[0488] What happens: A game creator visits a web form, selects a prompt from a drop-down menu, enters the required details, and submits it.
[0489] Step 5:
[0490] On the terminal, the selected prompt ID and the user's input are sent to the server's API in JSON format.
[0491] Input: Prompt ID, character details, situation text
[0492] Data processing: Convert this information into JSON format
[0493] Output: API request to the server
[0494] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[0495] Step 6:
[0496] The server retrieves prompts from the database and generates content by calling OpenAI's API along with the user's input information.
[0497] Input: Prompt ID, character details, situation text
[0498] Data processing: Retrieve prompts from the database, combine them with user input, and send them to the OpenAI API
[0499] Output: Generated content
[0500] What happens: A server-side script opens a database connection, retrieves prompt data, and calls the OpenAI API to generate content.
[0501] Step 7:
[0502] The generated content is temporarily stored and the generation results are returned to the game creator.
[0503] Input: Generated content
[0504] Data storage: temporarily stores generated content
[0505] Output: The generated response
[0506] Specific operation: The server-side script temporarily stores the generated content and returns the generated result to the client.
[0507] Step 8:
[0508] When a user checks the generated content on the terminal, the camera and microphone are activated to analyze facial expressions and tone of voice in real time and obtain emotional data.
[0509] Input: User's facial expression and tone of voice
[0510] Data processing: Analyze acquired data into emotion data
[0511] Output: Emotion data
[0512] Specific operation: The camera and microphone capture the user's facial expressions and voice, and the emotion engine analyzes them in real time.
[0513] Step 9:
[0514] Based on the emotion data transmitted from the emotion engine, the server evaluates whether the generated content matches the user's emotion, and issues an instruction to regenerate the content if necessary.
[0515] Input: emotion data, generated content
[0516] Data evaluation: Evaluate the degree of agreement between emotion data and generated content
[0517] Output: Regeneration instructions (if necessary)
[0518] Specific operation: A server-side script analyzes the emotion data, evaluates the degree of match of the generated content, and issues instructions for regeneration if necessary.
[0519] Step 10:
[0520] The user checks the generated content and saves it by clicking the save button.
[0521] Input: Generated content
[0522] Output: Saved content
[0523] Specific operation: The user checks the generated content in the browser and clicks the save button to save the content.
[0524] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0525] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0526] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.
[0527] [Second embodiment]
[0528] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0529] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.
[0530] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0531] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.
[0532] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[0533] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[0534] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[0535] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[0536] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0537] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0538] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0539] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."
[0540] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[0541] overview
[0542] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[0543] Program processing
[0544] 1. Generative AI creator registers a prompt
[0545] User (generative AI creator)
[0546] Fill in the prompts based on your drawing style through a web form.
[0547] The form has a text entry field where creators can describe their prompt in detail.
[0548] Terminal
[0549] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[0550] server
[0551] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[0552] 2. Game creators use prompts to generate content
[0553] User (game creator)
[0554] Select the prompt you want to generate from the prompt list and access the input form to specify character details and the situation.
[0555] Enter the required information and click the Generate button to send a generation request to the server.
[0556] Terminal
[0557] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[0558] server
[0559] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[0560] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[0561] The generated content is temporarily stored and the generation results are returned to the game creator.
[0562] 3. Store and manage generated content
[0563] User (game creator)
[0564] You can check the generated content displayed on the screen and save it by clicking the save button.
[0565] It can also be modified and regenerated as needed.
[0566] Terminal
[0567] When the save button is clicked, the generated content is sent to the server API in JSON format.
[0568] server
[0569] The received generated content is saved in a database and a response indicating success is returned to the client.
[0570] Supports the management and provision of generated content, making it easily accessible to game creators.
[0571] Specific examples
[0572] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[0573] 1. Generative AI Creator
[0574] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[0575] 2. Game Creator
[0576] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[0577] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[0578] 3. Generated results
[0579] Illustrations generated by AI are provided to game creators via a server.
[0580] The game creator checks the generated content and saves it.
[0581] This will promote collaboration between generative AI creators and game creators, and create a system that provides an environment in which even individuals and small organizations can efficiently generate and manage high-quality game content.
[0582] The processing flow will be explained below.
[0583] Step 1:
[0584] The user (generative AI creator) accesses a web form and fills in prompts based on their own drawing style.
[0585] Step 2:
[0586] The device captures the web form submit event and retrieves the input prompt in JavaScript.
[0587] Step 3:
[0588] The device converts the prompt into JSON format and sends it to the server's API endpoint.
[0589] Step 4:
[0590] The server saves the received prompt data in the database and generates a response indicating that the save was successful.
[0591] Step 5:
[0592] The server returns a successful save response to the device.
[0593] Step 6:
[0594] The user (game creator) accesses the prompt list page and selects the prompt they want to create.
[0595] Step 7:
[0596] Based on the prompt selected by the user (game creator), the necessary information is entered into an input form for entering character details and the situation.
[0597] Step 8:
[0598] The terminal captures the form submit event and obtains the selected prompt ID and the user's input.
[0599] Step 9:
[0600] The device converts the prompt ID and the user's input into JSON format and sends it to the server's API endpoint.
[0601] Step 10:
[0602] The server retrieves the corresponding prompt from the database based on the prompt ID received and the user input.
[0603] Step 11:
[0604] The server passes the obtained prompt and user input information to the AI generation service, instructing it to generate content.
[0605] Step 12:
[0606] The server receives the generated content from the AI generation service and temporarily stores it.
[0607] Step 13:
[0608] The server returns the generated results to the terminal.
[0609] Step 14:
[0610] The device displays the generated results on the user's (game creator's) screen so that they can be checked.
[0611] Step 15:
[0612] The user (game creator) clicks the save button for the generated content.
[0613] Step 16:
[0614] The device captures the click event of the save button, converts the generated content into JSON format, and sends it to the server's API endpoint.
[0615] Step 17:
[0616] The server saves the received generated content in the database and generates a response indicating that saving was successful.
[0617] Step 18:
[0618] The server returns a successful save response to the device.
[0619] Step 19:
[0620] The device displays a message indicating successful saving on the user's (game creator's) screen.
[0621] The above is the specific operational flow of each processing step in the present invention. This will realize an environment in which AI creators and game creators can work together to efficiently generate and manage high-quality game content.
[0622] Example 1
[0623] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0624] Previous game content generation systems had issues such as creators being unable to effectively use prompts based on their own drawing style, and the time and effort required to check, modify, and regenerate generated content. Furthermore, there was a lack of a way to display generated content in real time and easily save it.
[0625] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[0626] In this invention, the server includes a means for a generation AI creator to register prompts regarding their drawing style, a means for a game creator to input an outline of a situation or character, a means for the generation AI to generate illustrations and music, a means for saving the generated content in a database, a means for the game creator to check, modify, regenerate, and save the generated content, and a means for displaying the generated content in real time and processing save requests, thereby enabling creators to efficiently generate high-quality content and instantly check, modify, and save it.
[0627] A "generative AI creator" is a creator who creates and registers prompts based on their own drawing style.
[0628] A "prompt" is a text description of instructions and conditions for generating content such as illustrations and music.
[0629] A "game creator" is a creator whose role is to input an outline of the situation and characters based on prompts and instruct the generation of game content.
[0630] A "situation" is a specific description of a scene or situation within the game.
[0631] "Character Overview" is information that describes the character's appearance, personality, behavior, etc.
[0632] "Generative AI" is AI that automatically generates content such as illustrations and music based on input information.
[0633] A "database" is a system that permanently stores and manages data such as generated content and prompts.
[0634] An "interface" is a screen or tool that provides an input means for a user to register a prompt or enter information.
[0635] A "generation request" is a request that a game creator inputs detailed information about the content to be generated based on a prompt and sends to the server.
[0636] A "storage request" is a request sent to a server to store generated content in a database.
[0637] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[0638] overview
[0639] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[0640] Additionally, generated content can be easily reviewed, modified, regenerated, and saved, and creation and saving requests are handled in real time.
[0641] Program processing
[0642] Generative AI creator registers prompts
[0643] User (generative AI creator)
[0644] Through a web form, users enter prompts based on their drawing style, such as "fantasy character, young wizard in blue robes, with a magical tower in the background."
[0645] Terminal
[0646] When the form is submitted, JavaScript takes the prompt content, converts it to JSON format, and sends it to the server's API.
[0647] server
[0648] The server saves the received prompt data in a database and returns a response indicating that the save was successful to the client.
[0649] Game creators use prompts to generate content
[0650] User (game creator)
[0651] The user selects the prompt they want to generate from a list of prompts, enters details about the character, such as "A young wizard undergoes trials to become a full-fledged wizard," and clicks the Generate button to send a generation request to the server.
[0652] Terminal
[0653] JavaScript gets the selected prompt ID and the user's input, converts it into JSON format, and sends it to the server's API.
[0654] server
[0655] The server retrieves the prompt from the database and calls the AI generation service along with the user's input information. The AI generation service is used to automatically generate content such as a scene in which a young wizard in a blue robe is put to the test in front of a magical tower. The generated content is temporarily saved and the results are returned to the game creator.
[0656] Store and manage generated content
[0657] User (game creator)
[0658] The user can check the generated content displayed on the screen, and modify or regenerate it as necessary. The generated content is saved by clicking the Save button.
[0659] Terminal
[0660] When the save button is clicked, the generated content is sent to the server API in JSON format.
[0661] server
[0662] The server stores the generated content in a database and returns a successful save response to the client. This system enables creators to efficiently generate high-quality content and instantly check, modify, and save it.
[0663] For example, a generative AI creator can register a prompt to draw a fantasy character, and a game creator can generate a brave young wizard. By using this system, creators can efficiently generate and manage high-quality game content.
[0664] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0665] Step 1:
[0666] User (generative AI creator)
[0667] Input: Enter a prompt into a web form, such as "Fantasy character, young wizard in blue robes, with a magical tower in the background."
[0668] How it works: A generative AI creator visits a specific web form and fills in text fields with prompts that reflect their drawing style.
[0669] Output: The prompt text entered.
[0670] Step 2:
[0671] Terminal
[0672] Input: The prompt text entered into the web form.
[0673] How it works: When the submit button on the form is clicked, a JavaScript is triggered that retrieves the prompt text that was entered.
[0674] Data processing: Convert the obtained prompt text into JSON format.
[0675] Output: Prompt data in JSON format.
[0676] Step 3:
[0677] server
[0678] Input: Prompt data sent from the terminal in JSON format.
[0679] Operation: The server stores the received prompt data in a database.
[0680] Output: Save result (success or failure response) to database.
[0681] Step 4:
[0682] User (game creator)
[0683] Input: A request to generate content based on a saved prompt. Specifically, you select a prompt and enter character details and a situation, such as "A young wizard undergoes trials to become a full wizard."
[0684] How it works: The game creator selects the prompt they want to generate from the prompt list screen and enters character details and the situation.
[0685] Output: The generated request and associated input information.
[0686] Step 5:
[0687] Terminal
[0688] Input: The generated request and prompt ID entered by the user.
[0689] What it does: JavaScript takes the generated request and prompt ID and converts it to JSON format.
[0690] Data processing: The generation request and prompt ID converted to JSON format are sent to the server API.
[0691] Output: Generated request data in JSON format.
[0692] Step 6:
[0693] server
[0694] Input: The generated request data in JSON format sent from the terminal.
[0695] How it works: The server retrieves prompt data from the database based on the prompt ID, then passes the prompt data and a generation request to the AI generation service.
[0696] Data Computing: AI generation services auto-generate content such as illustrations and music based on prompts and generation requests.
[0697] Output: The generated content and the generated result (success or failure response).
[0698] Step 7:
[0699] server
[0700] Input: Generated content from an AI-generated service.
[0701] How it works: The server temporarily stores the generated content and returns the generated results to the game creator.
[0702] Output: The URL or file path of the generated content.
[0703] Step 8:
[0704] User (game creator)
[0705] Input: The URL or file path of the generated content.
[0706] Action: The game creator reviews the generated content displayed, modifies it or regenerates it as needed, and clicks the Save button if they wish to save it.
[0707] Output: Save request.
[0708] Step 9:
[0709] Terminal
[0710] Input: Save request and generated content.
[0711] What it does: JavaScript converts the save request and generated content into JSON format.
[0712] Data processing: The save request and generated content converted into JSON format are sent to the server's API.
[0713] Output: Save request data in JSON format.
[0714] Step 10:
[0715] server
[0716] Input: Save request data sent from the device in JSON format.
[0717] Operation: The server stores the received save request data in a database.
[0718] Output: Save result (success or failure response) to database.
[0719] (Application example 1)
[0720] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0721] With conventional content generation systems, collaboration between general users and professional creators was difficult, making it difficult to quickly and efficiently materialize users' ideas. Furthermore, the storage and management of generated content was also inefficient, resulting in problems such as a decline in content quality and productivity.
[0722] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0723] In this invention, the server includes means for a generating AI creator to register prompts related to their drawing style, means for a content creator to input an outline of a situation or character, means for the generating AI to generate illustrations, music, and video, means for saving the generated content in a database, means for providing the generated content to the content creator, means for providing an interface for the generating AI creator to register prompts, and means for displaying content generated in real time based on the outline of a situation or character input by the content creator. This enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality.
[0724] A "generative AI creator" refers to an AI that registers prompts related to one's drawing style and contributes to content generation based on those prompts.
[0725] A "prompt" is a piece of text or keyword that provides instructions or guidelines for a generative AI model to generate a particular depiction or situation.
[0726] "Content creators" refer to users who input a situation or character outline based on prompts and use or edit the content generated by the generative AI.
[0727] A "situation" is information that describes a specific scene or setting, providing the background or environment for a generative AI model to generate content.
[0728] "Character Description" refers to text describing the characteristics and details of a character used in content generation.
[0729] "Generative AI" refers to AI that has the technology to automatically generate content such as illustrations, music, and video based on prompts and additional input information.
[0730] "Content" refers to digital works such as illustrations, music, and video created by generative AI models.
[0731] "Database" refers to a digital storage system for storing and managing Generated Content.
[0732] "Interface" means the web form or application user interface for entering and registering a Student Configuration Prompt.
[0733] "Real-time" refers to the system's ability to respond almost immediately to input information and quickly display generated content.
[0734] This embodiment of the present invention relates to a system in which a user generates content using a generative AI model, stores the content in a database, and provides it to other users. In this system, a server, a terminal, and users (generative AI creators and content creators) work together to perform processing.
[0735] Overall processing overview of the program
[0736] 1. Generative AI creator registers prompt
[0737] user:
[0738] Generative AI creators use a dedicated web form to enter prompts based on their drawing style, such as specific drawing guidelines like "underwater city, futuristic design, adventurer adventure scene."
[0739] Device:
[0740] The prompt information entered into the form by the artificial intelligence creator is obtained using JavaScript and sent to the server's API in JSON format.
[0741] server:
[0742] The received prompt data is saved in the database and a response indicating successful saving is returned to the client (user).
[0743] 2. Content creators use prompts to generate content
[0744] user:
[0745] Content creators select a prompt they want to generate from a list of prompts and enter a brief description of the characters and situation, such as "a scene in which an adventurer finds treasure in a futuristic underwater city."
[0746] Device:
[0747] Obtain the selected prompt ID and detailed information about the character and situation, and send it in JSON format to the server's API.
[0748] server:
[0749] The system retrieves a prompt from the database and calls an AI generation service (e.g., OpenAI GPT-4 or Stable Diffusion) along with the user's input. The AI generation service automatically generates content such as illustrations, music, and video based on the specified prompt and input. The generated content is then temporarily stored and returned to the content creator.
[0750] 3. Store and manage generated content
[0751] user:
[0752] The content creator can review the generated content and, if satisfied, press the "Save" button to save the content to the database. It can also be modified or regenerated as needed.
[0753] Device:
[0754] Once the save button is clicked, the generated content is sent to the server API in JSON format.
[0755] server:
[0756] It stores the received generated content in a database and returns a successful save response to the client, making it easier to manage and serve generated content and make it easily accessible to content creators.
[0757] Specific step-by-step instructions
[0758] Server Roles and Configuration
[0759] The server includes the following means:
[0760] A means for generative AI creators to register prompts.
[0761] A way for content creators to input situations and character descriptions.
[0762] A means for generative AI to generate illustrations, music, and video.
[0763] A means of storing generated content in a database.
[0764] A means of providing generated content to content creators.
[0765] A means to provide an interface for generative AI creators to register prompts.
[0766] A means of displaying content generated in real time based on situations and character descriptions entered by content creators.
[0767] This will enable efficient collaboration between general users and professional creators, and will enable users' ideas to be realized quickly and with high quality. Below are some examples of prompt sentences:
[0768] Prompt: Underwater city, futuristic design, adventurer adventure scene
[0769] Details: Underwater city features transparent domes, alien colonies, and hidden treasure
[0770] In this way, the present invention realizes a system that allows users to register prompts based on their own ideas and visual and auditory instructions, and efficiently manage, store, and use the generated content.
[0771] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0772] Step 1:
[0773] This is the stage where the user (generative AI creator) registers a prompt. The user enters a prompt based on their own drawing style into a dedicated web form. The entered prompt is converted into JSON format using JavaScript. The device sends this JSON data to the server's API. The server saves the received prompt data in a database and returns a successful save response to the client (user). For example, a prompt such as "underwater city, futuristic design, scene of adventurers on an adventure" can be entered here.
[0774] Input: User input for prompt (text)
[0775] Output: JSON format prompt data, save success response
[0776] Step 2:
[0777] The server retrieves the saved prompt data from the database. The user (content creator) selects the prompt they want to generate from the prompt list and enters a summary of the situation and character. This detailed information is also converted into JSON format and sent from the device to the server's API. The server retrieves the corresponding prompt from the database based on the received data.
[0778] Input: Prompt ID, situation, character summary (text)
[0779] Output: Prompts and detailed information from the database
[0780] Step 3:
[0781] The server calls the AI generation service using the obtained prompt and the input situation and character summary. It sends the prompt and detailed information to the AI generation service (e.g., OpenAI GPT-4, Stable Diffusion). The AI generation service generates content such as illustrations, music, and video based on this information. This generated content is temporarily stored on the server.
[0782] Input: Prompt, Situation, Character Summary (Text)
[0783] Output: Generated content such as illustrations, music, and videos
[0784] Step 4:
[0785] The server provides the generated content to the content creator. The user (content creator) can review the provided content and make further corrections or additions. An interface displaying the generated content in real time is displayed on the terminal. The content creator can request regeneration as needed.
[0786] Input: Generated content, corrections and additional input (text)
[0787] Output: Display of content updated in real time
[0788] Step 5:
[0789] If the content creator is satisfied with the generated content, they press the save button to save it to the server. When the save button is pressed, the device converts the generated content into JSON format and sends it to the server's API. The server saves the received generated content in its database and returns a successful save response to the client.
[0790] Input: Press the save button, generated content (JSON format)
[0791] Output: Content saved to database, save success response
[0792] In this way, the system enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality, while the generated content is efficiently managed, stored, and used.
[0793] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[0794] This invention is an improvement to a system in which a generative AI creator registers prompts related to their drawing style, and a game creator generates the necessary content based on those prompts, by combining it with an emotion engine that recognizes the user's emotions and adjusts the generated content to match the user's emotions. In this system, the server, terminal, and user (generative AI creator, game creator) work together to perform processing and improve the quality of the generated content.
[0795] overview
[0796] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on the prompts, (3) the AI generates content based on the input, (4) the emotion engine recognizes the user's emotions and adjusts the generated content, (5) the generated content is saved and managed, and (6) it is provided to the game creator.
[0797] Program processing
[0798] 1. Generative AI creator registers a prompt
[0799] User (generative AI creator)
[0800] Access a web form and fill out prompts based on your drawing style.
[0801] The form has a text entry field where creators can describe their prompt in detail.
[0802] Terminal
[0803] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[0804] server
[0805] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[0806] 2. Game creators use prompts to generate content
[0807] User (game creator)
[0808] Select the prompt you want to generate from the prompt list and enter the required information in the input form to specify the character details and situation.
[0809] Enter the required information and click the Generate button to send a generation request to the server.
[0810] Terminal
[0811] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[0812] server
[0813] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[0814] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[0815] The generated content is temporarily stored and the generation results are returned to the game creator.
[0816] 3. Tuning the emotion engine and generated content
[0817] Terminal
[0818] When game creators check the generated content, sensors such as cameras and microphones are activated to recognize the user's emotions.
[0819] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates emotion data.
[0820] server
[0821] Based on the emotion data sent from the emotion engine, the generated content is evaluated to see if it matches the user's emotion.
[0822] Run a regeneration and tweak process to adjust the content as needed.
[0823] 4. Store and manage generated content
[0824] User (game creator)
[0825] You can check the generated content displayed on the screen and save it by clicking the save button.
[0826] It can also be modified and regenerated as needed.
[0827] Terminal
[0828] When the save button is clicked, the generated content is sent to the server API in JSON format.
[0829] server
[0830] The received generated content is saved in a database and a response indicating success is returned to the client.
[0831] Supports the management and provision of generated content, making it easily accessible to game creators.
[0832] Specific examples
[0833] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[0834] 1. Generative AI Creator
[0835] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[0836] 2. Game Creator
[0837] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[0838] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[0839] 3. Emotion Engine
[0840] Analyze game creators' emotions in real time to ensure the generated content meets expectations.
[0841] If the emotion does not match, it instructs the AI generation service to regenerate it.
[0842] 4. Generated results
[0843] Illustrations generated by AI are provided to game creators via a server.
[0844] Optimized content is provided based on the results confirmed through the emotion engine.
[0845] The game creator checks the generated content and saves it.
[0846] This will enable collaboration between generative AI creators, game creators, and emotion engines, providing an environment in which high-quality game content that matches user emotions can be efficiently generated and managed.
[0847] The processing flow will be explained below.
[0848] Step 1:
[0849] The user (generative AI creator) accesses a web form and enters a prompt based on their drawing style. The form includes a text input field where the creator can further describe the prompt.
[0850] Step 2:
[0851] The device captures the submit event of the web form, gets the prompt entered in JavaScript, converts the input into JSON format, and sends it to the server's API endpoint.
[0852] Step 3:
[0853] The server saves the received prompt data in the database. After the save process is complete, it generates a save success response and returns it to the client.
[0854] Step 4:
[0855] The user (game creator) accesses the prompt list page and selects the prompt they want to create. Based on the selected prompt, they enter the necessary information into the input form to specify the character details and situation.
[0856] Step 5:
[0857] The terminal captures the form submission event, obtains the selected prompt ID and the user's input, converts it to JSON format, and sends it to the server's API endpoint.
[0858] Step 6:
[0859] The server retrieves the corresponding prompt from the database based on the received prompt ID and user input, passes the retrieved prompt and user input information to the AI generation service, and instructs it to generate content.
[0860] Step 7:
[0861] The server receives the generated content from the AI generation service, temporarily stores it, and returns the generated results to the game creator.
[0862] Step 8:
[0863] The device displays the generated content on the user's (game creator's) screen. When the user checks the generated content, sensors such as the device's camera and microphone are activated to collect emotional data.
[0864] Step 9:
[0865] The emotion engine analyzes the user's facial expressions and tone of voice in real time to generate emotion data, which is then sent to the server.
[0866] Step 10:
[0867] The server evaluates whether the generated content matches the user's emotions based on the emotion data received from the emotion engine. Based on the evaluation results, the content is regenerated or fine-tuned as necessary.
[0868] Step 11:
[0869] The server returns the adjusted generated content to the device, and the user (game creator) checks the generated content again.
[0870] Step 12:
[0871] When the user (game creator) is satisfied with the generated content, they click the save button. The device then captures the save button click event, converts the generated content into JSON format, and sends it to the server's API endpoint.
[0872] Step 13:
[0873] The server saves the generated content it receives in the database. After the save process is complete, it generates a save success response and returns it to the client.
[0874] Step 14:
[0875] The device displays a message indicating successful saving on the user's (game creator's) screen.
[0876] The above is the specific flow of operation for each processing step in this invention. This allows AI creators and game creators to work together, and by introducing an emotion engine, an environment is realized in which high-quality game content that matches the user's emotions can be efficiently generated and managed.
[0877] Example 2
[0878] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0879] Current content generation systems using generative AI do not take user emotions into account, so the generated content may not necessarily match the user's expectations or emotions. This poses challenges in improving the user experience and optimizing the quality of generated content.
[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0881] In this invention, the server includes means for a generation device creator to register instructions regarding his or her drawing style, means for a developer to input an outline of the situation and characters based on the instructions, means for the generation device to generate video and audio based on the input information, means for saving the generated content in a data storage device, means for providing the generated content to the developer, means for acquiring user emotions using a sensing device and analyzing them with an emotion engine, and means for adjusting the generated content based on the analysis results, thereby making it possible to generate and provide high-quality content that matches the user's emotions.
[0882] A "generator creator" is a user who is responsible for registering instructions based on their own drawing style and concept into the system.
[0883] "Instructions" are information that details the style and specific elements of the content to be generated.
[0884] The "developer" is a user who inputs details about the situation and characters based on the generated prompts, and then generates and checks the final content.
[0885] "Context" is information that indicates a specific situation or background of the generated content.
[0886] "Characters" refers to information that refers to the characters and character details that appear in the generated content.
[0887] A "generation device" is an artificial intelligence system that automatically generates content such as video and audio based on information entered by the user.
[0888] "Video" is a form of visual content, including illustrations, animations, and videos.
[0889] "Audio" refers to a form of auditory content, including music, sound effects, narration, etc.
[0890] A "data store" is a physical or virtual storage system for storing generated content.
[0891] A "sensing device" is a device used to acquire emotional data of a user, and includes a camera, a microphone, and the like.
[0892] The "emotion engine" is a software component that analyzes acquired emotion data and evaluates the user's emotional state.
[0893] The "analysis results" are information about the user's emotional state obtained by the emotion engine.
[0894] "Tuning" is the process of modifying or regenerating generated content to match the user's emotional state.
[0895] "Content" refers to content such as video and audio automatically created by a generating device.
[0896] This invention is a system in which a generator creator registers instructions (prompts) based on their own drawing style and concept into the system, and a developer uses the prompts to input details of the situation and characters, and the generator generates content such as video and audio. This generated content is adjusted by acquiring the user's emotions using a sensing device and analyzing them with an emotion engine, providing high-quality content that matches the user's emotions.
[0897] Specifically, the system is implemented according to the following steps: First, the creator of the generator accesses the web interface and describes in detail their drawing style and the characteristics of their work. The input prompt is obtained by JavaScript on the device, converted into JSON format, and sent to the server's API. The server saves this prompt data in a data storage device and returns a response to the device indicating that the save was successful.
[0898] Next, the developer selects the desired prompt from a list of prompts and enters a summary of the situation and character. For example, the developer selects "Fantasy character, young wizard in blue robes, against a magical tower background" as the prompt and enters "Young wizard undergoes trials to become a full wizard" as the character details. This input is captured on the device and sent back to the server's API in JSON format.
[0899] The server then passes prompts and additional information to the AI generation service based on the received data. The AI generation service then automatically generates content such as video and audio based on this information. The generated content is temporarily stored in a data storage device, and the generated results are returned to the developer.
[0900] When the developer checks the generated content, sensing devices (cameras and microphones) are activated to capture the user's emotional data in real time. The emotion engine analyzes this data, evaluates whether the generated content matches the user's emotions, and regenerates or fine-tunes it as necessary.
[0901] For example, consider a scenario where a developer wants to generate a scene depicting a young wizard undergoing a trial using a prompt registered by a generator creator: "Fantasy character, young wizard in blue robes, with a magical tower in the background." The generator uses this information to generate the corresponding video and evaluates and adjusts the generated content using a sensing device and emotion engine. Ultimately, high-quality content that matches the user's emotions is provided, and the developer can save the content.
[0902] In this way, the present invention realizes efficient generation and management of high-quality content that reflects the user's emotions through collaboration between generation device creators, developers, sensing devices, and emotion engines.
[0903] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0904] Step 1:
[0905] The user (generator creator) accesses a web interface and inputs instructions (prompts) describing their drawing style and the characteristics of their work. For example, they might input "a fantasy character, a young wizard in a blue robe, with a magical tower as the background." The input instructions are retrieved using JavaScript on the device. Input: The prompt text entered by the user into the web form. Output: The prompt text is converted to JSON format.
[0906] Step 2:
[0907] The terminal converts the prompt text into JSON format and sends it as a POST request to the server's API. At this time, by sending data to a specific endpoint, the server prepares to receive the instruction data. Input: Prompt text in JSON format. Output: POST request sent to the server.
[0908] Step 3:
[0909] The server parses the received JSON data and validates the contents before saving it to the database. If the validation is successful, the data is saved to the database and a response indicating successful saving is returned to the terminal. Input: Prompt text in JSON format sent to the server. Output: Prompt text is saved to the database and a response indicating successful saving is returned.
[0910] Step 4:
[0911] The user (developer) selects the desired prompt from the prompt list and enters details of the situation and characters. For example, "A young wizard undergoes the trials to become a full-fledged wizard." Input: The prompt ID selected from the prompt list and additional information from the user. Output: The generation request converted to JSON format.
[0912] Step 5:
[0913] The terminal converts the selected prompt ID and additional information into JSON format and sends it to the server's API. Input: Prompt ID and user's additional information. Output: Sends a generation request to the server.
[0914] Step 6:
[0915] The server receives the generation request, retrieves a prompt from the database, and then passes the prompt and additional information to the AI generation service. The AI generation service uses this information to generate content such as video and audio. The generated content is stored in a temporary storage area on the server. Input: Generation request sent to the server. Output: Generated content.
[0916] Step 7:
[0917] The server stores the generated content in a temporary storage area and returns the generated result to the end user. Input: Generated content. Output: Return of generated result to the end user.
[0918] Step 8:
[0919] When a user (developer) checks the generated content, sensing devices (camera and microphone) connected to the device collect the user's emotional data. For example, the camera detects the user's facial expressions, and the microphone detects the tone of voice. Input: Generated content and user's emotional data. Output: Collected emotional data.
[0920] Step 9:
[0921] The device sends the collected emotion data to the server in real time. Input: Collected emotion data. Output: Sending emotion data to the server.
[0922] Step 10:
[0923] The server passes emotional data to the emotion engine for analysis. Based on the analysis results, it evaluates how well the generated content matches the user's emotions and regenerates or fine-tunes it as necessary. Input: Emotion data passed to the emotion engine. Output: Analysis results and adjustment instructions.
[0924] Step 11:
[0925] The server finally provides the adjusted generated content to the end user, allowing the user to review the content. Input: Adjusted generated content. Output: Provided to the end user.
[0926] Step 12:
[0927] The user (developer) checks the generated content displayed on the screen and saves it by clicking the save button. It is also possible to modify or regenerate the content as needed. Input: User actions on the generated content. Output: The final saved content.
[0928] (Application example 2)
[0929] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0930] Conventional content generation systems using generative artificial intelligence have had difficulty generating content that matches the user's emotions. In the entertainment field in particular, there is a demand for content that responds to the user's emotions and reactions. Therefore, there is a need for technology that can recognize user emotions in real time and adjust and optimize content based on those emotions.
[0931] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[0932] In this invention, the server includes means for the generating AI creator to register prompts related to his / her drawing style, means for the game creator to input an outline of the situation and characters, means for the generating AI to generate illustrations and music based on the input information, means for saving the generated content in a database, means for providing the generated content to the game creator, means for adjusting the generated content using an emotion engine that recognizes the user's emotions, and means for providing the adjusted content to the user, thereby enabling the generation of content that matches the user's emotions.
[0933] The "generative AI creator" is an AI that is responsible for registering prompts based on its own drawing style.
[0934] A "prompt" is a sentence or keyword that a generative AI model uses as an instruction to generate content.
[0935] A "game creator" is a user whose role is to input a summary of the situation and characters based on prompts.
[0936] "Situation" refers to the specific scene or situation in which a character is placed within a game.
[0937] "Character Overview" refers to the basic characteristics and background information of characters that appear in the game.
[0938] "Generative AI" is AI that generates content such as illustrations and music based on input information.
[0939] A "database" is a system that stores generated content and makes it accessible as needed.
[0940] The "emotion engine" is a system that recognizes the user's emotions in real time and acquires that data.
[0941] "Adjustment" refers to the process of making changes to the generated content based on the user's emotions as recognized by the emotion engine.
[0942] "Means" refers to a device, method, or composition of matter employed to accomplish a particular purpose.
[0943] This embodiment describes a system for generating and providing entertainment content that matches a user's emotions. This system features a generative AI creator registering prompts, a game creator using the prompts to generate content, and an emotion engine adjusting the generated content based on the user's emotions.
[0944] Hardware and software used
[0945] Hardware
[0946] Smartphone or head-mounted display (HMD)
[0947] Camera and microphone for emotion recognition by the emotion engine
[0948] software
[0949] JavaScript (front-end data processing)
[0950] Python (server-side script)
[0951] TensorFlow (a machine learning framework for emotion recognition)
[0952] OpenAI API (generative AI models for content generation)
[0953] Detailed process description
[0954] 1. Prompt registration by generative AI creator
[0955] Users, or generative AI creators, submit prompts based on their drawing style through a web form, such as "a fantasy character, a young wizard in blue robes, with a magical tower in the background."
[0956] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[0957] The server stores the received prompt data in a database and returns a response indicating successful storage to the client.
[0958] 2. Content generation by game creators
[0959] The user, the game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and the situation, such as "a scene in which a young wizard is put to the test."
[0960] On the terminal, the selected prompt ID and the user's input are sent to the server API in JSON format.
[0961] The server retrieves prompts from the database and calls the OpenAI API based on the user's input. The AI generates content such as illustrations and music based on the specified prompts and input.
[0962] 3. Content adjustment using emotion engines
[0963] When a user checks the content generated on the device, the camera and microphone are activated to recognize emotions. Facial expressions and tone of voice are analyzed in real time to obtain emotional data.
[0964] The server evaluates whether the generated content matches the user's emotion based on the emotion data sent from the emotion engine. If the emotion does not match, it instructs the AI generation service to regenerate the content.
[0965] 4. Storing and Managing Generated Content
[0966] The user can review the generated content and save it by clicking the save button, and can also regenerate or fine-tune it as needed.
[0967] 5. Specific Examples
[0968] Example prompt from a generative AI creator: "A quiet street lit by streetlights on a new moon night."
[0969] Example input from a game creator: "A scene in which the main character walks through a quiet street."
[0970] These operations enable the generation and provision of high-quality game content that responds to the user's emotions.
[0971] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0972] Step 1:
[0973] The user, a generative AI creator, registers prompts based on their drawing style through a web form.
[0974] Input: The prompt text entered by the user into the web form
[0975] Specific Action: A user accesses a web form, enters text based on their drawing style, and clicks the submit button.
[0976] Step 2:
[0977] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[0978] Input: Prompt text taken from a web form
[0979] Data processing: Convert the input text into JSON format
[0980] Output: API request to the server
[0981] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[0982] Step 3:
[0983] The server saves the prompt data received in the database and returns a response indicating success to the client.
[0984] Input: Prompt data in JSON format
[0985] Data processing: Convert prompt data into database format
[0986] Output: Save successful response
[0987] What happens: The server-side script opens a database connection, saves the prompt data, and returns a response to the client if successful.
[0988] Step 4:
[0989] The user, a game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and situation.
[0990] Input: Prompt ID, character details, situation text
[0991] What happens: A game creator visits a web form, selects a prompt from a drop-down menu, enters the required details, and submits it.
[0992] Step 5:
[0993] On the terminal, the selected prompt ID and the user's input are sent to the server's API in JSON format.
[0994] Input: Prompt ID, character details, situation text
[0995] Data processing: Convert this information into JSON format
[0996] Output: API request to the server
[0997] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[0998] Step 6:
[0999] The server retrieves prompts from the database and generates content by calling OpenAI's API along with the user's input information.
[1000] Input: Prompt ID, character details, situation text
[1001] Data processing: Retrieve prompts from the database, combine them with user input, and send them to the OpenAI API
[1002] Output: Generated content
[1003] What happens: A server-side script opens a database connection, retrieves prompt data, and calls the OpenAI API to generate content.
[1004] Step 7:
[1005] The generated content is temporarily stored and the generation results are returned to the game creator.
[1006] Input: Generated content
[1007] Data storage: temporarily stores generated content
[1008] Output: The generated response
[1009] Specific operation: The server-side script temporarily stores the generated content and returns the generated result to the client.
[1010] Step 8:
[1011] When a user checks the generated content on the terminal, the camera and microphone are activated to analyze facial expressions and tone of voice in real time and obtain emotional data.
[1012] Input: User's facial expression and tone of voice
[1013] Data processing: Analyze acquired data into emotion data
[1014] Output: Emotion data
[1015] Specific operation: The camera and microphone capture the user's facial expressions and voice, and the emotion engine analyzes them in real time.
[1016] Step 9:
[1017] Based on the emotion data transmitted from the emotion engine, the server evaluates whether the generated content matches the user's emotion, and issues an instruction to regenerate the content if necessary.
[1018] Input: emotion data, generated content
[1019] Data evaluation: Evaluate the degree of agreement between emotion data and generated content
[1020] Output: Regeneration instructions (if necessary)
[1021] Specific operation: A server-side script analyzes the emotion data, evaluates the degree of match of the generated content, and issues instructions for regeneration if necessary.
[1022] Step 10:
[1023] The user checks the generated content and saves it by clicking the save button.
[1024] Input: Generated content
[1025] Output: Saved content
[1026] Specific operation: The user checks the generated content in the browser and clicks the save button to save the content.
[1027] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[1028] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[1029] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.
[1030] [Third embodiment]
[1031] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[1032] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.
[1033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[1034] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.
[1035] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[1036] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[1037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[1038] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[1039] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[1040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[1041] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[1042] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."
[1043] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[1044] overview
[1045] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[1046] Program processing
[1047] 1. Generative AI creator registers a prompt
[1048] User (generative AI creator)
[1049] Fill in the prompts based on your drawing style through a web form.
[1050] The form has a text entry field where creators can describe their prompt in detail.
[1051] Terminal
[1052] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[1053] server
[1054] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[1055] 2. Game creators use prompts to generate content
[1056] User (game creator)
[1057] Select the prompt you want to generate from the prompt list and access the input form to specify character details and the situation.
[1058] Enter the required information and click the Generate button to send a generation request to the server.
[1059] Terminal
[1060] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[1061] server
[1062] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[1063] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[1064] The generated content is temporarily stored and the generation results are returned to the game creator.
[1065] 3. Store and manage generated content
[1066] User (game creator)
[1067] You can check the generated content displayed on the screen and save it by clicking the save button.
[1068] It can also be modified and regenerated as needed.
[1069] Terminal
[1070] When the save button is clicked, the generated content is sent to the server API in JSON format.
[1071] server
[1072] The received generated content is saved in a database and a response indicating success is returned to the client.
[1073] Supports the management and provision of generated content, making it easily accessible to game creators.
[1074] Specific examples
[1075] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[1076] 1. Generative AI Creator
[1077] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[1078] 2. Game Creator
[1079] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[1080] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[1081] 3. Generated results
[1082] Illustrations generated by AI are provided to game creators via a server.
[1083] The game creator checks the generated content and saves it.
[1084] This will promote collaboration between generative AI creators and game creators, and create a system that provides an environment in which even individuals and small organizations can efficiently generate and manage high-quality game content.
[1085] The processing flow will be explained below.
[1086] Step 1:
[1087] The user (generative AI creator) accesses a web form and fills in prompts based on their own drawing style.
[1088] Step 2:
[1089] The device captures the web form submit event and retrieves the input prompt in JavaScript.
[1090] Step 3:
[1091] The device converts the prompt into JSON format and sends it to the server's API endpoint.
[1092] Step 4:
[1093] The server saves the received prompt data in the database and generates a response indicating that the save was successful.
[1094] Step 5:
[1095] The server returns a successful save response to the device.
[1096] Step 6:
[1097] The user (game creator) accesses the prompt list page and selects the prompt they want to create.
[1098] Step 7:
[1099] Based on the prompt selected by the user (game creator), the necessary information is entered into an input form for entering character details and the situation.
[1100] Step 8:
[1101] The terminal captures the form submit event and obtains the selected prompt ID and the user's input.
[1102] Step 9:
[1103] The device converts the prompt ID and the user's input into JSON format and sends it to the server's API endpoint.
[1104] Step 10:
[1105] The server retrieves the corresponding prompt from the database based on the prompt ID received and the user input.
[1106] Step 11:
[1107] The server passes the obtained prompt and user input information to the AI generation service, instructing it to generate content.
[1108] Step 12:
[1109] The server receives the generated content from the AI generation service and temporarily stores it.
[1110] Step 13:
[1111] The server returns the generated results to the terminal.
[1112] Step 14:
[1113] The device displays the generated results on the user's (game creator's) screen so that they can be checked.
[1114] Step 15:
[1115] The user (game creator) clicks the save button for the generated content.
[1116] Step 16:
[1117] The device captures the click event of the save button, converts the generated content into JSON format, and sends it to the server's API endpoint.
[1118] Step 17:
[1119] The server saves the received generated content in the database and generates a response indicating that saving was successful.
[1120] Step 18:
[1121] The server returns a successful save response to the device.
[1122] Step 19:
[1123] The device displays a message indicating successful saving on the user's (game creator's) screen.
[1124] The above is the specific operational flow of each processing step in the present invention. This will realize an environment in which AI creators and game creators can work together to efficiently generate and manage high-quality game content.
[1125] Example 1
[1126] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1127] Previous game content generation systems had issues such as creators being unable to effectively use prompts based on their own drawing style, and the time and effort required to check, modify, and regenerate generated content. Furthermore, there was a lack of a way to display generated content in real time and easily save it.
[1128] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[1129] In this invention, the server includes a means for a generation AI creator to register prompts regarding their drawing style, a means for a game creator to input an outline of a situation or character, a means for the generation AI to generate illustrations and music, a means for saving the generated content in a database, a means for the game creator to check, modify, regenerate, and save the generated content, and a means for displaying the generated content in real time and processing save requests, thereby enabling creators to efficiently generate high-quality content and instantly check, modify, and save it.
[1130] A "generative AI creator" is a creator who creates and registers prompts based on their own drawing style.
[1131] A "prompt" is a text description of instructions and conditions for generating content such as illustrations and music.
[1132] A "game creator" is a creator whose role is to input an outline of the situation and characters based on prompts and instruct the generation of game content.
[1133] A "situation" is a specific description of a scene or situation within the game.
[1134] "Character Overview" is information that describes the character's appearance, personality, behavior, etc.
[1135] "Generative AI" is AI that automatically generates content such as illustrations and music based on input information.
[1136] A "database" is a system that permanently stores and manages data such as generated content and prompts.
[1137] An "interface" is a screen or tool that provides an input means for a user to register a prompt or enter information.
[1138] A "generation request" is a request that a game creator inputs detailed information about the content to be generated based on a prompt and sends to the server.
[1139] A "storage request" is a request sent to a server to store generated content in a database.
[1140] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[1141] overview
[1142] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[1143] Additionally, generated content can be easily reviewed, modified, regenerated, and saved, and creation and saving requests are handled in real time.
[1144] Program processing
[1145] Generative AI creator registers prompts
[1146] User (generative AI creator)
[1147] Through a web form, users enter prompts based on their drawing style, such as "fantasy character, young wizard in blue robes, with a magical tower in the background."
[1148] Terminal
[1149] When the form is submitted, JavaScript takes the prompt content, converts it to JSON format, and sends it to the server's API.
[1150] server
[1151] The server saves the received prompt data in a database and returns a response indicating that the save was successful to the client.
[1152] Game creators use prompts to generate content
[1153] User (game creator)
[1154] The user selects the prompt they want to generate from a list of prompts, enters details about the character, such as "A young wizard undergoes trials to become a full-fledged wizard," and clicks the Generate button to send a generation request to the server.
[1155] Terminal
[1156] JavaScript gets the selected prompt ID and the user's input, converts it into JSON format, and sends it to the server's API.
[1157] server
[1158] The server retrieves the prompt from the database and calls the AI generation service along with the user's input information. The AI generation service is used to automatically generate content such as a scene in which a young wizard in a blue robe is put to the test in front of a magical tower. The generated content is temporarily saved and the results are returned to the game creator.
[1159] Store and manage generated content
[1160] User (game creator)
[1161] The user can check the generated content displayed on the screen, and modify or regenerate it as necessary. The generated content is saved by clicking the Save button.
[1162] Terminal
[1163] When the save button is clicked, the generated content is sent to the server API in JSON format.
[1164] server
[1165] The server stores the generated content in a database and returns a successful save response to the client. This system enables creators to efficiently generate high-quality content and instantly check, modify, and save it.
[1166] For example, a generative AI creator can register a prompt to draw a fantasy character, and a game creator can generate a brave young wizard. By using this system, creators can efficiently generate and manage high-quality game content.
[1167] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1168] Step 1:
[1169] User (generative AI creator)
[1170] Input: Enter a prompt into a web form, such as "Fantasy character, young wizard in blue robes, with a magical tower in the background."
[1171] How it works: A generative AI creator visits a specific web form and fills in text fields with prompts that reflect their drawing style.
[1172] Output: The prompt text entered.
[1173] Step 2:
[1174] Terminal
[1175] Input: The prompt text entered into the web form.
[1176] How it works: When the submit button on the form is clicked, a JavaScript is triggered that retrieves the prompt text that was entered.
[1177] Data processing: Convert the obtained prompt text into JSON format.
[1178] Output: Prompt data in JSON format.
[1179] Step 3:
[1180] server
[1181] Input: Prompt data sent from the terminal in JSON format.
[1182] Operation: The server stores the received prompt data in a database.
[1183] Output: Save result (success or failure response) to database.
[1184] Step 4:
[1185] User (game creator)
[1186] Input: A request to generate content based on a saved prompt. Specifically, you select a prompt and enter character details and a situation, such as "A young wizard undergoes trials to become a full wizard."
[1187] How it works: The game creator selects the prompt they want to generate from the prompt list screen and enters character details and the situation.
[1188] Output: The generated request and associated input information.
[1189] Step 5:
[1190] Terminal
[1191] Input: The generated request and prompt ID entered by the user.
[1192] What it does: JavaScript takes the generated request and prompt ID and converts it to JSON format.
[1193] Data processing: The generation request and prompt ID converted to JSON format are sent to the server API.
[1194] Output: Generated request data in JSON format.
[1195] Step 6:
[1196] server
[1197] Input: The generated request data in JSON format sent from the terminal.
[1198] How it works: The server retrieves prompt data from the database based on the prompt ID, then passes the prompt data and a generation request to the AI generation service.
[1199] Data Computing: AI generation services auto-generate content such as illustrations and music based on prompts and generation requests.
[1200] Output: The generated content and the generated result (success or failure response).
[1201] Step 7:
[1202] server
[1203] Input: Generated content from an AI-generated service.
[1204] How it works: The server temporarily stores the generated content and returns the generated results to the game creator.
[1205] Output: The URL or file path of the generated content.
[1206] Step 8:
[1207] User (game creator)
[1208] Input: The URL or file path of the generated content.
[1209] Action: The game creator reviews the generated content displayed, modifies it or regenerates it as needed, and clicks the Save button if they wish to save it.
[1210] Output: Save request.
[1211] Step 9:
[1212] Terminal
[1213] Input: Save request and generated content.
[1214] What it does: JavaScript converts the save request and generated content into JSON format.
[1215] Data processing: The save request and generated content converted into JSON format are sent to the server's API.
[1216] Output: Save request data in JSON format.
[1217] Step 10:
[1218] server
[1219] Input: Save request data sent from the device in JSON format.
[1220] Operation: The server stores the received save request data in a database.
[1221] Output: Save result (success or failure response) to database.
[1222] (Application example 1)
[1223] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1224] With conventional content generation systems, collaboration between general users and professional creators was difficult, making it difficult to quickly and efficiently materialize users' ideas. Furthermore, the storage and management of generated content was also inefficient, resulting in problems such as a decline in content quality and productivity.
[1225] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[1226] In this invention, the server includes means for a generating AI creator to register prompts related to their drawing style, means for a content creator to input an outline of a situation or character, means for the generating AI to generate illustrations, music, and video, means for saving the generated content in a database, means for providing the generated content to the content creator, means for providing an interface for the generating AI creator to register prompts, and means for displaying content generated in real time based on the outline of a situation or character input by the content creator. This enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality.
[1227] A "generative AI creator" refers to an AI that registers prompts related to one's drawing style and contributes to content generation based on those prompts.
[1228] A "prompt" is a piece of text or keyword that provides instructions or guidelines for a generative AI model to generate a particular depiction or situation.
[1229] "Content creators" refer to users who input a situation or character outline based on prompts and use or edit the content generated by the generative AI.
[1230] A "situation" is information that describes a specific scene or setting, providing the background or environment for a generative AI model to generate content.
[1231] "Character Description" refers to text describing the characteristics and details of a character used in content generation.
[1232] "Generative AI" refers to AI that has the technology to automatically generate content such as illustrations, music, and video based on prompts and additional input information.
[1233] "Content" refers to digital works such as illustrations, music, and video created by generative AI models.
[1234] "Database" refers to a digital storage system for storing and managing Generated Content.
[1235] "Interface" means the web form or application user interface for entering and registering a Student Configuration Prompt.
[1236] "Real-time" refers to the system's ability to respond almost immediately to input information and quickly display generated content.
[1237] This embodiment of the present invention relates to a system in which a user generates content using a generative AI model, stores the content in a database, and provides it to other users. In this system, a server, a terminal, and users (generative AI creators and content creators) work together to perform processing.
[1238] Overall processing overview of the program
[1239] 1. Generative AI creator registers prompt
[1240] user:
[1241] Generative AI creators use a dedicated web form to enter prompts based on their drawing style, such as specific drawing guidelines like "underwater city, futuristic design, adventurer adventure scene."
[1242] Device:
[1243] The prompt information entered into the form by the artificial intelligence creator is obtained using JavaScript and sent to the server's API in JSON format.
[1244] server:
[1245] The received prompt data is saved in the database and a response indicating successful saving is returned to the client (user).
[1246] 2. Content creators use prompts to generate content
[1247] user:
[1248] Content creators select a prompt they want to generate from a list of prompts and enter a brief description of the characters and situation, such as "a scene in which an adventurer finds treasure in a futuristic underwater city."
[1249] Device:
[1250] Obtain the selected prompt ID and detailed information about the character and situation, and send it in JSON format to the server's API.
[1251] server:
[1252] The system retrieves a prompt from the database and calls an AI generation service (e.g., OpenAI GPT-4 or Stable Diffusion) along with the user's input. The AI generation service automatically generates content such as illustrations, music, and video based on the specified prompt and input. The generated content is then temporarily stored and returned to the content creator.
[1253] 3. Store and manage generated content
[1254] user:
[1255] The content creator can review the generated content and, if satisfied, press the "Save" button to save the content to the database. It can also be modified or regenerated as needed.
[1256] Device:
[1257] Once the save button is clicked, the generated content is sent to the server API in JSON format.
[1258] server:
[1259] It stores the received generated content in a database and returns a successful save response to the client, making it easier to manage and serve generated content and make it easily accessible to content creators.
[1260] Specific step-by-step instructions
[1261] Server Roles and Configuration
[1262] The server includes the following means:
[1263] A means for generative AI creators to register prompts.
[1264] A way for content creators to input situations and character descriptions.
[1265] A means for generative AI to generate illustrations, music, and video.
[1266] A means of storing generated content in a database.
[1267] A means of providing generated content to content creators.
[1268] A means to provide an interface for generative AI creators to register prompts.
[1269] A means of displaying content generated in real time based on situations and character descriptions entered by content creators.
[1270] This will enable efficient collaboration between general users and professional creators, and will enable users' ideas to be realized quickly and with high quality. Below are some examples of prompt sentences:
[1271] Prompt: Underwater city, futuristic design, adventurer adventure scene
[1272] Details: Underwater city features transparent domes, alien colonies, and hidden treasure
[1273] In this way, the present invention realizes a system that allows users to register prompts based on their own ideas and visual and auditory instructions, and efficiently manage, store, and use the generated content.
[1274] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1275] Step 1:
[1276] This is the stage where the user (generative AI creator) registers a prompt. The user enters a prompt based on their own drawing style into a dedicated web form. The entered prompt is converted into JSON format using JavaScript. The device sends this JSON data to the server's API. The server saves the received prompt data in a database and returns a successful save response to the client (user). For example, a prompt such as "underwater city, futuristic design, scene of adventurers on an adventure" can be entered here.
[1277] Input: User input for prompt (text)
[1278] Output: JSON format prompt data, save success response
[1279] Step 2:
[1280] The server retrieves the saved prompt data from the database. The user (content creator) selects the prompt they want to generate from the prompt list and enters a summary of the situation and character. This detailed information is also converted into JSON format and sent from the device to the server's API. The server retrieves the corresponding prompt from the database based on the received data.
[1281] Input: Prompt ID, situation, character summary (text)
[1282] Output: Prompts and detailed information from the database
[1283] Step 3:
[1284] The server calls the AI generation service using the obtained prompt and the input situation and character summary. It sends the prompt and detailed information to the AI generation service (e.g., OpenAI GPT-4, Stable Diffusion). The AI generation service generates content such as illustrations, music, and video based on this information. This generated content is temporarily stored on the server.
[1285] Input: Prompt, Situation, Character Summary (Text)
[1286] Output: Generated content such as illustrations, music, and videos
[1287] Step 4:
[1288] The server provides the generated content to the content creator. The user (content creator) can review the provided content and make further corrections or additions. An interface displaying the generated content in real time is displayed on the terminal. The content creator can request regeneration as needed.
[1289] Input: Generated content, corrections and additional input (text)
[1290] Output: Display of content updated in real time
[1291] Step 5:
[1292] If the content creator is satisfied with the generated content, they press the save button to save it to the server. When the save button is pressed, the device converts the generated content into JSON format and sends it to the server's API. The server saves the received generated content in its database and returns a successful save response to the client.
[1293] Input: Press the save button, generated content (JSON format)
[1294] Output: Content saved to database, save success response
[1295] In this way, the system enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality, while the generated content is efficiently managed, stored, and used.
[1296] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[1297] This invention is an improvement to a system in which a generative AI creator registers prompts related to their drawing style, and a game creator generates the necessary content based on those prompts, by combining it with an emotion engine that recognizes the user's emotions and adjusts the generated content to match the user's emotions. In this system, the server, terminal, and user (generative AI creator, game creator) work together to perform processing and improve the quality of the generated content.
[1298] overview
[1299] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on the prompts, (3) the AI generates content based on the input, (4) the emotion engine recognizes the user's emotions and adjusts the generated content, (5) the generated content is saved and managed, and (6) it is provided to the game creator.
[1300] Program processing
[1301] 1. Generative AI creator registers a prompt
[1302] User (generative AI creator)
[1303] Access a web form and fill out prompts based on your drawing style.
[1304] The form has a text entry field where creators can describe their prompt in detail.
[1305] Terminal
[1306] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[1307] server
[1308] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[1309] 2. Game creators use prompts to generate content
[1310] User (game creator)
[1311] Select the prompt you want to generate from the prompt list and enter the required information in the input form to specify the character details and situation.
[1312] Enter the required information and click the Generate button to send a generation request to the server.
[1313] Terminal
[1314] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[1315] server
[1316] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[1317] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[1318] The generated content is temporarily stored and the generation results are returned to the game creator.
[1319] 3. Tuning the emotion engine and generated content
[1320] Terminal
[1321] When game creators check the generated content, sensors such as cameras and microphones are activated to recognize the user's emotions.
[1322] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates emotion data.
[1323] server
[1324] Based on the emotion data sent from the emotion engine, the generated content is evaluated to see if it matches the user's emotion.
[1325] Run a regeneration and tweak process to adjust the content as needed.
[1326] 4. Store and manage generated content
[1327] User (game creator)
[1328] You can check the generated content displayed on the screen and save it by clicking the save button.
[1329] It can also be modified and regenerated as needed.
[1330] Terminal
[1331] When the save button is clicked, the generated content is sent to the server API in JSON format.
[1332] server
[1333] The received generated content is saved in a database and a response indicating success is returned to the client.
[1334] Supports the management and provision of generated content, making it easily accessible to game creators.
[1335] Specific examples
[1336] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[1337] 1. Generative AI Creator
[1338] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[1339] 2. Game Creator
[1340] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[1341] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[1342] 3. Emotion Engine
[1343] Analyze game creators' emotions in real time to ensure the generated content meets expectations.
[1344] If the emotion does not match, it instructs the AI generation service to regenerate it.
[1345] 4. Generated results
[1346] Illustrations generated by AI are provided to game creators via a server.
[1347] Optimized content is provided based on the results confirmed through the emotion engine.
[1348] The game creator checks the generated content and saves it.
[1349] This will enable collaboration between generative AI creators, game creators, and emotion engines, providing an environment in which high-quality game content that matches user emotions can be efficiently generated and managed.
[1350] The processing flow will be explained below.
[1351] Step 1:
[1352] The user (generative AI creator) accesses a web form and enters a prompt based on their drawing style. The form includes a text input field where the creator can further describe the prompt.
[1353] Step 2:
[1354] The device captures the submit event of the web form, gets the prompt entered in JavaScript, converts the input into JSON format, and sends it to the server's API endpoint.
[1355] Step 3:
[1356] The server saves the received prompt data in the database. After the save process is complete, it generates a save success response and returns it to the client.
[1357] Step 4:
[1358] The user (game creator) accesses the prompt list page and selects the prompt they want to create. Based on the selected prompt, they enter the necessary information into the input form to specify the character details and situation.
[1359] Step 5:
[1360] The terminal captures the form submission event, obtains the selected prompt ID and the user's input, converts it to JSON format, and sends it to the server's API endpoint.
[1361] Step 6:
[1362] The server retrieves the corresponding prompt from the database based on the received prompt ID and user input, passes the retrieved prompt and user input information to the AI generation service, and instructs it to generate content.
[1363] Step 7:
[1364] The server receives the generated content from the AI generation service, temporarily stores it, and returns the generated results to the game creator.
[1365] Step 8:
[1366] The device displays the generated content on the user's (game creator's) screen. When the user checks the generated content, sensors such as the device's camera and microphone are activated to collect emotional data.
[1367] Step 9:
[1368] The emotion engine analyzes the user's facial expressions and tone of voice in real time to generate emotion data, which is then sent to the server.
[1369] Step 10:
[1370] The server evaluates whether the generated content matches the user's emotions based on the emotion data received from the emotion engine. Based on the evaluation results, the content is regenerated or fine-tuned as necessary.
[1371] Step 11:
[1372] The server returns the adjusted generated content to the device, and the user (game creator) checks the generated content again.
[1373] Step 12:
[1374] When the user (game creator) is satisfied with the generated content, they click the save button. The device then captures the save button click event, converts the generated content into JSON format, and sends it to the server's API endpoint.
[1375] Step 13:
[1376] The server saves the generated content it receives in the database. After the save process is complete, it generates a save success response and returns it to the client.
[1377] Step 14:
[1378] The device displays a message indicating successful saving on the user's (game creator's) screen.
[1379] The above is the specific flow of operation for each processing step in this invention. This allows AI creators and game creators to work together, and by introducing an emotion engine, an environment is realized in which high-quality game content that matches the user's emotions can be efficiently generated and managed.
[1380] Example 2
[1381] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1382] Current content generation systems using generative AI do not take user emotions into account, so the generated content may not necessarily match the user's expectations or emotions. This poses challenges in improving the user experience and optimizing the quality of generated content.
[1383] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1384] In this invention, the server includes means for a generation device creator to register instructions regarding his or her drawing style, means for a developer to input an outline of the situation and characters based on the instructions, means for the generation device to generate video and audio based on the input information, means for saving the generated content in a data storage device, means for providing the generated content to the developer, means for acquiring user emotions using a sensing device and analyzing them with an emotion engine, and means for adjusting the generated content based on the analysis results, thereby making it possible to generate and provide high-quality content that matches the user's emotions.
[1385] A "generator creator" is a user who is responsible for registering instructions based on their own drawing style and concept into the system.
[1386] "Instructions" are information that details the style and specific elements of the content to be generated.
[1387] The "developer" is a user who inputs details about the situation and characters based on the generated prompts, and then generates and checks the final content.
[1388] "Context" is information that indicates a specific situation or background of the generated content.
[1389] "Characters" refers to information that refers to the characters and character details that appear in the generated content.
[1390] A "generation device" is an artificial intelligence system that automatically generates content such as video and audio based on information entered by the user.
[1391] "Video" is a form of visual content, including illustrations, animations, and videos.
[1392] "Audio" refers to a form of auditory content, including music, sound effects, narration, etc.
[1393] A "data store" is a physical or virtual storage system for storing generated content.
[1394] A "sensing device" is a device used to acquire emotional data of a user, and includes a camera, a microphone, and the like.
[1395] The "emotion engine" is a software component that analyzes acquired emotion data and evaluates the user's emotional state.
[1396] The "analysis results" are information about the user's emotional state obtained by the emotion engine.
[1397] "Tuning" is the process of modifying or regenerating generated content to match the user's emotional state.
[1398] "Content" refers to content such as video and audio automatically created by a generating device.
[1399] This invention is a system in which a generator creator registers instructions (prompts) based on their own drawing style and concept into the system, and a developer uses the prompts to input details of the situation and characters, and the generator generates content such as video and audio. This generated content is adjusted by acquiring the user's emotions using a sensing device and analyzing them with an emotion engine, providing high-quality content that matches the user's emotions.
[1400] Specifically, the system is implemented according to the following steps: First, the creator of the generator accesses the web interface and describes in detail their drawing style and the characteristics of their work. The input prompt is obtained by JavaScript on the device, converted into JSON format, and sent to the server's API. The server saves this prompt data in a data storage device and returns a response to the device indicating that the save was successful.
[1401] Next, the developer selects the desired prompt from a list of prompts and enters a summary of the situation and character. For example, the developer selects "Fantasy character, young wizard in blue robes, against a magical tower background" as the prompt and enters "Young wizard undergoes trials to become a full wizard" as the character details. This input is captured on the device and sent back to the server's API in JSON format.
[1402] The server then passes prompts and additional information to the AI generation service based on the received data. The AI generation service then automatically generates content such as video and audio based on this information. The generated content is temporarily stored in a data storage device, and the generated results are returned to the developer.
[1403] When the developer checks the generated content, sensing devices (cameras and microphones) are activated to capture the user's emotional data in real time. The emotion engine analyzes this data, evaluates whether the generated content matches the user's emotions, and regenerates or fine-tunes it as necessary.
[1404] For example, consider a scenario where a developer wants to generate a scene depicting a young wizard undergoing a trial using a prompt registered by a generator creator: "Fantasy character, young wizard in blue robes, with a magical tower in the background." The generator uses this information to generate the corresponding video and evaluates and adjusts the generated content using a sensing device and emotion engine. Ultimately, high-quality content that matches the user's emotions is provided, and the developer can save the content.
[1405] In this way, the present invention realizes efficient generation and management of high-quality content that reflects the user's emotions through collaboration between generation device creators, developers, sensing devices, and emotion engines.
[1406] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1407] Step 1:
[1408] The user (generator creator) accesses a web interface and inputs instructions (prompts) describing their drawing style and the characteristics of their work. For example, they might input "a fantasy character, a young wizard in a blue robe, with a magical tower as the background." The input instructions are retrieved using JavaScript on the device. Input: The prompt text entered by the user into the web form. Output: The prompt text is converted to JSON format.
[1409] Step 2:
[1410] The terminal converts the prompt text into JSON format and sends it as a POST request to the server's API. At this time, by sending data to a specific endpoint, the server prepares to receive the instruction data. Input: Prompt text in JSON format. Output: POST request sent to the server.
[1411] Step 3:
[1412] The server parses the received JSON data and validates the contents before saving it to the database. If the validation is successful, the data is saved to the database and a response indicating successful saving is returned to the terminal. Input: Prompt text in JSON format sent to the server. Output: Prompt text is saved to the database and a response indicating successful saving is returned.
[1413] Step 4:
[1414] The user (developer) selects the desired prompt from the prompt list and enters details of the situation and characters. For example, "A young wizard undergoes the trials to become a full-fledged wizard." Input: The prompt ID selected from the prompt list and additional information from the user. Output: The generation request converted to JSON format.
[1415] Step 5:
[1416] The terminal converts the selected prompt ID and additional information into JSON format and sends it to the server's API. Input: Prompt ID and user's additional information. Output: Sends a generation request to the server.
[1417] Step 6:
[1418] The server receives the generation request, retrieves a prompt from the database, and then passes the prompt and additional information to the AI generation service. The AI generation service uses this information to generate content such as video and audio. The generated content is stored in a temporary storage area on the server. Input: Generation request sent to the server. Output: Generated content.
[1419] Step 7:
[1420] The server stores the generated content in a temporary storage area and returns the generated result to the end user. Input: Generated content. Output: Return of generated result to the end user.
[1421] Step 8:
[1422] When a user (developer) checks the generated content, sensing devices (camera and microphone) connected to the device collect the user's emotional data. For example, the camera detects the user's facial expressions, and the microphone detects the tone of voice. Input: Generated content and user's emotional data. Output: Collected emotional data.
[1423] Step 9:
[1424] The device sends the collected emotion data to the server in real time. Input: Collected emotion data. Output: Sending emotion data to the server.
[1425] Step 10:
[1426] The server passes emotional data to the emotion engine for analysis. Based on the analysis results, it evaluates how well the generated content matches the user's emotions and regenerates or fine-tunes it as necessary. Input: Emotion data passed to the emotion engine. Output: Analysis results and adjustment instructions.
[1427] Step 11:
[1428] The server finally provides the adjusted generated content to the end user, allowing the user to review the content. Input: Adjusted generated content. Output: Provided to the end user.
[1429] Step 12:
[1430] The user (developer) checks the generated content displayed on the screen and saves it by clicking the save button. It is also possible to modify or regenerate the content as needed. Input: User actions on the generated content. Output: The final saved content.
[1431] (Application example 2)
[1432] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1433] Conventional content generation systems using generative artificial intelligence have had difficulty generating content that matches the user's emotions. In the entertainment field in particular, there is a demand for content that responds to the user's emotions and reactions. Therefore, there is a need for technology that can recognize user emotions in real time and adjust and optimize content based on those emotions.
[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[1435] In this invention, the server includes means for the generating AI creator to register prompts related to his / her drawing style, means for the game creator to input an outline of the situation and characters, means for the generating AI to generate illustrations and music based on the input information, means for saving the generated content in a database, means for providing the generated content to the game creator, means for adjusting the generated content using an emotion engine that recognizes the user's emotions, and means for providing the adjusted content to the user, thereby enabling the generation of content that matches the user's emotions.
[1436] The "generative AI creator" is an AI that is responsible for registering prompts based on its own drawing style.
[1437] A "prompt" is a sentence or keyword that a generative AI model uses as an instruction to generate content.
[1438] A "game creator" is a user whose role is to input a summary of the situation and characters based on prompts.
[1439] "Situation" refers to the specific scene or situation in which a character is placed within a game.
[1440] "Character Overview" refers to the basic characteristics and background information of characters that appear in the game.
[1441] "Generative AI" is AI that generates content such as illustrations and music based on input information.
[1442] A "database" is a system that stores generated content and makes it accessible as needed.
[1443] The "emotion engine" is a system that recognizes the user's emotions in real time and acquires that data.
[1444] "Adjustment" refers to the process of making changes to the generated content based on the user's emotions as recognized by the emotion engine.
[1445] "Means" refers to a device, method, or composition of matter employed to accomplish a particular purpose.
[1446] This embodiment describes a system for generating and providing entertainment content that matches a user's emotions. This system features a generative AI creator registering prompts, a game creator using the prompts to generate content, and an emotion engine adjusting the generated content based on the user's emotions.
[1447] Hardware and software used
[1448] Hardware
[1449] Smartphone or head-mounted display (HMD)
[1450] Camera and microphone for emotion recognition by the emotion engine
[1451] software
[1452] JavaScript (front-end data processing)
[1453] Python (server-side script)
[1454] TensorFlow (a machine learning framework for emotion recognition)
[1455] OpenAI API (generative AI models for content generation)
[1456] Detailed process description
[1457] 1. Prompt registration by generative AI creator
[1458] Users, or generative AI creators, submit prompts based on their drawing style through a web form, such as "a fantasy character, a young wizard in blue robes, with a magical tower in the background."
[1459] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[1460] The server stores the received prompt data in a database and returns a response indicating successful storage to the client.
[1461] 2. Content generation by game creators
[1462] The user, the game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and the situation, such as "a scene in which a young wizard is put to the test."
[1463] On the terminal, the selected prompt ID and the user's input are sent to the server API in JSON format.
[1464] The server retrieves prompts from the database and calls the OpenAI API based on the user's input. The AI generates content such as illustrations and music based on the specified prompts and input.
[1465] 3. Content adjustment using emotion engines
[1466] When a user checks the content generated on the device, the camera and microphone are activated to recognize emotions. Facial expressions and tone of voice are analyzed in real time to obtain emotional data.
[1467] The server evaluates whether the generated content matches the user's emotion based on the emotion data sent from the emotion engine. If the emotion does not match, it instructs the AI generation service to regenerate the content.
[1468] 4. Storing and Managing Generated Content
[1469] The user can review the generated content and save it by clicking the save button, and can also regenerate or fine-tune it as needed.
[1470] 5. Specific Examples
[1471] Example prompt from a generative AI creator: "A quiet street lit by streetlights on a new moon night."
[1472] Example input from a game creator: "A scene in which the main character walks through a quiet street."
[1473] These operations enable the generation and provision of high-quality game content that responds to the user's emotions.
[1474] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1475] Step 1:
[1476] The user, a generative AI creator, registers prompts based on their drawing style through a web form.
[1477] Input: The prompt text entered by the user into the web form
[1478] Specific Action: A user accesses a web form, enters text based on their drawing style, and clicks the submit button.
[1479] Step 2:
[1480] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[1481] Input: Prompt text taken from a web form
[1482] Data processing: Convert the input text into JSON format
[1483] Output: API request to the server
[1484] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[1485] Step 3:
[1486] The server saves the prompt data received in the database and returns a response indicating success to the client.
[1487] Input: Prompt data in JSON format
[1488] Data processing: Convert prompt data into database format
[1489] Output: Save successful response
[1490] What happens: The server-side script opens a database connection, saves the prompt data, and returns a response to the client if successful.
[1491] Step 4:
[1492] The user, a game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and situation.
[1493] Input: Prompt ID, character details, situation text
[1494] What happens: A game creator visits a web form, selects a prompt from a drop-down menu, enters the required details, and submits it.
[1495] Step 5:
[1496] On the terminal, the selected prompt ID and the user's input are sent to the server's API in JSON format.
[1497] Input: Prompt ID, character details, situation text
[1498] Data processing: Convert this information into JSON format
[1499] Output: API request to the server
[1500] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[1501] Step 6:
[1502] The server retrieves prompts from the database and generates content by calling OpenAI's API along with the user's input information.
[1503] Input: Prompt ID, character details, situation text
[1504] Data processing: Retrieve prompts from the database, combine them with user input, and send them to the OpenAI API
[1505] Output: Generated content
[1506] What happens: A server-side script opens a database connection, retrieves prompt data, and calls the OpenAI API to generate content.
[1507] Step 7:
[1508] The generated content is temporarily stored and the generation results are returned to the game creator.
[1509] Input: Generated content
[1510] Data storage: temporarily stores generated content
[1511] Output: The generated response
[1512] Specific operation: The server-side script temporarily stores the generated content and returns the generated result to the client.
[1513] Step 8:
[1514] When a user checks the generated content on the terminal, the camera and microphone are activated to analyze facial expressions and tone of voice in real time and obtain emotional data.
[1515] Input: User's facial expression and tone of voice
[1516] Data processing: Analyze acquired data into emotion data
[1517] Output: Emotion data
[1518] Specific operation: The camera and microphone capture the user's facial expressions and voice, and the emotion engine analyzes them in real time.
[1519] Step 9:
[1520] Based on the emotion data transmitted from the emotion engine, the server evaluates whether the generated content matches the user's emotion, and issues an instruction to regenerate the content if necessary.
[1521] Input: emotion data, generated content
[1522] Data evaluation: Evaluate the degree of agreement between emotion data and generated content
[1523] Output: Regeneration instructions (if necessary)
[1524] Specific operation: A server-side script analyzes the emotion data, evaluates the degree of match of the generated content, and issues instructions for regeneration if necessary.
[1525] Step 10:
[1526] The user checks the generated content and saves it by clicking the save button.
[1527] Input: Generated content
[1528] Output: Saved content
[1529] Specific operation: The user checks the generated content in the browser and clicks the save button to save the content.
[1530] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[1531] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[1532] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.
[1533] [Fourth embodiment]
[1534] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1535] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.
[1536] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[1537] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.
[1538] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[1539] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[1540] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[1541] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.
[1542] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[1543] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[1544] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[1545] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[1546] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1547] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[1548] overview
[1549] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[1550] Program processing
[1551] 1. Generative AI creator registers a prompt
[1552] User (generative AI creator)
[1553] Fill in the prompts based on your drawing style through a web form.
[1554] The form has a text entry field where creators can describe their prompt in detail.
[1555] Terminal
[1556] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[1557] server
[1558] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[1559] 2. Game creators use prompts to generate content
[1560] User (game creator)
[1561] Select the prompt you want to generate from the prompt list and access the input form to specify character details and the situation.
[1562] Enter the required information and click the Generate button to send a generation request to the server.
[1563] Terminal
[1564] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[1565] server
[1566] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[1567] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[1568] The generated content is temporarily stored and the generation results are returned to the game creator.
[1569] 3. Store and manage generated content
[1570] User (game creator)
[1571] You can check the generated content displayed on the screen and save it by clicking the save button.
[1572] It can also be modified and regenerated as needed.
[1573] Terminal
[1574] When the save button is clicked, the generated content is sent to the server API in JSON format.
[1575] server
[1576] The received generated content is saved in a database and a response indicating success is returned to the client.
[1577] Supports the management and provision of generated content, making it easily accessible to game creators.
[1578] Specific examples
[1579] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[1580] 1. Generative AI Creator
[1581] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[1582] 2. Game Creator
[1583] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[1584] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[1585] 3. Generated results
[1586] Illustrations generated by AI are provided to game creators via a server.
[1587] The game creator checks the generated content and saves it.
[1588] This will promote collaboration between generative AI creators and game creators, and create a system that provides an environment in which even individuals and small organizations can efficiently generate and manage high-quality game content.
[1589] The processing flow will be explained below.
[1590] Step 1:
[1591] The user (generative AI creator) accesses a web form and fills in prompts based on their own drawing style.
[1592] Step 2:
[1593] The device captures the web form submit event and retrieves the input prompt in JavaScript.
[1594] Step 3:
[1595] The device converts the prompt into JSON format and sends it to the server's API endpoint.
[1596] Step 4:
[1597] The server saves the received prompt data in the database and generates a response indicating that the save was successful.
[1598] Step 5:
[1599] The server returns a successful save response to the device.
[1600] Step 6:
[1601] The user (game creator) accesses the prompt list page and selects the prompt they want to create.
[1602] Step 7:
[1603] Based on the prompt selected by the user (game creator), the necessary information is entered into an input form for entering character details and the situation.
[1604] Step 8:
[1605] The terminal captures the form submit event and obtains the selected prompt ID and the user's input.
[1606] Step 9:
[1607] The device converts the prompt ID and the user's input into JSON format and sends it to the server's API endpoint.
[1608] Step 10:
[1609] The server retrieves the corresponding prompt from the database based on the prompt ID received and the user input.
[1610] Step 11:
[1611] The server passes the obtained prompt and user input information to the AI generation service, instructing it to generate content.
[1612] Step 12:
[1613] The server receives the generated content from the AI generation service and temporarily stores it.
[1614] Step 13:
[1615] The server returns the generated results to the terminal.
[1616] Step 14:
[1617] The device displays the generated results on the user's (game creator's) screen so that they can be checked.
[1618] Step 15:
[1619] The user (game creator) clicks the save button for the generated content.
[1620] Step 16:
[1621] The device captures the click event of the save button, converts the generated content into JSON format, and sends it to the server's API endpoint.
[1622] Step 17:
[1623] The server saves the received generated content in the database and generates a response indicating that saving was successful.
[1624] Step 18:
[1625] The server returns a successful save response to the device.
[1626] Step 19:
[1627] The device displays a message indicating successful saving on the user's (game creator's) screen.
[1628] The above is the specific operational flow of each processing step in the present invention. This will realize an environment in which AI creators and game creators can work together to efficiently generate and manage high-quality game content.
[1629] Example 1
[1630] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1631] Previous game content generation systems had issues such as creators being unable to effectively use prompts based on their own drawing style, and the time and effort required to check, modify, and regenerate generated content. Furthermore, there was a lack of a way to display generated content in real time and easily save it.
[1632] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[1633] In this invention, the server includes a means for a generation AI creator to register prompts regarding their drawing style, a means for a game creator to input an outline of a situation or character, a means for the generation AI to generate illustrations and music, a means for saving the generated content in a database, a means for the game creator to check, modify, regenerate, and save the generated content, and a means for displaying the generated content in real time and processing save requests, thereby enabling creators to efficiently generate high-quality content and instantly check, modify, and save it.
[1634] A "generative AI creator" is a creator who creates and registers prompts based on their own drawing style.
[1635] A "prompt" is a text description of instructions and conditions for generating content such as illustrations and music.
[1636] A "game creator" is a creator whose role is to input an outline of the situation and characters based on prompts and instruct the generation of game content.
[1637] A "situation" is a specific description of a scene or situation within the game.
[1638] "Character Overview" is information that describes the character's appearance, personality, behavior, etc.
[1639] "Generative AI" is AI that automatically generates content such as illustrations and music based on input information.
[1640] A "database" is a system that permanently stores and manages data such as generated content and prompts.
[1641] An "interface" is a screen or tool that provides an input means for a user to register a prompt or enter information.
[1642] A "generation request" is a request that a game creator inputs detailed information about the content to be generated based on a prompt and sends to the server.
[1643] A "storage request" is a request sent to a server to store generated content in a database.
[1644] This invention relates to a system in which a generation AI creator registers prompts related to images, and a game creator uses the prompts to generate the necessary content. In this system, a server, a terminal, and users (the generation AI creator and the game creator) work together to perform processing.
[1645] overview
[1646] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on those prompts, (3) the AI generates content based on the input, (4) the generated content is saved and managed, and (5) it is provided to the game creator.
[1647] Additionally, generated content can be easily reviewed, modified, regenerated, and saved, and creation and saving requests are handled in real time.
[1648] Program processing
[1649] Generative AI creator registers prompts
[1650] User (generative AI creator)
[1651] Through a web form, users enter prompts based on their drawing style, such as "fantasy character, young wizard in blue robes, with a magical tower in the background."
[1652] Terminal
[1653] When the form is submitted, JavaScript takes the prompt content, converts it to JSON format, and sends it to the server's API.
[1654] server
[1655] The server saves the received prompt data in a database and returns a response indicating that the save was successful to the client.
[1656] Game creators use prompts to generate content
[1657] User (game creator)
[1658] The user selects the prompt they want to generate from a list of prompts, enters details about the character, such as "A young wizard undergoes trials to become a full-fledged wizard," and clicks the Generate button to send a generation request to the server.
[1659] Terminal
[1660] JavaScript gets the selected prompt ID and the user's input, converts it into JSON format, and sends it to the server's API.
[1661] server
[1662] The server retrieves the prompt from the database and calls the AI generation service along with the user's input information. The AI generation service is used to automatically generate content such as a scene in which a young wizard in a blue robe is put to the test in front of a magical tower. The generated content is temporarily saved and the results are returned to the game creator.
[1663] Store and manage generated content
[1664] User (game creator)
[1665] The user can check the generated content displayed on the screen, and modify or regenerate it as necessary. The generated content is saved by clicking the Save button.
[1666] Terminal
[1667] When the save button is clicked, the generated content is sent to the server API in JSON format.
[1668] server
[1669] The server stores the generated content in a database and returns a successful save response to the client. This system enables creators to efficiently generate high-quality content and instantly check, modify, and save it.
[1670] For example, a generative AI creator can register a prompt to draw a fantasy character, and a game creator can generate a brave young wizard. By using this system, creators can efficiently generate and manage high-quality game content.
[1671] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1672] Step 1:
[1673] User (generative AI creator)
[1674] Input: Enter a prompt into a web form, such as "Fantasy character, young wizard in blue robes, with a magical tower in the background."
[1675] How it works: A generative AI creator visits a specific web form and fills in text fields with prompts that reflect their drawing style.
[1676] Output: The prompt text entered.
[1677] Step 2:
[1678] Terminal
[1679] Input: The prompt text entered into the web form.
[1680] How it works: When the submit button on the form is clicked, a JavaScript is triggered that retrieves the prompt text that was entered.
[1681] Data processing: Convert the obtained prompt text into JSON format.
[1682] Output: Prompt data in JSON format.
[1683] Step 3:
[1684] server
[1685] Input: Prompt data sent from the terminal in JSON format.
[1686] Operation: The server stores the received prompt data in a database.
[1687] Output: Save result (success or failure response) to database.
[1688] Step 4:
[1689] User (game creator)
[1690] Input: A request to generate content based on a saved prompt. Specifically, you select a prompt and enter character details and a situation, such as "A young wizard undergoes trials to become a full wizard."
[1691] How it works: The game creator selects the prompt they want to generate from the prompt list screen and enters character details and the situation.
[1692] Output: The generated request and associated input information.
[1693] Step 5:
[1694] Terminal
[1695] Input: The generated request and prompt ID entered by the user.
[1696] What it does: JavaScript takes the generated request and prompt ID and converts it to JSON format.
[1697] Data processing: The generation request and prompt ID converted to JSON format are sent to the server API.
[1698] Output: Generated request data in JSON format.
[1699] Step 6:
[1700] server
[1701] Input: The generated request data in JSON format sent from the terminal.
[1702] How it works: The server retrieves prompt data from the database based on the prompt ID, then passes the prompt data and a generation request to the AI generation service.
[1703] Data Computing: AI generation services auto-generate content such as illustrations and music based on prompts and generation requests.
[1704] Output: The generated content and the generated result (success or failure response).
[1705] Step 7:
[1706] server
[1707] Input: Generated content from an AI-generated service.
[1708] How it works: The server temporarily stores the generated content and returns the generated results to the game creator.
[1709] Output: The URL or file path of the generated content.
[1710] Step 8:
[1711] User (game creator)
[1712] Input: The URL or file path of the generated content.
[1713] Action: The game creator reviews the generated content displayed, modifies it or regenerates it as needed, and clicks the Save button if they wish to save it.
[1714] Output: Save request.
[1715] Step 9:
[1716] Terminal
[1717] Input: Save request and generated content.
[1718] What it does: JavaScript converts the save request and generated content into JSON format.
[1719] Data processing: The save request and generated content converted into JSON format are sent to the server's API.
[1720] Output: Save request data in JSON format.
[1721] Step 10:
[1722] server
[1723] Input: Save request data sent from the device in JSON format.
[1724] Operation: The server stores the received save request data in a database.
[1725] Output: Save result (success or failure response) to database.
[1726] (Application example 1)
[1727] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1728] With conventional content generation systems, collaboration between general users and professional creators was difficult, making it difficult to quickly and efficiently materialize users' ideas. Furthermore, the storage and management of generated content was also inefficient, resulting in problems such as a decline in content quality and productivity.
[1729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[1730] In this invention, the server includes means for a generating AI creator to register prompts related to their drawing style, means for a content creator to input an outline of a situation or character, means for the generating AI to generate illustrations, music, and video, means for saving the generated content in a database, means for providing the generated content to the content creator, means for providing an interface for the generating AI creator to register prompts, and means for displaying content generated in real time based on the outline of a situation or character input by the content creator. This enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality.
[1731] A "generative AI creator" refers to an AI that registers prompts related to one's drawing style and contributes to content generation based on those prompts.
[1732] A "prompt" is a piece of text or keyword that provides instructions or guidelines for a generative AI model to generate a particular depiction or situation.
[1733] "Content creators" refer to users who input a situation or character outline based on prompts and use or edit the content generated by the generative AI.
[1734] A "situation" is information that describes a specific scene or setting, providing the background or environment for a generative AI model to generate content.
[1735] "Character Description" refers to text describing the characteristics and details of a character used in content generation.
[1736] "Generative AI" refers to AI that has the technology to automatically generate content such as illustrations, music, and video based on prompts and additional input information.
[1737] "Content" refers to digital works such as illustrations, music, and video created by generative AI models.
[1738] "Database" refers to a digital storage system for storing and managing Generated Content.
[1739] "Interface" means the web form or application user interface for entering and registering a Student Configuration Prompt.
[1740] "Real-time" refers to the system's ability to respond almost immediately to input information and quickly display generated content.
[1741] This embodiment of the present invention relates to a system in which a user generates content using a generative AI model, stores the content in a database, and provides it to other users. In this system, a server, a terminal, and users (generative AI creators and content creators) work together to perform processing.
[1742] Overall processing overview of the program
[1743] 1. Generative AI creator registers prompt
[1744] user:
[1745] Generative AI creators use a dedicated web form to enter prompts based on their drawing style, such as specific drawing guidelines like "underwater city, futuristic design, adventurer adventure scene."
[1746] Device:
[1747] The prompt information entered into the form by the artificial intelligence creator is obtained using JavaScript and sent to the server's API in JSON format.
[1748] server:
[1749] The received prompt data is saved in the database and a response indicating successful saving is returned to the client (user).
[1750] 2. Content creators use prompts to generate content
[1751] user:
[1752] Content creators select a prompt they want to generate from a list of prompts and enter a brief description of the characters and situation, such as "a scene in which an adventurer finds treasure in a futuristic underwater city."
[1753] Device:
[1754] Obtain the selected prompt ID and detailed information about the character and situation, and send it in JSON format to the server's API.
[1755] server:
[1756] The system retrieves a prompt from the database and calls an AI generation service (e.g., OpenAI GPT-4 or Stable Diffusion) along with the user's input. The AI generation service automatically generates content such as illustrations, music, and video based on the specified prompt and input. The generated content is then temporarily stored and returned to the content creator.
[1757] 3. Store and manage generated content
[1758] user:
[1759] The content creator can review the generated content and, if satisfied, press the "Save" button to save the content to the database. It can also be modified or regenerated as needed.
[1760] Device:
[1761] Once the save button is clicked, the generated content is sent to the server API in JSON format.
[1762] server:
[1763] It stores the received generated content in a database and returns a successful save response to the client, making it easier to manage and serve generated content and make it easily accessible to content creators.
[1764] Specific step-by-step instructions
[1765] Server Roles and Configuration
[1766] The server includes the following means:
[1767] A means for generative AI creators to register prompts.
[1768] A way for content creators to input situations and character descriptions.
[1769] A means for generative AI to generate illustrations, music, and video.
[1770] A means of storing generated content in a database.
[1771] A means of providing generated content to content creators.
[1772] A means to provide an interface for generative AI creators to register prompts.
[1773] A means of displaying content generated in real time based on situations and character descriptions entered by content creators.
[1774] This will enable efficient collaboration between general users and professional creators, and will enable users' ideas to be realized quickly and with high quality. Below are some examples of prompt sentences:
[1775] Prompt: Underwater city, futuristic design, adventurer adventure scene
[1776] Details: Underwater city features transparent domes, alien colonies, and hidden treasure
[1777] In this way, the present invention realizes a system that allows users to register prompts based on their own ideas and visual and auditory instructions, and efficiently manage, store, and use the generated content.
[1778] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1779] Step 1:
[1780] This is the stage where the user (generative AI creator) registers a prompt. The user enters a prompt based on their own drawing style into a dedicated web form. The entered prompt is converted into JSON format using JavaScript. The device sends this JSON data to the server's API. The server saves the received prompt data in a database and returns a successful save response to the client (user). For example, a prompt such as "underwater city, futuristic design, scene of adventurers on an adventure" can be entered here.
[1781] Input: User input for prompt (text)
[1782] Output: JSON format prompt data, save success response
[1783] Step 2:
[1784] The server retrieves the saved prompt data from the database. The user (content creator) selects the prompt they want to generate from the prompt list and enters a summary of the situation and character. This detailed information is also converted into JSON format and sent from the device to the server's API. The server retrieves the corresponding prompt from the database based on the received data.
[1785] Input: Prompt ID, situation, character summary (text)
[1786] Output: Prompts and detailed information from the database
[1787] Step 3:
[1788] The server calls the AI generation service using the obtained prompt and the input situation and character summary. It sends the prompt and detailed information to the AI generation service (e.g., OpenAI GPT-4, Stable Diffusion). The AI generation service generates content such as illustrations, music, and video based on this information. This generated content is temporarily stored on the server.
[1789] Input: Prompt, Situation, Character Summary (Text)
[1790] Output: Generated content such as illustrations, music, and videos
[1791] Step 4:
[1792] The server provides the generated content to the content creator. The user (content creator) can review the provided content and make further corrections or additions. An interface displaying the generated content in real time is displayed on the terminal. The content creator can request regeneration as needed.
[1793] Input: Generated content, corrections and additional input (text)
[1794] Output: Display of content updated in real time
[1795] Step 5:
[1796] If the content creator is satisfied with the generated content, they press the save button to save it to the server. When the save button is pressed, the device converts the generated content into JSON format and sends it to the server's API. The server saves the received generated content in its database and returns a successful save response to the client.
[1797] Input: Press the save button, generated content (JSON format)
[1798] Output: Content saved to database, save success response
[1799] In this way, the system enables efficient collaboration between general users and professional creators, enabling users' ideas to be realized quickly and with high quality, while the generated content is efficiently managed, stored, and used.
[1800] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[1801] This invention is an improvement to a system in which a generative AI creator registers prompts related to their drawing style, and a game creator generates the necessary content based on those prompts, by combining it with an emotion engine that recognizes the user's emotions and adjusts the generated content to match the user's emotions. In this system, the server, terminal, and user (generative AI creator, game creator) work together to perform processing and improve the quality of the generated content.
[1802] overview
[1803] The main functions of this system are as follows: (1) the generation AI creator registers image prompts, (2) the game creator inputs characters and situations based on the prompts, (3) the AI generates content based on the input, (4) the emotion engine recognizes the user's emotions and adjusts the generated content, (5) the generated content is saved and managed, and (6) it is provided to the game creator.
[1804] Program processing
[1805] 1. Generative AI creator registers a prompt
[1806] User (generative AI creator)
[1807] Access a web form and fill out prompts based on your drawing style.
[1808] The form has a text entry field where creators can describe their prompt in detail.
[1809] Terminal
[1810] When the form is submitted, JavaScript is used to retrieve the prompt contents and send them in JSON format to the server's API.
[1811] server
[1812] The received prompt data is saved in the database and a response indicating successful saving is returned to the client.
[1813] 2. Game creators use prompts to generate content
[1814] User (game creator)
[1815] Select the prompt you want to generate from the prompt list and enter the required information in the input form to specify the character details and situation.
[1816] Enter the required information and click the Generate button to send a generation request to the server.
[1817] Terminal
[1818] The selected prompt ID and the user's input are obtained and sent to the server API in JSON format.
[1819] server
[1820] The prompt is retrieved from the database and called with the user's input information to the AI generation service.
[1821] Using AI, it automatically generates content such as illustrations and music based on specified prompts and input.
[1822] The generated content is temporarily stored and the generation results are returned to the game creator.
[1823] 3. Tuning the emotion engine and generated content
[1824] Terminal
[1825] When game creators check the generated content, sensors such as cameras and microphones are activated to recognize the user's emotions.
[1826] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates emotion data.
[1827] server
[1828] Based on the emotion data sent from the emotion engine, the generated content is evaluated to see if it matches the user's emotion.
[1829] Run a regeneration and tweak process to adjust the content as needed.
[1830] 4. Store and manage generated content
[1831] User (game creator)
[1832] You can check the generated content displayed on the screen and save it by clicking the save button.
[1833] It can also be modified and regenerated as needed.
[1834] Terminal
[1835] When the save button is clicked, the generated content is sent to the server API in JSON format.
[1836] server
[1837] The received generated content is saved in a database and a response indicating success is returned to the client.
[1838] Supports the management and provision of generated content, making it easily accessible to game creators.
[1839] Specific examples
[1840] If a generative AI creator registers a prompt to draw a fantasy character and a game creator wants to generate a brave young wizard:
[1841] 1. Generative AI Creator
[1842] Prompt: "Fantasy character, young wizard in blue robes, magical tower in the background."
[1843] 2. Game Creator
[1844] Character Summary: "A young wizard undergoes trials to become a full-fledged wizard."
[1845] Content Generation: "A young wizard in a blue robe is put to the test in front of a magical tower."
[1846] 3. Emotion Engine
[1847] Analyze game creators' emotions in real time to ensure the generated content meets expectations.
[1848] If the emotion does not match, it instructs the AI generation service to regenerate it.
[1849] 4. Generated results
[1850] Illustrations generated by AI are provided to game creators via a server.
[1851] Optimized content is provided based on the results confirmed through the emotion engine.
[1852] The game creator checks the generated content and saves it.
[1853] This will enable collaboration between generative AI creators, game creators, and emotion engines, providing an environment in which high-quality game content that matches user emotions can be efficiently generated and managed.
[1854] The processing flow will be explained below.
[1855] Step 1:
[1856] The user (generative AI creator) accesses a web form and enters a prompt based on their drawing style. The form includes a text input field where the creator can further describe the prompt.
[1857] Step 2:
[1858] The device captures the submit event of the web form, gets the prompt entered in JavaScript, converts the input into JSON format, and sends it to the server's API endpoint.
[1859] Step 3:
[1860] The server saves the received prompt data in the database. After the save process is complete, it generates a save success response and returns it to the client.
[1861] Step 4:
[1862] The user (game creator) accesses the prompt list page and selects the prompt they want to create. Based on the selected prompt, they enter the necessary information into the input form to specify the character details and situation.
[1863] Step 5:
[1864] The terminal captures the form submission event, obtains the selected prompt ID and the user's input, converts it to JSON format, and sends it to the server's API endpoint.
[1865] Step 6:
[1866] The server retrieves the corresponding prompt from the database based on the received prompt ID and user input, passes the retrieved prompt and user input information to the AI generation service, and instructs it to generate content.
[1867] Step 7:
[1868] The server receives the generated content from the AI generation service, temporarily stores it, and returns the generated results to the game creator.
[1869] Step 8:
[1870] The device displays the generated content on the user's (game creator's) screen. When the user checks the generated content, sensors such as the device's camera and microphone are activated to collect emotional data.
[1871] Step 9:
[1872] The emotion engine analyzes the user's facial expressions and tone of voice in real time to generate emotion data, which is then sent to the server.
[1873] Step 10:
[1874] The server evaluates whether the generated content matches the user's emotions based on the emotion data received from the emotion engine. Based on the evaluation results, the content is regenerated or fine-tuned as necessary.
[1875] Step 11:
[1876] The server returns the adjusted generated content to the device, and the user (game creator) checks the generated content again.
[1877] Step 12:
[1878] When the user (game creator) is satisfied with the generated content, they click the save button. The device then captures the save button click event, converts the generated content into JSON format, and sends it to the server's API endpoint.
[1879] Step 13:
[1880] The server saves the generated content it receives in the database. After the save process is complete, it generates a save success response and returns it to the client.
[1881] Step 14:
[1882] The device displays a message indicating successful saving on the user's (game creator's) screen.
[1883] The above is the specific flow of operation for each processing step in this invention. This allows AI creators and game creators to work together, and by introducing an emotion engine, an environment is realized in which high-quality game content that matches the user's emotions can be efficiently generated and managed.
[1884] Example 2
[1885] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1886] Current content generation systems using generative AI do not take user emotions into account, so the generated content may not necessarily match the user's expectations or emotions. This poses challenges in improving the user experience and optimizing the quality of generated content.
[1887] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1888] In this invention, the server includes means for a generation device creator to register instructions regarding his or her drawing style, means for a developer to input an outline of the situation and characters based on the instructions, means for the generation device to generate video and audio based on the input information, means for saving the generated content in a data storage device, means for providing the generated content to the developer, means for acquiring user emotions using a sensing device and analyzing them with an emotion engine, and means for adjusting the generated content based on the analysis results, thereby making it possible to generate and provide high-quality content that matches the user's emotions.
[1889] A "generator creator" is a user who is responsible for registering instructions based on their own drawing style and concept into the system.
[1890] "Instructions" are information that details the style and specific elements of the content to be generated.
[1891] The "developer" is a user who inputs details about the situation and characters based on the generated prompts, and then generates and checks the final content.
[1892] "Context" is information that indicates a specific situation or background of the generated content.
[1893] "Characters" refers to information that refers to the characters and character details that appear in the generated content.
[1894] A "generation device" is an artificial intelligence system that automatically generates content such as video and audio based on information entered by the user.
[1895] "Video" is a form of visual content, including illustrations, animations, and videos.
[1896] "Audio" refers to a form of auditory content, including music, sound effects, narration, etc.
[1897] A "data store" is a physical or virtual storage system for storing generated content.
[1898] A "sensing device" is a device used to acquire emotional data of a user, and includes a camera, a microphone, and the like.
[1899] The "emotion engine" is a software component that analyzes acquired emotion data and evaluates the user's emotional state.
[1900] The "analysis results" are information about the user's emotional state obtained by the emotion engine.
[1901] "Tuning" is the process of modifying or regenerating generated content to match the user's emotional state.
[1902] "Content" refers to content such as video and audio automatically created by a generating device.
[1903] This invention is a system in which a generator creator registers instructions (prompts) based on their own drawing style and concept into the system, and a developer uses the prompts to input details of the situation and characters, and the generator generates content such as video and audio. This generated content is adjusted by acquiring the user's emotions using a sensing device and analyzing them with an emotion engine, providing high-quality content that matches the user's emotions.
[1904] Specifically, the system is implemented according to the following steps: First, the creator of the generator accesses the web interface and describes in detail their drawing style and the characteristics of their work. The input prompt is obtained by JavaScript on the device, converted into JSON format, and sent to the server's API. The server saves this prompt data in a data storage device and returns a response to the device indicating that the save was successful.
[1905] Next, the developer selects the desired prompt from a list of prompts and enters a summary of the situation and character. For example, the developer selects "Fantasy character, young wizard in blue robes, against a magical tower background" as the prompt and enters "Young wizard undergoes trials to become a full wizard" as the character details. This input is captured on the device and sent back to the server's API in JSON format.
[1906] The server then passes prompts and additional information to the AI generation service based on the received data. The AI generation service then automatically generates content such as video and audio based on this information. The generated content is temporarily stored in a data storage device, and the generated results are returned to the developer.
[1907] When the developer checks the generated content, sensing devices (cameras and microphones) are activated to capture the user's emotional data in real time. The emotion engine analyzes this data, evaluates whether the generated content matches the user's emotions, and regenerates or fine-tunes it as necessary.
[1908] For example, consider a scenario where a developer wants to generate a scene depicting a young wizard undergoing a trial using a prompt registered by a generator creator: "Fantasy character, young wizard in blue robes, with a magical tower in the background." The generator uses this information to generate the corresponding video and evaluates and adjusts the generated content using a sensing device and emotion engine. Ultimately, high-quality content that matches the user's emotions is provided, and the developer can save the content.
[1909] In this way, the present invention realizes efficient generation and management of high-quality content that reflects the user's emotions through collaboration between generation device creators, developers, sensing devices, and emotion engines.
[1910] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1911] Step 1:
[1912] The user (generator creator) accesses a web interface and inputs instructions (prompts) describing their drawing style and the characteristics of their work. For example, they might input "a fantasy character, a young wizard in a blue robe, with a magical tower as the background." The input instructions are retrieved using JavaScript on the device. Input: The prompt text entered by the user into the web form. Output: The prompt text is converted to JSON format.
[1913] Step 2:
[1914] The terminal converts the prompt text into JSON format and sends it as a POST request to the server's API. At this time, by sending data to a specific endpoint, the server prepares to receive the instruction data. Input: Prompt text in JSON format. Output: POST request sent to the server.
[1915] Step 3:
[1916] The server parses the received JSON data and validates the contents before saving it to the database. If the validation is successful, the data is saved to the database and a response indicating successful saving is returned to the terminal. Input: Prompt text in JSON format sent to the server. Output: Prompt text is saved to the database and a response indicating successful saving is returned.
[1917] Step 4:
[1918] The user (developer) selects the desired prompt from the prompt list and enters details of the situation and characters. For example, "A young wizard undergoes the trials to become a full-fledged wizard." Input: The prompt ID selected from the prompt list and additional information from the user. Output: The generation request converted to JSON format.
[1919] Step 5:
[1920] The terminal converts the selected prompt ID and additional information into JSON format and sends it to the server's API. Input: Prompt ID and user's additional information. Output: Sends a generation request to the server.
[1921] Step 6:
[1922] The server receives the generation request, retrieves a prompt from the database, and then passes the prompt and additional information to the AI generation service. The AI generation service uses this information to generate content such as video and audio. The generated content is stored in a temporary storage area on the server. Input: Generation request sent to the server. Output: Generated content.
[1923] Step 7:
[1924] The server stores the generated content in a temporary storage area and returns the generated result to the end user. Input: Generated content. Output: Return of generated result to the end user.
[1925] Step 8:
[1926] When a user (developer) checks the generated content, sensing devices (camera and microphone) connected to the device collect the user's emotional data. For example, the camera detects the user's facial expressions, and the microphone detects the tone of voice. Input: Generated content and user's emotional data. Output: Collected emotional data.
[1927] Step 9:
[1928] The device sends the collected emotion data to the server in real time. Input: Collected emotion data. Output: Sending emotion data to the server.
[1929] Step 10:
[1930] The server passes emotional data to the emotion engine for analysis. Based on the analysis results, it evaluates how well the generated content matches the user's emotions and regenerates or fine-tunes it as necessary. Input: Emotion data passed to the emotion engine. Output: Analysis results and adjustment instructions.
[1931] Step 11:
[1932] The server finally provides the adjusted generated content to the end user, allowing the user to review the content. Input: Adjusted generated content. Output: Provided to the end user.
[1933] Step 12:
[1934] The user (developer) checks the generated content displayed on the screen and saves it by clicking the save button. It is also possible to modify or regenerate the content as needed. Input: User actions on the generated content. Output: The final saved content.
[1935] (Application example 2)
[1936] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1937] Conventional content generation systems using generative artificial intelligence have had difficulty generating content that matches the user's emotions. In the entertainment field in particular, there is a demand for content that responds to the user's emotions and reactions. Therefore, there is a need for technology that can recognize user emotions in real time and adjust and optimize content based on those emotions.
[1938] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[1939] In this invention, the server includes means for the generating AI creator to register prompts related to his / her drawing style, means for the game creator to input an outline of the situation and characters, means for the generating AI to generate illustrations and music based on the input information, means for saving the generated content in a database, means for providing the generated content to the game creator, means for adjusting the generated content using an emotion engine that recognizes the user's emotions, and means for providing the adjusted content to the user, thereby enabling the generation of content that matches the user's emotions.
[1940] The "generative AI creator" is an AI that is responsible for registering prompts based on its own drawing style.
[1941] A "prompt" is a sentence or keyword that a generative AI model uses as an instruction to generate content.
[1942] A "game creator" is a user whose role is to input a summary of the situation and characters based on prompts.
[1943] "Situation" refers to the specific scene or situation in which a character is placed within a game.
[1944] "Character Overview" refers to the basic characteristics and background information of characters that appear in the game.
[1945] "Generative AI" is AI that generates content such as illustrations and music based on input information.
[1946] A "database" is a system that stores generated content and makes it accessible as needed.
[1947] The "emotion engine" is a system that recognizes the user's emotions in real time and acquires that data.
[1948] "Adjustment" refers to the process of making changes to the generated content based on the user's emotions as recognized by the emotion engine.
[1949] "Means" refers to a device, method, or composition of matter employed to accomplish a particular purpose.
[1950] This embodiment describes a system for generating and providing entertainment content that matches a user's emotions. This system features a generative AI creator registering prompts, a game creator using the prompts to generate content, and an emotion engine adjusting the generated content based on the user's emotions.
[1951] Hardware and software used
[1952] Hardware
[1953] Smartphone or head-mounted display (HMD)
[1954] Camera and microphone for emotion recognition by the emotion engine
[1955] software
[1956] JavaScript (front-end data processing)
[1957] Python (server-side script)
[1958] TensorFlow (a machine learning framework for emotion recognition)
[1959] OpenAI API (generative AI models for content generation)
[1960] Detailed process description
[1961] 1. Prompt registration by generative AI creator
[1962] Users, or generative AI creators, submit prompts based on their drawing style through a web form, such as "a fantasy character, a young wizard in blue robes, with a magical tower in the background."
[1963] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[1964] The server stores the received prompt data in a database and returns a response indicating successful storage to the client.
[1965] 2. Content generation by game creators
[1966] The user, the game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and the situation, such as "a scene in which a young wizard is put to the test."
[1967] On the terminal, the selected prompt ID and the user's input are sent to the server API in JSON format.
[1968] The server retrieves prompts from the database and calls the OpenAI API based on the user's input. The AI generates content such as illustrations and music based on the specified prompts and input.
[1969] 3. Content adjustment using emotion engines
[1970] When a user checks the content generated on the device, the camera and microphone are activated to recognize emotions. Facial expressions and tone of voice are analyzed in real time to obtain emotional data.
[1971] The server evaluates whether the generated content matches the user's emotion based on the emotion data sent from the emotion engine. If the emotion does not match, it instructs the AI generation service to regenerate the content.
[1972] 4. Storing and Managing Generated Content
[1973] The user can review the generated content and save it by clicking the save button, and can also regenerate or fine-tune it as needed.
[1974] 5. Specific Examples
[1975] Example prompt from a generative AI creator: "A quiet street lit by streetlights on a new moon night."
[1976] Example input from a game creator: "A scene in which the main character walks through a quiet street."
[1977] These operations enable the generation and provision of high-quality game content that responds to the user's emotions.
[1978] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1979] Step 1:
[1980] The user, a generative AI creator, registers prompts based on their drawing style through a web form.
[1981] Input: The prompt text entered by the user into the web form
[1982] Specific Action: A user accesses a web form, enters text based on their drawing style, and clicks the submit button.
[1983] Step 2:
[1984] On the terminal, the contents of the prompt entered are obtained using JavaScript and sent to the server API in JSON format.
[1985] Input: Prompt text taken from a web form
[1986] Data processing: Convert the input text into JSON format
[1987] Output: API request to the server
[1988] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[1989] Step 3:
[1990] The server saves the prompt data received in the database and returns a response indicating success to the client.
[1991] Input: Prompt data in JSON format
[1992] Data processing: Convert prompt data into database format
[1993] Output: Save successful response
[1994] What happens: The server-side script opens a database connection, saves the prompt data, and returns a response to the client if successful.
[1995] Step 4:
[1996] The user, a game creator, selects the prompt they want to generate from a list of prompts and specifies the character details and situation.
[1997] Input: Prompt ID, character details, situation text
[1998] What happens: A game creator visits a web form, selects a prompt from a drop-down menu, enters the required details, and submits it.
[1999] Step 5:
[2000] On the terminal, the selected prompt ID and the user's input are sent to the server's API in JSON format.
[2001] Input: Prompt ID, character details, situation text
[2002] Data processing: Convert this information into JSON format
[2003] Output: API request to the server
[2004] Specific behavior: JavaScript code is executed, retrieves the form contents, and sends them to the server in JSON format using AJAX.
[2005] Step 6:
[2006] The server retrieves prompts from the database and generates content by calling OpenAI's API along with the user's input information.
[2007] Input: Prompt ID, character details, situation text
[2008] Data processing: Retrieve prompts from the database, combine them with user input, and send them to the OpenAI API
[2009] Output: Generated content
[2010] What happens: A server-side script opens a database connection, retrieves prompt data, and calls the OpenAI API to generate content.
[2011] Step 7:
[2012] The generated content is temporarily stored and the generation results are returned to the game creator.
[2013] Input: Generated content
[2014] Data storage: temporarily stores generated content
[2015] Output: The generated response
[2016] Specific operation: The server-side script temporarily stores the generated content and returns the generated result to the client.
[2017] Step 8:
[2018] When a user checks the generated content on the terminal, the camera and microphone are activated to analyze facial expressions and tone of voice in real time and obtain emotional data.
[2019] Input: User's facial expression and tone of voice
[2020] Data processing: Analyze acquired data into emotion data
[2021] Output: Emotion data
[2022] Specific operation: The camera and microphone capture the user's facial expressions and voice, and the emotion engine analyzes them in real time.
[2023] Step 9:
[2024] Based on the emotion data transmitted from the emotion engine, the server evaluates whether the generated content matches the user's emotion, and issues an instruction to regenerate the content if necessary.
[2025] Input: emotion data, generated content
[2026] Data evaluation: Evaluate the degree of agreement between emotion data and generated content
[2027] Output: Regeneration instructions (if necessary)
[2028] Specific operation: A server-side script analyzes the emotion data, evaluates the degree of match of the generated content, and issues instructions for regeneration if necessary.
[2029] Step 10:
[2030] The user checks the generated content and saves it by clicking the save button.
[2031] Input: Generated content
[2032] Output: Saved content
[2033] Specific operation: The user checks the generated content in the browser and clicks the save button to save the content.
[2034] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.
[2035] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[2036] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.
[2037] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.
[2038] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.
[2039] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.
[2040] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).
[2041] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.
[2042] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."
[2043] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.
[2044] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).
[2045] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.
[2046] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.
[2047] 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.
[2048] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.
[2049] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.
[2050] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.
[2051] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.
[2052] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.
[2053] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.
[2054] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.
[2055] The following is further disclosed regarding the above embodiment.
[2056] (Claim 1)
[2057] A means for creators to register prompts about their drawing style;
[2058] A means for a game creator to input a summary of a situation or character based on the prompt;
[2059] A means for generating illustrations and music by a generating artificial intelligence based on the input information;
[2060] a means for storing the generated content in a database;
[2061] A system including a means for providing the generated content to a game creator.
[2062] (Claim 2)
[2063] and means for providing an interface for a generative artificial intelligence creator to register a prompt.
[2064] 10. The system of claim 1.
[2065] (Claim 3)
[2066] Based on the situation and character outline entered by the game creator,
[2067] and further including means for displaying the real-time generated content.
[2068] 10. The system of claim 1.
[2069] "Example 1"
[2070] (Claim 1)
[2071] A means for creators to register prompts about their drawing style;
[2072] A means for a game creator to input a summary of a situation or character based on the prompt;
[2073] A means for generating illustrations and music by a generating artificial intelligence based on the input information;
[2074] a means for storing the generated content in a database;
[2075] means for providing the generated content to a game creator;
[2076] A system that includes a means for game creators to review, modify, regenerate, and save generated content.
[2077] (Claim 2)
[2078] and means for providing an interface for a generative artificial intelligence creator to register a prompt.
[2079] 10. The system of claim 1.
[2080] (Claim 3)
[2081] Based on the situation and character outline entered by the game creator,
[2082] Further includes means for displaying real-time generated content and processing save requests.
[2083] 10. The system of claim 1.
[2084] "Application Example 1"
[2085] (Claim 1)
[2086] A means for creators to register prompts about their drawing style;
[2087] A means for a content creator to input a summary of a situation or character based on the prompt;
[2088] A means for generating illustrations, music, and videos by a generating artificial intelligence based on the input information;
[2089] a means for storing the generated content in a database;
[2090] The system includes means for providing the generated content to a content creator.
[2091] (Claim 2)
[2092] and means for providing an interface for a generative artificial intelligence creator to register a prompt.
[2093] 10. The system of claim 1.
[2094] (Claim 3)
[2095] Based on the situation and character outline entered by the content creator,
[2096] and further including means for displaying the real-time generated content.
[2097] 10. The system of claim 1.
[2098] "Example 2: Combining Emotion Engines"
[2099] (Claim 1)
[2100] a means for a generator creator to register instructions regarding his or her drawing style;
[2101] A means for the developer to input an outline of the situation and characters based on the instructions;
[2102] a generating device for generating video and audio based on the input information;
[2103] means for storing the generated content in a data storage device;
[2104] means for providing the generated content to a developer;
[2105] A means for acquiring user emotions using a sensing device and analyzing the emotions using an emotion engine;
[2106] The system includes means for adjusting the generated content based on the analysis results.
[2107] (Claim 2)
[2108] and means for providing an interface for a generator creator to register instructions.
[2109] 10. The system of claim 1.
[2110] (Claim 3)
[2111] Based on the situation and character outline entered by the developer,
[2112] Further includes means for displaying the generated content in real time.
[2113] 10. The system of claim 1.
[2114] "Application example 2 when combining emotion engines"
[2115] (Claim 1)
[2116] A means for creators to register prompts about their drawing style;
[2117] A means for a game creator to input a summary of a situation or character based on the prompt;
[2118] A means for generating illustrations and music by a generating artificial intelligence based on the input information;
[2119] a means for storing the generated content in a database;
[2120] means for providing the generated content to a game creator;
[2121] means for adjusting the generated content using an emotion engine that recognizes the emotion of a user;
[2122] A system including means for providing the tailored content to a user.
[2123] (Claim 2)
[2124] and means for providing an interface for a generative artificial intelligence creator to register a prompt.
[2125] 10. The system of claim 1.
[2126] (Claim 3)
[2127] Based on the situation and character outline entered by the game creator,
[2128] and further including means for displaying the real-time generated content.
[2129] 10. The system of claim 1. [Explanation of symbols]
[2130] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>
Claims
1. A means for creators to register prompts about their drawing style; A means for a game creator to input a summary of a situation or character based on the prompt; A means for generating illustrations and music by a generating artificial intelligence based on the input information; a means for storing the generated content in a database; A system including a means for providing the generated content to a game creator.
2. and means for providing an interface for a generative artificial intelligence creator to register a prompt. The system of claim 1 .
3. Based on the situation and character outline entered by the game creator, and further including means for displaying the real-time generated content. The system of claim 1 .
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A