System

Abstract

To provide a system.SOLUTION: A system comprises: means for generating a prompt text related to at least one of a specific state and an incident that a user desires and sets; means for generating a video based on the prompt text using the generated prompt text and a generative AI model; means for analyzing user's emotional state using an emotion engine; means for generating a virtual space based on the analyzed user's emotional state; means for synthesizing the generated virtual space with the video; and means for streaming the video with the synthesized virtual space.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the world of sports, there are many "what if" questions, and many viewers imagine what would have happened if that had happened. However, currently there is no way for users to realize and watch the results or scenes of their desired matches. [Means for solving the problem]

[0005] The system allows users to set their own desired match results and scenes, and generates a video with a different story from the original video based on those settings. This allows users to create their own original scenes, and even other leagues from a different world from reality can be provided through a virtual space. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

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

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a 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.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. 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."

[0014] [First embodiment]

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

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, 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.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (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.

[0021] 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.

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

[0023] 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.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output 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.

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

[0027] "Example 1"

[0028] This embodiment of the present invention provides an interface that allows users to set desired game results and scenes. This interface includes items that users can set, such as the participants in the game, the game results, and the results of important scenes. For example, in a soccer game, users can set the scorer, the timing of the goal, and the method of scoring (heading, shooting, etc.).

[0029] "Example 2"

[0030] We provide a method for generating a different story video from the original video based on the user's settings. This method appropriately combines scenes from the original video to recreate the scene set by the user. For example, if the user sets a goal scene, the system searches for a scoring scene by the same player in the original video and generates a new scene based on that scene.

[0031] "Example 3"

[0032] A means for distributing the generated video is provided. This means streams the generated video to users. A function is also provided that allows users to share the video they generated with other users. For example, a user can share the "what if" scene they generated on social media and discuss the scene with other users.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user accesses the system and opens the interface to set the participants in the match, the match results, the results of important scenes, etc.

[0036] Step 2: The user sets the desired outcome and scene on the interface. For example, for a soccer match, the user sets the scorer, the timing of the goal, and the method of scoring (heading, shooting, etc.).

[0037] Step 3: Once the configuration is complete, the user saves the configuration and the system receives the user's settings.

[0038] "Example 2"

[0039] Step 1: The system begins the process of generating a different story video from the original video based on the user's settings.

[0040] Step 2: The system searches the source footage for footage that corresponds to the scene set by the user. For example, if the user sets a goal, the system will search the source footage for a scoring scene by the same player.

[0041] Step 3: The system generates a new scene based on the footage it finds. The generated scene recreates the scene set by the user.

[0042] "Example 3"

[0043] Step 1: The system starts the process of distributing the generated video.

[0044] Step 2: Stream the system-generated video to the user.

[0045] Step 3: Provide a function that allows users to share the videos they create with other users. For example, users can share the "what if" scenes they create on social media and discuss them with other users.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0048] With conventional match result and scene generation systems, it was difficult for users to set the specific match results and scenes they wanted, and the generated results often did not meet users' expectations. Furthermore, it was difficult to provide the generated results to users in real time. This led to problems such as lower user satisfaction and a decrease in the frequency of system use.

[0049] 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.

[0050] In this invention, the server includes means for allowing a user to set desired game results and scenes, means for generating prompt sentences based on the settings, means for sending the generated prompt sentences to a generative AI model, means for receiving game results and scenes returned from the generative AI model, and means for displaying the received game results and scenes to the user. This allows a user to set specific game results and scenes and receive results based on the settings in real time.

[0051] "User" refers to an individual or organization that uses the System to set match results and scenes and receive the generated results.

[0052] "Game result" refers to the final score or outcome in a sport or competition.

[0053] A "scene" refers to a specific moment or event during a game or competition.

[0054] A "prompt sentence" refers to a text-based input sentence that provides instructions to a generative AI model.

[0055] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate match results or scenes based on user input.

[0056] "Server" refers to the computer system that receives input from users, processes data, and communicates with the generative AI model.

[0057] A "means" refers to a method or device used to achieve a particular purpose.

[0058] "Interface" refers to the screens and input forms that allow users to interact with the system.

[0059] "Database" refers to an information management system for storing user input data and generated results.

[0060] "Real-time" refers to a timeframe in which a user's input is responded to immediately.

[0061] This invention is a system that allows a user to set desired game results and scenes, and generates game results and scenes using a generative AI model based on those settings, and provides them to the user. Specific embodiments of this system are described below.

[0062] Hardware and software used

[0063] Hardware:

[0064] High-performance server (e.g. general-purpose server)

[0065] The device used by the user to access the site (e.g., personal computer, smartphone)

[0066] software:

[0067] Generative AI models (e.g., general-purpose generative AI models)

[0068] Web browser (e.g., general-purpose web browser)

[0069] Database management systems (e.g., general-purpose database management systems)

[0070] System processing flow

[0071] 1. User accesses the interface:

[0072] Users access the system's interface using a web browser, which provides input forms for setting match results and scenes.

[0073] 2. User enters match settings:

[0074] The user enters information about the participants in the match, the match results, and details of important scenes (such as the scorer, the timing of the goal, and the method of scoring) into an input form on the interface.

[0075] 3. The server receives the input data:

[0076] The server receives the data entered by the user and stores it in a database for further processing.

[0077] 4. The server generates a prompt:

[0078] The server generates a prompt to send to the generative AI model based on the data entered by the user. For example, if the user enters "Team A wins 2-1," the prompt will be "Generate the results of a soccer match. The participants in the match are Team A and Team B. The result of the match is that Team A wins 2-1."

[0079] 5. The server sends a prompt to the generative AI model:

[0080] The server sends the generated prompts to the generative AI model, which then instructs the model to generate game results and scenes.

[0081] 6. Generative AI models generate game results and scenes:

[0082] The generative AI model generates match results and scenes based on prompts received from the server. The model analyzes the input information and generates results that meet the user's wishes.

[0083] 7. The server receives the generated results:

[0084] The server receives the match results and scenes returned by the generative AI model, which are then formatted for display to the user.

[0085] 8. The server displays the results to the user:

[0086] The server sends the generated match results and scenes to the user's browser, where the user can view the results and change the settings as needed.

[0087] Examples of specific examples and prompts

[0088] Examples:

[0089] The user sets up "Team A" and "Team B" as participants in the match.

[0090] Set the result of the match as "Team A wins 2-1."

[0091] The key scenes are set as follows: "The scorers are Team A's Player X and Player Y, the timing of the goals is 20 minutes into the first half and 75 minutes into the second half, and the scoring methods are shots and headers."

[0092] Example prompt sentence:

[0093] Generate the results of a soccer match. The participants in the match are Team A and Team B. Team A wins 2-1. The scorers are Player X and Player Y of Team A. The goals are scored at the 20th minute of the first half and the 75th minute of the second half. The methods of scoring are shots and headers.

[0094] In this way, users can set specific match results or scenes and receive real-time results based on those settings.

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1:

[0097] The user accesses the interface.

[0098] A user accesses the system's interface using a web browser. As input, the user enters the system's URL into the browser. As output, the interface is displayed. In particular, the user opens a web browser such as GOOGLE CHROME® and enters the system's URL to access the interface.

[0099] Step 2:

[0100] The user enters the match settings.

[0101] The user enters the participants of the match, the match results, and details of important scenes (such as the scorers, the timing of the goals, and the method of scoring) into an input form on the interface. As input, the user enters detailed information about the match. As output, the entered data is displayed on the interface. In concrete terms, the user uses text boxes and drop-down menus to enter detailed information about the match.

[0102] Step 3:

[0103] The server receives the input data.

[0104] The server receives the data entered by the user and stores it in a database. As input, the match details entered by the user are sent to the server. As output, data stored in the database is generated. Specifically, the server receives an HTTP request and stores the data in a MySQL® database.

[0105] Step 4:

[0106] The server generates a prompt.

[0107] The server generates a prompt sentence to send to the generative AI model based on the data entered by the user. The match details stored in the database are used as input. The generated prompt sentence is obtained as output. Specifically, the server uses a Python script to generate the prompt sentence based on the data entered by the user.

[0108] Step 5:

[0109] The server sends a prompt to the generative AI model.

[0110] The server sends the generated prompt sentence to the generative AI model. The generated prompt sentence is used as input. The prompt sentence is sent to the generative AI model as output. Specifically, the server sends the prompt sentence to the generative AI model via an HTTP request.

[0111] Step 6:

[0112] Generative AI models generate match results and scenes.

[0113] The generative AI model generates match results and scenes based on prompts received from the server. The prompts are used as input. The generated match results and scenes are obtained as output. Specifically, the generative AI model analyzes the prompts and generates match results and scenes that meet the user's wishes.

[0114] Step 7:

[0115] The server receives the generated results.

[0116] The server receives the match results and scenes returned from the generative AI model. The output from the generative AI model is used as input. The received match results and scenes are obtained as output. Specifically, the server receives the JSON format data returned from the generative AI model and formats it into HTML.

[0117] Step 8:

[0118] The server displays the results to the user.

[0119] The server sends the generated match results and scenes to the user's browser. As input, the formatted match results and scenes are used. As output, the results are displayed in the user's browser. In concrete terms, the server sends the formatted data to the user's browser as an HTTP response, and the user sees the results on the interface.

[0120] (Application example 1)

[0121] Next, a description will be given of Application Example 1 of Embodiment 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."

[0122] Conventional sports game video distribution systems make it difficult for users to freely set specific game results or scenes they want and watch customized videos based on those settings. Furthermore, the lack of technology to generate videos in real time based on user-defined scenes hinders user satisfaction. Furthermore, there is a lack of a means to efficiently distribute the generated videos.

[0123] 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.

[0124] In this invention, the server includes means for setting the match results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating match highlight text using a generative AI model, and means for editing the video based on the generated text. This allows the user to freely set the specific match results and scenes desired, generate customized videos based on the settings in real time, and distribute them efficiently.

[0125] "User" refers to an individual or organization that uses the system to set match results and scenes.

[0126] "Game result" refers to the final outcome of a sports game, such as the score or victory or defeat.

[0127] A "scene" refers to a specific moment or event during a match.

[0128] "Setting" refers to the act of the user inputting the desired match results and scenes into the system.

[0129] "Original footage" refers to footage of an actual match.

[0130] "Another story video" refers to a new video that differs from the original footage and is generated based on the match results and scenes set by the user.

[0131] "Generative AI model" refers to an algorithm or program that uses artificial intelligence technology to generate text or video.

[0132] "Highlight text" refers to written descriptions of important scenes and events in a match.

[0133] "Video editing" refers to the act of processing and editing video based on the generated text.

[0134] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[0135] The system for implementing this invention allows users to set desired game results and scenes, and then generates and distributes customized videos based on those settings. A specific embodiment of this system is described below.

[0136] System Configuration

[0137] The system consists of the following main components:

[0138] 1. User device: A device that provides an interface for users to set game results and scenes. This includes smartphones, tablets, and PCs.

[0139] 2. Server: A central processing unit that receives user settings, generates highlight text using generative AI models, and edits and generates videos.

[0140] 3. Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate text based on game results and scenes set by the user.

[0141] 4. Video editing software: Software for editing videos based on the generated text, for example using libraries such as OpenCV (registered trademark).

[0142] 5. Distribution server: A server for distributing the generated video to users.

[0143] Processing flow

[0144] 1. User settings: The user inputs the desired match results and scenes from the user's device. For example, the user can set "Scorer: Tanaka, Score timing: 20 minutes into the first half, Score method: Heading."

[0145] 2. Prompt generation: The server generates a prompt based on the user's settings. For example, it generates a prompt such as, "Please describe the scene in a soccer game where Tanaka scores a header in the 20th minute of the first half."

[0146] 3. Highlight text generation: Using a generative AI model, highlight text is generated based on the prompt sentence.

[0147] 4. Video editing: Based on the generated highlight text, another story video is created from the original footage using video editing software.

[0148] 5. Video distribution: The generated video is provided to the user through a distribution server.

[0149] Specific examples

[0150] For example, if the user sets the scene where Tanaka scores with a header in the 20th minute of the first half, the following prompt will be generated:

[0151] Describe a scene in a soccer match where Tanaka scores a header in the 20th minute of the first half.

[0152] By inputting this prompt into a generative AI model, text for the desired game scene is generated, and a highlight video is created based on that text.

[0153] Hardware and software used

[0154] Generative AI model: GPT-3 (registered trademark) from OpenAI (registered trademark)

[0155] Video editing software: OpenCV (registered trademark)

[0156] User devices: smartphones, tablets, computers

[0157] Server: High-performance central processing unit (equipped with CPU and GPU)

[0158] In this way, users can freely set the specific match results or scenes they want, and customized videos based on those settings can be generated in real time and distributed efficiently.

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] The user uses the device to set the desired match results and scenes.

[0162] Input: Match results and scene setting information entered by the user into the device (e.g., "Scorer: Tanaka, Score timing: 20 minutes into the first half, Score method: Header").

[0163] Output: The configuration information is sent to the server.

[0164] Specific operation: The user inputs the match results and scenes through the terminal interface and sends the setting information to the server.

[0165] Step 2:

[0166] The server receives the user's configuration information and generates a prompt.

[0167] Input: Configuration information submitted by the user.

[0168] Output: The generated prompt sentence (e.g., "Please describe a scene in a soccer game where Tanaka scores a header in the 20th minute of the first half.").

[0169] Specific operation: The server analyzes the configuration information and generates a prompt sentence to input into the generative AI model.

[0170] Step 3:

[0171] The server uses a generative AI model to generate highlighted text based on the prompt.

[0172] Input: The generated prompt statement.

[0173] Output: The generated highlighted text.

[0174] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and obtains the highlighted text from the model.

[0175] Step 4:

[0176] The server generates another story video using video editing software based on the generated highlight text.

[0177] Input: The generated highlighted text.

[0178] Output: Generated Another Story video.

[0179] Specific operation: The server uses video editing software (e.g., OpenCV (registered trademark)) to generate another story video from the original video based on the highlight text.

[0180] Step 5:

[0181] The server provides the generated Another Story video to the user through a distribution server.

[0182] Input: Generated Another Story video.

[0183] Output: A video file that can be played on the user's device.

[0184] Specific operation: The server uploads the generated video to the distribution server so that the user can watch it on their device.

[0185] Example 2

[0186] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0187] With conventional video generation systems, it was difficult to generate another story video that reflected specific scenes or game results desired by the user. Furthermore, the process of extracting relevant scenes from the original video and generating a new video based on the user's settings was complicated and inefficient. Furthermore, there was a lack of a way to quickly provide the generated video to the user.

[0188] 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.

[0189] In this invention, the server includes means for setting the game results and scenes desired by the user, means for generating another story video that differs from the original video based on the settings, means for distributing the generated video, means for analyzing the user's setting conditions, means for searching the original video database and extracting relevant scenes, means for generating a new video using a generative AI model, and means for displaying the generated video to the user. This makes it possible to efficiently generate and quickly provide another story video that reflects the specific scenes and game results desired by the user.

[0190] "User" refers to an individual or organization that uses the system to set match results and scenes and generate another story video.

[0191] A "means for setting game results or scenes" is a device or software that provides an interface or functionality for a user to input or select a particular game result or scene desired.

[0192] "Another Story Video" is a new video generated according to the user's settings based on scenes extracted from the original video.

[0193] "Generating means" refers to a device or software that extracts relevant scenes from the source video based on the user's settings and creates a new video using a generative AI model.

[0194] "Means for providing distribution" refers to a device or software for transmitting the generated Another Story video to users and making it viewable.

[0195] "Means for analyzing" refers to a device or software that understands the settings entered or selected by the user and performs appropriate processing.

[0196] The "means for searching and extracting relevant scenes" refers to a device or software that searches the original video database to find and extract scenes that meet the user's set conditions.

[0197] A "generative AI model" is a model for generating new videos using artificial intelligence technology, including, for example, natural language processing and video generation technology.

[0198] "Displaying means" refers to a device or software for displaying the generated Another Story video on the user's terminal.

[0199] This invention relates to a system that allows a user to set a desired game result or scene, and based on that, generates a different story video from the original video, and distributes it. Specific embodiments of this system are described below.

[0200] First, the user inputs the conditions for the Another Story video they want to generate through the device interface. For example, they might input, "I want a video of Player A's scoring scenes." This input is done using the device's input form and selection menu.

[0201] Next, the device receives the user's input and sends the request to the server. The request includes the conditions set by the user. The server analyzes the received request and understands the conditions the user is looking for. For example, it analyzes the condition "collect scenes of player A scoring."

[0202] The server searches a database where the original video is stored to find scenes that match the conditions set by the user. This search uses video analysis software (e.g., OpenCV (registered trademark)). The server extracts relevant scenes from the search results. For example, it extracts all scenes in which player A scores.

[0203] The server then uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a new "Another Story" video based on the extracted scenes. This process also uses video editing software. The generative AI model combines scenes based on the user's settings to generate a new video.

[0204] The generated video is sent from the server to the device using a high-speed data transfer protocol (e.g. HTTP / 2). The device then displays the received video to the user. The user can then watch the generated Another Story video on the device screen.

[0205] For example, if a user requests "I want a video of player A scoring," the following prompt might be used:

[0206] "Generate a video of player A scoring."

[0207] In this way, different, alternative story videos are generated from the original footage based on user requests and quickly provided. This system allows users to efficiently generate and watch videos that reflect specific scenes or game results they desire.

[0208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0209] Step 1:

[0210] The user enters a request.

[0211] The user inputs the conditions for the Another Story video they want to generate through the device interface. For example, they might input, "I want a video of Player A's scoring scenes." The input conditions are saved in the device's input form.

[0212] Step 2:

[0213] The device sends a request to the server.

[0214] The terminal receives the user's input and sends the request to the server. The request includes the conditions set by the user. The input data is sent to the server as an HTTP request.

[0215] Step 3:

[0216] The server parses the request.

[0217] The server analyzes the received request and understands the conditions the user is looking for. For example, it analyzes the condition "collect scenes of player A scoring." The analysis results are stored in an internal data structure.

[0218] Step 4:

[0219] The server searches the original video database.

[0220] The server searches the database where the original video is stored to find scenes that match the conditions set by the user. This search is performed using video analysis software (e.g., OpenCV (registered trademark)). The input is the analysis results, and the output is a list of matching scenes.

[0221] Step 5:

[0222] The server extracts the relevant scenes.

[0223] The server extracts relevant scenes from the search results. For example, it extracts all scenes in which player A scores. The input is the search results, and the output is the data of the extracted scenes.

[0224] Step 6:

[0225] The server uses the generative AI model to generate new videos.

[0226] The server generates a new Another Story video using a generative AI model (e.g., GPT-4 (registered trademark)) based on the extracted scenes. This process also uses video editing software. The input is the extracted scene data, and the output is the generated video.

[0227] Step 7:

[0228] The video generated by the server is sent to the terminal.

[0229] The server sends the generated video to the device using a high-speed data transfer protocol (e.g., HTTP / 2). The input is the generated video, and the output is the data transfer to the device.

[0230] Step 8:

[0231] The terminal displays the generated video to the user.

[0232] The device displays the received video to the user, who can then watch the generated Another Story video on the device screen. The input is the video sent from the server, and the output is the user's viewing experience.

[0233] (Application example 2)

[0234] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0235] Conventional video generation systems have had difficulty extracting specific scenes desired by users from source video and generating them as new videos. Furthermore, they lacked a means to efficiently detect user-specified scenes, connect them, and generate new videos, making it impossible to provide videos customized to meet user needs. This resulted in lower user satisfaction and reduced value for content distribution services.

[0236] 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.

[0237] In this invention, the server includes means for setting the match results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for detecting scenes specified by the user from the original video, and means for generating a new video by linking the detected scenes. This makes it possible to efficiently extract specific scenes desired by the user and generate and distribute customized videos.

[0238] "User" means an individual or entity that uses the System to generate and view customized videos by setting specific match results or scenes.

[0239] "Game results" refers to the results of sports or competitions, such as scores or wins and losses.

[0240] A "scene" refers to a specific moment in a video or a portion of a continuous sequence of images.

[0241] "Setting" refers to the act of the user inputting the desired match results and scenes into the system.

[0242] "Original video" refers to original video data that has not been edited or processed.

[0243] "Another story video" refers to a new video generated from the original video based on the user's settings.

[0244] "Generation" refers to the process of creating new video from original footage.

[0245] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[0246] "Detection" refers to the process of finding the scene specified by the user from the original video.

[0247] "Concatenation" refers to the act of connecting detected scenes in order to compile them into a single video.

[0248] The system for implementing this invention allows users to set their desired game results and scenes, generates another story video from the original video based on those settings, and distributes the generated video. Specific embodiments are described below.

[0249] System configuration

[0250] The system consists of the following main components:

[0251] 1. User device: A device such as a smartphone or tablet that the user uses to set up a scene.

[0252] 2. Server: A central processing unit for video generation and distribution.

[0253] 3. Database: Storage for saving original footage and generated videos.

[0254] Hardware and software used

[0255] Hardware: Smartphones, tablets, servers, storage devices

[0256] Software: Python, OpenCV (registered trademark) (image processing library), MoviePy (registered trademark) (video editing library)

[0257] Processing flow

[0258] 1. User device: The user uses a smartphone or tablet to set the desired game results and scenes, for example, by entering a prompt such as "Please create a highlight video of a specific player's scoring scenes."

[0259] 2. Server: Based on the user's settings, the server detects the specified scenes from the original video. It uses OpenCV (registered trademark) to analyze the video frame by frame and finds the scenes specified by the user.

[0260] 3. Server: Concatenate the detected scenes to create a new video. Using MoviePy (registered trademark), the detected scenes are connected in order to create a single video.

[0261] 4. Server: The generated Another Story video is stored in a database and distributed to users.

[0262] Specific examples

[0263] If a user wants to create a highlight video of a specific soccer player's goals, they can do the following:

[0264] 1. The user opens the application on their smartphone and enters the command, "Please create a highlight video of a specific player's scoring moments."

[0265] 2. The server analyzes the original video and detects the scoring scenes of the specified player.

[0266] 3. The detected scenes are concatenated to generate a new highlight video.

[0267] 4. Deliver the generated video to the user.

[0268] Prompt Sentence Examples

[0269] "Create a highlight video from a soccer match that includes only the scoring scenes of a specific player."

[0270] In this way, users can easily create and watch customized videos containing their desired scenes.

[0271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0272] Step 1:

[0273] User device: The user uses a smartphone or tablet to set the desired game results and scenes. Specifically, the user opens the application and enters a prompt such as, "Please create a highlight video of a specific player's scoring scenes."

[0274] Input: User prompt

[0275] Output: User settings information

[0276] Step 2:

[0277] Server: Receives the user's setting information and retrieves the original video from the database.

[0278] Input: User settings, original video database

[0279] Output: Original video data

[0280] Step 3:

[0281] Server: Analyzes the original video frame by frame using OpenCV (registered trademark) and detects scenes specified by the user. Specifically, it calculates the average color and feature values ​​of the frames and finds scenes that match the conditions specified by the user.

[0282] Input: Original video data, user setting information

[0283] Output: A list of detected scenes

[0284] Step 4:

[0285] Server: Using MoviePy (registered trademark), the detected scenes are concatenated in order to generate a new video. Specifically, the detected scenes are read as clips, concatenated, and written as a single video file.

[0286] Input: A list of detected scenes

[0287] Output: Generated Another Story video

[0288] Step 5:

[0289] Server: The server stores the generated Another Story video in a database and delivers it to users. Specifically, it stores the generated video file in storage and notifies the user of its URL.

[0290] Input: Generated Another Story video

[0291] Output: Delivery URL to user

[0292] In this way, users can easily create and watch customized videos containing their desired scenes.

[0293] Example 3

[0294] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] While conventional video generation systems allow users to set their desired scenes and game results, they lack the ability to share the generated videos with other users. Furthermore, there are limited means for streaming the generated videos in real time, often limiting the user experience. Furthermore, the process of generating videos using generative AI models is complex, creating a need for an easy-to-use interface.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0297] In this invention, the server includes means for allowing a user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating a video based on a prompt sentence using a generative AI model, means for streaming the generated video, and means for the user to share the generated video with other users. This allows a user to easily set desired scenes and watch and share the generated video in real time.

[0298] "User" refers to any individual or entity that uses the System to generate, view, or share videos.

[0299] "Means for setting game outcomes or scenes" refers to functionality that provides an interface for users to input or select specific scenes or results they desire.

[0300] "Means for generating another story video" refers to the function that generates a video with a new story different from the original video based on scenes and results set by the user.

[0301] "Means for distributing and providing the generated video" refers to the technology and process for distributing the generated video to users.

[0302] "Generative AI model" refers to an artificial intelligence model that generates videos based on prompts entered by users.

[0303] "Prompt" refers to a textual instruction that a user inputs to a generative AI model.

[0304] "Means for generating video" refers to the technology or process for generating video based on prompt text using a generative AI model.

[0305] "Means for streaming" refers to the technology and processes used to deliver generated video to users in real time.

[0306] "Means for sharing videos" refers to link generation and sharing functions that allow users to share videos they generate with other users.

[0307] This invention is a system that allows users to set desired scenes and game results, and streams and shares videos generated based on those settings. Specific embodiments of this system are described below.

[0308] System configuration

[0309] server

[0310] The server generates a video based on the prompt entered by the user using a generative AI model. Generative AI models include, for example, natural language processing models and image generation models. Specifically, models such as OpenAI's GPT-4 and DALL-E can be used.

[0311] The server converts the generated video into a suitable format for streaming. For example, it converts the video to MP4 format and uploads it to the streaming server. Once the upload is complete, a streaming URL is generated.

[0312] In addition, the server generates a link for users to share their videos with other users. This link can be shared via social media, email, etc.

[0313] Terminal

[0314] The terminal is responsible for sending the prompt text entered by the user to the server. When the user enters the prompt text through the terminal interface and presses the send button, the data is sent to the server. The terminal application generates an HTTP request and sends the data, including the prompt text, to the server.

[0315] The device also receives and plays streaming video from the server, allowing users to view the generated video on the device screen.

[0316] The device also provides an interface for users to share the videos they generate with other users. Users can share links to videos generated using the device via social media or email.

[0317] User

[0318] The user uses a device to create a prompt to be input to the generative AI model. For example, they can enter a prompt such as "What if dinosaurs were alive today?" When the user enters the prompt and presses the send button, the data is sent to the server.

[0319] The user watches the generated video streamed from the server. For example, if the user inputs the prompt "What if dinosaurs were alive today?", the generated video will include a scene of dinosaurs walking around a modern city.

[0320] Furthermore, users can share the generated video with other users. For example, users can share the link of the generated video on social media and discuss the scene with other users.

[0321] Specific examples

[0322] Prompt Sentence Examples

[0323] "If dinosaurs were alive today"

[0324] Operation flow

[0325] 1. The user uses the terminal to enter the prompt sentence "What if dinosaurs were alive today?" and presses the send button.

[0326] 2. The terminal sends the prompt text to the server.

[0327] 3. The server uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a video based on the prompt.

[0328] 4. The server converts the generated video into a format suitable for streaming and uploads it to the streaming server.

[0329] 5. The server provides the generated streaming URL to the user, allowing the user to watch the video.

[0330] 6. The user accesses the streaming URL through the device's browser or a dedicated application and watches the video.

[0331] 7. The user shares the link of the generated video via SNS or email, and discusses the scene with other users. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0332] Step 1:

[0333] The user enters a prompt statement.

[0334] The user inputs a prompt that describes the content of the video they want to generate through the device interface. For example, they input a prompt such as "What if dinosaurs were alive today?" The input prompt is temporarily stored in the device's memory.

[0335] Step 2:

[0336] The terminal sends the prompt to the server.

[0337] The terminal sends the prompt text entered by the user to the server. Specifically, the terminal application generates an HTTP request and sends data including the prompt text to the server's API endpoint. The input is the prompt text, and the output is a transmission completion notification to the server.

[0338] Step 3:

[0339] The server generates the video using a generative AI model.

[0340] The server inputs the received prompt sentence into a generative AI model. The generative AI model (e.g., GPT-4 (registered trademark) or DALL-E) analyzes the prompt sentence and generates appropriate scenes and characters. The input is the prompt sentence, and the output is the generated video data. Specifically, the server analyzes the prompt sentence, determines the components of the scene, and generates a video based on them.

[0341] Step 4:

[0342] The server prepares the generated video for streaming.

[0343] The server converts the generated video into a format appropriate for streaming. For example, it converts the video into MP4 format and uploads it to the streaming server. The input is the generated video data and the output is a streaming URL. Specifically, the server encodes the video and uploads it to the streaming server.

[0344] Step 5:

[0345] The server streams the video.

[0346] The server distributes the generated video to the user through the streaming server. The user can watch the video in real time through the browser on their device or a dedicated application. The input is a streaming URL, and the output is the video played on the user's device. Specifically, the server provides the streaming URL to the user, and the user accesses that URL.

[0347] Step 6:

[0348] A user watches a video.

[0349] The user watches the generated video using their device. For example, if the user inputs the prompt "What if dinosaurs were alive today?", the generated video will include a scene of dinosaurs walking through a modern city. The input is a streaming URL, and the output is the video to be watched. Specifically, the user opens a browser or dedicated application on their device and accesses the provided streaming URL.

[0350] Step 7:

[0351] A user shares a video.

[0352] Users can share the generated video with other users. Specifically, the server provides a link to the generated video, and the user shares the link via social media or email. The input is the streaming URL, and the output is the shared link. Specifically, the user copies the link of the generated video and shares it via social media or email.

[0353] (Application example 3)

[0354] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0355] While conventional video generation systems allow users to set their desired scenes and game results, they lack the means to share and discuss the generated videos with other users. Furthermore, the content of the generated videos is limited, preventing users from fully utilizing their creativity. Furthermore, there is no way to stream the generated videos in real time, limiting the user experience.

[0356] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0357] In this invention, the server includes means for allowing a user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating video content based on prompt sentences using a generative AI model, means for streaming the generated video, and means for sharing the generated video with other users. This allows a user to freely set desired scenes, stream the generated video in real time, and share and discuss it with other users.

[0358] "User" means an individual or organization that uses the system to generate and distribute videos.

[0359] "Game results" refers to the final score or outcome in a sport, game, or other competition.

[0360] A "scene" is a part of a video or movie that shows a specific situation or situation.

[0361] "Setting" is the act of the user inputting desired conditions and parameters into the system.

[0362] "Original video" refers to the original video material that is the basis for generating the video.

[0363] "Another story video" is a newly generated video with a different storyline from the original video.

[0364] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate content based on user input.

[0365] A "prompt" is a sentence of instructions or questions that a user inputs to a generative AI model.

[0366] "Streaming distribution" is a technology that distributes generated video in real time over the Internet.

[0367] "Sharing" refers to the act of showing the created video to other users via the Internet.

[0368] The system for implementing this invention allows users to set their desired scenes and match results, generate video content based on prompts using a generative AI model, and stream the generated video for sharing with other users.

[0369] System Configuration

[0370] The system consists of the following main components:

[0371] 1. User terminal: A device used by a user to access the system, such as a smartphone or computer.

[0372] 2. Server: A central server for providing video generation, streaming, and sharing functions.

[0373] 3. Generative AI model: An artificial intelligence model that generates video content based on user prompts.

[0374] Operating procedure

[0375] 1. User terminal: The user accesses the system using a terminal and sets the desired scene and game result. For example, the user enters a prompt sentence such as "What if dinosaurs appeared in the modern world?"

[0376] 2. Server: The server sends the prompt received from the user to the generative AI model to generate the video content, which is then stored on the server.

[0377] 3. Streaming: The server streams the generated video in real time, allowing users to watch the video through their devices.

[0378] 4. Sharing function: Users can share the videos they create with other users on social media, etc. Other users can view the shared videos and comment and discuss them.

[0379] Hardware and software used

[0380] Hardware: smartphones, PCs, servers

[0381] Software: Python®, Streamlit®, OpenAI® API, MoviePy®

[0382] Specific examples

[0383] If the user wants to generate a scene in which dinosaurs appear in the present day, they would enter the following prompt:

[0384] Example prompt sentence:

[0385] If dinosaurs were to appear in the modern world, what kind of scene would unfold?

[0386] By entering this prompt, the generative AI model will generate the scene and stream it as a video, which users can then share on social media and discuss with other users.

[0387] In this way, users can freely set up the scenes they want, stream the generated videos in real time, and share and discuss them with other users.

[0388] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0389] Step 1:

[0390] The user accesses the system using a terminal and sets the desired scene and game result. Specifically, the user inputs a prompt sentence. For example, the user inputs a prompt sentence such as "What if dinosaurs appeared in the present day?" The input data is the prompt sentence, which becomes the input for the next step.

[0391] Step 2:

[0392] The terminal sends the input prompt to the server, which receives the prompt and passes it to the generative AI model. The input data is the prompt, and the output data is the prompt passed to the generative AI model.

[0393] Step 3:

[0394] The server uses a generative AI model to generate video content based on the prompt. Specifically, the generative AI model analyzes the prompt and generates corresponding video scenes. The input data is the prompt, and the output data is the generated video content.

[0395] Step 4:

[0396] The server saves the generated video content as a video file. Specifically, the generated video content is converted into a video file format and saved within the server. The input data is the generated video content, and the output data is the saved video file.

[0397] Step 5:

[0398] The server streams the stored video files in real time. Specifically, the streaming server delivers the video files to the user's device. The input data is the stored video file, and the output data is the video to be streamed.

[0399] Step 6:

[0400] Users watch the streamed video through their devices. Specifically, they play the video using their device's browser or a dedicated app. The input data is the streamed video, and the output data is the video the user watches.

[0401] Step 7:

[0402] Users can share the generated video with other users on social media platforms. Specifically, they click the share button to post a link to the video on the social media platform. The input data is the link to the generated video, and the output data is the video link shared on the social media platform.

[0403] Step 8:

[0404] Other users can watch the video through the shared video link and comment and discuss. Specifically, they click on the video link on the SNS to watch the video and post their opinions in the comments section. The input data is the video link shared on the SNS, and the output data is the comments and discussions from other users.

[0405] 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.

[0406] "Example 1"

[0407] One embodiment of the present invention provides a system including an emotion engine that recognizes a user's emotions. This system includes a means for setting a desired match result or scene for the user, a means for generating a video with a different story from the original video based on the setting, and a means for distributing the generated video. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, text input, etc., and generates a video based on the emotion. For example, if the user expresses joy, a joyful scene is generated to match that emotion.

[0408] "Example 2"

[0409] Another embodiment of the present invention provides a system in which an emotion engine generates a user's own original scene. This system allows the system to generate an original scene based on the user's emotion. For example, if the user expresses sadness, a sad scene is generated to match the emotion. In this way, various scenes can be generated according to the user's emotion.

[0410] "Example 3"

[0411] As a further embodiment of the present invention, a system is provided in which an emotion engine provides a different league or the like in a virtual space that is different from reality. This system makes it possible to provide a different league or the like in the virtual space based on the user's emotions. For example, if the user is expressing excitement, the system provides an exciting different league that matches that emotion. In this way, it is possible to provide various virtual spaces according to the user's emotions.

[0412] The processing flow of each embodiment will be described below.

[0413] "Example 1"

[0414] Step 1: The user accesses the system and sets the match results and scenes.

[0415] Step 2: The emotion engine recognizes emotions from the user's facial expressions, tone of voice, text input, etc.

[0416] Step 3: Based on the recognized emotions, another story video is generated that is different from the original video.

[0417] Step 4: The generated video is distributed to users.

[0418] "Example 2"

[0419] Step 1: The user accesses the system and sets the match results and scenes.

[0420] Step 2: The emotion engine recognizes the user's emotion.

[0421] Step 3: Generate your own original scene based on the recognized emotions.

[0422] Step 4: The generated original scene is distributed to users.

[0423] "Example 3"

[0424] Step 1: The user accesses the system and sets the match results and scenes.

[0425] Step 2: The emotion engine recognizes the user's emotion.

[0426] Step 3: Based on the recognized emotions, a different league or world from reality is provided through a virtual space.

[0427] Step 4: The virtual space provided is distributed to users.

[0428] Example 1

[0429] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0430] Conventional systems allow users to set their desired match results and scenes, but they have the problem of not being able to generate videos that reflect the user's emotions. Also, if the generated video does not match the user's emotions, user satisfaction may decrease. Furthermore, if the generated video is not delivered smoothly, the user experience may be impaired.

[0431] 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.

[0432] In this invention, the server includes a means for allowing the user to set desired game results and scenes, a means for generating a story video different from the original video based on the settings, a means for distributing the generated video, a means for recognizing the user's emotions, a means for generating a video based on the recognized emotions, and a means for generating a video by inputting a prompt sentence using a generative AI model. This allows for the generation of videos that reflect the user's desired game results and scenes and are based on the user's emotions. Furthermore, the smooth distribution of the generated videos improves the user experience.

[0433] "User" means an individual or organization that uses the system to set match results and scenes and view the generated videos.

[0434] "Game result" refers to the final score or outcome of a sport or competition.

[0435] A "scene" refers to a specific moment or event during a game or competition.

[0436] "Means for setting" refers to the interface or tool that allows the user to input or select the desired match results or scenes.

[0437] "Original footage" refers to footage of actual matches or competitions.

[0438] "Another Story Video" refers to a new video with different content from the original video based on the user's settings.

[0439] "Means of generation" refers to the technology and algorithms used to create new videos based on user settings.

[0440] "Means of distribution" refers to the technology and methods for transmitting the generated video to the user's device.

[0441] "Means of recognizing emotions" refers to technologies and algorithms that analyze emotions from users' facial expressions, tone of voice, text input, etc.

[0442] A "generative AI model" refers to a model that uses artificial intelligence to generate videos based on user settings and emotions.

[0443] A "prompt sentence" is an instruction sentence that is input into a generative AI model and is used to specifically specify the content of the video to be generated.

[0444] This invention is a system that allows users to set their desired game results and scenes, generate a video with a different story from the original video based on the settings, and distribute the generated video. This system includes a function to recognize the user's emotions and generate a video based on those emotions.

[0445] System configuration

[0446] The system consists of the following main components:

[0447] 1. User Interface: An interface for users to set their desired match results and scenes. This can be implemented as a web application or a mobile application.

[0448] 2. Server: Receives user settings, recognizes user emotions using an emotion engine, and generates another story video using a generative AI model.

[0449] 3. Emotion engine: Software that analyzes emotions from the user's facial expressions, tone of voice, text input, etc.

[0450] 4. Generative AI model: An artificial intelligence model that generates videos by inputting prompt sentences based on the user's settings and recognized emotional information.

[0451] 5. Delivery system: Technology for delivering the generated video to the user's device.

[0452] How it works

[0453] The user sets the desired game result or scene through the provided interface. For example, if the user sets a scene in which "Player A scores with a header," the user inputs that information into the interface.

[0454] The server receives the user's settings and stores them in a database. It then activates the emotion engine and analyzes the user's facial expressions, tone of voice, and text input to recognize their emotions. For example, if the user expresses joy, that information is recognized by the emotion engine.

[0455] Next, the server inputs a prompt sentence into the generative AI model. An example of a prompt sentence is, "Generate a scene in which player A scores a header in a soccer game. The user expresses joy." The generative AI model generates another story video based on this prompt sentence.

[0456] The generated video is then distributed to the user's device via a distribution system, allowing the user to watch the video and enjoy a video that reflects the desired match results or scenes.

[0457] Specific examples

[0458] For example, if a user wants to see a scene in which a specific player scores a header in a soccer game, the user can select "Player A scores a header" through the interface. The emotion engine will recognize the user's emotion of joy and generate a video based on that emotion.

[0459] An example of a prompt to input to a generative AI model is as follows:

[0460] "Generate a scene in which Player A scores a header in a soccer match. The user shows the emotion of joy."

[0461] By inputting this prompt into a generative AI model, a video based on the user's wishes and emotions is generated. The generated video is then delivered to the user's device via a distribution system, where the user can watch it.

[0462] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0463] Step 1:

[0464] The user sets the match results and scenes.

[0465] The user inputs the desired game result and scene through the provided interface. For example, they can set a scene in which "Player A scores with a header." The input data includes detailed information such as the participants in the game, the scorer, the timing of the goal, and the method of scoring. This allows the user to specifically set the game result and scene they want.

[0466] Step 2:

[0467] The server receives the user's settings.

[0468] The server receives the match results and scene setting information entered by the user through the interface. The received data is stored in a database. The input data is the user's setting information, and the output data is the setting information stored in the database. In this way, the user's setting information is managed within the system.

[0469] Step 3:

[0470] The server uses an emotion engine to recognize the user's emotion.

[0471] The server activates an emotion engine and recognizes emotions by analyzing the user's facial expressions, tone of voice, text input, etc. The input data is the user's facial expression data, voice data, and text data, and the output data is the recognized emotion information. For example, if the user expresses joy, that information is recognized by the emotion engine. This allows the user's emotion to be reflected in the system.

[0472] Step 4:

[0473] The server generates another story video using the generative AI model.

[0474] The server inputs a prompt sentence into the generative AI model based on the user's settings and the recognized emotion information. An example of a prompt sentence is, "Generate a scene in which player A scores a header in a soccer game. The user expresses joy." The input data is the prompt sentence, and the output data is the generated another story video. The generative AI model generates a video based on this prompt sentence. This generates a video based on the user's wishes and emotions.

[0475] Step 5:

[0476] The video generated by the server is delivered to the user's device.

[0477] The server distributes the generated "Another Story" video to the user's device. Distribution is achieved using streaming technology or by providing a download link. The input data is the generated video, and the output data is the video distributed to the user's device. This allows the user to watch a video that reflects the desired match results or scenes.

[0478] Step 6:

[0479] The user watches the video generated on the device.

[0480] Users watch the streamed video through their devices. The input data is the streamed video, and the output data is the user's viewing experience. This allows users to enjoy videos that reflect the game results and scenes they desire.

[0481] (Application example 1)

[0482] Next, a description will be given of Application Example 1 of Embodiment 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."

[0483] Conventional sports video distribution systems have made it difficult for users to freely set their desired game results and scenes and generate custom videos based on those settings. Furthermore, they are unable to generate videos that reflect the user's emotions, making it difficult to increase user satisfaction. Furthermore, there has been a lack of systems that can be easily used on mobile devices such as smartphones.

[0484] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for setting the game results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means including an emotion engine that recognizes the user's emotions, means for generating video based on the emotions, and means including an application to be installed on a smartphone. This enables the user to freely set the game results and scenes desired and easily generate and view custom videos based on the settings and emotions on their smartphone.

[0485] "User" refers to an individual who uses the system to set match results and scenes and watch the generated videos.

[0486] "Game result" refers to the final score or outcome of a sports game.

[0487] A "moment" refers to a specific moment or event during a match, such as a goal or a penalty.

[0488] "Means for setting" refers to an interface that allows a user to input or select the desired match results or scenes.

[0489] "Another story video" refers to a new video generated based on the user's settings that differs from the original match footage.

[0490] "Means of generation" refers to the technology and algorithms used to create Another Story videos based on user settings.

[0491] "Means of distribution" refers to the technology and services used to deliver the generated video to users.

[0492] An "emotion engine" refers to software or hardware that recognizes emotions from a user's facial expressions, tone of voice, text input, etc.

[0493] "Means for generating videos based on emotions" refers to technology that adjusts and generates video content according to the recognized emotions of a user.

[0494] "Application installed on a smartphone" refers to software that runs on a smartphone and allows users to set match results and scenes and view the generated videos.

[0495] An embodiment of the present invention will be described.

[0496] First, the user launches the application installed on their smartphone. This application provides an interface for the user to set the desired match results and scenes. The user inputs or selects the participants in the match, the match results, and important scenes (e.g., goals and penalties).

[0497] Next, the application uses the smartphone's camera and microphone to recognize the user's emotions. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, and text input. This emotion engine uses software called EmotionEngine (registered trademark), for example.

[0498] The server generates another story video based on the user's settings and the recognized emotions. The technology and algorithm for video generation uses a module called VideoGenerator (registered trademark). This module creates a new video that is different from the original video based on the match results and scenes set by the user.

[0499] The generated video is delivered from the server to the user's smartphone, where the user can watch the generated video using a module called VideoPlayer (registered trademark).

[0500] As a specific example, if a user selects "Team A wins the match" and expresses joy, VideoGenerator (registered trademark) will generate a highlight video that highlights the scenes where Team A wins. This video will be delivered to the user's smartphone and played on VideoPlayer (registered trademark).

[0501] An example of a prompt for a generative AI model is:

[0502] Generate a custom sports highlight video based on your emotions by setting the desired game results and scenes. User settings include:

[0503] Team 1: Team A

[0504] Team 2: Team B

[0505] Desired outcome: Team A wins

[0506] Key moments: goals, penalties, free kicks

[0507] The user's emotion is "joy." Generate a custom highlight video based on this setting and emotion.

[0508] In this way, users can freely set their desired match results and scenes, and easily generate and watch custom videos based on those settings and emotions on their smartphones.

[0509] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0510] Step 1:

[0511] A user launches an application installed on a smartphone. The application provides an interface for the user to set desired match results and scenes. The user inputs or selects the participants in the match, the match results, and key scenes. The input data includes the team name, desired results, and key scenes. The output is the user's setting information.

[0512] Step 2:

[0513] The device uses the smartphone's camera and microphone to capture the user's facial expressions and tone of voice. The emotion engine receives this data as input and recognizes the user's emotions. The input data includes facial image data and voice data. The output is the recognized emotion information.

[0514] Step 3:

[0515] The server receives the user's settings and the recognized emotion information and generates another story video. The technology and algorithm for video generation uses a module called VideoGenerator (registered trademark). The input data includes the user's settings and emotion information. The output is the generated custom video data.

[0516] Step 4:

[0517] The server distributes the generated custom video data to the user's smartphone. The distribution method uses data transfer via the Internet. The input data includes the generated custom video data. The output is the video data sent to the user's smartphone.

[0518] Step 5:

[0519] The terminal uses a module called VideoPlayer (registered trademark) on the smartphone to play the generated custom video. The user can watch the video on the smartphone screen. The input data includes the delivered custom video data. The output is the video played for the user to watch.

[0520] In this way, users can freely set their desired match results and scenes, and easily generate and watch custom videos based on those settings and emotions on their smartphones.

[0521] Example 2

[0522] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0523] Conventional video generation systems have had difficulty generating original videos based on specific scenes or emotions desired by users. They also lacked a means to extract specific scenes from the original video and generate a new, alternate story video based on the user's settings. Furthermore, there was also a lack of a means to quickly and efficiently provide the generated video to users.

[0524] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting setting information based on scenes and emotions desired by the user, a means for receiving the setting information and analyzing the original video data to extract necessary scenes, a means for generating a new another story video by combining the extracted scenes, and a means for transmitting the generated video to the user's terminal. This makes it possible to generate an original video based on specific scenes and emotions desired by the user and provide it quickly and efficiently.

[0525] A "user" is an individual or group that uses the system to generate videos based on specific scenes or emotions.

[0526] "Setting information" is data that includes information about the scene and emotion desired by the user.

[0527] "Original video data" refers to a video file that is the basis for extracting a scene that the user desires.

[0528] "Analysis" is the process of identifying and extracting specific scenes and elements from the original video data.

[0529] A "scene" is a specific moment in a video or a portion of a continuous video.

[0530] "Another story video" is a new video generated by combining scenes extracted from the original video data.

[0531] "Emotion data" is information that indicates the user's emotional state, and is data obtained from user input or biometric sensors.

[0532] An "original scene" is a scene newly generated based on the user's emotional data.

[0533] "Terminal" means an electronic device that a user uses to access the system.

[0534] "Sending" is the process of transferring the generated video to the user's device.

[0535] This invention is a system that generates a new another story video from an original video based on a user's desired scenes and emotions, and provides the video to the user. A specific embodiment of this system will be described below.

[0536] System Overview

[0537] This system involves a series of processes: the user inputs setting information based on the scenes and emotions they desire, analyzes the original video data based on that setting information to extract the necessary scenes, combines the extracted scenes to generate a new, alternate story video, and sends the generated video to the user's device.

[0538] Hardware and software used

[0539] Server: A computer system with high-performance computing capabilities that processes video analysis and video generation.

[0540] Device: An electronic device used by a user, such as a personal computer, smartphone, or tablet.

[0541] Video analysis software: Uses libraries such as OpenCV (registered trademark) to analyze and extract specific scenes from the original video data.

[0542] Video editing software: Use tools such as FFmpeg® to combine the extracted scenes to generate a new video.

[0543] Generative AI models: Generative AI models such as GPT-4 are used to generate original scenes based on user emotion data.

[0544] Program processing

[0545] The server receives configuration information from the user, including information about specific scenes and emotions. The server loads the original video data and begins analyzing the scenes using video analysis software (e.g., OpenCV). Specifically, it performs facial recognition and motion analysis to identify scenes associated with specific players and emotions within the video.

[0546] The server then extracts the necessary scenes based on the analysis results. For example, to extract a scene in which a specific player scores, the server extracts the scene containing the moment that player scores from the original video. When using the emotion engine, the server selects the appropriate scene based on the user's emotional data.

[0547] The server then combines the extracted scenes to create a new, alternate story video, using video editing software to adjust the sequence of the scenes and add transitions and effects as needed.

[0548] The generated video is sent from the server to the user's device using streaming technology or file transfer protocols (e.g., HTTP, FTP). The user can then watch the video sent to their device.

[0549] Examples of specific examples and prompts

[0550] As a concrete example, consider the case where a user requests a specific soccer player to score a goal. The user requests, "I want a new video to be created by collecting the goal scenes of a specific player." The server extracts the goal scenes of that player from the original video and generates a new video using video editing software.

[0551] When using the emotion engine, the user inputs, "I'm feeling sad, so I want a sad scene generated." The server analyzes the user's emotion data and generates a sad scene using GPT-4 (registered trademark).

[0552] Example prompt sentence:

[0553] "I want you to create a new video by collecting scoring scenes of a specific soccer player."

[0554] "I'm feeling sad, so I want a sad scene to be generated."

[0555] In this way, a system is realized in which the server, terminals, and users work together to generate another story video.

[0556] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0557] Step 1:

[0558] The user enters the configuration information.

[0559] The user inputs setting information about specific scenes and emotions through the system interface. For example, they input prompts such as "I want to collect scenes where a specific soccer player scores" or "I'm in a sad mood, so I want to generate sad scenes." The input setting information is then sent to the server.

[0560] Step 2:

[0561] The server receives the setting information and analyzes the original video data.

[0562] The server receives the configuration information sent by the user. The server then loads the original video data and begins analyzing the scenes using video analysis software (e.g., OpenCV®). Specifically, it performs facial recognition and motion analysis to identify scenes related to specific players or emotions within the video. The input is the original video data and the configuration information, and the output is the analysis results.

[0563] Step 3:

[0564] The server extracts and combines the necessary scenes.

[0565] The server extracts the necessary scenes based on the analysis results. For example, to extract a scene in which a specific player scores, the server cuts out the scene containing the moment that player scores from the original video. When using an emotion engine, the server selects the appropriate scene based on the user's emotion data. The input is the analysis results, and the output is the extracted scene.

[0566] Step 4:

[0567] The server generates a new Another Story video.

[0568] The server then combines the extracted scenes to generate a new, "Another Story" video. This process uses video editing software, which adjusts the order of the scenes and adds transitions and effects as needed. The input is the extracted scenes, and the output is the generated video.

[0569] Step 5:

[0570] The server sends the generated video to the user's device.

[0571] The server sends the generated Another Story video to the user's device using streaming technology or file transfer protocols (e.g., HTTP, FTP). The input is the generated video, and the output is the video sent to the user's device.

[0572] Step 6:

[0573] The user watches the generated video.

[0574] The user watches the video sent to the device. The user can enjoy the other story video generated by the system. The input is the video sent to the user's device, and the output is the video being watched.

[0575] In this way, the system generates a new another story video from the original video based on the user's settings and provides it to the user.

[0576] (Application example 2)

[0577] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0578] Conventional video generation systems allow users to set their desired scenes and match results, but they are unable to select scenes based on the user's emotions and generate new, alternate story videos. Furthermore, they lack a way to preview the generated videos in real time and increase user satisfaction. This limits the user's viewing experience and makes it difficult to customize the experience to meet individual needs.

[0579] 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.

[0580] In this invention, the server includes means for allowing the user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for recognizing the user's emotions, means for selecting scenes based on the recognized emotions, means for generating a new video by combining the selected scenes, and means for previewing the generated video in real time. This makes it possible to generate a new another story video according to the user's emotions and settings, allowing for an individually customized viewing experience.

[0581] "User" refers to any individual or entity that uses the System.

[0582] "Game results" refers to the final score or results in a sport, game, or other competition.

[0583] A "scene" refers to an event or situation at a specific time in a video or movie.

[0584] "Configuration" refers to the act of a user inputting desired conditions and requirements into the system.

[0585] "Original video" refers to the original video data before any editing or processing has been done.

[0586] "Another story video" refers to a video with a new story that is created based on the original video.

[0587] "Distribution" refers to the act of providing the generated video to users via communication means such as the Internet.

[0588] "Emotion" refers to the user's psychological state or mood.

[0589] "Means for recognizing emotions" refers to technology that analyzes and recognizes emotions from the user's facial expressions, voice, etc.

[0590] "Scene selection means" refers to technology that selects appropriate scenes based on the user's settings and emotions.

[0591] "Means for combining scenes to generate new videos" refers to the technology for combining selected scenes to create new videos.

[0592] "Means for previewing in real time" refers to technology that allows users to instantly view and check the generated video.

[0593] As an embodiment of the present invention, we will explain the system called Emotion-Driven Story Creator (registered trademark) as an example. This system generates new another story video based on the user's emotions and settings, and allows them to preview it in real time.

[0594] The server uses the following hardware and software:

[0595] Smartphone camera

[0596] Head-mounted display sensors

[0597] OpenCV (registered trademark) (image processing library)

[0598] EmotionRecognizer (emotion recognition library)

[0599] VideoProcessor (video processing library)

[0600] SceneGenerator (scene generation library)

[0601] The server first recognizes the user's emotions by analyzing the user's facial expressions and voice using the smartphone camera and head-mounted display sensors, and then uses an emotion recognition library to recognize the user's emotions.

[0602] The server then selects scenes based on the user's preferences, using a video processing library to select scenes from the raw footage that match the user's preferences and recognized emotions.

[0603] The server then combines the selected scenes to generate a new video. Using the scene generation library, the server combines the selected scenes to generate a new, alternate story video.

[0604] Finally, the server previews the generated video in real time, using a video processing library to instantly display the generated video to the user, allowing them to make adjustments until they are satisfied.

[0605] As a concrete example, consider the case where a user is watching a soccer match. If the user selects "I want to see more goal scenes" and the emotion recognition engine detects "excitement" in the user's facial expression, the server will select goal scenes from the original video and combine them to generate a new video.

[0606] Examples of prompts include:

[0607] "Select a goal scene from the original footage of a soccer match and generate a new Another Story video that matches the user's excited emotions."

[0608] In this way, Emotion-Driven Story Creator(R) enables the generation of new, alternative story videos based on the user's emotions and settings, allowing for an individually customized viewing experience.

[0609] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0610] Step 1:

[0611] The server acquires the user's facial expression and voice data from the smartphone camera and head-mounted display sensor. This is the input data. The server then analyzes this data using an emotion recognition engine to recognize the user's emotions. The output is the recognized emotion data.

[0612] Step 2:

[0613] The server receives the user's desired match results and scene settings. This is the input data. The server uses a video processing library to select scenes from the raw footage that match the user's settings. The output is a list of selected scenes.

[0614] Step 3:

[0615] The server receives as input the emotion data recognized in step 1 and the list of scenes selected in step 2. Based on these data, the server generates a new Another Story video using a scene generation library. The output is the generated new video.

[0616] Step 4:

[0617] The server previews the new video generated in real time. Using a video processing library, the generated video is instantly displayed to the user, who can make adjustments until satisfied. The input is the new generated video, and the output is the preview video shown to the user.

[0618] Step 5:

[0619] If the user is satisfied with the preview video, the server stores and delivers the final Another Story video. The input is the final video that the user is satisfied with, and the output is the delivered video.

[0620] In this way, Emotion-Driven Story Creator(R) enables the generation of new, alternative story videos based on the user's emotions and settings, allowing for an individually customized viewing experience.

[0621] Example 3

[0622] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0623] Conventional video generation and distribution systems have made it difficult for users to freely set their desired game results and scenes and generate original videos based on them. They also lacked the ability to share generated videos with other users or to provide a virtual space based on the user's emotions. This limited the user experience and made it difficult to provide flexible content tailored to individual needs.

[0624] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0625] In this invention, the server includes means for allowing the user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for streaming the generated video to the user, means for the user to share the generated video with other users, means for collecting and analyzing user emotion data, and means for providing a virtual space based on the user's emotions. This allows the user to freely set desired scenes and share the generated video with other users, and further allows the user to experience a virtual space that corresponds to their emotions.

[0626] "User" means an individual or organization that uses the system to generate and distribute videos and experience virtual spaces.

[0627] "Match results and scenes" refer to specific situations or events desired by the user, based on which videos are generated.

[0628] "Means for setting" refers to the interface or function that allows the user to input or select the desired match results or scenes.

[0629] "Original footage" refers to the original video material from which the Another Story video is generated.

[0630] An "Another Story Video" is a new video with a different scenario or outcome from the original video.

[0631] "Means of generation" refers to the technology and algorithms used to generate another story video based on the match results and scenes set by the user.

[0632] "Means of distribution" refers to the technology and infrastructure used to provide the generated video to users.

[0633] "Means of streaming" refers to the technology and protocols used to deliver the generated video to users in real time.

[0634] "Means for sharing" refers to link generation and social media integration functions that allow users to share videos they create with other users.

[0635] "Emotional data" refers to information about emotions collected from users' facial expressions, voice, etc.

[0636] "Means for analysis" refers to the technology or algorithms used to analyze collected emotional data and identify the user's emotional state.

[0637] "Virtual space" refers to an imaginary environment or scenario that users can experience.

[0638] "Means of provision" refers to the technology and infrastructure for generating an appropriate virtual space based on the user's emotions and providing it to the user.

[0639] This invention is a system that allows users to set their desired game results and scenes, generate original videos based on those results, and distribute and share them. It also includes a function to provide a virtual space based on the user's emotions.

[0640] Video Creation and Distribution

[0641] Entering a prompt statement

[0642] The user inputs a prompt to the AI ​​model using a terminal. For example, if the user wants to generate a scene of "what if dinosaurs appeared in the present day," the user can input that content.

[0643] Video generation

[0644] The server receives the prompt sentence entered by the user and generates a video using a generative AI model (e.g., a natural language processing model or an image generation model). The generated video is stored on the server. Specifically, models such as GPT-4 (registered trademark) and DALL-E from OpenAI (registered trademark) are used.

[0645] Preparing your video for streaming

[0646] The server prepares the generated video for streaming distribution using streaming technologies such as HLS (registered trademark) (HTTP Live Streaming) or DASH (registered trademark) (Dynamic Adaptive Streaming over HTTP).

[0647] Video streaming

[0648] Users access the server using devices (PCs, smartphones, tablets, etc.) and watch the generated video in real time. The server streams the video in response to user requests.

[0649] Video sharing

[0650] To share the generated video with other users, the user obtains a sharing link from the server. The user can send this link to other users via social networking sites or email. For example, a user can share a "what if" scene they generated on social networking sites and discuss it with other users.

[0651] Providing a virtual space using an emotion engine

[0652] Collecting Emotional Data

[0653] Users access the virtual space through a device, which collects emotional data such as facial expressions and voice and transmits it to a server.

[0654] Emotion analysis

[0655] The server uses an emotion engine (e.g., an emotion analysis API) to analyze the user's emotion data. Based on the analysis results, the server identifies the user's emotional state. Specifically, the server uses an emotion analysis API such as IBM Watson (registered trademark).

[0656] Virtual space generation

[0657] The server generates an appropriate virtual space depending on the emotional state of the user. For example, if the user is excited, the server generates an exciting virtual space of a different league.

[0658] Providing a virtual space

[0659] Users access and experience the virtual space created through their devices, and the server provides the virtual space in response to user requests.

[0660] Examples of specific examples and prompts

[0661] Examples of video creation and sharing

[0662] 1. Enter the prompt:

[0663] A user types the prompt "What if dinosaurs appeared in the present day?" into a terminal.

[0664] 2. Video generation:

[0665] The server uses a generative AI model (e.g., DALL-E) to generate a video based on the prompt sentence.

[0666] 3. Prepare your video for streaming:

[0667] The server converts the generated video into HLS format and prepares it for streaming.

[0668] 4. Streaming Video:

[0669] The user accesses the server from a terminal and watches the generated video in real time.

[0670] 5. Share videos:

[0671] The user obtains a sharing link from the server and shares the link on a social networking site.

[0672] Example prompt sentence:

[0673] Generate a scene that imagines what would happen if dinosaurs appeared in the modern world.

[0674] A concrete example of providing a virtual space using an emotion engine

[0675] 1. Collecting Emotional Data:

[0676] A user accesses the virtual space through a terminal, and the terminal collects facial expression data of the user.

[0677] 2. Emotion analysis:

[0678] The server uses an emotion engine to analyze the user's facial expression data and determine that the user is excited.

[0679] 3. Virtual space generation:

[0680] The server generates an exciting virtual space in a different league.

[0681] 4. Providing a virtual space:

[0682] Users access the virtual space generated on their devices and enjoy the experience.

[0683] In this way, the system realizes the distribution of generated videos and the provision of a virtual space based on emotions through cooperation between the server, the terminal, and the user. The flow of the specific processing in the third embodiment will be described with reference to FIG.

[0684] Step 1:

[0685] The user inputs a prompt to the AI ​​model using a device. For example, if the user wants to generate a scene such as "What if dinosaurs appeared in the present day?", the user inputs the content. The input prompt is sent from the device to the server.

[0686] Input: The prompt text entered by the user

[0687] Output: The prompt sent to the server

[0688] Step 2:

[0689] The server passes the received prompt sentence to a generative AI model. The generative AI model (for example, a natural language processing model or an image generation model) generates a video based on the prompt sentence. The generated video is stored on the server.

[0690] Input: The prompt received by the server

[0691] Output: Generated video file

[0692] Step 3:

[0693] The server prepares the generated video for streaming using a streaming technology such as HLS (registered trademark) (HTTP Live Streaming) or DASH (Dynamic Adaptive Streaming over HTTP), specifically by converting the video into an appropriate format and dividing it into segments for streaming.

[0694] Input: Generated video file

[0695] Output: Streamable video segments

[0696] Step 4:

[0697] Users access the server using their devices and watch the generated videos in real time. The server streams the videos in response to user requests. Users watch the videos through their device's browser or a dedicated app.

[0698] Input: User's streaming request

[0699] Output: Real-time streaming video

[0700] Step 5:

[0701] To share the generated video with other users, the user obtains a sharing link from the server. The server generates the sharing link and provides it to the user. The user can then send this link to other users via social networking sites or email to share it with them.

[0702] Input: User's shared link request

[0703] Output: Generated shared link

[0704] Step 6:

[0705] Users access the virtual space through their devices. The devices collect emotional data, such as facial expressions and voice, and transmit it to a server. The emotional data is collected using sensors such as cameras and microphones.

[0706] Input: User emotion data

[0707] Output: Emotion data sent to the server

[0708] Step 7:

[0709] The server uses the emotion engine to analyze the user's emotion data and identifies the user's emotional state based on the analysis result. For example, if the user is excited, the emotional state is identified.

[0710] Input: Emotion data sent to the server

[0711] Output: Parsed emotional state

[0712] Step 8:

[0713] The server generates an appropriate virtual space according to the user's emotional state. For example, if the user is excited, the server generates an exciting virtual space of a different league. The generated virtual space is stored in the server.

[0714] Input: Parsed emotional state

[0715] Output: Generated virtual space

[0716] Step 9:

[0717] Users access and experience the virtual space created through their devices. The server provides the virtual space in response to user requests. Users experience the virtual space through their device's browser or a dedicated app.

[0718] Input: User's request to access virtual space

[0719] Output: The virtual space provided

[0720] In this way, the system allows the server, terminals, and users to work together to distribute generated videos and provide a virtual space based on emotions.

[0721] (Application example 3)

[0722] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0723] Conventional video streaming systems do not allow users to set their desired game results or scenes, nor can they provide a virtual space based on the user's emotions. This makes it difficult to provide a realistic video experience that responds to the user's emotions. Furthermore, the ability to share generated videos with other users is limited, resulting in a lack of interaction between users. To solve these issues, a video generation and streaming system that responds to the user's wishes and emotions is needed.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0725] In this invention, the server includes means for allowing the user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for recognizing the user's emotions, means for generating a virtual space based on the recognized emotions, means for compositing the generated virtual space into the video, and means for streaming the composite video. This allows the server to provide a realistic video experience according to the user's wishes and emotions, and to share the generated video with other users.

[0726] "User" means any individual or entity that uses the System.

[0727] A "match result" is the final result or score in a competition such as a sport or game.

[0728] A "scene" refers to a specific moment or scene in a video or footage.

[0729] "Setting" is the act of specifying the conditions and parameters desired by the user.

[0730] "Original video" refers to the original video data before any editing or processing is performed.

[0731] An "Another Story Video" is a new video with a different scenario or development from the original video.

[0732] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[0733] "Emotions" are psychological states such as happiness, sadness, excitement, etc. that users experience.

[0734] "Recognition" is the process by which a system detects and understands a user's emotions and behavior.

[0735] "Virtual space" is a virtual environment or world generated by a computer.

[0736] "Synthesis" is the process of combining multiple images or data into a single image.

[0737] "Streaming distribution" is a technology that transmits video data to users in real time and plays it back.

[0738] The following system configuration will be described as an embodiment of the present invention.

[0739] System Configuration

[0740] The system allows users to set their desired match results and scenes, generates a video with a different story from the original footage, and distributes the generated video. It also recognizes the user's emotions, generates a virtual space based on the recognized emotions, synthesizes the generated virtual space into the video, and distributes the synthesized video via streaming.

[0741] Hardware and software used

[0742] Hardware: Smartphone camera, display

[0743] software:

[0744] OpenCV(R): Capture and display video frames

[0745] EmotionRecognizer: Emotion recognition engine

[0746] VideoStreamingService:Video streaming service

[0747] VirtualEnvironment: Virtual Environment Generation Engine

[0748] Program processing explanation

[0749] The server provides a means for users to set their desired match results and scenes. When users set their desired match results and scenes using their smartphones, an alternative story video different from the original video is generated based on those settings. This generation process uses a generative AI model.

[0750] The generated video is then distributed using a video streaming service, allowing users to watch the video on their smartphone displays.

[0751] Furthermore, the server uses an emotion recognition engine to recognize the user's emotions. Based on the recognized emotions, a virtual environment generation engine generates a virtual space. This virtual space changes according to the user's emotions.

[0752] The generated virtual space is composited into the original video frames using OpenCV (registered trademark). The composited video is streamed in real time. Users can view the composited video on their smartphone displays.

[0753] Specific examples

[0754] As a concrete example, consider a user streaming a video of a sporting event. If the emotion engine detects that the user is excited, the virtual environment will generate a scene of an enthusiastic crowd in a sports stadium and superimpose it onto the video, giving the user a more immersive video experience.

[0755] Prompt Sentence Examples

[0756] Example prompts to input to a generative AI model:

[0757] "If the user is excited, generate a scene of an excited sports stadium crowd."

[0758] In this way, it is possible to provide a realistic video experience that matches the user's wishes and emotions, and to share the generated video with other users.

[0759] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0760] Step 1:

[0761] Users can set the desired match results and scenes using their smartphone.

[0762] Input: User's desired match results and scene settings information

[0763] Output: The configuration information is sent to the server.

[0764] Specific operation: The user opens the application on their smartphone, selects the desired match result or scene, and sends the setting information to the server.

[0765] Step 2:

[0766] The server generates another story video that is different from the original video based on the setting information.

[0767] Input: User setting information, original video data

[0768] Output: Another Story Video

[0769] Specific operation: The server uses the generative AI model to generate another story video based on the user's settings, and the generated video is stored on the server.

[0770] Step 3:

[0771] The generated another story video will be distributed using a video streaming service.

[0772] Input: Another Story video

[0773] Output: Streamed video

[0774] Specific operation: The server uses a video streaming service to deliver the generated Another Story video to the user in real time, who then watches the video on their smartphone.

[0775] Step 4:

[0776] The server recognizes the user's emotions using an emotion recognition engine.

[0777] Input: User's facial image and voice data

[0778] Output: Recognized emotion data

[0779] Specific operation: The server acquires the user's facial image and voice data through the smartphone's camera and microphone, and recognizes emotions using an emotion recognition engine. The recognized emotion data is stored on the server.

[0780] Step 5:

[0781] Based on the recognized emotions, a virtual environment generation engine generates a virtual space.

[0782] Input: Recognized emotion data

[0783] Output: Virtual space data

[0784] Specific operation: The server generates an appropriate virtual space using a virtual environment generation engine based on the recognized emotion data. The generated virtual space data is stored on the server.

[0785] Step 6:

[0786] The generated virtual space is composited onto the original video frames using OpenCV (registered trademark).

[0787] Input: Original video frames, virtual space data

[0788] Output: Composite video frames

[0789] How it works: The server uses OpenCV to synthesize the original video frames with the generated virtual space, and the synthesized video frames are stored on the server.

[0790] Step 7:

[0791] The synthesized video is streamed in real time.

[0792] Input: Synthesized video frames

[0793] Output: Streamed composite video

[0794] How it works: The server uses a video streaming service to deliver the synthesized video to the user in real time, who then watches it on their smartphone.

[0795] 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.

[0796] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0797] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0798] 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.

[0799] [Second embodiment]

[0800] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0801] 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.

[0802] 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).

[0803] 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.

[0804] 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.

[0805] 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).

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0811] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0812] "Example 1"

[0813] This embodiment of the present invention provides an interface that allows users to set desired game results and scenes. This interface includes items that users can set, such as the participants in the game, the game results, and the results of important scenes. For example, in a soccer game, users can set the scorer, the timing of the goal, and the method of scoring (heading, shooting, etc.).

[0814] "Example 2"

[0815] We provide a method for generating a different story video from the original video based on the user's settings. This method appropriately combines scenes from the original video to recreate the scene set by the user. For example, if the user sets a goal scene, the system searches for a scoring scene by the same player in the original video and generates a new scene based on that scene.

[0816] "Example 3"

[0817] A means for distributing the generated video is provided. This means streams the generated video to users. A function is also provided that allows users to share the video they generated with other users. For example, a user can share the "what if" scene they generated on social media and discuss the scene with other users.

[0818] The processing flow of each embodiment will be described below.

[0819] "Example 1"

[0820] Step 1: The user accesses the system and opens the interface to set the participants in the match, the match results, the results of important scenes, etc.

[0821] Step 2: The user sets the desired outcome and scene on the interface. For example, for a soccer match, the user sets the scorer, the timing of the goal, and the method of scoring (heading, shooting, etc.).

[0822] Step 3: Once the configuration is complete, the user saves the configuration and the system receives the user's settings.

[0823] "Example 2"

[0824] Step 1: The system begins the process of generating a different story video from the original video based on the user's settings.

[0825] Step 2: The system searches the source footage for footage that corresponds to the scene set by the user. For example, if the user sets a goal, the system will search the source footage for a scoring scene by the same player.

[0826] Step 3: The system generates a new scene based on the footage it finds. The generated scene recreates the scene set by the user.

[0827] "Example 3"

[0828] Step 1: The system starts the process of distributing the generated video.

[0829] Step 2: Stream the system-generated video to the user.

[0830] Step 3: Provide a function that allows users to share the videos they create with other users. For example, users can share the "what if" scenes they create on social media and discuss them with other users.

[0831] Example 1

[0832] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0833] With conventional match result and scene generation systems, it was difficult for users to set the specific match results and scenes they wanted, and the generated results often did not meet users' expectations. Furthermore, it was difficult to provide the generated results to users in real time. This led to problems such as lower user satisfaction and a decrease in the frequency of system use.

[0834] 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.

[0835] In this invention, the server includes means for allowing a user to set desired game results and scenes, means for generating prompt sentences based on the settings, means for sending the generated prompt sentences to a generative AI model, means for receiving game results and scenes returned from the generative AI model, and means for displaying the received game results and scenes to the user. This allows a user to set specific game results and scenes and receive results based on the settings in real time.

[0836] "User" refers to an individual or organization that uses the System to set match results and scenes and receive the generated results.

[0837] "Game result" refers to the final score or outcome in a sport or competition.

[0838] A "scene" refers to a specific moment or event during a game or competition.

[0839] A "prompt sentence" refers to a text-based input sentence that provides instructions to a generative AI model.

[0840] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate match results or scenes based on user input.

[0841] "Server" refers to the computer system that receives input from users, processes data, and communicates with the generative AI model.

[0842] A "means" refers to a method or device used to achieve a particular purpose.

[0843] "Interface" refers to the screens and input forms that allow users to interact with the system.

[0844] "Database" refers to an information management system for storing user input data and generated results.

[0845] "Real-time" refers to a timeframe in which a user's input is responded to immediately.

[0846] This invention is a system that allows a user to set desired game results and scenes, and generates game results and scenes using a generative AI model based on those settings, and provides them to the user. Specific embodiments of this system are described below.

[0847] Hardware and software used

[0848] Hardware:

[0849] High-performance server (e.g. general-purpose server)

[0850] The device used by the user to access the site (e.g., personal computer, smartphone)

[0851] software:

[0852] Generative AI models (e.g., general-purpose generative AI models)

[0853] Web browser (e.g., general-purpose web browser)

[0854] Database management systems (e.g., general-purpose database management systems)

[0855] System processing flow

[0856] 1. User accesses the interface:

[0857] Users access the system's interface using a web browser, which provides input forms for setting match results and scenes.

[0858] 2. User enters match settings:

[0859] The user enters information about the participants in the match, the match results, and details of important scenes (such as the scorer, the timing of the goal, and the method of scoring) into an input form on the interface.

[0860] 3. The server receives the input data:

[0861] The server receives the data entered by the user and stores it in a database for further processing.

[0862] 4. The server generates a prompt:

[0863] The server generates a prompt to send to the generative AI model based on the data entered by the user. For example, if the user enters "Team A wins 2-1," the prompt will be "Generate the results of a soccer match. The participants in the match are Team A and Team B. The result of the match is that Team A wins 2-1."

[0864] 5. The server sends a prompt to the generative AI model:

[0865] The server sends the generated prompts to the generative AI model, which then instructs the model to generate game results and scenes.

[0866] 6. Generative AI models generate game results and scenes:

[0867] The generative AI model generates match results and scenes based on prompts received from the server. The model analyzes the input information and generates results that meet the user's wishes.

[0868] 7. The server receives the generated results:

[0869] The server receives the match results and scenes returned by the generative AI model, which are then formatted for display to the user.

[0870] 8. The server displays the results to the user:

[0871] The server sends the generated match results and scenes to the user's browser, where the user can view the results and change the settings as needed.

[0872] Examples of specific examples and prompts

[0873] Examples:

[0874] The user sets up "Team A" and "Team B" as participants in the match.

[0875] Set the result of the match as "Team A wins 2-1."

[0876] The key scenes are set as follows: "The scorers are Team A's Player X and Player Y, the timing of the goals is 20 minutes into the first half and 75 minutes into the second half, and the scoring methods are shots and headers."

[0877] Example prompt sentence:

[0878] Generate the results of a soccer match. The participants in the match are Team A and Team B. Team A wins 2-1. The scorers are Player X and Player Y of Team A. The goals are scored at the 20th minute of the first half and the 75th minute of the second half. The methods of scoring are shots and headers.

[0879] In this way, users can set specific match results or scenes and receive real-time results based on those settings.

[0880] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0881] Step 1:

[0882] The user accesses the interface.

[0883] A user accesses the system's interface using a web browser. As input, the user enters the system's URL into the browser. As output, the interface is displayed. Specifically, the user opens a web browser, such as Google® Chrome, and enters the system's URL to access the interface.

[0884] Step 2:

[0885] The user enters the match settings.

[0886] The user enters the participants of the match, the match results, and details of important scenes (such as the scorers, the timing of the goals, and the method of scoring) into an input form on the interface. As input, the user enters detailed information about the match. As output, the entered data is displayed on the interface. In concrete terms, the user uses text boxes and drop-down menus to enter detailed information about the match.

[0887] Step 3:

[0888] The server receives the input data.

[0889] The server receives the data entered by the user and stores it in a database. As input, the match details entered by the user are sent to the server. As output, data stored in the database is generated. Specifically, the server receives an HTTP request and stores the data in a MySQL database.

[0890] Step 4:

[0891] The server generates a prompt.

[0892] The server generates a prompt sentence to send to the generative AI model based on the data entered by the user. The match details stored in the database are used as input. The generated prompt sentence is obtained as output. Specifically, the server uses a Python script to generate the prompt sentence based on the data entered by the user.

[0893] Step 5:

[0894] The server sends a prompt to the generative AI model.

[0895] The server sends the generated prompt sentence to the generative AI model. The generated prompt sentence is used as input. The prompt sentence is sent to the generative AI model as output. Specifically, the server sends the prompt sentence to the generative AI model via an HTTP request.

[0896] Step 6:

[0897] Generative AI models generate match results and scenes.

[0898] The generative AI model generates match results and scenes based on prompts received from the server. The prompts are used as input. The generated match results and scenes are obtained as output. Specifically, the generative AI model analyzes the prompts and generates match results and scenes that meet the user's wishes.

[0899] Step 7:

[0900] The server receives the generated results.

[0901] The server receives the match results and scenes returned from the generative AI model. The output from the generative AI model is used as input. The received match results and scenes are obtained as output. Specifically, the server receives the JSON format data returned from the generative AI model and formats it into HTML.

[0902] Step 8:

[0903] The server displays the results to the user.

[0904] The server sends the generated match results and scenes to the user's browser. As input, the formatted match results and scenes are used. As output, the results are displayed in the user's browser. In concrete terms, the server sends the formatted data to the user's browser as an HTTP response, and the user sees the results on the interface.

[0905] (Application example 1)

[0906] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0907] Conventional sports game video distribution systems make it difficult for users to freely set specific game results or scenes they want and watch customized videos based on those settings. Furthermore, the lack of technology to generate videos in real time based on user-defined scenes hinders user satisfaction. Furthermore, there is a lack of a means to efficiently distribute the generated videos.

[0908] 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.

[0909] In this invention, the server includes means for setting the match results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating match highlight text using a generative AI model, and means for editing the video based on the generated text. This allows the user to freely set the specific match results and scenes desired, generate customized videos based on the settings in real time, and distribute them efficiently.

[0910] "User" refers to an individual or organization that uses the system to set match results and scenes.

[0911] "Game result" refers to the final outcome of a sports game, such as the score or victory or defeat.

[0912] A "scene" refers to a specific moment or event during a match.

[0913] "Setting" refers to the act of the user inputting the desired match results and scenes into the system.

[0914] "Original footage" refers to footage of an actual match.

[0915] "Another story video" refers to a new video that differs from the original footage and is generated based on the match results and scenes set by the user.

[0916] "Generative AI model" refers to an algorithm or program that uses artificial intelligence technology to generate text or video.

[0917] "Highlight text" refers to written descriptions of important scenes and events in a match.

[0918] "Video editing" refers to the act of processing and editing video based on the generated text.

[0919] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[0920] The system for implementing this invention allows users to set desired game results and scenes, and then generates and distributes customized videos based on those settings. A specific embodiment of this system is described below.

[0921] System Configuration

[0922] The system consists of the following main components:

[0923] 1. User device: A device that provides an interface for users to set game results and scenes. This includes smartphones, tablets, and PCs.

[0924] 2. Server: A central processing unit that receives user settings, generates highlight text using generative AI models, and edits and generates videos.

[0925] 3. Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate text based on game results and scenes set by the user.

[0926] 4. Video editing software: Software for editing videos based on the generated text, for example using libraries such as OpenCV (registered trademark).

[0927] 5. Distribution server: A server for distributing the generated video to users.

[0928] Processing flow

[0929] 1. User settings: The user inputs the desired match results and scenes from the user's device. For example, the user can set "Scorer: Tanaka, Score timing: 20 minutes into the first half, Score method: Heading."

[0930] 2. Prompt generation: The server generates a prompt based on the user's settings. For example, it generates a prompt such as, "Please describe the scene in a soccer game where Tanaka scores a header in the 20th minute of the first half."

[0931] 3. Highlight text generation: Using a generative AI model, highlight text is generated based on the prompt sentence.

[0932] 4. Video editing: Based on the generated highlight text, another story video is created from the original footage using video editing software.

[0933] 5. Video distribution: The generated video is provided to the user through a distribution server.

[0934] Specific examples

[0935] For example, if the user sets the scene where Tanaka scores with a header in the 20th minute of the first half, the following prompt will be generated:

[0936] Describe a scene in a soccer match where Tanaka scores a header in the 20th minute of the first half.

[0937] By inputting this prompt into a generative AI model, text for the desired game scene is generated, and a highlight video is created based on that text.

[0938] Hardware and software used

[0939] Generative AI model: GPT-3 (registered trademark) from OpenAI (registered trademark)

[0940] Video editing software: OpenCV (registered trademark)

[0941] User devices: smartphones, tablets, computers

[0942] Server: High-performance central processing unit (equipped with CPU and GPU)

[0943] In this way, users can freely set the specific match results or scenes they want, and customized videos based on those settings can be generated in real time and distributed efficiently.

[0944] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0945] Step 1:

[0946] The user uses the device to set the desired match results and scenes.

[0947] Input: Match results and scene setting information entered by the user into the device (e.g., "Scorer: Tanaka, Score timing: 20 minutes into the first half, Score method: Header").

[0948] Output: The configuration information is sent to the server.

[0949] Specific operation: The user inputs the match results and scenes through the terminal interface and sends the setting information to the server.

[0950] Step 2:

[0951] The server receives the user's configuration information and generates a prompt.

[0952] Input: Configuration information submitted by the user.

[0953] Output: The generated prompt sentence (e.g., "Please describe a scene in a soccer game where Tanaka scores a header in the 20th minute of the first half.").

[0954] Specific operation: The server analyzes the configuration information and generates a prompt sentence to input into the generative AI model.

[0955] Step 3:

[0956] The server uses a generative AI model to generate highlighted text based on the prompt.

[0957] Input: The generated prompt statement.

[0958] Output: The generated highlighted text.

[0959] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and obtains the highlighted text from the model.

[0960] Step 4:

[0961] The server generates another story video using video editing software based on the generated highlight text.

[0962] Input: The generated highlighted text.

[0963] Output: Generated Another Story video.

[0964] Specific operation: The server uses video editing software (e.g., OpenCV (registered trademark)) to generate another story video from the original video based on the highlight text.

[0965] Step 5:

[0966] The server provides the generated Another Story video to the user through a distribution server.

[0967] Input: Generated Another Story video.

[0968] Output: A video file that can be played on the user's device.

[0969] Specific operation: The server uploads the generated video to the distribution server so that the user can watch it on their device.

[0970] Example 2

[0971] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0972] With conventional video generation systems, it was difficult to generate another story video that reflected specific scenes or match results desired by the user. In addition, the process of extracting relevant scenes from the original video and generating a new video based on the user's settings was complicated and inefficient. Furthermore, there was a lack of a way to quickly provide the generated video to the user.

[0973] 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.

[0974] In this invention, the server includes means for setting the game results and scenes desired by the user, means for generating another story video that differs from the original video based on the settings, means for distributing the generated video, means for analyzing the user's setting conditions, means for searching the original video database and extracting relevant scenes, means for generating a new video using a generative AI model, and means for displaying the generated video to the user. This makes it possible to efficiently generate and quickly provide another story video that reflects the specific scenes and game results desired by the user.

[0975] "User" refers to an individual or organization that uses the system to set match results and scenes and generate another story video.

[0976] A "means for setting game results or scenes" is a device or software that provides an interface or functionality for a user to input or select a particular game result or scene desired.

[0977] "Another Story Video" is a new video generated according to the user's settings based on scenes extracted from the original video.

[0978] "Generating means" refers to a device or software that extracts relevant scenes from the source video based on the user's settings and creates a new video using a generative AI model.

[0979] "Means for providing distribution" refers to a device or software for transmitting the generated Another Story video to users and making it viewable.

[0980] "Means for analyzing" refers to a device or software that understands the settings entered or selected by the user and performs appropriate processing.

[0981] The "means for searching and extracting relevant scenes" refers to a device or software that searches the original video database to find and extract scenes that meet the user's set conditions.

[0982] A "generative AI model" is a model for generating new videos using artificial intelligence technology, including, for example, natural language processing and video generation technology.

[0983] "Displaying means" refers to a device or software for displaying the generated Another Story video on the user's terminal.

[0984] This invention relates to a system that allows a user to set a desired game result or scene, and based on that, generates a different story video from the original video, and distributes it. Specific embodiments of this system are described below.

[0985] First, the user inputs the conditions for the Another Story video they want to generate through the device interface. For example, they might input, "I want a video of Player A's scoring scenes." This input is done using the device's input form and selection menu.

[0986] Next, the device receives the user's input and sends the request to the server. The request includes the conditions set by the user. The server analyzes the received request and understands the conditions the user is looking for. For example, it analyzes the condition "collect scenes of player A scoring."

[0987] The server searches a database where the original video is stored to find scenes that match the conditions set by the user. This search uses video analysis software (e.g., OpenCV (registered trademark)). The server extracts relevant scenes from the search results. For example, it extracts all scenes in which player A scores.

[0988] The server then uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a new "Another Story" video based on the extracted scenes. This process also uses video editing software. The generative AI model combines scenes based on the user's settings to generate a new video.

[0989] The generated video is sent from the server to the device using a high-speed data transfer protocol (e.g. HTTP / 2). The device then displays the received video to the user. The user can then watch the generated Another Story video on the device screen.

[0990] For example, if a user requests "I want a video of player A scoring," the following prompt might be used:

[0991] "Generate a video of player A scoring."

[0992] In this way, different, alternative story videos are generated from the original footage based on user requests and quickly provided. This system allows users to efficiently generate and watch videos that reflect specific scenes or game results they desire.

[0993] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0994] Step 1:

[0995] The user enters a request.

[0996] The user inputs the conditions for the Another Story video they want to generate through the device interface. For example, they might input, "I want a video of Player A's scoring scenes." The input conditions are saved in the device's input form.

[0997] Step 2:

[0998] The device sends a request to the server.

[0999] The terminal receives the user's input and sends the request to the server. The request includes the conditions set by the user. The input data is sent to the server as an HTTP request.

[1000] Step 3:

[1001] The server parses the request.

[1002] The server analyzes the received request and understands the conditions the user is looking for. For example, it analyzes the condition "collect scenes of player A scoring." The analysis results are stored in an internal data structure.

[1003] Step 4:

[1004] The server searches the original video database.

[1005] The server searches the database where the original video is stored to find scenes that match the conditions set by the user. This search is performed using video analysis software (e.g., OpenCV (registered trademark)). The input is the analysis results, and the output is a list of matching scenes.

[1006] Step 5:

[1007] The server extracts the relevant scenes.

[1008] The server extracts relevant scenes from the search results. For example, it extracts all scenes in which player A scores. The input is the search results, and the output is the data of the extracted scenes.

[1009] Step 6:

[1010] The server uses the generative AI model to generate new videos.

[1011] The server generates a new Another Story video using a generative AI model (e.g., GPT-4 (registered trademark)) based on the extracted scenes. This process also uses video editing software. The input is the extracted scene data, and the output is the generated video.

[1012] Step 7:

[1013] The video generated by the server is sent to the terminal.

[1014] The server sends the generated video to the device using a high-speed data transfer protocol (e.g., HTTP / 2). The input is the generated video, and the output is the data transfer to the device.

[1015] Step 8:

[1016] The terminal displays the generated video to the user.

[1017] The device displays the received video to the user, who can then watch the generated Another Story video on the device screen. The input is the video sent from the server, and the output is the user's viewing experience.

[1018] (Application example 2)

[1019] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1020] Conventional video generation systems have had difficulty extracting specific scenes desired by users from source video and generating them as new videos. Furthermore, they lacked a means to efficiently detect user-specified scenes, connect them, and generate new videos, making it impossible to provide videos customized to meet user needs. This resulted in lower user satisfaction and reduced value for content distribution services.

[1021] 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.

[1022] In this invention, the server includes means for setting the match results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for detecting scenes specified by the user from the original video, and means for generating a new video by linking the detected scenes. This makes it possible to efficiently extract specific scenes desired by the user and generate and distribute customized videos.

[1023] "User" means an individual or entity that uses the System to generate and view customized videos by setting specific match results or scenes.

[1024] "Game results" refers to the results of sports or competitions, such as scores or wins and losses.

[1025] A "scene" refers to a specific moment in a video or a portion of a continuous sequence of images.

[1026] "Setting" refers to the act of the user inputting the desired match results and scenes into the system.

[1027] "Original video" refers to original video data that has not been edited or processed.

[1028] "Another story video" refers to a new video generated from the original video based on the user's settings.

[1029] "Generation" refers to the process of creating new video from original footage.

[1030] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[1031] "Detection" refers to the process of finding the scene specified by the user from the original video.

[1032] "Concatenation" refers to the act of connecting detected scenes in order to compile them into a single video.

[1033] The system for implementing this invention allows users to set their desired game results and scenes, generates another story video from the original video based on those settings, and distributes the generated video. Specific embodiments are described below.

[1034] System configuration

[1035] The system consists of the following main components:

[1036] 1. User device: A device such as a smartphone or tablet that the user uses to set up a scene.

[1037] 2. Server: A central processing unit for video generation and distribution.

[1038] 3. Database: Storage for saving original footage and generated videos.

[1039] Hardware and software used

[1040] Hardware: Smartphones, tablets, servers, storage devices

[1041] Software: Python (registered trademark), OpenCV (registered trademark) (image processing library), MoviePy (registered trademark) (video editing library)

[1042] Processing flow

[1043] 1. User device: The user uses a smartphone or tablet to set the desired game results and scenes, for example, by entering a prompt such as "Please create a highlight video of a specific player's scoring scenes."

[1044] 2. Server: Detects the specified scenes from the original video based on the user's settings. OpenCV is used to analyze the video frame by frame and find the scenes specified by the user.

[1045] 3. Server: Concatenate the detected scenes to create a new video. Using MoviePy, we connect the detected scenes in order to create a single video.

[1046] 4. Server: The generated Another Story video is stored in a database and distributed to users.

[1047] Specific examples

[1048] If a user wants to create a highlight video of a specific soccer player's goals, they can do the following:

[1049] 1. The user opens the application on their smartphone and enters the command, "Please create a highlight video of a specific player's scoring moments."

[1050] 2. The server analyzes the original video and detects the scoring scenes of the specified player.

[1051] 3. The detected scenes are concatenated to generate a new highlight video.

[1052] 4. Deliver the generated video to the user.

[1053] Prompt Sentence Examples

[1054] "Create a highlight video from a soccer match that includes only the scoring scenes of a specific player."

[1055] In this way, users can easily create and watch customized videos containing their desired scenes.

[1056] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1057] Step 1:

[1058] User device: The user uses a smartphone or tablet to set the desired game results and scenes. Specifically, the user opens the application and enters a prompt such as, "Please create a highlight video of a specific player's scoring scenes."

[1059] Input: User prompt

[1060] Output: User settings information

[1061] Step 2:

[1062] Server: Receives the user's setting information and retrieves the original video from the database.

[1063] Input: User settings, original video database

[1064] Output: Original video data

[1065] Step 3:

[1066] Server: Analyzes the original video frame by frame using OpenCV (registered trademark) and detects scenes specified by the user. Specifically, it calculates the average color and feature values ​​of the frames and finds scenes that match the conditions specified by the user.

[1067] Input: Original video data, user setting information

[1068] Output: A list of detected scenes

[1069] Step 4:

[1070] Server: Using MoviePy (registered trademark), the detected scenes are concatenated in order to generate a new video. Specifically, the detected scenes are read as clips, concatenated, and written as a single video file.

[1071] Input: A list of detected scenes

[1072] Output: Generated Another Story video

[1073] Step 5:

[1074] Server: The server stores the generated Another Story video in a database and delivers it to users. Specifically, it stores the generated video file in storage and notifies the user of its URL.

[1075] Input: Generated Another Story video

[1076] Output: Delivery URL to user

[1077] In this way, users can easily create and watch customized videos containing their desired scenes.

[1078] Example 3

[1079] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1080] While conventional video generation systems allow users to set their desired scenes and game results, they lack the ability to share the generated videos with other users. Furthermore, there are limited means for streaming the generated videos in real time, often limiting the user experience. Furthermore, the process of generating videos using generative AI models is complex, creating a need for an easy-to-use interface.

[1081] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1082] In this invention, the server includes means for allowing a user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating a video based on a prompt sentence using a generative AI model, means for streaming the generated video, and means for the user to share the generated video with other users. This allows a user to easily set desired scenes and watch and share the generated video in real time.

[1083] "User" refers to any individual or entity that uses the System to generate, view, or share videos.

[1084] "Means for setting game outcomes or scenes" refers to functionality that provides an interface for users to input or select specific scenes or results they desire.

[1085] "Means for generating another story video" refers to the function that generates a video with a new story different from the original video based on scenes and results set by the user.

[1086] "Means for distributing and providing the generated video" refers to the technology and process for distributing the generated video to users.

[1087] "Generative AI model" refers to an artificial intelligence model that generates videos based on prompts entered by users.

[1088] "Prompt" refers to a textual instruction that a user inputs to a generative AI model.

[1089] "Means for generating video" refers to the technology or process for generating video based on prompt text using a generative AI model.

[1090] "Means for streaming" refers to the technology and processes used to deliver generated video to users in real time.

[1091] "Means for sharing videos" refers to link generation and sharing functions that allow users to share videos they generate with other users.

[1092] This invention is a system that allows users to set desired scenes and game results, and streams and shares videos generated based on those settings. Specific embodiments of this system are described below.

[1093] System configuration

[1094] server

[1095] The server generates a video based on the prompt entered by the user using a generative AI model. Generative AI models include, for example, natural language processing models and image generation models. Specifically, models such as OpenAI's GPT-4 and DALL-E can be used.

[1096] The server converts the generated video into a suitable format for streaming. For example, it converts the video to MP4 format and uploads it to the streaming server. Once the upload is complete, a streaming URL is generated.

[1097] In addition, the server generates a link for users to share their videos with other users. This link can be shared via social media, email, etc.

[1098] Terminal

[1099] The terminal is responsible for sending the prompt text entered by the user to the server. When the user enters the prompt text through the terminal interface and presses the send button, the data is sent to the server. The terminal application generates an HTTP request and sends the data, including the prompt text, to the server.

[1100] The device also receives and plays streaming video from the server, allowing users to view the generated video on the device screen.

[1101] The device also provides an interface for users to share the videos they generate with other users. Users can share links to videos generated using the device via social media or email.

[1102] User

[1103] The user uses a device to create a prompt to be input to the generative AI model. For example, they can enter a prompt such as "What if dinosaurs were alive today?" When the user enters the prompt and presses the send button, the data is sent to the server.

[1104] The user watches the generated video streamed from the server. For example, if the user inputs the prompt "What if dinosaurs were alive today?", the generated video will include a scene of dinosaurs walking around a modern city.

[1105] Furthermore, users can share the generated video with other users. For example, users can share the link of the generated video on social media and discuss the scene with other users.

[1106] Specific examples

[1107] Prompt Sentence Examples

[1108] "If dinosaurs were alive today"

[1109] Operation flow

[1110] 1. The user uses the terminal to enter the prompt sentence "What if dinosaurs were alive today?" and presses the send button.

[1111] 2. The terminal sends the prompt text to the server.

[1112] 3. The server uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a video based on the prompt.

[1113] 4. The server converts the generated video into a format suitable for streaming and uploads it to the streaming server.

[1114] 5. The server provides the generated streaming URL to the user, allowing the user to watch the video.

[1115] 6. The user accesses the streaming URL through the device's browser or a dedicated application and watches the video.

[1116] 7. The user shares the link of the generated video via SNS or email, and discusses the scene with other users. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] The user enters a prompt statement.

[1119] The user inputs a prompt that describes the content of the video they want to generate through the device interface. For example, they input a prompt such as "What if dinosaurs were alive today?" The input prompt is temporarily stored in the device's memory.

[1120] Step 2:

[1121] The terminal sends the prompt to the server.

[1122] The terminal sends the prompt text entered by the user to the server. Specifically, the terminal application generates an HTTP request and sends data including the prompt text to the server's API endpoint. The input is the prompt text, and the output is a transmission completion notification to the server.

[1123] Step 3:

[1124] The server generates the video using a generative AI model.

[1125] The server inputs the received prompt sentence into a generative AI model. The generative AI model (e.g., GPT-4 (registered trademark) or DALL-E) analyzes the prompt sentence and generates appropriate scenes and characters. The input is the prompt sentence, and the output is the generated video data. Specifically, the server analyzes the prompt sentence, determines the components of the scene, and generates a video based on them.

[1126] Step 4:

[1127] The server prepares the generated video for streaming.

[1128] The server converts the generated video into a format appropriate for streaming. For example, it converts the video into MP4 format and uploads it to the streaming server. The input is the generated video data and the output is a streaming URL. Specifically, the server encodes the video and uploads it to the streaming server.

[1129] Step 5:

[1130] The server streams the video.

[1131] The server distributes the generated video to the user through the streaming server. The user can watch the video in real time through the browser on their device or a dedicated application. The input is a streaming URL, and the output is the video played on the user's device. Specifically, the server provides the streaming URL to the user, and the user accesses that URL.

[1132] Step 6:

[1133] A user watches a video.

[1134] The user watches the generated video using their device. For example, if the user inputs the prompt "What if dinosaurs were alive today?", the generated video will include a scene of dinosaurs walking through a modern city. The input is a streaming URL, and the output is the video to be watched. Specifically, the user opens a browser or dedicated application on their device and accesses the provided streaming URL.

[1135] Step 7:

[1136] A user shares a video.

[1137] Users can share the generated video with other users. Specifically, the server provides a link to the generated video, and the user shares the link via social media or email. The input is the streaming URL, and the output is the shared link. Specifically, the user copies the link of the generated video and shares it via social media or email.

[1138] (Application example 3)

[1139] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1140] While conventional video generation systems allow users to set their desired scenes and game results, they lack the means to share and discuss the generated videos with other users. Furthermore, the content of the generated videos is limited, preventing users from fully utilizing their creativity. Furthermore, there is no way to stream the generated videos in real time, limiting the user experience.

[1141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1142] In this invention, the server includes means for allowing a user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating video content based on prompt sentences using a generative AI model, means for streaming the generated video, and means for sharing the generated video with other users. This allows a user to freely set desired scenes, stream the generated video in real time, and share and discuss it with other users.

[1143] "User" means an individual or organization that uses the system to generate and distribute videos.

[1144] "Game results" refers to the final score or outcome in a sport, game, or other competition.

[1145] A "scene" is a part of a video or movie that shows a specific situation or situation.

[1146] "Setting" is the act of the user inputting desired conditions and parameters into the system.

[1147] "Original video" refers to the original video material that is the basis for generating the video.

[1148] "Another story video" is a newly generated video with a different storyline from the original video.

[1149] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate content based on user input.

[1150] A "prompt" is a sentence of instructions or questions that a user inputs to a generative AI model.

[1151] "Streaming distribution" is a technology that distributes generated video in real time over the Internet.

[1152] "Sharing" refers to the act of showing the created video to other users via the Internet.

[1153] The system for implementing this invention allows users to set their desired scenes and match results, generate video content based on prompts using a generative AI model, and stream the generated video for sharing with other users.

[1154] System Configuration

[1155] The system consists of the following main components:

[1156] 1. User terminal: A device used by a user to access the system, such as a smartphone or computer.

[1157] 2. Server: A central server for providing video generation, streaming, and sharing functions.

[1158] 3. Generative AI model: An artificial intelligence model that generates video content based on user prompts.

[1159] Operating procedure

[1160] 1. User terminal: The user accesses the system using a terminal and sets the desired scene and game result. For example, the user enters a prompt sentence such as "What if dinosaurs appeared in the modern world?"

[1161] 2. Server: The server sends the prompt received from the user to the generative AI model to generate the video content, which is then stored on the server.

[1162] 3. Streaming: The server streams the generated video in real time, allowing users to watch the video through their devices.

[1163] 4. Sharing function: Users can share the videos they create with other users on social media, etc. Other users can view the shared videos and comment and discuss them.

[1164] Hardware and software used

[1165] Hardware: smartphones, PCs, servers

[1166] Software: Python®, Streamlit®, OpenAI® API, MoviePy®

[1167] Specific examples

[1168] If the user wants to generate a scene in which dinosaurs appear in the present day, they would enter the following prompt:

[1169] Example prompt sentence:

[1170] If dinosaurs were to appear in the modern world, what kind of scene would unfold?

[1171] By entering this prompt, the generative AI model will generate the scene and stream it as a video, which users can then share on social media and discuss with other users.

[1172] In this way, users can freely set up the scenes they want, stream the generated videos in real time, and share and discuss them with other users.

[1173] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1174] Step 1:

[1175] The user accesses the system using a terminal and sets the desired scene and game result. Specifically, the user inputs a prompt sentence. For example, the user inputs a prompt sentence such as "What if dinosaurs appeared in the present day?" The input data is the prompt sentence, which becomes the input for the next step.

[1176] Step 2:

[1177] The terminal sends the input prompt to the server, which receives the prompt and passes it to the generative AI model. The input data is the prompt, and the output data is the prompt passed to the generative AI model.

[1178] Step 3:

[1179] The server uses a generative AI model to generate video content based on the prompt. Specifically, the generative AI model analyzes the prompt and generates corresponding video scenes. The input data is the prompt, and the output data is the generated video content.

[1180] Step 4:

[1181] The server saves the generated video content as a video file. Specifically, the generated video content is converted into a video file format and saved within the server. The input data is the generated video content, and the output data is the saved video file.

[1182] Step 5:

[1183] The server streams the stored video files in real time. Specifically, the streaming server delivers the video files to the user's device. The input data is the stored video file, and the output data is the video to be streamed.

[1184] Step 6:

[1185] Users watch the streamed video through their devices. Specifically, they play the video using their device's browser or a dedicated app. The input data is the streamed video, and the output data is the video the user watches.

[1186] Step 7:

[1187] Users can share the generated video with other users on social media platforms. Specifically, they click the share button to post a link to the video on the social media platform. The input data is the link to the generated video, and the output data is the video link shared on the social media platform.

[1188] Step 8:

[1189] Other users can watch the video through the shared video link and comment and discuss. Specifically, they click on the video link on the SNS to watch the video and post their opinions in the comments section. The input data is the video link shared on the SNS, and the output data is the comments and discussions from other users.

[1190] 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.

[1191] "Example 1"

[1192] One embodiment of the present invention provides a system including an emotion engine that recognizes a user's emotions. This system includes a means for setting a desired match result or scene for the user, a means for generating a video with a different story from the original video based on the setting, and a means for distributing the generated video. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, text input, etc., and generates a video based on the emotion. For example, if the user expresses joy, a joyful scene is generated to match that emotion.

[1193] "Example 2"

[1194] Another embodiment of the present invention provides a system in which an emotion engine generates a user's own original scene. This system allows the system to generate an original scene based on the user's emotion. For example, if the user expresses sadness, a sad scene is generated to match the emotion. In this way, various scenes can be generated according to the user's emotion.

[1195] "Example 3"

[1196] As a further embodiment of the present invention, a system is provided in which an emotion engine provides a different league or the like in a virtual space that is different from reality. This system makes it possible to provide a different league or the like in the virtual space based on the user's emotions. For example, if the user is expressing excitement, the system provides an exciting different league that matches that emotion. In this way, it is possible to provide various virtual spaces according to the user's emotions.

[1197] The processing flow of each embodiment will be described below.

[1198] "Example 1"

[1199] Step 1: The user accesses the system and sets the match results and scenes.

[1200] Step 2: The emotion engine recognizes emotions from the user's facial expressions, tone of voice, text input, etc.

[1201] Step 3: Based on the recognized emotions, another story video is generated that is different from the original video.

[1202] Step 4: The generated video is distributed to users.

[1203] "Example 2"

[1204] Step 1: The user accesses the system and sets the match results and scenes.

[1205] Step 2: The emotion engine recognizes the user's emotion.

[1206] Step 3: Generate your own original scene based on the recognized emotions.

[1207] Step 4: The generated original scene is distributed to users.

[1208] "Example 3"

[1209] Step 1: The user accesses the system and sets the match results and scenes.

[1210] Step 2: The emotion engine recognizes the user's emotion.

[1211] Step 3: Based on the recognized emotions, a different league or world from reality is provided through a virtual space.

[1212] Step 4: The virtual space provided is distributed to users.

[1213] Example 1

[1214] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1215] Conventional systems allow users to set their desired match results and scenes, but they have the problem of not being able to generate videos that reflect the user's emotions. Also, if the generated video does not match the user's emotions, user satisfaction may decrease. Furthermore, if the generated video is not delivered smoothly, the user experience may be impaired.

[1216] 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.

[1217] In this invention, the server includes a means for allowing the user to set desired game results and scenes, a means for generating a story video different from the original video based on the settings, a means for distributing the generated video, a means for recognizing the user's emotions, a means for generating a video based on the recognized emotions, and a means for generating a video by inputting a prompt sentence using a generative AI model. This allows for the generation of videos that reflect the user's desired game results and scenes and are based on the user's emotions. Furthermore, the smooth distribution of the generated videos improves the user experience.

[1218] "User" means an individual or organization that uses the system to set match results and scenes and view the generated videos.

[1219] "Game result" refers to the final score or outcome of a sport or competition.

[1220] A "scene" refers to a specific moment or event during a game or competition.

[1221] "Means for setting" refers to the interface or tool that allows the user to input or select the desired match results or scenes.

[1222] "Original footage" refers to footage of actual matches or competitions.

[1223] "Another Story Video" refers to a new video with different content from the original video based on the user's settings.

[1224] "Means of generation" refers to the technology and algorithms used to create new videos based on user settings.

[1225] "Means of distribution" refers to the technology and methods for transmitting the generated video to the user's device.

[1226] "Means of recognizing emotions" refers to technologies and algorithms that analyze emotions from users' facial expressions, tone of voice, text input, etc.

[1227] A "generative AI model" refers to a model that uses artificial intelligence to generate videos based on user settings and emotions.

[1228] A "prompt sentence" is an instruction sentence that is input into a generative AI model and is used to specifically specify the content of the video to be generated.

[1229] This invention is a system that allows users to set their desired game results and scenes, generate a video with a different story from the original video based on the settings, and distribute the generated video. This system includes a function to recognize the user's emotions and generate a video based on those emotions.

[1230] System configuration

[1231] The system consists of the following main components:

[1232] 1. User Interface: An interface for users to set their desired match results and scenes. This can be implemented as a web application or a mobile application.

[1233] 2. Server: Receives user settings, recognizes user emotions using an emotion engine, and generates another story video using a generative AI model.

[1234] 3. Emotion engine: Software that analyzes emotions from the user's facial expressions, tone of voice, text input, etc.

[1235] 4. Generative AI model: An artificial intelligence model that generates videos by inputting prompt sentences based on the user's settings and recognized emotional information.

[1236] 5. Delivery system: Technology for delivering the generated video to the user's device.

[1237] How it works

[1238] The user sets the desired game result or scene through the provided interface. For example, if the user sets a scene in which "Player A scores with a header," the user inputs that information into the interface.

[1239] The server receives the user's settings and stores them in a database. It then activates the emotion engine and analyzes the user's facial expressions, tone of voice, and text input to recognize their emotions. For example, if the user expresses joy, that information is recognized by the emotion engine.

[1240] Next, the server inputs a prompt sentence into the generative AI model. An example of a prompt sentence is, "Generate a scene in which player A scores a header in a soccer game. The user expresses joy." The generative AI model generates another story video based on this prompt sentence.

[1241] The generated video is then distributed to the user's device via a distribution system, allowing the user to watch the video and enjoy a video that reflects the desired match results or scenes.

[1242] Specific examples

[1243] For example, if a user wants to see a scene in which a specific player scores a header in a soccer game, the user can select "Player A scores a header" through the interface. The emotion engine will recognize the user's emotion of joy and generate a video based on that emotion.

[1244] An example of a prompt to input to a generative AI model is as follows:

[1245] "Generate a scene in which Player A scores a header in a soccer match. The user shows the emotion of joy."

[1246] By inputting this prompt into a generative AI model, a video based on the user's wishes and emotions is generated. The generated video is then delivered to the user's device via a distribution system, where the user can watch it.

[1247] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1248] Step 1:

[1249] The user sets the match results and scenes.

[1250] The user inputs the desired game result and scene through the provided interface. For example, they can set a scene in which "Player A scores with a header." The input data includes detailed information such as the participants in the game, the scorer, the timing of the goal, and the method of scoring. This allows the user to specifically set the game result and scene they want.

[1251] Step 2:

[1252] The server receives the user's settings.

[1253] The server receives the match results and scene setting information entered by the user through the interface. The received data is stored in a database. The input data is the user's setting information, and the output data is the setting information stored in the database. In this way, the user's setting information is managed within the system.

[1254] Step 3:

[1255] The server uses an emotion engine to recognize the user's emotion.

[1256] The server activates an emotion engine and recognizes emotions by analyzing the user's facial expressions, tone of voice, text input, etc. The input data is the user's facial expression data, voice data, and text data, and the output data is the recognized emotion information. For example, if the user expresses joy, that information is recognized by the emotion engine. This allows the user's emotion to be reflected in the system.

[1257] Step 4:

[1258] The server generates another story video using the generative AI model.

[1259] The server inputs a prompt sentence into the generative AI model based on the user's settings and the recognized emotion information. An example of a prompt sentence is, "Generate a scene in which player A scores a header in a soccer game. The user expresses joy." The input data is the prompt sentence, and the output data is the generated another story video. The generative AI model generates a video based on this prompt sentence. This generates a video based on the user's wishes and emotions.

[1260] Step 5:

[1261] The video generated by the server is delivered to the user's device.

[1262] The server distributes the generated "Another Story" video to the user's device. Distribution is achieved using streaming technology or by providing a download link. The input data is the generated video, and the output data is the video distributed to the user's device. This allows the user to watch a video that reflects the desired match results or scenes.

[1263] Step 6:

[1264] The user watches the video generated on the device.

[1265] Users watch the streamed video through their devices. The input data is the streamed video, and the output data is the user's viewing experience. This allows users to enjoy videos that reflect the game results and scenes they desire.

[1266] (Application example 1)

[1267] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1268] Conventional sports video distribution systems have made it difficult for users to freely set their desired game results and scenes and generate custom videos based on those settings. Furthermore, they are unable to generate videos that reflect the user's emotions, making it difficult to increase user satisfaction. Furthermore, there has been a lack of systems that can be easily used on mobile devices such as smartphones.

[1269] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for setting the game results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means including an emotion engine that recognizes the user's emotions, means for generating video based on the emotions, and means including an application to be installed on a smartphone. This enables the user to freely set the game results and scenes desired and easily generate and view custom videos based on the settings and emotions on their smartphone.

[1270] "User" refers to an individual who uses the system to set match results and scenes and watch the generated videos.

[1271] "Game result" refers to the final score or outcome of a sports game.

[1272] A "moment" refers to a specific moment or event during a match, such as a goal or a penalty.

[1273] "Means for setting" refers to an interface that allows a user to input or select the desired match results or scenes.

[1274] "Another story video" refers to a new video generated based on the user's settings that differs from the original match footage.

[1275] "Means of generation" refers to the technology and algorithms used to create Another Story videos based on user settings.

[1276] "Means of distribution" refers to the technology and services used to deliver the generated video to users.

[1277] An "emotion engine" refers to software or hardware that recognizes emotions from a user's facial expressions, tone of voice, text input, etc.

[1278] "Means for generating videos based on emotions" refers to technology that adjusts and generates video content according to the recognized emotions of a user.

[1279] "Application installed on a smartphone" refers to software that runs on a smartphone and allows users to set match results and scenes and view the generated videos.

[1280] An embodiment of the present invention will be described.

[1281] First, the user launches the application installed on their smartphone. This application provides an interface for the user to set the desired match results and scenes. The user inputs or selects the participants in the match, the match results, and important scenes (e.g., goals and penalties).

[1282] Next, the application uses the smartphone's camera and microphone to recognize the user's emotions. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, and text input. This emotion engine uses software called EmotionEngine (registered trademark), for example.

[1283] The server generates another story video based on the user's settings and the recognized emotions. The technology and algorithm for video generation uses a module called VideoGenerator (registered trademark). This module creates a new video that is different from the original video based on the match results and scenes set by the user.

[1284] The generated video is delivered from the server to the user's smartphone, where the user can watch the generated video using a module called VideoPlayer (registered trademark).

[1285] As a specific example, if a user selects "Team A wins the match" and expresses joy, VideoGenerator (registered trademark) will generate a highlight video that highlights the scenes where Team A wins. This video will be delivered to the user's smartphone and played on VideoPlayer (registered trademark).

[1286] An example of a prompt for a generative AI model is:

[1287] Generate a custom sports highlight video based on your emotions by setting the desired game results and scenes. User settings include:

[1288] Team 1: Team A

[1289] Team 2: Team B

[1290] Desired outcome: Team A wins

[1291] Key moments: goals, penalties, free kicks

[1292] The user's emotion is "joy." Generate a custom highlight video based on this setting and emotion.

[1293] In this way, users can freely set their desired match results and scenes, and easily generate and watch custom videos based on those settings and emotions on their smartphones.

[1294] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1295] Step 1:

[1296] A user launches an application installed on a smartphone. The application provides an interface for the user to set desired match results and scenes. The user inputs or selects the participants in the match, the match results, and key scenes. The input data includes the team name, desired results, and key scenes. The output is the user's setting information.

[1297] Step 2:

[1298] The device uses the smartphone's camera and microphone to capture the user's facial expressions and tone of voice. An emotion engine (e.g., EmotionEngine®) receives this data as input and recognizes the user's emotions. The input data includes facial image data and voice data. The output is recognized emotion information.

[1299] Step 3:

[1300] The server receives the user's settings and the recognized emotion information and generates another story video. The technology and algorithm for video generation uses a module called VideoGenerator (registered trademark). The input data includes the user's settings and emotion information. The output is the generated custom video data.

[1301] Step 4:

[1302] The server distributes the generated custom video data to the user's smartphone. The distribution method uses data transfer via the Internet. The input data includes the generated custom video data. The output is the video data sent to the user's smartphone.

[1303] Step 5:

[1304] The terminal uses a module called VideoPlayer (registered trademark) on the smartphone to play the generated custom video. The user can watch the video on the smartphone screen. The input data includes the delivered custom video data. The output is the video played for the user to watch.

[1305] In this way, users can freely set their desired match results and scenes, and easily generate and watch custom videos based on those settings and emotions on their smartphones.

[1306] Example 2

[1307] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1308] Conventional video generation systems have had difficulty generating original videos based on specific scenes or emotions desired by users. They also lacked a means to extract specific scenes from the original video and generate a new, alternate story video based on the user's settings. Furthermore, there was also a lack of a means to quickly and efficiently provide the generated video to users.

[1309] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for inputting setting information based on scenes and emotions desired by the user, a means for receiving the setting information and analyzing the original video data to extract necessary scenes, a means for generating a new another story video by combining the extracted scenes, and a means for transmitting the generated video to the user's terminal. This makes it possible to generate an original video based on specific scenes and emotions desired by the user and provide it quickly and efficiently.

[1310] A "user" is an individual or group that uses the system to generate videos based on specific scenes or emotions.

[1311] "Setting information" is data that includes information about the scene and emotion desired by the user.

[1312] "Original video data" refers to a video file that is the basis for extracting a scene that the user desires.

[1313] "Analysis" is the process of identifying and extracting specific scenes and elements from the original video data.

[1314] A "scene" is a specific moment in a video or a portion of a continuous video.

[1315] "Another story video" is a new video generated by combining scenes extracted from the original video data.

[1316] "Emotion data" is information that indicates the user's emotional state, and is data obtained from user input or biometric sensors.

[1317] An "original scene" is a scene newly generated based on the user's emotional data.

[1318] "Terminal" means an electronic device that a user uses to access the system.

[1319] "Sending" is the process of transferring the generated video to the user's device.

[1320] This invention is a system that generates a new another story video from an original video based on a user's desired scenes and emotions, and provides the video to the user. A specific embodiment of this system will be described below.

[1321] System Overview

[1322] This system involves a series of processes: the user inputs setting information based on the scenes and emotions they desire, analyzes the original video data based on that setting information to extract the necessary scenes, combines the extracted scenes to generate a new, alternate story video, and sends the generated video to the user's device.

[1323] Hardware and software used

[1324] Server: A computer system with high-performance computing capabilities that processes video analysis and video generation.

[1325] Device: An electronic device used by a user, such as a personal computer, smartphone, or tablet.

[1326] Video analysis software: Uses libraries such as OpenCV (registered trademark) to analyze and extract specific scenes from the original video data.

[1327] Video editing software: Use tools such as FFmpeg® to combine the extracted scenes to generate a new video.

[1328] Generative AI models: Generative AI models such as GPT-4® are used to generate original scenes based on user emotion data.

[1329] Program processing

[1330] The server receives configuration information from the user, including information about specific scenes and emotions. The server loads the original video data and begins analyzing the scenes using video analysis software (e.g., OpenCV®). Specifically, the server performs facial recognition and motion analysis to identify scenes associated with specific players and emotions within the video.

[1331] The server then extracts the necessary scenes based on the analysis results. For example, to extract a scene in which a specific player scores, the server extracts the scene containing the moment that player scores from the original video. When using the emotion engine, the server selects the appropriate scene based on the user's emotional data.

[1332] The server then combines the extracted scenes to create a new, alternate story video, using video editing software to adjust the sequence of the scenes and add transitions and effects as needed.

[1333] The generated video is sent from the server to the user's device using streaming technology or file transfer protocols (e.g., HTTP, FTP). The user can then watch the video sent to their device.

[1334] Examples of specific examples and prompts

[1335] As a concrete example, consider the case where a user requests a specific soccer player to score a goal. The user requests, "I want a new video to be created by collecting the goal scenes of a specific player." The server extracts the goal scenes of that player from the original video and generates a new video using video editing software.

[1336] When using the emotion engine, the user inputs, "I'm feeling sad, so I want a sad scene generated." The server analyzes the user's emotion data and generates a sad scene using GPT-4.

[1337] Example prompt sentence:

[1338] "I want you to create a new video by collecting scoring scenes of a specific soccer player."

[1339] "I'm feeling sad, so I want a sad scene to be generated."

[1340] In this way, a system is realized in which the server, terminals, and users work together to generate another story video.

[1341] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1342] Step 1:

[1343] The user enters the configuration information.

[1344] The user inputs setting information about specific scenes and emotions through the system interface. For example, they input prompts such as "I want to collect scenes where a specific soccer player scores" or "I'm in a sad mood, so I want to generate sad scenes." The input setting information is then sent to the server.

[1345] Step 2:

[1346] The server receives the setting information and analyzes the original video data.

[1347] The server receives the configuration information sent by the user. The server then loads the original video data and begins analyzing the scenes using video analysis software (e.g., OpenCV®). Specifically, it performs facial recognition and motion analysis to identify scenes related to specific players or emotions within the video. The input is the original video data and the configuration information, and the output is the analysis results.

[1348] Step 3:

[1349] The server extracts and combines the necessary scenes.

[1350] The server extracts the necessary scenes based on the analysis results. For example, to extract a scene in which a specific player scores, the server cuts out the scene containing the moment that player scores from the original video. When using an emotion engine, the server selects the appropriate scene based on the user's emotion data. The input is the analysis results, and the output is the extracted scene.

[1351] Step 4:

[1352] The server generates a new Another Story video.

[1353] The server then combines the extracted scenes to generate a new, "Another Story" video. This process uses video editing software, which adjusts the order of the scenes and adds transitions and effects as needed. The input is the extracted scenes, and the output is the generated video.

[1354] Step 5:

[1355] The server sends the generated video to the user's device.

[1356] The server sends the generated Another Story video to the user's device using streaming technology or file transfer protocols (e.g., HTTP, FTP). The input is the generated video, and the output is the video sent to the user's device.

[1357] Step 6:

[1358] The user watches the generated video.

[1359] The user watches the video sent to the device. The user can enjoy the other story video generated by the system. The input is the video sent to the user's device, and the output is the video being watched.

[1360] In this way, the system generates a new another story video from the original video based on the user's settings and provides it to the user.

[1361] (Application example 2)

[1362] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1363] Conventional video generation systems allow users to set their desired scenes and match results, but they are unable to select scenes based on the user's emotions and generate new, alternate story videos. Furthermore, they lack a way to preview the generated videos in real time and increase user satisfaction. This limits the user's viewing experience and makes it difficult to customize the experience to meet individual needs.

[1364] 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.

[1365] In this invention, the server includes means for allowing the user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for recognizing the user's emotions, means for selecting scenes based on the recognized emotions, means for generating a new video by combining the selected scenes, and means for previewing the generated video in real time. This makes it possible to generate a new another story video according to the user's emotions and settings, allowing for an individually customized viewing experience.

[1366] "User" refers to any individual or entity that uses the System.

[1367] "Game results" refers to the final score or results in a sport, game, or other competition.

[1368] A "scene" refers to an event or situation at a specific time in a video or movie.

[1369] "Configuration" refers to the act of a user inputting desired conditions and requirements into the system.

[1370] "Original video" refers to the original video data before any editing or processing has been done.

[1371] "Another story video" refers to a video with a new story that is created based on the original video.

[1372] "Distribution" refers to the act of providing the generated video to users via communication means such as the Internet.

[1373] "Emotion" refers to the user's psychological state or mood.

[1374] "Means for recognizing emotions" refers to technology that analyzes and recognizes emotions from the user's facial expressions, voice, etc.

[1375] "Scene selection means" refers to technology that selects appropriate scenes based on the user's settings and emotions.

[1376] "Means for combining scenes to generate new videos" refers to the technology for combining selected scenes to create new videos.

[1377] "Means for previewing in real time" refers to technology that allows users to instantly view and check the generated video.

[1378] As an embodiment of the present invention, we will explain the system called Emotion-Driven Story Creator (registered trademark) as an example. This system generates new another story video based on the user's emotions and settings, and allows them to preview it in real time.

[1379] The server uses the following hardware and software:

[1380] Smartphone camera

[1381] Head-mounted display sensors

[1382] OpenCV (registered trademark) (image processing library)

[1383] EmotionRecognizer (emotion recognition library)

[1384] VideoProcessor (video processing library)

[1385] SceneGenerator (scene generation library)

[1386] The server first recognizes the user's emotions by analyzing the user's facial expressions and voice using the smartphone camera and head-mounted display sensors, and then uses an emotion recognition engine to recognize the user's emotions.

[1387] The server then selects scenes based on the user's preferences, using a video processing library to select scenes from the raw footage that match the user's preferences and recognized emotions.

[1388] The server then combines the selected scenes to generate a new video. Using the scene generation library, the server combines the selected scenes to generate a new, alternate story video.

[1389] Finally, the server previews the generated video in real time, using a video processing library to instantly display the generated video to the user, allowing them to make adjustments until they are satisfied.

[1390] As a concrete example, consider the case where a user is watching a soccer match. If the user selects "I want to see more goal scenes" and the emotion recognition engine detects "excitement" in the user's facial expression, the server will select goal scenes from the original video and combine them to generate a new video.

[1391] Examples of prompts include:

[1392] "Select a goal scene from the original footage of a soccer match and generate a new Another Story video that matches the user's excited emotions."

[1393] In this way, Emotion-Driven Story Creator(R) enables the generation of new, alternative story videos based on the user's emotions and settings, allowing for an individually customized viewing experience.

[1394] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1395] Step 1:

[1396] The server acquires the user's facial expression and voice data from the smartphone camera and head-mounted display sensor. This is the input data. The server then analyzes this data using an emotion recognition engine to recognize the user's emotions. The output is the recognized emotion data.

[1397] Step 2:

[1398] The server receives the user's desired match results and scene settings. This is the input data. The server uses a video processing library to select scenes from the raw footage that match the user's settings. The output is a list of selected scenes.

[1399] Step 3:

[1400] The server receives as input the emotion data recognized in step 1 and the list of scenes selected in step 2. Based on these data, the server generates a new Another Story video using a scene generation library. The output is the generated new video.

[1401] Step 4:

[1402] The server previews the new video generated in real time. Using a video processing library, the generated video is instantly displayed to the user, who can make adjustments until satisfied. The input is the new generated video, and the output is the preview video shown to the user.

[1403] Step 5:

[1404] If the user is satisfied with the preview video, the server stores and delivers the final Another Story video. The input is the final video that the user is satisfied with, and the output is the delivered video.

[1405] In this way, Emotion-Driven Story Creator(R) enables the generation of new, alternative story videos based on the user's emotions and settings, allowing for an individually customized viewing experience.

[1406] Example 3

[1407] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1408] Conventional video generation and distribution systems have made it difficult for users to freely set their desired game results and scenes and generate original videos based on them. They also lacked the ability to share generated videos with other users or to provide a virtual space based on the user's emotions. This limited the user experience and made it difficult to provide flexible content tailored to individual needs.

[1409] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1410] In this invention, the server includes means for allowing the user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for streaming the generated video to the user, means for the user to share the generated video with other users, means for collecting and analyzing user emotion data, and means for providing a virtual space based on the user's emotions. This allows the user to freely set desired scenes and share the generated video with other users, and further allows the user to experience a virtual space that corresponds to their emotions.

[1411] "User" means an individual or organization that uses the system to generate and distribute videos and experience virtual spaces.

[1412] "Match results and scenes" refer to specific situations or events desired by the user, based on which videos are generated.

[1413] "Means for setting" refers to the interface or function that allows the user to input or select the desired match results or scenes.

[1414] "Original footage" refers to the original video material from which the Another Story video is generated.

[1415] An "Another Story Video" is a new video with a different scenario or outcome from the original video.

[1416] "Means of generation" refers to the technology and algorithms used to generate another story video based on the match results and scenes set by the user.

[1417] "Means of distribution" refers to the technology and infrastructure used to provide the generated video to users.

[1418] "Means of streaming" refers to the technology and protocols used to deliver the generated video to users in real time.

[1419] "Means for sharing" refers to link generation and social media integration functions that allow users to share videos they create with other users.

[1420] "Emotional data" refers to information about emotions collected from users' facial expressions, voice, etc.

[1421] "Means for analysis" refers to the technology or algorithms used to analyze collected emotional data and identify the user's emotional state.

[1422] "Virtual space" refers to an imaginary environment or scenario that users can experience.

[1423] "Means of provision" refers to the technology and infrastructure for generating an appropriate virtual space based on the user's emotions and providing it to the user.

[1424] This invention is a system that allows users to set their desired game results and scenes, generate original videos based on those results, and distribute and share them. It also includes a function to provide a virtual space based on the user's emotions.

[1425] Video Creation and Distribution

[1426] Entering a prompt statement

[1427] The user inputs a prompt to the AI ​​model using a terminal. For example, if the user wants to generate a scene of "what if dinosaurs appeared in the present day," the user can input that content.

[1428] Video generation

[1429] The server receives the prompt sentence entered by the user and generates a video using a generative AI model (for example, a natural language processing model or an image generation model). The generated video is stored on the server. Specifically, models such as OpenAI's GPT-4 and DALL-E are used.

[1430] Preparing your video for streaming

[1431] The server prepares the generated video for streaming distribution using streaming technologies such as HLS (registered trademark) (HTTP Live Streaming) or DASH (registered trademark) (Dynamic Adaptive Streaming over HTTP).

[1432] Video streaming

[1433] Users access the server using devices (PCs, smartphones, tablets, etc.) and watch the generated video in real time. The server streams the video in response to user requests.

[1434] Video sharing

[1435] To share the generated video with other users, the user obtains a sharing link from the server. The user can send this link to other users via social networking sites or email. For example, a user can share a "what if" scene they generated on social networking sites and discuss it with other users.

[1436] Providing a virtual space using an emotion engine

[1437] Collecting Emotional Data

[1438] Users access the virtual space through a device, which collects emotional data such as facial expressions and voice and transmits it to a server.

[1439] Emotion analysis

[1440] The server uses an emotion engine (e.g., an emotion analysis API) to analyze the user's emotion data. Based on the analysis results, the server identifies the user's emotional state. Specifically, an emotion analysis API or the like is used.

[1441] Virtual space generation

[1442] The server generates an appropriate virtual space depending on the emotional state of the user. For example, if the user is excited, the server generates an exciting virtual space of a different league.

[1443] Providing a virtual space

[1444] Users access and experience the virtual space created through their devices, and the server provides the virtual space in response to user requests.

[1445] Examples of specific examples and prompts

[1446] Examples of video creation and sharing

[1447] 1. Enter the prompt:

[1448] A user types the prompt "What if dinosaurs appeared in the present day?" into a terminal.

[1449] 2. Video generation:

[1450] The server uses a generative AI model (e.g., DALL-E) to generate a video based on the prompt sentence.

[1451] 3. Prepare your video for streaming:

[1452] The server converts the generated video into HLS format and prepares it for streaming.

[1453] 4. Streaming Video:

[1454] The user accesses the server from a terminal and watches the generated video in real time.

[1455] 5. Share videos:

[1456] The user obtains a sharing link from the server and shares the link on Twitter.

[1457] Example prompt sentence:

[1458] Generate a scene that imagines what would happen if dinosaurs appeared in the modern world.

[1459] A concrete example of providing a virtual space using an emotion engine

[1460] 1. Collecting Emotional Data:

[1461] A user accesses the virtual space through a terminal, and the terminal collects facial expression data of the user.

[1462] 2. Emotion analysis:

[1463] The server uses an emotion engine to analyze the user's facial expression data and determine that the user is excited.

[1464] 3. Virtual space generation:

[1465] The server generates an exciting virtual space in a different league.

[1466] 4. Providing a virtual space:

[1467] Users access the virtual space generated on their devices and enjoy the experience.

[1468] In this way, the system realizes the distribution of generated videos and the provision of a virtual space based on emotions through cooperation between the server, the terminal, and the user. The flow of the specific processing in the third embodiment will be described with reference to FIG.

[1469] Step 1:

[1470] The user inputs a prompt to the AI ​​model using a device. For example, if the user wants to generate a scene such as "What if dinosaurs appeared in the present day?", the user inputs the content. The input prompt is sent from the device to the server.

[1471] Input: The prompt text entered by the user

[1472] Output: The prompt sent to the server

[1473] Step 2:

[1474] The server passes the received prompt sentence to a generative AI model. The generative AI model (for example, a natural language processing model or an image generation model) generates a video based on the prompt sentence. The generated video is stored on the server.

[1475] Input: The prompt received by the server

[1476] Output: Generated video file

[1477] Step 3:

[1478] The server prepares the generated video for streaming using a streaming technology such as HLS (registered trademark) (HTTP Live Streaming) or DASH (Dynamic Adaptive Streaming over HTTP), specifically by converting the video into an appropriate format and dividing it into segments for streaming.

[1479] Input: Generated video file

[1480] Output: Streamable video segments

[1481] Step 4:

[1482] Users access the server using their devices and watch the generated videos in real time. The server streams the videos in response to user requests. Users watch the videos through their device's browser or a dedicated app.

[1483] Input: User's streaming request

[1484] Output: Real-time streaming video

[1485] Step 5:

[1486] To share the generated video with other users, the user obtains a sharing link from the server. The server generates the sharing link and provides it to the user. The user can then send this link to other users via social networking sites or email to share it with them.

[1487] Input: User's shared link request

[1488] Output: Generated shared link

[1489] Step 6:

[1490] Users access the virtual space through their devices. The devices collect emotional data, such as facial expressions and voice, and transmit it to a server. The emotional data is collected using sensors such as cameras and microphones.

[1491] Input: User emotion data

[1492] Output: Emotion data sent to the server

[1493] Step 7:

[1494] The server uses the emotion engine to analyze the user's emotion data and identifies the user's emotional state based on the analysis result. For example, if the user is excited, the emotional state is identified.

[1495] Input: Emotion data sent to the server

[1496] Output: Parsed emotional state

[1497] Step 8:

[1498] The server generates an appropriate virtual space according to the user's emotional state. For example, if the user is excited, the server generates an exciting virtual space of a different league. The generated virtual space is stored in the server.

[1499] Input: Parsed emotional state

[1500] Output: Generated virtual space

[1501] Step 9:

[1502] Users access and experience the virtual space created through their devices. The server provides the virtual space in response to user requests. Users experience the virtual space through their device's browser or a dedicated app.

[1503] Input: User's request to access virtual space

[1504] Output: The virtual space provided

[1505] In this way, the system allows the server, terminals, and users to work together to distribute generated videos and provide a virtual space based on emotions.

[1506] (Application example 3)

[1507] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1508] Conventional video streaming systems do not allow users to set their desired game results or scenes, nor can they provide a virtual space based on the user's emotions. This makes it difficult to provide a realistic video experience that responds to the user's emotions. Furthermore, the ability to share generated videos with other users is limited, resulting in a lack of interaction between users. To solve these issues, a video generation and streaming system that responds to the user's wishes and emotions is needed.

[1509] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1510] In this invention, the server includes means for allowing the user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for recognizing the user's emotions, means for generating a virtual space based on the recognized emotions, means for compositing the generated virtual space into the video, and means for streaming the composite video. This allows the server to provide a realistic video experience according to the user's wishes and emotions, and to share the generated video with other users.

[1511] "User" means any individual or entity that uses the System.

[1512] A "match result" is the final result or score in a competition such as a sport or game.

[1513] A "scene" refers to a specific moment or scene in a video or footage.

[1514] "Setting" is the act of specifying the conditions and parameters desired by the user.

[1515] "Original video" refers to the original video data before any editing or processing is performed.

[1516] An "Another Story Video" is a new video with a different scenario or development from the original video.

[1517] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[1518] "Emotions" are psychological states such as happiness, sadness, excitement, etc. that users experience.

[1519] "Recognition" is the process by which a system detects and understands a user's emotions and behavior.

[1520] "Virtual space" is a virtual environment or world generated by a computer.

[1521] "Synthesis" is the process of combining multiple images or data into a single image.

[1522] "Streaming distribution" is a technology that transmits video data to users in real time and plays it back.

[1523] The following system configuration will be described as an embodiment of the present invention.

[1524] System Configuration

[1525] The system allows users to set their desired match results and scenes, generates a video with a different story from the original footage, and distributes the generated video. It also recognizes the user's emotions, generates a virtual space based on the recognized emotions, synthesizes the generated virtual space into the video, and distributes the synthesized video via streaming.

[1526] Hardware and software used

[1527] Hardware: Smartphone camera, display

[1528] software:

[1529] OpenCV(R): Capture and display video frames

[1530] EmotionRecognizer: Emotion recognition engine

[1531] VideoStreamingService:Video streaming service

[1532] VirtualEnvironment: Virtual Environment Generation Engine

[1533] Program processing explanation

[1534] The server provides a means for users to set their desired match results and scenes. When users set their desired match results and scenes using their smartphones, an alternative story video different from the original video is generated based on those settings. This generation process uses a generative AI model.

[1535] The generated video is then distributed using a video streaming service, allowing users to watch the video on their smartphone displays.

[1536] Furthermore, the server uses an emotion recognition engine to recognize the user's emotions. Based on the recognized emotions, a virtual environment generation engine generates a virtual space. This virtual space changes according to the user's emotions.

[1537] The generated virtual space is composited into the original video frames using OpenCV (registered trademark). The composited video is streamed in real time. Users can view the composited video on their smartphone displays.

[1538] Specific examples

[1539] As a concrete example, consider a user streaming a video of a sporting event. If the emotion engine detects that the user is excited, the virtual environment will generate a scene of an enthusiastic crowd in a sports stadium and superimpose it onto the video, giving the user a more immersive video experience.

[1540] Prompt Sentence Examples

[1541] Example prompts to input to a generative AI model:

[1542] "If the user is excited, generate a scene of an excited sports stadium crowd."

[1543] In this way, it is possible to provide a realistic video experience that matches the user's wishes and emotions, and to share the generated video with other users.

[1544] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1545] Step 1:

[1546] Users can set the desired match results and scenes using their smartphone.

[1547] Input: User's desired match results and scene settings information

[1548] Output: The configuration information is sent to the server.

[1549] Specific operation: The user opens the application on their smartphone, selects the desired match result or scene, and sends the setting information to the server.

[1550] Step 2:

[1551] The server generates another story video that is different from the original video based on the setting information.

[1552] Input: User setting information, original video data

[1553] Output: Another Story Video

[1554] Specific operation: The server uses the generative AI model to generate another story video based on the user's settings, and the generated video is stored on the server.

[1555] Step 3:

[1556] The generated another story video will be distributed using a video streaming service.

[1557] Input: Another Story video

[1558] Output: Streamed video

[1559] Specific operation: The server uses a video streaming service to deliver the generated Another Story video to the user in real time, who then watches the video on their smartphone.

[1560] Step 4:

[1561] The server recognizes the user's emotions using an emotion recognition engine.

[1562] Input: User's facial image and voice data

[1563] Output: Recognized emotion data

[1564] Specific operation: The server acquires the user's facial image and voice data through the smartphone's camera and microphone, and recognizes emotions using an emotion recognition engine. The recognized emotion data is stored on the server.

[1565] Step 5:

[1566] Based on the recognized emotions, a virtual environment generation engine generates a virtual space.

[1567] Input: Recognized emotion data

[1568] Output: Virtual space data

[1569] Specific operation: The server generates an appropriate virtual space using a virtual environment generation engine based on the recognized emotion data. The generated virtual space data is stored on the server.

[1570] Step 6:

[1571] The generated virtual space is composited onto the original video frames using OpenCV (registered trademark).

[1572] Input: Original video frames, virtual space data

[1573] Output: Composite video frames

[1574] Specific operation: The server uses OpenCV (registered trademark) to synthesize the original video frames with the generated virtual space. The synthesized video frames are stored on the server.

[1575] Step 7:

[1576] The synthesized video is streamed in real time.

[1577] Input: Synthesized video frames

[1578] Output: Streamed composite video

[1579] How it works: The server uses a video streaming service to deliver the synthesized video to the user in real time, who then watches it on their smartphone.

[1580] 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.

[1581] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[1582] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1583] 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.

[1584] [Third embodiment]

[1585] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1586] 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.

[1587] 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).

[1588] 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.

[1589] 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.

[1590] 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).

[1591] 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.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] 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.

[1596] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1597] "Example 1"

[1598] This embodiment of the present invention provides an interface that allows users to set desired game results and scenes. This interface includes items that users can set, such as the participants in the game, the game results, and the results of important scenes. For example, in a soccer game, users can set the scorer, the timing of the goal, and the method of scoring (heading, shooting, etc.).

[1599] "Example 2"

[1600] We provide a method for generating a different story video from the original video based on the user's settings. This method appropriately combines scenes from the original video to recreate the scene set by the user. For example, if the user sets a goal scene, the system searches for a scoring scene by the same player in the original video and generates a new scene based on that scene.

[1601] "Example 3"

[1602] A means for distributing the generated video is provided. This means streams the generated video to users. A function is also provided that allows users to share the video they generated with other users. For example, a user can share the "what if" scene they generated on social media and discuss the scene with other users.

[1603] The processing flow of each embodiment will be described below.

[1604] "Example 1"

[1605] Step 1: The user accesses the system and opens the interface to set the participants in the match, the match results, the results of important scenes, etc.

[1606] Step 2: The user sets the desired outcome and scene on the interface. For example, for a soccer match, the user sets the scorer, the timing of the goal, and the method of scoring (heading, shooting, etc.).

[1607] Step 3: Once the configuration is complete, the user saves the configuration and the system receives the user's settings.

[1608] "Example 2"

[1609] Step 1: The system begins the process of generating a different story video from the original video based on the user's settings.

[1610] Step 2: The system searches the source footage for footage that corresponds to the scene set by the user. For example, if the user sets a goal, the system will search the source footage for a scoring scene by the same player.

[1611] Step 3: The system generates a new scene based on the footage it finds. The generated scene recreates the scene set by the user.

[1612] "Example 3"

[1613] Step 1: The system starts the process of distributing the generated video.

[1614] Step 2: Stream the system-generated video to the user.

[1615] Step 3: Provide a function that allows users to share the videos they create with other users. For example, users can share the "what if" scenes they create on social media and discuss them with other users.

[1616] Example 1

[1617] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1618] With conventional match result and scene generation systems, it was difficult for users to set the specific match results and scenes they wanted, and the generated results often did not meet users' expectations. Furthermore, it was difficult to provide the generated results to users in real time. This led to problems such as lower user satisfaction and a decrease in the frequency of system use.

[1619] 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.

[1620] In this invention, the server includes means for allowing a user to set desired game results and scenes, means for generating prompt sentences based on the settings, means for sending the generated prompt sentences to a generative AI model, means for receiving game results and scenes returned from the generative AI model, and means for displaying the received game results and scenes to the user. This allows a user to set specific game results and scenes and receive results based on the settings in real time.

[1621] "User" refers to an individual or organization that uses the System to set match results and scenes and receive the generated results.

[1622] "Game result" refers to the final score or outcome in a sport or competition.

[1623] A "scene" refers to a specific moment or event during a game or competition.

[1624] A "prompt sentence" refers to a text-based input sentence that provides instructions to a generative AI model.

[1625] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate match results or scenes based on user input.

[1626] "Server" refers to the computer system that receives input from users, processes data, and communicates with the generative AI model.

[1627] A "means" refers to a method or device used to achieve a particular purpose.

[1628] "Interface" refers to the screens and input forms that allow users to interact with the system.

[1629] "Database" refers to an information management system for storing user input data and generated results.

[1630] "Real-time" refers to a timeframe in which a user's input is responded to immediately.

[1631] This invention is a system that allows a user to set desired game results and scenes, and generates game results and scenes using a generative AI model based on those settings, and provides them to the user. Specific embodiments of this system are described below.

[1632] Hardware and software used

[1633] Hardware:

[1634] High-performance server (e.g. general-purpose server)

[1635] The device used by the user to access the site (e.g., personal computer, smartphone)

[1636] software:

[1637] Generative AI models (e.g., general-purpose generative AI models)

[1638] Web browser (e.g., general-purpose web browser)

[1639] Database management systems (e.g., general-purpose database management systems)

[1640] System processing flow

[1641] 1. User accesses the interface:

[1642] Users access the system's interface using a web browser, which provides input forms for setting match results and scenes.

[1643] 2. User enters match settings:

[1644] The user enters information about the participants in the match, the match results, and details of important scenes (such as the scorer, the timing of the goal, and the method of scoring) into an input form on the interface.

[1645] 3. The server receives the input data:

[1646] The server receives the data entered by the user and stores it in a database for further processing.

[1647] 4. The server generates a prompt:

[1648] The server generates a prompt to send to the generative AI model based on the data entered by the user. For example, if the user enters "Team A wins 2-1," the prompt will be "Generate the results of a soccer match. The participants in the match are Team A and Team B. The result of the match is that Team A wins 2-1."

[1649] 5. The server sends a prompt to the generative AI model:

[1650] The server sends the generated prompts to the generative AI model, which then instructs the model to generate game results and scenes.

[1651] 6. Generative AI models generate game results and scenes:

[1652] The generative AI model generates match results and scenes based on prompts received from the server. The model analyzes the input information and generates results that meet the user's wishes.

[1653] 7. The server receives the generated results:

[1654] The server receives the match results and scenes returned by the generative AI model, which are then formatted for display to the user.

[1655] 8. The server displays the results to the user:

[1656] The server sends the generated match results and scenes to the user's browser, where the user can view the results and change the settings as needed.

[1657] Examples of specific examples and prompts

[1658] Examples:

[1659] The user sets up "Team A" and "Team B" as participants in the match.

[1660] Set the result of the match as "Team A wins 2-1."

[1661] The key scenes are set as follows: "The scorers are Team A's Player X and Player Y, the timing of the goals is 20 minutes into the first half and 75 minutes into the second half, and the scoring methods are shots and headers."

[1662] Example prompt sentence:

[1663] Generate the results of a soccer match. The participants in the match are Team A and Team B. Team A wins 2-1. The scorers are Player X and Player Y of Team A. The goals are scored at the 20th minute of the first half and the 75th minute of the second half. The methods of scoring are shots and headers.

[1664] In this way, users can set specific match results or scenes and receive real-time results based on those settings.

[1665] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1666] Step 1:

[1667] The user accesses the interface.

[1668] A user accesses the system's interface using a web browser. As input, the user enters the system's URL into the browser. As output, the interface is displayed. Specifically, the user opens a web browser such as Google Chrome® and enters the system's URL to access the interface.

[1669] Step 2:

[1670] The user enters the match settings.

[1671] The user enters the participants of the match, the match results, and details of important scenes (such as the scorers, the timing of the goals, and the method of scoring) into an input form on the interface. As input, the user enters detailed information about the match. As output, the entered data is displayed on the interface. In concrete terms, the user uses text boxes and drop-down menus to enter detailed information about the match.

[1672] Step 3:

[1673] The server receives the input data.

[1674] The server receives the data entered by the user and stores it in a database. As input, the match details entered by the user are sent to the server. As output, data stored in the database is generated. Specifically, the server receives an HTTP request and stores the data in a MySQL database.

[1675] Step 4:

[1676] The server generates a prompt.

[1677] The server generates a prompt sentence to send to the generative AI model based on the data entered by the user. The match details stored in the database are used as input. The generated prompt sentence is obtained as output. Specifically, the server uses a Python script to generate the prompt sentence based on the data entered by the user.

[1678] Step 5:

[1679] The server sends a prompt to the generative AI model.

[1680] The server sends the generated prompt sentence to the generative AI model. The generated prompt sentence is used as input. The prompt sentence is sent to the generative AI model as output. Specifically, the server sends the prompt sentence to the generative AI model via an HTTP request.

[1681] Step 6:

[1682] Generative AI models generate match results and scenes.

[1683] The generative AI model generates match results and scenes based on prompts received from the server. The prompts are used as input. The generated match results and scenes are obtained as output. Specifically, the generative AI model analyzes the prompts and generates match results and scenes that meet the user's wishes.

[1684] Step 7:

[1685] The server receives the generated results.

[1686] The server receives the match results and scenes returned from the generative AI model. The output from the generative AI model is used as input. The received match results and scenes are obtained as output. Specifically, the server receives the JSON format data returned from the generative AI model and formats it into HTML.

[1687] Step 8:

[1688] The server displays the results to the user.

[1689] The server sends the generated match results and scenes to the user's browser. As input, the formatted match results and scenes are used. As output, the results are displayed in the user's browser. In concrete terms, the server sends the formatted data to the user's browser as an HTTP response, and the user sees the results on the interface.

[1690] (Application example 1)

[1691] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1692] Conventional sports game video distribution systems make it difficult for users to freely set specific game results or scenes they want and watch customized videos based on those settings. Furthermore, the lack of technology to generate videos in real time based on user-defined scenes hinders user satisfaction. Furthermore, there is a lack of a means to efficiently distribute the generated videos.

[1693] 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.

[1694] In this invention, the server includes means for setting the match results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating match highlight text using a generative AI model, and means for editing the video based on the generated text. This allows the user to freely set the specific match results and scenes desired, generate customized videos based on the settings in real time, and distribute them efficiently.

[1695] "User" refers to an individual or organization that uses the system to set match results and scenes.

[1696] "Game result" refers to the final outcome of a sports game, such as the score or victory or defeat.

[1697] A "scene" refers to a specific moment or event during a match.

[1698] "Setting" refers to the act of the user inputting the desired match results and scenes into the system.

[1699] "Original footage" refers to footage of an actual match.

[1700] "Another story video" refers to a new video that differs from the original footage and is generated based on the match results and scenes set by the user.

[1701] "Generative AI model" refers to an algorithm or program that uses artificial intelligence technology to generate text or video.

[1702] "Highlight text" refers to written descriptions of important scenes and events in a match.

[1703] "Video editing" refers to the act of processing and editing video based on the generated text.

[1704] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[1705] The system for implementing this invention allows users to set desired game results and scenes, and then generates and distributes customized videos based on those settings. A specific embodiment of this system is described below.

[1706] System Configuration

[1707] The system consists of the following main components:

[1708] 1. User device: A device that provides an interface for users to set game results and scenes. This includes smartphones, tablets, and PCs.

[1709] 2. Server: A central processing unit that receives user settings, generates highlight text using generative AI models, and edits and generates videos.

[1710] 3. Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate text based on game results and scenes set by the user.

[1711] 4. Video editing software: Software for editing videos based on the generated text, for example using libraries such as OpenCV (registered trademark).

[1712] 5. Distribution server: A server for distributing the generated video to users.

[1713] Processing flow

[1714] 1. User settings: The user inputs the desired match results and scenes from the user's device. For example, the user can set "Scorer: Tanaka, Score timing: 20 minutes into the first half, Score method: Heading."

[1715] 2. Prompt generation: The server generates a prompt based on the user's settings. For example, it generates a prompt such as, "Please describe the scene in a soccer game where Tanaka scores a header in the 20th minute of the first half."

[1716] 3. Highlight text generation: Using a generative AI model, highlight text is generated based on the prompt sentence.

[1717] 4. Video editing: Based on the generated highlight text, another story video is created from the original footage using video editing software.

[1718] 5. Video distribution: The generated video is provided to the user through a distribution server.

[1719] Specific examples

[1720] For example, if the user sets the scene where Tanaka scores with a header in the 20th minute of the first half, the following prompt will be generated:

[1721] Describe a scene in a soccer match where Tanaka scores a header in the 20th minute of the first half.

[1722] By inputting this prompt into a generative AI model, text for the desired game scene is generated, and a highlight video is created based on that text.

[1723] Hardware and software used

[1724] Generative AI model: GPT-3 (registered trademark) from OpenAI (registered trademark)

[1725] Video editing software: OpenCV (registered trademark)

[1726] User devices: smartphones, tablets, computers

[1727] Server: High-performance central processing unit (equipped with CPU and GPU)

[1728] In this way, users can freely set the specific match results or scenes they want, and customized videos based on those settings can be generated in real time and distributed efficiently.

[1729] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1730] Step 1:

[1731] The user uses the device to set the desired match results and scenes.

[1732] Input: Match results and scene setting information entered by the user into the device (e.g., "Scorer: Tanaka, Score timing: 20 minutes into the first half, Score method: Header").

[1733] Output: The configuration information is sent to the server.

[1734] Specific operation: The user inputs the match results and scenes through the terminal interface and sends the setting information to the server.

[1735] Step 2:

[1736] The server receives the user's configuration information and generates a prompt.

[1737] Input: Configuration information submitted by the user.

[1738] Output: The generated prompt sentence (e.g., "Please describe a scene in a soccer game where Tanaka scores a header in the 20th minute of the first half.").

[1739] Specific operation: The server analyzes the configuration information and generates a prompt sentence to input into the generative AI model.

[1740] Step 3:

[1741] The server uses a generative AI model to generate highlighted text based on the prompt.

[1742] Input: The generated prompt statement.

[1743] Output: The generated highlighted text.

[1744] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3) and obtains the highlighted text from the model.

[1745] Step 4:

[1746] The server generates another story video using video editing software based on the generated highlight text.

[1747] Input: The generated highlighted text.

[1748] Output: Generated Another Story video.

[1749] Specific operation: The server uses video editing software (e.g., OpenCV (registered trademark)) to generate another story video from the original video based on the highlight text.

[1750] Step 5:

[1751] The server provides the generated Another Story video to the user through a distribution server.

[1752] Input: Generated Another Story video.

[1753] Output: A video file that can be played on the user's device.

[1754] Specific operation: The server uploads the generated video to the distribution server so that the user can watch it on their device.

[1755] Example 2

[1756] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1757] With conventional video generation systems, it was difficult to generate another story video that reflected specific scenes or match results desired by the user. In addition, the process of extracting relevant scenes from the original video and generating a new video based on the user's settings was complicated and inefficient. Furthermore, there was a lack of a way to quickly provide the generated video to the user.

[1758] 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.

[1759] In this invention, the server includes means for setting the game results and scenes desired by the user, means for generating another story video that differs from the original video based on the settings, means for distributing the generated video, means for analyzing the user's setting conditions, means for searching the original video database and extracting relevant scenes, means for generating a new video using a generative AI model, and means for displaying the generated video to the user. This makes it possible to efficiently generate and quickly provide another story video that reflects the specific scenes and game results desired by the user.

[1760] "User" refers to an individual or organization that uses the system to set match results and scenes and generate another story video.

[1761] A "means for setting game results or scenes" is a device or software that provides an interface or functionality for a user to input or select a particular game result or scene desired.

[1762] "Another Story Video" is a new video generated according to the user's settings based on scenes extracted from the original video.

[1763] "Generating means" refers to a device or software that extracts relevant scenes from the source video based on the user's settings and creates a new video using a generative AI model.

[1764] "Means for providing distribution" refers to a device or software for transmitting the generated Another Story video to users and making it viewable.

[1765] "Means for analyzing" refers to a device or software that understands the settings entered or selected by the user and performs appropriate processing.

[1766] The "means for searching and extracting relevant scenes" refers to a device or software that searches the original video database to find and extract scenes that meet the user's set conditions.

[1767] A "generative AI model" is a model for generating new videos using artificial intelligence technology, including, for example, natural language processing and video generation technology.

[1768] "Displaying means" refers to a device or software for displaying the generated Another Story video on the user's terminal.

[1769] This invention relates to a system that allows a user to set a desired game result or scene, and based on that, generates a different story video from the original video, and distributes it. Specific embodiments of this system are described below.

[1770] First, the user inputs the conditions for the Another Story video they want to generate through the device interface. For example, they might input, "I want a video of Player A's scoring scenes." This input is done using the device's input form and selection menu.

[1771] Next, the device receives the user's input and sends the request to the server. The request includes the conditions set by the user. The server analyzes the received request and understands the conditions the user is looking for. For example, it analyzes the condition "collect scenes of player A scoring."

[1772] The server searches a database containing the original footage to find scenes that match the criteria set by the user. This search is performed using video analysis software (e.g., OpenCV). The server then extracts the relevant scenes from the search results. For example, it extracts all scenes in which player A scores.

[1773] The server then uses a generative AI model (e.g., GPT-4) to generate a new, alternative story video based on the extracted scenes. This process also involves video editing software. The generative AI model combines scenes based on the user's settings to generate a new video.

[1774] The generated video is sent from the server to the device using a high-speed data transfer protocol (e.g. HTTP / 2). The device then displays the received video to the user. The user can then watch the generated Another Story video on the device screen.

[1775] For example, if a user requests "I want a video of player A scoring," the following prompt might be used:

[1776] "Generate a video of player A scoring."

[1777] In this way, different, alternative story videos are generated from the original footage based on user requests and quickly provided. This system allows users to efficiently generate and watch videos that reflect specific scenes or game results they desire.

[1778] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1779] Step 1:

[1780] The user enters a request.

[1781] The user inputs the conditions for the Another Story video they want to generate through the device interface. For example, they might input, "I want a video of Player A's scoring scenes." The input conditions are saved in the device's input form.

[1782] Step 2:

[1783] The device sends a request to the server.

[1784] The terminal receives the user's input and sends the request to the server. The request includes the conditions set by the user. The input data is sent to the server as an HTTP request.

[1785] Step 3:

[1786] The server parses the request.

[1787] The server analyzes the received request and understands the conditions the user is looking for. For example, it analyzes the condition "collect scenes of player A scoring." The analysis results are stored in an internal data structure.

[1788] Step 4:

[1789] The server searches the original video database.

[1790] The server searches the database where the original video is stored to find scenes that match the conditions set by the user. This search is performed using video analysis software (e.g., OpenCV (registered trademark)). The input is the analysis results, and the output is a list of matching scenes.

[1791] Step 5:

[1792] The server extracts the relevant scenes.

[1793] The server extracts relevant scenes from the search results. For example, it extracts all scenes in which player A scores. The input is the search results, and the output is the data of the extracted scenes.

[1794] Step 6:

[1795] The server uses the generative AI model to generate new videos.

[1796] The server generates a new Another Story video using a generative AI model (e.g., GPT-4 (registered trademark)) based on the extracted scenes. This process also uses video editing software. The input is the extracted scene data, and the output is the generated video.

[1797] Step 7:

[1798] The video generated by the server is sent to the terminal.

[1799] The server sends the generated video to the device using a high-speed data transfer protocol (e.g., HTTP / 2). The input is the generated video, and the output is the data transfer to the device.

[1800] Step 8:

[1801] The terminal displays the generated video to the user.

[1802] The device displays the received video to the user, who can then watch the generated Another Story video on the device screen. The input is the video sent from the server, and the output is the user's viewing experience.

[1803] (Application example 2)

[1804] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1805] Conventional video generation systems have had difficulty extracting specific scenes desired by users from source video and generating them as new videos. Furthermore, they lacked a means to efficiently detect user-specified scenes, connect them, and generate new videos, making it impossible to provide videos customized to meet user needs. This resulted in lower user satisfaction and reduced value for content distribution services.

[1806] 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.

[1807] In this invention, the server includes means for setting the match results and scenes desired by the user, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for detecting scenes specified by the user from the original video, and means for generating a new video by linking the detected scenes. This makes it possible to efficiently extract specific scenes desired by the user and generate and distribute customized videos.

[1808] "User" means an individual or entity that uses the System to generate and view customized videos by setting specific match results or scenes.

[1809] "Game results" refers to the results of sports or competitions, such as scores or wins and losses.

[1810] A "scene" refers to a specific moment in a video or a portion of a continuous sequence of images.

[1811] "Setting" refers to the act of the user inputting the desired match results and scenes into the system.

[1812] "Original video" refers to original video data that has not been edited or processed.

[1813] "Another story video" refers to a new video generated from the original video based on the user's settings.

[1814] "Generation" refers to the process of creating new video from original footage.

[1815] "Distribution" refers to the act of providing the generated video to users via the Internet or other means.

[1816] "Detection" refers to the process of finding the scene specified by the user from the original video.

[1817] "Concatenation" refers to the act of connecting detected scenes in order to compile them into a single video.

[1818] The system for implementing this invention allows users to set their desired game results and scenes, generates another story video from the original video based on those settings, and distributes the generated video. Specific embodiments are described below.

[1819] System configuration

[1820] The system consists of the following main components:

[1821] 1. User device: A device such as a smartphone or tablet that the user uses to set up a scene.

[1822] 2. Server: A central processing unit for video generation and distribution.

[1823] 3. Database: Storage for saving original footage and generated videos.

[1824] Hardware and software used

[1825] Hardware: Smartphones, tablets, servers, storage devices

[1826] Software: Python (registered trademark), OpenCV (registered trademark) (image processing library), MoviePy (registered trademark) (video editing library)

[1827] Processing flow

[1828] 1. User device: The user uses a smartphone or tablet to set the desired game results and scenes, for example, by entering a prompt such as "Please create a highlight video of a specific player's scoring scenes."

[1829] 2. Server: Based on the user's settings, the server detects the specified scenes from the original video. It uses OpenCV (registered trademark) to analyze the video frame by frame and finds the scenes specified by the user.

[1830] 3. Server: Concatenate the detected scenes to create a new video. Using MoviePy (registered trademark), the detected scenes are connected in order to create a single video.

[1831] 4. Server: The generated Another Story video is stored in a database and distributed to users.

[1832] Specific examples

[1833] If a user wants to create a highlight video of a specific soccer player's goals, they can do the following:

[1834] 1. The user opens the application on their smartphone and enters the command, "Please create a highlight video of a specific player's scoring moments."

[1835] 2. The server analyzes the original video and detects the scoring scenes of the specified player.

[1836] 3. The detected scenes are concatenated to generate a new highlight video.

[1837] 4. Deliver the generated video to the user.

[1838] Prompt Sentence Examples

[1839] "Create a highlight video from a soccer match that includes only the scoring scenes of a specific player."

[1840] In this way, users can easily create and watch customized videos containing their desired scenes.

[1841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1842] Step 1:

[1843] User device: The user uses a smartphone or tablet to set the desired game results and scenes. Specifically, the user opens the application and enters a prompt such as, "Please create a highlight video of a specific player's scoring scenes."

[1844] Input: User prompt

[1845] Output: User settings information

[1846] Step 2:

[1847] Server: Receives the user's setting information and retrieves the original video from the database.

[1848] Input: User settings, original video database

[1849] Output: Original video data

[1850] Step 3:

[1851] Server: Analyzes the original video frame by frame using OpenCV (registered trademark) and detects scenes specified by the user. Specifically, it calculates the average color and feature values ​​of the frames and finds scenes that match the conditions specified by the user.

[1852] Input: Original video data, user setting information

[1853] Output: A list of detected scenes

[1854] Step 4:

[1855] Server: Using MoviePy (registered trademark), the detected scenes are concatenated in order to generate a new video. Specifically, the detected scenes are read as clips, concatenated, and written as a single video file.

[1856] Input: A list of detected scenes

[1857] Output: Generated Another Story video

[1858] Step 5:

[1859] Server: The server stores the generated Another Story video in a database and delivers it to users. Specifically, it stores the generated video file in storage and notifies the user of its URL.

[1860] Input: Generated Another Story video

[1861] Output: Delivery URL to user

[1862] In this way, users can easily create and watch customized videos containing their desired scenes.

[1863] Example 3

[1864] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1865] While conventional video generation systems allow users to set their desired scenes and game results, they lack the ability to share the generated videos with other users. Furthermore, there are limited means for streaming the generated videos in real time, often limiting the user experience. Furthermore, the process of generating videos using generative AI models is complex, creating a need for an easy-to-use interface.

[1866] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1867] In this invention, the server includes means for allowing a user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating a video based on a prompt sentence using a generative AI model, means for streaming the generated video, and means for the user to share the generated video with other users. This allows a user to easily set desired scenes and watch and share the generated video in real time.

[1868] "User" refers to any individual or entity that uses the System to generate, view, or share videos.

[1869] "Means for setting game outcomes or scenes" refers to functionality that provides an interface for users to input or select specific scenes or results they desire.

[1870] "Means for generating another story video" refers to the function that generates a video with a new story different from the original video based on scenes and results set by the user.

[1871] "Means for distributing and providing the generated video" refers to the technology and process for distributing the generated video to users.

[1872] "Generative AI model" refers to an artificial intelligence model that generates videos based on prompts entered by users.

[1873] "Prompt" refers to a textual instruction that a user inputs to a generative AI model.

[1874] "Means for generating video" refers to the technology or process for generating video based on prompt text using a generative AI model.

[1875] "Means for streaming" refers to the technology and processes used to deliver generated video to users in real time.

[1876] "Means for sharing videos" refers to link generation and sharing functions that allow users to share videos they generate with other users.

[1877] This invention is a system that allows users to set desired scenes and game results, and streams and shares videos generated based on those settings. Specific embodiments of this system are described below.

[1878] System configuration

[1879] server

[1880] The server generates a video based on the prompt entered by the user using a generative AI model. Generative AI models include, for example, natural language processing models and image generation models. Specifically, models such as OpenAI's GPT-4 and DALL-E can be used.

[1881] The server converts the generated video into a suitable format for streaming. For example, it converts the video to MP4 format and uploads it to the streaming server. Once the upload is complete, a streaming URL is generated.

[1882] In addition, the server generates a link for users to share their videos with other users. This link can be shared via social media, email, etc.

[1883] Terminal

[1884] The terminal is responsible for sending the prompt text entered by the user to the server. When the user enters the prompt text through the terminal interface and presses the send button, the data is sent to the server. The terminal application generates an HTTP request and sends the data, including the prompt text, to the server.

[1885] The device also receives and plays streaming video from the server, allowing users to view the generated video on the device screen.

[1886] The device also provides an interface for users to share the videos they generate with other users. Users can share links to videos generated using the device via social media or email.

[1887] User

[1888] The user uses a device to create a prompt to be input to the generative AI model. For example, they can enter a prompt such as "What if dinosaurs were alive today?" When the user enters the prompt and presses the send button, the data is sent to the server.

[1889] The user watches the generated video streamed from the server. For example, if the user inputs the prompt "What if dinosaurs were alive today?", the generated video will include a scene of dinosaurs walking around a modern city.

[1890] Furthermore, users can share the generated video with other users. For example, users can share the link of the generated video on social media and discuss the scene with other users.

[1891] Specific examples

[1892] Prompt Sentence Examples

[1893] "If dinosaurs were alive today"

[1894] Operation flow

[1895] 1. The user uses the terminal to enter the prompt sentence "What if dinosaurs were alive today?" and presses the send button.

[1896] 2. The terminal sends the prompt text to the server.

[1897] 3. The server uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a video based on the prompt.

[1898] 4. The server converts the generated video into a format suitable for streaming and uploads it to the streaming server.

[1899] 5. The server provides the generated streaming URL to the user, allowing the user to watch the video.

[1900] 6. The user accesses the streaming URL through the device's browser or a dedicated application and watches the video.

[1901] 7. The user shares the link of the generated video via SNS or email, and discusses the scene with other users. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1902] Step 1:

[1903] The user enters a prompt statement.

[1904] The user inputs a prompt that describes the content of the video they want to generate through the device interface. For example, they input a prompt such as "What if dinosaurs were alive today?" The input prompt is temporarily stored in the device's memory.

[1905] Step 2:

[1906] The terminal sends the prompt to the server.

[1907] The terminal sends the prompt text entered by the user to the server. Specifically, the terminal application generates an HTTP request and sends data including the prompt text to the server's API endpoint. The input is the prompt text, and the output is a transmission completion notification to the server.

[1908] Step 3:

[1909] The server generates the video using a generative AI model.

[1910] The server inputs the received prompt sentence into a generative AI model. The generative AI model (e.g., GPT-4 (registered trademark) or DALL-E) analyzes the prompt sentence and generates appropriate scenes and characters. The input is the prompt sentence, and the output is the generated video data. Specifically, the server analyzes the prompt sentence, determines the components of the scene, and generates a video based on them.

[1911] Step 4:

[1912] The server prepares the generated video for streaming.

[1913] The server converts the generated video into a format appropriate for streaming. For example, it converts the video into MP4 format and uploads it to the streaming server. The input is the generated video data and the output is a streaming URL. Specifically, the server encodes the video and uploads it to the streaming server.

[1914] Step 5:

[1915] The server streams the video.

[1916] The server distributes the generated video to the user through the streaming server. The user can watch the video in real time through the browser on their device or a dedicated application. The input is a streaming URL, and the output is the video played on the user's device. Specifically, the server provides the streaming URL to the user, and the user accesses that URL.

[1917] Step 6:

[1918] A user watches a video.

[1919] The user watches the generated video using their device. For example, if the user inputs the prompt "What if dinosaurs were alive today?", the generated video will include a scene of dinosaurs walking through a modern city. The input is a streaming URL, and the output is the video to be watched. Specifically, the user opens a browser or dedicated application on their device and accesses the provided streaming URL.

[1920] Step 7:

[1921] A user shares a video.

[1922] Users can share the generated video with other users. Specifically, the server provides a link to the generated video, and the user shares the link via social media or email. The input is the streaming URL, and the output is the shared link. Specifically, the user copies the link of the generated video and shares it via social media or email.

[1923] (Application example 3)

[1924] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1925] While conventional video generation systems allow users to set their desired scenes and game results, they lack the means to share and discuss the generated videos with other users. Furthermore, the content of the generated videos is limited, preventing users from fully utilizing their creativity. Furthermore, there is no way to stream the generated videos in real time, limiting the user experience.

[1926] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1927] In this invention, the server includes means for allowing a user to set desired match results and scenes, means for generating another story video different from the original video based on the settings, means for distributing the generated video, means for generating video content based on prompt sentences using a generative AI model, means for streaming the generated video, and means for sharing the generated video with other users. This allows a user to freely set desired scenes, stream the generated video in real time, and share and discuss it with other users.

[1928] "User" means an individual or organization that uses the system to generate and distribute videos.

[1929] "Game results" refers to the final score or outcome in a sport, game, or other competition.

[1930] A "scene" is a part of a video or movie that shows a specific situation or situation.

[1931] "Setting" is the act of the user inputting desired conditions and parameters into the system.

[1932] "Original video" refers to the original video material that is the basis for generating the video.

[1933] "Another story video" is a newly generated video with a different storyline from the original video.

[1934] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate content based on user input.

[1935] A "prompt" is a sentence of instructions or questions that a user inputs to a generative AI model.

[1936] "Streaming distribution" is a technology that distributes generated video in real time over the Internet.

[1937] "Sharing" refers to the act of showing the created video to other users via the Internet.

[1938] The system for implementing this invention allows users to set their desired scenes and match results, generate video content based on prompts using a generative AI model, and stream the generated video for sharing with other users.

[1939] System Configuration

[1940] The system consists of the following main components:

[1941] 1. User terminal: A device used by a user to access the system, such as a smartphone or computer.

[1942] 2. Server: A central server for providing video generation, streaming, and sharing functions.

[1943] 3. Generative AI model: An artificial intelligence model that generates video content based on user prompts.

[1944] Operating procedure

[1945] 1. User terminal: The user accesses the system using a terminal and sets the desired scene and game result. For example, the user enters a prompt sentence such as "What if dinosaurs appeared in the modern world?"

[1946] 2. Server: The server sends the prompt received from the user to the generative AI model to generate the video content, which is then stored on the server.

[1947] 3. Streaming: The server streams the generated video in real time, allowing users to watch the video through their devices.

[1948] 4. Sharing function: Users can share the videos they create with other users on social media, etc. Other users can view the shared videos and comment and discuss them.

[1949] Hardware and software used

[1950] Hardware: smartphones, PCs, servers

[1951] Software: Python®, Streamlit®, OpenAI® API, MoviePy®

[1952] Specific examples

[1953] If the user wants to generate a scene in which dinosaurs appear in the present day, they would enter the following prompt:

[1954] Example prompt sentence:

[1955] If dinosaurs were to appear in the modern world, what kind of scene would unfold?

[1956] By entering this prompt, the generative AI model will generate the scene and stream it as a video, which users can then share on social media and discuss with other users.

[1957] In this way, users can freely set up the scenes they want, stream the generated videos in real time, and share and discuss them with other users.

[1958] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1959] Step 1:

[1960] The user accesses the system using a terminal and sets the desired scene and game result. Specifically, the user inputs a prompt sentence. For example, the user inputs a prompt sentence such as "What if dinosaurs appeared in the present day?" The input data is the prompt sentence, which becomes the input for the next step.

[1961] Step 2:

[1962] The terminal sends the input prompt to the server, which receives the prompt and passes it to the generative AI model. The input data is the prompt, and the output data is the prompt passed to the generative AI model.

[1963] Step 3:

[1964] The server uses a generative AI model to generate video content based on the prompt. Specifically, the generative AI model analyzes the prompt and generates corresponding video scenes. The input data is the prompt, and the output data is the generated video content.

[1965] Step 4:

[1966] The server saves the generated video content as a video file. Specifically, the generated video content is converted into a video file format and saved within the server. The input data is the generated video content, and the output data is the saved video file.

[1967] Step 5:

[1968] The server streams the stored video files in real time. Specifically, the streaming server delivers the video files to the user's device. The input data is the stored video file, and the output data is the video to be streamed.

[1969] Step 6:

[1970] Users watch the streamed video through their devices. Specifically, they play the video using their device's browser or a dedicated app. The input data is the streamed video, and the output data is the video the user watches.

[1971] Step 7:

[1972] Users can share the generated video with other users on social media platforms. Specifically, they click the share button to post a link to the video on the social media platform. The input data is the link to the generated video, and the output data is the video link shared on the social media platform.

[1973] Step 8:

[1974] Other users can watch the video through the shared video link and comment and discuss. Specifically, they click on the video link on the SNS to watch the video and post their opinions in the comments section. The input data is the video link shared on the SNS, and the output data is the comments and discussions from other users.

[1975] 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.

[1976] "Example 1"

[1977] One embodiment of the present invention provides a system including an emotion engine that recognizes a user's emotions. This system includes a means for setting a desired match result or scene for the user, a means for generating a video with a different story from the original video based on the setting, and a means for distributing the generated video. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, text input, etc., and generates a video based on the emotion. For example, if the user expresses joy, a joyful scene is generated to match that emotion.

[1978] "Example 2"

[1979] Another embodiment of the present invention provides a system in which an emotion engine generates a user's own original scene. This system allows the system to generate an original scene based on the user's emotion. For example, if the user expresses sadness, a sad scene is generated to match the emotion. In this way, various scenes can be generated according to the user's emotion.

[1980] "Example 3"

[1981] As a further embodiment of the present invention, a system is provided in which an emotion engine provides a different league or the like in a virtual space that is different from reality. This system makes it possible to provide a different league or the like in the virtual space based on the user's emotions. For example, if the user is expressing excitement, the system provides an exciting different league that matches that emotion. In this way, it is possible to provide various virtual spaces according to the user's emotions.

[1982] The processing flow of each embodiment will be described below.

[1983] "Example 1"

[1984] Step 1: The user accesses the system and sets the match results and scenes.

[1985] Step 2: The emotion engine recognizes emotions from the user's facial expressions, tone of voice, text input, etc.

[1986] Step 3: Based on the recognized emotions, another story video is generated that is different from the original video.

[1987] Step 4: The generated video is distributed to users.

[1988] "Example 2"

[1989] Step 1: The user accesses the system and sets the match results and scenes.

[1990] Step 2: The emotion engine recognizes the user's emotion.

[1991] Step 3: Generate your own original scene based on the recognized emotions.

[1992] Step 4: The generated original scene is distributed to users.

[1993] "Example 3"

[1994] Step 1: The user accesses the system and sets the match results and scenes.

[1995] Step 2: The emotion engine recognizes the user's emotion.

[1996] Step 3: Based on the recognized emotions, a different league or world from reality is provided through a virtual space.

[1997] Step 4: The virtual space provided is distributed to users.

[1998] Example 1

[1999] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2000] While conventional systems allow users to set their desired match results and scenes, they have the problem of not being able to generate videos that reflect the user's emotions. Furthermore, if the generated video does not match the user's emotions, user satisfaction may decrease. Furthermore, if the generated video is not delivered smoothly, the user experience may be impaired.

[2001] 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.

[2002] In this invention, the server includes a means for allowing the user to set desired game results and scenes, a means for generating a story video different from the original video based on the settings, a means for distributing the generated video, a means for recognizing the user's emotions, a means for generating a video based on the recognized emotions, and a means for generating a video by inputting a prompt sentence using a generative AI model. This allows for the generation of videos that reflect the user's desired game results and scenes and are based on the user's emotions. Furthermore, the smooth distribution of the generated videos improves the user experience.

[2003] "User" means an individual or organization that uses the system to set match results and scenes and view the generated videos.

[2004] "Game result" refers to the final score or outcome of a sport or competition.

[2005] A "scene" refers to a specific moment or event during a game or competition.

[2006] "Means for setting" refers to the interface or tool that allows the user to input or select the desired match results or scenes.

[2007] "Original footage" refers to footage of actual matches or competitions.

[2008] "Another Story Video" refers to a new video with different content from the original video based on the user's settings.

[2009] "Means of generation" refers to the technology and algorithms used to create new videos based on user settings.

[2010] "Means of distribution" refers to the technology and methods for transmitting the generated video to the user's device.

[2011] "Means of recognizing emotions" refers to technologies and algorithms that analyze emotions from users' facial expressions, tone of voice, text input, etc.

[2012] A "generative AI model" refers to a model that uses artificial intelligence to generate videos based on user settings and emotions.

[2013] A "prompt sentence" is an instruction sentence that is input into a generative AI model and is used to specifically specify the content of the video to be generated.

[2014] This invention is a system that allows users to set their desired game results and scenes, generate a video with a different story from the original video based on the settings, and distribute the generated video. This system includes a function to recognize the user's emotions and generate a video based on those emotions.

[2015] System configuration

[2016] The system consists of the following main components:

[2017] 1. User Interface: An interface for users to set their desired match results and scenes. This can be implemented as a web application or a mobile application.

[2018] 2. Server: Receives user settings, recognizes user emotions using an emotion engine, and generates another story video using a generative AI model.

[2019] 3. Emotion engine: Software that analyzes emotions from the user's facial expressions, tone of voice, text input, etc.

[2020] 4. Generative AI model: An artificial intelligence model that generates videos by inputting prompt sentences based on the user's settings and recognized emotional information.

[2021] 5. Delivery system: Technology for delivering the generated video to the user's device.

[2022] How it works

[2023] The user sets the desired game result or scene through the provided interface. For example, if the user sets a scene in which "Player A scores with a header," the us...

Claims

1. means for generating a prompt sentence relating to a particular situation and / or event desired by the user; A means for generating a video based on the generated prompt sentence using the generated prompt sentence and a generation AI model; means for analyzing an emotional state of a user using an emotion engine; A means for generating a virtual space based on the analyzed emotional state of the user; A means for synthesizing the generated virtual space with the video; A means for distributing and providing the video into which the virtual space is synthesized; A system including:

2. A means for obtaining a shared link; The system of claim 1 , further comprising: means for sharing the obtained shared link.

3. The system according to claim 1 , wherein the virtual space is a space showing a situation or environment in a world different from reality.

Images