System and program

Abstract

An object of the present invention is to provide a system and a program capable of reducing a communication load.SOLUTION: Each of the one or more second computers includes a second generation AI. The one or more first computers acquire generation information indicating a text to be input to the first generation AI and generation information indicating a text to be generated by the first generation AI, and transmit the generation information to the one or more second computers. The one or more second computers acquire the generation information and cause the second generator to generate the second image AI based on the generation information.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to a system and a program. [Background technology]

[0002] As an invention related to a conventional system, for example, a program described in Patent Document 1 is known. In this program, a server distributes video captured by a terminal to multiple participant terminals. This allows multiple participants to view live video from the distributor.

[0003] Incidentally, in the field of the program described in Patent Document 1, there is a system that distributes an avatar video linked to the distributor's movements. In this case, the avatar video data is transmitted from a server to a plurality of distributor terminals. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7128338 Summary of the Invention [Problem to be solved by the invention]

[0005] In such a system, there is a demand for reducing the communication load.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a system and program that can reduce the communication load. [Means for solving the problem]

[0007] The first form is A system comprising one or more first computers and one or more second computers, each of the one or more second computers includes a second generation AI; The one or more first computers Acquire generation information indicating text to be input to the first generation AI when generating the first image data, and / or acquisition information indicating text to be generated by the first generation AI when generating the first image data; transmitting the generated information to the one or more second computers; The one or more second computers: Acquire the generation information; causing the second generation AI to generate second image data based on the generation information; It is a system.

[0008] The second form is The one or more first computers inputting a first prompt into the first generating AI to generate the first image data; Obtaining a first seed value generated by the first generation AI in response to input of the first prompt; In the process of acquiring the generation information, a second seed value related to the first seed value is acquired as the generation information; the step of transmitting the generation information includes transmitting the second seed value to the one or more second computers; The one or more second computers: In the process of generating the second image data, the second generation AI is caused to generate the second image data based on a third seed value related to the second seed value. The system according to the first aspect.

[0009] The third form is a second seed value in the second generation AI corresponds to a first seed value in the first generation AI; the third seed value is the same as the second seed value; The system according to the second aspect.

[0010] The fourth form is The one or more first computers storing correspondence information indicating a correspondence between a seed value in the first generation AI and a seed value in the second generation AI; identifying the second seed value corresponding to the first seed value based on the correspondence information; The system is described in the third aspect.

[0011] The fifth form is There are a plurality of types of models of the second generation AI, the correspondence information indicates a correspondence between a seed value in the first generation AI and a seed value in the second generation AI of the plurality of types of models; The one or more first computers Acquire model information indicating a model of the second generation AI from the one or more second computers; Identifying the second seed value corresponding to the first seed value generated by the first generation AI based on the model information and the correspondence information. The system according to the fourth aspect.

[0012] The sixth form is There are multiple versions of the second generation AI, the correspondence information indicates a correspondence between a seed value in the first generation AI and a plurality of versions of a seed value in the second generation AI; The one or more first computers acquiring version information indicating a version of the second generation AI from the one or more second computers; Identifying the second seed value corresponding to the first seed value generated by the first generation AI based on the version information and the correspondence information. The system according to the fourth or fifth aspect.

[0013] The seventh form is The one or more first computers In the process of acquiring the generation information, the first prompt and the second seed value are acquired as the generation information; The one or more second computers: In the process of generating the second image data, the second generation AI is caused to generate the second image data based on the third seed value and the first prompt. The system according to any one of the second to sixth aspects.

[0014] The eighth form is The one or more second computers: storing the first prompt; In the process of generating the second image data, the second generation AI is caused to generate the second image data based on the third seed value and the first prompt. The system according to any one of the second to sixth aspects.

[0015] The ninth form is The one or more first computers Acquire motion information indicating the motion of the person; inputting the first prompt into the first generated AI; Obtaining a first seed value generated by the first generation AI in response to input of the first prompt; In the process of acquiring the generation information, a second seed value related to the first seed value is acquired as the generation information; the process of transmitting the generation information includes transmitting the operation information and the second seed value to the one or more second computers; The one or more second computers: In the process of generating the second image data, the second generation AI is caused to generate video data in which a plurality of second images indicated by the second image data are arranged in time series, based on the third seed value and the motion information. The system according to any one of the second to eighth aspects.

[0016] The tenth form is the one or more first computers include a third computer and a fourth computer; the fourth computer is equipped with the first generation AI, The third computer generating person video data showing a video of the person; acquiring motion information indicating a motion of the person included in the person video data; transmitting the operation information to the fourth computer; The fourth computer In the process of acquiring the motion information, the motion information is acquired. The system according to the ninth aspect.

[0017] The 11th form is The fourth computer obtaining a second prompt for causing the second generation AI to generate, based on the motion information, the video data representing a video of an object linked to a motion of the person; transmitting the generated information includes transmitting the second prompt to the one or more second computers; The one or more second computers: In the process of generating the second image data, the second generation AI is caused to generate the video data based on the third seed value, the action information, and the second prompt. The system according to the tenth aspect.

[0018] The 12th form is the one or more second computers further include a fifth computer and a sixth computer; The fifth computer transmitting viewer action information generated in response to a viewer's operation to the fourth computer; The fourth computer Acquire the viewer action information; obtaining a third prompt that causes a change in the object in response to the viewer action information; the step of transmitting the generated information includes transmitting the third prompt to the sixth computer; The sixth computer In the process of generating the second image data, the second generation AI is caused to generate the video data in which a change occurs in the object according to the viewer action information, based on the third prompt. The system according to the eleventh aspect.

[0019] The 13th form is A program executed on a second computer, the second computer includes a second generating AI; The program Acquire generation information transmitted from the first computer, the generation information being information indicating the text to be input to the first generation AI when generating the first image data, and / or the generation information being information indicating the text to be generated by the first generation AI when generating the first image data; generating image data by the second generation AI based on the generation information; Displaying an image based on the image data. causing the second computer to perform an operation; It is a program. [Effects of the Invention]

[0020] According to the present disclosure, the communication load can be reduced. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 is a block diagram of systems 1, 1a to 1d. [Figure 2] FIG. 2 is an explanatory diagram of the operation of the system 1. [Figure 3] FIG. 3 is an explanatory diagram of the operation of the system 1. [Figure 4] FIG. 4 is an explanatory diagram of the operation of the system 1. [Figure 5] FIG. 5 shows an image displayed on the viewer terminal 210-1. [Figure 6]FIG. 6 is a block diagram of the distributor terminal 10. [Figure 7] FIG. 7 is a block diagram of the server 110. [Figure 8] FIG. 8 is a block diagram of the viewer terminal 210-1. [Figure 9] FIG. 9 is a flowchart showing the operation of the control unit 12 of the distributor terminal 10, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-1. [Figure 10] FIG. 10 is a flowchart showing the operation of the control unit 12 of the distributor terminal 10, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-1. [Figure 11] FIG. 11 is a seed value conversion table. [Figure 12] FIG. 12 is a flowchart showing the operation of the control unit 12 of the distributor terminal 10, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-1. [Figure 13] FIG. 13 is a seed value conversion table. [Figure 14] FIG. 14 is a flowchart showing the operation of the control unit 12 of the distributor terminal 10, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-1. [Figure 15] FIG. 15 is a flowchart showing the operation of the control unit 12 of the distributor terminal 10, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-1. [Figure 16] FIG. 16 shows an image displayed on the viewer terminal 210-1. [Figure 17] FIG. 17 is a flowchart showing the operation of the control unit 212 of the viewer terminal 210-1, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-2. [Figure 18] 18 is a block diagram of the system 1e. FIG. 19 is a flowchart showing the operation of the control unit 212 of the viewer terminal 210-1 and the operation of the control unit 112 of the server 110. [Figure 19]FIG. 19 is a flowchart showing the operation of the control unit 212 of the viewer terminal 210-1 and the operation of the control unit 112 of the server 110. [Figure 20] FIG. 20 is a table showing the relationship between the first to third seed values ​​in the present disclosure and the first to third seed values ​​in the systems 1, 1a to 1b. DETAILED DESCRIPTION OF THE INVENTION

[0022] (Embodiment) A system 1 according to an embodiment of the present disclosure will be described with reference to the drawings.

[0023] [System 1 Overview] First, the overall configuration of the system 1 will be described with reference to the drawings. Figure 1 is a block diagram of the systems 1, 1a to 1d.

[0024] The system 1 shown in Fig. 1 includes a distributor terminal 10, a server 110, and viewer terminals 210-1 to 210-N, where N is a natural number. The distributor terminal 10, the server 110, and the viewer terminals 210-1 to 210-N can communicate with each other via a communication network. The network may be the Internet, an intranet, or the like.

[0025] The distributor terminal 10 is an information processing device used by a distributor of video content. The distributor terminal 10 is, for example, a smartphone, a tablet terminal, a home game console, a portable game console, a personal computer, or a standalone virtual reality (VR) head-mounted display.

[0026] The viewer terminals 210-1 to 210-N are information processing devices used by the first viewer to the Nth viewer, respectively. The viewer terminals 210-1 to 210-N are, for example, smartphones, tablet terminals, home game consoles, portable game consoles, or personal computers.

[0027] Server 110 is an information processing device used by the operator of a video distribution service. Server 110 distributes videos to viewer terminals 210-1 to 210-N. Server 110 is a computer.

[0028] [System 1 Operation Overview] Next, we will explain the outline of the operation of the system 1. Figures 2 to 4 are explanatory diagrams of the operation of the system 1. Figure 5 shows an image displayed on the viewer terminal 210-1.

[0029] In System 1, the following two actions are performed: (1) Character selection (2) Distribution of video data

[0030] (1) Character selection The character determination operation is an operation performed by the system 1 when a streamer determines a character to be used when streaming a video. Specifically, the server 110 (fourth computer) is equipped with a first generation AI. The generation AI refers to a large-scale artificial intelligence model used in the field of natural language processing (NLP). These models can understand patterns of human language by learning from large amounts of text data (web pages, books, articles, etc.) and effectively perform natural language generation (NLG) tasks.

[0031] Generative AI is used in many NLP tasks, such as generating answers to specific questions, automatic sentence generation, text summarization, translation, sentiment analysis, and image generation. It can also be used in a variety of applications, including education, entertainment, customer service, and product development. The following models exist for generative AI. In this specification, machine learning models, including large-scale language models that primarily output text information and images, are described as a type of generative AI. OpenAI GPT-4o, Sora Google Gemini Stable Diffusion Midjourney

[0032] As shown in FIG. 2, the broadcaster operates the broadcaster terminal 10 to input a first prompt P1. The first prompt P1 describes the characteristics of a character to be used as the broadcaster's avatar. In this embodiment, the first prompt P1 is text information stating, "Please create a humanoid character with the face of a Shiba Inu." However, the first prompt P1 may be text information that has been compressed, vectorized, or binarized. Like the first prompt P1, the second prompt P2 and third prompt P3, which will be described later, may also be text information or text information that has been compressed, vectorized, or binarized. In this specification, text information and text information that has been compressed, vectorized, or binarized are referred to as information indicating text. The broadcaster terminal 10 transmits the first prompt P1 to the server 110.

[0033] Next, the server 110 inputs the first prompt P1 to the first generation AI. In response, the server 110 generates a first seed value S1 when generating the first image data D1. The first generation AI then generates the first image data D1 shown in Figure 2 based on the first seed value S1 and the first prompt P1. The first image data D1 shows an image of a humanoid character with the face of a Shiba Inu.

[0034] The seed value is the initial value of the random number generator included in the first generation AI. If the seed value is different, the first generation AI will generate image data with different characters even if the same prompt is input to the first generation AI. In other words, if the seed value is not changed, it is possible to prevent the character of the image data generated by the first generation AI from changing. In this embodiment, the first generation AI generates the first seed value S1 as “12345.” Note that for convenience of explanation, the seed value is illustrated as being only numbers, but the actual first seed value S1 and the second seed value S2 to fourth seed value S4 described later may include alphabets and symbols. Note that in this embodiment, the first seed value S1 is text information written as “12345.” However, the first seed value S1 may be text information that has been compressed, vectorized, or binarized. Like the first seed value S1, the second seed value S2 to fourth seed value S4 described later may also be text information, or may be text information that has been compressed, vectorized, or binarized.

[0035] Next, the server 110 transmits the first image data D1 and the first seed value S1 to the broadcaster terminal 10. The broadcaster terminal 10 displays the image of the character indicated by the first image data D1. This allows the broadcaster to check the image of the character. If the broadcaster likes the image of the character, the broadcaster operates the broadcaster terminal 10 to perform a character determination process. Once the character determination process has been performed, the server 110 stores the first seed value S1 and the first prompt P1.

[0036] On the other hand, if the distributor does not like the character image, the distributor has the distributor terminal 10 resend the first prompt P1 shown in FIG. 2 to the server 110. The server 110 regenerates the first image data D1 based on the first seed value S1 and the first prompt P1 that are different from "12345." The server 110 then transmits the first image data D1 and the first seed value S1 to the distributor terminal 10. In this way, the distributor can have the first generation AI repeatedly generate the first image data D1 until the distributor obtains a preferred character image.

[0037] (2) Distribution of video data The operation of distributing video data is an operation performed by the system 1 when distributing a video of a distributor's character. Specifically, the distributor shoots his / her own video by operating the distributor terminal 10. As a result, as shown in FIG. 3, the distributor terminal 10 generates person video data D0 that shows the video of the distributor (person).

[0038] Next, the broadcaster terminal 10 generates motion information A1 indicating the motion of the broadcaster (person) included in the person video data D0. More specifically, as shown in FIG. 3, the broadcaster terminal 10 extracts and analyzes the broadcaster's skeleton included in the person video data D0. Then, the broadcaster terminal 10 generates motion information A1 indicating changes in the coordinates of the broadcaster's skeleton over time. This process is realized, for example, by motion capture such as OpenPose. Then, the broadcaster terminal 10 transmits the motion information A1 to the server 110.

[0039] The server 110 stores a second prompt P2. The second prompt P2 is text information stating, "Please move the character generated using the first prompt and the first seed value according to the action of the action information." The server 110 also stores a first prompt P1 and a first seed value S1 for setting the action of the character. Therefore, as shown in FIG. 4, the server 110 transmits the action information A1, the first prompt P1, the second prompt P2, and the first seed value S1 to the viewer terminals 210-1 to 210-N.

[0040] Each of the viewer terminals 210-1 to 210-N (one or more second computers) is equipped with a second generation AI. As shown in FIG. 4, each of the viewer terminals 210-1 to 210-N causes the second generation AI to generate video data D00 based on action information A1, a first prompt P1, a second prompt P2, and a first seed value S1. As described above, the second prompt P2 states, "Please move the character generated using the first prompt and the first seed value according to the action of the action information." Therefore, in the video represented by the video data D00, the character generated using the first prompt P1 and the first seed value S1 performs the action represented by the action information A1.

[0041] The characters included in the video data D00 are substantially identical to or similar to the characters included in the first image data D1. However, the characters included in the video data D00 do not have to be completely identical to the characters included in the first image data D1, or they may be similar. This is because even if the same prompt and the same seed value are input to the first and second generation AIs, the characters included in the image data generated by the first and second generation AIs may not be completely identical to the characters included in the image data generated by the second generation AI.

[0042] Finally, each of viewer terminals 210-1 to 210-N displays the video based on video data D00, as shown in Fig. 5. This allows each of first viewer to Nth viewer to view the video of the distributor's character using viewer terminals 210-1 to 210-N.

[0043] [Structure of distributor terminal 10] The structure of the distributor terminal 10 will be described with reference to the drawings. Figure 6 is a block diagram of the distributor terminal 10.

[0044] As shown in FIG. 6, the distributor terminal 10 includes a control unit 12, a memory unit 14, a network interface 16, a camera 17, a graphics processing unit 18, a display 20, an audio processing unit 22, a speaker 24, and an operation unit 26.

[0045] The storage unit 14 stores programs and data and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and a storage (for example, a flash memory or a hard disk).

[0046] The programs include, for example, the following programs: OS (Operating System) programs - Programs for applications that process information (e.g., web browsers or target apps described below)

[0047] The data includes, for example, the following data: Databases referenced in information processing Data obtained by performing information processing (i.e., the results of performing information processing)

[0048] The control unit 12 executes the programs stored in the storage unit 14 to realize the functions of the distributor terminal 10. The control unit 12 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Gate Array)

[0049] The control unit 12 includes a data generation unit 30, an information acquisition unit 32, a communication control unit 34, and a display control unit 36 ​​as functional blocks.

[0050] The network interface 16 controls communication between the distributor terminal 10 and an external device. The external device is a server 110.

[0051] The camera 17 captures an image of the surroundings of the broadcaster terminal 10 and generates image data. In this embodiment, the camera 17 captures an image of the broadcaster.

[0052] The graphics processing unit 18 displays an image on the display 20 based on the image data generated by the control unit 12. The display 20 is a liquid crystal display or an organic EL (Electro Luminescence) display.

[0053] The audio processing unit 22 causes the speaker 24 to output sound based on the audio data generated by the control unit 12 .

[0054] The operation unit 26 generates an operation signal based on an operation by the distributor, and outputs the operation signal to the control unit 12.

[0055] [Server 110 Structure] Next, the structure of the server 110 will be described with reference to the drawings.

[0056] The server 110 is capable of communicating with the distributor terminal 10 and the viewer terminals 210-1 to 210-N. As shown in FIG.

[0057] The storage unit 114 stores programs and data and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and a storage (for example, a flash memory or a hard disk). The programs include, for example, the following programs: OS (Operating System) programs - Programs for applications that process information (e.g., web browsers or target apps described below)

[0058] The data includes, for example, the following data: Databases referenced in information processing Data obtained by performing information processing (i.e., the results of performing information processing)

[0059] The control unit 112 executes the programs stored in the storage unit 114 to realize the functions of the server 110. The control unit 112 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Gate Array)

[0060] The control unit 112 includes an information acquisition unit 120, a communication control unit 122, a prompt input unit 124, a seed value acquisition unit 126, a seed value specification unit 128, and a prompt acquisition unit 130 as functional blocks.

[0061] The network interface 116 controls communication between the server 110 and external devices. The external devices are the distributor terminal 10 and the viewer terminals 210-1 to 210-N.

[0062] [Structure of viewer terminals 210-1 to 210-N] Next, the structure of the viewer terminals 210-1 to 210-N will be described with reference to the drawings. Figure 8 is a block diagram of the viewer terminal 210-1.

[0063] As shown in FIG. 8, the viewer terminal 210-1 includes a control unit 212, a memory unit 214, a network interface 216, a camera 217, a graphics processing unit 218, a display 220, an audio processing unit 222, a speaker 224, and an operation unit 226.

[0064] The storage unit 214 stores programs and data and is, for example, a combination of a read-only memory (ROM), a random access memory (RAM), and storage (for example, a flash memory or a hard disk).

[0065] The programs include, for example, the following programs: OS (Operating System) programs - Programs for applications that process information (e.g., web browsers or target apps described below)

[0066] The data includes, for example, the following data: Databases referenced in information processing Data obtained by performing information processing (i.e., the results of performing information processing)

[0067] The control unit 212 realizes the functions of the viewer terminal 210-1 by executing the program stored in the storage unit 214. The control unit 212 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Gate Array)

[0068] The control unit 212 includes a data generation unit 230, an information acquisition unit 234, and a display control unit 236 as functional blocks.

[0069] The network interface 216 controls communication between the viewer terminal 210-1 and an external device, which is the server 110.

[0070] The camera 217 captures the surroundings of the viewer terminal 210-1 and generates image data.

[0071] The graphics processing unit 218 displays an image on the display 220 based on the image data generated by the control unit 212. The display 220 is a liquid crystal display or an organic EL (Electro Luminescence) display.

[0072] The audio processing unit 222 causes the speaker 224 to output sound based on the audio data generated by the control unit 212 .

[0073] The operation unit 226 generates an operation signal based on the operation of the first viewer, and outputs the operation signal to the control unit 212.

[0074] The structure of the viewer terminals 210-2 to 210-N is the same as that of the viewer terminal 210-1, so a description thereof will be omitted.

[0075] [System 1 operation] Next, the operation of the system 1 will be described with reference to the drawings. Figures 9 and 10 are flowcharts showing the operation of the control unit 12 of the distributor terminal 10, the operation of the control unit 112 of the server 110, and the operation of the control unit 212 of the viewer terminal 210-1.

[0076] The control unit 12 of the distributor terminal 10 reads out the programs stored in the storage unit 14, causing the distributor terminal 10 to execute the operations described below. The programs then cause the distributor terminal 10 to function as a data generation unit 30, an information acquisition unit 32, a communication control unit 34, and a display control unit 36.

[0077] The control unit 112 of the server 110 reads out the programs stored in the memory unit 114, causing the server 110 to execute the operations described below. The programs then cause the server 110 to function as an information acquisition unit 120, a communication control unit 122, a prompt input unit 124, a seed value acquisition unit 126, a seed value identification unit 128, and a prompt acquisition unit 130.

[0078] When the control unit 212 of the viewer terminal 210-1 reads out the programs stored in the memory unit 214, these programs cause the viewer terminal 210-1 to perform the operations described below. The programs then cause the viewer terminal 210-1 to function as a data generation unit 230, an information acquisition unit 234, and a display control unit 236.

[0079] (1) Character selection First, the broadcaster inputs a first prompt P1 by operating the operation unit 26 of the broadcaster terminal 10. As shown in FIG. 2, the first prompt P1 is generation information input to the first generation AI when generating the first image data D1. The first prompt P1 is information indicating text. The first prompt P1 is text information stating, "Please create a humanoid character with the face of a Shiba Inu." In this way, the first prompt P1 describes the characteristics of the character of the first image indicated by the first image data D1. In response, the control unit 12 of the broadcaster terminal 10 acquires the first prompt P1 (step S1).

[0080] Next, the control unit 12 of the distributor terminal 10 transmits the first prompt P1 to the server 110 via the network interface 16 (step S2). In response, the network interface 116 of the server 110 receives the first prompt P1 and outputs the first prompt P1 to the control unit 112. As a result, the control unit 112 (information acquisition unit 120) of the server 110 (one or more first computers) acquires the first prompt P1 (generation information) (step S11).

[0081] Next, the control unit 112 (prompt input unit 124) of the server 110 (one or more first computers) inputs a first prompt P1 to the first generation AI to generate first image data D1 (step S12). In response, the control unit 112 (seed value acquisition unit 126) of the server 110 (one or more first computers) generates a first seed value S1, which is generation information generated by the first generation AI when generating the first image data D1 (step S13). As a result, the control unit 112 (seed value acquisition unit 126) of the server 110 (one or more first computers) acquires the first seed value S1 generated by the first generation AI in response to the input of the first prompt P1. The first seed value S1 is information indicating text. In this embodiment, the first seed value S1 is "12345".

[0082] Furthermore, the control unit 112 of the server 110 (one or more first computers) causes the first generation AI to generate first image data D1 based on the first seed value S1 and the first prompt P1 (step S14). Specifically, the first generation AI analyzes the first prompt P1. At this time, the first generation AI uses natural language processing (NLP) techniques to understand the content of the text. Next, the first generation AI maps the text prompt to a learned latent space. This latent space represents patterns and features learned from the training dataset. Next, the first generation AI generates first image data D1 from the latent space based on the first prompt P1 and the first seed value S1. At this time, the first generation AI utilizes the learned features and patterns to create first image data D1 that is most suitable for the first prompt P1. The first image data D1 as described above represents an image of a humanoid character with the face of a Shiba Inu, as shown in FIG. 2.

[0083] Next, the control unit 112 (communication control unit 122) of the server 110 transmits the first image data D1 and the first seed value S1 to the distributor terminal 10 via the network interface 116 (step S15). In response, the network interface 16 of the distributor terminal 10 receives the first image data D1 and the first seed value S1, and outputs the first image data D1 and the first seed value S1 to the control unit 12. As a result, the control unit 12 of the distributor terminal 10 acquires the first image data D1 and the first seed value S1 (step S3).

[0084] Next, the control unit 12 (display control unit 36) of the broadcaster terminal 10 displays an image (first image) of the character indicated by the first image data D1 on the display 20 (step S4). Then, the control unit 12 of the broadcaster terminal 10 determines whether or not to confirm the first image data D1 (step S5). In step S5, the broadcaster operates the operation unit 26 of the broadcaster terminal 10 to input whether or not to confirm the character. If the broadcaster has input to confirm the character, the control unit 12 of the broadcaster terminal 10 determines that the first image data D1 has been confirmed. In this case, the process proceeds to step S6. If the broadcaster has not input to confirm the character, the control unit 12 of the broadcaster terminal 10 determines that the first image data D1 has not been confirmed. In this case, the process returns to step S1.

[0085] When the first image data D1 is determined, the control unit 12 of the distributor terminal 10 transmits a determination notification indicating that the first image data D1 has been determined to the server 110 via the network interface 16 (step S6). In response, the network interface 116 of the server 110 receives the determination notification and outputs the determination notification to the control unit 112. As a result, the control unit 112 of the server 110 acquires the determination notification (step S16).

[0086] The control unit 112 of the server 110 stores the first prompt P1 and the first seed value S1 acquired in steps S11 and S13 in the storage unit 114 (step S17), thereby completing the character determination operation.

[0087] (2) Distribution of video data First, the distributor operates the operation unit 26 of the distributor terminal 10 to start the video distribution. In response, the control unit 12 of the distributor terminal 10 transmits a distribution start notification indicating the start of video distribution to the server 110 via the network interface 16 (step S101). In response, the network interface 116 of the server 110 receives the distribution start notification and outputs the distribution start notification to the control unit 112. As a result, the control unit 112 of the server 110 acquires the distribution start notification (step S201).

[0088] Here, the storage unit 114 of the server 110 stores a first prompt P1, a second prompt P2, and a first seed value S1. The second prompt P2 is a prompt for causing the second generation AI to generate video data D00 showing a video of a character (object) linked to the broadcaster's (person's) movements based on the movement information A1. The second prompt P2 is information indicating text. In this embodiment, the second prompt P2 is text information stating, "Please move the character generated using the first prompt and the first seed value according to the movements of the movement information." The control unit 112 (information acquisition unit 120 and prompt acquisition unit 130) of the server 110 (one or more first computers and one or more fourth computers) reads the first prompt P1, the second prompt P2, and the first seed value S1 from the storage unit 114 to acquire the first prompt P1 (generation information), the second prompt P2, and the first seed value S1 (a second seed value related to the generation information and the first seed value) (step S202).

[0089] Next, the control unit 112 (communications control unit 122) of the server 110 (one or more first computers) transmits the first prompt P1 (generation information), the second prompt P2, and the first seed value S1 (a second seed value related to the generation information and the first seed value) to the viewer terminal 210-1 (one or more second computers) via the network interface 116 (step S203). In response, the network interface 216 of the viewer terminal 210-1 receives the first prompt P1, the second prompt P2, and the first seed value S1, and outputs the first prompt P1, the second prompt P2, and the first seed value S1 to the control unit 212. As a result, the control unit 112 (information acquisition unit 234) of the viewer terminal 210-1 (one or more second computers) acquires the first prompt P1 (generation information), the second prompt P2, and the first seed value S1 (a second seed value related to the generation information and the first seed value) (step S301).

[0090] Next, the distributor shoots his / her own video by operating the operation unit 26 of the distributor terminal 10. Specifically, the camera 17 shoots the distributor. As a result, as shown in FIG. 3, the control unit 12 (data generation unit 30) of the distributor terminal 10 (third computer) generates person video data D0 representing the video of the distributor (step S102).

[0091] Next, the control unit 12 (information acquisition unit 32) of the distributor terminal 10 (third computer) generates (acquires) motion information A1 indicating the motion of the person included in the person video data D0 (step S103). More specifically, as shown in FIG. 3, the control unit 12 of the distributor terminal 10 extracts and analyzes the distributor's skeleton included in the person video data D0. Then, the control unit 12 of the distributor terminal 10 generates motion information A1 indicating temporal changes in the coordinates of the distributor's skeleton. Then, the control unit 12 (communication control unit 34) of the distributor terminal 10 (third computer) transmits the motion information A1 to the server 110 (fourth computer) via the network interface 16 (step S104). In response, the network interface 116 of the server 110 receives the motion information A1 and outputs the motion information A1 to the control unit 112. As a result, the control unit 112 (information acquisition unit 120) of the server 110 (fourth computer) acquires the motion information A1 (step S204).

[0092] Next, control unit 112 (communications control unit 122) of server 110 (one or more first computers) transmits action information A1 to viewer terminal 210-1 (one or more second computers) via network interface 116 (step S205). In response, network interface 216 of viewer terminal 210-1 receives action information A1 and outputs it to control unit 212. As a result, control unit 212 of viewer terminal 210-1 acquires action information A1 (step S302).

[0093] Next, the control unit 212 (data generation unit 230) of the viewer terminal 210-1 (one or more second computers) causes the second generation AI to generate video data D00 (second image data) based on the action information A1, the first prompt P1 (generation information), the second prompt P2, and the first seed value S1 (a third seed value related to the second seed value, generation information), as shown in FIG. 4 (step S303). The video data D00 is data in which multiple second images indicated by the second image data D2 are arranged in chronological order. The second image data D2 is data indicating second images generated by the second generation AI based on the first prompt P1 and the first seed value S1. As described above, the second prompt P2 is text information stating, "Please move the character generated using the first prompt and the first seed value according to the actions of the action information." Therefore, in the moving image represented by the moving image data D00, the character generated using the first prompt P1 and the first seed value S1 performs the action represented by the action information A1.

[0094] Next, control unit 212 (display control unit 236) of viewer terminal 210-1 displays a video (image) on display 220 based on video data D00 (image data) (step S304), as shown in Fig. 5. This allows the first viewer to view the video of the distributor's character using viewer terminal 210-1.

[0095] Next, the control unit 12 of the distributor terminal 10 determines whether or not to end the distribution of the video (step S105). If the distribution of the video is to end, the process proceeds to step S106. If the distribution of the video is not to end, the process returns to step S102.

[0096] When the distribution of the moving image is to be ended, the control unit 12 of the distributor terminal 10 transmits a distribution end notice indicating that the distribution of the moving image is to be ended to the server 110 via the network interface 216 (step S106). In response, the network interface 116 of the server 110 receives the distribution end notice and outputs the distribution end notice to the control unit 112.

[0097] The control unit 112 of the server 110 determines whether or not a distribution end notification has been received (step S206). If the control unit 112 has received the distribution end notification, the process proceeds to step S207. If the control unit 112 has not received the distribution end notification, the process returns to step S204.

[0098] When control unit 112 acquires the distribution end notification, control unit 112 of server 110 transmits the distribution end notification to viewer terminal 210-1 via network interface 116 (step S207). In response, network interface 216 of viewer terminal 210-1 receives the distribution end notification and outputs it to control unit 212.

[0099] The control unit 212 of the viewer terminal 210-1 determines whether or not a distribution end notification has been received (step S305). If the control unit 212 has received the distribution end notification, this process ends. If the control unit 212 has not received the distribution end notification, this process returns to step S302.

[0100] Although the flowchart shown in FIG. 10 only describes the operation of the control unit 212 of the viewer terminal 210-1, the control units 212 of the viewer terminals 210-2 to 210-N also perform the same operations as the control unit 212 of the viewer terminal 210-1.

[0101] [effect] The system 1 can reduce communication load. More specifically, the control unit 112 of the server 110 acquires a first prompt P1 to be input to the first generation AI when generating the first image data D1 and / or a first seed value S1 generated by the first generation AI when generating the first image data D1. In this embodiment, the control unit 112 of the server 110 acquires the first prompt P1 to be input to the first generation AI when generating the first image data D1 and the first seed value S1 generated by the first generation AI when generating the first image data D1. The control unit 112 of the server 110 then transmits the first prompt P1 and / or the first seed value S1 to the viewer terminal 210-1. In this embodiment, the control unit 112 of the server 110 transmits the first prompt P1 and the first seed value S1 to the viewer terminal 210-1. Here, the first prompt P1 and the first seed value S1 are information indicating text having a relatively small amount of data. Therefore, the first image data D1, which has a relatively large amount of data, does not need to be transmitted from the server 110 to the viewer terminal 210-1. As a result, the system 1 can reduce the communication load.

[0102] In the system 1, the first image data D1 does not need to be transmitted from the server 110 to the viewer terminal 210-1. Therefore, the server 110 does not need to encode the video data, and the viewer terminal 210-1 does not need to decode the video data. As a result, the processing load on the server 110 is reduced.

[0103] In the system 1, the first prompt P1 and the first seed value S1 are transmitted from the server 110 to the viewer terminal 210-1, so that the viewer terminal 210-1 can generate the first image data D1. Therefore, the viewer terminal 210-1 does not need to download image data of the characters included in the first image data D1 from the server 110.

[0104] In system 1, control unit 212 of viewer terminal 210-1 can generate video data D00. More specifically, control unit 112 of server 110 acquires motion information A1 indicating a person's motion and transmits the motion information A1 to viewer terminal 210-1 via network interface 116. Based on the first seed value S1 and the motion information A1, control unit 212 of viewer terminal 210-1 causes second generation AI to generate video data D00 in which multiple second images indicated by second image data D2 are arranged in chronological order. In this way, in system 1, control unit 212 of viewer terminal 210-1 can generate video data D00 without first image data D1 being transmitted from server 110 to viewer terminal 210-1.

[0105] System 1 can also reduce the communication load for the following reason. More specifically, control unit 12 of distributor terminal 10 generates person video data D0 indicating a video of the distributor, and generates motion information A1 indicating the motion of the distributor included in person video data D0. Then, control unit 12 of distributor terminal 10 transmits motion information A1 to server 110 via network interface 116. As a result, control unit 112 of server 110 acquires motion information A1. Therefore, person video data D0, which has a relatively large amount of data, is not transmitted from distributor terminal 10 to server 110, and control unit 112 of server 110 can acquire motion information A1. As a result, system 1 can reduce the communication load.

[0106] In system 1, the communication load can also be reduced for the following reason. More specifically, the control unit 112 of the server 110 transmits the second prompt P2 to the viewer terminal 210-1 via the network interface 116. The second prompt P2 is a prompt for causing the second generation AI to generate video data D00 showing a character video linked to the distributor's action, based on the action information A1. The control unit 212 of the viewer terminal 210-1 then causes the second generation AI to generate the video data D00 based on the first seed value S1, the action information A1, and the second prompt P2. In this way, the second prompt P2, which has a relatively small amount of data, is transmitted from the server 110 to the viewer terminal 210-1, allowing the control unit 212 of the viewer terminal 210-1 to generate the video data D00. Therefore, in system 1, the communication load can be reduced.

[0107] (First Modification) The system 1a according to the first modification will be described below. Fig. 11 is a seed value conversion table.

[0108] System 1a differs from System 1 in that multiple models of second generation AI exist for each of multiple viewer terminals 210-1 to 210-N, and multiple versions of second generation AI exist. The model of the generation AI indicates the type of generation AI. Examples of generation AI models include GPT-4o, Sora, Gemini, Bard, Stable Diffusion, and midjourney. If the model of the second generation AI is different, the seed value of the second generation AI corresponding to the seed value generated by the first generation AI will be a different value.

[0109] The version of the generator AI is a number that is revised when the model of the generator AI is updated. When the version of the second generator AI changes, the seed value of the second generator AI corresponding to the seed value generated by the first generator AI changes.

[0110] Therefore, the storage unit 114 of the server 110 stores correspondence relationship information indicating the correspondence relationship between the seed value in the first generation AI and the seed value in the second generation AI. More specifically, the storage unit 114 of the server 110 stores correspondence relationship information indicating the correspondence relationship between the seed value in the first generation AI and the seed value in the second generation AI of multiple types of models, and indicating the correspondence relationship between the seed value in the first generation AI and the seed value in the second generation AI of multiple types of versions.

[0111] The seed value conversion table shown in FIG. 11 is an example of correspondence information. The second seed value S2 is a value related to the first seed value S1. Specifically, the second seed value S2 in the second generation AI corresponds to the first seed value S1 in the first generation AI. Therefore, the second image generated by the second generation AI based on the second seed value S2 and the first prompt P1 is substantially identical to or similar to the first image generated by the first generation AI based on the first seed value S1 and the first prompt P1. In the seed value conversion table shown in FIG. 11, the second seed value S2 is described for each model of the second generation AI and each version of the second generation AI.

[0112] Next, the operation of system 1a will be described with reference to Fig. 12. Fig. 12 is a flowchart showing the operation of control unit 12 of distributor terminal 10, the operation of control unit 112 of server 110, and the operation of control unit 212 of viewer terminal 210-1. Note that the operation of determining a character in system 1a is the same as the operation of determining a character in system 1, so a description thereof will be omitted.

[0113] The operation of distributing video data in system 1a will be described below. The operation of distributing video data in system 1a differs from the operation of distributing video data in system 1 in that steps S210 to S212, S311, and S312 are added. Therefore, the following description will focus on these differences.

[0114] When step S201 is completed, control unit 112 of server 110 transmits a distribution start notification to viewer terminal 210-1 via network interface 116 (step S210). In response, network interface 216 of viewer terminal 210-1 receives the distribution start notification and outputs the distribution start notification to control unit 212. As a result, control unit 212 of viewer terminal 210-1 acquires the distribution start notification (step S311).

[0115] The storage unit 214 of the viewer terminal 210-1 stores model information M and version information V. The model information M is information indicating the model of the second generated AI. The version information V is information indicating the version of the second generated AI. The control unit 212 of the viewer terminal 210-1 reads out the model information M and the version information V and transmits the model information M and the version information V to the server 110 via the network interface 216 (step S311). In response, the network interface 116 of the server 110 receives the model information M and the version information V and outputs the model information M and the version information V to the control unit 112. As a result, the control unit 112 (information acquisition unit 120) of the server 110 (one or more first computers to fourth computers) acquires the model information M and the version information V from the viewer terminal 210-1 (one or more second computers) (step S211).

[0116] Next, the control unit 112 (seed value identification unit 128) of the server 110 (one or more first computers through fourth computers) identifies a second seed value S2 corresponding to the first seed value S1 generated by the first generation AI in step S13 based on the model information M, version information V, and seed value conversion table (correspondence information) (step S212). For example, if the model of the second generation AI is generation AI X, the version of the second generation AI is ver. 2, and the first seed value S1 is "12345," the control unit 112 of the server 110 identifies the second seed value S2 as "12945." After this, the process proceeds to step S202.

[0117] The processing from step S202 onwards in the system 1a is the same as that in the system 1 except that the second seed value S2 is used instead of the first seed value S1, and therefore a description thereof will be omitted.

[0118] System 1a has the same effect as System 1.

[0119] Furthermore, in the system 1a, even if the model or version of the second generation AI changes, the control unit 212 of the viewer terminal 210-1 can generate the video data D00 appropriately.

[0120] (Second Modification) A system 1b according to the second modification will be described below. Fig. 13 is a seed value conversion table.

[0121] System 1b differs from system 1a in that the control unit 212 of the viewer terminal 210-1 specifies a third seed value S3 corresponding to the first seed value S1. Therefore, the storage unit 214 of the viewer terminal 210-1 stores the seed value conversion table shown in FIG. 13. The third seed value S3 is a value related to the first seed value S1 (second seed value). Specifically, the third seed value S3 in the second generation AI corresponds to the first seed value S1 in the first generation AI. Therefore, the second image generated by the second generation AI based on the third seed value S3 and the first prompt P1 is substantially identical to or similar to the first image generated by the first generation AI based on the first seed value S1 and the first prompt P1. In the seed value conversion table shown in FIG. 13, the third seed value S3 is described for each model of the second generation AI and each version of the second generation AI.

[0122] Next, the operation of system 1b will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the operation of control unit 12 of distributor terminal 10, the operation of control unit 112 of server 110, and the operation of control unit 212 of viewer terminal 210-1. Note that the operation of determining a character in system 1b is the same as the operation of determining a character in system 1, so a description thereof will be omitted.

[0123] The operation of distributing video data in system 1b will be described below. The operation of distributing video data in system 1b differs from the operation of distributing video data in system 1 in that step S321 is added. Therefore, the following description will focus on this difference.

[0124] After step S301 is completed, the control unit 112 of the viewer terminal 210-1 determines the third seed value S3 corresponding to the first seed value S1 (the second seed value related to the first seed value) acquired in step S301 based on the model information M, version information V, and seed value conversion table (correspondence information) (step S321). For example, if the model of the second generation AI is generation AI·X, the version of the second generation AI is ver. 2, and the first seed value S1 is "12345," the control unit 212 of the viewer terminal 210-1 determines the second seed value S2 to be "12945." The process then proceeds to step S302.

[0125] The processing from step S302 onwards in the system 1b is the same as that in the system 1 except that the third seed value S3 is used instead of the first seed value S1, and therefore a description thereof will be omitted.

[0126] System 1b has the same effect as System 1.

[0127] Furthermore, in the system 1b, even if the model or version of the second generation AI changes, the control unit 112 of the viewer terminal 210-1 can generate the video data D00 appropriately.

[0128] (Third Modification) A system 1c according to a third modified example will be described below.

[0129] System 1c differs from system 1 in that memory unit 114 of viewer terminal 210-1 (one or more second computers) stores first prompt P1 and second prompt P2. Therefore, first prompt P1 and second prompt P2 are not transmitted from server 110 to viewer terminal 210-1. Figure 15 is a flowchart showing the operation of control unit 12 of distributor terminal 10, the operation of control unit 112 of server 110, and the operation of control unit 212 of viewer terminal 210-1. Note that the operation of determining a character in system 1c is the same as the operation of determining a character in system 1, so a description thereof will be omitted.

[0130] The operation of distributing video data in system 1c will be described below. The operation of distributing video data in system 1c differs from the operation of distributing video data in system 1 in that steps S202, S203, and S301 are replaced with steps S252, S253, and S351, and that step S352 has been added. Therefore, the following description will focus on these differences.

[0131] After step S201 is completed, the control unit 112 of the server 110 reads the first seed value S1 from the storage unit 114 to obtain the first seed value S1 (step S252). The control unit 112 of the server 110 then transmits the first seed value S1 to the viewer terminal 210-1 via the network interface 116 (step S253). In response, the network interface 216 of the viewer terminal 210-1 receives the first seed value S1 and outputs the first seed value S1 to the control unit 212. As a result, the control unit 212 of the viewer terminal 210-1 obtains the first seed value S1 (step S351).

[0132] Next, the control unit 212 of the viewer terminal 210-1 acquires the first prompt P1 and the second prompt P2 by reading them from the storage unit 114 (step S352). Thereafter, the process proceeds to step S302.

[0133] The processing from step S302 onwards in the system 1c is the same as that in the system 1, and therefore a description thereof will be omitted. The system 1c achieves the same effects as the system 1.

[0134] (Fourth Modification) A system 1d according to the fourth modification will be described below. Fig. 16 shows an image displayed on the viewer terminal 210-1.

[0135] System 1d differs from System 1 in that each of the first through Nth viewers can perform a viewer action. More specifically, the first through Nth viewers can perform a viewer action while watching a video. A viewer action is an action taken by the first through Nth viewers on a video when the video is being distributed. Specific examples of viewer actions will be described below with reference to FIG. 16.

[0136] The image shown in FIG. 16 includes a heart button, a gift button, and a text input box. The heart button is called the "Like" button. The gift button is called the "Gift" button. The text input box is called the "Input" box. Viewer actions include an action in which the first through Nth viewers press the "Like" button, an action in which the first through Nth viewers press the "Gift" button, and an action in which the first through Nth viewers send a comment. When any of the first through Nth viewers presses the "Like" button, a heart button is displayed on viewer terminals 210-1 through 210-N, as shown in the image in FIG. 16. When any of the first through Nth viewers presses the "Gift" button, a gift button is displayed on viewer terminals 210-1 through 210-N, as shown in the image in FIG. 16, and a gift is given to the broadcaster from any of the first through Nth viewers. The gift is a hat. As shown in FIG. 16, an image of the character and an image of the hat are combined together to make it appear as if the character is wearing the hat. Furthermore, when any one of the first through N-th viewers inputs a comment into the input box and presses the send button, the comment is displayed on the viewer terminals 210-1 through 210-N as shown in the image in FIG.

[0137] The following describes the operation of a viewer action performed by a first viewer in system 1c. A viewer action is an action in which the first viewer presses a gift button. This action is performed in parallel with the operation of distributing video data. Figure 17 is a flowchart showing the operation of control unit 212 of viewer terminal 210-1, the operation of control unit 112 of server 110, and the operation of control unit 212 of viewer terminal 210-2.

[0138] The first viewer performs a viewer action by operating the operation unit 26 of the viewer terminal 210-1. In this embodiment, the first viewer presses the gift button displayed on the display 20. As a result, the control unit 212 of the viewer terminal 210-1 acquires viewer action information AC (step S). The viewer action information AC indicates that the first viewer is giving a hat object to the broadcaster. Then, the control unit 212 (communication control unit 122) of the viewer terminal 210-1 (fifth computer) transmits the viewer action information AC generated in response to the first viewer's operation to the server 110 (fourth computer) via the network interface 216 (step S402). In response, the network interface 116 of the server 110 receives the viewer action information AC and outputs the viewer action information AC to the control unit 112. As a result, the control unit 112 (information acquisition unit 120) of the server 110 (fourth computer) acquires the viewer action information AC (step S501).

[0139] Next, the control unit 112 (prompt acquisition unit 130) of the server 110 (fourth computer) acquires a third prompt P3 that causes the character (object) to change in accordance with the viewer action information AC (step S502). More specifically, the viewer action information AC indicates that the first viewer is giving the broadcaster a hat object. Therefore, the control unit 112 of the server 110 generates the third prompt P3, which is text information stating, "Please put a hat on the character's head," based on the viewer action information AC.

[0140] Next, control unit 112 (communications control unit 122) of server 110 (fourth computer) transmits third prompt P3 to viewer terminal 210-2 (sixth computer) via network interface 116 (step S503). In response, network interface 216 of viewer terminal 210-2 receives third prompt P3 and outputs third prompt P3 to control unit 212. As a result, control unit 212 (information acquisition unit 234) of viewer terminal 210-2 (sixth computer) acquires third prompt P3 (step S601).

[0141] Next, the control unit 212 (data generation unit 230) of the viewer terminal 210-2 (sixth computer) causes the second generation AI to generate video data D00 in which a change occurs in the character (object) according to the viewer action information AC, based on the third prompt P3 (step S602). More specifically, in step S303, the control unit 212 of the viewer terminal 210-1 causes the second generation AI to generate video data D00 based on the action information A1, the first prompt P1, the second prompt P2, and the first seed value S1, as shown in FIG. 4. The control unit 212 of the viewer terminal 210-2 performs the process of step S602 instead of step S303. Therefore, the control unit 212 of the viewer terminal 210-1 causes the second generation AI to generate video data D00 based on the action information A1, the first prompt P1, the second prompt P2, the third prompt P3, and the first seed value S1, as shown in FIG. 4. As mentioned above, the second prompt P2 states, "Please move the character generated using the first prompt and the first seed value according to the movement information." Furthermore, the third prompt P3 states, "Please put a hat on the character's head." Therefore, in the video represented by the video data D00, the character generated using the first prompt P1 and the first seed value S1 is wearing a hat and performing the movement represented by the movement information A1.

[0142] Next, control unit 212 of viewer terminal 210-2 causes display 220 to display a video (image) based on video data D00 (image data) (step S603), as shown in Fig. 16. This allows the second viewer to view the video of the character wearing a hat using viewer terminal 210-1.

[0143] In system 1d, server 110 generates third prompt P3 based on viewer action information AC. Server 110 then transmits third prompt P3 to viewer terminal 210-2. This allows viewer terminal 210-2 to cause second generation AI to generate video data D00 in which a change occurs in an object in response to the viewer action. Therefore, system 1d does not transmit image data of the hat, which has a relatively large amount of data, thereby reducing the communication load.

[0144] (Fifth Modification) A system 1e according to the fifth modified example will be described below. Fig. 18 is a block diagram of the system 1e. Fig. 19 is a flowchart showing the operation of the control unit 212 of the viewer terminal 210-1 and the operation of the control unit 112 of the server 110.

[0145] As shown in Fig. 18, system 1d differs from system 1 in that it does not include a distributor terminal 10. That is, instead of distributing live video of the distributor, pre-recorded video is distributed. The memory unit 114 of server 110 stores a first prompt P1, a second prompt P2, a first seed value S1 (a second seed value related to the first seed value), and operation information A1.

[0146] The operation of video data distribution will be described below with reference to Fig. 19. Control unit 112 of server 110 transmits a distribution start notification indicating the start of video distribution to viewer terminal 210-1 via network interface 16 (step S261). In response, network interface 216 of viewer terminal 210-1 receives the distribution start notification and outputs the distribution start notification to control unit 212. As a result, control unit 212 of viewer terminal 210-1 acquires the distribution start notification (step S361).

[0147] As described above, the memory unit 114 of the server 110 stores the first prompt P1, the second prompt P2, and the first seed value S1. The second prompt P2 is a prompt for causing the second generation AI to generate video data D00 showing a video of an object linked to the broadcaster's (person's) movement based on the movement information A1. The second prompt P2 is information indicating text. In this embodiment, the second prompt P2 is text information stating, "Please move the character generated using the first prompt and the first seed value according to the movement in the movement information." The control unit 112 (information acquisition unit 120 and prompt acquisition unit 130) of the server 110 (one or more first computers and one or more fourth computers) reads the first prompt P1, the second prompt P2, and the first seed value S1 from the memory unit 114 to acquire the first prompt P1, the second prompt P2, and the first seed value S1 (a second seed value related to the first seed value) (step S202).

[0148] Next, the control unit 112 (communications control unit 122) of the server 110 (one or more first computers) transmits the first prompt P1 (generation information), the second prompt P2, and the first seed value S1 (a second seed value related to the first seed value) to the viewer terminal 210-1 via the network interface 116 (step S203). In response, the network interface 216 of the viewer terminal 210-1 receives the first prompt P1, the second prompt P2, and the first seed value S1, and outputs the first prompt P1, the second prompt P2, and the first seed value S1 to the control unit 212. As a result, the control unit 212 (information acquisition unit 234) of the viewer terminal 210-1 acquires the first prompt P1 (generation information), the second prompt P2, and the first seed value S1 (a second seed value related to the first seed value) (step S301).

[0149] Next, as described above, the operation information A1 is stored in the storage unit 114 of the server 110. The control unit 112 of the server 110 reads out the operation information A1 from the storage unit 114, thereby acquiring the operation information A1 (step S204).

[0150] Next, control unit 112 of server 110 transmits motion information A1 to viewer terminal 210-1 via network interface 116 (step S205). In response, network interface 216 of viewer terminal 210-1 receives motion information A1 and outputs it to control unit 212. As a result, control unit 212 of viewer terminal 210-1 acquires motion information A1 (step S302). Thereafter, the process proceeds to step S303.

[0151] The process from step S303 onwards in the system 1e is the same as the process from step S303 onwards in the system 1, so a description thereof will be omitted.

[0152] System 1e can achieve the same effect as System 1.

[0153] (supplement) The relationship between the first to third seed values ​​in this disclosure and the first to third seed values ​​in the systems 1, 1a to 1b will be described below with reference to the drawings. Figure 20 is a table showing the relationship between the first to third seed values ​​in this disclosure and the first to third seed values ​​in the systems 1, 1a to 1b.

[0154] In the present disclosure, one or more first computers acquire a first seed value and acquire a second seed value related to the first seed value, and then the one or more first computers transmit the second seed value to one or more second computers, while the one or more second computers acquire the second seed value and generate second image data based on a third seed value related to the second seed value.

[0155] Here, the relationship between the first seed value S1 to the third seed value S3 in each embodiment and the above-mentioned first seed value to third seed value will be summarized and explained.

[0156] In system 1, server 110 (one or more first computers) generates (acquires) a first seed value S1 and transmits the first seed value S1 to viewer terminal 210-1 (one or more second computers). Viewer terminal 210-1 (one or more second computers) receives (acquires) the first seed value S1 and generates second image data D2 based on the first seed value S1. Thus, in system 1, the second seed value is the same as the first seed value, and the third seed value is the same as the second seed value. This is because, in system 1, the model and version of the second generation AI are the same as the model and version of the first generation AI.

[0157] In system 1a, server 110 (one or more first computers) generates (acquires) a first seed value S1 and acquires a second seed value S2 related to the first seed value S1. Then, server 110 (one or more first computers) transmits the second seed value S2 to viewer terminal 210-1 (one or more second computers). Viewer terminal 210-1 (one or more second computers) receives the second seed value S2 and generates second image data D2 based on the second seed value S2. Thus, in system 1a, the second seed value S2 in the second generation AI corresponds to the first seed value S1 in the first generation AI. And the third seed value is the same value as the second seed value. This is because, in system 1a, the model and version of the second generation AI are different from the model and version of the first generation AI.

[0158] In system 1b, server 110 (one or more first computers) generates (obtains) a first seed value S1 and transmits the first seed value S1 to viewer terminal 210-1 (one or more second computers). Viewer terminal 210-1 (one or more second computers) receives the first seed value S1 and obtains a third seed value S3 related to the first seed value S1. Viewer terminal 210-1 (one or more second computers) generates second image data D2 based on the third seed value S3. Thus, in system 1b, the third seed value S3 in the second generation AI corresponds to the first seed value S1 in the first generation AI. The second seed value is the same value as the first seed value. This is because, in system 1, the model and version of the second generation AI are different from the model and version of the first generation AI.

[0159] (Other embodiments) The various control means and processing procedures described in the above embodiments are merely examples and are not intended to limit the scope of the present invention, its applications, or its uses. The various control means and processing procedures can be appropriately modified in design within the scope that does not change the gist of the present invention.

[0160] The configurations of the systems 1, 1a to 1e may be combined in any manner.

[0161] The server 110 of the systems 1, 1a to 1e may include a plurality of computers.

[0162] In the systems 1, 1a to 1e, the generation information transmitted from the server 110 to the viewer terminal 210-1 does not have to be the first seed value S1 or the second seed value S2. The generation information may be information generated by the first generation AI when generating the first image data D1, and may include information equivalent to the seed value.

[0163] In the systems 1, 1a to 1e, the first prompt P1 may include information corresponding to the first seed value S1 or the second seed value S2. In this case, the first seed value S1 or the second seed value S2 is not transmitted from the server 110 to the viewer terminal 210-1, but the first prompt P1 is transmitted from the server 110 to the viewer terminal 210-1.

[0164] In the systems 1, 1a to 1e, the server 110 is described as having the first generation AI. However, if the distributor terminal 10 has the first generation AI, for example, the functions of the present invention may be achieved using the first generation AI provided in the distributor terminal 10 instead of the server 110. In this case, the server 110 may not have the first generation AI, and the distributor terminal 10 may have the first generation AI. Also, a computer provided separately from the systems 1, 1a to 1e may have the first generation AI.

[0165] The distributor terminal 10 transmits the first prompt P1 to the server 110, and the server 110 transmits the first prompt P1 to the viewer terminal 210-1. However, the distributor terminal 10 may transmit original image data that is the basis for the first image data D1 to the server 110 instead of the first prompt P1, and the server 110 may transmit the original image data that is the basis for the first image data D1 together with the first seed value S1 to the viewer terminal 210-1 instead of the first prompt P1. Alternatively, the distributor terminal 10 may transmit the first prompt P1 and the original image data that is the basis for the first image data D1 to the server 110, and the server 110 may transmit the original image data that is the basis for the first prompt P1 and the first image data D1 to the viewer terminal 210-1. The viewer terminal 210-1 generates video data D00 based on the first prompt P1, the second prompt P2, and the original image data that is the basis for the first image data D1.

[0166] The second prompt may be a command statement for instructing the second generation AI to generate the video data D00 by continuously generating the second image data D2 a predetermined number of times or for a predetermined period of time.

[0167] The viewer terminal 210-1 may store the video data D00 generated by the second generation AI going back a predetermined time, allowing the viewer terminal 210-1 to rewind and play the video, or to fast-forward and play the video.

[0168] Although the systems 1, 1a to 1e are applied to video distribution, they can also be applied to a virtual space in which multiple players participate. In this case, there are multiple player terminals that serve as the distributor terminal 10 and viewer terminal 210-1.

[0169] When the systems 1, 1a to 1e are applied to a virtual space, the character is displayed in a three-dimensional space. In this case, the movement information A1 includes the coordinates of the character in the virtual space, the direction the character is facing in the virtual space, and the three-dimensional shape of the character in addition to the character's movement.

[0170] When the systems 1, 1a to 1e are applied to a virtual space, a first player terminal generates motion information A1 and transmits the motion information A1 to the server 110. The server 110 transmits a first seed value S1, a first prompt P1, and the motion information A1 to a second player terminal. This allows the second player terminal to generate and display a character for the first player terminal. The second player terminal also generates motion information A1 and transmits it to the server 110. The server 110 transmits the first seed value S1, the first prompt P1, and the motion information A1 to the first player terminal. This allows the first player terminal to generate and display a character for the second player terminal.

[0171] In this specification, the term "image" includes a moving image, which is generated by arranging a plurality of images in time series.

[0172] The characters included in the first image data D1 are not limited to animals, but may be non-animal objects, animation characters, or the like.

[0173] The second generation AI may generate second image data D2 instead of the video data D00. In this case, the server 110 distributes the images to the viewer terminals 210-1 to 210-N.

[0174] In system 1c, storage unit 114 of viewer terminal 210-1 does not have to store first prompt P1. In this case, first prompt P1, together with first seed value S1, is transmitted from distributor terminal 10 to server 110, and is also transmitted from server 110 to viewer terminal 210-1.

[0175] The effects of this embodiment can be achieved even when these other embodiments are adopted. Furthermore, this embodiment can be combined with other embodiments, and other embodiments can be combined with each other as appropriate. [Explanation of symbols]

[0176] 1, 1a to 1e: System 10: Streamer terminal 12: Control unit 14: Storage part 16: Network interface 17: Camera 18: Graphics processing unit 20: Display 22: Audio processing section 24: Speaker 26:Operation section 30: Data generation unit 32: Information acquisition department 34: Communication control unit 36: Display control unit 110: Server 112: Control unit 114: Storage section 116: Network interface 120: Information acquisition department 122: Communication control unit 124: Prompt input section 126: Seed value acquisition section 128: Seed value specification part 130: Prompt acquisition unit 210-1~210-N: Viewer terminals 212: Control unit 214: Storage section 216: Network interface 217: Camera 218: Graphics processing unit 220: Display 222: Audio processing section 224: Speaker 226:Operation unit 230: Data generation unit 232: Communication control unit 234: Information acquisition department 236: Display control unit

Claims

1. 1. A system comprising one or more first computers and one or more second computers, each of the one or more second computers includes a second generation AI; The one or more first computers Acquire generation information that is information indicating text to be input to the first generation AI when generating the first image data, and / or acquire generation information that is information indicating text to be generated by the first generation AI when generating the first image data; transmitting the generated information to the one or more second computers; The one or more second computers Acquire the generation information; causing the second generation AI to generate second image data based on the generation information; system.

2. The one or more first computers inputting a first prompt into the first generating AI to generate the first image data; Obtaining a first seed value generated by the first generation AI in response to input of the first prompt; In the process of acquiring the generation information, a second seed value related to the first seed value is acquired as the generation information; transmitting the second seed value to the one or more second computers; The one or more second computers In the process of generating the second image data, the second generation AI is caused to generate the second image data based on a third seed value related to the second seed value. The system of claim 1 .

3. a second seed value in the second generation AI corresponds to a first seed value in the first generation AI; the third seed value is the same as the second seed value. The system of claim 2 .

4. The one or more first computers storing correspondence relationship information indicating a correspondence relationship between a seed value in the first generation AI and a seed value in the second generation AI; identifying the second seed value corresponding to the first seed value based on the correspondence relationship information; The system of claim 3.

5. There are a plurality of types of models of the second generated AI, the correspondence information indicates a correspondence between a seed value in the first generation AI and a seed value in the second generation AI of the plurality of types of models, The one or more first computers acquiring model information indicating a model of the second generated AI from the one or more second computers; Identifying the second seed value corresponding to the first seed value generated by the first generation AI based on the model information and the correspondence information. The system of claim 4.

6. There are multiple versions of the second generated AI; the correspondence information indicates a correspondence between a seed value in the first generation AI and a plurality of versions of seed values ​​in the second generation AI, The one or more first computers acquiring version information indicating a version of the second generated AI from the one or more second computers; Identifying the second seed value corresponding to the first seed value generated by the first generation AI based on the version information and the correspondence information.

6. The system according to claim 4 or claim 5.

7. The one or more first computers In the process of acquiring the generation information, the first prompt and the second seed value are acquired as the generation information; The one or more second computers In the process of generating the second image data, the second generation AI is caused to generate the second image data based on the third seed value and the first prompt. A system according to any one of claims 2 to 5.

8. The one or more second computers storing the first prompt; In the process of generating the second image data, the second generation AI is caused to generate the second image data based on the third seed value and the first prompt. A system according to any one of claims 2 to 5.

9. The one or more first computers Acquire motion information indicating the motion of the person; inputting the first prompt into the first generated AI; Obtaining a first seed value generated by the first generation AI in response to input of the first prompt; In the process of acquiring the generation information, a second seed value related to the first seed value is acquired as the generation information; the process of transmitting the generation information includes transmitting the operation information and the second seed value to the one or more second computers; The one or more second computers In the process of generating the second image data, the second generation AI generates video data in which a plurality of second images indicated by the second image data are arranged in time series based on the third seed value and the motion information. A system according to any one of claims 2 to 5.

10. the one or more first computers include a third computer and a fourth computer; the fourth computer is equipped with the first generation AI; The third computer generating person video data showing a video of the person; acquiring motion information indicating a motion of the person included in the person video data; transmitting the operation information to the fourth computer; The fourth computer In the process of acquiring the motion information, the motion information is acquired. The system of claim 9.

11. The fourth computer obtaining a second prompt for causing the second generation AI to generate the video data indicating a video of an object linked to a motion of the person based on the motion information; transmitting the generated information includes transmitting the second prompt to the one or more second computers; The one or more second computers In the process of generating the second image data, the second generation AI is caused to generate the video data based on the third seed value, the operation information, and the second prompt. The system of claim 10.

12. the one or more second computers further include a fifth computer and a sixth computer; The fifth computer transmitting viewer action information generated in response to an operation of the viewer to the fourth computer; The fourth computer Acquire the viewer action information; obtaining a third prompt that causes a change in the object in response to the viewer action information; the step of transmitting the generated information includes transmitting the third prompt to the sixth computer; The sixth computer In the process of generating the second image data, the second generation AI is caused to generate the video data in which a change occurs in the object according to the viewer action information, based on the third prompt. The system of claim 11.

13. A program executed on a second computer, the second computer includes a second generating AI; The program Acquire generation information transmitted from the first computer, the generation information being information indicating the text to be input to the first generation AI when generating the first image data, and / or the generation information being information indicating the text to be generated by the first generation AI when generating the first image data; generating image data by the second generation AI based on the generation information; Displaying an image based on the image data. causing the second computer to perform an operation; program.

Images