Server device, information processing method, information processing system, and program
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- CANON EURPOPA NV
- Filing Date
- 2025-10-10
- Publication Date
- 2026-06-16
Smart Images

Figure 0007874817000001 
Figure 0007874817000002 
Figure 0007874817000003
Abstract
Description
Technical Field
[0001] This embodiment relates to Server equipment, information processing method, an information processing system and program is related to.
Background Art
[0002] In video production, after creating a planning document necessary for producing a video, a story line and a storyboard of the video are created. A lot of workload has been required to create these planning documents, story lines, and storyboards.
[0003] Patent Document 1 describes a method of determining camera work for an object in an image of a cut constituting a storyboard, generating an image shown by the determined camera work, and assigning a cut number to the generated image and information related to the cut of the image.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0005] " In video production support technologies such as those disclosed in Patent Document 1, there may be a need for a user interface that can produce more suitable videos.
Means for Solving the Problems
[0006] As one means to solve the above problems, the information processing system disclosed herein has the following configuration. That is, in an information processing system comprising an information processing device and a server device, the server device has a transmission means for transmitting information for video production generated using a first process having a first role to the information processing device, the information processing device has a display control means for displaying the information for video production on a display unit, an instruction unit which does not accept character input from the user and accepts a review of the information for video production by a second process having a second role, the display control means displays on the display unit when the information for video production is displayed on the display unit, and the display control means displays on the display unit improvements to the information for video production generated using the second process having a second role and the information for video production, in accordance with instructions to the instruction unit.
[0007] Furthermore, the information processing system disclosed herein has the following configuration: an information processing system comprising an information processing device and a server device, wherein the information processing device has a first receiving unit that receives information related to video generation, a second receiving unit that receives budget information related to the budget for video shooting, a display unit that displays the information, and a control unit that controls the display of the display unit, and the server device has a communication unit that transmits the information related to video generation and the budget information to an external device and receives video production design information created by the external device, wherein the control unit displays the created video production design information on the display unit. [Effects of the Invention]
[0008] According to this disclosure, a user interface is provided that enables the creation of more suitable video.
[0009] The features of this embodiment will become clear from the following description of the embodiment (see attached drawings). The following description of the embodiment is provided as an example. [Brief explanation of the drawing]
[0010] [Figure 1] This diagram shows the configuration of a system including an information processing unit, an application server, and a generation AI server. [Figure 2] This diagram shows the hardware configuration of the information processing unit, application server, and generation AI server. [Figure 3A] This diagram shows the software configuration of the information processing device and the application server. [Figure 3B] This diagram shows the software configuration of the information processing device and the application server. [Figure 3C] This diagram shows the software configuration of the information processing device and the application server. [Figure 3D] This diagram shows the software configuration of the information processing device and the application server. [Figure 4] This is a flowchart showing the overall processing flow. [Figure 5] This is a sequence diagram showing the process of creating a project proposal. [Figure 6] This is a sequence diagram showing the process flow for creating a concept. [Figure 7] This is a sequence diagram showing the process flow for creating a storyline. [Figure 8] This is a sequence diagram showing the process flow for creating an image. [Figure 9] This is a sequence diagram showing the process of creating a storyboard. [Figure 10] This diagram shows a screen that accepts different types of video. [Figure 11A] This is a diagram showing the screen where the question is displayed. [Figure 11B] This is a diagram showing the screen where the question is displayed. [Figure 12A] This is a diagram showing the screen displaying the project proposal. [Figure 12B] This is a diagram showing the screen displaying the project proposal. [Figure 13] This diagram shows a screen displaying multiple concepts. [Figure 14]This is a diagram showing a screen on which a selected concept is displayed. [Figure 15] This is a diagram showing a screen on which improvements of the concept are displayed. [Figure 16] This is a diagram showing a screen on which a story line is displayed. [Figure 17] This is a diagram showing a screen on which an image of a character used in a storyboard is displayed. [Figure 18] This is a diagram showing a screen on which an image of a location used in a storyboard is displayed. [Figure 19] This is a diagram showing a screen on which an image of an object used in a storyboard is displayed. [Figure 20] This is a diagram showing a screen for selecting the style and color tone of image generation used in a storyboard. [Figure 21] This is a diagram showing a series of storyboard screens. [Figure 22] This is a diagram showing a flowchart of the plan update executed by an information processing apparatus. [Figure 23] This is a diagram showing a flowchart of the concept update executed by an information processing apparatus. [Figure 24] This is a diagram showing a flowchart of the story line update executed by an information processing apparatus. [Figure 25] This is a diagram showing a flowchart of the storyboard update executed by an information processing apparatus. [Figure 26] This is a flowchart showing the overall processing flow of the second embodiment. [Figure 27] This is a sequence diagram showing the processing flow of creating a plan document in the second embodiment. [Figure 28] This is a sequence diagram showing the processing flow of creating a concept in the second embodiment. [Figure 29] This is a diagram showing a screen for accepting the type and budget of a video in the second embodiment. [Figure 30] This is a diagram showing a screen for inputting the budget and budget allocation ratio in the second embodiment. [Figure 31]This figure shows the screen for inputting the budget and budget allocation ratio in the second embodiment. [Figure 32] This figure shows the screen for inputting the budget and budget allocation ratio in the second embodiment. [Figure 33] This figure shows a screen for sorting a series of storyboards in the second embodiment. [Figure 34] This figure shows the screens that divide the series of storyboards in the second embodiment. [Figure 35] This figure shows a flowchart of the concept update performed by the information processing device of the second embodiment. [Modes for carrying out the invention]
[0011] The following describes the implementation of this disclosure using drawings.
[0012] <First Embodiment> Figure 1 shows the overall configuration of a system for creating information for video production according to this embodiment. In Figure 1, the client information processing device 101 and the application server 102 are connected via a network 110. The network 110 can be implemented by, for example, a Local Area Network (hereinafter abbreviated as LAN), Wide Area Network (hereinafter abbreviated as WAN), a dedicated digital line, an ATM or Frame Relay line, a cable television line, a wireless line for data broadcasting, etc. The network 110 can be of any type as long as it is capable of transmitting and receiving data.
[0013] The information processing device 101 is an information device with a built-in program execution environment. Examples include desktop computers, laptop computers, Personal Data Assistants (hereinafter abbreviated as PDAs), and smartphones. The information processing device 101 has a built-in environment for executing programs such as web browsers (internet browsers, WWW browsers, software for using the World Wide Web).
[0014] The application server 102 has applications installed for creating project proposals, concepts, storylines, and storyboards. The application server 102 creates the storyline (text storyboard) and storyboard (picture storyboard) requested by the user according to the instructions received from the information processing device 101, and sends the created storyline and storyboard to the information processing device 101.
[0015] The generation AI server 103 is a server that generates responses using generation AI in accordance with prompts from the application server 102. Here, AI refers to artificial intelligence, and generation AI refers to artificial intelligence that learns data patterns and relationships to generate content including text, images, videos, audio, music, or combinations thereof. The generation AI server 103 has multiple AIs with assigned roles. Each AI has a different role. By assigning roles to the AIs, the AI's response style and content become appropriate to its role.
[0016] The role of the generating AI is assigned by giving it a role that mimics a specific person, occupation, or skill. The specific procedure for assigning a role to the AI involves clearly defining the role, communicating the background and situation, clarifying the objective (setting the goal expected of the AI), and finally setting additional rules (adding instructions regarding the tone and style of the response). In this embodiment, examples of roles include strategist, creative director, and copywriter. Therefore, the role in this embodiment can also be described as the premise, constraint, and other conditions under which the AI generates output content from the input it receives.
[0017] There are several ways to assign a role to AI, as listed below.
[0018] First, the AI's role can be changed by altering the content of the prompt. By devising instructions and settings for the AI, its response style and direction can be adjusted. To set the AI's role, the application server 102 can send a prompt to the generated AI server 103 that includes the name of the role (strategist, creative director, copywriter, etc.), the job description of the role, the expertise required for the role, the job function of the role, or any combination thereof.
[0019] In addition, configuration messages (system messages) are sometimes used to define "what role" an AI system should play. By adjusting these settings, the behavior of the AI can be changed without changing the prompts.
[0020] Alternatively, you can obtain responses that appear to have a different role simply by adding instructions regarding tone and style, without significantly altering the content of the prompt.
[0021] Additionally, the AI's role can be changed by switching between pre-set modes such as "Creative Mode" and "Accuracy-Focused Mode" without altering the prompt.
[0022] Furthermore, the generation AI server 103 may be a data server that aggregates information on many storylines and storyboards, or it may be a combination of a data server that aggregates storylines, storyboards, and other information related to video creation, and a server equipped with generation AI and other AI functions. In this embodiment, the video includes both audio and video, but the video may be a still image, a video, or a combination of a still image and a video, and these may be combined with one or more of text, audio, or music. In Figure 1, the application server 102 and the generation AI server 103 are shown as a single unit each in order to simplify the explanation of this embodiment, but there is no intention to limit the number of units. Each server may be composed of multiple physical server computers, multiple virtual server computers, or both.
[0023] Figure 2 shows an example of the hardware configuration of the information processing device 101, application server 102, and generation AI server 103 in a system for creating information for video production according to this embodiment. The system bus 201 is a system bus that connects each component of the information processing device 101. The CPU 202 (control unit) is a Central Processing Unit that controls the entire device and comprehensively controls access to each component connected to the system bus 201.
[0024] ROM203 is a Read Only Memory, a storage means, and stores various data such as basic I / O programs internally. RAM204 is a Random Access Memory, a temporary storage means, and functions as the main memory, work area, etc., of the CPU202. Storage device205 is one of the external storage means, and functions as a large-capacity memory, storing programs, etc., according to this embodiment. For example, it is a Hard Disk Drive (hereinafter abbreviated as HDD).
[0025] NIC206 is a Network Interface Controller that exchanges data with each component shown in Figure 1 via the network 110. The input unit 207 is an instruction input means via input devices such as a keyboard (not shown) or mouse (not shown). The display unit 208 is a display means via output devices such as a display (not shown). The CPU 202 controls the display of each screen on the display unit 208. The GPU 209 is a Graphics Processing Unit that performs processing when learning is carried out multiple times using a learning model such as deep learning. By using the GPU 209, it becomes possible to process more data in parallel and perform calculations efficiently.
[0026] It should be noted that the configuration of the information processing device 101 described above is merely an example and is not limited to the combination shown in Figure 2. For example, the storage location for data and programs can be changed to ROM 203, RAM 204, or storage device 205 depending on their characteristics.
[0027] Figure 2 shows an example of the hardware configuration of the application server 102.
[0028] The system bus 211 is the system bus that connects the various components of the server. The CPU 212 is the Central Processing Unit that controls the entire device and comprehensively controls access to each component connected to the system bus 211.
[0029] ROM213 is a Read Only Memory, a storage means, and stores various data such as basic I / O programs internally. RAM214 is a Random Access Memory, a temporary storage means, and functions as the main memory and work area of the CPU212 and GPU219. Storage device215 is one of the external storage means, and functions as a large-capacity memory, storing programs and the like according to this embodiment. For example, it is a Hard Disk Drive (hereinafter abbreviated as HDD). NIC216 is a Network Interface Controller, and exchanges data with each component shown in Figure 1 via the network 110.
[0030] The input unit 217 is an instruction input means via input devices such as a keyboard (not shown) or a mouse (not shown). The display unit 218 is a display means via output devices such as a display (not shown). The GPU 219 is a Graphics Processing Unit that performs processing when learning is carried out multiple times using a learning model such as deep learning. By using the GPU 219, it becomes possible to process more data in parallel and perform calculations efficiently. Note that the configuration of the application server 102 described above is merely an example and is not limited to the combination shown in Figure 2. For example, the storage location of data and programs can be changed to ROM 213, RAM 214, or storage device 215 depending on their characteristics.
[0031] Figure 2 shows an example of the hardware configuration of the generation AI server 103.
[0032] The system bus 221 is the system bus that connects the various components of the server. The CPU 222 is the Central Processing Unit that controls the entire device and comprehensively controls access to each component connected to the system bus 221.
[0033] ROM223 is a Read Only Memory, a storage means, and stores various data such as basic I / O programs internally. RAM224 is a Random Access Memory, a temporary storage means, and functions as the main memory and work area of the CPU222 and GPU229. Storage device225 is one of the external storage means, and functions as a large-capacity memory, storing programs and the like according to this embodiment. For example, it is a Hard Disk Drive (hereinafter abbreviated as HDD). NIC226 is a Network Interface Controller, and exchanges data with each component shown in Figure 1 via the network 120.
[0034] The GPU229 is a Graphics Processing Unit that handles processing when training a learning model, such as deep learning, over multiple iterations. By using the GPU229, it becomes possible to process more data in parallel, enabling more efficient computation. Note that the configuration of the generation AI server 103 described above is merely an example and is not limited to the combination shown in Figure 2. For example, the storage location for data and programs can be changed to ROM223, RAM224, or storage device225 depending on their characteristics.
[0035] Figures 3A to 3D show examples of the software configurations of each component of the system for creating information for video production according to this embodiment. Figure 3A is a block diagram illustrating the software configuration of the information processing device 101 according to this embodiment. These software modules are stored as programs in the storage device 205, and the CPU 202 loads these programs into the RAM 204 and executes them.
[0036] The information processing device 101 consists of an information receiving unit 301 and a web page information transmission / reception unit 302.
[0037] The information receiving unit 301 receives instructions from the user via the input unit 207. The web page information transmission / reception unit 302 connects to the application server 102 via the NIC 206 and network 110 to transmit and receive web page information.
[0038] The application server 102 consists of a web page information creation unit 316 and a web page information transmission / reception unit 317.
[0039] The Web page information creation unit 316 creates Web page information that includes at least one of the created project proposals, concepts, storylines, images, and storyboards.
[0040] The Web page information transmission / reception unit 317 connects to the information processing device 101 via the NIC 216 and network 110, and transmits and receives Web page information created by the Web page information creation unit 316. The generation AI server 103 consists of a proposal creation unit 311, a concept creation unit 312, a storyline creation unit 313, an image creation unit 314, and a storyboard creation unit 315.
[0041] The proposal creation department 311 creates questions necessary for creating a proposal based on the type and length of the received video, and then creates the proposal based on the answers to those questions.
[0042] The concept creation unit 312 creates multiple concepts from the proposal created by the proposal creation unit 311, receives instructions from the user on which concept to adopt, and decides on a concept in accordance with the received instructions.
[0043] The storyline creation unit 313 creates a storyline (text storyboard) from the concept created by the concept creation unit 312.
[0044] The image creation unit 314 creates images from the storyline created by the storyline creation unit 313.
[0045] The storyboard creation unit 315 creates a storyboard (illustrated storyboard) from the storyline created by the storyline creation unit 313 and the images created by the image creation unit 314.
[0046] Alternatively, the application server 102 may hold some of the creation units for the proposal creation unit 311, concept creation unit 312, storyline creation unit 313, image creation unit 314, and storyboard creation unit 315, and perform some of the processing from the proposal creation unit 311 to the storyboard creation unit 315.
[0047] The generation AI server 103 consists of, for example, an operating system (OS), a compiler / interpreter for a programming language, libraries, a database management system (DBMS), APIs and interfaces, security software, monitoring tools, etc.
[0048] The operating system (OS) manages the server's hardware resources and runs applications. Programming language compilers / interpreters are compilers and interpreters for programming languages necessary for AI development. Libraries are various libraries used for efficient data processing and numerical calculations. Database management systems are databases for managing large amounts of data. APIs and interfaces accept requests from external sources and return results.
[0049] Figure 4 is a flowchart illustrating the overall processing flow according to this embodiment.
[0050] A portion of the control program in the flowchart shown in Figure 4 is stored in the memory device 205 installed in the information processing device 101, and is read into RAM 204 and executed by the CPU 202. Furthermore, a portion of the control program in the flowchart shown in Figure 4 is stored in the memory device 215 installed in the application server 102, and is read into RAM 214 and executed by the CPU 212. Finally, a portion of the control program in the flowchart shown in Figure 4 is stored in the memory device 225 installed in the generation AI server 103, and is read into RAM 224 and executed by the CPU 222.
[0051] In S401, the information receiving unit 301 receives information from the user via the input unit 207, including the type and length of the video to be created, and what the user wants to convey through the video. The type of video is accepted in text, and can be any type of video, such as educational, sports, or commercial. The length of the video can be any specified time, for example, 60 seconds. What the user wants to convey through the video is the purpose of the video, the subject matter of the video, etc. In addition to text, the information receiving unit 301 can also accept images of items or characters to be used in the video.
[0052] Figure 10 shows the operation screen displayed on the display unit 208 of the information processing device 101 for receiving the type of video in S401. The type of video is entered into the reception unit 1001 in Figure 10. Alternatively, the desired image can be stored in the storage device 205 of the information processing device 101 and the image can be entered into the area 1003 in Figure 10 by dragging and dropping, etc. Accepting the input to the instruction unit 1002 in Figure 10 allows the process to proceed to S402. The instruction unit 1002 is a button displayed on the display unit 208, and input to the instruction unit 1002 can be accepted by clicking the button using a pointing device or touch operation, or by a predetermined keyboard operation. Acceptance of such input can be performed in the same manner in the following explanation.
[0053] Next, in S402, the proposal creation unit 311 creates questions necessary for creating the proposal based on the type and length of the video received in S401, and creates the proposal from the answers to the created questions. Figure 11A is a screen displayed on the display unit 208 of the information processing device 101, showing the questions 1101 and 1103 created in S402. Answers to each question are entered into the input fields 1102 and 1104 via the input unit 207. The questions 1101 and 1103 displayed in S402 are determined based on the type of video received in S401. Furthermore, example answers 1107 proposed to the questions are determined based on the type of video received in S401.
[0054] After the user enters their answers in input fields 1102 and 1104, the input is accepted by the instruction unit 1108, which starts the process of creating the proposal. Once the proposal is created, the screen shown in Figure 12A is displayed. Figure 12A is the proposal created in S402, displayed on the display unit 208. If the user agrees to the contents of the proposal, the input is accepted by the instruction unit 1210, which proceeds to the process in S403.
[0055] Next, in S403, the concept creation unit 312 creates multiple concepts from the project proposal created in S402, receives instructions from the user on which concept to adopt, and determines the concept according to the received instructions. Figure 13 shows the multiple concepts created in S403 displayed on the display unit 208. A concept is selected by selecting one of the multiple instruction units 1301 and 1302. Although Figure 13 shows two instruction units 1301 and 1302 as an example, there may be three or more concepts and instruction units. The process proceeds to S404 by accepting input to instruction unit 1501 in Figure 15.
[0056] Next, in S404, the storyline creation unit 313 creates a storyline (text storyboard) from the concept decided in S403. Figure 16 shows the storyline created in S404, displayed on the display unit 208. By accepting the input for Figure 16 to the instruction unit 1603, the process proceeds to S405.
[0057] Next, in S405, the image creation unit 314 creates an image from the storyline created in S404. Figure 17 shows the image created in S405, which is displayed on the display unit 208.
[0058] Next, in S406, the storyboard creation unit 315 creates a storyboard from the storyline created in S404 and the images created in S405. Figure 21 shows the storyboard created in S406, as displayed on the display unit 208.
[0059] The above-mentioned project proposal, concept, storyline, images, and storyboards are just examples of information needed for video production. Any information relevant to video production is acceptable.
[0060] Figure 5 is a sequence diagram illustrating the process flow for creating a project proposal in S402.
[0061] In S501, the type and length of the video received in S401, the message to be conveyed by the video, etc. (information related to video generation) are sent to the application server 102. In S502, the application server 102 sends a prompt to the generation AI server 103 for creating a question based on the type and length of the video received in S501 and the message to be conveyed by the video.
[0062] In S503, the AI (AI Strategist) 1105 of the first role of the generation AI server 103 creates a question from the prompt received in S502, and in S504 sends the created question to the application server 102. An example of a suggested answer 1107 to the question can be generated in S503 by the AI (AI Strategist) 1105 of the first role of the generation AI server 103. At this time, the generation AI server 103 can generate an example of an answer 1107 based on all or part of the information about the video generation, such as the type of video, length, what to convey with the video, and other information transmitted from the information processing device 101 in S501, the prompt received by the generation AI server 103 in S502, and the question generated in S503, and send it to the application server 102 in S504.
[0063] In S505, the application server 102 can create a web page containing the question and comments, as well as an example answer 1107, and send it to the information processing device 101. The generation AI server 103 has multiple AIs with assigned roles. Each AI has a different role.
[0064] The application server 102 receives multiple questions necessary for creating a proposal from the generation AI server 103 (for example, 1101, 1103, etc. in Figure 11A), and the web page information creation unit 316 creates a web page containing the questions and comments. In S505, the web page information transmission / reception unit 317 sends the created web page to the information processing device 101. The information processing device 101 displays the received web page.
[0065] The first role of AI1105 is that of a strategist, whose role is to faithfully determine the overall direction and purpose of the video based on the type of video input and the answers to the questions, and to clarify the message and concept that the video should convey. The first role can be set by sending a prompt to the generating AI server 103 from the application server 102 that includes the name "strategist," the strategist's duties such as planning, the strategic perspective and other expertise required of the strategist, the strategist's functions, or any combination thereof. Such a prompt may be sent in S502 or before S501.
[0066] Next, in S506, the information processing device 101 receives the answer to the question, and in S507, the received answer is sent to the application server 102. In the input fields 1102, 1104, etc. in Figure 11A, example answers 1107 proposed for the question are displayed based on the type of video received in S401. The example answers 1107 proposed for the question are generated in S502 by the AI (AI Strategist) 1105 of the first role of the generating AI server 103 from the prompt received in S502, based on the type and length of the video received in S501 and what the video wants to convey. The user refers to the example answer 1107 and enters the answer in the input fields 1102, 1104, etc. in Figure 11A. Also, when input is received to the instruction unit 1109 while the example answer 1107 is displayed, the example answer 1107 is entered as text 1110 in the input fields 1102, 1104 (see Figure 11B).
[0067] In S508, the application server 102 sends a prompt to the generation AI server 103 for creating a project proposal based on the response received in S507.
[0068] In S509, the generation AI server 103 creates a proposal using the processing of the AI 1105 with the first role based on the received prompt, and in S510, it sends the created proposal to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the proposal, and in S511, the web page information transmission / reception unit 317 sends the web page containing the proposal to the information processing device 101.
[0069] In S512, the received project proposal 1209 and the comments 1203 from the second role AI (AI Creative Director) 1201 are displayed on the display unit 208 of the information processing device 101. Also in S512, while the project proposal 1209 is displayed, the review button 1204, which is an instruction unit for accepting a review of the project proposal by the second role AI 1201, is displayed on the display unit 208. Note that the second role AI 1201 has a different role from the first role AI 1105. The second role AI 1201 is a creative director, and its role is to realize the actual video expression, such as the expression of visuals and story in the concrete video production process. The creative director is sometimes called an integrated producer. A second role can be set by sending a prompt from the application server 102 to the generation AI server 103 that includes the title "Creative Director," the duties of a Creative Director such as managing the quality of video and other products based on an overall understanding of the project or the consistency between products, the expertise required of a Creative Director such as refining products based on the purpose of the video, the functions of a Creative Director such as reviewing the quality of products or the strategic consistency between products, or any combination thereof. Such a prompt may be sent in S502 or earlier.
[0070] Thus, in this embodiment, the user can review the project proposal created by the AI 1105 in the first role and, depending on the content of the proposal, instruct whether or not to have the AI 1201 in the second role review the proposal. By having the AI 1201 in the second role review the proposal, multifaceted opinions can be incorporated into the creation of the proposal. In this embodiment, the AI 1201 in the second role, which corresponds to the position of creative director that oversees and manages the entire video production process, reviews the quality of the content included in the proposal created by the AI 1105 in the first role, which corresponds to the specialist position of strategist, or the strategic consistency between the content and the purpose of the video. Such a review includes evaluating such quality and consistency, and generating points for improvement based on that evaluation. The AI 1201 in the second role may review the entire process from S401 to S406 in Figure 4, or it may review only a part of the process in Figure 4 (for example, S402 to S404). By reviewing multiple processes from an overview perspective, it becomes possible to review them from a different viewpoint than that of AI1105, which plays the primary role.
[0071] The user can review the project proposal 1209 created by the AI 1105 in the first role and decide whether to request the AI 1201 in the second role to review the proposal. Regardless of the instruction to press the review button 1204, displaying the proposed improvements 1205 of the proposal at all times would increase the system load. However, in this embodiment, if the user agrees with the contents of the project proposal 1209, the AI 1201 in the second role will not generate the proposed improvements 1205, thereby reducing the load on the system that generates the proposed improvements.
[0072] Furthermore, in Figure 12A, the project proposal created by AI1105 (the first role) is displayed in the left area of the screen, while the comments 1203 and review button 1204 from AI1201 (the second role) are displayed in the right area of the screen. By separating the display areas, the content of the project proposal being reviewed is clearly displayed, and the user operating the review button 1204 can recognize the correct item to review. This reduces the number of review processes performed on the wrong item, thereby reducing the overall processing load on the system that performs the review process. In addition, in Figure 12A, the size of the area displaying the project proposal created by AI1105 (the first role) is larger than the size of the area displaying the comments 1203 and review button 1204 from AI1201 (the second role). This makes it easier to check the content of the project proposal.
[0073] Furthermore, region 1212 in Figure 12A shows the contents of multiple products, and the underlined process (Brief in Figure 12A) represents the contents currently being generated.
[0074] If no instructions are given for review button 1204, the AI 1201, which plays a second role, will not generate improvement points 1205 for the proposal, and therefore will not display improvement points 1205. This reduces the load on the system that generates improvement points for the proposal. Displaying improvement points 1205 for the proposal at all times, regardless of instructions for review button 1204, will increase the system load.
[0075] Furthermore, in Figure 12A, the review button 1204 is positioned closer to the comment 1203 of AI 1201 (the second role AI) than to the comment 1105 (the first role AI). This arrangement allows users operating the review button to intuitively understand that they are requesting a review from AI 1201 (the second role AI), preventing them from mistakenly requesting a review from AI 1105 (the first role AI). This also reduces the overall processing load on the system in Figure 1 that performs the review process.
[0076] Furthermore, since the review button 1204 displays "Ask for a review" (text indicating the content of the review request), users can easily recognize that the review button 1204 is for requesting a review. This reduces the misuse of the review button 1204 and also reduces the overall processing load of the system shown in Figure 1 that performs the review process. In addition, the review button 1204 does not accept text input; it is a button (instruction part) that instructs a review, and the review is initiated by the user clicking or tapping the button (instruction part).
[0077] In S513, when an instruction is received to the review button 1204, in S514, the information processing device 101 sends a review instruction to the application server 102, and in S515, the application server 102 sends a review instruction prompt to the generation AI server 103. Since the review instruction in S515 is a predetermined prompt to instruct a review, it can reduce the processing load on the generation AI server 103 compared to instructions given by arbitrary character input.
[0078] In S516, following the review instructions, the AI1201 in the second role generates improvement points 1205 for the project proposal. In S517, the created improvement points 1205 for the project proposal are sent to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the improvement points 1205 for the project proposal, and in S518, the web page information transmission / reception unit 317 sends the web page containing the improvement points 1205 for the project proposal to the information processing device 101.
[0079] In S519, the improvements 1205 to the project proposal are displayed on the display unit 208 of the information processing device 101.
[0080] In S520, if all of the displayed improvements 1205 are to be reflected in the project proposal, input is accepted via the Apply button 1206. Upon acceptance of input via the Apply button 1206, the content of the project proposal is updated so that the improvements 1205 are reflected in the proposal. By placing the Apply button 1206 near the improvements 1205, users operating the Apply button 1206 will know that they are applying the improvements 1205 and will be able to select the correct improvement target. This reduces the processing required to reflect incorrect content and also reduces the overall processing load of the system in Figure 1 that performs the improvement processing.
[0081] Furthermore, since the Apply button 1206 is labeled "Apply improvements," users can easily recognize that the Apply button 1206 is for requesting improvements. This reduces the misuse of the Apply button 1206 and also reduces the overall processing load of the system in Figure 1 that performs the improvement processing.
[0082] If you wish to incorporate some of the improvements from 1205 into the proposal, enter the content to be incorporated into input field 1207 and click the update button 1208 to update the proposal. Note that you can enter requests into input field 1207 before or after clicking the review button 1204. If you enter a request into input field 1207 after clicking the review button 1204, you can refer to improvements from 1205 to input your request, allowing you to request diverse opinions that incorporate the input of AI 1201, which plays a second role.
[0083] In S520, input is received to the apply button 1206 or entered into the input field 1207. In S521, the information processing device 101 sends an instruction to the application server 102, and in S522, the application server 102 sends an instruction to the generation AI server 103. In S523, the project proposal is updated based on the instruction. In S524, the generation AI server 103 sends the updated project proposal to the application server 102, and in S525, the application server 102 sends the updated project proposal to the information processing device 101.
[0084] In S526, the updated project proposal is displayed on the display unit 208 of the information processing device 101. Upon agreeing to the contents of the project proposal, the input is received by the instruction unit 1210, and the process proceeds to S403, i.e., to the concept creation sequence diagram in Figure 6.
[0085] Figure 22 is a flowchart of the process for updating a project proposal, which is executed by the information processing device 101. The control program for the flowchart shown in Figure 22 is stored in the storage device 205 of the information processing device 101 and is read into the RAM 204 by the CPU 202 and executed.
[0086] In S2201, upon receiving instructions to the review button 1204, in S2202, the information processing device 101 sends a review instruction to the application server 102 and receives the improvement points 1205 of the project proposal generated using the AI 1201 of the second role of the generation AI server 103.
[0087] In S2203, the improvements 1205 to the proposal are displayed on the display unit 208 of the information processing device 101. Note that if no instruction is received for the review button 1204 in S2201, the AI 1201, which has a second role, will not generate the improvements 1205 to the proposal, and therefore the improvements 1205 will not be displayed. This reduces the load on the system that generates the improvements to the proposal.
[0088] In S2204, if all of the displayed improvements 1205 are to be reflected in the proposal, input is accepted at the Apply button 1206. Upon acceptance of input at the Apply button 1206, the contents of the proposal are updated so that the improvements 1205 are reflected in the proposal. If only some of the improvements 1205 are to be reflected in the proposal, the contents of the proposal are updated by entering the content to be reflected in the input field 1207 and accepting input at the Update button 1208. Upon acceptance of input at the Apply button 1206 or by entering information in the input field 1207, in S2205, the information processing device 101 sends a correction instruction to the application server 102, and the updated proposal is received using the AI 1201, which has a second role.
[0089] In S2206, the updated project proposal is displayed on the display unit 208 of the information processing device 101.
[0090] If the request for revisions to the proposal is not accepted in S2204, the process proceeds to S2206, where the proposal created in S509 continues to be displayed.
[0091] Once the contents of the proposal are agreed upon, the system proceeds to process S403 by accepting input to the instruction unit 1210 in Figures 12A and 12B.
[0092] Figure 6 is a sequence diagram illustrating the process flow for concept creation in S403.
[0093] In S631, the information processing device 101 sends a concept generation instruction to the application server 102 in accordance with the input received by the instruction unit 1210 in Figures 12A and 12B. In S632, the application server 102 sends a concept generation instruction to the generation AI server 103. In S633, multiple concepts are created from the project proposal created in S402, and in S634, the generation AI server 103 sends the multiple concepts to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the multiple concepts, and in S635, the web page information transmission / reception unit 317 sends the web page containing the concepts to the information processing device 101.
[0094] In S601, comment 1304 from AI1303 (copywriter), who has a third role, is displayed. Note that AI1303, who has a third role, has a different role from AI1105, who has a first role, and AI1201, who has a second role. Based on the project proposal created and approved by AI1105, who has a first role, AI1303, who has a third role, is responsible for determining the words and phrases that will resonate with viewers, the tone and style of the video, and presenting a video concept that includes important elements for constructing the story. Also in S601, multiple concepts received in S635 are displayed on the display unit 208.
[0095] Figure 13 shows the first concept 1305 and the second concept 1306, among the multiple (e.g., three) concepts created. The third role can be set by sending a prompt from the application server 102 to the generation AI server 103 that includes the name "copywriter," the copywriter's duties such as creating multiple concepts, the expertise required of the copywriter, the copywriter's functions, or any combination thereof. Such a prompt may be sent in S632 or earlier.
[0096] The third role in this embodiment, the copywriter, shares the same characteristic as the first role as it is a professional role, but differs from the second role, which is a position that oversees and manages the entire project. Thus, different generating AIs based on different prompts can be used for the first role's AI 1105, which is used in the creation of the proposal (S401), and the third role's AI 1303, which is used in the creation of the concept (S403). This allows for setting appropriate expertise for each stage of the process or project phase and performing individual processing, thereby reducing the load on the generating AI server 103 while obtaining output that matches the objective.
[0097] In this embodiment, the AI 1201 in the second role can be used in both the creation of the project proposal (S401) and the creation of the concept (S403). The AI 1201 in the second role corresponds to the position of creative director, which oversees and manages the entire video production process, and can therefore play a common role throughout the video production process. This eliminates the need to increase the number of reviewing AIs depending on the progress of the processing or the phase of the project, reducing the load on the generation AI server 103 while obtaining consistent output that matches the purpose.
[0098] Here, "project" refers to a plan and its execution to achieve a predetermined goal, and in this embodiment, it may be all or part of the video creation specified by the user. Furthermore, "project phase" refers to a unit into which the project is divided, and in this embodiment, it may be a unit into which the work performed for video creation is divided. As an example, the project may encompass the entire process from receiving the video type, length, and message to be conveyed (S401) to creating the storyboard (S406), as shown in Figure 4, either in whole or in part. The project phases may be, but are not limited to, receiving the video type (S401), creating the project proposal (S402), creating the concept (S403), creating the storyline (S404), creating the images (S405), and creating the storyboard (S406).
[0099] In S602, a concept is selected from among the multiple concepts displayed in S601 based on the user's instructions. The concept is selected by selecting one of the multiple instruction units 1301, 1302 in Figure 13. To select the first concept 1305 in Figure 13, instruction unit 1301 is selected, and to select the second concept 1306, instruction unit 1302 is selected. In this embodiment, instruction unit 1302 is selected to select the second concept 1306. In S603, the information processing device 101 sends the selected concept to the application server 102.
[0100] In S604, the concept is received, and in S605, the concept and the comment 1403 from the second role AI (AI Creative Director) 1201 (Figure 14) are displayed. Also in S605, while the concept is displayed, a review button 1204, which is an instruction unit for accepting a review of the concept by the second role AI 1201, is displayed on the display unit 208.
[0101] In S606, upon receiving a command to the review button 1204, in S607, the information processing device 101 sends a review command to the application server 102, and in S608, the application server 102 sends a review command to the generation AI server 103. Since the review command in S608 is a predetermined prompt to instruct a review, it can reduce the processing load on the generation AI server 103 compared to commands entered by arbitrary characters.
[0102] In S609, following the review instructions, the AI1201 in the second role generates improvement points 1505 to the concept. In S610, the created improvement points to the concept are sent to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the improvement points to the concept, and in S611, the web page information transmission / reception unit 317 sends the web page containing the improvement points to the concept to the information processing device 101.
[0103] In S612, the improvements to the concept 1505 are displayed on the display unit 208 of the information processing device 101.
[0104] In S613, if you want to reflect all of the displayed improvements 1505 into the concept, the Apply button will be clicked. Upon clicking the Apply button, the concept content will be updated to reflect the improvements 1505. If you want to reflect only a portion of the improvements 1505 into the concept, enter the content to be reflected in input field 1506 and click the Update button 1507 to update the concept content. Note that you can enter a request in input field 1506 before or after instructing the Review button 1204. If you enter a request in input field 1506 after instructing the Review button 1204, you can refer to improvements 1505 when entering the request, allowing you to request diverse opinions that incorporate the opinions of the second role AI 1201.
[0105] In S613, input is received via the apply button or by entering information in the input field 1506. In S614, the information processing device 101 sends an instruction to the application server 102, and in S615, the application server 102 sends an instruction to the generation AI server 103. In S616, the concept is updated based on the instruction. In S617, the generation AI server 103 sends the updated concept to the application server 102, and in S618, the application server 102 sends the updated concept to the information processing device 101.
[0106] In S619, the updated concept is displayed on the display unit 208 of the information processing device 101. Upon agreeing to the content of the concept, input is received to the instruction unit 1501 in Figure 15, and the process proceeds to S404, i.e., to the storyline creation sequence diagram in Figure 7.
[0107] Figure 23 is a flowchart showing the process of updating a concept executed by the information processing device 101. The control program of the flowchart shown in Figure 23 is stored in the storage device 205 of the information processing device 101 and is read into the RAM 204 by the CPU 202 and executed.
[0108] In S2301, upon receiving instructions to the review button 1204, in S2302, the information processing device 101 sends a review instruction to the application server 102 and receives the improvement points 1505 of the concept generated using the second role AI 1201 of the generation AI server 103.
[0109] In S2303, the improvement points 1505 of the concept are displayed on the display unit 208 of the information processing device 101. However, if no instruction is received for the review button 1204 in S2301, the AI 1201, which has a second role, will not generate the improvement points 1505 of the concept, and therefore the improvement points 1505 of the concept will not be displayed.
[0110] In S2304, if all of the displayed improvements 1505 are to be reflected in the concept, input is accepted at the Apply button. Upon acceptance of input at the Apply button, the content of the concept is updated so that the improvements 1505 are reflected in the concept. If only some of the improvements 1505 are to be reflected in the concept, the content of the concept is updated by entering the content to be reflected in the input field 1506 and accepting input at the Update button 1507. Upon acceptance of input at the Apply button or by entering information in the input field 1506, in S2305, the information processing device 101 sends a correction instruction to the application server 102, and the updated concept is received using the AI 1201, which has a second role.
[0111] In S2306, the updated concept is displayed on the display unit 208 of the information processing device 101.
[0112] If no feedback is received on the concept in S2304, the process proceeds to S2306, where the concept created in S633 is displayed.
[0113] Figure 7 is a sequence diagram illustrating the process flow for creating the storyline in S404.
[0114] In S701, the instruction unit 1501 receives input, thereby receiving an instruction to generate a storyline. In S702, the information processing device 101 sends the storyline generation instruction to the application server 102, and in S703, the application server 102 sends the storyline generation instruction to the generation AI server 103.
[0115] In S704, the generation AI server 103 generates a storyline; in S705, the generation AI server 103 sends the generated storyline to the application server 102; and in S706, the application server 102 sends the storyline to the information processing device 101.
[0116] In S707, the received storyline is displayed on the display unit 208. Figure 16 shows the storyline displayed in S707.
[0117] Furthermore, in S707, while the storyline is displayed, a review button 1204, which is an instruction unit for accepting a review of the storyline by the AI 1201 (which has a second role), is displayed on the display unit 208.
[0118] In S708, upon receiving a command to the review button 1204, in S709, the information processing device 101 sends a review command to the application server 102, and in S710, the application server 102 sends a review command to the generation AI server 103. Since the review command in S710 is a predetermined prompt to instruct a review, it can reduce the processing load on the generation AI server 103 compared to commands entered by arbitrary characters.
[0119] In S711, following the review instructions, the AI1201, which plays the second role, generates improvements to the storyline. In S712, the created improvements to the storyline are sent to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the improvements to the storyline, and in S713, the web page information transmission / reception unit 317 sends the web page containing the improvements to the storyline to the information processing device 101.
[0120] In S714, improvements to the storyline are displayed on the display unit 208 of the information processing device 101.
[0121] In S715, if you want to reflect all the displayed improvements in the storyline, the Apply button will accept input. When the Apply button is accepted, the storyline content will be updated so that the improvements are reflected in the storyline. If you want to reflect only some of the improvements in the storyline, enter the content to be reflected in input field 1601 and accept input in update button 1602 to update the storyline content. Note that you can enter a request in input field 1601 before or after instructing the Review button 1204. If you enter a request in input field 1601 after instructing the Review button 1204, you can enter the request by referring to the improvements, so you can request diverse opinions that incorporate the opinions of the second role AI 1201.
[0122] In S715, input is received via the Apply button or by entering information in the input field 1601. In S716, the information processing device 101 sends an instruction to the application server 102, and in S717, the application server 102 sends an instruction to the generation AI server 103. In S718, the storyline is updated based on the instruction. In S719, the generation AI server 103 sends the updated storyline to the application server 102, and in S720, the application server 102 sends the updated storyline to the information processing device 101.
[0123] In S721, the updated storyline is displayed on the display unit 208 of the information processing device 101. Upon agreeing to the content of the storyline, the input is received by the instruction unit 1603, and the process proceeds to S405, i.e., to the image creation sequence diagram shown in Figure 8.
[0124] Figure 24 is a flowchart showing the process of updating the storyline executed by the information processing device 101. The control program for the flowchart shown in Figure 24 is stored in the storage device 205 of the information processing device 101 and is read into the RAM 204 by the CPU 202 and executed.
[0125] In S2401, upon receiving instructions to the review button 1204, in S2402, the information processing device 101 sends a review instruction to the application server 102 and receives improvements to the storyline generated using the AI 1201, which is the second role of the generation AI server 103.
[0126] In S2403, improvements to the storyline are displayed on the display unit 208 of the information processing device 101. However, if no instruction is received from the review button 1204 in S2401, the AI 1201, which has a second role, will not generate improvements to the storyline, and therefore the improvements to the storyline will not be displayed.
[0127] In S2404, if all of the displayed improvements are to be reflected in the storyline, input is accepted at the Apply button. Upon acceptance of input at the Apply button, the content of the storyline is updated so that the improvements are reflected in the storyline. If only some of the improvements are to be reflected in the storyline, the content of the storyline is updated by entering the content to be reflected in input field 1601 and accepting input at the Update button 1602. Upon acceptance of input at the Apply button or by entering information in input field 1601, in S2405, the information processing device 101 sends a correction instruction to the application server 102, and the updated storyline is received using the AI 1201, which has a second role.
[0128] In S2406, the updated storyline is displayed on the display unit 208 of the information processing device 101.
[0129] Figure 8 is a sequence diagram illustrating the process flow for creating the image in S405.
[0130] In S801, the display unit 208 displays an image 1701 of a character used in the storyboard, as shown in Figure 17, and text 1702 of the character's age, gender, appearance, accessories, clothing, and image type (colored image, line drawing, etc.). In S802, when the user inputs the content to modify the text 1702 of the character's age, gender, appearance, accessories, clothing, and image type (colored image, line drawing, etc.) and the input is accepted by the update button 1703, the information processing device 101 sends a modification instruction to the application server 102 in S803. In S804, the application server 102 sends a modification instruction to the generation AI server 103, and in S805, the character image is updated based on the instruction. In S806, the generation AI server 103 sends the updated character image to the application server 102, and in S807, the application server 102 sends the updated character image to the information processing device 101.
[0131] Next, in S808, the display unit 208 displays the location image 1801 used in the storyboard, along with the image description, location, and city text 1802, as shown in Figure 18. In S809, after inputting the content to modify the location image description, location, and city text 1802 and receiving input to the update button 1803, in S810, the information processing device 101 sends a modification instruction to the application server 102. In S811, the application server 102 sends the modification instruction to the generation AI server 103, and in S812, the location image is updated based on the instruction. In S813, the generation AI server 103 sends the updated location image to the application server 102, and in S814, the application server 102 sends the updated location image to the information processing device 101.
[0132] Next, in S815, the display unit 208 displays the image 1901 of the object used in the storyboard and the text 1902 describing the image, as shown in Figure 19. In S816, when the content to be modified in the text 1902 describing the object image is entered and input is received at the update button 1903, in S817, the information processing device 101 sends a modification instruction to the application server 102. In S818, the application server 102 sends a modification instruction to the generation AI server 103, and in S819, the object image is updated based on the instruction. In S820, the generation AI server 103 sends the updated object image to the application server 102, and in S821, the application server 102 sends the updated object image to the information processing device 101. In S822, the updated object image is displayed on the display unit 208.
[0133] Furthermore, in the screens shown in Figures 17, 18, and 19, the review button 1204 shown in Figure 12A may be placed, and by following the instructions on the review button 1204, the AI 1201, which has a second role, may be asked to review the character image 1701, location image 1801, and object image 1901.
[0134] Figure 9 is a sequence diagram illustrating the process flow for creating the storyboard for S406.
[0135] In S901, the image generation style 2001 and color tone 2002 shown in Figure 20 are selected. The image generation style can be selected from, for example, POP ART, COLOR SKETCH, PHOTOREAL, and ANIME. The color tone can be selected from, for example, MUTED, VIVID, WARM, and COLD. Alternatively, the image generation style can be selected from line drawings without color. By accepting input to the instruction unit 2003 in Figure 20, the process proceeds to S902.
[0136] In S902, the information processing device 101 sends the style and color tone to the application server 102, and in S903, the application server 102 sends a prompt to the generation AI server 103 for creating a storyboard based on the style and color tone.
[0137] In S904, the generation AI server 103 generates a storyboard; in S905, the generation AI server 103 sends the generated storyboard to the application server 102; and in S906, the application server 102 sends the storyboard to the information processing device 101.
[0138] In S907, a series of storyboards 2101-2103 are displayed as shown in Figure 21. Also in S907, the action, viewpoint, and location 2104 during filming are displayed. Filming actions include long shots that capture the entire subject, full shots that fill the screen with the subject, medium shots to express movement in detail, close-up shots that show a part of the subject, especially the face or hands, in detail, and extreme close-up shots that capture a specific part of the subject from very close up. Furthermore, when there are multiple people, filming actions include over-the-shoulder shots that capture one person over the shoulder of another person, and bird's-eye view shots that are shot from directly above to get an overview of the entire scene.
[0139] In S908, upon receiving instructions to the review button, in S909, the information processing device 101 sends a review instruction to the application server 102, and in S910, the application server 102 sends a review instruction to the generation AI server 103. In S911, according to the review instruction, the AI 1201 with the second role generates improvements to the storyboard. In S912, the created improvements to the storyboard are sent to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the improvements to the storyboard, and in S913, the web page information transmission / reception unit 317 sends the web page containing the improvements to the storyboard to the information processing device 101.
[0140] In S914, improvements to the storyboard are displayed on the display unit 208 of the information processing device 101.
[0141] In S915, when the content to modify the action, viewpoint, and location 2104 during shooting is entered and the input is accepted by the update button 2105, in S916, an update instruction based on the entered modification content is sent from the information processing device 101 to the application server 102. In S917, the application server 102 sends an instruction to the generation AI server 103.
[0142] In S918, the storyboard is updated based on the above instructions. In S919, the updated storyboard is sent from the generation AI server 103 to the application server 102, and in S920, the updated storyboard is sent from the application server 102 to the information processing device 101.
[0143] In S921, the updated storyboard is displayed on the display unit 208 of the information processing device 101. Through these processes, multiple storyboards are completed.
[0144] In addition, the review button for receiving review instructions from the S908 during storyboard creation is optional, and this embodiment also includes configurations where the review button is not displayed, or where improvements to the storyboard are not displayed.
[0145] Figure 25 is a flowchart showing the process of updating the storyboard, which is executed by the information processing device 101. The control program for the flowchart shown in Figure 25 is stored in the storage device 205 of the information processing device 101 and is read into the RAM 204 by the CPU 202 and executed. In S2501, upon receiving instructions to the review button, in S2502, the information processing device 101 sends a review instruction to the application server 102 and receives improvements to the storyboard generated using the AI 1201, which is the second role of the generation AI server 103.
[0146] In S2503, improvements to the storyboard are displayed on the display unit 208 of the information processing device 101. However, if no instruction is received to the review button in S2501, the AI 1201, which has a second role, will not generate improvements to the storyboard, and therefore the improvements to the storyboard will not be displayed.
[0147] In S2504, when the user inputs changes to the action, viewpoint, and location 2104 during filming and the input is accepted by the update button 2105, the contents of the storyboard are updated so that the improvements are reflected in the storyboard. Upon accepting the input by the update button 2105, in S2505, the information processing device 101 sends a correction instruction to the application server 102, and the updated storyboard is received using the AI 1201, which has a second role.
[0148] In S2506, the updated storyboard is displayed on the display unit 208 of the information processing device 101.
[0149] If no modification instructions for the storyboard are accepted in S2504, the process proceeds to S2506, where the storyboard created in S907 continues to be displayed.
[0150] In this embodiment, the process of creating a storyboard was described using the flowchart in Figure 4. However, it is not necessary to execute all the processes in Figure 4, but only some of them. For example, S401 to S402 may be executed to create a video proposal, S401 to S403 may be executed to create a video concept, or S401 to S404 may be executed to create a video storyline.
[0151] Furthermore, in this embodiment, although Figure 1 describes a configuration in which the information processing device 101, application server 102, and generation AI server 103 are connected via a network, the program stored in the application server 102 (Figure 3B) may be stored in the information processing device 101, and the flowcharts shown in Figures 4 to 9 may be executed in the information processing device 101 without using the application server 102. In that case, the information processing device 101 and the generation AI server 103 communicate directly via the network.
[0152] Furthermore, although this embodiment describes an example using the generation AI server 103, it is also possible to store a lookup table (LUT) in the storage device 215 of the application server 102 and perform each process using the LUT without using the generation AI server 103. For example, in S502 of Figure 5, a LUT may be used that takes information related to video generation as input and outputs a question, or in S505 of Figure 5, a LUT may be used that takes the answer to the question as input and outputs a project proposal. When performing each process using a LUT, as shown in Figure 3D, the application server 102 has a project proposal creation unit 311, a concept creation unit 312, a storyline creation unit 313, an image creation unit 314, and a storyboard creation unit 315.
[0153] When using a LUT, the number of input / output patterns is limited, but when using the generation AI server 103, a larger number of input / output patterns can be used than when using a LUT, allowing for high-precision output for a given input.
[0154] According to this embodiment, information generated by a process with a first role can be reviewed, and depending on the content of the information, it is possible to instruct whether or not to perform a review of the information by a process with a second role. By performing a review of the information by the second role, multifaceted opinions can be incorporated for information creation. If the information generated by the process with the first role is agreed upon, the review of the information by the second role is not performed, thereby reducing the overall processing load of the system.
[0155] Furthermore, by placing the review button 1204 near the comment 1203 of the second AI 1201, users operating the review button will understand that they are requesting a review from the second AI 1201, thus ensuring they select the correct review target. This reduces the number of review processes performed on the wrong target, thereby lowering the overall processing load on the system performing the review.
[0156] Furthermore, since the review button 1204 displays "Ask for a review" (text indicating the content of the review request), users can easily recognize that the review button 1204 is for requesting a review. This reduces the misuse of the review button 1204 and also reduces the overall processing load on the system that handles the review process.
[0157] <Second Embodiment> In the first embodiment, the system received information from the user regarding the type and length of video they wanted to create, the message they wanted to convey, etc., and then sequentially created a project proposal, concept, storyline, images, and storyboards. The difference between this embodiment and the first embodiment is that it receives the budget required for filming, and then creates a project proposal, concept, storyline, and storyboards based on the type and length of video the user wanted to create, the message they wanted to convey, and the received budget. Note that the same reference numerals are used for each step of the configuration and flowchart already described in the first embodiment, and their explanations are omitted.
[0158] In the first and second embodiments, the "project proposal" includes, but is not limited to, the purpose and direction of the video production, the target audience for the video, the platform on which the video will be published, and at least all or part of the message to be conveyed by the video. It may also include synonyms and similar concepts that a person skilled in the art would understand, but each concept has its own effect. In this embodiment, the "concept" is a more concrete version of the project proposal, including, but is not limited to, at least all or part of the title of the video to be created, what scenes will be included in the video, and descriptions that will excite the target audience for the video (for example, content encouraging participation in an event). It may also include synonyms and similar concepts that a person skilled in the art would understand, but each concept has its own effect. In this embodiment, the "storyline" is a description of the story development in the video production, and in a story that includes multiple scenes, a description of the theme and location of each scene. It may also include synonyms and similar concepts that a person skilled in the art would understand, but each concept has its own effect. In this embodiment, "storyboard" refers to a series of illustrations or images used to visually represent the flow and structure of a scene in video production or animation, but is not limited to this. It may include synonyms and similar concepts that a person skilled in the art would understand, but each concept has its own effect.
[0159] Figure 26 is a flowchart illustrating the overall processing flow according to this embodiment.
[0160] A portion of the control program in the flowchart shown in Figure 26 is stored in the memory device 205 installed in the information processing device 101, and is read into RAM 204 and executed by the CPU 202. Furthermore, a portion of the control program in the flowchart shown in Figure 26 is stored in the memory device 215 installed in the application server 102, and is read into RAM 214 and executed by the CPU 212. Finally, a portion of the control program in the flowchart shown in Figure 26 is stored in the memory device 225 installed in the generation AI server 103, and is read into RAM 224 and executed by the CPU 222.
[0161] In S2601, the information receiving unit 301 receives information about video generation from the user via the input unit 207. This information includes, for example, the type and length of the video to be created, and what the user wants to convey through the video. The type of video is accepted in text form and can be any type of video, such as educational, sports, or commercial. The length of the video can be any specified time, for example, 60 seconds. What the user wants to convey through the video includes the purpose of the video and the subject matter of the video. In addition to text, the information receiving unit 301 can also accept images of items or characters to be used in the video.
[0162] Figure 29 is an operation screen displayed on the display unit 208 of the information processing device 101, which accepts the type of video in S2601. The type of video is entered into the reception unit 2901 (first reception unit) in Figure 29. Alternatively, the desired image can be stored in the storage device 205 of the information processing device 101 and the image can be accepted by dragging and dropping it into the area 2903 in Figure 29. Accepting the input to the instruction unit 2902 in Figure 29 allows the process to proceed to S2602. The instruction unit 2902 is a button displayed on the display unit 208, and input to the instruction unit 2902 can be accepted by clicking the button using a pointing device or touch operation, or by using a predetermined keyboard. Acceptance of such input can be done in the same way in the following explanation. Also, in Figure 29, the budget is entered into the reception unit 2904. This budget is the cost incurred when the photographer takes pictures, referring to the storyboard created in S406 of Figure 26. If the budget has not yet been decided, select indicator 2905 to indicate that the budget has not yet been decided.
[0163] Next, in S2602, the proposal creation unit 311 creates questions necessary for creating the proposal based on the type and length of the video received in S2601, and creates the proposal from the answers to the created questions. Figure 11A is a screen displayed on the display unit 208 of the information processing device 101, showing the questions 1101 and 1103 created in S2602. Answers to each question are entered into the input fields 1102 and 1104 via the input unit 207. The questions 1101 and 1103 displayed in S2602 are determined based on the type of video received in S2601. Furthermore, example answers 1107 proposed to the questions are determined based on the type of video received in S2601.
[0164] After the user enters their answers in input fields 1102 and 1104, the input is accepted by the instruction unit 1108, which starts the process of creating the proposal. Once the proposal is created, the screen shown in Figure 12A is displayed. Figure 12A is the proposal created in S2602, displayed on the display unit 208. If the user agrees to the contents of the proposal, the input is accepted by the instruction unit 1210, which proceeds to the process in S2603.
[0165] In addition, in S2602, the proposal creation unit 311 may create questions necessary for creating a proposal from the video generation information and budget received in S2601, and create a proposal from the answers to the created questions. Alternatively, in S2602, the proposal creation unit 311 may create questions necessary for creating a proposal from the video generation information received in S2601, and create a proposal from the answers to the created questions and the budget.
[0166] Next, in S2603, the concept creation unit 312 creates multiple concepts from the project proposal created in S2602, receives instructions from the user on which concept to adopt, and determines the concept according to the received instructions. Figure 13 shows the multiple concepts created in S2603 displayed on the display unit 208. A concept is selected by selecting one of the multiple instruction units 1301 and 1302. Although Figure 13 shows two instruction units 1301 and 1302 as an example, there may be three or more concepts and instruction units. The process proceeds to S404 by accepting input to instruction unit 1501 in Figure 15. Note that the processing in S404 to S406 in Figure 26 is the same as the processing in S404 to S406 in Figure 4, so the explanation is omitted.
[0167] The photographer takes the shots referring to the location, composition, and type of shot shown in the storyboard created in S406 of Figure 4.
[0168] Figure 27 is a sequence diagram illustrating the process flow for creating a project proposal in S2602.
[0169] In S2701, the type and length of the video received in S2601, the message to be conveyed in the video (information related to video generation), and the budget are sent to the application server 102. In S2702, the application server 102 sends a prompt to the generation AI server 103 to create a question based on the video generation information and budget received in S2701.
[0170] In S2703, the AI (AI Strategist) 1105 of the first role in the generation AI server 103 creates a question from the prompt received in S2702. Specifically, in S2702, a basic prompt and a prompt for question generation are sent to the AI (AI Strategist) 1105 of the first role. The basic prompt defines the basic thinking patterns and approaches to the problem as a strategist and is set to extract the information necessary for creating the proposal. The prompt for question generation includes instructions to analyze the content of the information related to video generation and check for any discrepancies, and is set to ask questions about any deficiencies by comparing the information from coarse to fine granularity with the information necessary for creating the proposal.
[0171] The first role of AI1105 is that of a strategist, whose role is to faithfully determine the overall direction and purpose of the video based on the type of video input and the answers to the questions, and to clarify the message and concept that the video should convey. The first role can be set by sending a prompt to the generating AI server 103 from the application server 102 that includes the name "strategist," the strategist's duties such as planning, the strategic perspective and other expertise required of the strategist, the strategist's functions, or any combination thereof. Such a prompt may be sent in S2702 or before S2701.
[0172] Next, in S2706, the information processing device 101 receives the answer to the question, and in S2707, the received answer is sent to the application server 102. In the input fields 1102, 1104, etc. in Figure 11A, examples of suggested answers 1107 to the question are displayed based on the type of video received in S2601. The examples of suggested answers 1107 to the question are generated in S2702 by the AI (AI Strategist) 1105 of the generation AI server 103, based on the video generation information and budget received in S2701, from the prompt received. The user refers to the example answer 1107 and enters the answer in the input fields 1102, 1104, etc. in Figure 11A. Also, when input is received to the instruction unit 1109 while the example answer 1107 is displayed, the example answer 1107 is entered as text 1110 in the input fields 1102, 1104 (see Figure 11B). In S2708, the application server 102 sends a prompt to the generation AI server 103 for creating a project proposal based on the response received in S2707.
[0173] Furthermore, in S2707, the response received in S2706 and the budget received in S2601 may be sent to the application server 102, and in S2708, the application server 102 may send a prompt to the generation AI server 103 for creating a project proposal based on the response and budget received in S2707.
[0174] In S2709, the generation AI server 103 creates a proposal using the processing of the AI 1105 with the first role based on the received prompt, and in S2710, it sends the created proposal to the application server 102. The web page information creation unit 316 of the application server 102 creates a web page containing the proposal, and in S2711, the web page information transmission / reception unit 317 sends the web page containing the proposal to the information processing device 101. In S2712, the received project proposal 1209 and the comments 1203 from the second role AI (AI Creative Director) 1201 are displayed on the display unit 208 of the information processing device 101. Also in S2712, while the project proposal 1209 is displayed, a review button 1204, which is an instruction unit for accepting a review of the project proposal by the second role AI 1201, is displayed on the display unit 208.
[0175] Note that the processes S504, S505, and S513-S526 in Figure 27 are the same as those in S504, S505, and S513-S526 in Figure 5, so their explanation is omitted.
[0176] Figure 28 is a sequence diagram illustrating the process flow for concept creation in S2603.
[0177] In S641, the budget is entered into the instruction unit 1222 (second reception unit) in Figure 30. This budget represents the costs incurred by the photographer when shooting, based on the storyboard created in S406 in Figure 26. For example, it includes the rental fee for the shooting location, the fees paid to the talent who is the subject of the shoot, and the rental fees for equipment such as cameras and lenses used for shooting. Furthermore, it may also include the personnel costs of art staff, lighting staff, and sound staff involved in the shoot.
[0178] In addition, in S641, the allocation ratios of multiple elements that make up the budget may be input in addition to the budget itself. For example, the allocation ratios of budgets such as filming location, talent, equipment, and personnel costs may be directly input into the instruction unit 1215, or the allocation ratios may be indicated by moving the arrows 1213 and 1214. The size 1216 of each area corresponds to the allocation ratio, and the allocation ratios of filming location and talent can be changed by changing the arrow 1213 at the boundary between filming location and talent, and the allocation ratios of talent and equipment can be changed by changing the arrow 1214 at the boundary between talent and equipment.
[0179] The budget for each element is determined based on the budget entered in the instruction unit 1222 and the allocation ratio of the elements entered. For example, if a budget of "2000" is entered in the instruction unit 1222, and the ratios for location, talent, and equipment are specified as 60%, 30%, and 10%, the budgets for location, talent, and equipment will be 2000 × 0.6 = "1200", 2000 × 0.3 = "600", and 2000 × 0.1 = "200", respectively.
[0180] In S642, in accordance with the acceptance of input to the instruction unit 1230 in Figure 30, the information processing device 101 sends a budget and a concept generation instruction to the application server 102. Alternatively, the budget, budget allocation ratio, and concept generation instruction may be sent, and in S643, the budget, budget allocation ratio, and concept generation instruction may be sent. In S644, multiple concepts are created from the project proposal and budget created in S2602. For example, multiple concepts are created from the project proposal and budget so that the contents of the project proposal stay within the budget. For example, as shown in Figure 13, a first concept 1305 and a second concept 1306 that stay within the budget are generated. Alternatively, in S644, multiple concepts may be created from the project proposal, budget, and allocation ratio created in S2602. For example, if the ratio of shooting locations is high and the ratio of talent and equipment is low, shooting is possible in many locations or luxurious locations, but a concept is created that minimizes the number of talents and shoots are carried out by renting inexpensive equipment. Furthermore, if the ratio of filming locations is low and the ratio of talent to equipment is high, filming will be done in locations with fewer or lower costs, a concept will be created that features many talents, and expensive equipment will be rented for filming.
[0181] Before deciding on a concept, the necessary budget for filming is entered in advance. A concept is then generated that allows for a filming plan within that budget. Based on this generated concept, a storyboard is created. This prevents exceeding the budget during filming, which is based on the storyboard. It avoids having to recreate the video production design information from scratch due to budget overruns, and reduces the processing load on the device that generates the proposal, concept, storyline, and storyboard. Note that video production design information refers to at least one of the following: proposal, concept, storyline, images, and storyboard.
[0182] Furthermore, when entering the budget into the instruction unit 1222 in Figure 30, it is not necessary to enter the budget into the reception unit 2904 in Figure 29; entering the budget at least once is sufficient. Also, when entering the budget into the reception unit 2904 in Figure 29, it is not necessary to enter the budget into the instruction unit 1222 in Figure 30; entering the budget at least once is sufficient.
[0183] Furthermore, in the embodiment where the budget is received at S2601 in Figure 26 using the reception unit 2904 in Figure 29 before the proposal is created, the purpose is to understand the scale of the budget, so detailed budget allocation ratios are not necessary, and it is sufficient to input only an estimated total budget.
[0184] Alternatively, in S641, different budgets may be entered into each of the instruction units 1216 to 1218 in Figure 31. In that case, in S644, a concept corresponding to each budget is created.
[0185] In S645, the generation AI server 103 sends multiple concepts to the application server 102. The application server 102's web page information creation unit 316 creates a web page containing the multiple concepts, and in S646, the web page information transmission / reception unit 317 sends the web page containing the concepts to the information processing device 101.
[0186] In S647, the comment 1304 from the third role AI1303 (copywriter) and multiple concepts received in S646 are displayed on the display unit 208.
[0187] Note that the processes S602 to S619 in Figure 28 are the same as those in Figure 6, so their explanation is omitted.
[0188] Figure 35 is a flowchart showing the process of updating a concept executed by the information processing device 101. The control program of the flowchart shown in Figure 35 is stored in the storage device 205 of the information processing device 102 and is read into the RAM 204 by the CPU 202 and executed.
[0189] In S3501, if a command to generate a concept is received via button 1230 in Figure 30, the process proceeds to S3502. In S3502, if a budget is entered in the instruction unit 1222 in Figure 30, it is determined that the budget has been received, and the process proceeds to S3503. If no budget is entered in the instruction unit 1222 in Figure 30, it is determined that the budget has not been received, and the process proceeds to S3504.
[0190] In S3503, the entered budget and concept generation instructions are sent to the application server 102. In S3504, the concept generation instructions are sent to the application server 102.
[0191] In S3505, multiple concepts are received from the application server 102 and displayed on the display unit 208 of the information processing device 101.
[0192] Next, in S3506, when a selection of a concept is received from among the multiple concepts displayed, in S3507, the selected concept is displayed on the display unit 208 of the information processing device 101.
[0193] Alternatively, in S3502, the instruction unit 1215, arrows 1213 and 1214 in Figure 30 may be operated to receive the budget and the allocation ratios of multiple elements that make up the budget, and in S3503, the budget, allocation ratios, and concept generation instructions may be sent to the application server 102.
[0194] Furthermore, as shown in Figure 33, by checking checkbox 3301, the series of storyboards displayed in S907 can be sorted and displayed by location. This allows the cameraman to easily recognize the storyboard for each location when shooting footage while referring to the storyboards.
[0195] Furthermore, as shown in Figure 34, by checking checkbox 3401, the series of storyboards displayed in S907 can be divided into storyboards for which a shooting plan can be proposed and storyboards for which a shooting plan is difficult to propose and which are generated by AI. For example, a storyboard showing the city center is classified as an AI-generated storyboard because it is determined that a shooting plan cannot be proposed as it would require traffic restrictions in the city area for filming, making filming impractical.
[0196] Furthermore, the storyboard generated in S406 in Figures 4 and 26 may be stored in the storage device 205 of the information processing device 101 along with the shot list and used as a navigator during filming. Here, the shot list is a document created after the storyboard is made that summarizes the types of shots required for a scene, outdoor and indoor locations, and an overview of the characters and shots. The filming data actually shot according to this navigator is linked to the storyboard. In addition, the filming data may be sorted according to the order of the storyboard and stored in the storage device 205 of the information processing device 101.
[0197] Before the concept is finalized, the budget required for filming is entered in advance. However, after the storyboard is completed, the user may review the storyboard content, revise the budget, and recreate the storyboard. Recreation can be done by returning to S2603 in Figure 26 and recreating the concept, storyline, images, and storyboard, or by returning to S406 in Figure 26 and recreating the storyboard. In the screen shown in Figure 32, the revised budget is entered into the instruction unit 3230. Also, in the screen shown in Figure 32, the allocation ratio of the budget elements can be changed.
[0198] In this embodiment, the process of creating a storyboard was described using the flowchart in Figure 26. However, it is not necessary to execute all the processes in Figure 26, but only some of them. For example, S2601 to S2602 may be executed to create a video proposal, S2601 to S2603 may be executed to create a video concept, or S2601 to S404 may be executed to create a video storyline.
[0199] Furthermore, in this embodiment, although Figure 1 describes a configuration in which the information processing device 101, application server 102, and generation AI server 103 are connected via a network, the program stored in the application server 102 (Figure 3B) may be stored in the information processing device 101, and the flowcharts shown in Figures 26 to 28 may be executed in the information processing device 101 without using the application server 102. In that case, the information processing device 101 and the generation AI server 103 communicate directly via the network.
[0200] Furthermore, although this embodiment describes an example using the generation AI server 103, it is also possible to store a lookup table (LUT) in the storage device 215 of the application server 102 and perform each process using the LUT without using the generation AI server 103. For example, in S2702 of Figure 27, a LUT may be used that takes information related to video generation as input and outputs a question, or in S505 of Figure 27, a LUT may be used that takes the answer to the question as input and outputs a project proposal. When performing each process using a LUT, as shown in Figure 3D, the application server 102 has a project proposal creation unit 311, a concept creation unit 312, a storyline creation unit 313, an image creation unit 314, and a storyboard creation unit 315.
[0201] When using a LUT, the number of input / output patterns is limited, but when using the generation AI server 103, a larger number of input / output patterns can be used than when using a LUT, allowing for high-precision output for a given input.
[0202] According to this embodiment, information for video production can be created and displayed within the budget for the accepted filming. This prevents exceeding the filming budget after generating the storyboard, avoids the need to recreate the proposal, concept, storyline, and storyboard from scratch, and reduces the processing load on the device that generates the proposal, concept, storyline, and storyboard.
[0203] This disclosure can also be implemented by supplying a program that implements one or more of the functions of the embodiments described above to a system or device via a network or storage medium, and by a computer in that system or device reading and executing the program. The computer has one or more processors or circuits and may include a plurality of separate computers or a network of a plurality of separate processors or circuits for reading and executing computer executable instructions.
[0204] A processor or circuit may include a central processing unit (CPU), a microprocessing unit (MPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), or a field-programmable gateway (FPGA). It may also include a digital signal processor (DSP), a dataflow processor (DFP), or a neural processing unit (NPU).
[0205] While various embodiments have been described in detail above, it should be understood that this disclosure is not limited to these embodiments and encompasses all modifications, variations, substitutions, and equivalents included within the claims.
[0206] This disclosure is not limited to the embodiments described above, and various modifications and alterations are possible without departing from the spirit and scope of this disclosure. Accordingly, the following claims are attached to make the scope of this disclosure public.
[0207] This application claims priority based on European Patent Application No. 25159754.8, filed on 24 February 2025, the entire contents of which are incorporated herein by reference.
Claims
1. A server device used for video production comprising a plurality of processes including a first process for generating first information for video production and a second process for generating second information for video production based on the generated first information, An instruction means for instructing an AI server to generate the first information using the AI of the first role, A first generation means for generating first display data, which includes the first information received from the AI server, and which does not accept character input from the user but includes a review instruction unit that accepts instructions for reviewing the first information, A first transmission means for transmitting the first display data generated by the first generation means to an information processing device, A second transmission means that transmits a prompt to the AI server based on an instruction received from the information processing device to the review instruction unit, Based on a prompt transmitted by the second transmission means, the second generation means generates second display data including improvements to the first information generated by an AI in a second role different from the first role, the improvements being generated by reviewing the first information by overseeing multiple processes including the first and second processes, and the second generation means generates second display data including these improvements. A third transmission means for transmitting the second display data generated by the second generation means to the information processing device, The instruction means instructs the AI server to perform the second processing based on the instruction for performing the second processing received from the information processing device. A server device characterized by the following features.
2. The server device according to claim 1, characterized in that the review instruction unit is located closer to the location of the comment made by the AI in the second role than to the location of the comment made by the AI in the first role.
3. The server device according to claim 1, characterized in that when the AI server is instructed to perform the second processing without receiving instructions to the review instruction unit, the second display data is not generated.
4. The server device according to claim 1, characterized in that the review instruction unit includes text indicating the content of the review request.
5. The second display data includes a reflection instruction unit that receives instructions to reflect the improvements, The server device according to claim 1, further comprising a fourth transmission means for transmitting to the information processing device third display data, which includes information reflecting the improvements to the first information, in accordance with instructions to the reflection instruction unit.
6. The server device according to claim 5, characterized in that the reflection instruction unit is located near the improvement point.
7. The server device according to claim 1, characterized in that the first display data includes a reception unit for receiving comments on the first information.
8. The server device according to claim 7, characterized in that the instruction means instructs the AI server to modify the first information based on the opinion received by the reception unit.
9. The server device according to claim 1, characterized in that the first information is information generated based on the type of video received from the information processing device.
10. The server device according to claim 9, characterized in that the type of video is information based on text input from a user.
11. The server device according to claim 1, characterized in that the first role is that of a strategist and the second role is that of a creative director.
12. The server device according to any one of claims 1 to 11, characterized in that the plurality of processes are two or more processes from the processes of creating a project proposal, creating a concept, creating a storyline, creating images, and creating a storyboard.
13. The server device according to claim 1, characterized in that the first display data is a first web page and the second display data is a second web page.
14. The server device according to claim 1, characterized in that it does not instruct the AI server to perform the second processing until it receives an instruction from the information processing device to perform the second processing.
15. The server device according to claim 1, characterized in that the first information is a concept and the second information is a storyline.
16. An information processing method performed by a server device used for video production, comprising a plurality of processes including a first process for generating first information for video production and a second process for generating second information for video production based on the generated first information, An instruction step of instructing the AI server to generate the first information using the AI in the first role, A first generation step for generating first display data, which includes the first information received from the AI server, and which does not accept character input from the user but includes a review instruction unit that accepts instructions for reviewing the first information; A first transmission step of transmitting the first display data generated by the first generation step to an information processing device, A second transmission step involves sending a prompt to the AI server based on an instruction received from the information processing device to the review instruction unit, Based on the prompt transmitted in the second transmission step, the AI in a second role, which has a different role from the first role, generates improvements to the first information, which are generated by reviewing the first information by overseeing multiple processes including the first and second processes, and the second generation step generates second display data including the improvements, A third transmission step involves transmitting the second display data generated by the second generation step to the information processing device, The instruction step is characterized by instructing the AI server to perform the second processing based on an instruction for performing the second processing received from the information processing device.
17. A server device according to any one of claims 1 to 11, An information processing device having a receiving means that is communicatively connected to the server device and receives the first display data and the second display data from the server device, and a display control means that displays the first display data and the second display data received by the receiving means on a display unit, An information processing system equipped with the following features.
18. A program for causing a computer to function as the server device described in Claim 1.
19. A server device used for video production comprising a plurality of processes including a concept generation process for generating a concept and a storyboard generation process for generating a storyboard based on the generated concept, A receiving means that receives information and budget related to video generation from an information processing device, A first instruction means that instructs an AI server to generate a storyboard corresponding to the video generation information and the shooting plan based on the budget using AI, A first generation means for generating first display data, including a storyboard received from the AI server, The system includes a first transmission means for transmitting the first display data generated by the first generation means to the information processing device. A server device characterized by the following features.
20. A server device used for video production comprising a plurality of processes including a first process for generating first information for video production and a second process for generating second information for video production based on the generated first information, A receiving means that receives information and budget related to video generation from an information processing device, A first instruction means that instructs an AI server to generate the information related to the video generation and the second information corresponding to the shooting plan based on the budget using AI, A first generation means for generating first display data including the second information received from the AI server, A first transmission means for transmitting the first display data generated by the first generation means to the information processing device, A second instruction means for instructing the AI server to generate revised second information corresponding to the shooting plan based on the revised budget received from the information processing device, A second generation means for generating second display data, which includes the modified second information received from the AI server, A server device characterized by having a second transmission means for transmitting the second display data generated by the second generation means to the information processing device.
21. The information relating to the video generation includes at least one of the following: the type of video, the length of the video, and the purpose of the video. The server device according to claim 20, characterized in that the aforementioned plurality of processes are two or more processes from among a project proposal, a concept, a storyline, an image, and a storyboard.
22. The server device according to claim 19 or 20, characterized in that the first instruction means instructs the AI server to generate a video production plan based on the video generation information, and to generate a video production concept based on the plan and the budget.
23. The server device according to claim 19 or 20, characterized in that the budget includes at least one of the total amount of the budget and the allocation ratio of the budget to the budget components constituting the budget.
24. The server device according to claim 23, characterized in that the budget allocation ratio is information based on instructions from the user.
25. The server device according to claim 23, characterized in that the budget allocation ratio can be input by the user via an instruction unit.
26. The server device according to claim 23, characterized in that the budget components include at least one of a filming location, a talent who is the subject of filming, and equipment used for filming.
27. The receiving means receives multiple budgets, The first instruction means instructs the AI server to generate multiple storyboards for each of the multiple budgets, The first generation means generates second display data, which includes a plurality of storyboards received from the AI server. The server device according to claim 19, characterized in that the first transmission means transmits the second display data generated by the first generation means to the information processing device.
28. The second information includes a plurality of storyboards, Furthermore, a third generation means generates a fourth display data which arranges the multiple storyboards according to location using information indicating the location where the video associated with each storyboard is filmed, The server device according to claim 1, further comprising a fifth transmission means for transmitting the fourth display data generated by the third generation means to the information processing device.
29. The server device according to claim 1, wherein the second information includes a plurality of storyboards, the first generation means generates fifth display data which arranges the plurality of storyboards into storyboards which can propose a shooting plan and storyboards which are recommended to be generated by AI, and transmits the fifth display data generated by the first generation means to the information processing device.
30. The server device according to claim 19 or 20, characterized in that the first instruction means instructs the AI server to generate a concept based on the budget using the AI and to generate a storyboard based on the generated concept.
31. The server device according to claim 19, An information processing device having a receiving means that is communicatively connected to the server device and receives the first display data from the server device, and a display control means that displays the first display data received by the receiving means on a display unit, An information processing system equipped with the following features.
32. The server device according to claim 20, An information processing device having a receiving means that is communicatively connected to the server device and receives the first display data and the second display data from the server device, and a display control means that displays the first display data and the second display data received by the receiving means on a display unit, An information processing system equipped with the following features.
33. An information processing method performed by a server device used for video production, comprising a plurality of processes including a concept generation process for generating a concept and a storyboard generation process for generating a storyboard based on the generated concept, A receiving process that receives information and budget related to video generation from an information processing device, An instruction step of instructing an AI server to generate a storyboard corresponding to the information related to the video generation and the shooting plan based on the budget using AI, A first generation step of generating first display data, including a storyboard received from the AI server, The process includes a first transmission step of transmitting the first display data generated by the first generation step to the information processing device. An information processing method characterized by the following:
34. An information processing method performed by a server device used for video production, comprising a plurality of processes including a first process for generating first information for video production and a second process for generating second information for video production based on the generated first information, A receiving process that receives information and budget related to video generation from an information processing device, An instruction step of instructing an AI server to generate the information related to the video generation and the second information corresponding to the shooting plan based on the budget using AI, A first generation step of generating first display data including the second information received from the AI server, A first transmission step of transmitting the first display data generated by the first generation step to the information processing device, A second instruction step instructs the AI server to generate revised second information corresponding to the shooting plan based on the revised budget received from the information processing device, A second generation step of generating second display data including the modified second information received from the AI server, An information processing method characterized by comprising a second transmission step of transmitting the second display data generated by the second generation step to the information processing device.
35. A program for causing a computer to function as the server device described in claim 19 or 20.
36. A program that causes a computer to function as an information processing device used for video production, comprising a plurality of processes including a first process for generating first information for video production and a second process for generating second information for video production based on the generated first information, The aforementioned computer, An instruction means for instructing an AI server to generate the first information using the AI of the first role, A first generation means for generating first display data, which includes the first information received from the AI server, and which does not accept character input from the user but includes a review instruction unit that accepts instructions for reviewing the first information, A first display control means for displaying the first display data generated by the first generation means to a display unit, A second transmission means that transmits a prompt based on the instructions given to the review instruction unit to the AI server, Based on a prompt transmitted by the second transmission means, the second generation means generates second display data including improvements to the first information generated by an AI in a second role different from the first role, the improvements being generated by reviewing the first information by overseeing multiple processes including the first and second processes, and the second generation means generates second display data including these improvements. The second display data generated by the second generation means is made to function as a second display control means for displaying the data on the display unit. The instruction means is characterized by instructing the AI server to perform the second processing based on the instruction to perform the second processing. program.
37. The program according to claim 36, characterized in that the review instruction unit is located closer to the position of the comment made by the AI in the second role than to the position of the comment made by the AI in the first role.
38. The program according to claim 36 or 37, characterized in that the plurality of processes are two or more processes from among the processes of creating a proposal, creating a concept, creating a storyline, creating images, and creating a storyboard.
39. The program according to claim 36 or 37, characterized in that the first role is a strategist and the second role is a creative director.
40. The program according to claim 36 or 37, characterized in that when the AI server is instructed to perform the second processing without receiving instructions to the review instruction unit, the second display data is not generated.
41. A program that causes a computer to function as an information processing device used for video production, comprising a plurality of processes including a concept generation process for generating a concept and a storyboard generation process for generating a storyboard based on the generated concept, The aforementioned computer, An instruction means for instructing an AI server to generate a storyboard corresponding to a shooting plan based on information and budget related to video generation using AI, A first generation means for generating first display data, including a storyboard received from the AI server, The first display data generated by the first generation means is configured to function as a display control means for displaying the data on the display unit. program.
42. A program that causes a computer to function as an information processing device used for video production, comprising a plurality of processes including a first process for generating first information for video production and a second process for generating second information for video production based on the generated first information, The aforementioned computer, A first instruction means that instructs an AI server to generate the second information corresponding to the shooting plan based on the budget and information related to video generation using AI, A first generation means for generating first display data including the second information received from the AI server, A first display control means for displaying the first display data generated by the first generation means to a display unit, A second instruction means for instructing the AI server to generate revised second information corresponding to the shooting plan based on the revised budget, A second generation means for generating second display data, which includes the modified second information received from the AI server, The second display control means is characterized by having the second display data generated by the second generation means function as a means for displaying the data on the display unit. program.
43. The program according to claim 41 or 42, wherein the budget includes at least one of the total amount of the budget and the allocation ratio of the budget to the budget components constituting the budget.
44. The program according to claim 43, characterized in that the budget allocation ratio can be input by the user via an instruction unit.
45. The program according to claim 41 or 42, characterized in that the information relating to the video generation includes at least one of the type of video, the length of the video, and the purpose of the video.
46. The program according to claim 42, characterized in that the plurality of processes are two or more processes selected from the processes of creating a project proposal, creating a concept, creating a storyline, creating images, and creating a storyboard.