Information processing system, information processing method, and program
The information processing system addresses the burden of creating advertisements by using a generation AI model to generate storyboard data, thereby automating and streamlining the production process.
Patent Information
- Application Number
- JP2024192876
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-11-01
- Publication Date
- 2025-05-16
- Estimated Expiration
- 2044-11-01
AI Technical Summary
The process of creating production products like advertisements is burdensome due to the need to consider various factors such as themes, image and video content, and narration.
An information processing system that includes a data acquisition unit and a data generation unit, utilizing a generation AI model to generate storyboard data for production targets like advertisements, thereby reducing the production burden.
The system automates the generation of storyboard data, significantly reducing the time and effort required for creating advertisements, while allowing for easier handling of modifications and improvements in the visual and narrative aspects of the production.
Smart Images

Figure 0007678922000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]
[0002] Conventionally, various proposals have been made regarding systems for creating creative works (production targets) such as advertisements (for example, Patent Document 1). Patent Document 1 discloses a system for automatically generating advertising copy, but the form of advertisements is not limited to text. One example is an advertising video (commercial) broadcast on television, etc. As a preliminary preparation for the production of an advertising video, a storyboard is created that visually represents each scene in the advertising video. The storyboard is created in the early stages of the production of the advertising video to explain the flow and composition of the video. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2024-017517 A Summary of the Invention [Problem to be solved by the invention]
[0004] For example, when producing a work (production subject) such as an advertisement, a wide range of elements must be considered, such as the theme, the content of images and videos, and narration, which poses a problem of heavy workload.
[0005] The present invention aims to reduce the burden on those involved in the production of a production (production subject) such as an advertisement. [Means for solving the problem]
[0006] According to the present invention, there is provided an information processing system for generating storyboard data for an object to be produced, comprising a data acquisition unit and a data generation unit, wherein the data acquisition unit is configured to be able to acquire content data, the content data including data relating to contents of scenes in the object to be produced, the data generation unit is made up of a generative AI model, and the data generation unit is configured to generate the storyboard data corresponding to the scenes in the object to be produced based on the content data.
[0007] According to the present invention, the data generation unit is configured to generate storyboard data corresponding to scenes in a production target based on content data, thereby reducing the burden on those involved in the production of a production (production target) such as an advertisement. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 shows an example of a system configuration of an information processing system 100 according to the embodiment. [Diagram 2] FIG. 2 is a block diagram showing a hardware configuration of the information processing device 1. As shown in FIG. [Diagram 3] FIG. 3 is a functional block diagram of the control unit 12 shown in FIG. [Figure 4] Fig. 4 is an example of a display screen ds1 (user interface) displayed on the user terminal 2 when automatically generating scene data d12 as character data. The display screen ds1 shown in Fig. 4 shows an example of an area (input text box) where project content (project data d11) as character data is input. [Diagram 5] Fig. 5 is an example of a display screen ds2 (user interface) displayed on the user terminal 2 when automatically generating storyboard data d3 (see Fig. 6) including a storyboard image d31. The display screen ds2 shown in Fig. 5 shows an example of an area (input text box) where scene data d12 as character data is input. [Figure 6]FIG. 6 is an example of a storyboard (storyboard data d3) showing one scene in an advertisement video. [Figure 7] FIG. 7 is an explanatory diagram showing a schematic diagram of the flow of various data in the information processing device. [Figure 8] FIG. 8 is an example of a flowchart of information processing in the information processing system 100 according to the embodiment. [Figure 9] FIG. 9 shows a modified example of the configuration of the information processing system 100 according to the embodiment. [Figure 10] FIG. 10 shows a modified example of the configuration of the information processing device 1 according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Various features shown in the following embodiments can be combined with each other. Also, each feature can be an invention independently.
[0010] 1. System configuration of information processing system 100 The information processing system 100 is a system that automatically generates a storyboard to visually express the contents of a production (production target) in the production of the production. In the embodiment, the production (production target) is described as an advertising video. In other words, the information processing system 100 takes over the work of producing a storyboard, which was previously done manually, and significantly improves the efficiency of the storyboard production work, thereby making it possible to reduce the time and labor burden of producing an advertising video. Here, the production (production target) may be an image (still image), but the embodiment is preferably applied to a video. Furthermore, the production (production target) is not limited to advertisements, but may be promotional content (for example, program advertisements, announcements, presentations, events, business plans for stores and services) or entertainment content (for example, TV programs, movies, plays, games) in accordance with the request of the production client.
[0011] The information processing system 100 is configured to integrate the functions of acquiring, generating, editing, and outputting data, and to be able to manage a wide range of data. In addition, by generating a storyboard as a preliminary step rather than generating the advertising video itself in the information processing system 100, the visuals and story of the advertisement can be grasped in advance, and it is easy to respond to minute corrections, making the information processing system 100 a system with improved convenience.
[0012] As shown in FIG. 1, the information processing system 100 includes an information processing device 1 and a user terminal 2. These are connected so as to be able to exchange information via a communication network 3 (for example, the Internet, etc.). Note that the communication network 3 may be a closed network separated from the Internet in part or in whole. Each component of the information processing system 100, such as the information processing device 1, has one or more functions (functional units). Each component may be configured as a single device as shown in FIG. 1, or may be configured as multiple independent devices configured to be able to exchange information. The same applies to each functional unit, such as a control unit 12 of the information processing device 1 described later. Each component included in the information processing system 100 will be further described below.
[0013] 1-1. Information processing device 1 As shown in FIG. 2, the information processing device 1 has a communication unit 10, a memory unit 11, a control unit 12, an output unit 13, and an input unit 14, and these components are electrically connected within the information processing device 1 via a communication bus 15. 3, the control unit 12 includes a data acquisition unit 121, a data generation unit 122, a prompt generation unit 123, and a data presentation unit 124. The data generation unit 122 includes a first generation unit 122a, a second generation unit 122b, and a data editing unit 122c.
[0014] Each of the above components may be realized by software or by hardware. When realized by software, various functions can be realized by a CPU executing a computer program. The program may be stored in a non-transitory recording medium that can be read by a computer, or may be provided so as to be downloadable from an external server, or may be realized by so-called cloud computing, which reads out a program stored in an external storage unit and realizes the function. When realized by hardware, it can be realized by various circuits such as ASIC, FPGA, or DRP. In the embodiment, various information and concepts that include the information are handled, and these are represented by high and low signal values or quantum bits as a binary bit collection consisting of 0 or 1, and communication and calculation can be performed by the above software or hardware aspects. The software may be a general-purpose OS or a dedicated OS.
[0015] The communication unit 10 may employ a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc. The communication unit 10 may employ a configuration in which it is connected to the communication network 3 via a wireless communication means such as wireless LAN network communication, mobile communication such as 3G / LTE / 5G, Bluetooth (registered trademark) communication, etc. The communication unit 10 may also employ a configuration in which the above-mentioned wired communication means and wireless communication means are used in combination.
[0016] The storage unit 11 stores, for example, various programs, constants, variables, and setting values of the information processing device 1 executed by the control unit 12. The storage unit 11 also stores, for example, data acquired by communicating with the user terminal 2. The storage unit 11 may employ, for example, a storage device such as a solid state drive (SSD), or a storage medium such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to program calculations. The information processing device 1 may also use an external storage unit (for example, an external storage medium, cloud, etc.) in addition to the storage unit 11.
[0017] The control unit 12 is configured to execute information processing of the information processing device 1. The control unit 12 can be configured, for example, by a central processing unit (CPU), and in the embodiment, the control unit 12 is an example of a processor capable of executing programs related to the operation (steps) of the information processing device 1 described below. The control unit 12 realizes various functions related to the information processing device 1, for example, by reading out programs stored in the storage unit 11. Furthermore, the information processing of the software in the information processing device 1 is realized, for example, by the control unit 12 as hardware processing various programs stored in the storage unit 11.
[0018] The output unit 13 is, for example, a display unit of the information processing device 1. The output unit 13 may be, for example, included in the housing of the information processing device 1 or may be externally attached. The output unit 13 displays a screen of a graphical user interface (GUI) that can be operated by a user. For example, the output unit 13 may be a display device such as a CRT display, a liquid crystal display, an organic EL display, a plasma display, or an electronic paper display, as well as a display device such as a light that can be turned on or a projector. It is optional whether or not the information processing device 1 includes the output unit 13. For example, the output of the information processing device 1 may be displayed on a display unit that is located at a location independent of the location where the information processing device 1 is installed. The output unit 13 may also have a device that outputs audio.
[0019] The input unit 14 is configured to receive, for example, an operation input made by an administrator of the information processing device 1. The input unit 14 may be included in the housing of the information processing device 1, or may be attached externally. For example, a touch panel, a switch button, a mouse, a keyboard camera, a scanner, or the like may be adopted as the input unit 14. It is optional whether or not the information processing device 1 includes the input unit 14. For example, the information processing device 1 may receive an operation input to the information processing device 1 via an information processing terminal located at a location independent of and separate from the location where the information processing device 1 is installed.
[0020] 1-2. User terminal 2 1 is an information processing device (for example, a personal computer) used by a person receiving the provision of the automatic storyboard generation service, and is a terminal that can access the information processing device 1. The user terminal 2 is capable of information processing such as outputting data to the information processing device 1 in order to generate a desired storyboard, and is also capable of information processing such as accepting and displaying various data generated by the information processing device 1.
[0021] 2. Functional configuration The functional configuration of the information processing device 1 according to this embodiment will be described with reference to Fig. 3. Information processing by software stored in the storage unit 11 is specifically realized by the control unit 12, which is an example of hardware, and each functional unit included in the control unit 12 is executed.
[0022] 2-1. Data Acquisition Unit 121 The data acquisition unit 121 is configured to acquire various data transmitted from the user terminal 2. The data acquisition unit 121 is also configured to acquire various data accepted from the input unit 14. Furthermore, the data acquisition unit 121 can also acquire data stored in advance in the storage unit 11, for example, and may also be configured to collect (acquire) various data from any external server or the like connected to the Internet via the communication unit 10.
[0023] In the embodiment, the data acquisition unit 121 is capable of acquiring content data d1 and editing instruction data d2, as shown in Fig. 7. These pieces of data will be described later in "3. Data used in the information processing system 100". The function of data acquisition unit 121 may be a function to receive similar data and transmit it to another functional unit (for example, prompt generation unit 123), or a function to perform a predetermined process (preprocessing) on the received data to create desired data and then transmit it to another functional unit, or it may be both of these functions. In other words, acquisition does not only involve simply acquiring data, but may also include processing to modify the data by preprocessing.
[0024] 2-2. Data generation unit 122 The data generating unit 122 is configured to generate storyboard data d3 corresponding to scenes in the advertisement video based on the content data d1. In the embodiment, the data generating unit 122 has a first generating unit 122a and a second generating unit 122b, and is capable of generating the storyboard data d3 through a step-by-step process.
[0025] In an example of the embodiment, the first generating unit 122a generates scene data d12 based on the content data d1. In the embodiment, the content data d1 is included in prompt data dp generated by the prompt generating unit 123 described later, and the first generating unit 122a processes the prompt data dp when generating the scene data d12. The information processing system 100 can output the scene data d12 to the user terminal 2 once, and if necessary, the user can edit the scene data d12. That is, the information processing system 100 allows a preview of the scene data d12, and if necessary, the scene data d12 can be used in the next information processing (generation of storyboard data d3) after editing. The scene data d12 is also included in the content data d1. In the embodiment, the scene data edited by the user is also referred to as scene data d12.
[0026] In one example of the embodiment, the second generating unit 122b generates storyboard data d3 based on scene data d12, which is the content data d1. That is, in the embodiment, the storyboard data d3 is generated in stages (the scene data d12 is generated first, and then the storyboard data d3 is generated). This makes it easier to make small corrections, and is expected to have the effect of improving the completeness of the advertising video. Note that, in the embodiment, the scene data d12 is included in prompt data dp generated by the prompt generating unit 123, which will be described later, and the second generating unit 122b processes this prompt data dp when generating the storyboard data d3. The second generating unit 122b generates storyboard data d3 that is a combination of not only image data but also character data such as narration. In this manner, the embodiment employs a stepwise information process in which scene data d12 is generated and then storyboard data d3 is generated. Note that the information process for generating the storyboard data d3 is not limited to this, and other examples will be described in a modified example below with reference to FIG. 10.
[0027] The data generation unit 122 further includes a data editing unit 122c. The data editing unit 122c is configured to edit data (scene data d12 and storyboard data d3) based on the editing instruction data d2.
[0028] The data generation function of the data generation unit 122 uses a generative AI model (large-scale language model). In other words, the data generation unit 122 is configured with a generative AI model, and upon receiving input data, is capable of generating scene data d12 and storyboard data d3 as output. Here, the generative AI model of the data generating unit 122 can be configured by adding specific data (unique data) to a trained generative AI model and re-training it. This specific data (unique data) will be described in detail later. In addition, as a method of re-learning, for example, fine tuning, transfer learning, short-shot learning, etc. can be adopted. In addition, RAG (Retrieval-Augmented Generation) may be used for the data generation function of the data generating unit 122.
[0029] In the embodiment, the first generating unit 122a and the second generating unit 122b are described as being configured with independent generative AI models, but this is not limited thereto. Data may be generated in stages using one generative AI model. That is, the scene data d12 is generated first, and then the storyboard data d3 is generated. In addition, these generating units may be specialized according to the target to be generated. For example, the first generating unit 122a may be retrained with specific data (unique data) so as to be specialized for document generation, and the second generating unit 122b may be retrained with specific data (unique data) so as to be specialized for image generation. In other words, the specific data used to retrain the generative AI model is different between the first generating unit 122a and the second generating unit 122b.
[0030] 2-3. Prompt Generation Unit 123 The prompt generation unit 123 has a function of generating a prompt to be input to the generation AI model. The prompt generation unit 123 can generate prompt data dp having contents in which a predetermined sentence (hereinafter also referred to as a fixed sentence) is added to various data (content data d1 and editing instruction data d2) acquired from the data acquisition unit 121, for example. The template may be, for example, an instruction to generate data taking into consideration the following data (content data d1 and editing instruction data d2), but the content is not limited thereto. Furthermore, the prompt data dp may be the character (symbol) information contained in the content data d1 or the editing instruction data d2 itself, or may have been modified. Needless to say, the prompt data dp may also include an image, for example, in the same way that the content data d1 or the editing instruction data d2 may include image data. The modification is, for example, modification that increases the accuracy of data generation, such as segmenting character (symbol) information contained in the content data d1 and the editing instruction data d2.
[0031] 2-4. Data presentation section 124 The data presentation unit 124 has a function of presenting a display screen for accepting various data from the user. As a result, the screen is displayed on the display unit of the user terminal 2. The presented display screen may be, for example, FIG. 4 (a screen for accepting project data d11) or FIG. 5 (a screen for accepting scene data d12, etc.). The presentation means by the data presentation unit 124 may be only the display of an image, but may also additionally use sound.
[0032] 3. Data Description in Information Processing System 100 Here, various types of data used in the information processing system 100 will be described. In the embodiment, as shown in FIG. 7, the information processing system 100 exchanges data such as content data d1, prompt data dp, editing instruction data d2, and storyboard data d3. In the embodiment, the generated AI model in the data generating unit 122 is a model that has been re-learned using specific data (unique data) as described above.
[0033] 3-1. Content data d1 The content data d1 is data for generating various data (scene data d12 and storyboard data d3) by the data generating unit 122. The content data d1 includes at least one of the project data d11, the scene data d12, and the expression format data d13. In the embodiment, all of the project data d11, the scene data d12, and the expression format data d13 are included.
[0034] <Project data d11> The project data d11 is created and prepared by the user. In the embodiment, the scene data d12 is automatically generated, but since it is once output from the data generation unit 122 and presented (displayed) to the user and can be edited if necessary, the scene data d12 can also be said to be data created and prepared by the user. Of course, the scene data d12 may be in a form in which the user cannot edit it and the content generated by the data generation unit 122 is automatically determined. In the embodiment, the project data d11 and the scene data d12 described later are character data (including numbers and symbols, and the language is not limited to Japanese), but may also include images.
[0035] The project data d11 can include at least one of a direct object in the production object, a theme of the production object, a target of the production object, a length of the production object, and an expression technique of the production object. Direct objects in the production target may include, for example, products, services, brands, logos, names, catchphrases, names of organizations such as companies, programs, videos, movies, talents, characters, product names, genres, etc. The form may be character (symbol) data or image data. The theme of the production object corresponds to, for example, a concept to be communicated to users through the production object, and is character data indicating what impression or emotion is to be given to the viewer, and what action is to be encouraged. The target of the production is information about the audience, and can be expressed based on information such as gender, age, area of residence, personal status, personal hobbies, etc. For example, the target audience may be working women in their 20s and 30s. The expression method of the production subject may include, for example, whether or not audio (narration) and music are included, and if audio is included, the type of audio (gender, voice quality, voice volume, etc.), and if music is included, the genre of music.
[0036] In the embodiment, the production target is an advertisement video. In this case, the project data d11 includes at least one of the advertising target of the advertisement video, the theme of the advertisement video, the length of the advertisement video, the target of the advertisement video, and the expression method of the advertisement video. The advertising target of the advertising video may include, for example, a product, a service, a brand, a logo, a name, a catchphrase, a name of an organization such as a company, a program, a video, a movie, a talent, a character, a product name, a genre, etc. Also, the form may be character (symbol) data or image data. The theme of an advertising video corresponds to the concept to be conveyed through the advertising video, and is text data that indicates what impression or emotion it will give to the viewer and what action it will encourage. For example, in the hot summer, cooling the body with an air conditioner can make you sick, so clothing that prevents the air conditioner's wind from blowing directly on the body may be used. The length of the advertisement video is data indicating the total playback time of the advertisement video. Note that the length of the advertisement video may refer to the length of each scene in the advertisement video. The target of an advertising video is information about the audience that the advertising video is intended for, and can be expressed, for example, as information based on gender, age, area of residence, personal status, personal hobbies, etc. For example, it could be women in their 20s and 30s who are in the prime of their working lives. The expression technique of an advertising video may include, for example, whether or not it includes audio (narration) and music, and if it includes audio, the type of audio (gender, voice quality, voice volume, etc.), and if it includes music, the genre of music.
[0037] <Scene data d12> The scene data d12 is character data showing (explaining) a scene in the production target (in the embodiment, an advertising video). Note that the scene data d12 may additionally include image data. However, this image data is different from the image data (storyboard image d31) finally generated by the second generation unit 122b. The scene data d12 is composed of data of a series of scenes in the advertisement video. In other words, the scene data d12 is premised on the existence of data for each scene in the advertisement video, and this point is a major difference from the project data d11. In other words, the contents of the project data d11 do not need to be divided by scene.
[0038] The scene data d12 preferably includes at least one of the following elements: a commercial story outline, narration, subtitles, music, sound effects, storyboard instructions (e.g., to have the actors move in a certain way), location, and background. The prompt data dp is preferably configured to include at least one of these elements, and the first generator 122a is preferably re-learned so that these elements are appropriately generated.
[0039] <Expression format data d13> The expression format data d13 is data indicating the expression format of data (storyboard image d31 of storyboard data d3 in the embodiment) generated by the data generating unit 122. In the embodiment, the expression format data d13 corresponds to the content selected by the user. That is, in one example of the embodiment, a painting style is adopted as the expression format data d13, and the expression format data d13 corresponds to the type of painting style selected by the user.
[0040] The expression format can include various formats, but for example, the style, contrast, saturation, aspect ratio of the video (image), frame rate, and camera angle (close-up, wide angle, telephoto) of the subject of production (in this embodiment, an advertising video) can be adopted. In one embodiment, the style of advertising video is adopted as the expression format, and there are three types of styles: realistic, illustration, and line drawing. Of course, there is no limitation to these. For example, watercolor painting, pencil, colored pencil, crayon, oil painting, anime, CG, Japanese painting, and other styles may be adopted. In addition, realistic tones depict objects in a realistic manner, like a photograph. The tone of the illustrations is not a faithful depiction of reality; for example, the subjects are depicted in a deformed manner. Line art is a simple depiction made using lines only. In the example shown in FIG. 5 and FIG. 6, the line drawing style is selected for the storyboard image d31 of the storyboard data d3.
[0041] 3-2. Specific Data DR (Proprietary Data) The specific data dr is training data for retraining the generative AI model. Retraining the model with the specific data dr makes it possible to adjust and customize the output from the generative AI model. The specific data dr can include at least one of production object image data dr1, thumbnail data dr2, and data dr3 corresponding to analysis results or research results related to the production object.
[0042] The production object image data dr1 is, for example, data corresponding to CM content (image data in a CM). The CM content is, for example, image data constituting a video related to the production object, and may be the entire video or a part (image). For example, if the production object is an advertisement video, the CM content can be image data constituting the advertisement video. Furthermore, the CM content is not limited to CMs that have already been aired, and CM content that has not been aired may also be used. The production target image data dr1 may be accompanied by metadata, which may include, for example, product names, product genres, corporate or organization names, performer names, catchphrases, lines, subtitles, viewer ratings, 10-digit CM codes, languages, regions, material lengths, seconds, campaign periods, expected targets, broadcasting stations, media, broadcast times, and broadcast frequency.
[0043] The thumbnail data dr2 is, for example, video (image) data obtained by extracting a portion with a high emotion score from a commercial content (image data in a commercial). The emotion score can be obtained, for example, by using emotion visualization technology. Here, emotion visualization technology calculates a scoring value (emotion score) of an emotion label (for example, various emotions such as happy, sad, etc.) for each scene or time of the video, which is the content material. For the thumbnail data dr2, an image with a high score for a specific emotion label from the video thus obtained is used.
[0044] The data dr3 corresponding to the analysis result or the investigation result may be, for example, data such as a commercial questionnaire investigation result, a pure recall rate, a recall rate, a norm value, an emotion visualization waveform, or a commercial analysis report. The results of the CM questionnaire survey are data corresponding to the results of a questionnaire survey on impressions and impressions received regarding various advertising videos. The pure recall rate is an indicator of the percentage of viewers who can spontaneously recall a specific advertising target, for example, a brand, when no clues about the advertising target are given. It is used to evaluate whether the advertising target leaves a deeper impression than competitors. Recall rate is an index that indicates the percentage of viewers who recall an advertising target, such as a brand, when given a clue about the advertising target, and is used to evaluate the recognition of the advertising target. The norm value is, for example, a value used to evaluate the effectiveness of advertising. The norm value can be defined from various perspectives. For example, a value showing the relationship between the number of exposures to a certain commercial and its recall rate can be used. The emotion visualization waveform is data showing the time progression of the scoring values of the emotion labels described above. The commercial analysis report is not limited in content, but is a report that analyzes the effectiveness of any commercial from various angles, and may include various perspectives such as commercial recognition rate, favorability, level of interest in the product, and level of purchase stimulation. Although the data dr3 has been described above, various survey results and analysis results regarding the data dr3 may use data aggregated for each target. The target is not particularly limited, but may be represented by information based on, for example, gender, age, area of residence, personal status, personal hobbies and preferences, use of products and services, intention to use, media contact status, etc.
[0045] 3-3. Editing instruction data d2 The edit instruction data d2 is data for instructing editing of the data generated by the data generating unit 122. The edit instruction data d2 itself is created, prepared, and selected by the user. The edit instruction data d2 includes edit target data d21, edit shape data d22, and edit image data d23. The editing target data d21 is character data indicating the editing target, and can include data such as what the editing target is and the position of the editing target. The editing target data d21 can also include data specifying an editing method, such as how to edit the editing target (for example, change the position, change the size, change the color, or replace with edited image data d23). The editing target is not particularly limited, but when the editing target is a storyboard image d31 of the storyboard data d3, for example, image data of a figure (logo) related to the advertising target can be edited. The edit shape data d22 is data that specifies the shape (contour) of the edit target, and in the embodiment, is selectable by the user. In one embodiment, there are options such as "rectangle" and "as per the shape of the edit target". For example, if a rectangular logo is shown in the image and the logo is the edit target, it is recommended to select "rectangle". Also, if a flower with a complex contour is shown in the image, it is recommended to select "as per the shape of the edit target". The edited image data d23 is image data showing how to change the edited object. For example, when modifying a logo, this corresponds to an image of the logo to be replaced. In the embodiment, the edited image data d23 is used to improve the editing accuracy because the character data of the edited object data d21 cannot fully express the color or shape to be modified.
[0046] 3-4. Storyboard data d3 6 includes a storyboard image d31, and in addition, the storyboard data d3 further includes at least one of scene description data d32 and audio data d33. In the embodiment, both the scene description data d32 and the audio data d33 are included.
[0047] The storyboard image d31 is data that is essential to the storyboard data d3. Although only the storyboard data d3 of one scene is shown in Fig. 6, in reality, the storyboard data is made up of storyboard data of a series of scenes. In other words, a storyboard image d31 is generated for each scene. The same applies to the scene description data d32 and audio data d33 described below.
[0048] The scene description data d32 is text data that explains the contents of the storyboard image d31. The scene description data d32 is content that follows the content of the storyboard image d31, and in one embodiment, is composed of a scene description d321 and a detailed description d322. The scene description d321 is, for example, a heading that succinctly explains the state of the storyboard image d31, and the detailed description d322 can include more detailed information than the scene description d321 or information that is to be used as a supplementary explanation.
[0049] The audio data d33 is character data corresponding to the audio played in the advertising video. The character data may include symbols. It may also be the title of a piece of music or a URL. The audio data d33 is, for example, character data indicating the textual representation of narration, subtitles, lines, and sound effects according to the storyboard image d31, and the content of the music played in the advertising video. The audio data d33 may include, for example, the type of voice (gender, voice quality, voice strength, etc.), language, and, if music is included, the genre of music and instruments. The audio data d33 may be associated with (related to) the storyboard data d3 to be output, or may be associated with (related to) the data to be input to the data generating unit 122.
[0050] 4. Information Processing by Information Processing System 100 The program of the information processing system 100 according to the embodiment executes each step (information processing method) described below. Each step will be described with reference to FIG.
[0051] <Step S1: Presentation of display screen ds1> 4, the data presentation unit 124 executes information processing for presenting a display screen ds1 for receiving project data d11. As a result, the display screen ds1 is displayed on the display unit of the user terminal 2. In one example of the embodiment, the display screen ds1 has, for example, an input area a1 for the project data d11 and an object a2 for generating data to be generated. In one embodiment, the object a2 is a button, and the user performs a selection operation (e.g., clicking with a mouse or tapping on a touch panel) to proceed to the next information processing (generation processing of scene data d12). The input area a1 is a text box that receives input of characters, etc. via a keyboard of the user terminal 2, etc. The input area a1 may be configured to receive image data. The image data may include character data corresponding to the project data d11, or may include data such as sketches, figures, and photographs. When the image data includes character data corresponding to the project data d11, it is preferable that the information processing device 1 has a function of analyzing the character data, but the image data may be transmitted to an external server that analyzes the character data to obtain the analysis results.
[0052] <Step S2 (an example of an acquisition step): Acquisition of content data d1> When the user inputs project data d11 (content data d1) via the user terminal 2 and selects an object a2, the data is stored in the storage unit 11 via the communication unit 10. The data acquisition unit 121 reads out and acquires character input for generating scene data d12.
[0053] <Step S3: Prompt generation> The prompt generation unit 123 generates prompt data dp using the project data d11 (content data d1) and fixed phrases stored in the storage unit 11, and outputs the prompt data dp to the data generation unit 122. This prompt data dp is instruction data for generating scene data d12 in the data generation unit 122 as a large-scale language model.
[0054] <Step S4: Generation of scene data d12> The data generating unit 122 (first generating unit 122a) generates scene data d12 using prompt data dp including project data d11. The generated data is composed of a plurality of scene data d12 corresponding to a series of scenes of the production target (in this embodiment, an advertising video). Note that the plurality of scene data d12 means that it includes content explaining each scene of the advertising video, and does not necessarily mean that the data itself is generated in multiple files.
[0055] <Step S5: Presentation of display screen ds2> The data presentation unit 124 executes information processing for presenting a display screen having the generated scene data d12 (not shown). As a result, the display screen is displayed on the display unit of the user terminal 2, and the user can check the contents. If necessary, the scene data d12 may be editable. In that case, the edit input data is acquired by the data acquisition unit 121 from the user terminal 2. Specific examples of the embodiment will be described below.
[0056] The data presentation unit 124 executes information processing for presenting a display screen ds2 for receiving the scene data d12, as shown in Fig. 5. As a result, the display screen ds2 is displayed on the display unit of the user terminal 2. In one embodiment, the display screen ds2 has objects b1 to b10. A storyboard image d31 of storyboard data d3 to be generated by proceeding to the next information processing is displayed as a preview image on the display screen ds2. This allows a predetermined image to be grasped, making it easy to perform editing in advance. Note that the above-mentioned display screen ds1 and this display screen ds2 are examples of interfaces, and are not limited to these.
[0057] Object b1 indicates, for example, which scene the input operation is being performed for, and in Fig. 5, scene 1 is selected as an example. By selecting a part other than scene 1, the display can be switched to another scene. The object b2 is a text box that receives input of characters and the like via a keyboard or the like of the user terminal 2. Here, the scene data d12 generated in the previous step may be automatically input to the object b2. This allows input and editing to be performed simultaneously. In other words, if editing is not required, the user can simply use the input contents of the object b2 as is, and if editing is required, the user can select the object b2, activate it, and perform input work.
[0058] The object b3 is an object for acquiring the expression format data d13 (art style in one embodiment). The object b4 is an object to be selected when there is a reference image or a reference image to generate the storyboard image d31 of the storyboard data d3. When this object b4 is selected as "with reference image", for example, the user is prompted to upload the reference image d311. In one embodiment, the object b5 is a button, and when the user performs a selection operation (for example, clicking with a mouse or tapping on a touch panel), the object b5 proceeds to the next information processing (generation processing of storyboard data d3).
[0059] The object b6 is an object for downloading a storyboard image d31 to be displayed as a preview image. The object b7 is an input area for editing the storyboard image d31. In other words, the object b7 is an input area for receiving the edit target data d21 as the edit instruction data d2. The object b7 is a text box for receiving input of characters, etc. via a keyboard, etc. of the user terminal 2. The object b8 is an object for acquiring edited shape data d22 as the edit instruction data d2. The object b9 is an object for acquiring edited image data d23 as the edit instruction data d2. When the object b9 is selected, for example, a screen for selecting an image file is displayed, or a screen for accepting an image file by drag and drop is displayed. In one embodiment, the object b10 is a button, and the storyboard image d31 is edited when the user performs a selection operation (for example, clicking with a mouse or tapping on a touch panel).
[0060] <Step S6: Acquisition of content data d1, etc.> The data acquisition unit 121 reads and acquires the scene data d12 (contents data d1) and the expression format data d13 of the object b2. If there is a reference image d311, it is also read and acquired. Each time the user inputs these data to the information processing device 1, the data acquisition unit 121 may acquire these data, and the process of step S7 described later may be automatically performed to automatically generate a preview image. Alternatively, an object for preview generation (not shown) may be displayed on the display screen ds2, and when the object is selected, the data acquisition unit 121 may acquire these and generate a preview image. In the embodiment, the reference image d311 may include a non-modified reference image and an alteration-permitted reference image. The non-modification reference image is an image that is not intended to be altered in content in consideration of various rights, as will be described later, and the alteration-permitted reference image is, for example, an image of a character, an image that permits various alterations, such as clothing, accessories such as glasses, and posture.
[0061] <Step S7: Prompt generation> The prompt generation unit 123 generates prompt data dp using the scene data d12 (content data d1), the expression format data d13, and the fixed phrases stored in the storage unit 11, and outputs the prompt data dp to the data generation unit 122. This prompt data dp is instruction data for generating storyboard data d3 in the data generation unit 122 as a large-scale language model.
[0062] Here, in step S6, if there is a reference image d311 as an unaltered reference image, the template text of the prompt data dp may include an instruction to incorporate the reference image d311 into the storyboard image d31 without altering the content of the reference image d311. For example, if the reference image d311 is a logo or a character related to the production target, there is a possibility that an image with undesirable content may be generated in terms of rights such as copyright and trademark. For this reason, the information processing system 100 is configured so that a reference image d311 that has been determined in advance to be free from these rights is placed as is in the storyboard image d31. Note that modification of the content may exclude changes to the size of the reference image d311 within the storyboard image d31, and may also exclude adjustments to contrast, saturation, shades, and the like. In addition, images that are determined to be free from copyright issues may be data that has been judged by a human, or may be data that has been subjected to data analysis and judgment by the data acquisition unit 121 based on, for example, the similarity between images.
[0063] Furthermore, in step S6, if there is a reference image d311 as an alteration-permitted reference image, the standard text of the prompt data dp can include an instruction to incorporate the reference image d311 into the storyboard image d31 so that alteration of the contents of the reference image d311 is permitted.
[0064] It is also preferable to configure the system so that it is possible to explicitly distinguish whether the reference image used in step S6 is an alteration-permitted reference image or an unaltered reference image. For example, in a user interface (see, for example, FIG. 5), an object for uploading an alteration-permitted reference image and an object for uploading an unaltered reference image may be displayed separately to distinguish them, and a standard prompt phrase corresponding to the object may be selected.
[0065] <Step S8: Data Editing> The data generating unit 122 presents the storyboard image d31 as a preview image on the display screen ds2 through steps S6 and S7. This step is a process for the user to modify the contents of this image in advance. Specifically, it is as follows. When object b10 is selected, the data acquisition unit 121 reads and acquires the editing instruction data d2 corresponding to object b7, the edited shape data d22 corresponding to object b8, and the edited image data d23 corresponding to object b9. The prompt generation unit 123 then generates prompt data dp using these data and the template stored in the storage unit 11, and outputs the generated data to the data generation unit 122 (data editing unit 122c). The data presentation unit 124 then presents the generated storyboard image d31 as a new preview image on the display screen ds2, and feeds back the editing results to the user. For example, this editing information processing can be utilized when modifying a reference image d311 (e.g., a logo or character) attached to the clothing of a woman who is the advertising target in a storyboard image d31, as shown in FIG. This step S8 is omitted if the user does not perform a selection operation of the object b10.
[0066] <Step S9 (an example of a generation step): Generation of storyboard data d3> This step S9 is executed by selecting the object b5 shown in Fig. 5. The data generating unit 122 (second generating unit 122b) generates storyboard data d3 as shown as an example in Fig. 6 using the prompt data dp. The generated data is made up of a plurality of storyboard data d3 corresponding to a series of scenes in the advertising video. Note that the plurality of storyboard data d3 means that it includes content explaining each scene in the advertising video, and does not necessarily mean that the data itself is generated in a plurality of files.
[0067] It should be noted that in step S6, if there is a reference image d311, the data generation unit 122 can generate storyboard data d3 including a storyboard image d31 in which the reference image d311 is shown.
[0068] <Other information processing 1> Here, the data generating unit 122 (second generating unit 122b) is configured to be able to generate storyboard data corresponding to a later scene in the chronological order by taking into account storyboard data d3 corresponding to a previous scene in the chronological order. Since a storyboard has continuity between scenes, it is preferable to give each scene a relationship. For this reason, the information processing system 100 executes a generation process that takes into account such a previous scene.
[0069] A specific example of taking into account storyboard data d3 corresponding to a previous scene is, for example, making characters appearing in multiple scenes the same. For example, a possible scenario would be one in which scene 1 and scene 2 share a common character, scene 2 and scene 3 share a common character, and so on, scene n and scene n+1 (n is an integer equal to or greater than 1) share a common character. In other words, scene n+1 is in a relationship in which the elements of scene n are taken into account. Note that, for scene 1, since there are no image elements to be taken into account prior to this, the reference image d311 relating to object b4 can be used as an element to be taken into account.
[0070] As described above, in order to generate an image of a later scene (scene n+1) by taking into account an image of a previous scene (scene n), a process may be executed in which the image of scene n is used as a reference image d311. That is, in step S7, when the prompt generating unit 123 generates an image of scene n+1, the prompt generating unit 123 may generate an instruction (prompt) for generating storyboard data d3 (storyboard image d31) of scene n+1 using scene data d12 of scene n+1 that has already been created (generated), expression format data d13, and the image of scene n as the reference image d311. In other words, the prompt generating unit 123 is configured to be capable of generating a standard text for generating an image of scene n+1 by taking into account the image of scene n as the reference image.
[0071] Here, the relationship between the previous scene and the next scene has been described as being consecutive (scene n, scene n+1), but this is not limited to this, and it may be that one scene is skipped (scene n, scene n+2), or that two or more scenes are skipped.
[0072] <Other information processing 2> The information processing device 1 may store a predetermined image in the storage unit 11 so that the storyboard image d31 to be generated does not become an image with undesirable contents in terms of rights such as copyright and trademark. For example, the case where the reference image d311 is acquired in the above step S6 has been described. The reference image d311 is an image (e.g., a logo, etc.) that the user or the like wants to use, which is appropriately uploaded to the information processing system 100 (storage unit 11). In order to avoid problems from the viewpoint of rights such as copyright with respect to the image that the user or the like wants to use, the user or the like may be shown whether the image uploaded by the user or the like is appropriate as an image to be used. In other words, the above-mentioned predetermined image is an image selected in terms of rights, and when the storyboard image d31 is generated using the reference image d311, the degree of similarity between the reference image d311 and the predetermined image may be calculated, and information related to the degree of similarity may be presented to the user according to the degree of similarity. The degree of similarity may be evaluated by comparing pixel values of each pixel of the image, by comparing histograms showing the distribution of color and brightness of the image, or by using the degree of similarity (cosine similarity).In addition, the information related to the degree of similarity presented is not particularly limited, and may simply indicate whether or not the images are similar, or may be a score. Note that, although an example of calculating the degree of similarity between a predetermined image and a reference image d311 (an image that a user wishes to use and uploads) has been described here, the present invention is not limited to this, and the degree of similarity between a predetermined image and a storyboard image d31 may also be calculated. The information processing 2 described here can be performed, for example, after the above-mentioned step S6, S8, or S9. For example, if the degree of similarity is higher than a predetermined threshold, the data presentation unit 124 may present that fact to the user or display a warning, or the data generation unit 122 may stop outputting the storyboard image. In addition, together with the image stored in the storage unit 11, a character name or a proper name indicating the image may be stored, and when such a character name is designated by the user, control may be performed so that the character is not included in the storyboard image. When carrying out this information processing 2, the control unit 12 preferably has an image matching unit (not shown) in addition to the functional units shown in FIG. 3. Specifically, the image matching unit can be configured to match (compare) the reference image d311 (or the storyboard image d31) with an image previously stored in the storage unit, and to match (determine) whether the reference image d311 is an appropriate image from the viewpoint of the rights relationship. In other words, the image matching unit can be configured to be capable of calculating the degree of similarity between the reference image d311 (or the storyboard image d31) and a predetermined image. Then, when the image matching unit determines that the image is inappropriate, it causes the data presenting unit 124 to present that fact (for example, the reference image d311 or the storyboard image d31 is similar to an image from the viewpoint of the rights relationship and is an inappropriate image, etc.), or causes the data generating unit 122 to stop generating the storyboard image d31.
[0073] 5. Variations 5-1. Variation 1 In the embodiment, the data generation unit 122 configured with the generative AI model is included in the information processing device 1 as an example, but the present invention is not limited to this. As shown in FIG. 9, an external server (large-scale language model server 4) independent of the information processing device 1 may include the data generation unit 122. In this case, the prompt generation unit 123 of the information processing device 1 transmits the prompt data dp to the large-scale language model server 4 via the communication network 3, and the information processing device 1 receives the output result (scene data d12 and storyboard data d3), and the information processing device 1 presents the output result to the user terminal 2.
[0074] 5-2. Variation 2 In the embodiment, when the prompt data dp corresponding to the project data d11 is input to the data generating unit 122, the scene data d12 is temporarily generated. Thereafter, when the prompt data dp corresponding to the scene data d12 is input to the data generating unit 122, the storyboard data d3 is generated. In other words, although the storyboard data d3 is generated in stages, the present invention is not limited to this. 10, when prompt data dp corresponding to content data d1 is input to the data generation unit 122, storyboard data d3 may be generated. In other words, the generative AI model of the data generation unit 122 and the prompt generation unit 123 may be configured so that the storyboard data d3 is generated all at once, without going through multiple stages as described in the embodiment. In this modification, the content data d1 prepared by the user may be the project data d11 or the scene data d12. This is because the project data d11 and the scene data d12 do not completely match, but have overlapping parts in terms of content (qualitatively).
[0075] In this modified example 2, even if there is no scene data d12, when the product (advertising target) in the project data d11 is canned coffee, storyboard data d3 including a storyboard image d31 of a person drinking canned coffee in an office can be generated. The following data can also be generated even if there is no scene data d12. When the service (advertising target) of the planning data d11 is a fitness gym and the target of the planning data d11 is working people in their twenties, storyboard data d3 can be generated that includes a storyboard image d31 showing a working person in his twenties running on a treadmill in a fitness gym. In the case where only the target is specified in the project data d11, the data generation unit 122 can refer to the specific data dr (unique data) to generate storyboard data d3 including a representative storyboard image d31 representing one scene of a commercial content having a good pure recall rate for the specified target. When only the length of the commercial is specified in the project data d11, the data generation unit 122 can refer to the specific data dr (unique data) to generate storyboard data d3 including a representative storyboard image d31 representing one scene of a commercial content having a good norm value from among commercials of the specified length.
[0076] Various embodiments are exemplified below. The embodiments shown below can be combined with each other. [Appendix 1] An information processing system for generating storyboard data to be produced, A data acquisition unit and a data generation unit are provided, the data acquisition unit is configured to be able to acquire content data; the content data includes data relating to the content of a scene in the production object, the data generation unit is configured to generate, based on the content data, the storyboard data corresponding to the scene in the production target. [Appendix 2] 2. An information processing system according to claim 1, the data generation unit is configured to be able to generate the storyboard data corresponding to a later scene in the chronological order by taking into account the storyboard data corresponding to a previous scene in the chronological order. [Appendix 3] 3. An information processing system according to claim 2, A prompt generating unit is provided, The prompt generator generates prompt data; an information processing system, wherein the prompt data includes content for generating storyboard data corresponding to a later scene in the chronological order by taking into account the storyboard data corresponding to a previous scene in the chronological order. [Appendix 4] An information processing system according to claim 2 or 3, An information processing system, wherein the storyboard data includes storyboard images. [Appendix 5] 5. The information processing system according to claim 4, Further comprising an image matching unit, The data acquisition unit acquires the content data including a reference image, The reference image includes at least one of a logo related to the production object and a character related to the production object, The image matching unit compares the reference image with a predetermined image stored in a memory unit, and if the reference image is an inappropriate image from the standpoint of copyright, displays that fact or causes the data generation unit to stop generating the storyboard image. [Appendix 6] An information processing system according to claim 4 or 5, The data acquisition unit acquires the content data including a reference image, The reference image includes at least one of a logo related to the production object and a character related to the production object, The data generation unit generates the storyboard data including the storyboard image in which the reference image whose content has not been altered is shown. [Appendix 7] An information processing system according to any one of Supplementary Note 4 to Supplementary Note 6, The storyboard data further includes audio data. An information processing system, wherein the audio data is character data corresponding to the audio played in the production target. [Appendix 8] An information processing system according to any one of claims 1 to 7, The data generation unit is composed of the generation AI model retrained with specific data, An information processing system, wherein the specific data includes at least one of image data of a production object, thumbnail data, and data corresponding to analysis results or research results related to the production object. [Appendix 9] An information processing system according to any one of claims 1 to 8, The content data includes at least one of project data and scene data, The project data includes at least one of a direct object in the production object, a theme of the production object, a length of the production object, a target of the production object, and an expression method of the production object; An information processing system, wherein the scene data is data representing the scene in the production object. [Appendix 10] An information processing system according to any one of claims 1 to 9, The production target is an advertising video, The content data includes at least one of project data and scene data, The plan data includes at least one of an advertising target of the advertising video, a theme of the advertising video, a target of the advertising video, and an expression method of the advertising video; An information processing system, wherein the scene data is data showing the scene in the advertising video. [Appendix 11] The information processing system according to claim 9 or 10, The content data further includes expression format data; An information processing system, wherein the expression format data is data indicating an expression format of the storyboard data. [Appendix 12] An information processing system according to any one of Supplementary Note 9 to Supplementary Note 11, the data acquisition unit is configured to be able to acquire character input related to the content data; The data generation unit generates the storyboard data based on the content data. [Appendix 13] An information processing system according to any one of Supplementary Note 9 to Supplementary Note 12, the content data includes both the project data and the scene data, The data generating unit includes a first generating unit and a second generating unit, The first generation unit generates the scene data as character data based on the project data, The second generation unit generates the storyboard data including images based on the scene data. [Appendix 14] 14. The information processing system according to claim 13, At least one of the first generation unit and the second generation unit is configured with the generation AI model retrained with specific data, An information processing system, wherein the specific data includes at least one of image data of a production object, thumbnail data, and data corresponding to analysis results or research results related to the production object. [Appendix 15] 15. The information processing system according to claim 14, Both the first generation unit and the second generation unit are configured with the generative AI model retrained with the specific data, An information processing system, wherein at least a portion of the specific data used for relearning is different between the first generation unit and the second generation unit. [Appendix 16] 16. The information processing system according to claim 15, The first generation unit generates a plurality of the scene data corresponding to a series of scenes to be produced based on the project data. [Appendix 17] An information processing system according to any one of claims 1 to 16, The data generating unit has a data editing unit, the data acquisition unit is configured to be able to acquire editing instruction data; The information processing system, wherein the data editing unit is configured to edit the storyboard data based on the editing instruction data. [Appendix 18] 18. The information processing system according to claim 17, In the case of editing a storyboard image of the storyboard data, The editing instruction data includes editing target data, editing shape data, and editing image data, the editing target data is character data indicating an editing target in the storyboard image, the edited shape data is data indicating a shape of the edit target, An information processing system, wherein the edited image data is image data to be replaced with the edited image data. [Appendix 19] An information processing method comprising information processing for generating storyboard data to be produced, The information processing includes an acquisition step and a generation step, The acquiring step acquires content data, the content data includes data relating to the content of a scene in the production object, The generating step is an information processing method, comprising: inputting the content data into a generative AI model to generate the storyboard data corresponding to the scene in the production target. [Appendix 20] A program that causes a computer to execute the information processing method described in Appendix 19.
[0077] Although the embodiments have been described above, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made. The embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]
[0078] 100: Information processing systems 1: Information processing equipment 10: Communications Department 11: Storage section 12: Control section 121: Data acquisition section 122: Data generation unit 122a: 1st generation part 122b: Second generation part 122c: Data Editorial Department 123: Prompt generation unit 124: Data presentation section 13: Output section 14: Input section 15: Communication bus 2: User terminal 3: Communication network 4: Large-scale language model server d1: Content data d11: Project data d12: Scene data d13: Expression format data d2: Editing instruction data d21: Data to be edited d22: Edit shape data d23:Edited image data d3: Storyboard data d31: Storyboard image d32:Scene description data d321:Scene description d322:Detailed explanation d33: Audio data dp:prompt data dr: specific data dr1: Image data to be produced dr2: Thumbnail data dr3: data ds1:Display screen ds2:display screen
Claims
1. An information processing system for generating storyboard data to be produced, The system includes a data acquisition unit, a prompt generation unit, and a data generation unit, the data acquisition unit is configured to be able to acquire content data; the content data includes data relating to the content of a scene in the production object, The prompt generation unit generates prompt data using a sentence pre-stored in a storage unit; the sentence of the prompt data includes in advance a content for generating the storyboard data corresponding to the later scene in the time series by taking into account the storyboard data corresponding to the earlier scene in the time series, an information processing system, wherein the data generation unit is configured to generate, based on the content data and the prompt data, the storyboard data corresponding to an earlier scene in the timeline of the production object and the storyboard data corresponding to a later scene in the timeline of the production object.
2. 2. The information processing system according to claim 1, the storyboard data includes storyboard images; an information processing system, wherein the sentences of the prompt data previously include content for generating the storyboard image of the storyboard data corresponding to the later scene in the chronological order by taking into account the storyboard image of the storyboard data corresponding to the earlier scene in the chronological order.
3. 3. The information processing system according to claim 2, Further comprising an image matching unit, The data acquisition unit acquires the content data including a reference image, The reference image includes at least one of a logo related to the production object and a character related to the production object, The image matching unit compares the reference image with a predetermined image stored in the memory unit, and if the reference image is an inappropriate image from the standpoint of copyright, displays that fact or causes the data generation unit to stop generating the storyboard image.
4. 3. The information processing system according to claim 2, The data acquisition unit acquires the content data including a reference image, The reference image includes at least one of a logo related to the production object and a character related to the production object, The data generation unit generates the storyboard data including the storyboard image in which the reference image whose content has not been altered is shown.
5. An information processing system according to any one of claims 1 to 4, The storyboard data further includes audio data. The audio data is character data corresponding to the audio played in the production target. An information processing system, wherein the sentences of the prompt data previously contain content for generating the voice data of the storyboard data corresponding to the scene.
6. An information processing system according to any one of claims 1 to 4, The data generation unit is composed of the generated AI model re-trained with specific data, An information processing system, wherein the specific data includes at least one of production object image data, thumbnail data, and data corresponding to analysis results or research results related to the production object.
7. An information processing system according to any one of claims 1 to 4, The content data includes at least one of project data and scene data, The project data includes at least one of a direct object in the production object, a theme of the production object, a length of the production object, a target of the production object, and an expression method of the production object, An information processing system, wherein the scene data is data representing the scene in the production object.
8. An information processing system according to any one of claims 1 to 4, The production target is an advertising video, The content data includes at least one of project data and scene data, The plan data includes at least one of an advertising target of the advertising video, a theme of the advertising video, a target of the advertising video, and an expression method of the advertising video; An information processing system, wherein the scene data is data showing the scene in the advertising video.
9. The information processing system according to claim 7, The content data further includes expression format data; An information processing system, wherein the expression format data is data indicating an expression format of the storyboard data.
10. The information processing system according to claim 7, the data acquisition unit is configured to be able to acquire character input related to the content data; The data generation unit generates the storyboard data based on the content data.
11. The information processing system according to claim 7, the content data includes both the project data and the scene data, The data generating unit includes a first generating unit and a second generating unit, The first generation unit generates the scene data as character data based on the project data, The second generation unit generates the storyboard data including images based on the scene data.
12. The information processing system according to claim 11, At least one of the first generation unit and the second generation unit is composed of the generation AI model re-trained with specific data, An information processing system, wherein the specific data includes at least one of production object image data, thumbnail data, and data corresponding to analysis results or research results related to the production object.
13. The information processing system according to claim 12, Both the first generation unit and the second generation unit are configured with the generation AI model re-trained with the specific data, An information processing system, wherein at least a portion of the specific data used for relearning is different between the first generation unit and the second generation unit.
14. The information processing system according to claim 13, An information processing system, wherein the first generation unit generates a plurality of the scene data corresponding to a series of the scenes to be produced based on the project data.
15. An information processing system according to any one of claims 1 to 4, The data generating unit has a data editing unit, the data acquisition unit is configured to be able to acquire editing instruction data; The information processing system, wherein the data editing unit is configured to edit the storyboard data based on the editing instruction data.
16. 16. The information processing system according to claim 15, In the case of editing a storyboard image of the storyboard data, The editing instruction data includes editing target data, editing shape data, and editing image data, the editing target data is character data indicating an editing target in the storyboard image, the edited shape data is data indicating a shape of the edit target, An information processing system, wherein the edited image data is image data to be replaced with the edited image data.
17. An information processing method comprising information processing for generating storyboard data to be produced, The information processing includes an acquisition step, a prompt generation step, and a generation step; The acquiring step acquires content data, the content data includes data relating to the content of a scene in the production object, The prompt generating step generates prompt data using a sentence pre-stored in a storage unit; the sentence of the prompt data includes in advance a content for generating the storyboard data corresponding to the later scene in the time series by taking into account the storyboard data corresponding to the earlier scene in the time series, The generation step is an information processing method in which the content data and the prompt data are input into a generative AI model to generate storyboard data corresponding to the earlier scene in the chronological order and storyboard data corresponding to the later scene in the chronological order in the production target.
18. A program causing a computer to execute the information processing method according to claim 17.
Citation Information
Patent Citations
Automatically generating storyboards
CN112685582A
Video generation method, video generation device, electronic equipment and readable storage medium
CN118509618A
Dynamic video generation method and device, electronic equipment and storage medium
CN118612367A
Intelligent sub-shot script generation system and method
CN118690739A
Video generation method, electronic device, storage medium and computer program product
CN118748738A