Device, method, and program for comparing commercial plans with past commercials

Abstract

To provide a method for comparing commercial plans with past commercials.SOLUTION: First, designation of a commercial plan is received from a user terminal 100 (S201). Next, a device 100 requests a generative AI model to generate a first series of illustrations based on the plan (S202), and receives the generated first series of illustrations (S203). The device 100 that has received the first series of illustrations generates a first video storyboard including the first series of illustrations as needed (S204). Next, the device 100 receives designation of a past commercial (S205). The device 100 requests the generative AI model to generate a second series of illustrations corresponding to the commercial (S206), and receives the second series of illustrations (S207). The device 100 then generates a second video storyboard including the second series of illustrations as needed (step S208).SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an apparatus, a method, and a program for comparing a commercial plan with past commercials. [Background technology]

[0002] Commercial production involves the processes of planning, filming and editing. Generally, advertising agencies propose multiple plans to an advertiser, and the footage filmed based on the plan adopted by the advertiser is then edited to create the completed video.

[0003] A project is often expressed in a form called a "storyboard." A storyboard includes a series of static pictures and corresponding dialogue, narration, or subtitle text for each picture. A storyboard may further include a description of the situation each picture represents, the number of seconds each picture lasts, etc.

[0004] Advertising agencies need to present effective proposals based on the objectives that advertisers want to achieve through the broadcast of their commercials, and to do so, they compare multiple proposals. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 6953643 Summary of the Invention [Problem to be solved by the invention]

[0006] When comparing multiple projects, if it is possible to compare them with past commercials, the effectiveness of the past commercials can be analyzed using the applicant's technology, for example, as shown in Patent Document 1, making it possible to quantitatively explain the degree of effectiveness that can be expected from the proposed project.

[0007] However, filming and editing a project in order to compare it with past commercials is not realistic in terms of the costs involved in the filming and editing processes.

[0008] When comparing multiple projects, there are times when you want to directly compare new projects with each other. Even in such cases, it is not realistic to compare them in the form of a commercial that has been shot and edited, and even if you try to compare them in the form of storyboards at the planning stage, it is not easy because the specific content of each project differs.

[0009] The present invention has been made in consideration of the above problems, and a first object of the present invention is to provide an apparatus, method, or program for comparing a commercial plan with past commercials.

[0010] A second object of the present invention is to provide an apparatus, method, or program for comparing a first CM plan with a second CM plan. [Means for solving the problem]

[0011] In order to achieve this goal, a first aspect of the present invention is a method for comparing a commercial plan with past commercials, comprising the steps of receiving a first input specifying the plan, sending a first request to a first generative AI model to generate a first series of illustrations based on the plan, and receiving the first series of illustrations, receiving a second input specifying the past commercial, and sending a second request to a second generative AI model to generate a second series of illustrations corresponding to the past commercial, and receiving the second series of illustrations.

[0012] A second aspect of the present invention is the method of the first aspect, wherein the project includes a series of pictures and a description of at least some of the pictures in the series.

[0013] A third aspect of the present invention is the method of the second aspect, wherein the sequence of pictures is each a photograph or an image including at least a portion of a photograph.

[0014] A fourth aspect of the present invention is the method of the second or third aspect, wherein the number of illustrations in the first series is the same as the number of pictures in the series.

[0015] A fifth aspect of the present invention is the method of any one of the second to fourth aspects, wherein the first input includes a selection of the series of pictures.

[0016] Further, a sixth aspect of the present invention is a method according to any one of the second to fifth aspects, wherein the project includes a line, a narration or a subtitle corresponding to at least one of the series of pictures.

[0017] A seventh aspect of the present invention is the method according to the sixth aspect, wherein the narration includes a catch phrase.

[0018] Furthermore, an eighth aspect of the present invention is the method of any one of the second to seventh aspects, wherein the project includes music.

[0019] A ninth aspect of the present invention is the method of any one of the second to eighth aspects, wherein the plan includes a number of seconds for each picture in the sequence of pictures.

[0020] A tenth aspect of the present invention is the method according to any one of the first to ninth aspects, wherein the second series of illustrations corresponds to a series of images included in the past commercials.

[0021] Furthermore, an eleventh aspect of the present invention is the method of the tenth aspect, further comprising the step of selecting the series of images from the past commercials using AI generated by machine learning.

[0022] A twelfth aspect of the present invention is the method according to the tenth aspect, further comprising the step of selecting, as the series of images, from said past commercials, a number of images equal to the number of cuts in said past commercials.

[0023] A thirteenth aspect of the present invention is the method of the tenth aspect, wherein the second input includes a selection of the series of images.

[0024] Furthermore, a 14th aspect of the present invention is a method according to any one of the 10th to 13th aspects, wherein the second generative AI model is different from the first generative AI model.

[0025] In addition, a 15th aspect of the present invention is a method of the 14th aspect, wherein the first generative AI model and the second generative AI model are each models trained using the same set of illustrations and their style names.

[0026] A sixteenth aspect of the present invention is a method according to any one of the tenth to thirteenth aspects, The second generative AI model is identical to the first generative AI model.

[0027] Further, a 17th aspect of the present invention is the method of the 16th aspect, wherein the first and second generative AI models are models trained using a set of illustrations and their art style names.

[0028] Further, an 18th aspect of the present invention is the method according to the 15th or 17th aspect, wherein the first request and the second request include an instruction for the name of the art style.

[0029] A 19th aspect of the present invention is the method of any one of the 1st to 18th aspects, wherein the second request includes an instruction to suppress a characteristic of a talent appearing in the past commercial.

[0030] Also, a twentieth aspect of the present invention is a method of any one of the first to nineteenth aspects, further comprising a step of requesting the first AI model to modify the first series of illustrations.

[0031] Furthermore, a 21st aspect of the present invention is a method of any one of the 1st to 20th aspects, further comprising the steps of generating a first video storyboard including the first series of illustrations, and generating a second video storyboard including the second series of illustrations.

[0032] A twenty-second aspect of the present invention is the method of the twenty-first aspect, further comprising the step of displaying a comparison result between the first video continuity and the second video continuity.

[0033] Further, a 23rd aspect of the present invention is a program for causing a computer to execute a method for comparing a commercial plan with past commercials, the method including the steps of receiving a first input specifying the plan, sending a first request to a first generative AI model to generate a first series of illustrations based on the plan, and receiving the first series of illustrations, receiving a second input specifying the past commercial, and sending a second request to a second generative AI model to generate a second series of illustrations corresponding to the past commercial, and receiving the second series of illustrations.

[0034] Further, a 24th aspect of the present invention is an apparatus for comparing a commercial plan with past commercials, which sends a first request to a first generative AI model to generate a first series of illustrations based on a specified plan, receives the first series of illustrations, and sends a second request to a second generative AI model to generate a second series of illustrations corresponding to the specified past commercial, and receives the second series of illustrations.

[0035] Also, a 25th aspect of the present invention is a method for comparing a first commercial plan with a second commercial plan, comprising the steps of receiving a first input specifying the first commercial plan, sending a first request to a first generative AI model to generate a first series of illustrations based on the first commercial plan and receiving the first series of illustrations, receiving a second input specifying the second commercial plan, and sending a second request to a second generative AI model to generate a second series of illustrations based on the second commercial plan and receiving the second series of illustrations.

[0036] In addition, a 26th aspect of the present invention is a method of the 25th aspect, wherein the first and second generative AI models are the same generative AI model, and are models trained using a set of illustrations and their art style names.

[0037] Also, a 27th aspect of the present invention is a program for causing a computer to execute a method for comparing a first commercial plan with a second commercial plan, the method including the steps of receiving a first input specifying the first commercial plan, sending a first request to a first generative AI model to generate a first series of illustrations based on the first commercial plan and receiving the first series of illustrations, receiving a second input specifying the second commercial plan, and sending a second request to a second generative AI model to generate a second series of illustrations based on the second commercial plan and receiving the second series of illustrations.

[0038] In addition, a 28th aspect of the present invention is a method of the 27th aspect, wherein the first and second generative AI models are the same generative AI model, and are models trained using a set of illustrations and their art style names.

[0039] Also, a 29th aspect of the present invention is an apparatus for comparing a first commercial plan with a second commercial plan, sending a first request to a first generative AI model to generate a first series of illustrations based on a specified first commercial plan, receiving the first series of illustrations, and sending a second request to a second generative AI model to generate a second series of illustrations based on a specified second commercial plan, and receiving the second series of illustrations.

[0040] In addition, a 30th aspect of the present invention is a method of the 29th aspect, wherein the first and second generative AI models are the same generative AI model, and are models trained using a set of illustrations and their art style names. Effect of the Invention

[0041] According to one aspect of the present invention, it is possible to compare the planning of a commercial with past commercials by sending a first request to a first generative AI model to generate a first series of illustrations based on a planning for a specified commercial, receiving the first series of illustrations, and sending a second request to a second generative AI model to generate a second series of illustrations corresponding to a specified past commercial, and receiving the second series of illustrations.

[0042] According to another aspect of the present invention, it is possible to compare a commercial plan with past commercials by sending a first request to a first generative AI model to generate a first series of illustrations based on a plan for a specified first commercial, receiving the first series of illustrations, and sending a second request to a second generative AI model to generate a second series of illustrations based on a plan for a specified second commercial, and receiving the second series of illustrations. [Brief description of the drawings]

[0043] [Figure 1] FIG. 1 shows an apparatus according to a first embodiment of the present invention. [Diagram 2] FIG. 1 is a diagram showing a flow of a method according to a first embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0044] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

[0045] (First embodiment) 1 shows a system according to a first embodiment of the present invention. An apparatus 100 communicates with a user terminal 110 used by a user and a server 120 such as a platform that provides a generative AI model via an IP network such as the Internet.

[0046] The device 100 includes a communication unit 101 such as a communication interface, a processing unit 102 such as a processor or CPU, and a storage unit 103 including a storage device or storage medium such as a memory or a hard disk, and can be configured by executing a program for performing each process or operation in the processing unit 102. The device 100 may include one or more devices, computers, or servers. The program may include one or more programs, and may be recorded in a computer-readable storage medium to form a non-transient program product. The program may be stored in a storage device or storage medium 104 accessible from the storage unit 103 or the device 100 via an IP network, and instructions included in the program may be executed in at least one processor of the processing unit 102. Data described below as being stored in the storage unit 103 may be stored in the storage device or storage medium 104, and vice versa.

[0047] First, a first input specifying a commercial plan is received from the user terminal 100 (S201). The plan includes a series of pictures and at least one explanatory text from the series of pictures, and may include lines, narration or subtitles corresponding to at least one of the pictures, music, and the number of seconds for each picture in the series. An example is a plan including a series of nine images, lines or narration corresponding to each image, and explanatory text explaining the situation of each image. An example of the narration is a catchphrase expressing the concept to be promoted in the plan. Also, the series of pictures can be photographs or images including at least a part of a photograph. Images that can be easily used may be processed as necessary, arranged, and any of explanatory text, lines, narration, and subtitles may be appropriately added to form a rough storyboard. The explanatory text may be, for example, a plan for filming such as actions, behavior, poses, feelings, facial expressions, backgrounds, and camera angles.

[0048] The first input can be, for example, by transmitting plan input screen display information to the user terminal 110 as a file in HTML format, and allowing the user to select a series of pictures included in the plan on an input screen displayed on a web browser on the display screen of the user terminal 110, or by operating an application (also called an "app") installed on the user terminal 110 and allowing the user to select from an input screen displayed on the app. The selection can be transmitted as a first input from the user terminal 110 to the device 100, and the device 100 can obtain a series of pictures to be used in subsequent processing. Note that the "input screen" can adopt various formats such as a web page, a modal window, a pop-up window, etc. when displayed on a web browser, and can be one screen of the app when displayed on an app. In either case, a screen that includes an area having an input field for inputting a series of picture selections corresponds to the input screen. Similar techniques can be applied to other screens mentioned in this specification.

[0049] Next, device 100 makes a request (hereinafter referred to as a "first request") to a generative AI model (hereinafter referred to as the "first generative AI model") to generate a first series of illustrations based on a specified project (S202).

[0050] The first request may include instructions for various conditions, which will be described later, but may also include, for example, an instruction for the aspect ratio of the first series of illustrations. The first request may also be made, for example, by calling an API, to a generative AI model developed by the business operator operating the device 100 or a generative AI model developed by another business operator. The code for making the first request may be stored in the storage unit 103, and the device 100 may acquire the code and execute the code obtained by setting appropriate values ​​to variables included in the code.

[0051] The device 100 then receives (S203) the first series of illustrations generated in response to the first request. The number of illustrations in the first series may, for example, be the same as the number of series of pictures included in the project.

[0052] The device 100 that has received the first series of illustrations generates a first video storyboard including the first series of illustrations as necessary (S204). As an example, the first video storyboard can be generated by generating audio that reads lines or narration included in the project, and generating a video in which multiple illustrations included in the first series of illustrations transition in accordance with the audio data. The number of illustrations in the first series corresponds to the number of scenes in the first video storyboard, and each illustration may be enlarged, reduced, moved, or otherwise processed in order to enhance the expression of each scene.

[0053] Next, the device 100 receives a second input specifying a past commercial (S205). The second input may include, for example, a URL for playing a video of the commercial. The device 100 may select, from the commercial, a number of images equal to the number of cuts in the commercial as a series of images. The use of the selected series of images will be described later. When the second input includes the number of cuts in the commercial, the selection is made more efficient. The selection may be performed, for example, by determining the similarity of a plurality of images included in the commercial using a model generated by machine learning such as deep learning, extracting a plurality of images whose similarity meets a predetermined standard, or by excluding images whose similarity does not meet the predetermined standard and extracting the remaining plurality of images. The second input may also include a selection by the user of a series of images included in the commercial on the input screen displayed on the user terminal 110.

[0054] The device 100 makes a request (referred to as a "second request") to the generative AI model (referred to as a "second generative AI model") to generate a second series of illustrations corresponding to the commercial (S206). If a series of images has been selected from the commercial as described above, the second request may be more specifically a request to generate a second series of illustrations corresponding to the series of images contained in the commercial. The second request may also include instructions to suppress a feature of a talent appearing in the commercial.

[0055] The apparatus 100 then receives a second series of illustrations (S207). The second series of illustrations may correspond to a series of images included in the commercial. The number of images in the series may be the same as the number of cuts in the commercial.

[0056] The device 100 then generates a second video storyboard including the second series of illustrations as necessary (step S208). As an example, the second video storyboard can be generated by generating a video in which a plurality of illustrations included in the second series of illustrations transition in accordance with the sound, including the dialogue or narration, included in the commercial. The number of illustrations in the second series of illustrations corresponds to the number of scenes in the second video storyboard, and each illustration may be enlarged, reduced, moved, or otherwise processed in order to enhance the expression of each scene.

[0057] In FIG. 2, the first and second generative AI models are distinguished from each other, but they may be the same generative AI model. In this specification, "AI model" refers to a machine learning model that has been trained to be able to predict output for input, and "generative AI model" refers to an AI model to which the Transformer architecture is applied. Since it is expected that the name of the architecture will change with technological advances, in this specification, "Transformer architecture" includes architectures that use one or more features of the Transformer architecture or improvements thereof. In this specification, whether "generative AI models" are the same or not is determined based on whether the type of generative AI model specified by the user is the same or not. If the first and second generative AI models are not the same, they may be provided on the same platform 120. In the example of FIG. 2, a second request is made after the first request, and if the first and second generative AI models are the same generative AI models or are provided on the same platform, these requests may be made by a single call to the API.

[0058] In order to make the comparison of multiple plans objective, the first and second generative AI models can be models trained using the same set of illustrations and their style names. By using the first and second generative AI models trained in this way, details other than the points to be compared at the planning stage can be made uniform by including an instruction for the style name in the first and second requests. If the second generative AI model is the same as the first generative AI model, the model can be trained using a set of illustrations and their style names, and the instruction for the style name can be included in the first and second requests. In addition to being trained by giving a style name in advance, the first generative AI model can also be trained by giving a style name for the set of illustrations in the first request, and the same applies to the second generative AI model.

[0059] An example of an instruction for the name of the painting style included in the first request is as follows: {styleName} like illustrations of {cutExplanation}, {background} Here, styleName, cutExplanation, and background are variables that respectively indicate the name of the art style, the description of each of the series of pictures included in the project, and the background color, and their values ​​may be set separately within the first request. Also, simultaneously with or before or after the first request, the device 100 may obtain the series of pictures included in the project and use them to generate the first series of illustrations.

[0060] The first request may also include an indication of elements that should not be reflected in the generated result, as in the following example. bad anatomy, cropped, robot eyes, ugly

[0061] If desired, the device 100 may request the first AI model to modify the received first series of illustrations. Also, if desired, the device 100 may compare the first and second videocontinuities and display the comparison results.

[0062] In the above description, the first and second video storyboards are generated by device 100; however, the first generative AI model may be caused to generate the first video storyboard in addition to generating the first series of illustrations, the second generative AI model may be caused to generate the second video storyboard in addition to generating the second series of illustrations, the first and second video storyboards may not be generated by device 100 but may be generated separately, or the first and second video storyboards may not be generated but the first series of illustrations and the second series of illustrations may be used as comparison targets.

[0063] Second embodiment In the first embodiment, the commercial plan is compared with past commercials, but sometimes multiple commercial plans are compared directly. In that case, the commercial plan described in the first embodiment is regarded as the "first commercial plan," the second input is changed to an input specifying the "second commercial plan" like the first input, and the process or operation described in the first embodiment is performed as necessary as the process or operation following the designation of the second commercial plan.

[0064] In particular, when the second generative AI model is identical to the first generative AI model, the model can be trained using a set of illustrations and their art style names, and an instruction for the art style name can be included in the first request and the second request, thereby bringing the expressions of the first CM plan and the second CM plan closer together and standardizing details other than those that want to be compared at the planning stage.

[0065] In the above-mentioned embodiments, it should be noted that unless there is a statement of "only" such as "based only on", "depending only on", or "only in the case of", it is assumed in this specification that additional information may be taken into consideration. Also, as an example, it should be noted that the statement "do b when a" does not necessarily mean "always do b when a" or "do b immediately after a" unless expressly stated. Also, the statement "each a constituting A" does not necessarily mean that A is composed of multiple components, but includes the case where the component is singular.

[0066] Also, just to be clear, even if there is an aspect of a method, program, terminal, device, server or system (hereinafter referred to as a "method, etc.") that performs an operation different from that described in this specification, each aspect of the present invention is directed to an operation that is the same as any of the operations described in this specification, and the existence of an operation different from that described in this specification does not make the method, etc. outside the scope of each aspect of the present invention. [Explanation of symbols]

[0067] 100 devices 101 Communications Department 102 Processing section 103 Storage section 104 Database 110 User Terminal 120 Generative AI Platform

Claims

1. This is a method for comparing the concept of a commercial with past commercials. A step of receiving a first input specifying the aforementioned plan, The steps include sending a first request to a first generating AI model to generate a first series of illustrations based on the aforementioned plan, and receiving the first series of illustrations, The steps include receiving a second input that specifies the past commercial, The steps include sending a second request to a second generating AI model requesting a second series of illustrations corresponding to the aforementioned past commercials, and receiving the second series of illustrations. Includes.

2. The method according to claim 1, The aforementioned project is A series of paintings, The explanatory text for at least one of the series of pictures mentioned above and Includes.

3. The method according to claim 2, Each of the aforementioned series of images is a photograph or an image containing at least a portion of a photograph.

4. The method according to claim 2, The number of the first series of illustrations is the same as the number of the series of pictures.

5. The method according to claim 2, The first input includes the selection of the series of pictures.

6. The method according to claim 2, The aforementioned plan includes dialogue, narration, or captions corresponding to at least one of the images in the aforementioned series.

7. The method according to claim 6, The aforementioned narration includes a catchphrase.

8. The method according to claim 2, The aforementioned project includes music.

9. The method according to claim 2, The aforementioned plan includes the duration of each image in the series of images.

10. The method according to claim 1, The second series of illustrations mentioned above corresponds to the series of images included in the past commercial.

11. The method according to claim 10, The process further includes the step of selecting the series of images from past commercials using an AI model generated by machine learning.

12. The method according to claim 10, The step further includes selecting a number of images from past commercials equal to the number of cuts in those past commercials as the series of images.

13. The method according to claim 10, The second input includes the selection of the series of images.

14. The method according to claim 10, The second generative AI model differs from the first generative AI model.

15. The method according to claim 14, The first generative AI model and the second generative AI model are models that have been trained using the same set of illustrations and their style names.

16. The method according to claim 10, The second generative AI model is identical to the first generative AI model.

17. The method according to claim 16, The first and second generative AI models are models that have been trained using a set of illustrations and their style names.

18. The method according to claim 15, The first and second requirements include the indication of the style name.

19. The method according to claim 1, The second requirement includes instructions to suppress the characteristics of the talents appearing in the aforementioned past commercials.

20. The method according to claim 1, The further step includes requesting the first AI model to modify the first series of illustrations.

21. The method according to claim 1, The steps include generating a first video storyboard including the first series of illustrations, The steps include generating a second video storyboard including the second series of illustrations and It also includes.

22. The method according to claim 21, The process further includes the step of displaying the results of comparing the first video storyboard with the second video storyboard.

23. A program for causing a computer to perform a method for comparing a commercial plan with past commercials, wherein the method is: A step of receiving a first input specifying the aforementioned plan, The steps include sending a first request to a first generating AI model to generate a first series of illustrations based on the aforementioned plan, and receiving the first series of illustrations, The steps include receiving a second input that specifies the past commercial, The steps include sending a second request to a second generating AI model requesting a second series of illustrations corresponding to the aforementioned past commercials, and receiving the second series of illustrations. Includes.

24. It is a device for comparing the concept of a commercial with past commercials. A first request is sent to a first generating AI model requesting it to generate a first series of illustrations based on the specified plan, and the first series of illustrations is received. A second request is sent to a second generating AI model requesting a second series of illustrations corresponding to the specified past commercial, and the second series of illustrations is received.

25. A method for comparing the first commercial plan with the second commercial plan, The steps include receiving a first input specifying the plan for the first commercial, The steps include sending a first request to a first generating AI model to generate a first series of illustrations based on the first CM plan, and receiving the first series of illustrations, The steps include receiving a second input specifying the plan for the second commercial, The steps include sending a second request to a second generating AI model requesting a second series of illustrations based on the second CM plan, and receiving the second series of illustrations. Includes.

26. The method according to claim 25, The first and second generative AI models are the same generative AI model, trained using a set of illustrations and their style names.

27. A program for causing a computer to perform a method for comparing a first commercial plan with a second commercial plan, wherein the method is: The steps include receiving a first input specifying the plan for the first commercial, The steps include sending a first request to a first generating AI model to generate a first series of illustrations based on the first CM plan, and receiving the first series of illustrations, The steps include receiving a second input specifying the plan for the second commercial, The steps include sending a second request to a second generating AI model requesting a second series of illustrations based on the second CM plan, and receiving the second series of illustrations. Includes.

28. The method according to claim 27, The first and second generative AI models are the same generative AI model, trained using a set of illustrations and their style names.

29. A device for comparing the first commercial plan with the second commercial plan, A first request is sent to a first generating AI model requesting it to generate a first series of illustrations based on the specified first CM plan, and the first series of illustrations is received. A second request is sent to the second generating AI model requesting a second series of illustrations based on the specified second commercial plan, and the second series of illustrations is received.

30. The apparatus according to claim 29, The first and second generative AI models are the same generative AI model, trained using a set of illustrations and their style names.

Images