Information processing device and advertising data generation method

Abstract

An information processing device, an advertisement data generation method, and a program are provided that allow for easily creating appealing manga advertisements. [Solution] In an advertisement generation system in which a PC and a server are communicatively connected via a network including a wireless communication network and a wired communication network, the server 14 includes a cutting unit 30 that cuts out frames from a manga, an evaluation unit 36 ​​that derives an evaluation value indicating the likelihood of attracting attention for each frame based on characteristic features of each frame cut out by the cutting unit 30, and a banner generation unit 38 that generates advertisement data using frames selected based on the evaluation values. The evaluation unit 36 ​​derives an evaluation value for each frame based on evaluation rules that are predetermined for each characteristic feature of the frame.

Description

[Technical Field]

[0001] The present invention relates to an information processing device and an advertisement data generating method. [Background technology]

[0002] In recent years, so-called web manga, which are digitized manga that can be viewed on websites, have become widespread.

[0003] Here, Patent Document 1 describes an information processing device that extracts images of important or characteristic scenes from multiple images based on content such as still image content and video content, and generates digest content that is rearranged in a manga-like manner. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6580894 Summary of the Invention [Problem to be solved by the invention]

[0005] In order to increase the number of viewers for online comics, frames that make up the online comics are extracted and used to generate advertising banners. However, this requires manual labor and effort to extract frames suitable for advertisements from the many frames that make up the comic.

[0006] The information processing device described in Patent Document 1 extracts scenes and generates digest content, but this digest content does not necessarily extract scenes that are appropriate as advertisements for web comics.

[0007] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an information processing device and an advertisement data generation method that can easily create highly appealing manga advertisements. [Means for solving the problem]

[0008] The information processing device of the present invention comprises a cutting unit that cuts out frames from a manga, an evaluation unit that derives an evaluation value indicating the likelihood of each frame attracting attention based on characteristic parts of each frame cut out by the cutting unit, and a generation unit that generates advertising data using the frames selected based on the evaluation value.

[0009] The advertising data generation method of the present invention includes a first step in which a cutting unit cuts out frames from a manga, a second step in which an evaluation unit derives an evaluation value indicating the likelihood of the frame attracting attention based on characteristic parts of the frame cut out by the cutting unit, and a third step in which a generation unit generates advertising data using the frame selected based on the evaluation value. [Effects of the Invention]

[0010] According to the present invention, it is possible to easily create an appealing manga advertisement. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a configuration diagram of a manga advertisement generation system according to a first embodiment. [Figure 2] FIG. 3 is a functional block diagram of a server related to the manga advertisement generation process of the first embodiment. [Figure 3] FIG. 4 is a diagram showing the derivation of an evaluation value for a frame in the first embodiment. [Figure 4] 10 is a flowchart showing the flow of manga advertisement generation processing in the first embodiment. [Figure 5] FIG. 10 is a functional block diagram of a server related to the manga advertisement generation process of the second embodiment. [Figure 6] 10 is a flowchart showing the flow of a manga advertisement generation process according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the embodiment described below shows an example of how the present invention can be implemented, and the present invention is not limited to the specific configuration described below. When implementing the present invention, a specific configuration corresponding to the embodiment may be appropriately adopted.

[0013] (First embodiment) 1 is a configuration diagram of a manga advertisement generation system 10 according to this embodiment. The manga advertisement generation system 10 includes at least one personal computer (hereinafter referred to as "PC") 12 and a server 14. The PC 12 and the server 14 are communicatively connected via a network 16, which may include a wireless communication network or a wired communication network.

[0014] PC 12 is an information processing device such as a desktop computer, laptop computer, smartphone, or tablet device equipped with a display 13, and is operated by an operator to create advertisement data (hereinafter referred to as a "banner") for web manga, which is manga that can be viewed on a website. Specifically, the operator uses PC 12 to select a manga for which to create a banner, and server 14 executes a manga advertisement generation process for the selected manga. Note that the banner in this embodiment is displayed on a website, SNS (Social Networking Service), etc.

[0015] The server 14 is an information processing device that stores data on multiple manga and performs manga advertisement generation processing for manga selected by an operator. The manga stored as data in the server 14 is, for example, image data obtained by scanning a paper-based manga, or manga generated as digital data. In this embodiment, the manga is formed of multiple frames and is divided into pages. The manga is also specified by the number of volumes and chapters of the book.

[0016] Manga data is associated with attribute data indicating the manga author, the publication date of the manga, the manga genre, etc. Manga genres include, for example, romance, other worlds, battle, sports, etc.

[0017] The manga advertisement generation process of this embodiment derives an evaluation value indicating the likelihood of attracting attention for each frame based on the characteristic parts of each frame cut out from the manga, and generates advertisement data using frames selected based on the evaluation value. This makes it possible to easily create appealing manga advertisements.

[0018] FIG. 2 is a functional block diagram relating to the manga advertisement generation process executed by the server 14. As shown in FIG.

[0019] The server 14 includes a storage unit 20, a communication unit 22, and a calculation unit 24.

[0020] The communication unit 22 transmits and receives data to and from the PC 12 and other information processing devices via the network 16 .

[0021] The storage unit 20 stores a program for executing the manga advertisement generation process, manga data, and various other programs and data.

[0022] The calculation unit 24 is a computer such as a CPU (Central Processing Unit), and includes a cutting unit 30, an extraction unit 32, a foot cutting unit 34, an evaluation unit 36, and a banner generation unit 38. These functions are realized by executing a program stored in the storage unit 20 provided in the server 14.

[0023] The cutting unit 30 reads out manga data stored in the storage unit 20 and cuts out frames from the manga. The manga to be read out is selected by an operator using the PC 12. The frames cut out by the cutting unit 30 are associated with information such as the chapter number, volume number, page, and numbers assigned sequentially from the beginning of each chapter (hereinafter referred to as "frame numbers") of the manga that has been cut out. The frame numbers are information that indicate the chronological order of the frames.

[0024] The cutting unit 30 of this embodiment cuts out frames included in at least one of a predetermined page, episode, and volume number from the manga as the target for deriving an evaluation value. As a result, the manga advertisement generation process of this embodiment evaluates only specific frames that are appropriate for advertisements. These specific frames are, for example, frames that include exciting scenes in the manga, such as the first five pages or the last five pages of each episode, or frames in the first to third episodes or the first volume. The pages, episodes, or volumes from which the cutting unit 30 cuts out frames are set in advance.

[0025] The manga advertisement generation process of this embodiment generates a banner using such specific frames, thereby increasing the sense of anticipation for the manga among those who see the banner displayed on a website, etc. Furthermore, by rating only specific frames, the overall processing load is smaller than when rating all frames.

[0026] The extraction unit 32 extracts characteristic parts for each frame cut out by the cutting unit 30. In this embodiment, the extraction unit 32 extracts characteristic parts for frames that do not satisfy the cut-off conditions. The characteristic parts for each frame are extracted by image recognition. The characteristic parts include, for example, the proportion of a page that the frame occupies, the aspect ratio of the frame, whether or not the frame contains a character, whether or not the frame contains a main character, the facial direction of the character in the frame, the character's facial expression, the proportion of the frame that the character's face occupies, whether or not the character in the frame is deformed, the amount of text included in the frame, etc.

[0027] The cutoff unit 34 selects frames that satisfy a predetermined condition (hereinafter referred to as a "cutoff condition") as frames for which evaluation values ​​will not be derived. The cutoff condition will be described in detail later.

[0028] The evaluation unit 36 ​​derives an evaluation value indicating the likelihood of attracting attention for each frame based on the characteristic parts of each frame extracted by the extraction unit 32. The evaluation unit 36 ​​of this embodiment derives an evaluation value for each frame based on evaluation rules that are predetermined for each characteristic part of the frame. In this way, the evaluation unit 36 ​​of this embodiment derives an evaluation value for each frame based on the predetermined evaluation rules, making it easy to evaluate the frames as advertisements.

[0029] The banner generation unit 38 generates a banner, which is advertising data, using frames selected based on the evaluation value. Note that the manga advertisement generation process of this embodiment displays frames on the display 13 of the PC 12 based on the evaluation value, and the banner generation unit 38 generates a banner using frames selected by the operator from among the frames displayed on the display 13. Note that the frames displayed on the display 13 of the PC 12 are, as an example, frames with relatively high evaluation values. As a result, the banner generation unit 38 generates a banner using frames with relatively high evaluation values.

[0030] The banner generated by the banner generating unit 38 displays at least one selected frame, along with, for example, the title of the manga and the URL (Uniform Resource Locator) of the site where the manga can be viewed.

[0031] Furthermore, if multiple frames are selected to be used as a banner, a GIF format image (hereinafter referred to as "GIF image") will be created that displays the selected frames in chronological order based on their frame numbers. By generating a banner that includes GIF images from multiple frames in this way, people who see the banner displayed on a website or the like can predict the general development of the manga, making the advertisement more appealing.

[0032] Next, the derivation of an evaluation value for a frame by the manga advertisement generation process of this embodiment will be described with reference to Fig. 3. Fig. 3 shows an example of a one-page manga for deriving an evaluation value for each frame. The genre of the manga shown in Fig. 3 is romance, for example.

[0033] As described above, the manga advertisement generation process of this embodiment does not derive evaluation values ​​for frames that satisfy the cutoff conditions. Examples of cutoff conditions are shown below. Note that the cutoff conditions below are only examples, and it is not necessary for all of the following conditions to be included in the cutoff conditions, and other conditions may also be included.

[0034] Cut-off condition 1: There are not enough characters in the frames. Cutoff condition 2: Even if a character is included in the frame, there is no description of the character's facial expression. For example, the character is facing backwards. Cutoff condition 3: The frame does not fit within a certain aspect ratio. Cutoff condition 4: No lines. Cutoff condition 5: The area of ​​the dialogue (speech bubble) is equal to or greater than a specified percentage of the frame. Cut-off condition 6: The character's entire face does not fit within the frame. Cutoff condition 7: The characters included in the frame are not main characters. Cut-off condition 8: The face of the character included in the frame is deformed.

[0035] In the example of FIG. 3, frame 40A satisfies cutoff condition 4, so an evaluation value is not derived. Also, frame 40B satisfies cutoff condition 1, so an evaluation value is not derived. On the other hand, frames 40C and 40D do not satisfy either cutoff condition, so evaluation values ​​are derived by the evaluation unit 36.

[0036] The following are examples of evaluation rules for evaluating frames of a manga in the romance genre, and scores are set for each evaluation rule. The evaluation rules are determined, for example, based on the relationship between the characteristic parts of frames used in banners that have already been distributed as advertisements and the click rate for the banners.

[0037] Rule 1: Two characters' faces are close together (10 points) Rule 2: Other than the above (5 points) Rule 3: The size of the panel must be at least 50% of the page (+2 points)

[0038] Piece 40C matches rule 2 and is therefore evaluated as 5 points. Piece 40D matches rules 2 and 3 and is therefore evaluated as 7 points, the sum of 5 points and 2 points. These scores for each piece are the evaluation value for each piece.

[0039] The criteria for deriving the evaluation value (in this embodiment, the evaluation rules) differ for each manga genre. That is, the evaluation rules differ for each genre, such as romance, other world, battle, sports, etc. This allows appropriate frames to be used in the advertising data for each manga genre. Furthermore, the cutoff conditions may also differ for each manga genre.

[0040] FIG. 4 is a flowchart showing the flow of the manga advertisement generation process of this embodiment.

[0041] First, in step 100, the operator selects a manga for which a banner is to be generated using the PC 12. The selected manga is stored in the storage unit 20 provided in the server .

[0042] In the next step 102, the cutting unit 30 uses image recognition to cut out frames from the manga selected in step 100. Note that the frames to be cut out are not frames from all volumes or pages of the manga, but rather frames included in, for example, a predetermined page, chapter, or volume.

[0043] In the next step 104, the extraction unit 32 extracts the characteristic parts of the frame.

[0044] In the next step 106, the cutoff unit 34 selects pieces that satisfy the cutoff conditions as pieces not to be evaluated.

[0045] In the next step 108, for frames that do not satisfy the cutoff conditions, the evaluation unit 36 ​​derives an evaluation value for each frame using evaluation rules according to the genre of manga.

[0046] In the next step 110, the banner generation unit 38 displays the frames with the highest evaluation values ​​on the display 13 of the PC 12. The frames displayed on the display 13 are, for example, the 20 frames in descending order of evaluation value. Alternatively, for example, of a plurality of consecutive frames (hereinafter referred to as a "consecutive frame group"), a consecutive frame group with a high average evaluation value may be displayed.

[0047] In the next step 112, the operator selects at least one frame to be used for the banner from among the multiple frames displayed on the display 13.

[0048] In the next step 114, the banner generation unit 38 generates a banner using the frame selected in step 110, and the manga advertisement generation process ends.

[0049] As described above, the manga advertisement generation process of this embodiment derives an evaluation value for each frame based on evaluation rules predetermined for each characteristic part of the frame, and generates a banner using frames selected based on the evaluation value.

[0050] (Second embodiment) The manga advertisement generation process of this embodiment uses a machine learning model to evaluate frames. Note that the configuration of the manga advertisement generation system 10 of the second embodiment is the same as the configuration of the manga advertisement generation system 10 of the first embodiment, so a description thereof will be omitted.

[0051] 5 is a functional block diagram relating to the manga advertisement generation process executed by the server 14 of this embodiment. Note that, in the configuration of the functional block diagram according to the second embodiment, the same parts as those in the first embodiment are denoted by the same reference numerals, and their description will be omitted.

[0052] The calculation unit 24 includes a model generation unit 50, a clipping unit 30, an extraction unit 32, a leg clipping unit 34, an evaluation unit 52, and a banner generation unit 38.

[0053] The model generation unit 50 generates an evaluation model by machine learning using the frames used in the banner and the click rate for the banner as training data. This evaluation model derives an evaluation value indicating the likelihood of attracting attention for each input frame.

[0054] For example, the model generation unit 50 generates an evaluation model using training data in which banners with high click rates are assigned high scores and banners with low click rates are assigned low scores based on the performance of banners that have already been distributed. This allows the model generation unit 50 to learn the characteristics of frames that have high click rates.

[0055] The model generation unit 50 also generates a different evaluation model for each manga genre. That is, the evaluation model differs for each genre, such as romance, other world, battle, and sports. Therefore, the distributed banners used as training data are banners for manga of the same genre. As a result, the evaluation model has different standards for each manga genre, and appropriate frames according to the manga genre can be used in the advertising data.

[0056] The evaluation model may learn the relationship between the time series position in the manga of the banner frame used as training data and the click rate, and may assign a high evaluation value to a frame at a time series position that is appropriate for a banner.

[0057] The evaluation unit 52 derives an evaluation value for each frame by inputting the frame cut out by the cutout unit 30 into the evaluation model generated by the model generation unit 50. As described above, different evaluation models are used for different manga genres, so the evaluation unit 36A derives an evaluation value for each frame using an evaluation model that corresponds to the manga genre for which the banner is to be generated. Note that frames that are determined by the cutout unit 34 to satisfy the cutout conditions are not evaluated using the evaluation model.

[0058] 6 is a flowchart showing the flow of the manga advertisement generation process of this embodiment. Steps of the manga advertisement generation process according to the second embodiment that are the same as those of the first embodiment are given the same reference numerals, and their description will be omitted.

[0059] In step 106, the cutoff unit 34 selects a piece that satisfies the cutoff condition, and then the process proceeds to step 200.

[0060] In step 200, the evaluation unit 52 derives an evaluation value for each frame using the evaluation model, and the process proceeds to step .

[0061] As described above, the manga advertisement generation process of this embodiment derives an evaluation value for a frame by inputting the frame into an evaluation model that has been machine-learned using the characteristic parts of the frame used in the banner and the click rate for the banner as training data, and generates a banner using frames selected based on the evaluation value.

[0062] Although the present invention has been described above using the above-mentioned embodiment, the technical scope of the present invention is not limited to the scope described in the above-mentioned embodiment. Various changes or improvements can be made to the above-mentioned embodiment without departing from the gist of the invention, and such changes or improvements are also included in the technical scope of the present invention.

[0063] In the above embodiment, the evaluation value derived by the evaluation unit 36 ​​is expressed as a score, but the present invention is not limited to this. For example, the evaluation unit 36 ​​may express the evaluation value as a rank such as A, B, or C instead of a score. In the first embodiment, for example, a score is derived as the evaluation value, but the range of scores may be expressed as ranks such as A, B, or C as the output presented to the worker. In the second embodiment, an evaluation model may be generated in which delivered banners are ranked A, B, or C according to the click rate and used as training data, and a rank of A, B, or C may be derived for the frames input to the evaluation model.

[0064] In the above embodiment, the banner generation unit 38 generates a banner using frames with high evaluation values ​​selected by the worker, but the present invention is not limited to this. The banner generation unit 38 may automatically generate a banner using frames with high evaluation values ​​without the worker selecting frames.

[0065] The following additional notes are provided regarding the above-described embodiment. [Appendix 1] The information processing device of Appendix 1 includes a cutting unit that cuts out frames from a manga, an evaluation unit that derives an evaluation value indicating the likelihood of attracting attention for each frame based on characteristic parts of each frame cut out by the cutting unit, and a generation unit that generates advertising data using the frames selected based on the evaluation value.

[0066] According to this configuration, an evaluation value indicating the likelihood of attracting attention for each frame is derived based on the characteristic parts of each frame cut out from the manga, and advertising data is generated using frames selected based on the evaluation value. Therefore, this configuration makes it easy to create appealing manga advertisements.

[0067] [Appendix 2] In the information processing device of Supplementary Note 1, the evaluation unit may derive the evaluation value for each of the frames based on an evaluation rule that is predetermined for each characteristic part of the frame.

[0068] According to this configuration, an evaluation value is derived for each frame based on a predetermined evaluation rule, so that the frame can be easily evaluated as an advertisement.

[0069] [Appendix 3] In the information processing device of Appendix 1, the evaluation unit may derive the evaluation value for the frame by inputting the frame into an evaluation model that has been machine-trained using the frame used in the advertising data and a click rate for the advertising data as training data.

[0070] According to this configuration, an evaluation value is derived for each frame based on a machine-learned evaluation model, making it easy to evaluate the frame as an advertisement.

[0071] [Appendix 4] In the information processing device of any one of Supplementary Note 1 to Supplementary Note 3, the evaluation value may not be derived for the frame that satisfies a predetermined condition.

[0072] According to this configuration, frames that are not appropriate as advertisements are not evaluated, so the overall processing load for evaluating frames as advertisements is reduced.

[0073] [Appendix 5] In any of the information processing devices of Supplementary Note 1 to Supplementary Note 4, the cutting unit may cut out a frame from the manga that is included in at least one of a predetermined page, chapter number, and volume number as the target for deriving the evaluation value.

[0074] According to this configuration, evaluation is performed only on specific frames that are appropriate for advertisements. These specific frames are, for example, frames that include exciting scenes in the manga, and can heighten expectations for the manga among those who view the advertisement data. Furthermore, by evaluating only specific frames, the overall processing load is smaller than when evaluating all frames.

[0075] [Appendix 6] In the information processing device of any one of Supplementary Note 1 to Supplementary Note 5, the criteria for deriving the evaluation value may be different for each genre of the manga.

[0076] According to this configuration, appropriate frames according to the genre of the manga can be used for the advertisement data.

[0077] [Appendix 7] In the information processing device of Supplementary Note 1, the frames may be displayed on a display based on the evaluation value, and the generation unit may generate the advertising data using a frame selected from the frames displayed on the display.

[0078] According to this configuration, the advertising worker can check frames that are appropriate as advertising data.

[0079] [Appendix 8] The advertising data generation method of Appendix 8 includes a first step in which a cutting unit cuts out frames from a manga, a second step in which an evaluation unit derives an evaluation value indicating the likelihood of the frame attracting attention based on characteristic parts of the frame cut out by the cutting unit, and a third step in which a generation unit generates advertising data using the frame selected based on the evaluation value. [Explanation of symbols]

[0080] 10. Ad Generation System 14 Server (information processing device) 30 Cutout 36 Evaluation Department 38 Generation unit (banner generation unit)

Claims

1. A cutting section for cutting out frames from manga, an evaluation unit that derives an evaluation value indicating the likelihood of attracting attention for each of the frames based on the characteristic portion of each of the frames cut out by the cutting unit; a generating unit that generates advertisement data using the frames selected based on the evaluation values, An information processing device in which the criteria for deriving the evaluation value differ for each genre of the manga.

2. The information processing device according to claim 1 , wherein the evaluation unit derives the evaluation value for each of the frames based on an evaluation rule that is predetermined for each characteristic portion of the frame.

3. The information processing device according to claim 1 , wherein the evaluation unit derives the evaluation value for the frame by inputting the frame into an evaluation model that has been machine-learned using the frame used in the advertising data and a click rate for the advertising data as training data.

4. The information processing device according to claim 1 , wherein the evaluation value is not derived for the frame that satisfies a predetermined condition.

5. The information processing device according to claim 1 , wherein the cutting unit cuts out a frame included in at least one of a predetermined page, a predetermined chapter number, and a predetermined volume number from the manga as the target for deriving the evaluation value.

6. displaying the frame on a display based on the evaluation value; The information processing device according to claim 1 , wherein the generating unit generates the advertisement data using the frame selected from the frames displayed on the display.

7. a first step in which a cutting unit cuts out frames from the manga; a second step in which an evaluation unit derives an evaluation value indicating the likelihood of attracting attention to the frame based on the characteristic portion of the frame cut out by the cutting unit; a third step in which a generation unit generates advertisement data using the frames selected based on the evaluation values; and The criteria for deriving the evaluation value differ for each genre of the manga. Advertising data generation method.

Images