JP6370854B2 - Creation device, creation method, and creation program - Google Patents

Description

The present invention, creation device, about the creation how and create programs.

  In recent years, with the rapid spread of the Internet, various services are provided through the network. One of the services is a video distribution service. The provider of the moving image distribution service distributes various moving images in response to a user request.

  A provider of a video distribution service may distribute advertising content together with a video. In such a service, a technology related to a content viewing system that can appropriately distribute effective advertisement / advertisement information to a viewer user is known (for example, Patent Document 1).

  In addition, as a means of utilizing video content, there is a technology that creates an individual optimal distribution list (program guide) for individual viewers and distributes / views content that matches the viewer's taste, mood, and emotion. Known (for example, Patent Document 2). In addition, when playing back an information recording medium in which video content is recorded, a video thumbnail corresponding to the video content is displayed so that the viewer can grasp the content of the video or view desired moving image data. The technique to do is known (for example, patent document 3).

JP 2007-104439 A JP 2010-130051 A JP 2001-238175 A

  However, in the above-described conventional technology, it is not always possible to promote the user's desire for viewing the distributed content. For example, in a commercial video content such as a movie, a partial video showing an outline for promoting viewing of the video content may be created. However, depending on the content of the partial video, the user's desire to view the video content may not be increased.

  The moving image content distributed by the moving image distribution service is not necessarily commercial moving image content such as a movie. In many non-commercial moving image contents, a partial moving image showing an outline is not created. Therefore, moving image content is introduced using a still image thumbnail or the like on which the title of the moving image content is displayed. Then, it is difficult for the viewer to determine whether or not to view the moving image content based on scarce information such as a still image thumbnail, and as a result, a situation in which viewing of the moving image content in the moving image distribution service is not promoted may occur.

  The present application has been made in view of the above, and an object thereof is to provide a creation device, a creation method, and a creation program that can promote a user's desire to view distributed content.

  The creation device according to the present application includes an acquisition unit that acquires information regarding a usage situation in which video content corresponding to the partial video is used in a terminal device that is a distribution destination of the partial video used as a headline of the video content; And a creation unit that creates a partial moving image corresponding to the moving image content based on the information acquired by the acquisition unit.

  According to one aspect of the embodiment, there is an effect that the user's desire to view the content to be distributed can be promoted.

FIG. 1 is a diagram illustrating an example of a creation process according to the embodiment. FIG. 2 is a diagram illustrating an example of a video distribution site according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of a creation processing system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the creation apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of a content storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of a usage status storage unit according to the embodiment. FIG. 8 is a diagram for explaining a process of creating a moving image thumbnail by the creating unit according to the embodiment. FIG. 9 is a diagram illustrating a new moving image thumbnail creation process by the creation unit according to the embodiment. FIG. 10 is a flowchart (1) illustrating a processing procedure performed by the creation apparatus according to the embodiment. FIG. 11 is a flowchart (2) illustrating a processing procedure performed by the creation apparatus according to the embodiment. FIG. 12 is a flowchart (3) illustrating a processing procedure performed by the creation apparatus according to the embodiment. FIG. 13 is a diagram illustrating an example of a user information storage unit according to the modification. FIG. 14 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the creation apparatus.

  Hereinafter, a creation apparatus, a creation method, and a creation program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. Note that the creation device, creation method, and creation program according to the present application are not limited to the embodiment. In addition, the embodiments can be appropriately combined within a range that does not contradict processing contents. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[1. Example of creation process)
First, an example of a creation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a creation process according to the embodiment. FIG. 1 shows an example in which a creation apparatus 100 that executes creation processing according to the present application performs processing for creating a moving image thumbnail that is a heading of moving image content.

  The creation device 100 is a server device that holds video content used in the video distribution service. The moving image distribution service is a service for distributing moving image content to a user who desires moving image content for a fee or free of charge. The video distribution service is provided via a video distribution site, for example. The creation apparatus 100 creates a partial movie (hereinafter referred to as “moving image thumbnail”) as a heading of the moving image content by cutting out a part of the moving image content. Then, the creation device 100 presents the user with information by acquiring information on the user who uses the video distribution service (hereinafter referred to as “user information”) and information on the usage status of the user's video distribution service. Appropriate matching processing with the video thumbnail is executed. Alternatively, the creation device 100 creates a moving image thumbnail based on the acquired information. Hereinafter, an example of the moving image thumbnail creation process performed by the creation apparatus 100 will be described along the flow.

  First, the creating apparatus 100 creates a plurality of moving image thumbnails corresponding to the stored moving image content at random. For example, the creating apparatus 100 creates a moving image thumbnail by cutting out a part of moving image content (for example, 10 seconds) at an arbitrary position. In the example of FIG. 1, the creation apparatus 100 creates moving image thumbnails T01, T02, and T03 cut out at random positions for the moving image content C01 (step S11).

  Then, when the user accesses the moving image distribution site, the creating apparatus 100 distributes the created moving image thumbnail together with a list of moving image contents that are distribution candidates. Here, an example of the display of the moving image thumbnail will be described with reference to FIG.

  FIG. 2 is a diagram illustrating an example of a video distribution site according to the embodiment. FIG. 2 shows an example of a moving image distribution site displayed on the web browser 50 of the user terminal 10 (illustration is omitted in FIGS. 1 and 2) when the user accesses the moving image distribution site. As shown in FIG. 2, still image thumbnails such as moving image contents C01 to C04 that are distribution candidates are displayed on the moving image distribution site. Usually, the user receives the distribution of the moving image content by checking still image thumbnails such as the moving image contents C01 to C04 and selecting the desired moving image content with the mouse cursor 40.

  On the other hand, according to the creating apparatus 100, the moving image thumbnail is displayed as the heading of the moving image content. For example, as shown in FIG. 2, when the user moves the mouse cursor 40 to a position overlapping the moving image content C01 (so-called mouse-over state), the user terminal 10 is associated with the moving image content C01. Any one of the moving image thumbnails T01 to T03 is displayed (reproduced). That is, the user can confirm a part of the content included in the moving image content C01 before the moving image content C01 is distributed. As described above, according to the creation apparatus 100, the user can directly grasp the content of the moving image content by using the moving image thumbnail instead of estimating the moving image content by using the still image thumbnail. It becomes easy to do.

  Returning to FIG. 1, the description will be continued. The creation device 100 randomly distributes the video thumbnails T01 to T03 to the user terminal 10 as the headline of the video content C01 when the user accesses the video distribution site. Then, the creation apparatus 100 grasps the usage status such as the video thumbnails T01 to T03 viewed by the user and whether or not the user has requested distribution of the video content C01 when the video thumbnail is viewed.

  For example, in FIG. 1, it is assumed that a predetermined male user accesses the moving image distribution site, views the moving image thumbnail T01, and requests distribution of the moving image content C01 (step S12). The request for distribution of the moving image content C01 in this case is made, for example, when the user clicks the area where the moving image thumbnail T01 is displayed while the moving image thumbnail T01 is being reproduced.

  It is assumed that another male user requests distribution of the moving image content C01 after viewing the moving image thumbnail T02 (step S13). In the example of FIG. 1, the number of users who have requested the distribution of the video content C01 after viewing the video thumbnail T02 is greater than the number of users who have requested the distribution of the video content C01 after viewing the video thumbnail T01. Suppose there are many.

  Further, it is assumed that the female user requests distribution of the moving image content C01 after viewing the moving image thumbnail T03 (step S14). That is, in the example of FIG. 1, the number of users who have requested the distribution of the moving image content C01 by viewing the moving image thumbnails T01 and T02 is larger than that of women, and the viewing of the moving image content C01 by viewing the moving image thumbnail T02. It is observed that the number of users who have requested distribution is greater than the number of users who have viewed the moving image thumbnail T01 and requested distribution of the moving image content C01. In addition, it is observed that the number of users who view the moving image thumbnail T03 and request the distribution of the moving image content C01 is larger than that of men.

  The creation apparatus 100 acquires information regarding the usage status for each user as described above (step S15). Here, the usage status information includes user information of the user who has accessed the video distribution site, the rate at which video content is selected using the video thumbnail as described above, and correlation with user attributes, etc. Contains information. For example, the creation device 100 generates information on the user and information on the usage status of the moving image content (in other words, operations on the browser performed on the user terminal 10) based on a cookie (Cookie) transmitted from the user terminal 10 or the like. Get. The user information refers to, for example, user attribute information. Specifically, the user information includes the age and sex of the user.

  Subsequently, the creation apparatus 100 performs a predetermined learning process based on the acquired information (step S16). As will be described in detail later, the creation apparatus 100 evaluates the score for each distributed video thumbnail, and determines whether each video thumbnail is effective in the video distribution service. Based on this, the creation apparatus 100 learns a model that optimizes a moving image thumbnail to be distributed for each user who uses the moving image distribution service. Here, the optimization of the moving image thumbnail means that when the moving image thumbnail is distributed to the user, distribution of the moving image thumbnail that exhibits the most appealing effect to the user is executed. By optimizing the video thumbnail, for example, the creation apparatus 100 has the highest rate of transmission of video content distribution requests (that is, the rate at which the video thumbnail is clicked) to a user having the attribute of male in his twenties. It is possible to perform processing for selecting and distributing a specific moving image thumbnail assumed to be.

  The creation apparatus 100 optimizes the moving image thumbnail to be distributed based on learning (step S17). For example, the creation apparatus 100 optimizes the distribution ratio so that a relatively large number of moving image thumbnails T02 are distributed to male users for moving image thumbnails distributed as headings of the moving image content C01. Further, the creation apparatus 100 optimizes the distribution ratio so that a relatively large number of moving image thumbnails T03 are distributed to female users.

  Note that the creation apparatus 100 may create a new moving image thumbnail based on the acquired information (step S17). For example, when the score obtained by evaluating the moving image thumbnail T01 is equal to or less than a predetermined numerical value, the creating apparatus 100 deletes the moving image thumbnail T01 from the distribution candidates and newly creates the moving image thumbnail T04. Then, the creation device 100 distributes the moving image thumbnail T04 when the moving image distribution service is newly accessed. For example, the creation device 100 uses a uniform distribution ratio for the video thumbnails T02 to T04 for users whose distribution destinations are not users suitable for the video thumbnail T02 and the video thumbnail T03 as described above. Select and distribute one video thumbnail from the list. As described above, the creating apparatus 100 may distribute the newly created moving image thumbnail T04 to an arbitrary user. Then, the creation device 100 improves the effect of the moving image thumbnail to be distributed step by step by repeating the process of acquiring information about the usage status and the learning process.

  As described above, the creating apparatus 100 according to the embodiment creates a moving image thumbnail that is a partial moving image used as a heading of the moving image content from a portion of the moving image content. Then, the creation apparatus 100 acquires information regarding the usage status in which the moving image content corresponding to the moving image thumbnail is used. In addition, the creation apparatus 100 optimizes the selection of a moving image thumbnail to be associated with the moving image content on the basis of the acquired information on the usage situation and distributes a suitable moving image thumbnail to the user. In addition, the creation apparatus 100 creates a new moving image thumbnail based on the acquired information on the usage situation and the like.

  As described above, the creation apparatus 100 according to the embodiment performs the optimization process of the moving image thumbnail to be referred to when the user selects the moving image content. For example, by using the creation device 100, the submitter can create a moving image thumbnail that can be expected to appeal to various user groups. That is, according to the creation apparatus 100, the user's interest is aroused by selecting and distributing a moving image thumbnail assumed to be interested in a specific user layer. Also, for the user, it is determined whether or not to use the video content after actually viewing the video thumbnail, rather than guessing the content of the video content from still image thumbnails or comments of other users. be able to. This leads to lowering the threshold of the user's action to view the moving image content. As a result, the creation apparatus 100 can promote the user's desire to view the distributed content.

[2. Configuration of creation processing system]
Next, the configuration of the creation processing system 1 including the creation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the creation processing system 1 according to the embodiment. As illustrated in FIG. 3, the creation processing system 1 according to the embodiment includes a user terminal 10, a submission terminal 20, and a creation device 100. These various devices are communicably connected via a network N by wire or wireless. Note that the creation processing system 1 shown in FIG. 3 may include a plurality of user terminals 10 and a plurality of submission terminals 20.

  The user terminal 10 is, for example, an information processing terminal such as a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, or a PDA (Personal Digital Assistant). For example, the user terminal 10 acquires a web page related to a desired service by accessing a web server (corresponding to the creation device 100 in the embodiment) that provides a moving image distribution site or the like according to an operation by the user. Then, the user terminal 10 displays the acquired web page on a display device (for example, a liquid crystal display).

  The submission terminal 20 is an information processing apparatus used by a submitter who requests the creation apparatus 100 for moving image content. The submission terminal 20 submits the moving image content to the creation apparatus 100 according to the operation by the submitter.

  As described above, the creation device 100 is a server device that creates a moving image thumbnail corresponding to the moving image content. In addition, the creation apparatus 100 promotes viewing of the moving image content of the user by the process of optimizing the moving image thumbnail to be distributed.

  Note that, as described above, the creation device 100 can identify the user terminal 10 and specify the user terminal 10 that distributes the moving image thumbnail when distributing the moving image thumbnail. For example, the user can be identified by including user identification information in a cookie exchanged between the web browser of the user terminal 10 and the creation apparatus 100. However, the method for identifying the user is not limited to the above. For example, a dedicated program may be set in the user terminal 10 and user identification information may be transmitted to the creation apparatus 100 from the dedicated program.

[3. Configuration of creation device]
Next, the configuration of the creation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the creation apparatus 100 according to the embodiment. As illustrated in FIG. 4, the creation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The creation device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the creation device 100, and a display unit (for example, a liquid crystal display) that displays various types of information. You may have.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the user terminal 10 and the submission terminal 20 via the network N.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a content storage unit 121, a user information storage unit 122, and a usage status storage unit 123.

(About the content storage unit 121)
The content storage unit 121 stores information regarding moving image content submitted from the submission terminal 20. Here, FIG. 5 shows an example of the content storage unit 121 according to the embodiment. FIG. 5 is a diagram illustrating an example of the content storage unit 121 according to the embodiment. As shown in FIG. 5, the content storage unit 121 includes items such as “contributor ID”, “moving image content ID”, and “moving image thumbnail ID”.

  “Submiter ID” indicates identification information for identifying the submitter or the submission terminal 20. The “moving image content ID” indicates identification information for identifying moving image content submitted to the creation apparatus 100 from the submitter. “Movie thumbnail ID” indicates information for identifying a movie thumbnail created from the corresponding movie content.

  In the following, the identification information shown in FIG. 5 may be used as a reference symbol. For example, the submitter identified by the submitter ID “CL11” is “trafficator CL11”, the video content identified by the video content ID “C11” is “video content C11”, and the video thumbnail ID “T11”. "May be referred to as" moving image thumbnail T11 ".

  That is, in the example illustrated in FIG. 5, the submitter identified by the submitter ID “CL11” submits the moving image content identified by the moving image content ID “C11”. Further, an example is shown in which moving image thumbnails T11 to T13 are created as moving image thumbnails corresponding to the moving image content C11.

  Note that moving image content and moving image thumbnail data that are actually distributed to the user terminal 10 may be stored in a predetermined storage server provided separately from the creating apparatus 100. In this case, the creation apparatus 100 identifies the moving image content and the moving image thumbnail stored in the external storage server based on the moving image content ID and the moving image thumbnail ID stored in the content storage unit 121. Then, the creation device 100 controls the storage server so as to distribute the specified moving image content and moving image thumbnail to the user terminal 10.

(User information storage unit 122)
The user information storage unit 122 stores information about a user who is a distribution target of moving image content. Here, FIG. 6 illustrates an example of the user information storage unit 122 according to the embodiment. FIG. 6 is a diagram illustrating an example of the user information storage unit 122 according to the embodiment. In the example illustrated in FIG. 6, the user information storage unit 122 includes items such as “user ID”, “sex”, and “age”.

  “User ID” is identification information for identifying the user terminal 10 or the user. Note that the user ID matches the reference code of the user who operates the user terminal 10. That is, the user terminal 10 identified by the user ID “U11” is assumed to be a terminal device operated by the user “U11”.

  “Gender” indicates the gender of the user. “Age” indicates the age of the user. As shown in FIG. 6, in the item “age”, a specific numerical value is not shown, and an age group may be shown like “20's”.

  For example, FIG. 6 shows an example in which the gender of the user U11 identified by the user ID “U11” is “male” and the age is “20s”.

  In the following description, it is assumed that the user includes not only an individual user but also a concept of a user layer having a certain attribute. For example, the user U11 includes a concept as a user group including not only an individual user U11 but also a user having the same attribute as the user U11. In other words, the user U11 may indicate a user group belonging to a layer of “male” and “20s”.

  Although not shown in FIG. 6, the user information storage unit 122 may store user behavior information such as a website access history and a shopping site purchase history. The user information storage unit 122 may store a device ID that is information for identifying the user terminal 10 itself. Unlike the user ID, the device ID indicates identification information recorded in the terminal device itself. The user information storage unit 122 includes items such as “name” indicating the user's name, “annual income” indicating the user's annual income, and “preference” indicating the user's preference as the user attribute information. May be.

(About usage status storage unit 123)
The usage status storage unit 123 stores information regarding the usage status of the moving image content. Here, FIG. 7 illustrates an example of the usage status storage unit 123 according to the embodiment. FIG. 7 is a diagram illustrating an example of the usage status storage unit 123 according to the embodiment. In the example illustrated in FIG. 7, the usage status storage unit 123 includes items such as “video content ID”, “video thumbnail ID”, “video content usage status”, and “attribute usage status”. In addition, the “video content usage status” includes items such as “viewing start rate”, “completion rate”, and “bookmark rate”. In addition, the “usage by attribute” includes items such as “user attribute” and “selection rate”.

  “Movie content ID” and “Movie thumbnail ID” correspond to the items stored in the content information storage unit 121 shown in FIG.

  “Video content usage status” indicates information regarding the status of video content usage on the video distribution site.

  “Viewing start rate” is a rate at which a user who has viewed a video thumbnail has started viewing video content corresponding to the video thumbnail (that is, the user has clicked on the video thumbnail and transmitted a video content distribution request). Show.

  The “completion rate” indicates a rate at which the moving image content viewed by the user is viewed to the end. “Bookmark rate” indicates the rate at which the user bookmarks the moving image content.

  “Attribute-specific usage status” indicates the usage status of the moving image content corresponding to the attribute of the user. “User attribute” indicates a group classified for each user attribute. The user attribute classification corresponds to the user classification stored in the user information storage unit 122. That is, the user attribute “U11” indicates “male” and “20s” attribute.

  “Selection rate” indicates a rate for each user attribute that has started viewing moving image content when viewing a moving image thumbnail.

  For example, FIG. 7 shows that there are moving image thumbnails T11 to T13 as moving image thumbnails corresponding to the moving image content C11. In addition, among the users who have viewed the moving image thumbnail T11, the user who has started viewing the moving image content C11 is “13.0%”, and the user who has viewed the moving image content C11 to the end is “7.0%”. This indicates that the user who added the moving image content C11 to the bookmark is “1.0%”. In addition, the moving image thumbnail T11 is viewed by the users U11 to U14, and the rate at which each user group views the moving image content C11 is “22.0%”, “13.0%”, “8.0%”. ”,“ 12.0% ”. That is, the selection rate of the user U11 who is “male” and “20s” among the users U11 to U14 is relatively high.

(About the control unit 130)
The control unit 130 is configured such that, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like stores various programs (corresponding to an example of a creation program) stored in a storage device inside the creation device 100 as RAM. This is realized by being executed as The control unit 130 is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 4, the control unit 130 includes a submission receiving unit 131, a creation unit 132, a reception unit 133, a distribution unit 134, an evaluation unit 135, an acquisition unit 136, and a learning unit 137. Then, the functions and operations of information processing described below are realized or executed. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as information processing described later is performed. In addition, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 4, and may be another connection relationship.

(About the submission acceptance part 131)
The submission accepting unit 131 accepts submission of moving image content from the submission terminal 20. Then, the submission receiving unit 131 associates the uploader ID for identifying the submitter of the submission source with the moving image content ID, and stores the information related to the input moving image content in the content storage unit 121. . In addition, when the moving image thumbnail created by the submitter is submitted, the submission receiving unit 131 stores the moving image thumbnail created by the submitter in association with the moving image content.

  Further, the submission accepting unit 131 may accept submission of advertisement content distributed together with the moving image content in the moving image distribution service.

(About the creation unit 132)
The creation unit 132 creates a moving image thumbnail corresponding to the moving image content. Specifically, the creation unit 132 creates a video thumbnail corresponding to the video content by cutting out a partial video of a predetermined time (for example, 10 seconds) from the video content received by the submission receiving unit 131. To do.

  Here, the moving image thumbnail creation processing will be described with reference to FIG. FIG. 8 is a diagram for explaining the moving image thumbnail creation processing by the creating unit 132 according to the embodiment. As shown in FIG. 8, the creation unit 132 creates a moving image thumbnail by cutting out a predetermined part of the moving image content. In the example of FIG. 8, the creation unit 132 creates moving image thumbnails T11, T12, and T13 cut out at random positions for the moving image content C11. FIG. 8 shows an example in which the moving image thumbnails T11, T12, and T13 are created by cutting out portions that do not overlap each other, but the creating unit 132 uses the overlapping portions to create a plurality of moving image thumbnails. You may create it.

  The creation unit 132 is immediately after the video content has been submitted, and before the video thumbnail corresponding to the video content is actually distributed, or when information regarding the usage status when the video thumbnail is distributed is not sufficiently acquired. Creates video thumbnails randomly. That is, the creation unit 132 creates a moving image thumbnail by cutting out an arbitrary position of the moving image content.

  In addition, after the moving image thumbnail is distributed and the moving image thumbnail is used by the user, the creating unit 132 creates a moving image thumbnail corresponding to the moving image content based on information acquired by the acquiring unit 136 described later. Note that the creation unit 132 does not necessarily need to create a new moving image thumbnail based on the information acquired by the acquisition unit 136. For example, the creation unit 132 does not need to create a new moving image thumbnail when a sufficient appeal effect is obtained for the moving image thumbnail currently created. In this case, the creation unit 132 can select a moving image thumbnail that is actually distributed from already created moving image thumbnails. Thus, the concept of the creation process of the creation unit 132 includes a process of selecting a moving image thumbnail that has already been created.

  When creating a new video thumbnail, the creation unit 132 creates a new video thumbnail based on the information acquired by the acquisition unit 136 when the appeal effect is recognized in a specific part of the video content. . Alternatively, the creation unit 132 performs a selection process on a partial moving image that can be used as a moving image thumbnail created for another use. The partial video created for another use corresponds to, for example, a short video for promotion created in advance by a video content uploader. In addition, when the video distribution site adopts a method for dividing and distributing the moving image content such as HLS (HTTP Live Streaming) method, the moving image content is divided into each segment (for example, a partial moving image for 10 seconds). Delivered to the user terminal 10. Therefore, the creation unit 132 may perform a selection process such that the segment after division is used as a moving image thumbnail. The appealing effect of the video thumbnail is that the video thumbnail is selected by the user (for example, a gesture such as a mouse click, a touch that can be placed on the touch panel, or an operation that can confirm the user's viewing intention such as voice input). Judgment is made based on the degree of connection with viewing of moving image content.

  That is, the creation unit 132 creates a moving image thumbnail based on the evaluation result by the evaluation unit 135. Specifically, the creation unit 132 newly creates a moving image thumbnail based on information regarding the user behavior that triggered the distribution of the moving image content among the user behavior with respect to the moving image thumbnail. For example, it is assumed that the evaluation unit 135, which will be described later, obtains information that a user can easily click on a video thumbnail in the vicinity of a specific time point. At this time, the creation unit 132 can create a new moving image thumbnail including the specific time point. For example, the creation unit 132 may create a moving image thumbnail whose center is at the center (near 5 seconds of the 10-second video constituting the moving image thumbnail), and the specific time is played back. A moving image thumbnail may be created immediately after the start. The elements of the index value evaluated by the evaluation unit 135 include not only the rate at which the video thumbnail is clicked but also the completion rate of the video content viewed through the video thumbnail, the bookmark rate of the video content, The exit rate from the moving image content may be included. Therefore, the creation unit 132 may create a moving image thumbnail that improves the index value indicated by each element. As an example, as a result of the evaluation by the evaluation unit 135, it is assumed that there is a moving image content having a high viewing rate in the first half portion although the moving image thumbnail click rate is high. At this time, the creating unit 132 creates a moving image thumbnail including the latter half as a moving image thumbnail corresponding to the moving image content. As a result, the creation unit 132 can create a moving image thumbnail that appeals to the user about the attention portion of the moving image content that is latent in the latter half. As described above, the creation unit 132 creates a moving image thumbnail that is assumed to make it easier for the user to view the moving image content by using the evaluation result of the evaluation unit 135.

  In addition, as a result of the evaluation process performed by the evaluation unit 135, the creation unit 132 may newly create a video thumbnail that replaces the video thumbnail when the appealing effect is not recognized for the specific video thumbnail. This point will be described with reference to FIG. FIG. 9 is a diagram illustrating a new moving image thumbnail creation process by the creation unit 132 according to the embodiment.

  As shown in FIG. 9, when the moving image thumbnails T21 to T23 corresponding to the moving image content C21 are prepared, it is assumed that the appeal effect of the moving image thumbnail T23 is evaluated to be relatively low. That is, it is assumed that the index value (score) indicating the appeal effect of the moving image thumbnail T23 is calculated by the evaluation unit 135 to be lower than a predetermined threshold value. At this time, the creation unit 132 cuts out a portion different from the moving image thumbnail T23 having a relatively low score from the moving image content C21 and newly creates a moving image thumbnail T24. Then, the distribution unit 134 described later distributes to the user one of the three video thumbnails including the newly created video thumbnail T24 instead of the video thumbnail T23 having a relatively low appeal effect.

  Further, in the creation process described above, the creation unit 132 may create a moving image thumbnail corresponding to each user layer classified by the user attribute information based on the user information acquired by the acquisition unit 136. . In other words, the acquisition unit 136 acquires information on points that are easily clicked in the moving image thumbnail for each user layer. Then, the creation unit 132 creates a moving image thumbnail optimized for the highest appeal effect for each user group.

(Receiver 133)
The receiving unit 133 receives a content distribution request. Specifically, the receiving unit 133 receives a distribution request for content (for example, a web page) related to the moving image distribution site when the user terminal 10 accesses the moving image distribution site. In other words, the receiving unit 133 receives a distribution request regarding a still image thumbnail or a moving image thumbnail displayed on the top page of the moving image distribution site.

  In addition, the receiving unit 133 receives a moving image content distribution request transmitted from the user terminal 10 when the user is selected as a moving image thumbnail. The selection of the moving image thumbnail indicates, for example, that the moving image thumbnail has been clicked by the user. In addition, the reception unit 133 may receive a distribution request for advertising content displayed on the video distribution site.

(About distribution unit 134)
The distribution unit 134 distributes content corresponding to the distribution request received by the reception unit 133. Specifically, the distribution unit 134 distributes the submitted video content or the video thumbnail created by the creation unit 132 in response to the distribution request transmitted from the user terminal 10.

  For example, the distribution unit 134 distributes a still image thumbnail or a moving image thumbnail that is a heading of moving image content to the user terminal 10 when the moving image distribution site is accessed. At this time, for the predetermined video content, the distribution unit 134 determines that the video content is not acquired sufficiently before the video content is actually distributed or when information on the usage status when the video content is distributed is not sufficiently acquired. A video thumbnail is randomly selected from a plurality of video thumbnails corresponding to and distributed.

  In addition, when learning by the evaluation unit 135 proceeds and a correlation between the appeal effect of the distributed video thumbnail and some element is obtained, the distribution unit 134 distributes the video thumbnail based on the learning result. .

  For example, when the correlation between the user layer and the moving image thumbnail is obtained, the distribution unit 134 distributes the distribution ratio adjusted so that the moving image thumbnail corresponding to the distribution-destination user layer is preferentially distributed. I do. Specifically, when it is determined that the predetermined video thumbnail is “male” and the user group “20s” is highly effective, the distribution unit 134 selects “male” and “20s” user. Deliver the video thumbnails at a relatively high ratio to the layer.

  Note that, as described above, the content data itself that is actually distributed may not be stored in the storage unit 120 of the creation apparatus 100. For example, the distribution unit 134 may distribute the content corresponding to the distribution request to the user terminal 10 by transmitting a control command to a predetermined storage server provided outside.

(About the evaluation unit 135)
The evaluation unit 135 includes an acquisition unit 136 and a learning unit 137, and executes content evaluation processing using each processing unit. Specifically, the evaluation unit 135 evaluates the moving image thumbnail based on the index value (score) indicating the influence of the moving image thumbnail on the viewing of the moving image content based on the information acquired by the acquiring unit 136.

  For example, the evaluation unit 135 evaluates the video thumbnail based on the usage status such as the ratio of the distributed video thumbnail as an opportunity to view the video content, with the degree of contribution of the video thumbnail to the promotion of viewing as a score. . In this case, the evaluation unit 135 may evaluate the appeal effect of the moving image thumbnail for each user layer using a score indicating the degree of appeal to which user layer.

  The result of the evaluation process by the evaluation unit 135 is reflected in the processing of the creation unit 132 and the distribution unit 134 as described above. For example, the creation unit 132 creates a new moving image thumbnail based on the evaluation result by the evaluation unit 135. The distribution unit 134 distributes the moving image thumbnail based on the distribution ratio adjusted in response to the evaluation result by the evaluation unit 135. Specifically, the distribution unit 134 distributes the video thumbnail based on the distribution ratio adjusted so that the video thumbnail having a higher score calculated by the evaluation unit 135 is distributed with higher priority.

(About the acquisition unit 136)
The acquisition unit 136 acquires various types of information. Specifically, the acquisition unit 136 acquires information regarding the usage status of the video content corresponding to the video thumbnail in the user terminal 10 to which the video thumbnail created by the creation unit 132 is distributed. The information related to the usage status in the user terminal 10 includes information related to the user terminal 10 (that is, a user) and information related to the usage status of content in the video distribution site.

  The acquisition unit 136 acquires information about a user who operates the user terminal 10 from the user terminal 10 that has accessed the moving image distribution site. Specifically, the acquisition unit 136 acquires attribute information such as the user's sex and age as information about the user. Note that the acquisition unit 136 may acquire user information such as the user's annual income, preferences, and residence. The acquisition unit 136 acquires information about the user based on a cookie transmitted / received with access to the moving image distribution site. The acquisition unit 136 may acquire user information by receiving provision of user information from a third party who manages the use situation of the network and the user. Then, the acquisition unit 136 stores the acquired user information in the user information storage unit 122.

  In addition, the acquisition unit 136 acquires information on the usage status of the video thumbnails and video content on the video distribution site. Specifically, the acquisition unit 136 acquires a viewing start rate, a completion rate, a bookmark rate, and the like of the moving image content for each moving image thumbnail as information regarding the usage state. That is, the information on the usage status of the content is not necessarily information indicating that the video thumbnail or the video content has been played, but also information indicating the usage status that the video content has not been played even though the video thumbnail has been viewed. Is also included. Note that the acquisition unit 136 may acquire information regarding the usage status when the moving image content is used via the moving image thumbnail. Thereby, the acquisition unit 136 can acquire information indicating how the video thumbnail is used and how the video content is used when viewing the video thumbnail.

  The acquisition unit 136 acquires the usage status of the moving image content for each user attribute. Specifically, the acquisition unit 136 acquires the selection rate for each user attribute and the like for the user who clicked the moving image thumbnail. The acquisition unit 136 stores information regarding the acquired usage status in the usage status storage unit 123.

  Further, the acquisition unit 136 may acquire information other than the information illustrated in FIGS. 6 and 7. For example, the acquisition unit 136 acquires information such as time information at the moment when the video thumbnail is selected by the user, information on the length of time that the user has watched the video content, and a withdrawal rate from the video content as information on the usage status. May be. When the acquiring unit 136 acquires time information at the moment when the moving image thumbnail is selected by the user, the generating unit 132 can generate the moving image thumbnail using the information. That is, since the moving image thumbnail is created by cutting out the moving image content, the time information at the time of clicking is information for specifying the time point in the moving image thumbnail and information for specifying the time point in the moving image content. For this reason, the creation unit 132 can newly create the moving image content based on the time information.

(About the learning unit 137)
The learning unit 137 performs learning for optimizing the content distributed to the user. For example, the learning unit 137 learns the correlation between the appealing effect of the moving image thumbnail corresponding to the predetermined moving image content and the user group based on the information acquired by the acquiring unit 136.

  For example, the learning unit 137 classifies the user group with two elements of “age and sex”. That is, the learning unit 137 classifies the users who have accessed the moving image distribution site by “age, gender”, and determines to which user group it belongs. For example, the learning unit 137 classifies the user U11 shown in FIG. 6 as belonging to the user group of (sex, age) = (male, 20s).

  Then, the learning unit 137 learns how much appealing effect is given to each user layer for a certain moving image thumbnail. As an example, the learning unit 137 counts the number of times a moving image thumbnail is clicked from each user layer. Then, the learning unit 137 learns the appeal effect of the target video thumbnail by statistically processing the counted number of clicks (that is, the number of video thumbnails selected).

  Further, the learning unit 137 can learn a user layer optimized for a moving image thumbnail by machine learning using a known technique. For example, the learning unit 137 establishes a model formula in which correct data (here, a moving image thumbnail is clicked) is placed on the left side, and each element formed by the weight value and the user layer is placed on the right side. Thereby, the learning unit 137 can learn the correlation between the click of the moving image thumbnail and each user layer. According to such a model formula, as the number of moving image thumbnails distributed (that is, the number of samples in the model formula) increases, the weight value of the user layer that is more easily clicked increases. Thereby, the learning unit 137 can derive the appeal effect of the moving image thumbnail for each user layer. Further, the learning unit 137 may link the weight value in the model formula with a distribution ratio that is a ratio at which a plurality of moving image thumbnails are distributed to the user layer. With this learning process, a moving image thumbnail is more likely to be distributed to a user layer that is assumed to have a higher appeal effect on a certain moving image thumbnail.

  Note that the learning unit 137 may adjust the moving image thumbnails to be distributed to a random user layer for a predetermined number of distributions in the course of the learning process. For example, when optimized video thumbnail distribution is executed for all distribution requests, only a limited number of video thumbnails among a plurality of video thumbnails may continue to be distributed. For example, when there is a difference in the appeal effect among a plurality of movie thumbnails, the learning unit 137 may learn to distribute only the movie thumbnail having the highest appeal effect. In order to avoid such excessive learning, the learning unit 137 may perform processing such as randomly distributing a plurality of video thumbnails for a predetermined ratio in response to a distribution request.

  Then, the learning unit 137 may calculate an index value for each moving image thumbnail based on the learning result. For example, the learning unit 137 calculates the appeal effect for each moving image thumbnail as a predetermined score. Then, the learning unit 137 causes the creating unit 132 to create a moving image thumbnail for the moving image thumbnail for which a score equal to or lower than a predetermined threshold is calculated. In this way, moving image thumbnails having a higher appeal effect are extracted by eliminating moving image thumbnails having a lower appeal effect. Alternatively, the creation unit 132 may create a moving image thumbnail that is predicted that the index value for the distribution destination user satisfies a predetermined condition based on the result of the machine learning. The predetermined condition means that an index value for a distribution destination user is higher than a predetermined threshold. For example, the creation unit 132 preferentially creates a moving image thumbnail that is predicted to have the highest index value for the distribution destination user based on the result of the learning process. As described above, the creation unit 132 can use the learning process result by the learning unit 137 to create a video thumbnail having a high appeal effect or to preferentially select a video thumbnail having a high appeal effect. Therefore, user viewing can be promoted. The score may be calculated as a comprehensive score for the entire user for each moving image thumbnail, or may be calculated as a score for each user layer. Such a score is used for evaluation by the evaluation unit 135.

  In addition, the result of learning by the learning unit 137 is held for each moving image content. Here, the learning result held for each video content may be used for other video content. For example, when a plurality of moving image contents are a series of series dramas or the like, the learning unit 137 may use the learning result of one moving image content for other moving image contents in the same series. Thereby, the preparation part 132 may be able to create the moving image content with a high appeal effect even before moving image content is distributed. For example, when the evaluation of a video thumbnail obtained by cutting out a specific time zone in one video content is high, the creation unit 132 also uses the vicinity of the specific time zone for the video thumbnail in the other video content. Can be performed.

  In the learning process described above, various known techniques may be used. For example, the learning process may use a technique used in so-called targeting advertisement, in which advertisement content is distributed to a specific user layer in advertisement distribution via a network.

[4. Processing procedure)
Next, a processing procedure performed by the creation apparatus 100 according to the embodiment will be described with reference to FIGS. 10 to 12. First, the flow of processing for creating a moving image thumbnail from the input moving image content will be described with reference to FIG. FIG. 10 is a flowchart (1) illustrating a processing procedure performed by the creation apparatus 100 according to the embodiment.

  As shown in FIG. 10, the submission accepting unit 131 accepts submission of moving image content (step S101). Then, the creating unit 132 creates a moving image thumbnail that is a partial moving image serving as a heading of the moving image content (step S102). The creation unit 132 stores the moving image content and the created moving image thumbnail in association with each other (step S103).

  Next, processing after the processing in FIG. 10 will be described. FIG. 11 is a flowchart (2) illustrating a processing procedure performed by the creation apparatus 100 according to the embodiment.

  The receiving unit 133 determines whether or not access has been received from the user at the moving image distribution site (step S201). When the access is not accepted (step S201; No), the reception unit 133 waits until the access is accepted.

  On the other hand, when access is accepted (step S201; Yes), the distribution unit 134 distributes the moving image thumbnail according to the distribution request received by the reception unit 133 (step S202). Subsequently, the acquisition unit 136 determines whether or not the moving image content is used on the moving image distribution site (step S203). If not used (step S203; No), the acquisition unit 136 waits until it is used.

  On the other hand, when the usage is accepted (step S203; Yes), the acquisition unit 136 acquires information regarding the usage status (step S204). Subsequently, the learning unit 137 performs optimization processing based on the acquired information (step S205). Details of the optimization process will be described with reference to FIG. After the optimization process, the process proceeds to step S201, and the above process is repeated.

  Next, details of the optimization process will be described. FIG. 12 is a flowchart (3) illustrating a processing procedure performed by the creation apparatus 100 according to the embodiment.

  Based on the information acquired by the acquisition unit 136, the learning unit 137 evaluates the moving image thumbnail (step S301). Then, the learning unit 137 determines whether there is a moving image thumbnail having a predetermined score or less (step S302).

  When there is a moving image thumbnail having a predetermined score or less (step S302; Yes), the learning unit 137 causes the creating unit 132 to newly create a moving image thumbnail (step S303).

  Then, the learning unit 137 optimizes the distribution ratio for a plurality of moving image thumbnails corresponding to the moving image content (step S304). In addition, also when there is no moving image thumbnail below a predetermined score in step S302 (step S302; No), a process transfers to step S304.

[5. (Modification)
The creation apparatus 100 described above may be implemented in various different forms other than the above embodiment. Therefore, in the following, another embodiment of the creation apparatus 100 will be described.

[5-1. Social graph)
In the above-described embodiment, the process of acquiring information about user attributes as user information and creating a moving image thumbnail optimized for each user layer has been described. Here, the user may be classified by different elements instead of attributes such as age.

  For example, the user information storage unit 122 may store information related to the user's social graph. This point will be described with reference to FIG. FIG. 13 is a diagram illustrating an example of the user information storage unit 122 according to the modification.

  As illustrated in FIG. 13, the user information storage unit 122 according to the modification includes items such as “user ID” and “social graph attribute”.

  “User ID” corresponds to the item of user ID shown in FIG. The “social graph attribute” is information for identifying the social graph to which the user belongs.

  That is, FIG. 13 shows an example in which the user U21 identified by the user ID “U21” belongs to the social graph attribute identified by “AAA”.

  The social graph is information indicating a correlation (connection) between users in a network environment. For example, the social graph is constructed by joining information registered in the SNS, information published in the SNS, or the like by participating in an SNS (Social Networking Service) or the like. As attributes of the social graph, for example, a social status of the user, a property assumed to be owned by the user (such as a real estate or a car), or a connection between friends can be used.

  The creation apparatus 100 can optimize the moving image thumbnail to be distributed for each social graph attribute by performing the learning process described in the above embodiment for each social graph attribute. If it demonstrates in the example shown in FIG. 13, the moving image thumbnail evaluated that the effect with respect to the user U21 is high becomes easy to be delivered with respect to the user U25 and the user U26 which belong to the same social graph attribute.

  As described above, the creation apparatus 100 can optimize the moving image thumbnail by classification based on the social graph attribute indicating social connection in addition to the classification based on the attribute of the individual user such as age. Thereby, the creation device 100 can create and distribute a moving image thumbnail that is assumed to have a high appeal effect to a wide range of users.

[5-2. (Video thumbnail display)
FIG. 2 shows an example in which viewing of moving image thumbnails is started when processing for expressing viewing intention such as mouse over is performed on still image thumbnails displayed in a list on the moving image distribution site. However, the creation apparatus 100 may display the moving image thumbnail by a different method.

  For example, the creation apparatus 100 may perform a process in which a moving image thumbnail is randomly or automatically reproduced in response to an operation from a list of moving image contents displayed in a list on the moving image distribution site. That is, the user can view the moving image thumbnail without having to bother the process of overlapping the still image thumbnail and the mouse cursor. As a result, the user can view the moving image thumbnail as if changing the TV channel. Then, if there is video content that interests the user, the user can send a video content distribution request by expressing his / her intention to view the corresponding video thumbnail by a click, gesture, sound, or the like.

[5-3. (Create video thumbnail)
In the above embodiment, it has been described that the creation unit 132 creates a moving image thumbnail used as a heading of moving image content from a part of the moving image content. Here, the part of the moving image content does not necessarily need to be a continuous part. For example, the creation unit 132 may cut out two partial moving images of 5 seconds as part of the moving image content, and create a moving image thumbnail by combining the two partial moving images. Even in this case, information such as when the moving image thumbnail is clicked can be acquired, so that the evaluation unit 135 can perform the optimization processing described in the embodiment. As described above, the creation device 100 can create a moving image thumbnail from a plurality of partial moving images including the vicinity of the time point even when there are a plurality of time points that are particularly easily clicked in the moving image content. Thereby, the creation apparatus 100 can flexibly create a moving image thumbnail according to the appeal effect of the moving image thumbnail and the like.

[5-4. Web server)
In the above embodiment, an example in which the creation apparatus 100 provides a moving image distribution site has been described. However, the moving image distribution site may be provided by a web server different from the creation device 100. In this case, the creation apparatus 100 distributes predetermined content to the web server in accordance with a request transmitted from the web server.

[5-5. Acquisition of usage status)
As described above, the acquisition unit 136 can acquire information such as how long the user has viewed the moving image content and when the user has left the moving image content. Then, the evaluation unit 135 may evaluate the appealing effect of the moving image thumbnail according to the viewing time of the moving image content as well as using the start of viewing of the moving image content as an index value. In addition, the acquisition unit 136 may acquire the retention time during which the line of sight is retained in the moving image thumbnail and the moving image content by an eye tracking method that analyzes the movement of the line of sight on the moving image distribution site of the user. . As described above, the acquisition unit 136 can acquire various types of information as usage state information.

[5-6. Acquisition of user information]
In the creation process according to the above-described embodiment, the acquisition unit 136 has shown an example in which user information is obtained when the user terminal 10 accesses a video distribution site provided by the creation device 100. However, the acquisition unit 136 may acquire user information from the user terminal 10 as well as the case where the user terminal 10 accesses the video distribution site provided by the creation device 100. This point will be described below.

  For example, when the video distribution site accessed by the user terminal 10 is provided from a predetermined web server managed by the same management device as the management device that manages the creation device 100 (for example, a front-end server for the creation device 100) The acquisition unit 136 can acquire user information from the user terminal 10. That is, when the user terminal 10 accesses a moving image distribution site provided by a predetermined web server managed by the management device, the user terminal 10 transmits user information of the user terminal 10 to the management device. This is realized by the user terminal 10 transmitting a cookie to the management apparatus. In this case, the user information transmitted from the user terminal 10 is transmitted to the creation apparatus 100 via the management apparatus. Thereby, the acquisition unit 136 according to the creation device 100 can obtain the user information of the user terminal 10 without using the creation device 100. Note that the acquisition unit 136 can identify each user terminal 10 by checking the above-described cookie or a device ID preset in the user terminal 10.

[5-7. (User layer)
In the embodiment described above, the creation apparatus 100 has shown an example in which users are classified into a predetermined user layer based on user attribute information. For example, in the embodiment, the creation apparatus 100 has shown an example in which users are classified into user groups based on “age”, “gender”, and the like. Here, the creation apparatus 100 may classify users using different user information. For example, the creation apparatus 100 may classify users using “residence”, “annual income”, “preference”, and the like in the user information. Further, the creation apparatus 100 may arbitrarily set the user layer by combining the elements of the user information. Thereby, the creation apparatus 100 can create a suitable moving image thumbnail for a wide user group.

[6. Hardware configuration)
The creation apparatus 100 according to the above-described embodiment is realized by a computer 1000 configured as shown in FIG. 14, for example. Hereinafter, the creation apparatus 100 will be described as an example. FIG. 14 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the creation apparatus 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N shown in FIG. 3), sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to the other devices via the communication network 500. Send to device.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the creation apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The HDD 1400 stores data in the storage unit 120. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from other devices via the communication network 500.

[7. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the acquisition unit 136 and the learning unit 137 illustrated in FIG. 4 may be integrated. Further, for example, information stored in the storage unit 120 may be stored in a storage device provided outside via the network N.

  Further, for example, in the above-described embodiment, an example is shown in which the creation apparatus 100 performs a reception process that accepts input of moving image content, a creation process that creates a moving image thumbnail to be distributed, and a distribution process that distributes a moving image thumbnail. It was. However, the creation device 100 described above may be separated into a reception device that performs reception processing, a creation device that performs creation processing, and a distribution device that performs distribution processing. In this case, the reception device includes a submission reception unit 131. The creation apparatus includes a creation unit 132 and an evaluation unit 135. In addition, the distribution device includes a reception unit 133 and a distribution unit 134. In this case, the processing by the creation device 100 is realized by the creation processing system 1 having each of the reception device, the creation device, and the distribution device.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

[8. effect〕
As described above, the creation device 100 according to the embodiment includes the creation unit 132 and the acquisition unit 136. The acquisition unit 136 acquires information on the usage status of the moving image content corresponding to the moving image thumbnail in the user terminal 10 that is the distribution destination of the moving image thumbnail used as the moving image content heading. The creation unit 132 creates a moving image thumbnail corresponding to the moving image content based on the information acquired by the acquiring unit 136.

  As described above, the creation apparatus 100 according to the embodiment obtains the usage status of the user regarding the content and creates a moving image thumbnail according to the obtained information. Thereby, the creation apparatus 100 can create a moving image thumbnail personalized by the user. For this reason, according to the creation apparatus 100, since the moving image thumbnail with a high appeal effect can be shown with respect to a user, the user's desire for viewing with respect to the delivered content can be promoted.

  In addition, the acquisition unit 136 acquires information on a user corresponding to the user terminal 10 as information on the usage status. The creation unit 132 creates a moving image thumbnail corresponding to each user layer classified by the user attribute information based on the acquired user information.

  Thereby, the creation apparatus 100 according to the embodiment can flexibly create a moving image thumbnail corresponding to various user layers. Therefore, the creation device 100 can create or select a moving image thumbnail that is effective for users having similar attributes. That is, the creation apparatus 100 can create a moving image thumbnail targeted to the user.

  Moreover, the acquisition part 136 acquires the social graph which is the information which shows the correlation between users in a network environment as user information. The creation unit 132 creates a moving image thumbnail corresponding to each user layer classified by the social graph.

  As described above, the creation apparatus 100 according to the embodiment classifies users into user layers using various user information. For this reason, since the creation apparatus 100 can create a moving image thumbnail corresponding to a social graph attribute that is a user layer having a common interest, the appeal effect of the moving image thumbnail to be created can be further improved.

  The creation apparatus 100 according to the embodiment further includes an evaluation unit 135 that evaluates a video thumbnail based on an index value (score) indicating the influence of the video thumbnail on the viewing of the video content based on the information acquired by the acquisition unit 136. Prepare. Further, the creation unit 132 creates a moving image thumbnail from the moving image content based on the evaluation result by the evaluation unit 135.

  As described above, the creation apparatus 100 according to the embodiment evaluates the created moving image thumbnail, and creates a moving image thumbnail based on the evaluation result. As a result, the creation apparatus 100 can eliminate, for example, low-quality video thumbnails, create alternative video thumbnails, and the like, and thus can improve the effect of video thumbnails as a whole. .

  Further, the evaluation unit 135 performs machine learning on the correlation between the index value and information related to the user who operates the user terminal 10. The creation unit 132 creates a moving image thumbnail that is predicted that the index value for the distribution destination user satisfies a predetermined condition based on the result of the machine learning.

  As described above, the creating apparatus 100 according to the embodiment performs machine learning on the created moving image thumbnail to optimize the effect of the moving image thumbnail. For example, the creation unit 132 creates a moving image thumbnail that is predicted to have the highest index value for the distribution destination user. As a result, the creation apparatus 100 can preferentially create or select a highly rated video thumbnail, and can therefore promote the use of video content such as a video distribution site using video thumbnails.

  The creation apparatus 100 according to the embodiment distributes the moving image thumbnail to the user terminal 10 according to the distribution ratio calculated based on the result evaluated by the evaluation unit 135.

  As described above, the creation apparatus 100 according to the embodiment can adjust the ratio of the moving image thumbnails to be distributed according to the evaluation of the moving image thumbnails. Thereby, the creation apparatus 100 can optimize not only the creation process but also the effect brought about by the distribution of the already created moving image thumbnail.

  In addition, the acquisition unit 136 acquires at least one of a rate at which the video thumbnail is selected by the user, a completion rate of the video content viewed through the video thumbnail, and a bookmark rate of the video content as information on the usage status. The creation unit 132 creates a moving image thumbnail based on the information regarding the usage status acquired by the acquisition unit 136.

  As described above, the creation apparatus 100 according to the embodiment acquires various information generated according to the use of the user, and creates a moving image thumbnail based on the acquired information. Therefore, the creation device 100 can create a moving image thumbnail from various viewpoints. For example, the creating apparatus 100 may create a moving image thumbnail that is most likely to start viewing or a moving image thumbnail that is assumed to have the highest completion rate.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, including the aspects described in the disclosure section of the invention, based on the knowledge of those skilled in the art, It is possible to implement the present invention in other forms with improvements.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Creation processing system 10 User terminal 20 Submission terminal 100 Creation apparatus 110 Communication part 120 Storage part 121 Content storage part 122 User information storage part 123 Usage status storage part 130 Control part 131 Submission reception part 132 Creation part 133 Reception part 134 Distribution Part 135 Evaluation part 136 Acquisition part 137 Learning part

Claims (9)

An acquisition unit that acquires information on a usage situation in which a video content corresponding to the partial video is used in a terminal device that is a distribution destination of the partial video composed of a part of the video content;
A creation unit for creating a partial video corresponding to the video content based on the information acquired by the acquisition unit;
A creation device characterized by comprising: The acquisition unit
As information on the usage status, obtain information of a user corresponding to the terminal device,
The creating unit
Based on the user information acquired by the acquisition unit, create the partial video corresponding to each user layer classified by the user attribute information,
The creation apparatus according to claim 1. The acquisition unit
As the user information, obtain a social graph that is information indicating the correlation between users in the network environment,
The creating unit
Creating the partial video corresponding to each user group classified by the social graph acquired by the acquisition unit;
The creation apparatus according to claim 2. Based on the information acquired by the acquisition unit, an evaluation unit that evaluates the partial video according to an index value indicating the influence of the partial video on the viewing of the video content;
Further comprising
The creating unit
Based on the result of the evaluation by the evaluation unit, create a partial video from the video content,
The creation apparatus according to any one of claims 1 to 3. The evaluation unit is
Perform machine learning on the correlation between the index value and information about the user operating the terminal device,
The creating unit
Based on the result of the machine learning, creating a partial video that is predicted that the index value for the user of the distribution destination satisfies a predetermined condition;
The creating apparatus according to claim 4. A distribution unit that distributes the partial video to the terminal device according to a distribution ratio calculated based on a result evaluated by the evaluation unit;
The creation device according to claim 4, further comprising: The acquisition unit
As the usage status information, at least one of a rate at which the partial video is selected by a user, a completion rate of video content viewed through the partial video, and a bookmark rate of the video content is acquired.
The creating unit
Creating the partial video based on information on the usage situation acquired by the acquisition unit;
The creating apparatus according to claim 1, wherein A creation method executed by a computer,
An acquisition step of acquiring information on a usage situation in which a video content corresponding to the partial video is used in a terminal device that is a distribution destination of the partial video composed of a part of the video content;
A creation step of creating a partial video corresponding to the video content based on the information acquired by the acquisition step;
The creation method characterized by including. An acquisition procedure for acquiring information on a usage situation in which a video content corresponding to the partial video is used in a terminal device that is a distribution destination of the partial video composed of a part of the video content;
A creation procedure for creating a partial video corresponding to the video content based on the information acquired by the acquisition procedure;
A program for causing a computer to execute.

Images