Moving image provision device, moving image provision method and moving image provision program

Abstract

To realize a technique that provides a user with a play moving image matching a play style of the user.SOLUTION: A server 3 includes: a play moving image acquisition unit 10 that acquires multiple play moving images; a score calculation unit 12 that calculates a score for each action type in each play moving image on the basis of the play moving images; a cluster generation unit 13 that clusters the multiple play moving images on the basis of the scores to generate the multiple clusters; a cluster selection unit 15 that selects a cluster corresponding to the play moving image of a provision destination user in the multiple clusters on the basis of the score for each action type in the play moving image of the provision destination user; and a play moving image provision unit 16 that provides the provision destination user with at least one of the multiple play moving images belonging to the cluster selected by the cluster selection unit 15. With this configuration, the play moving image matching a play style of a user can be provided to the user.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a moving image providing device, a moving image providing method, and a moving image providing program. [Background technology]

[0002] Patent Document 1 discloses a shogi game server that provides a player with strategy classification information classified according to the strategy adopted by the player, thereby providing the player with the original enjoyment of shogi. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2006-051250 A Summary of the Invention [Problem to be solved by the invention]

[0004] By the way, open-world computer games (hereinafter simply referred to as open-world games) such as FORTNITE (registered trademark) and Minecraft (registered trademark) are known. An open-world game is a game in which a user can freely move around and explore a virtual world within the game, thereby achieving a goal that each user has set freely. Therefore, the play style in an open-world game varies greatly from user to user, and it has been extremely difficult for each user to find a play video that matches his or her own play style on a video providing site.

[0005] An object of the present disclosure is to realize a technology that provides a user with a gameplay video that matches the user's play style. [Means for solving the problem]

[0006] According to the first aspect, A play video acquisition unit that acquires play video; a score calculation unit that calculates a score for each action type in the gameplay video based on the gameplay video; a cluster generation unit that generates one or more clusters by clustering the plurality of gameplay videos based on the scores; a cluster selection unit that selects a cluster corresponding to the gameplay video of the destination user from among one or more of the clusters based on a score for each action type in the gameplay video of the destination user; a gameplay video providing unit that provides at least one of a plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit to the destination user; Including, A video providing device is provided.

[0007] According to the second aspect, Get gameplay video, Calculating a score for each action type in the gameplay video based on the gameplay video; Clustering the plurality of gameplay videos based on the scores to generate one or more clusters; selecting a cluster corresponding to the gameplay video of the destination user from among the one or more clusters based on a score for each action type in the gameplay video of the destination user; providing at least one of a plurality of gameplay videos belonging to the selected cluster to the destination user; A method for providing video is provided.

[0008] According to the third viewpoint, Computer, A play video acquisition unit that acquires play video; a score calculation unit that calculates a score for each action type in the gameplay video based on the gameplay video; a cluster generation unit that generates one or more clusters by clustering the plurality of gameplay videos based on the scores; a cluster selection unit that selects a cluster corresponding to the gameplay video of the destination user from among one or more of the clusters based on a score for each action type in the gameplay video of the destination user; There is provided a video providing program that causes the gameplay video providing unit to function as a gameplay video providing unit that provides at least one of a plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit to the destination user. Effect of the Invention

[0009] According to the present disclosure, a gameplay video that matches the user's play style can be provided to the user. [Brief description of the drawings]

[0010] [Figure 1] 1 is an overall schematic diagram of a video distribution system. [Diagram 2] FIG. 2 is a functional block diagram of a server. [Diagram 3] FIG. 13 is a diagram showing the data structure of a play video DB. [Figure 4] FIG. 11 is an explanatory diagram of a score calculation method. [Diagram 5] FIG. 1 is an explanatory diagram of clustering. [Figure 6] FIG. 2 is a functional block diagram of a terminal. [Figure 7] 13 is a diagram showing an example of thumbnail video display on a terminal. [Figure 8] FIG. 1 is a sequence diagram of a video providing system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present disclosure will be described with reference to Figs. 1 to 8. Fig. 1 is an overall schematic diagram of a video distribution system. As shown in Fig. 1, the video distribution system 1 is composed of a plurality of terminals 2 and a server 3. The plurality of terminals 2 are configured to be capable of two-way communication with the server 3 via a communication network 4 such as a LAN (Local Area Network) or a WAN (Wide Area Network). The server 3 is a specific example of a video providing device. In this embodiment, the server 3 is realized by a single device. However, instead of this, the server 3 may be realized by distributed processing by a plurality of devices.

[0012] Fig. 2 shows a functional block diagram of the server 3. As shown in Fig. 2, the server 3 includes a processor 3a, a memory 3b, and a communication interface (communication IF) 3c. The processor 3a executes a program stored in the memory 3b, thereby causing hardware such as the processor 3a to function as a gameplay video acquisition unit 10, a score calculation unit 12, a cluster generation unit 13, a video request acceptance unit 14, a cluster selection unit 15, a gameplay video provision unit 16, and a reward processing unit 17. A gameplay video database 11 is built in the memory 3b.

[0013] The gameplay video acquisition unit 10 acquires gameplay videos of multiple users. In this embodiment, the length of each gameplay video is set to 10 minutes. The gameplay video acquisition unit 10 stores the acquired gameplay videos in the gameplay video database 11. Specifically, the process is as follows.

[0014] The gameplay video acquisition unit 10 acquires gameplay videos from multiple terminals 2 via the communication interface 3c. Then, the gameplay video acquisition unit 10 associates the acquired gameplay videos with the user accounts of the corresponding users and stores them in a gameplay video database 11 (gameplay video DB). FIG. 3 shows the data structure of the gameplay video database 11. As shown in FIG. 3, the gameplay video database 11 stores gameplay video IDs, gameplay video data, and user accounts in association with each other.

[0015] The score calculation unit 12 calculates a score for each action type in each of a plurality of play videos stored in the play video database 11 based on the content of the play video. In this embodiment, the action types include a battle score, a construction score, and a cooperative play score, as shown in FIG. 3. The score calculation unit 12 stores the calculated scores in the play video database 11. Specifically, the scores are as follows.

[0016] 4 shows a score calculation process by the score calculation unit 12. The score calculation unit 12 evaluates each gameplay video by analyzing the character's actions and the results of those actions in each gameplay video stored in the gameplay video database 11. When evaluating each gameplay video, multiple main action scores and multiple sub-action scores are calculated.

[0017] Each main action score is a score calculated based on at least one sub-action score, and is a score of a main action that comprehensively captures actions performed by the user while playing. In this embodiment, the multiple main action scores include a "combat score" that is a score of a combat action performed by the user while playing, a "building score" that is a score of a building action performed by the user while playing, and a "co-play score" that is a score of a co-play action performed by the user while playing. Then, the score calculation unit 12 calculates a combat score, a building score, and a co-play score for each play video. In this way, the score calculation unit 12 evaluates the play style in each play video from multiple perspectives.

[0018] Each sub-action score is a score for calculating the main action score, and is a score of a sub-action captured by subdividing an action performed by the player while playing. In this embodiment, the multiple sub-action scores are the scores of the following sub-actions performed by the user while playing: "run" "walk" "jump" "Travel by car with another player" "Pick up an item" "Use an item" "Create a building" "Destroy the building" "Kill an enemy using a ranged weapon" "Kill an enemy using a close-range weapon" "Move with another player" Chat with another player

[0019] When calculating the multiple subaction scores, the score calculation unit 12 divides the gameplay video into multiple segments at unit time intervals, acquires the action of each subaction based on the content of the gameplay video for each segment, and calculates the multiple subaction scores for each segment based on the acquired action of the subaction. For example, in segment No. 7, the subaction score of the subaction "run" is 10, the subaction score of the subaction "travel by car with another player" is 40, and the subaction score of the subaction "create a building" is 4. However, the subaction score of the subaction "run" is the number of seconds the subaction was performed, and the subaction score of the subaction "create a building" is the number of times the subaction was performed. Therefore, when calculating the multiple main action scores, the score calculation unit 12 needs to normalize the multiple subaction scores. Specifically, when calculating the combat score for the No. 7 segment, the score calculation unit 12 calculates the combat score by weighting and adding up the subaction scores of "walk", "run", "fly", "create a building", "destroy a building", and "kill an enemy using a long-range weapon", instead of simply adding up the subaction scores of "walk", "create a building", "destroy a building", and "kill an enemy using a long-range weapon". That is, in this embodiment, the score calculation unit 12 calculates the combat score by adding up the subaction score of "run" multiplied by 0.1, the subaction score of "walk" multiplied by 0.1, the subaction score of "fly" multiplied by 0.1, the subaction score of "create a building" multiplied by 0.5, the subaction score of "destroy a building" multiplied by 0.3, and the subaction score of "kill an enemy using a long-range weapon" multiplied by 1. Then, the score calculation unit 12 adds up the main action scores for each segment for each main action score. For example, the score calculation unit 12 calculates the battle score for the gameplay video by adding up the battle score for segment No. 1, the battle score for segment No. 2, the battle score for segment No. 3, ... and the battle score for segment No. 1000.3, the score calculation unit 12 associates the calculated main action scores with the gameplay video and stores them in the gameplay video database 11. The weighting may be changed as appropriate depending on the game category.

[0020] The score calculation unit 12 further deletes segments whose main action scores are less than a predetermined value, and generates a thumbnail video by connecting the remaining multiple segments together, as shown in Figures 3 and 4, and stores the generated thumbnail video in the gameplay video database 11 in association with the gameplay video.

[0021] The score calculation unit 12 further calculates an assigned point for the gameplay video by adding up the multiple main action scores as shown in FIG. 3, and stores the calculated assigned point in the gameplay video database 11 in association with the gameplay video.

[0022] The score calculation unit 12 may further add chapter data to the beginning of a segment in which any one of the main action scores exceeds a predetermined value in Fig. 4, so that the chapters can be played back when the gameplay video is played back. In this case, the predetermined value may be, for example, 30.

[0023] In this embodiment, the duration of the multiple gameplay videos is uniformly set to 10 minutes as described above. However, instead of this, the duration of the multiple gameplay videos may be different from each other. In this case, the score calculation unit 12 may normalize the multiple main action scores according to the duration of the gameplay videos when calculating the multiple main action scores. For example, if the battle score of a gameplay video with a duration of 20 minutes is 200, the battle score of the gameplay video may be set to 100, and if the battle score of a gameplay video with a duration of 5 minutes is 50, the battle score of the gameplay video may be set to 100.

[0024] The cluster generation unit 13 generates a plurality of clusters by clustering a plurality of play videos based on the main action score. Please refer to FIG. 5. FIG. 5 is a diagram illustrating clustering by the cluster generation unit 13. As shown in FIG. 5, the cluster generation unit 13 plots a plurality of play videos in a three-dimensional space configured with an axis corresponding to the battle score, an axis corresponding to the building score, and an axis corresponding to the co-play score. Then, the cluster generation unit 13 performs non-hierarchical clustering such as the k-means method. Here, the number of clusters when performing non-hierarchical clustering can be appropriately determined in consideration of the complexity of the game and the user's preferences. In FIG. 5, the number of clusters is set to 3. Therefore, the cluster generation unit 13 generates cluster A, cluster B, and cluster C.

[0025] Note that the cluster generation unit 13 may execute hierarchical clustering instead of non-hierarchical clustering. The cluster generation unit 13 clusters a plurality of gameplay videos based on three main action scores, but may instead cluster a plurality of gameplay videos based on one or more main action scores. For example, when clustering a plurality of gameplay videos based on one main action score, the plurality of gameplay videos are plotted in a one-dimensional space formed by an axis corresponding to one main action score. In other words, the number of dimensions of the space may be more than one dimension, with one dimension being the minimum, depending on the type of game.

[0026] The gameplay videos belonging to each cluster shown in Fig. 5 have similar play styles. It is believed that the accuracy of classifying gameplay videos by play style can be improved by clustering gameplay videos in a multidimensional space as shown in Fig. 5.

[0027] The cluster generating unit 13 may set a cluster point for each generated cluster. For example, when the number of play videos belonging to cluster A is 200, the cluster point of cluster A may be set to 200, and when the number of play videos belonging to cluster B is 5, the cluster point of cluster B may be set to 5. When the cluster point is set for each cluster in this way, the reward processing unit 17 described later can execute reward processing by referring to the cluster point set for each cluster.

[0028] The video request receiving unit 14 receives a video request from any of the terminals 2. The video request includes the user account of the user making the request.

[0029] The cluster selection unit 15 selects a cluster corresponding to the play video of the destination user from among the multiple clusters based on multiple main action scores in the play video of the destination user. The destination user means a party to whom the play video is provided, and means a user who is a request source of a video request. The cluster selection unit 15 executes a search in the play video database 11 shown in FIG. 3 using a user account included in the video request as a key. Then, obtains multiple main action scores corresponding to the play video of the user account. Here, the play video of the destination user already belongs to any of the clusters shown in FIG. 5. Therefore, the cluster selection unit 15 may specify a cluster corresponding to the play video of the destination user based on the clustering result by the cluster generation unit 13. If the play video of the destination user was not included in the processing target when the cluster generation unit 13 executed the clustering, the cluster selection unit 15 may calculate multiple main action scores in the play video of the destination user, and select a cluster corresponding to the play video of the destination user from among the multiple clusters based on the calculation result.

[0030] The gameplay video providing unit 16 provides at least one of the gameplay videos belonging to the cluster selected by the cluster selecting unit 15 to a destination user.

[0031] The gameplay video providing unit 16 may provide to the destination user a gameplay video having a higher total value of multiple clustering scores, which are multiple main action scores referred to at the time of clustering, among the multiple gameplay videos belonging to the cluster selected by the cluster selecting unit 15, than the total value of multiple clustering scores of the gameplay videos of the destination user. In this embodiment, the multiple clustering scores are composed of a battle score, a building score, and a cooperative play score. For example, when the total value of the multiple clustering scores of the gameplay videos of the destination user is 200, the gameplay video providing unit 16 may provide to the destination user at least one gameplay video having a total value of multiple clustering scores of 200 or more among the multiple gameplay videos belonging to the cluster selected by the cluster selecting unit 15.

[0032] Furthermore, the gameplay video providing unit 16 may provide to the destination user a gameplay video having the highest specific main action score among a plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit 15. Specifically, the gameplay video providing unit 16 may provide to the destination user a gameplay video having the highest battle score among a plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit 15.

[0033] Furthermore, the gameplay video providing unit 16 may provide to the destination user a gameplay video having a plurality of clustering scores equal to or greater than the plurality of clustering scores of the gameplay video of the destination user, among the plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit 15. For example, when the gameplay video of the destination user has a battle score of 100, a building score of 120, and a collaborative play score of 140, the gameplay video providing unit 16 may provide to the destination user at least one gameplay video having a battle score of 100 or more, a building score of 120 or more, and a collaborative play score of 140 or more, among the plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit 15.

[0034] In practice, first, the gameplay video providing unit 16 transmits thumbnail videos of a plurality of gameplay videos, for example, 10, among the plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit 15, to the destination user's terminal 2 via the communication interface 3c. Then, when the gameplay video providing unit 16 receives a selection result in which the destination user has selected at least one thumbnail video among the thumbnail videos of the plurality of gameplay videos, the gameplay video providing unit 16 provides the destination user with the selected at least one gameplay video based on the selection result.

[0035] There are various possible methods for providing gameplay videos. The first method is to transmit video data of the gameplay video to the destination user's terminal 2. The second method is to transmit access means for accessing the gameplay video stored in the gameplay video database 11 of the server 3 to the destination user's terminal 2. The access means is typically a URL.

[0036] When a play video is provided, the reward processing unit 17 transfers the grant points set for the provided play video from the user account of the destination user to the user account corresponding to the provided play video. By transferring the grant points in this manner, an incentive for using the video distribution system 1 can be given to all users. Note that the amount of the grant points transferred when a play video is provided may be the grant points set for the provided play video, or may be a final point amount calculated based on the grant points set for the provided play video and the cluster points set for the cluster to which the play video belongs.

[0037] Next, referring to Fig. 6, Fig. 6 shows a functional block diagram of the terminal 2. As shown in Fig. 6, the terminal 2 includes a processor 2a, a memory 2b, a communication interface (communication IF) 2c, an input interface (input IF) 2d, and an LCD 2e. The processor 2a executes a program stored in the memory 2b, causing hardware such as the processor 2a to function as a game application 20, a play video recording unit 21, a play video transmission unit 22, a play video request processing unit 23, a play video selection processing unit 24, and a play video playback unit 25.

[0038] The game application 20 is started by a user's operation of the input interface 2d as a trigger. Then, the gameplay recording unit 21 records the game play on the game application 20 and generates a gameplay video. The application 20 may be executed on another device. In this case, the game screen of the user playing on the other device may be captured by a camera provided on the terminal 2, and the gameplay recording unit 21 may generate a gameplay video based on the captured game screen.

[0039] The gameplay video sending unit 22 sends the gameplay video generated by the gameplay recording unit 21 to the server 3 via the communication interface 2c. At this time, the length of the gameplay video is appropriately set according to the type of game. As described above, the length of the gameplay video is set to 10 minutes.

[0040] The play video request processor 23 transmits a video request to the server 3 when triggered by a user's operation of the input interface 2d.

[0041] The gameplay video selection processing unit 24 displays a list of the multiple thumbnail videos received from the server 3 on the LCD 2e as shown in Fig. 7. At this time, the gameplay video selection processing unit 24 may superimpose the assigned points corresponding to each thumbnail video on the thumbnail video as shown in Fig. 7. The user selects one of the multiple thumbnail videos by, for example, tapping on the LCD 2e. The gameplay video selection processing unit 24 transmits the user's selection result to the server 3 via the communication interface 2c.

[0042] The gameplay video playback unit 25 plays back on the LCD 2e the gameplay video provided from the server 3. Typically, the gameplay video playback unit 25 accesses the gameplay video database 11 of the server 3 using an access means for the gameplay video provided from the server 3, receives the gameplay video in, for example, a streaming format, and plays it back on the LCD 2e.

[0043] The above-described functional blocks of the server 3 and the terminal 2 operate according to the control flow of the video distribution system 1 shown in FIG.

[0044] First, the user starts up game application 20 on terminal 2 (S100). Then, play recording unit 21 of terminal 2 records the game play on game application 20 and generates a gameplay video (S110).

[0045] Next, the gameplay video sending unit 22 of the terminal 2 sends the gameplay video generated by the gameplay recording unit 21 to the server 3 via the communication interface 2c (S120). The gameplay video acquiring unit 10 of the server 3 receives the gameplay video from the terminal 2 and stores the received gameplay video in the gameplay video database 11 (S120).

[0046] The process from step S100 to step S120 is repeatedly executed between all terminals 2 and the server 3 that use the video distribution system 1. As a result, the gameplay video database 11 accumulates, for example, tens of thousands of gameplay videos.

[0047] The score calculation unit 12 of the server 3 calculates a plurality of main action scores in each of a plurality of gameplay videos stored in the gameplay video database 11 (S130).

[0048] The cluster generating unit 13 of the server 3 clusters the gameplay videos based on the main action scores to generate a plurality of clusters (S140).

[0049] The play video request processing unit 23 of the terminal 2 is triggered by a user's operation of the input interface 2d to transmit a video request to the server 3 (S150). The video request receiving unit 14 of the server 3 receives the video request from the terminal 2 (S150).

[0050] The cluster selection unit 15 of the server 3 selects a cluster corresponding to the play video of the destination user from among the multiple clusters, based on a plurality of main action scores in the play video of the destination user (S160).

[0051] The gameplay video providing unit 16 of the server 3 transmits thumbnail videos of multiple gameplay videos, for example 10, among the multiple gameplay videos belonging to the cluster selected by the cluster selecting unit 15 to the destination user's terminal 2 via the communication interface 3c (S170).

[0052] The gameplay video selection processing unit 24 of the terminal 2 displays the multiple thumbnail videos received from the server 3 on the LCD 2e as shown in Fig. 7. The user selects one of the multiple thumbnail videos by, for example, tapping on the LCD 2e (S180). The gameplay video selection processing unit 24 transmits the user's selection result to the server 3 via the communication interface 2c (S190).

[0053] Upon receiving the selection result from the terminal 2, the gameplay video providing unit 16 of the server 3 provides at least one gameplay video selected based on the selection result to the destination user (S200).

[0054] The gameplay video playback unit 25 of the terminal 2 plays the gameplay video provided by the server 3 on the LCD 2e (S210).

[0055] Then, when a gameplay video is provided, the reward processing unit 17 of the terminal 2 transfers the final points from the user account of the destination user to the user account corresponding to the gameplay video (S220).

[0056] The preferred embodiment of the present disclosure has been described above, and the above embodiment has the following features.

[0057] The server 3 (video providing device) includes a play video acquisition unit 10 that acquires a gameplay video, a score calculation unit 12 that calculates a score for each action type in the play video based on the play video, a cluster generation unit 13 that clusters a plurality of play videos based on the scores to generate one or more clusters, a cluster selection unit 15 that selects a cluster corresponding to the play video of the destination user from the one or more clusters based on the score for each action type in the play video of the destination user, and a play video provision unit 16 that provides the destination user with at least one of the plurality of play videos belonging to the cluster selected by the cluster selection unit 15. With the above configuration, a play video that matches the user's play style can be provided to the user.

[0058] In addition, in the embodiments of the present disclosure, the example of gameplay video of an open world game has been described, but similar problems can also be solved in other game fields such as soccer, baseball, racing, and action role-playing games, not limited to open world games, as the unique play style of the user is reflected in the game.

[0059] In the above example, the program can be stored and provided to the computer using various types of non-transitory computer readable media. The non-transitory computer readable media includes various types of tangible storage media. Examples of the non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives) and magneto-optical recording media (e.g., magneto-optical disks). Examples of the non-transitory computer readable media further include CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM. Examples of the non-transitory computer readable media further include PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM (random access memory). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path. [Explanation of symbols]

[0060] 1. Video distribution system 2. Terminal 3 Server 4. Communication Network 10. Gameplay video acquisition section 11 Play video database 12 Score calculation section 13 Cluster Generation Unit 14 Video Request Reception Department 15 Cluster Selection Section 16 Play Video Provider 17 Reward Processing Unit 20. Gaming Applications 21 Play Recording Department 22 Play video transmission section 23 Play video request processing unit 24 Play video selection processing unit 25 Playback video section

Claims

1. A play video acquisition unit that acquires play video; a score calculation unit that calculates a score for each action type in the gameplay video based on the gameplay video; a cluster generation unit that generates one or more clusters by clustering the plurality of gameplay videos based on the scores; a cluster selection unit that selects a cluster corresponding to the gameplay video of the destination user from among the one or more clusters based on a score for each action type in the gameplay video of the destination user; a gameplay video providing unit that provides at least one of a plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit to the destination user; Including, Video providing device.

2. the gameplay video providing unit provides to the destination user a gameplay video having a higher total score for each action type than a total score for each action type of the gameplay video of the destination user, among the plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit; The video providing device according to claim 1 .

3. the gameplay video providing unit provides to the destination user a gameplay video having the highest score for a specific action type among the plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit; The video providing device according to claim 1 .

4. Get gameplay video, Calculating a score for each action type in the gameplay video based on the gameplay video; Clustering the plurality of gameplay videos based on the scores to generate one or a plurality of clusters; selecting a cluster corresponding to the gameplay video of the destination user from among the one or more clusters based on a score for each action type in the gameplay video of the destination user; providing at least one of a plurality of gameplay videos belonging to the selected cluster to the destination user; How to provide videos.

5. Computer, A play video acquisition unit that acquires play video; a score calculation unit that calculates a score for each action type in the gameplay video based on the gameplay video; a cluster generation unit that generates one or more clusters by clustering the plurality of gameplay videos based on the scores; a cluster selection unit that selects a cluster corresponding to the gameplay video of the destination user from among the one or more clusters based on a score for each action type in the gameplay video of the destination user; a gameplay video providing unit that provides at least one of a plurality of gameplay videos belonging to the cluster selected by the cluster selecting unit to the destination user; A video provision program that functions as a.

Images