Method and apparatus for generating heat video, storage medium and electronic device

Abstract

The present disclosure provides a heat video generation method, a heat video generation device, a computer storage medium and an electronic device, and relates to the technical field of game videos. The heat video generation method comprises the following steps: obtaining an initial heat video, performing video content analysis on the initial heat video to obtain a plurality of heat point dimension information; performing fusion processing on a heat video in which the sum of the heat of at least one same heat point dimension information in the initial heat video is greater than a preset heat value to obtain an intermediate heat video; generating a target heat video corresponding to the video identifier from the corresponding game based on the video identifier of the intermediate heat video, to obtain a new heat video. The present disclosure can improve the number of heat videos and the richness of video content.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of game video, and particularly relates to a hot video generation method, a hot video generation device, a computer storage medium and an electronic device. BACKGROUND

[0002] With the explosive growth of Internet content and the rapid development of video technology, people can watch various types of videos of interest such as games, entertainment, news, etc. For a new hot spot that breaks out in a short period of time, or a new function of a certain game that a large number of users are interested in, or a new game that is online, the access amount of users to the hot video of this type suddenly increases.

[0003] The newly broken-out hot spot or the newly online game in a short period of time usually has a small number of videos and poor video content. SUMMARY

[0004] The present disclosure provides a hot video generation method, a hot video generation device, a computer storage medium and an electronic device, thereby improving the number of hot videos and the richness of video content.

[0005] In a first aspect, one embodiment of the present disclosure provides a hot video generation method, comprising: obtaining an initial hot video, performing video content analysis on the initial hot video to obtain a plurality of hot spot dimension information; performing fusion processing on the hot video in which the sum of the hotness of at least one same hot spot dimension information in the initial hot video is greater than a preset hotness value to obtain an intermediate hot video; generating a target hot video corresponding to the video identifier based on the video identifier of the intermediate hot video from the corresponding game, to obtain a new hot video.

[0006] In an optional embodiment of the present disclosure, obtaining an initial hot video, and performing video content analysis on the initial hot video to obtain a plurality of hot spot dimension information, comprises: determining a statistical hot video according to a big data platform, performing video content analysis on the statistical hot video to obtain a plurality of first hot spot dimension information; determining hot spot dimension information with a matching degree greater than a preset matching degree as second hot spot dimension information, and determining a similar hot video corresponding to the second hot spot dimension information; based on the first hot spot dimension information and the second hot spot dimension information, obtaining a plurality of hot spot dimension information corresponding to the video content of the statistical hot video and the similar hot video that constitute the initial hot video.

[0007] In an optional embodiment of the present disclosure, the hot video whose hot sum of at least one same hot spot dimension information in the initial hot video is greater than a preset hot value is fused to obtain an intermediate hot video, including: determining a plurality of first hot videos corresponding to the current hot of each hot spot dimension information being greater than a preset hot value, and determining a plurality of second hot videos corresponding to the hot rising speed of each hot spot dimension information being greater than a preset rising speed; for each first hot video, determining a second target hot video from the plurality of second hot videos, which has at least one same hot spot dimension information as the first hot video and whose hot sum of the same hot spot dimension information is greater than the preset hot value; and fusing the first hot video and the second target hot video to obtain the intermediate hot video.

[0008] In an optional embodiment of the present disclosure, the target hot video corresponding to the video identifier is generated from the corresponding game based on the video identifier of the intermediate hot video to obtain a new hot video, including: detecting the game scene of the game to obtain the game scene identifier of the game; and taking the game scene identifier of the game scene in the game which has a similarity greater than a preset similarity with the video identifier of the intermediate hot video as the target hot video to obtain the new hot video.

[0009] In an optional embodiment of the present disclosure, the game scene identifier of the game scene in the game which has a similarity greater than or equal to a preset similarity with the video identifier of the intermediate hot video is taken as the target hot video to obtain a new hot video, including: taking the game scene identifier of the intermediate hot video which has a similarity greater than a preset similarity as an initial target video; and performing clipping processing on the video area containing the game scene in the initial target video to obtain the target hot video.

[0010] In an optional embodiment of the present disclosure, after obtaining the new hot video, it further includes: performing clipping processing on the target hot video based on the pre-acquired clipping rule information.

[0011] In an optional embodiment of the present disclosure, the target hot video generated within a preset time length is fused with the target hot video generated greater than the preset time length to obtain a synthesized hot video; and the synthesized hot video is clipped based on the pre-acquired clipping rule information.

[0012] In a second aspect, an embodiment of the present disclosure provides a hot video generation device, which includes: a content analysis module configured to acquire an initial hot video, and perform video content analysis on the initial hot video to obtain a plurality of hot spot dimension information; a video fusion module configured to fuse a hot video whose hot sum of at least one same hot spot dimension information in the initial hot video is greater than a preset hot value to obtain an intermediate hot video; and a video generation module configured to acquire a target hot video corresponding to a video identifier from a corresponding game based on the video identifier of the intermediate hot video to obtain a new hot video.

[0013] In an optional embodiment of the present disclosure, the content analysis module is configured to determine a statistical hot video according to the big data platform, perform video content analysis on the statistical hot video to obtain a plurality of first hot dimension information, determine hot dimension information with a matching degree greater than a preset matching degree as second hot dimension information, and determine a similar hot video corresponding to the second hot dimension information; and obtain a plurality of hot dimension information corresponding to the video content of the initial hot video composed of the statistical hot video and the similar hot video based on the first hot dimension information and the second hot dimension information.

[0014] In an optional embodiment of the present disclosure, the video fusion module is configured to determine a plurality of first hot videos with a current hot degree greater than a preset hot degree value in each hot dimension information, and determine a plurality of second hot videos with a hot degree rising speed greater than a preset rising speed in each hot dimension information; for each first hot video, determine a second target hot video with at least one same hot dimension information as the first hot video from the plurality of second hot videos, and a hot degree sum of the same hot dimension information greater than the preset hot degree value; and perform fusion processing on the first hot video and the second target hot video to obtain an intermediate hot video.

[0015] In an optional embodiment of the present disclosure, the video generation module is configured to detect a game scene of the game to obtain a game scene identifier of the game, and determine a game scene identifier with a similarity greater than a preset similarity to a video identifier of the intermediate hot video as a target hot video to obtain a new hot video.

[0016] In an optional embodiment of the present disclosure, the video generation module is configured to determine a game scene identifier with a similarity greater than a preset similarity to a video identifier of the intermediate hot video as an initial target video, and perform clipping processing on a video region containing the game scene in the initial target video to obtain a target hot video.

[0017] In an optional embodiment of the present disclosure, the video clipping module is configured to perform clipping processing on the target hot video based on pre-acquired clipping rule information.

[0018] In an optional embodiment of the present disclosure, the video fusion module is configured to perform fusion processing on a target hot video generated within a preset time length and a target hot video generated greater than the preset time length to obtain a synthetic hot video, and the video clipping module is configured to perform clipping processing on the synthetic hot video based on pre-acquired clipping rule information.

[0019] In a third aspect, an embodiment of the present disclosure provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the hot video generation method as above.

[0020] In a fourth aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the heat video generation method as above via execution of the executable instructions.

[0021] The technical solution of the present disclosure has the following beneficial effects:

[0022] The heat video generation method described above obtains an initial heat video, analyzes the initial heat video with high current heat to obtain multiple hot spot dimension information of interest to users, thereby fusing the hot spot dimension information corresponding to the heat video whose heat sum in the existing initial heat video exceeds a preset heat value, to obtain an intermediate heat video, so as to generate a new heat video corresponding to the video identifier of the intermediate heat video from the corresponding game. This method fuses different initial heat videos with the same hot spot dimension information and the heat value of the hot spot dimension information being higher than the preset heat value, to determine the game hot spot dimension with high user attention, thereby generating different heat videos according to the determined different hot spot dimension information, greatly enriching the video content of the generated heat video. At the same time, this method can quickly generate a large number of new heat videos in the process of the hot spot rising, thereby continuously promoting the heat rising. This method solves the technical problem of some technical solutions that the number of videos is small and the video content is poor for the newly emerging hot spot in a short period of time or the newly online game, and achieves the technical effect of improving the number of heat videos and the richness of video content.

[0023] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0025] Figure 1 The system architecture diagram of a heat video generation system in the present exemplary embodiment is schematically shown;

[0026] Figure 2 The flowchart of a heat video generation method in the present exemplary embodiment is schematically shown;

[0027] Figure 3 The flowchart of a method for obtaining an intermediate heat video in the present exemplary embodiment is schematically shown;

[0028] Figure 4 a flow chart illustrating another method of generating a heat video in the present exemplary embodiment;

[0029] Figure 5 a structural diagram of a heat video generation apparatus in the present exemplary embodiment;

[0030] Figure 6 a structural diagram of another heat video generation apparatus in the present exemplary embodiment;

[0031] Figure 7 a structural diagram of an electronic device in the present exemplary embodiment. DETAILED DESCRIPTION

[0032] Exemplary embodiments now will be described more fully hereinafter with reference to the accompanying drawings; however, this exemplary embodiment can be implemented in any number of ways, and is not limited to the examples described herein. In the drawings, the size, the relative sizes, and / or the shapes of layers, regions, and / or structures can be exaggerated for clarity. It should be understood that the embodiments described and shown herein are not meant to be limiting, and that a variety of changes and modifications can be made thereto without departing from the spirit and scope of the disclosure. Also, in the present disclosure, like reference numerals in the drawings indicate corresponding parts throughout the several embodiments.

[0033] Furthermore, the drawings s are only schematic and not necessarily to scale. Identical or similar elements are denoted by the same reference numerals throughout the description. Like reference numerals in the drawings and description specify identical or similar elements. Thus, the description will not be repeated for these identical or similar elements. Some of the blocks in the flowchart diagrams are functional blocks that can be implemented by software, hardware, or a combination of software and hardware. These functional blocks can be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0034] The flowchart diagrams shown in the drawings are merely illustrative and do not necessarily include all the steps. For example, some steps can be further divided, and some steps can be combined or partially combined, so that the actual execution order can be changed according to the actual situation.

[0035] The heat video generation method provided by the exemplary embodiments of the present disclosure can be applied to application scenarios that require generation of heat videos, and in particular to application scenarios that generate heat videos for newly emerging hotspots. For example, a newly launched online game has attracted a large number of users' attention in terms of game scenes, game content, level information, skill special effects, etc. Users repeatedly watch videos of the online game, which leads to an increase in the video heat of the game.

[0036] For a newly emerging hotspot or a newly launched online game, a video processing personnel needs to spend time searching for material content related to the hotspot or the online game. Therefore, it is difficult to generate a large number of heat videos in a short time, which leads to only a small number of videos for the hotspot in current video software, and the video content is poor, which limits the continuous rise of the heat of the hotspot or the game. At the same time, the small number of heat videos and the poor video content lead users to repeatedly view the same video content and fail to obtain new content information, which affects the user experience.

[0037] The exemplary embodiments of the present disclosure consider the above problems and propose a heat video generation method. For a newly emerging hotspot or a newly launched online game, the method obtains an initial heat video according to user access volume analysis, and performs video content analysis on the initial heat video to obtain a hotspot dimension corresponding to the video content. For example, for a newly launched online game, the hotspot dimension can be a game scene, a skill special effect, a level play, or the like that is interesting to users. Then, at least one heat video with a heat greater than a preset heat value for the same hotspot dimension is fused. Finally, a target heat video corresponding to a target video identifier of the heat video obtained by the fusion is obtained from a corresponding game according to the target video identifier, thereby obtaining a new heat video.

[0038] The heat video generation method can fuse a plurality of existing heat videos to determine a video identifier that is interesting to users for a newly emerging hotspot or a newly launched popular online game, thereby quickly generating a corresponding video clip from a corresponding game according to the video identifier. The method can quickly generate a corresponding heat video according to a video identifier that is interesting to users, thereby avoiding the technical problem of a small number of related heat videos when a hotspot emerges. At the same time, for the technical problem of poor video content, the method generates different video content for different video identifiers that are interesting to users, thereby enriching the video content of the heat video, and further promoting the continuous rise of the heat of the heat video and improving the user experience.

[0039] Figure 1 A system architecture diagram of a heat video generation system provided by the exemplary embodiments of the present disclosure is shown in FIG. 1. As shown in FIG. 1, the system architecture diagram includes a user terminal 100, a video server 200, and a game server 300. Figure 1As shown, the hot video generation system 100 includes a plurality of user terminals 101 and a server 102. In the above example running scenario, the plurality of user terminals 101 can be, for example, personal computers, servers, personal digital assistants (PDAs), notebooks, or any other computing devices with networking capabilities.

[0040] It should be noted that the server 102 can be one server, or a server cluster composed of a plurality of servers.

[0041] The server 102 can obtain an initial hot video, and parse the video content of the initial hot video to obtain a plurality of hot spot dimension information.

[0042] Then, the server 102 fuses the hot videos in which the sum of the hotness of at least one same hot spot dimension information in the initial hot video is greater than a preset hotness value to obtain an intermediate hot video. Finally, the server 102 generates a target hot video corresponding to the video identifier based on the video identifier of the intermediate hot video from the corresponding game, to obtain a new hot video. The server 102 pushes the generated new hot video to the plurality of user terminals 101, so that the user can watch the generated hot video through the user terminal 101.

[0043] Among them, the hot video is a video in which the user attention or access amount is greater than a preset attention amount or a preset access amount within a preset time period.

[0044] It should be understood that, in the above description, Figure 1 As shown in the system architecture, the number of user terminals 101 and servers 102 is only exemplary, and more or less is within the protection scope of the present application. The communication mode between the user terminals 101 and the servers 102 can include various types of wired and wireless networks.

[0045] The execution subject of the hot video generation method provided by the example embodiment of the present disclosure can be the user terminal 101. In the following, the hot video generation method is applied to the user terminal 101 as an example.

[0046] Referring to Figure 2 , Figure 2 The flowchart of a hot video generation method in the example embodiment is schematically shown. The hot video generation method provided by the example embodiment of the present disclosure can include the following steps S201-S203:

[0047] Step S201, obtaining an initial hot video, and parsing the video content of the initial hot video to obtain a plurality of hot spot dimension information.

[0048] The initial hot video is a current high hot video. The video dimension information contained in the initial hot video is diverse. Taking a game hot video as an example, the video dimension information can be game scene, skill special effect, level gameplay, character skill, character modeling and the like of the initial hot video. Meanwhile, the video dimension information can also be feature information of the initial hot video, such as video recording features, video editing methods, video types and the like.

[0049] The hot spot dimension information is the video dimension information of the initial hot video that is of interest to users or has a large access volume.

[0050] It should be understood that, for a hot spot dimension information with a larger generalization range (for example, video type), in order to make the hot spot dimension information have practical significance, the hot spot dimension information can be further disassembled to obtain a hot spot dimension information with a smaller range. For example, for a game type video, the disassembled hot spot dimension information can be scene information and level information of game A.

[0051] For example, when the initial hot video is obtained, the hot video ranking determined based on big data can be used to determine the hot video classification in priority, and then the initial hot video under each hot video classification is obtained. The hot video classification is obtained in priority, which facilitates the analysis of the hot spot dimension of the hot video, so as to quickly determine the video type that is more interesting to users at the current time.

[0052] In step S202, the hot videos with a hot spot dimension information sum greater than a preset hot value are fused to obtain an intermediate hot video.

[0053] Each initial hot video contains multiple hot spot dimension information, and the hot spot dimension information contained in each initial hot video can be different or the same. For example, the hot spot dimension information contained in game video A is game scene and skill special effect, and the hot spot dimension information contained in game video B is character modeling and skill special effect, and the same hot spot dimension information of game A and game B is skill special effect.

[0054] For example, when the hot videos are fused to obtain the intermediate hot video, multiple initial hot videos that can be fused are selected in priority.

[0055] When the initial hot videos that can be fused are selected, the hot spot dimension information of each initial hot video can be determined, and the similarity of the hot spot dimension information between the initial hot videos is compared to determine the hot videos with the same hot spot dimension information for fusion processing.

[0056] For example, the initial hotness video A and the initial hotness video B are the second level and the third level of a newly online network game respectively, and the same hot spot dimension information of the initial hotness video A and the initial hotness video B is character modeling and skill special effect. Then, the hotness weight of the character modeling in the initial hotness video A and the initial hotness video B is determined respectively, and the total hotness of the character modeling is calculated, and the hotness weight of the skill special effect in the initial hotness video A and the initial hotness video B is determined respectively, and the total hotness of the skill special effect is calculated, and compared with the preset hotness value of the character modeling and the preset hotness value of the skill special effect respectively.

[0057] It should be understood that the initial hotness video for fusion processing can be two or more, and the number of the initial hotness video for fusion processing is not limited in the present disclosure, and all belong to the protection scope of the present disclosure. The preset hotness value set for each hot spot dimension information can be a fixed value set in advance, or a dynamically changing value calculated in real time according to the hotness data, and can be set according to actual conditions.

[0058] In step S203, the target hotness video corresponding to the video identification is obtained from the corresponding game based on the video identification of the intermediate hotness video, and a new hotness video is obtained.

[0059] The video identification can be scene information of the video, that is, the video range for generating the target hotness video is determined from the game scene of the corresponding game according to the game scene of the intermediate hotness video, and the video range includes the video starting point and the video ending point, so as to obtain the new hotness video. For example, the intermediate hotness video is the second level and the third level of game A, and the video containing the second level and the third level of game A is determined as the new hotness video according to the scene information.

[0060] The video identification can also be the hot spot dimension information with the maximum hotness sum in the intermediate hotness video. For example, the hot spot dimension information with the maximum hotness sum is skill special effect, and the new hotness video is generated based on the position containing the above skill special effect in the game.

[0061] In the technical solution provided by some embodiments of the present disclosure, by obtaining an initial hot video, a plurality of hot dimension information of interest to users is obtained by analyzing the current high initial hot video, so that the hot dimension information corresponding to the hot video whose hot sum in the existing initial hot video exceeds a preset hot value is fused to obtain an intermediate hot video, so as to generate a new hot video corresponding to the video identifier of the intermediate hot video from the corresponding game. This method fuses different initial hot videos with the same hot dimension information and the hot value of the hot dimension information higher than the preset hot value, so as to determine the game hot dimension with high user attention, and generate different hot videos according to the determined different hot dimension information, thereby greatly enriching the video content of the generated hot video. At the same time, this method can quickly generate a large number of new hot videos in the process of hot rising, thereby continuously promoting the hot rising. This method solves the technical problem of some technical solutions for short-term newly emerging hot spots or newly online games with less video content, and achieves the technical effect of improving the quantity and richness of the hot video.

[0062] In the exemplary embodiments of the present disclosure, when obtaining an initial hot video, a plurality of hot dimension information is obtained by video content analysis of the initial hot video. According to the big data platform, a statistical hot video is determined, a plurality of first hot dimension information is obtained by video content analysis of the statistical hot video, a hot dimension information with a matching degree greater than a preset matching degree is determined as a second hot dimension information, and a similar hot video corresponding to the second hot dimension information is determined. Based on the first hot dimension information and the second hot dimension information, a plurality of hot dimension information corresponding to the video content of the statistical hot video and the similar hot video forming the initial hot video is obtained.

[0063] Among them, the statistical hot video is a hot video obtained based on the hot video ranking information of the big data platform; and the matching degree between the second hot dimension information and the first hot dimension information is greater than the preset matching degree. Assuming that the first hot dimension information is the game play information of game A, the second hot dimension information can be the similar game play information in game B to the above game play information. For example, the second hot dimension information and the first hot dimension information are both game play of the running and changing track to collect gold coins and avoid obstacles.

[0064] Among them, the hot dimension information is obtained by determining the first hot dimension information corresponding to the statistical hot video and the second hot dimension information of the same type based on big data statistics. And the initial hot video is the hot video corresponding to the hot dimension information, that is, the hot video set composed of at least the statistical hot video and the similar hot video.

[0065] Exemplarily, after determining the statistical hot videos based on the big data statistics, the video content of the statistical hot videos can be parsed to obtain a plurality of different first hot dimension information. Meanwhile, hot dimension information with a matching degree greater than a preset matching degree, i.e., second hot dimension information of the same type, can be determined to obtain similar hot videos corresponding to the second hot dimension information, so as to obtain initial hot videos and hot dimension information.

[0066] The first hot dimension information of the statistical hot videos is determined by big data, and the second hot dimension information similar to the first hot dimension information is determined to obtain the hot dimension information and the initial hot videos. This process can obtain hot videos of interest to users, and also obtain videos of the same type to achieve the technical effect of enriching the video content of hot videos.

[0067] Referring to Figure 3 In an optional embodiment of the present disclosure, the step S202 of fusing the hot videos with a total hot degree of at least one same hot dimension information greater than a preset hot degree to obtain the intermediate hot videos can include the following steps S301-S304:

[0068] Step S301, determining a plurality of first hot videos with a current hot degree greater than a preset hot degree in each hot dimension information.

[0069] Step S302, determining a plurality of second hot videos with a hot degree rising speed greater than a preset rising speed in each hot dimension information.

[0070] Step S303, for each first hot video, determining a second target hot video with at least one same hot dimension information as the first hot video and a total hot degree of the same hot dimension information greater than a preset hot degree from the plurality of second hot videos.

[0071] Exemplarily, if the total hot degree of the same hot dimension information is less than the preset hot degree, it indicates that the user attention of the hot dimension information is small.

[0072] Step S304, fusing the first hot video and the second target hot video to obtain the intermediate hot videos.

[0073] By matching the first hot video with a current hot degree greater than a preset hot degree and the second target hot video with a hot degree rising speed greater than a preset rising speed, the current hot video can be matched with the predicted hot video, so as to quickly generate a large number of hot videos at the initial stage of the hot video outbreak or the hot video outbreak, and improve the video content richness of the hot videos.

[0074] In the exemplary embodiments of the present disclosure, when the target hotness video corresponding to the video identification is obtained from the corresponding game based on the intermediate hotness video, the game scene of the game can be detected to obtain the game scene identification of the game; the game scene identification of the game scene in the game that is similar to the video scene identification of the intermediate hotness video by more than a preset similarity is taken as the target hotness video to obtain the new hotness video.

[0075] The game scene identification is the scene information of the game, such as a game background picture, a game character picture, a skill special effect picture, and the like.

[0076] For example, when the target hotness video corresponding to the video identification is obtained, the scene information of the current game can be detected in real time to obtain the game scene identification of the game. If the similarity between the video identification of the intermediate hotness video and the obtained game scene identification exceeds a preset similarity, it can be determined that the game scene is the same as the scene of the intermediate hotness video, so that the same game scene in the game process is taken as the target hotness video. For example, the intermediate hotness video is the second level of game A, and the game process of game A is detected in real time. When the game process of game A reaches the second level, the target hotness video corresponding to the second level game scene is generated.

[0077] It should be understood that the preset similarity can be pre-set or dynamically adjusted in real time, which is determined according to the actual situation.

[0078] By comparing the similarity between the game scene identification of the game and the video identification of the intermediate hotness video, the video range of the target hotness video generated based on the current game process is determined. This method can accurately generate a large number of new hotness videos corresponding to the video identification, and generate different video contents for different hot spot dimension information, thereby enriching the video content of the hotness video.

[0079] According to some embodiments of the present disclosure, when the target hotness video corresponding to the video identification is obtained from the game, the game video can be recorded when the game process is detected to run to the starting position corresponding to the video identification. For example, the intermediate hotness video is the second level and the third level of game A, and the current game process of multiple users starts from the first level. When the user terminal detects that game A runs to the scene information of the second level, the video recording function is triggered to start; when the third level of game A is detected to run to the game scene of the fourth level, the video recording function is triggered to stop, thereby obtaining the target hotness video under the game of each user. This process only needs to record the video segment that the user is interested in, thereby reducing the resource consumption of the system.

[0080] According to another embodiment of the present disclosure, when the target hotness video corresponding to the video identifier is acquired, the entire game process in which the plurality of users play the game can be preferentially recorded, and a video segment corresponding to the video identifier in the entire game video can be extracted as the target hotness video to obtain a new hotness video. The above method can enable the user to crop the same video segment multiple times, thereby improving the utilization rate of video resources.

[0081] In an exemplary embodiment of the present disclosure, when the game scene identifier with a similarity greater than a preset similarity to the video identifier of the intermediate hotness video is taken as the target hotness video, the game scene identifier with a similarity greater than the preset similarity to the video identifier of the intermediate hotness video is taken as the initial target video; and the video region containing the game scene in the initial target video is cropped to obtain the target hotness video.

[0082] For example, when the initial target video generated by the game scene identifier with a similarity greater than a preset similarity in the game process is acquired, video content unrelated to the game scene identifier is usually introduced, and therefore the video region corresponding to the unrelated video content needs to be cropped.

[0083] For example, when the user starts the game using the mobile terminal device, the mobile terminal also runs other application programs (such as chat software, video software, etc.) at the same time. These application programs can push notification messages to the user. For example, when the chat software receives a chat message sent by a friend, the player in the game is sent a notification message which is displayed in the graphical interface of the mobile terminal. In order to protect the privacy information of the user and improve the video quality of the hotness video, the video region in which the notification message appears is cropped when the video is recorded. Or some games do not expand the entire graphical interface of the mobile terminal during the running process, and therefore the video region not covered by the game scene identifier can be cropped.

[0084] After the initial target video is obtained, the video region containing the game scene in the initial target video is cropped, which can improve the video quality of the generated hotness video.

[0085] After the target hotness video is acquired, the target hotness video only contains video content about the hotness video, and cannot highlight the key points in the target hotness video, which is not suitable for the user to watch. In order to improve the aesthetics, video quality and video effect of the target video, the target hotness video can also be edited.

[0086] In an exemplary embodiment of the present disclosure, after the new hotness video is obtained, the target hotness video is edited based on the pre-acquired editing rule information.

[0087] The clip rule information can be a video clip method, for example, adding slow motion video frames, adding a flashing mark to a skill special effect, adding a video sound effect, shortening the video length occupied by the same video scene, etc.

[0088] For example, a hot video set can be constructed in advance, i.e., the current multiple hot videos are taken as a sample video set; then the clip rule information of the main stream of each hot video in the hot video set is disassembled to clip some video clips in the target hot video based on the clip rule information. When the clip rule information is obtained through the sample video set, the clip rule information can be obtained through a pre-trained neural network model, or the clip rule information commonly used for a certain video clip can be obtained according to big data analysis.

[0089] For example, through big data analysis, a large number of users will play the process of sending a skill special effect in slow motion at the moment when the character successfully kills the enemy character by launching a skill, so as to analyze the timing of the character sending the skill and watch the exciting moment of the character launching the skill to kill the enemy character. Or add sound effects when the player controls the game character to pick up virtual props to enrich the video content, etc.

[0090] Through the pre-obtained clip rule information, the target hot video is clipped and processed, which can improve the video quality and video effect of the generated hot video, and further enrich the video content of the hot video.

[0091] Further, in addition to the above generation of new hot videos, the video content of the generated hot video can be further enriched based on the target video obtained at the current time and the target hot video obtained at the historical time.

[0092] According to some embodiments of the present disclosure, the target hot video generated within a preset time length is fused with the target hot video generated in more than the preset time length to obtain a synthesized hot video; and the synthesized hot video is clipped based on the pre-obtained clip rule information.

[0093] The preset time length is a preset time period from the current time.

[0094] Exemplarily, the target heat video generated within the preset time period from the current time is fused with the target heat video generated beyond the preset time period from the current time. When the fusion is performed, similar to the method of fusing the plurality of initial heat videos, when the target heat video generated within the preset time period is fused with the target heat video generated beyond the preset time period, if the heat sum of at least one same hot spot dimension information is greater than the preset heat value, the target heat video generated within the preset time period is fused with the target heat video generated beyond the preset time period to obtain a synthesized heat video; otherwise, the fusion cannot be performed. After the synthesized heat video is obtained, the pre-acquired clip rule information is used for clip processing.

[0095] By fusing the target heat video generated within the preset time period with the target heat video generated beyond the preset time period, the corresponding target heat video does not need to be generated from the corresponding game again, and only the video content of the heat video needs to be re-fused and clipped, so that the video content of the heat video is enriched, and the efficiency of generating a new heat video is improved.

[0096] The entire generation process of the heat video generation method of the exemplary embodiment of the present disclosure will be described below with reference to the accompanying drawings. Figure 4 The entire generation process of the heat video generation method of the exemplary embodiment of the present disclosure will be described below with reference to the accompanying drawings.

[0097] First, in step S401, a statistical heat video is acquired.

[0098] Exemplarily, the popular video classification can be determined based on the heat video ranking information generated by big data to obtain the statistical heat video. The statistical heat video is a heat video set.

[0099] After the initial heat video is acquired, step S402 is performed to analyze the content of the statistical heat video to obtain a plurality of first hot spot dimension information. That is, the video content of the statistical heat video is analyzed to obtain a plurality of first hot spot dimension information corresponding to the video content.

[0100] In step S403, second hot spot dimension information and similar heat videos corresponding to the second hot spot dimension information are determined.

[0101] Exemplarily, the second hot spot dimension information is the hot spot dimension information with a matching degree greater than a preset matching degree with the first hot spot dimension information, and the heat video corresponding to the second hot spot dimension information is a similar heat video.

[0102] In step S404, the initial heat video and the hot spot dimension information are acquired.

[0103] The similar hotness video and the statistical hotness video constitute an initial hotness video, and the first hotness dimension information corresponding to the similar hotness video and the second hotness dimension information corresponding to the statistical hotness video constitute hotness dimension information of the initial hotness video.

[0104] Secondly, in step S405, hotness dimension information corresponding to a first hotness video is determined, where the current hotness is greater than a preset hotness, and hotness dimension information corresponding to a second hotness video is determined, where the hotness rising speed is greater than a preset rising speed.

[0105] Generally, the hotness video corresponding to the hotness dimension information where the current hotness is greater than the preset hotness is a video set, i.e., multiple first hotness videos, and the hotness video corresponding to the hotness dimension information where the hotness rising speed is greater than the preset rising speed is also a video set, i.e., multiple second hotness videos.

[0106] For each first hotness video, step S406 can be performed to determine a second target hotness video matching the first hotness video from the multiple second hotness videos.

[0107] Based on the second target hotness video, in step S407, an intermediate hotness video is obtained. That is, the first hotness video and the second target hotness video obtained by matching are fused to obtain the intermediate hotness video.

[0108] Next, in step S408, a target hotness video is generated.

[0109] In an exemplary embodiment of the present disclosure, the target video corresponding to the video identification of the intermediate hotness video can be generated from the corresponding game. For example, the target video can be generated according to the similarity between the video identification of the intermediate hotness video and the game scene identification of the game.

[0110] For example, if the similarity between the video identification of the intermediate hotness video and the game scene identification of the game is greater than or equal to a preset similarity, the video recording operation can be started; if the similarity between the video identification of the intermediate hotness video and the game scene identification of the game switches to less than the preset similarity, the video recording operation is stopped.

[0111] Finally, in step S409, the target hotness video is edited.

[0112] In an exemplary embodiment of the present disclosure, the editing process can also be performed while recording the target video. That is, only the video region containing the game scene in the recorded initial target video is cut out, and the video region irrelevant to the game scene is discarded.

[0113] In the exemplary embodiments of the present disclosure, the target video is processed based on the pre-acquired clip rule information. For example, slow motion effect is added, repeated video segments are clipped, and the like, to improve the content richness of the generated new hot video.

[0114] To implement the above-mentioned hot video generation method, one embodiment of the present disclosure provides a hot video generation device. Figure 5 A schematic architecture diagram of the hot video generation device is shown.

[0115] The hot video generation device 500 includes a content analysis module 501, a video fusion module 502, and a video generation module 503.

[0116] The content analysis module 501 is configured to acquire an initial hot video, and perform video content analysis on the initial hot video to obtain a plurality of hot spot dimension information. The video fusion module 502 is configured to fuse at least one hot video in the initial hot video, which has a same hot spot dimension information and a total hotness greater than a preset hotness value, to obtain an intermediate hot video. The video generation module 503 is configured to acquire a target hot video corresponding to the video identification from the corresponding game based on the video identification of the intermediate hot video, and obtain a new hot video.

[0117] The hot video generation device 500 provided by the embodiments of the present disclosure can implement the technical solutions of the hot video generation method in any of the above-mentioned embodiments, and has similar implementation principles and beneficial effects to the hot video generation method. For details, refer to the implementation principles and beneficial effects of the hot video generation method, which will not be described here.

[0118] Further, to implement the above-mentioned hot video generation method, one embodiment of the present disclosure provides a hot video generation device. Figure 6 A schematic architecture diagram of the hot video generation device is shown.

[0119] The hot video generation device 600 includes a content analysis module 601, a video fusion module 602, a video generation module 603, and a video clip module 604.

[0120] In an optional embodiment, the content analysis module 601 is configured to determine a statistical hot video according to a big data platform, perform video content analysis on the statistical hot video to obtain a plurality of first hot spot dimension information, determine a hot spot dimension information having a matching degree greater than a preset matching degree as a second hot spot dimension information, and determine a similar hot video corresponding to the second hot spot dimension information. Based on the first hot spot dimension information and the second hot spot dimension information, a plurality of hot spot dimension information corresponding to the video content of the statistical hot video and the similar hot video forming an initial hot video is obtained.

[0121] In an optional embodiment, the video fusion module 602 is configured to determine a plurality of first hot videos corresponding to a preset hotness value, and determine a plurality of second hot videos corresponding to a preset rising speed, from the hotness dimension information; for each first hot video, determine a second target hot video from the plurality of second hot videos, which has at least one same hotness dimension information as the first hot video, and the sum of the hotness of the same hotness dimension information is greater than the preset hotness value; and fuse the first hot video and the second target hot video to obtain an intermediate hot video.

[0122] In an optional embodiment, the video generation module 603 is configured to detect a game scene of the game to obtain a game scene identifier of the game; and determine a target hot video from a game scene identifier having a similarity greater than a preset similarity to a video identifier of the intermediate hot video, to obtain a new hot video.

[0123] In an optional embodiment, the video generation module 603 is configured to determine a game scene identifier having a similarity greater than a preset similarity to a video identifier of the intermediate hot video as an initial target video; and crop a video region containing a game scene in the initial target video to obtain a target hot video.

[0124] In an optional embodiment, the video clip module 604 is configured to clip the target hot video based on pre-acquired clip rule information.

[0125] In an optional embodiment, the video fusion module 602 is configured to fuse a target hot video generated within a preset time length with a target hot video generated greater than the preset time length, to obtain a synthesized hot video; and the video clip module is configured to clip the synthesized hot video based on pre-acquired clip rule information.

[0126] The hot video generation apparatus 600 provided by the example embodiments of the present disclosure can execute the technical solutions of the hot video generation method in any of the above embodiments, and the implementation principles and beneficial effects thereof are similar to those of the hot video generation method. For details, refer to the implementation principles and beneficial effects of the hot video generation method, which will not be described herein again.

[0127] In the example embodiments of the present disclosure, a computer readable storage medium having a program product stored thereon is also provided, which can implement the above-mentioned method of the present disclosure. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program code for causing a user terminal to execute the steps described in the above-mentioned “example method” section according to various example embodiments of the present disclosure when the program product is run on the user terminal.

[0128] A program product for implementing the above-described method according to the embodiments of the present application can take a portable compact disc read only memory (CD-ROM) and include a program code, and can be executed on a user terminal such as a personal computer. However, the program product of the present application is not limited thereto, and in the present document, a readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0129] The program product can take any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium, for example, can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0130] The computer readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave, in which the readable program code is embodied. Such propagated data signal can take multiple forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable signal medium can also be any readable medium that is not a readable storage medium and that can transmit, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.

[0131] The program code contained on the readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, and the like, or any suitable combination of the above.

[0132] The program code might be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0133] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above-described method is also provided.

[0134] Those skilled in the art can understand that each aspect of the present disclosure can be implemented as a system, a method or a program product. Therefore, each aspect of the present disclosure can be specifically implemented as a whole hardware embodiment, a whole software embodiment (including firmware, microcode, etc.), or an embodiment combining software and hardware aspects, which can be collectively referred to as "circuitry", "module" or "system".

[0135] The electronic device 700 according to this embodiment of the present disclosure will be described below with reference to Figure 7 Figure 7 The electronic device 700 shown is merely an example and should not limit the functions and usage range of the embodiments of the present disclosure.

[0136] As shown in Figure 7 The electronic device 700 is in the form of a general computing device. The components of the electronic device 700 can include, but are not limited to, the at least one processing unit 710 described above, the at least one storage unit 720 described above, a bus 730 connecting different system components, including the storage unit 720 and the processing unit 710, and a display unit 740.

[0137] The storage unit stores program code that can be executed by the processing unit 710, so that the processing unit 710 performs the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Method" section of the present specification. For example, the processing unit 710 can perform steps S201 to S203 as shown in Figure 2

[0138] ​​The storage unit 720 can include a readable medium in the form of volatile storage such as random access memory (RAM) 7201 and / or cache memory 7202, and also can include a non-volatile storage such as read only memory (ROM) 7203.

[0139] The storage unit 720 also can include a program / utility 7204 having a set of program modules 7205 such as an operating system, one or more application programs, other program modules, and program data, each of which can give the electronic device 700 its functionality, at least in part. The program modules 7205 can include, but are not limited to, a network environment implementation, either alone or in some combination.

[0140] The bus 730 can represent one or more of several types of bus structures, including a storage bus or bus controller, a peripheral bus, an accelerated graphics port, an electronic device 700, or a local bus using any of a variety of bus architectures.

[0141] The electronic device 700 also can communicate with one or more external devices 800 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices such as printers, scanners, monitors, etc.; and / or various devices to enable a user to interact with the electronic device 700 in various ways (e.g., a digital camera, a digital video camera, a sound card, video card, etc.). Such interaction can occur through input / output (I / O) interface(s) 750. Still yet, the electronic device 700 can communicate with one or more networks, such as one or more local area networks (LANs), one or more wide area networks (WANs) and / or the Internet, through a network adapter 760. As depicted, the network adapter 760 communicates with the other components of the electronic device 700 through the bus 730. It should be appreciated that the network adapter 760 and / or the other hardware and / or software components depicted in FIG. 7 can be implemented with various hardware and / or software components, including but not limited to a microcode, a device driver, redundant processing unit, external disk drive array, RAID system, tape drive, and data backup storage system, etc.

[0142] From the above description of the embodiments, those skilled in the art will readily perceive that the example embodiments described herein can be implemented by software and / or by software in combination with the requisite hardware. Thus, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to make a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) execute the methods according to the embodiments of the present disclosure.

[0143] Moreover, the above-described figures are only a schematic representation of the processes comprised in the method according to the exemplary embodiments of the application, and are not intended to limit purposes. It is readily understood that the processes shown in the above-described figures do not indicate or limit the chronological order of these processes. In addition, it is readily understood that these processes can be executed, for example, in a synchronous or asynchronous manner in a plurality of modules.

[0144] It should be noted that, although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, according to embodiments of the present disclosure, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided to be embodied by a plurality of modules or units.

[0145] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the description herein, the drawings, and the appended claims. The application is intended to cover any adaptations or variations of the present disclosure followed in the general principles of the present disclosure and including such modifications as would be readily apparent to those reasonably skilled in the art for example, with the scope of the present disclosure not to be limited to the exact details shown and described. The application is therefore to be considered as limited only by the scope of the claims, appropriately interpreted in light of the description, and the embodiments.

[0146] It is to be understood that the present disclosure is not limited to the precise construction described and shown in the above description and the accompanying drawings, and that changes and modifications can be effected therein by those skilled in the art without departing from the scope of the disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for generating trending videos, characterized in that, include: The initial trending videos for the game are obtained, and the video content of the initial trending videos is analyzed to obtain multiple trending dimension information. The trending dimension information represents the video feature information dimension and video content dimension of the initial trending videos. The video feature information dimension includes at least one of the following: video recording characteristics, video editing method, and video type. The video content dimension includes at least one of the following: game scene, skill effects, game level gameplay, character skills, and character appearance. The initial trending videos are fused together to obtain intermediate trending videos. The sum of the trending values ​​of at least one of the same trending dimension information in the initial trending videos is greater than a preset trending value. The game scene of the game is detected to obtain the game scene identifier of the game. Based on the game scene identifier in the game with a similarity greater than a preset similarity with the video identifier of the intermediate popular video, the video range of the target popular video corresponding to the game is determined so as to obtain new popular videos according to the video range in the game. The video identifier of the intermediate popularity video is the hotspot dimension information with the highest total popularity among the intermediate popularity videos.

2. The method for generating trending videos according to claim 1, characterized in that, The process involves acquiring initial trending videos for the game, and then parsing the content of these videos to obtain multiple trending dimensions, including: Based on the big data platform, statistically popular videos are determined, and video content analysis is performed on the statistically popular videos to obtain multiple first hot spot dimension information; The hotspot dimension information that matches the first hotspot dimension information with a higher matching degree than a preset matching degree is identified as the second hotspot dimension information, and similar hot videos corresponding to the second hotspot dimension information are identified. Based on the first hotspot dimension information and the second hotspot dimension information, the multiple hotspot dimension information corresponding to the video content that makes up the initial hotspot video, which consists of the statistical hotspot video and the similar hotspot video, is obtained.

3. The method for generating trending videos according to claim 1, characterized in that, The step of fusing videos with a sum of popularity of at least one common hotspot dimension information greater than a preset popularity value in the initial popularity videos to obtain intermediate popularity videos includes: Identify multiple first-hot videos in each of the aforementioned hotspot dimension information whose current popularity is greater than a preset popularity value, and identify multiple second-hot videos in each of the aforementioned hotspot dimension information whose popularity rise rate is greater than a preset rise rate. For each of the first trending videos, a second target trending video is determined from the plurality of second trending videos that has at least one of the same hotspot dimension information as the first trending video, and the sum of the popularity of the same hotspot dimension information is greater than a preset popularity value; The first trending video and the second target trending video are fused together to obtain an intermediate trending video.

4. The method for generating trending videos according to claim 1, characterized in that, The step of using game scene identifiers in the game with a similarity greater than or equal to a preset similarity with the video identifiers of the intermediate popular videos as target popular videos to obtain new popular videos includes: The game scene identifiers whose video identifier similarity to the intermediate popularity videos is greater than the preset similarity are used as the initial target videos; The target popularity video is obtained by cropping the video region containing the game scene in the initial target video.

5. The method for generating trending videos according to claim 1, characterized in that, After obtaining the new trending video, the following is also included: The target popularity video is edited based on the pre-acquired editing rule information.

6. The method for generating trending videos according to claim 1, characterized in that, Also includes: The target popularity video generated within a preset time period is merged with the target popularity video generated beyond the preset time period to obtain a composite popularity video. The synthesized trending video is edited based on pre-acquired editing rule information.

7. A heat video generation device, characterized in that, The device includes: The content analysis module is used to acquire initial trending videos for the game, and to perform video content analysis on the initial trending videos to obtain multiple trending dimension information. The trending dimension information represents the video feature information dimension and video content dimension of the initial trending videos. The video feature information dimension includes at least one of the following: video recording characteristics, video editing method, and video type. The video content dimension includes at least one of the following: game scene, skill effects, game level gameplay, character skills, and character appearance. The video fusion module is used to fuse videos with a total heat value of at least one of the same hotspot dimension information in the initial heat video to obtain an intermediate heat video. The video generation module is used to detect the game scene of the game to obtain the game scene identifier of the game, and determine the video range of the target popularity video corresponding to the game based on the game scene identifier whose similarity with the video identifier of the intermediate popularity video is greater than a preset similarity, so as to obtain a new popularity video according to the video range of the game; The video identifier of the intermediate popularity video is the hotspot dimension information with the highest total popularity among the intermediate popularity videos.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the heat video generation method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the thermal video generation method according to any one of claims 1 to 6 by executing the executable instructions.

Images