Video editing method and device, computer equipment and storage medium

Abstract

The invention relates to a video editing method and device, computer equipment, a storage medium and a computer program product. The embodiment of the invention can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like. The method comprises the following steps: displaying a video clip editing entry for a target video on a video clip viewing interface corresponding to the target video; the video clip viewing interface is used for viewing a published video clip corresponding to the target video; in response to a trigger operation for the video clip editing entry, displaying a clip editing tag set corresponding to the target video; in response to a selection operation for a target clip clip tag in the clip clip tag set, displaying a target video clip obtained by combining the candidate video clips based on the target clip clip tag in a candidate video clip set corresponding to the target video; and in response to a release operation for the target video clip, releasing the target video clip corresponding to the target video. By adopting the method, the video editing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a video editing method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0002] With the development of user demand and media technology, the number of videos has exploded exponentially, and video editing has become a video processing method that people are paying attention to. This video processing method is often used in video editing scenarios such as short video production and video highlights.

[0003] Traditionally, users have to download the video first and then manually perform a series of editing operations on it using specialized editing software. This traditional video editing method requires users to manually select various editing tools within the editing software, which is time-consuming and inefficient. Summary of the Invention

[0004] Based on this, it is necessary to provide a video editing method, device, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of video editing in order to address the above technical problems.

[0005] This application provides a video editing method, including:

[0006] On the video clip viewing interface corresponding to the target video, a video clip editing entry for the target video is displayed; the video clip viewing interface is used to view the published video clips corresponding to the target video;

[0007] In response to a triggering operation on the video clip clip entry, displaying a clip clip tag set corresponding to the target video;

[0008] In response to a selection operation on a target segment clip tag in the segment clip tag set, displaying a target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video;

[0009] In response to a publishing operation on the target video segment, the target video segment corresponding to the target video is published.

[0010] In one embodiment, the video clip viewing interface corresponding to the target video displays a video clip editing entry for the target video, including: in the video clip viewing interface corresponding to the target video, playing the first published video clip corresponding to the target video in full screen, and displaying a video clip editing entry for the target video.

[0011] In one embodiment, the method further includes: in response to a video clip switching operation triggered in the video clip viewing interface, switching from full-screen playback of the first published video clip to full-screen playback of other published video clips in the published video clip set corresponding to the target video.

[0012] In one embodiment, the method further includes: displaying a video clip viewing entrance corresponding to the target video on a video playback interface corresponding to the target video; and switching from the video playback interface to a video clip viewing interface corresponding to the target video in response to a triggering operation on the video clip viewing entrance.

[0013] In one embodiment, the method further includes: displaying a video playback entry corresponding to the target video on the video clip viewing interface; and switching from the video clip viewing interface to the video playback interface in response to a triggering operation on the video playback entry.

[0014] In one embodiment, the method also includes: entering a video application, and displaying a program playback entry corresponding to a target program provided by the video application in the video application; in response to a trigger operation on the program playback entry, triggering the playback of a single episode video corresponding to the target program, using the single episode video as the target video, and using the playback interface of the single episode video as the video playback interface corresponding to the target video.

[0015] In one embodiment, the method further includes: in the video clip viewing interface, playing the third published video clip in the published video clip set corresponding to the target video; in response to a video clip switching operation triggered in the video clip viewing interface, switching from playing the third published video clip to playing the fourth published video clip in the published video clip set; the interactivity corresponding to the third published video clip is greater than the interactivity corresponding to the fourth published video clip.

[0016] In one embodiment, the video clip viewing interface includes a video clip switching area and a video switching area; the switching from playing the third published video clip to playing the fourth published video clip in the published video clip set in response to a video clip switching operation triggered in the video clip viewing interface includes: responding to a sliding operation triggered in the video clip switching area in the video clip viewing interface, following the movement of a sliding key point, displaying in the video clip switching area the third published video clip that gradually exits the screen and the fourth published video clip in the published video clip set that gradually enters the screen; after the fourth published video clip is completely displayed, playing the fourth published video clip;

[0017] The method further includes: displaying a video playback entry corresponding to the target video in the video switching area of the video clip viewing interface; the video playback entry is used to switch from the video clip viewing interface to the video playback interface of the target video.

[0018] In one embodiment, the display of the clip clip tag set corresponding to the target video in response to the trigger operation on the video clip clip entry includes: entering the video clip clip interface corresponding to the target video in response to the trigger operation on the video clip clip entry; the video clip clip interface includes a video clip preview area, a clip clip tag display area, and an editing effect adjustment area; the video clip preview area is used to preview the video clip to be published, and the editing effect adjustment area is used to adjust the editing effect of the video clip based on the selected clip clip tag; in the clip clip tag display area, the clip clip tag set corresponding to the target video is displayed.

[0019] In one embodiment, the method further includes: when the first clip tag in the clip tag set is selected, displaying the candidate video clip set corresponding to the target video in the clip effect adjustment area; the first clip tag is the parent tag of other clip tags in the clip tag set; when any clip tag other than the first clip tag in the clip tag set is selected, displaying the target video clip obtained by combining the candidate video clips from the candidate video clip set based on the selected clip tag in the clip effect adjustment area.

[0020] In one embodiment, the target video segment obtained by combining candidate video segments from the candidate video segment set based on the selected segment editing tags is displayed in the editing effect adjustment area, including: displaying the initial video segment obtained by combining candidate video segments from the candidate video segment set based on the selected segment editing tags according to the initial segment mode in the editing effect adjustment area; in response to an editing operation on the initial video segment, displaying the target video segment obtained after the initial video segment undergoes the editing operation in the editing effect adjustment area; the editing operation includes at least one of a cropping operation, a segment mode switching operation, an editing undo operation, and an editing restoration operation.

[0021] In one embodiment, the method further includes: displaying a start preview control, a clip undo control, and a clip restore control in the video clip preview area; in response to a trigger operation on the start preview control, starting to play the video clip obtained by the current clip in the video clip preview area; in response to a trigger operation on the clip undo control, displaying a video clip obtained by undoing at least one step of the clipping operation on the video clip obtained by the current clip; in response to a trigger operation on the clip restore control, displaying a video clip obtained by canceling at least one step of the clipping operation on the video clip obtained by the current clip.

[0022] In one embodiment, in response to the selection operation of the target segment clip tag in the segment clip tag set, the target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video includes: in response to the selection operation of the target segment clip tag in the segment clip tag set, a supplementary clip tag set matching the target segment clip tag is displayed; in response to the selection operation of the target supplementary clip tag in the supplementary clip tag set, an initial video segment obtained by combining candidate video segments according to the initial segment pattern based on the target segment clip tag and the target supplementary clip tag from the candidate video segment set corresponding to the target video; in response to the clip confirmation operation for the initial video segment, a target video segment obtained based on the initial video segment is displayed.

[0023] In one embodiment, in response to a clip confirmation operation on the initial video segment, displaying a target video segment obtained based on the initial video segment includes: in response to a confirmation operation on the initial video segment, displaying the initial video segment as the target video segment.

[0024] In one embodiment, in response to a clip confirmation operation on the initial video clip, the target video clip obtained based on the initial video clip is displayed, including: displaying a cropping frame for the initial video clip; in response to an adjustment operation on the cropping frame, displaying a first updated video clip obtained by cropping the initial video clip based on the adjusted cropping frame; in response to a confirmation operation on the first updated video clip, displaying the first updated video clip as the target video clip.

[0025] In one embodiment, in response to a clip confirmation operation on the initial video clip, the target video clip obtained based on the initial video clip is displayed, including: displaying the initial clip mode; in response to a clip mode switching operation on the initial clip mode, the target clip mode is displayed, and a second updated video clip obtained by combining candidate video clips from the candidate video clip set according to the target clip mode based on the target clip clip tag and the target supplementary clip tag; in response to a confirmation operation on the second updated video clip, the second updated video clip is displayed as the target video clip.

[0026] In one embodiment, in response to the publishing operation for the target video segment, the target video segment corresponding to the target video is published, including: in response to the confirmation operation for the target video segment, displaying a segment introduction configuration control; in response to the configuration operation for the segment introduction configuration control, displaying the segment introduction information configured for the target video segment through the segment introduction configuration control; in response to the publishing operation for the target video segment and the segment introduction information, publishing the target video segment with the segment introduction information as an introduction to the video segment viewing interface corresponding to the target video.

[0027] In one embodiment, the segment introduction configuration control includes a segment title configuration control and a segment topic configuration control; the response to the configuration operation of the segment introduction configuration control, the segment introduction information configured for the target video segment through the segment introduction configuration control is displayed, including: in response to the entry operation of the segment title configuration control, the segment title entered through the segment title configuration control is displayed; in response to the editing operation of the segment topic configuration control, the topic tag edited through the segment topic configuration control is displayed; the segment title and the topic tag are used as the segment introduction information configured for the target video segment.

[0028] In one embodiment, the method further includes: displaying candidate content platforms for the target video segment; selecting a supplementary content platform in response to a selection operation for the candidate content platform; and publishing the target video segment with the segment introduction information as an introduction to the supplementary content platform in response to the publishing operation.

[0029] In one embodiment, the video clip viewing interface is an interface in a video application that provides the target video, and the supplementary content platform is a platform in the video application that provides target type videos, where the target type videos are videos whose duration is less than a preset duration.

[0030] In one embodiment, the method further includes: after triggering the publishing operation, entering the publishing result interface; displaying the video clip viewing entrance corresponding to the target video on the publishing result interface; and switching from the publishing result page to the video clip viewing interface in response to the triggering operation for the video clip viewing entrance.

[0031] In one embodiment, the method further includes: displaying a set of candidate sharing objects in the publishing result interface; and sharing the target video clip with the target sharing object using the clip introduction information as an introduction in response to a sharing operation on a target sharing object in the set of candidate sharing objects.

[0032] The present application also provides a video editing device, comprising:

[0033] A clip entry display module is used to display a video clip clip entry for the target video on a video clip viewing interface corresponding to the target video; the video clip viewing interface is used to view the published video clips corresponding to the target video;

[0034] A clip entry trigger response module, configured to display a clip tag set corresponding to the target video in response to a trigger operation on the video clip clip entry;

[0035] A tag selection response module is configured to, in response to a selection operation on a target segment clip tag in the segment clip tag set, display a target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video;

[0036] The video segment publishing module is configured to publish the target video segment corresponding to the target video in response to a publishing operation on the target video segment.

[0037] The present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps described in the above-mentioned video editing method when executing the computer program.

[0038] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned video editing method are implemented.

[0039] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned video editing method when executed by a processor.

[0040] The above-mentioned video editing method, apparatus, computer device, storage medium, and computer program product display a video clip editing entry for the target video on a video clip viewing interface corresponding to the target video; the video clip viewing interface is used to view published video clips corresponding to the target video; in response to a triggering operation on the video clip editing entry, a clip editing tag set corresponding to the target video is displayed; in response to a selection operation on a target clip editing tag in the clip editing tag set, a target video clip obtained by combining candidate video clips from a candidate video clip set corresponding to the target video based on the target clip editing tag is displayed; and in response to a publishing operation on the target video clip, a target video clip corresponding to the target video is published. In this way, a video clip editing entry is added to the video clip viewing interface corresponding to the target video. By triggering the video clip editing entry, the clip editing tag set corresponding to the target video is displayed for user selection. By selecting a clip editing tag, automatic editing to generate the target video clip is triggered, thereby effectively simplifying the video editing operation and improving video editing efficiency. No manual editing by the user is required. The target video clip is automatically combined from the candidate video clip set corresponding to the target video based on the target clip editing tag to obtain the target video clip. The target video clip obtained by intelligent editing can then be published for other users to view.

[0041] This application provides a video editing method, including:

[0042] A video clip editing request for a target video is received from a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video;

[0043] Combining candidate video segments from a set of candidate video segments corresponding to the target video based on the target segment clip tags to obtain a target video segment;

[0044] sending the target video segment corresponding to the target video to the terminal, so that the terminal displays the target video segment;

[0045] receiving a video segment publishing request for the target video segment sent by the terminal;

[0046] The target video clip is published to a target content platform.

[0047] In one embodiment, the method of combining candidate video segments based on the target segment clip tags from the candidate video segment set corresponding to the target video to obtain the target video segment includes: obtaining a segment annotation tag set corresponding to each candidate video segment in the candidate video segment set corresponding to the target video; obtaining the candidate video segment containing the target segment clip tag in the segment annotation tag set as the first video segment; and obtaining the target video segment based on each first video segment.

[0048] In one embodiment, obtaining a target video segment based on each first video segment includes: classifying each first video segment based on a segment annotation tag set corresponding to the first video segment to obtain a plurality of first video segment sets corresponding to the segment annotation tags; obtaining a first video segment as a second video segment from each first video segment set based on a segment weight corresponding to the first video segment on the corresponding segment annotation tag to obtain a plurality of second video segments; and combining each second video segment to obtain a target video segment.

[0049] In one embodiment, the method of obtaining a first video segment as a second video segment from each first video segment set based on the segment weight corresponding to the first video segment on the corresponding segment annotation tag to obtain multiple second video segments includes: determining a reference video segment set from each first video segment set; obtaining a first video segment from the reference video segment set as a reference video segment based on the segment weight corresponding to the first video segment on the segment annotation tag corresponding to the reference video segment set; using the reference video segment set as the current video segment set, and using the reference video segment as the first current segment; obtaining a first video segment from other first video segments as the second current segment based on the segment association between the first current segment and other first video segments in the current video segment set; obtaining a first video segment from other first video segments to which the second current segment belongs as the current video segment set, and using the second current segment as the first current segment, returning the step of obtaining a first video segment as the second current segment from other first video segments based on the segment association between the first current segment and other first video segments in the current video segment set to obtain multiple second current segments; and using the reference video segment and the multiple second current segments as second video segments respectively.

[0050] In one embodiment, the video clip editing request carries a target clip mode selected from a clip mode set, wherein the clip mode set includes at least one of a default clip mode, a pure share clip mode, a simplified clip mode, and a high-energy clip mode;

[0051] The method of obtaining a target video segment based on each first video segment includes: when the target segment mode is the default segment mode, combining each first video segment to obtain a target video segment; when the target segment mode is the pure sharing segment mode, deleting the video frames corresponding to the pushed content from each first video segment to obtain a target video segment; when the target segment mode is the streamlined segment mode, filtering the video frames from each first video segment to obtain a target video segment; the segment length of the target video segment is less than a preset length; when the target segment mode is the high-energy segment mode, deleting the video segment with an interactivity less than a preset threshold from each first video segment to obtain a target video segment.

[0052] The present application also provides a video editing device, comprising:

[0053] a request receiving module, configured to receive a video clip editing request for a target video sent by a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video;

[0054] A segment editing module, configured to combine candidate video segments from a set of candidate video segments corresponding to the target video based on the target segment editing tags to obtain a target video segment;

[0055] a segment feedback module, configured to send the target video segment corresponding to the target video to the terminal, so that the terminal displays the target video segment;

[0056] The request receiving module is further configured to receive a video clip publishing request for the target video clip sent by the terminal;

[0057] The segment publishing module is used to publish the target video segment to the target content platform.

[0058] The present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps described in the above-mentioned video editing method when executing the computer program.

[0059] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned video editing method are implemented.

[0060] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned video editing method when executed by a processor.

[0061] The above-mentioned video editing method, apparatus, computer device, storage medium, and computer program product receive a video clip editing request for a target video from a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video; candidate video clips are combined from a candidate video clip set corresponding to the target video based on the target clip editing tag to obtain a target video clip; a target video clip corresponding to the target video is sent to the terminal so that the terminal displays the target video clip; a video clip publishing request for the target video clip is received from the terminal; and the target video clip is published to a target content platform. Thus, a video clip editing request for the target video is triggered by selecting a target clip editing tag from the clip editing tag set corresponding to the target video. In response to the video clip editing request, corresponding candidate video clips are automatically combined from the candidate video clip set corresponding to the target video based on the target clip editing tag to obtain the target video clip. Automatic editing to generate the target video clip is triggered by selecting the clip editing tag, thereby effectively simplifying the video editing operation and improving video editing efficiency. Subsequently, in response to the video clip publishing request for the target video clip, the target video clip obtained by intelligent editing is published for other users to view. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 A diagram showing an application environment of a video editing method in one embodiment;

[0064] Figure 2 1 is a flow chart of a video editing method according to an embodiment;

[0065] Figure 3 A schematic diagram of a video clip viewing interface in one embodiment;

[0066] Figure 4 A schematic diagram of a process for entering a video clip viewing interface from a video playback interface in one embodiment;

[0067] Figure 5 This is a schematic diagram of a video clip viewing interface in another embodiment;

[0068] Figure 6 A schematic diagram of an interface for switching video clips in a video clip viewing interface in one embodiment;

[0069] Figure 7 A schematic diagram of an interface for full-screen playback of a published video clip in one embodiment;

[0070] Figure 8 A schematic diagram of an interface for entering a video clip editing interface from a video clip viewing interface in one embodiment;

[0071] Figure 9 is a schematic diagram of a video clip editing interface in one embodiment;

[0072] Figure 10 A schematic diagram of an interface for selecting a tag in a video clip editing interface according to one embodiment;

[0073] Figure 11 is a schematic diagram of a video clip editing interface in another embodiment;

[0074] Figure 12 A schematic diagram of an interface for changing a fragment mode in one embodiment;

[0075] Figure 13 A schematic diagram of an interface for publishing edited video clips in one embodiment;

[0076] Figure 14 1 is a flow chart of a video editing method according to an embodiment;

[0077] Figure 15 is a schematic diagram of a set of candidate video segments corresponding to a target video in one embodiment;

[0078] Figure 16 A schematic diagram of generating a target video segment based on a set of candidate video segments corresponding to a target video in one embodiment;

[0079] Figure 17 This is a front-end logic flow chart of a wonderful plot recommendation function in one embodiment;

[0080] Figure 18 This is a front-end logic flow chart of an AI-authored page in one embodiment;

[0081] Figure 19 This is a backend logic flow chart of a wonderful plot recommendation function in one embodiment;

[0082] Figure 20 A backend logic flow chart of an AI-authored page in one embodiment;

[0083] Figure 21 is a structural block diagram of a video editing device in one embodiment;

[0084] Figure 22 is a structural block diagram of a video editing device in another embodiment;

[0085] Figure 23 is a diagram of the internal structure of a computer device in one embodiment;

[0086] Figure 24 FIG. 4 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0087] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0088] The embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, audio and video, assisted driving, etc.

[0089] The solutions provided in the embodiments of this application involve artificial intelligence computer vision technology, machine learning and other technologies, which are specifically illustrated by the following embodiments:

[0090] The video editing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, can be integrated on the server 104, or can be placed on the cloud or other devices. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented as an independent server or a server cluster composed of multiple servers or a cloud server. The user can enter the application through the terminal 102, the server 104 can be the background server of the application, and the terminal 102 can obtain relevant data of the application from the server 104.

[0091] It can be understood that the application involved in this application may refer to a client installed in the terminal, and the client refers to a program installed and running in the terminal; the application may also refer to an installation-free application, that is, an application that can be used without downloading and installing. This type of application can also be called a mini-program, which usually runs as a subprogram in the client; the application may also refer to a web application opened through a browser; and so on.

[0092] Specifically, the terminal displays a video clip editing entry for the target video on a video clip viewing interface corresponding to the target video, wherein the video clip viewing interface is used to view published video clips corresponding to the target video. In response to a trigger operation on the video clip editing entry, the terminal displays a clip editing tag set corresponding to the target video, and in response to a selection operation on a target clip editing tag in the clip editing tag set, displays a target video clip obtained by combining candidate video clips from a candidate video clip set corresponding to the target video based on the target clip editing tag. In response to a publishing operation on the target video clip, the terminal publishes the target video clip corresponding to the target video.

[0093] The terminal sends a video clip editing request for the target video to the server. The video clip editing request carries the target clip editing tag selected from the clip editing tag set corresponding to the target video. The server responds to the video clip editing request, combines candidate video clips from the candidate video clip set corresponding to the target video based on the target clip editing tag, obtains the target video clip, and sends the target video clip corresponding to the target video to the terminal. The terminal displays the target video clip, triggering the generation of a video clip publishing request for the target video clip. The terminal then sends the video clip publishing request to the server. The server responds to the video clip publishing request and publishes the target video clip to the target content platform.

[0094] In one embodiment, Figure 2 As shown, a video editing method is provided, which is applied to Figure 1 The following example illustrates the terminal in the example.

[0095] Step S202: Display a video clip editing entry for the target video on a video clip viewing interface corresponding to the target video; the video clip viewing interface is used to view published video clips corresponding to the target video.

[0096] Among them, the target video refers to the video to be edited. The target video can be a variety of videos, for example, it can be a TV series, a movie, a news video, a game video, a live video, etc. The video clip viewing interface corresponding to the target video is an interface that provides the published video clips corresponding to the target video, which is used to view the published video clips corresponding to the target video. The video clip viewing interface corresponding to the target video can display a single published video clip corresponding to the target video on a single screen, or it can display multiple published video clips corresponding to the target video on a single screen. A published video clip refers to a video clip that has been made public. The published video clip corresponding to the target video is a published video clip generated based on a part of the video content of the target video.

[0097] The video clip editing entry for a target video is the entry for triggering the start of the editing operation for the target video. Specifically, it can be implemented through various interface elements such as buttons, sliders, text, graphics, hyperlinks, etc. For example, the video clip editing entry is a video clip editing button. The user can trigger the start of the editing operation for the target video by clicking the video clip editing button corresponding to the target video.

[0098] Specifically, the terminal displays a video clip editing entry for the target video on a video clip viewing interface corresponding to the target video, so that the user can trigger it and then start editing the target video.

[0099] Furthermore, the terminal can display the clip introduction information of the published video clip corresponding to the target video on the video clip viewing interface corresponding to the target video. The clip introduction information of the published video clip is used to introduce the published video clip. For example, the clip introduction information may include at least one information such as clip publisher information, clip title, topic tags, interactive information, and clip length.

[0100] Furthermore, the terminal can first display a portion of the released video clips corresponding to the target video in the video clip viewing interface corresponding to the target video. The user can switch video clips in the video clip viewing interface to trigger the display of another portion of the released video clips corresponding to the target video.

[0101] Step S204 : In response to the triggering operation on the video clip clip entry, display the clip clip tag set corresponding to the target video.

[0102] The trigger operation may specifically be a touch operation, a cursor operation, a key operation, a voice operation, etc. A touch operation may be a touch click operation, a touch press operation, or a touch slide operation, and the touch operation may be a single-touch operation or a multi-touch operation; a cursor operation may be an operation of controlling a cursor to click or an operation of controlling a cursor to press; a key operation may be a virtual key operation or a physical key operation, etc.

[0103] The segment clip label set corresponding to the target video includes multiple segment clip labels corresponding to the target video. The segment clip label corresponding to the target video is a label that describes the candidate video segment corresponding to the target video, and is used to classify the multiple candidate video segments corresponding to the target video. For example, the segment clip label is used to describe the story type of the candidate video segment, the segment clip label is used to describe the characters involved in the candidate video segment, and the segment clip label is used to describe the scene location involved in the candidate video segment. The target video can be split into multiple candidate video segments in advance, and the segment annotation labels corresponding to each candidate video segment are determined, and the segment clip labels are determined from each segment annotation label. For example, each segment annotation label can be used as a segment clip label; the segment annotation label belonging to the target dimension in each segment annotation label can be used as a segment clip label.

[0104] It can be understood that for different videos, the candidate video segment sets corresponding to the videos are different, and the segment clip label sets corresponding to the videos are usually also different.

[0105] Specifically, the user can trigger the displayed video clip editing entry to enter the video clip editing of the target video. In response to the triggering operation on the video clip editing entry, the terminal displays the clip editing tag set corresponding to the target video, allowing the user to select a desired clip editing tag from the clip editing tag set corresponding to the target video.

[0106] Step S206 , in response to the selection operation on the target segment clip tag in the segment clip tag set, displaying the target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video.

[0107] The target clip label is a clip label selected from the clip label set. The candidate video clip set corresponding to the target video includes multiple candidate video clips corresponding to the target video. The candidate video clip set corresponding to the target video is obtained by splitting the target video. The target video can be split into multiple candidate video clips manually in advance, or the target video can be split into multiple candidate video clips by a video splitting algorithm. For example, the target video is split into multiple candidate video clips by a video splitting algorithm based on machine learning; the target video is split into multiple candidate video clips by a video splitting algorithm based on color, shape or optical flow field; and so on.

[0108] From the set of candidate video segments corresponding to the target video, candidate video segments with the target segment clip tag are obtained, and the target video segment is obtained based on the candidate video segments with the target segment clip tag. For example, the target video segment is obtained by splicing the candidate video segments with the target segment clip tag together; from the candidate video segments with the target segment clip tag, several candidate video segments are selected and spliced together to obtain the target video segment; and so on.

[0109] Specifically, the user can select a displayed clip tag set to trigger intelligent video clip editing based on the selected clip tag. The user can select at least one clip tag from the clip tag set corresponding to the target video, and use the selected clip tag as the target clip tag. In response to the selection of the target clip tag from the clip tag set, the terminal displays a target video clip obtained by combining candidate video segments from the candidate video segment set corresponding to the target video based on the target clip tag.

[0110] As you can understand, users can trigger intelligent video editing with a simple tag selection. After the user selects a target tag from a set of tag collections, the terminal or server automatically edits the video for the user based on the target tag, intelligently generating a target video clip corresponding to the target video. Compared to traditional technologies, this significantly simplifies video editing operations and improves efficiency.

[0111] Furthermore, if the user is dissatisfied with the smart editing effect, the user can further crop the smart editing effect, trimming the unsatisfactory portion to obtain a new video clip. If the user is dissatisfied with the smart editing effect, the user can also change the selected clip tag to change the smart editing effect, selecting another clip tag from the clip tag set to obtain a new video clip through smart editing. If the user is dissatisfied with the smart editing effect, the user can also change the clip mode to change the smart editing effect. The clip mode is the combination method of corresponding candidate video clips based on the selected clip tag. The initial smart editing effect is obtained based on the initial clip mode. The user can change the initial clip mode to another clip mode to obtain a new video clip using the new clip mode. For example, in response to a selection operation for a target clip tag in the clip tag set, the initial clip mode and the initial video clip are displayed. The initial video clip is obtained by combining candidate video clips from the candidate video clip set corresponding to the target video based on the target clip tag and the initial clip mode. In response to a clip mode switching operation for the initial clip mode, the selected target clip mode and the target video clip are displayed. The target video clip is obtained by combining candidate video clips from the candidate video clip set corresponding to the target video based on the target clip tag and the target clip mode.

[0112] In one embodiment, in response to a trigger operation on a video clip editing entry, the clip tag set corresponding to the target video and the candidate video clip set corresponding to the target video are displayed; in response to an operation to select a target clip tag in the clip tag set, the target video clip is displayed, which is obtained by combining candidate video clips from the candidate video clip set corresponding to the target video based on the target clip tag. In this way, the candidate video clip set corresponding to the target video is first displayed for the user to view, the clip tag set corresponding to the target video is displayed for the user to select, and then the corresponding smart editing result is displayed based on the user's selection result.

[0113] Step S208 : In response to the publishing operation on the target video segment, the target video segment corresponding to the target video is published.

[0114] The publishing operation refers to an operation of making the edited video clips public. For example, the publishing operation may be a triggering operation for a publishing control.

[0115] Specifically, after viewing the target video clip, the user can choose to publish the target video clip for other users to view. In response to the publishing operation for the target video clip, the terminal publishes the target video clip corresponding to the target video. The target video clip corresponding to the target video can be published to the target content platform, making the target video clip open to access on the target content platform.

[0116] It is understood that the target video clip corresponding to the target video can be published to the video clip viewing interface corresponding to the target video. The target video clip corresponding to the target video can also be published to other platforms. For example, in a first application, by selecting a clip clip tag to trigger automatic editing to generate a target video clip, and then publishing the target video clip to a second application through a publishing operation, so that the user can view the target video clip in the second application; by selecting a clip clip tag on a first platform in a first application to trigger automatic editing to generate a target video clip, and then publishing the target video clip to a second platform in the first application through a publishing operation; and so on.

[0117] Taking video applications as an example, in traditional technologies, users usually need to download videos provided by the video application in the video application, and then manually perform a series of editing operations on the downloaded videos to obtain video clips. However, through the method of the present application, the terminal enters the video application and displays the video clip viewing interface corresponding to the target video provided by the video application. In the video clip viewing interface corresponding to the target video, a video clip editing entry for the target video is displayed. The user can trigger the video clip editing entry. In response to the triggering operation on the video clip editing entry, the terminal displays the clip editing tag set corresponding to the target video. The user can select a tag from the clip editing tag set. In response to the selection operation of the target clip editing tag in the clip editing tag set, the terminal displays the target video clip. The target video clip is obtained by combining candidate video clips from the candidate video clip set corresponding to the target video based on the target clip editing tag. The user can trigger the release of the target video clip. The terminal responds to the release operation on the target video clip and releases the target video clip corresponding to the target video. In this way, users can perform intelligent editing creation in real time in the video application, realizing a new video editing method. In the video application, by selecting the clip editing tag, intelligent editing can be triggered to generate the target video clip corresponding to the target video, thereby improving the efficiency of video editing.

[0118] It is understood that the present method can also be applied to other applications, such as live streaming applications, gaming applications, social applications, video social applications, and information reading applications. Video social applications are applications that enable social interaction by posting videos. Information reading applications are applications that provide information in various fields such as news, entertainment, sports, technology, and finance.

[0119] In the above-mentioned video editing method, a video clip editing entry is added to the video clip viewing interface corresponding to the target video. By triggering the video clip editing entry, the target video's corresponding clip editing tag set is displayed for the user to select. By selecting a clip editing tag, the automatic editing is triggered to generate the target video clip, thereby effectively simplifying the video editing operation and improving video editing efficiency. No manual editing is required by the user. Based on the target clip editing tags, the corresponding candidate video clips are automatically combined from the candidate video clip set corresponding to the target video to obtain the target video clip. The target video clip obtained by intelligent editing can then be published for other users to view.

[0120] In one embodiment, on the video clip viewing interface corresponding to the target video, a video clip editing entry for the target video is displayed, including:

[0121] In the video clip viewing interface corresponding to the target video, the first published video clip corresponding to the target video is played in full screen, and the video clip editing entrance for the target video is displayed.

[0122] Specifically, the video clip viewing interface can be a full-screen playback interface of a published video clip corresponding to the target video, and a video clip editing entry for the target video is displayed in the full-screen playback interface. The first published video clip corresponding to the target video is any published video clip corresponding to the target video. In the video clip viewing interface corresponding to the target video, the terminal plays the first published video clip corresponding to the target video in full screen and displays a video clip editing entry for the target video.

[0123] In one embodiment, a video clip editing entry for the target video is displayed on the full-screen playback interface. In response to a trigger operation on the video clip editing entry, a video clip editing interface is entered, and a clip editing tag set corresponding to the target video is displayed on the video clip editing interface.

[0124] In one embodiment, the target application refers to an application that provides the target video. A user can search for published video clips corresponding to the target video in the target application, thereby accessing a video clip viewing interface corresponding to the target video. For example, in response to a search operation for published video clips corresponding to the target video in the target application, a video clip viewing interface corresponding to the target video is displayed; in response to a search operation for published video clips corresponding to the target video in the target application, a set of published video clips corresponding to the target video is displayed; and in response to a trigger operation on the first published video clip in the set of published video clips, a video clip viewing interface corresponding to the target video is displayed.

[0125] In the above embodiment, a video clip editing entry for the target video is added to the full-screen playback interface of the published video clip corresponding to the target video, and the user can quickly enter the video editing creation through the video clip editing entry.

[0126] In one embodiment, the video editing method further includes:

[0127] On the video clip viewing interface, the clip publisher information corresponding to the first published video clip and the interactive controls for the first published video clip are displayed; in response to a trigger operation on the clip publisher information, the publisher interface corresponding to the clip publisher information is entered; the publisher interface is used to display the video clip set published by the clip publisher corresponding to the clip publisher information; in response to a trigger operation on the interactive controls, the corresponding interactive results are displayed; the interactive results are used to update the interactivity corresponding to the first published video clip.

[0128] The clip publisher is the user who publishes the video clip, that is, the author of the video clip. The clip publisher information describes the publisher of the video clip. For example, the clip publisher information may include the publisher's username, user profile picture, user level, and other information. The publisher interface provides a collection of video clips published by the publisher. The video clip collection published by the publisher includes each video clip published by the publisher.

[0129] Specifically, the terminal may also display the segment publisher information corresponding to the first published video segment on the video segment viewing interface. The user may trigger the segment publisher information to enter the publisher interface of the corresponding segment publisher to view other video segments published by the segment publisher. In response to the triggering operation on the segment publisher information, the terminal enters the publisher interface corresponding to the segment publisher information, and displays the video segment set published by the segment publisher corresponding to the segment publisher information on the publisher interface. The video segment set includes each video segment published by the segment publisher.

[0130] Interactive controls are controls that allow users to interact with video clips. For example, interactive controls can include a like control, allowing users to like a video clip; a comment control, allowing users to comment on a video clip; or a bullet screen control, allowing users to post comments on a video clip. The list of interactive controls is as follows:

[0131] The interactivity of a video clip is determined based on the interaction results of the video clip. For example, the interactivity of a video clip is determined based on at least one of the interactive information such as the number of likes, comments, and comments of the video clip.

[0132] Specifically, the terminal may also display an interactive control for the first published video clip on the video clip viewing interface, and the user may interact with the video clip by triggering the interactive control. In response to the triggering operation on the interactive control, the terminal may display the corresponding interaction result. For example, if the user clicks the like control to like the first published video clip, the terminal may update and display the number of likes for the first published video clip.

[0133] Furthermore, the interactivity corresponding to the video clips can be used for video clip recommendation and video clip search. For example, when searching for video clips, video clips with higher interactivity will be displayed first. The higher the interactivity corresponding to the video clip, the more popular the video clip is. Giving priority to video clips with higher interactivity can improve the accuracy and effectiveness of the search. Improving search accuracy can reduce the waste of physical resources required to implement the search and improve the utilization rate of physical resources. The physical resources here include server resources, network bandwidth resources, etc. Similarly, when recommending video clips, giving priority to video clips with higher interactivity can improve the accuracy and effectiveness of the recommendation.

[0134] In one embodiment, the video clip publisher can also interact with other users who have triggered the interactive controls for the video clip they posted through their own publisher interface. For example, if user A comments on a video clip posted by user B, user B can view user A's comment and reply to it through the publisher interface.

[0135] In the above embodiment, in the full-screen playback interface of a published video clip corresponding to a target video, the user can quickly access the publisher interface corresponding to the clip publisher information through the clip publisher information displayed in the full-screen playback interface. The user can conveniently view the various video clips published by the publisher corresponding to the clip publisher information in the publisher interface. In the full-screen playback interface of a published video clip corresponding to a target video, the user can interact with the published video clip through the interactive controls displayed in the full-screen playback interface, enriching the functionality of the full-screen playback interface.

[0136] In one embodiment, the video editing method further includes:

[0137] In response to a video segment switching operation triggered in the video segment viewing interface, full-screen playback of the first published video segment is switched to full-screen playback of other published video segments in the published video segment set corresponding to the target video.

[0138] The set of published video clips corresponding to the target video includes multiple published video clips corresponding to the target video. The video clip switching operation is an operation for switching video clips. For example, the video clip switching operation can be a sliding operation, where the user can slide on the video clip viewing interface to switch to a video clip played in full screen; the video clip switching operation can be a triggering operation on a video clip switching control, where the user can trigger the video clip switching control on the video clip viewing interface to switch to a video clip played in full screen; and so on.

[0139] Specifically, the user can quickly switch to play different published video clips in the video clip viewing interface. In response to the video clip switching operation triggered in the video clip viewing interface, the terminal switches from full-screen playback of the first published video clip to full-screen playback of other published video clips in the published video clip set corresponding to the target video.

[0140] It is understood that video clips can be switched randomly. For example, a published video clip other than the first published video clip is randomly selected from the published video clip set corresponding to the target video as the target published video clip, and the full-screen playback of the first published video clip is switched to the full-screen playback of the target published video clip. Video clips can also be switched in an orderly manner according to interactivity. For example, if a user performs a swipe operation in a first direction, a published video clip with a lower interactivity than the first published video clip is selected from the published video clip set corresponding to the target video as the target published video clip, and the full-screen playback of the first published video clip is switched to the full-screen playback of the target published video clip. If the user performs a swipe operation in a second direction, a published video clip with a higher interactivity than the first published video clip is selected from the published video clip set corresponding to the target video as the target published video clip, and the full-screen playback of the first published video clip is switched to the full-screen playback of the target published video clip. It is understood that the first direction and the second direction are different directions. For example, a swipe operation in the first direction is an upward swipe operation, and a swipe operation in the second direction is a downward swipe operation.

[0141] In the above embodiment, in the full-screen playback interface of the published video clip corresponding to the target video, the user can trigger the video clip switching operation to switch to playing different published video clips corresponding to the target video, thereby conveniently viewing different published video clips corresponding to the target video.

[0142] In a specific embodiment, Figure 3 This is the full-screen playback interface of the highlight clip 1 of video A. Figure 3 As shown, the full-screen playback interface displays a video clip editing entrance, specifically an interface element 302 with the words "+Go to AI creation". The user can trigger the video clip editing entrance to enter the AI creation page for creating highlights of video A. On the AI creation page, the user can trigger AI editing by selecting a clip editing tag from the clip editing tag set corresponding to video A to generate the corresponding highlight clip (i.e., video clip). The user can then publish the highlight clip generated by AI smart editing. Figure 3 As shown, the full-screen playback interface displays the clip publisher information, specifically the interface element 304 with the word "Zhang San". The user can trigger the clip publisher information to enter the personal center interface (i.e. publisher interface) of the creator of the highlight clip 1 of video A. The personal center interface includes various highlight clips published by the creator. Figure 3As shown, the full-screen playback interface displays interactive controls, specifically interface element 306 with the words "Post a fun comment," interface element 308 with a "Like" icon, and interface element 310 with a "Comment" icon. Users can trigger the interactive controls to post comments, like, and leave comments. Furthermore, within the full-screen playback interface, users can quickly switch between highlight clips created by different users for Video A by swiping up and down.

[0143] In one embodiment, on the video clip viewing interface corresponding to the target video, a video clip editing entry for the target video is displayed, including:

[0144] In the video clip viewing interface corresponding to the target video, multiple published video clips corresponding to the target video are displayed in separate windows; the second published video clip displayed in the target window is played, and the video clip editing entrance for the target video is displayed in the target window.

[0145] A window is an area within the interface used to display and manipulate objects. The video clip viewing interface includes multiple windows for displaying video clips. A target window is a window within the video clip viewing interface that meets preset conditions. For example, the target window is the window currently selected by the user; the target window is the window currently displayed in its entirety. It is understood that these preset conditions can be customized as needed.

[0146] The second published video segment is a published video segment corresponding to the target video and is displayed in the target window.

[0147] Specifically, the video clip viewing interface corresponding to the target video can display multiple published video clips corresponding to the target video on the same screen. It is understood that multiple means at least two. In the video clip viewing interface corresponding to the target video, the terminal displays multiple published video clips corresponding to the target video in separate windows, and one published video clip corresponds to one window. It is understood that in the video clip viewing interface, a complete window can be displayed, or a partial window can be displayed. The target window is determined from multiple windows, for example, the window currently positioned by the user's cursor is used as the target window; the currently fully displayed window is used as the target window; the window displayed at a preset position is used as the target window; and so on. The terminal automatically plays the second published video clip displayed in the target window, and displays the video clip clip entry for the target video in the target window.

[0148] Furthermore, the terminal may also display a playback progress bar of the second published video clip in the target window. The terminal may also display segment introduction information of the second published video clip in the target window.

[0149] It can be understood that in the video clip viewing interface, the published video clip displayed in the target window is automatically played, and the published video clips displayed in other windows are not played. The other windows can specifically display any frame in the published video clip, for example, the first frame.

[0150] In the above embodiment, multiple published video clips corresponding to the target video are displayed in separate windows on the video clip viewing interface corresponding to the target video. Users can view multiple published video clips on the same screen, improving viewing efficiency. A second published video clip displayed in the target window is played to facilitate the user's understanding of the video clip's content. A video clip editing entry for the target video is added to the target window, allowing users to quickly access video clip editing when viewing multiple published video clips.

[0151] In one embodiment, the video editing method further includes:

[0152] In the target window, a full-screen playback control is displayed; in response to a trigger operation on the full-screen playback control, the second published video clip is played in full screen; in the full-screen playback interface of the second published video clip, a video clip editing entry for the target video is displayed.

[0153] The full-screen playback control is used to control the full-screen playback of a video clip. The control can be implemented through various interface elements such as buttons, sliders, text, graphics, and hyperlinks.

[0154] Specifically, the second published video clip is played in a target window within the video clip viewing interface corresponding to the target video. The target window is a local area within the video clip viewing interface. The user can trigger the target window to maximize the second published video clip to play the second published video clip in full screen. The terminal displays a full-screen play control in the target window within the video clip viewing interface. The user can trigger the full-screen play control to play the second published video clip in full screen. In response to the triggering operation on the full-screen play control, the terminal plays the second published video clip in full screen. Furthermore, a video clip editing entry for the target video is added to the full-screen playback interface of the second published video clip. The user can trigger the video clip editing entry to trigger the start of the editing operation for the target video.

[0155] In the above embodiment, the user can not only access the video clip editing interface through the video clip editing portal in the target window within the video clip viewing interface, but also change the published video clip playing in the target window to full-screen playback using the full-screen playback control in the target window, and access the video clip editing interface through the video clip editing portal in the full-screen playback interface. The video clip editing portal can be displayed in different interfaces, thereby improving the convenience of video clip editing.

[0156] In one embodiment, the video editing method further includes:

[0157] On the video playback interface corresponding to the target video, a video clip viewing entrance corresponding to the target video is displayed; in response to a trigger operation on the video clip viewing entrance, the video playback interface is switched to a video clip viewing interface corresponding to the target video.

[0158] The video playback interface corresponding to the target video is an interface for playing the target video, for example, the video playback interface of the target video is a full-screen playback interface of the target video. The video clip viewing entrance corresponding to the target video is an entrance to the video clip viewing interface corresponding to the target video.

[0159] Specifically, the user can access the video clip viewing interface on demand while playing the target video. The terminal displays a video clip viewing entry corresponding to the target video on the video playback interface corresponding to the target video. The user can trigger the video clip viewing entry to enter the video clip viewing interface corresponding to the target video. In response to the triggering operation on the video clip viewing entry, the terminal switches from the video playback interface to the video clip viewing interface corresponding to the target video, and the user can then view the published video clips corresponding to the target video on the video clip viewing interface.

[0160] In the above embodiment, the user can quickly enter the video clip viewing interface of the target video through the video playback interface of the target video, and quickly start editing the target video in the video clip viewing interface of the target video.

[0161] In one embodiment, the video editing method further includes:

[0162] On the video clip viewing interface, the video playback entry corresponding to the target video is displayed; in response to a trigger operation on the video playback entry, the video clip viewing interface is switched to the video playback interface.

[0163] Among them, the video playback entrance corresponding to the target video is the entrance to the video playback interface corresponding to the target video.

[0164] Specifically, the user can return to the video playback interface as needed while viewing the published video clip corresponding to the target video. The terminal displays a video playback entry corresponding to the target video on the video clip viewing interface corresponding to the target video. The user can trigger the video playback entry to enter the video playback interface corresponding to the target video. In response to the triggering operation on the video playback entry, the terminal switches from the video clip viewing interface to the video playback interface, and the user can then continue to watch the target video on the video playback interface.

[0165] In the above embodiment, the user can quickly enter the video playback interface of the target video through the video clip viewing interface of the target video. The video clip viewing interface of the target video and the video playback interface of the target video can be quickly switched through corresponding entrances.

[0166] In one embodiment, the video editing method further includes:

[0167] Enter the video application and display the program playback entrance corresponding to the target program provided by the video application in the video application; in response to the trigger operation on the program playback entrance, trigger the playback of the single episode video corresponding to the target program, use the single episode video as the target video, and use the playback interface of the single episode video as the video playback interface corresponding to the target video.

[0168] Among them, the video application is an application that provides various types of programs. For example, the video application can be a comprehensive video content application that aggregates popular movies and TV shows, variety shows, sports events, news information and other programs. The target program is any one of the various programs provided by the video application. For example, the target program can be a program of interest selected by the user from the various programs provided by the video application; the target program can be a popular program recommended to the user by the video application; and so on. The target program can include at least one episode of video. For example, if the target program is a TV series, the target program includes multiple episodes of video; if the target program is a movie, the target program includes one episode of video. The program playback entrance corresponding to the target program is the entrance to enter the playback of the target program.

[0169] Specifically, the terminal enters a video application, which can be triggered by the user. After entering the video application, the terminal displays a program playback entry corresponding to the target program provided by the video application. The user can play the target program by triggering the program playback entry. In response to the triggering operation on the program playback entry, the terminal triggers the playback of a single episode of the target program, uses the single episode as the target video, and uses the playback interface of the single episode as the video playback interface corresponding to the target video. Subsequently, the terminal can enter the video clip viewing interface corresponding to the target video through the video playback interface corresponding to the target video, and trigger the quick start of the editing operation for the target video through the video clip viewing interface corresponding to the target video.

[0170] For example, the program playback entrance corresponding to TV series A provided by the video application is displayed. In response to the trigger operation on the program playback entrance, the playback of the latest released 6th episode of TV series A is triggered, and the 6th episode of TV series A is used as the target video. The user can enter the video clip viewing interface of the 6th episode of TV series A through the video playback interface of the 6th episode of TV series A, view the released video clips of the 6th episode of TV series A in the video clip viewing interface, enter the video clip editing interface for the 6th episode of TV series A through the video clip viewing interface, and create a new video clip of the 6th episode of TV series A in the video clip editing interface.

[0171] In the above embodiment, the method of the present application can be applied to a video application, in which a single episode of a target program provided by the video application is intelligently edited, thereby improving video editing efficiency. From the playback interface of a single episode of the target program, a video clip viewing interface for the single episode can be accessed, and a video clip editing entry is displayed on the video clip viewing interface. The user can trigger the video clip editing entry to start editing the single-click video.

[0172] In one embodiment, the video editing method further includes:

[0173] In the video clip viewing interface, the third published video clip in the published video clip set corresponding to the target video is played; in response to a video clip switching operation triggered in the video clip viewing interface, the playback is switched from the third published video clip to the fourth published video clip in the published video clip set; the interactivity corresponding to the third published video clip is greater than the interactivity corresponding to the fourth published video clip.

[0174] The third published video segment is a published video segment played before a video segment switching operation is triggered in the video segment viewing interface, and the fourth published video segment is a published video segment played after a video segment switching operation is triggered in the video segment viewing interface. The third and fourth published video segments are published video segments in the published video segment set corresponding to the target video.

[0175] The interactivity of a video clip is determined based on the interactive information of the video clip, for example, based on at least one of the interactive information such as the number of likes, comments, and comments of the video clip.

[0176] Specifically, after the terminal enters the video clip viewing interface corresponding to the target video, it first plays the third published video clip corresponding to the target video, which has a high degree of interactivity, in the video clip viewing interface to increase the user's attention to the video clip viewing interface. The user can switch between playing different published video clips in the video clip viewing interface. In response to a video clip switching operation triggered in the video clip viewing interface, the terminal switches from playing the third published video clip to playing the fourth published video clip corresponding to the target video, which has a lower degree of interactivity.

[0177] For example, after the terminal enters the video clip viewing interface corresponding to the target video, the published video clip with the highest number of likes corresponding to the target video is first played on the video clip viewing interface. The user can switch to playing the published video clip with the second highest number of likes corresponding to the target video by sliding the video clip viewing interface. The user can switch to playing the published video clip with the third highest number of likes corresponding to the target video by sliding the video clip viewing interface again.

[0178] It can be understood that when the third published video clip is played in the video clip viewing interface, it can be played in full screen in the interface or in a local area in the interface.

[0179] In the above embodiment, after entering the video clip viewing interface corresponding to the target video, the video clip with high interactivity is played first. If the user triggers the video clip switching operation, the video clip with low interactivity is switched to play. The video clip with high interactivity is relatively popular. Playing the video clip with high interactivity first can attract the user's attention and improve user retention rate. After the user triggers the video clip switching operation, the video clip switching is carried out in an orderly manner based on the interactivity, which can further improve user retention rate.

[0180] In one embodiment, the video clip viewing interface includes a video clip switching area and a video switching area.

[0181] In response to a video segment switching operation triggered in the video segment viewing interface, switching from playing the third published video segment to playing the fourth published video segment in the published video segment set includes:

[0182] In response to a sliding operation triggered in the video clip switching area in the video clip viewing interface, following the movement of the sliding key point, the third published video clip that gradually exits the screen and the fourth published video clip in the published video clip set that gradually enters the screen are displayed in the video clip switching area; after the fourth published video clip is completely displayed, the fourth published video clip is played.

[0183] The video editing method also includes:

[0184] In the video switching area of the video clip viewing interface, the video playback entrance corresponding to the target video is displayed; the video playback entrance is used to switch from the video clip viewing interface to the video playback interface of the target video.

[0185] The video clip viewing interface includes a video clip switching area and a video switching area. The video clip switching area is used to switch and play different video clips. The video switching area is used to switch from the video clip viewing interface to the video playing interface.

[0186] A slide operation is a sliding action performed on an interface. This is achieved by moving a slide key point on the interface. For example, the user's finger position on the interface serves as the slide key point, and the user drags the slide key point left or right to perform a slide operation.

[0187] Specifically, the video clip viewing interface corresponding to the target video includes a video clip switching area and a video switching area. The video clip switching area displays the published video clip corresponding to the target video, and the video playback entrance corresponding to the target video is displayed in the video switching area. After entering the video clip viewing interface, the terminal first plays the third published video clip in the video clip switching area of the video clip viewing interface. In response to the sliding operation triggered in the video clip switching area, following the movement of the sliding key point, the third published video clip that gradually exits the screen is displayed in the video clip switching area. Following the movement of the sliding key point, the fourth published video clip that gradually enters the screen is displayed in the video clip switching area. It can be understood that during the movement of the sliding key point, the third published video clip will gradually change from complete display to incomplete display and then to completely exit the screen, and the fourth published video clip will change from entering the screen to incomplete display and then gradually to complete display. After the fourth published video clip is fully displayed, the terminal automatically plays the fourth published video clip. As for the timing of canceling the playback of the third published video clip, it can be set as needed. For example, the playback of the third published video clip can be canceled after the third published video clip becomes incomplete; the playback of the third published video clip can be canceled after the display ratio corresponding to the third published video clip is less than the preset ratio. The display ratio refers to the size of the current display size of the third published video clip to the complete display size.

[0188] The terminal displays the video playback entry corresponding to the target video in the video switching area of the video clip viewing interface. The user can switch from the video clip viewing interface of the target video to the video playback interface of the target video by triggering the video playback entry.

[0189] In the above embodiment, the video clip viewing interface includes a video clip switching area and a video switching area. The video clip switching area displays the published video clip corresponding to the target video, and the video playback entrance corresponding to the target video is displayed in the video switching area. The content of different functions is displayed in different areas, which can effectively avoid user misoperation. When switching video clips, in response to the sliding operation triggered in the video clip switching area, following the movement of the sliding key point, the video clip switching area displays the third published video clip that gradually exits the screen and the fourth published video clip that gradually enters the screen in the published video clip set, which can achieve smooth switching of video clips. After the fourth published video clip is fully displayed, the fourth published video clip is played, which can ensure that the user can watch the complete content of the fourth published video clip, reduce or avoid the user's manual repeated playback operation of the fourth published video clip, and save computer resources.

[0190] In one embodiment, reference Figure 4 , users can enter the video clip viewing interface of the target video through the video playback interface of the target video, or enter the video playback interface of the target video through the video clip viewing interface of the target video. A video clip viewing entrance is displayed on the video playback interface of the target video, specifically an interface element with the words "Exciting Plot". Users click on the video clip viewing entrance to enter the video clip viewing interface. A video playback entrance is displayed on the video clip viewing interface of the target video, specifically an interface element with the words "Watch the Feature Film". Users click on the video playback entrance to enter the video playback interface. For example, when the user clicks on the video clip viewing entrance, the target video is folded upwards to display the published video clip corresponding to the target video; when the user clicks on the video playback entrance, the published video clip corresponding to the target video is folded downwards to display the target video.

[0191] refer to Figure 5 The video clip viewing interface includes a video switching area 502 and a video clip switching area 504. The video switching area 502 displays a video playback entry, and the video clip switching area 504 displays published video clips. The video clip switching area 504 displays different published video clips in separate windows. 5042 and 5044 correspond to different rectangular windows, and the size of the fully displayed window indicates the size of the window corresponding to 5042. The window corresponding to 5042 is the target window, in which the published video clip is played. The target window displays full-screen playback controls 50422, clip introduction information 50424, a video clip editing entry 50426 for the target video, and a playback progress bar 50428.

[0192] refer to Figure 6After entering the video clip viewing interface, the published video clip with the highest interaction rate is displayed first. In the video clip switching area, users can swipe left and right to switch to view different published video clips corresponding to the target video.

[0193] refer to Figure 7 Users can enter full-screen mode by clicking the full-screen playback control, which changes the published video clip playing in the target window to full-screen playback. The full-screen playback interface displays the clip publisher information, interactive controls, and video clip editing entry.

[0194] In one embodiment, in response to a trigger operation on a video clip entry, a clip clip tag set corresponding to a target video is displayed, including:

[0195] In response to the trigger operation for the video clip editing entrance, the video clip editing interface corresponding to the target video is entered; the video clip editing interface includes a video clip preview area, a clip editing tag display area, and an editing effect adjustment area; the video clip preview area is used to preview the video clip to be published, and the editing effect adjustment area is used to adjust the editing effect of the video editing based on the selected clip editing tag; in the clip editing tag display area, the clip editing tag set corresponding to the target video is displayed.

[0196] Among them, the video clip editing interface includes a video clip preview area, a clip editing label display area, and an editing effect adjustment area. The video clip preview area is used to preview the video clips to be published. For example, after the user selects the target clip editing label, the target video clip is generated based on the target clip editing label and the candidate video clip set corresponding to the target video, and the target video clip can be displayed in the video clip preview area. The clip editing label display area is used to display the clip editing label set corresponding to the target video. The editing effect adjustment area is used to adjust the editing effect of video editing based on the selected clip editing label. For example, users can manually crop video clips in the editing effect adjustment area to adjust the editing effect; users can change filters in the editing effect adjustment area to adjust the editing effect; and so on.

[0197] Specifically, in response to a trigger operation for a video clip editing entry, the terminal enters a video clip editing interface corresponding to the target video from a video clip viewing interface corresponding to the target video. The video clip editing interface includes a video clip preview area, a clip clip tag display area, and an editing effect adjustment area. The terminal can display a clip clip tag set corresponding to the target video in the clip clip tag display area, display a target video clip obtained by combining candidate video clips based on the target clip clip tags from the candidate video clip set corresponding to the target video in the video clip preview area, and adjust the editing effect of the video clip based on the selected clip clip tags in the editing effect adjustment area.

[0198] In the above embodiment, the user can enter the video clip editing interface corresponding to the target video by triggering the video clip editing entrance. The video clip editing interface includes a video clip preview area, a clip clip label display area, and a clip effect adjustment area. Different areas are responsible for different functions, which can effectively avoid user misoperation. The video clip preview area is used to preview the video clip to be published, allowing users to preview and confirm before publishing. The clip effect adjustment area is used to adjust the editing effect of the video clip based on the selected clip clip label, allowing users to perform other editing operations to adjust the editing effect. The clip clip label display area is used to display the clip clip label set corresponding to the target video for users to select to trigger smart editing.

[0199] In one embodiment, the video editing method further includes:

[0200] When the first clip tag in the clip tag set is selected, the candidate video clip set corresponding to the target video is displayed in the clip effect adjustment area; the first clip tag is the parent tag of other clip tags in the clip tag set;

[0201] When any clip tag other than the first clip tag in the clip tag set is selected, the target video clip obtained by combining candidate video clips from the candidate video clip set based on the selected clip tag is displayed in the clip effect adjustment area.

[0202] Among them, the first clip clip tag in the clip clip tag set is the parent tag of the other clip clip tags in the clip clip tag set. The other clip clip tags in the clip clip tag set are the child tags of the first clip clip tag in the clip clip tag set. For example, the clip clip tag set includes multiple clip clip tags representing plots, the first clip clip tag can be a clip clip tag representing all plots, and the other clip clip tags can be clip clip tags representing a certain type of plot, and each other clip clip tag can specifically be a clip clip tag representing a martial arts plot, a sweet plot, a suspense plot, a funny plot, a power struggle plot, and other types of plots; the clip clip tag set includes multiple clip clip tags representing characters, the first clip clip tag can be a clip clip tag representing all characters, and the other clip clip tags can be clip clip tags representing a certain character, and each other clip clip tag can specifically be a clip clip tag representing characters such as the leading actor, the leading actress, the supporting actor, and the supporting actress; and so on.

[0203] The selected state of a tag means that the tag is selected or chosen.

[0204] Specifically, when the first clip tag in the clip tag set is selected, the terminal displays the candidate video clip set corresponding to the target video in the clip effect adjustment area. When any clip tag other than the first clip tag in the clip tag set is selected, the terminal displays the target video clip obtained by combining the candidate video clips from the candidate video clip set based on the selected clip tags in the clip effect adjustment area.

[0205] In one embodiment, upon entering the video clip editing interface, the first clip tag is automatically selected, and the candidate video clip set corresponding to the target video is automatically displayed in the editing effect adjustment area. When the user selects another clip tag from the clip tag display area, the target video clip, obtained by combining the candidate video clips from the candidate video clip set based on the selected clip tag, is displayed in the editing effect adjustment area.

[0206] In one embodiment, when any clip tag other than the first clip tag in the clip tag set is selected, a clip mode selection control is displayed in the clip effect adjustment area, and the user can adjust the clip mode through the clip mode selection control, that is, adjust the combination mode of the candidate video clips from the candidate video clip set based on the selected clip clip tag, and then display the adjusted target video clip in the clip effect adjustment area.

[0207] In the above embodiment, when a parent tag is selected in the clip tag set, the set of candidate video clips corresponding to the target video is displayed in the editing effect adjustment area, so that the user can view the set of candidate video clips corresponding to the target video. When a subtag is selected in the clip tag set, the target video clip obtained by combining the candidate video clips from the candidate video clip set based on the selected subtag is displayed in the editing effect adjustment area, so that the user can view the smart editing effect based on the selected tag.

[0208] In one embodiment, in the editing effect adjustment area, a target video segment obtained by combining candidate video segments from the candidate video segment set based on the selected segment editing tags is displayed, including:

[0209] In the editing effect adjustment area, an initial video segment is displayed that is obtained by combining candidate video segments from the candidate video segment set according to the initial segment mode based on the selected segment editing tags; in response to an editing operation on the initial video segment, a target video segment is displayed in the editing effect adjustment area after the initial video segment is edited; the editing operation includes at least one of a cropping operation, a segment mode switching operation, a clip undo operation, and a clip restoration operation.

[0210] The initial clip mode refers to the initial clip mode, which can specifically be a preset default clip mode. After a user selects a clip editing tag, candidate video clips from the candidate video clip set are combined according to the initial clip mode based on the selected clip editing tags to generate the initial video clip. If the user is subsequently dissatisfied with the initial video clip, they can adjust the initial video clip by changing the clip mode.

[0211] A cropping operation is an operation of cropping a video clip. For example, a cropping operation can be deleting several frames in a video clip. A clip mode switching operation is an operation of switching clip modes. For example, a clip mode switching operation can be a selection operation for a clip mode set. A clip undo operation is an operation of undoing at least one clipping operation. For example, a clip undo operation can be a trigger operation for a clip undo control. A clip restore operation is an operation of restoring at least one clipping operation that has been undone. For example, a clip restore operation can be a trigger operation for a clip restore control. It can be understood that clip operations include clip clip tag selection operations, cropping operations, clip mode switching operations, and other operations.

[0212] Specifically, after the user selects a clip editing tag, the target video is first intelligently edited based on the initial clip mode and the selected clip editing tag to obtain an initial video clip. The initial video clip is obtained by combining candidate video clips from the candidate video clip set based on the selected clip editing tag and the initial clip mode. The terminal can display the initial video clip in the editing effect adjustment area. If the user is not satisfied with the initial video clip, the user can adjust the initial video clip through some editing operations. In response to the editing operation on the initial video clip, the terminal displays the target video clip obtained by the editing operation on the initial video clip in the editing effect adjustment area. For example, if the user is not satisfied with some video frames in the initial video clip, the user can delete some video frames from the initial video clip through the cropping operation to obtain the target video clip; if the user wants to try the combination effect of other clip modes, the user can switch the clip mode through the clip mode switching operation to obtain the target video clip; if the user is not satisfied with the most recent editing operation, the user can undo the most recent editing operation through the editing undo operation and use the previous editing result as the target video clip; if the user wants to restore the most recent editing operation that was undone, the user can restore the most recent editing operation through the editing recovery operation and use the restored editing result as the target video clip.

[0213] In the above embodiment, the editing effect adjustment area first displays the initial video clip obtained by combining candidate video clips from the candidate video clip set based on the selected clip clip tags according to the initial clip mode, allowing the user to quickly view the initial smart editing effect. If the user is not satisfied with the initial smart editing effect, the user can also perform other editing operations. In the editing effect adjustment area, the target video clip obtained after the initial video clip is edited is displayed, allowing the user to view the latest smart editing effect in real time. The user can view the editing effect of each editing operation in real time in the editing effect adjustment area, which helps to improve video editing efficiency.

[0214] In one embodiment, the video editing method further includes:

[0215] In the video clip preview area, a start preview control, a clip undo control, and a clip restore control are displayed; in response to a trigger operation for the start preview control, the video clip obtained by the current clip starts to play in the video clip preview area; in response to a trigger operation for the clip undo control, a video clip obtained by undoing at least one step of the clipping operation on the video clip obtained by the current clip is displayed; in response to a trigger operation for the clip restore control, a video clip obtained by canceling at least one step of the clipping operation on the video clip obtained by the current clip is displayed.

[0216] The Start Preview control is used to start playing a clip to preview the editing effect. The Undo control is used to undo a clipping operation. The Redo control is used to restore an undone clipping operation. The current clip is the most recently edited clip.

[0217] Specifically, the terminal displays a start preview control in the video clip preview area, and the user can trigger the start preview control to start playing the video clip obtained by the current clip. In response to the triggering operation for the start preview control, the terminal starts playing the video clip obtained by the current clip in the video clip preview area.

[0218] The terminal displays an undo control in the video clip preview area. The user can trigger the undo control to undo the most recent editing operation. In response to the triggering of the undo control, the terminal displays a video clip that would result from undoing at least one editing operation from the current clip. For example, clicking the undo control once undoes the most recent editing operation.

[0219] The terminal displays a clip undo control in the video clip preview area. The user can trigger the clip undo control to restore the most recently undone editing operation. In response to the triggering operation of the clip undo control, the terminal displays the video clip resulting from the currently edited video clip by undoing at least one of the undone editing operations. For example, clicking the clip undo control once restores the most recently undone editing operation.

[0220] In one embodiment, a video clip obtained by undoing at least one editing operation on the currently edited video clip is displayed in at least one of the video clip preview area and the editing effect adjustment area. A video clip obtained by undoing at least one editing operation on the currently edited video clip is displayed in at least one of the video clip preview area and the editing effect adjustment area.

[0221] In the above embodiment, a preview start control, a clip undo control, and a clip restore control are displayed in the video clip preview area. By activating the preview control, the user can start playing the currently edited video clip in the video clip preview area to view the smart editing effect. The user can use the clip undo control to undo at least one editing operation at any time for immediate rollback. The user can use the clip restore control to restore at least one undone editing operation at any time for immediate recovery. By activating the preview control, clip undo control, and clip restore control, the user can perform a richer range of editing operations and improve video editing effects.

[0222] In one embodiment, reference Figure 8 , the user clicks the video clip editing entrance (i.e., the "+Go to AI Creation" control) on the video clip viewing interface of the target video to enter the video clip editing interface (i.e., the AI Creation page).

[0223] refer to Figure 9The video clip editing interface includes a video clip preview area 902, a clip editing tag display area 904, and an editing effect adjustment area 906. The video clip preview area is used to preview the video clips to be published. The clip editing tag display area is used to display the clip editing tag set corresponding to the target video for user selection. Upon entering the video clip editing interface, the parent tag in the clip editing tag set (i.e., the "All Plots" tag) is selected, and the editing effect adjustment area displays the candidate video clip set corresponding to the target video. In the editing effect adjustment area, the candidate video clips corresponding to the target video are arranged in order according to the clip playback time. If the user selects any candidate video clip, the selected candidate video clip can be previewed in the video clip preview area. If the user selects a sub-tag from the clip editing tag set (i.e., a tag other than the "All Plots" tag), the editing effect adjustment area can display the target video clip obtained by combining the candidate video clips from the candidate video clip set corresponding to the target video based on the selected sub-tag. The video clip preview area can also preview the target video clip.

[0224] The video clip preview area displays a start preview control 9022, a clip undo control 9024, and a clip redo control 9026. If the user clicks the start preview control, the corresponding video clip begins playing in the video clip preview area. If the user clicks the clip redo control, the video clip resulting from undoing at least one editing operation is displayed in the video clip preview area and the editing effect adjustment area. If the user clicks the clip redo control, the video clip resulting from undoing at least one editing operation is displayed in the video clip preview area and the editing effect adjustment area.

[0225] The video clip editing interface also displays a return control 908. The user clicks the return control to return to the video clip viewing interface of the target video. The video clip editing interface also displays a segment introduction information configuration entry, specifically an interface element 910 with the word "Next". The user clicks the segment introduction information configuration entry to enter the segment introduction information configuration interface.

[0226] In one embodiment, in response to a selection operation on a target segment clip tag in a segment clip tag set, displaying a target video segment obtained by combining candidate video segments from a candidate video segment set corresponding to a target video based on the target segment clip tag includes:

[0227] In response to a selection operation on a target segment clip tag in a segment clip tag set, a supplementary clip tag set matching the target segment clip tag is displayed; in response to a selection operation on a target supplementary clip tag in a supplementary clip tag set, an initial video segment is displayed, obtained by combining candidate video segments according to an initial segment pattern based on the target segment clip tag and the target supplementary clip tag from a candidate video segment set corresponding to a target video; in response to a clip confirmation operation on the initial video segment, a target video segment obtained based on the initial video segment is displayed.

[0228] Among them, the supplementary clip label is also a label that describes the candidate video segment corresponding to the target video, but the segment clip label and the supplementary clip label are labels of different dimensions. For example, the segment clip label is a label that indicates the plot type, and the supplementary clip label is a label that indicates the character type; the segment clip label is a label that indicates the plot type, and the supplementary clip label is a label that indicates the location type. The set of supplementary clip labels that matches the target segment clip label refers to the set of supplementary clip labels that matches the candidate video segment belonging to the target segment clip label. The supplementary clip label set includes multiple supplementary clip labels.

[0229] In one embodiment, a segment annotation tag set corresponding to a candidate video segment belonging to a target segment clip tag is obtained, and from the segment annotation tags other than the target segment clip tag in the segment annotation tag set, a supplementary clip tag matching the target segment clip tag is determined, thereby obtaining a supplementary clip tag set matching the target segment clip tag. For example, the segment annotation tags belonging to the reference dimension other than the target segment clip tag in the segment annotation tag set are used as supplementary clip tags matching the target segment clip tag; the segment annotation tags other than the target segment clip tag in the segment annotation tag set are used as supplementary clip tags matching the target segment clip tag; and so on.

[0230] The target supplementary editing tag is a supplementary editing tag selected from the set of supplementary editing tags. It is understood that the user can select at least one supplementary editing tag from the set of supplementary editing tags as the target supplementary editing tag. The editing confirmation operation is an operation to confirm whether the editing is completed.

[0231] Specifically, the terminal first displays a set of clip tags corresponding to the target video. The user can select a tag from the set of clip tags. After the user selects the target clip tag, the terminal can further display a set of supplementary clip tags that match the target clip tag, and the user can select a tag from the supplementary clip tags. It is understood that the user can select a supplementary clip tag from the set of supplementary clip tags, or not. If the user does not select a supplementary clip tag, the terminal displays an initial video segment obtained by combining candidate video segments from the set of candidate video segments corresponding to the target video based on the target clip tag according to the initial segment pattern. If the user selects a target supplementary clip tag from the set of supplementary clip tags, the terminal, in response to the selection of the target supplementary clip tag in the set of supplementary clip tags, displays an initial video segment obtained by combining candidate video segments from the set of candidate video segments corresponding to the target video based on the target clip tag and the target supplementary clip tag according to the initial segment pattern. After determining the target clip tag and the target supplementary clip tag, candidate video segments that belong to both the target clip tag and the target supplementary clip tag are obtained from the set of candidate video segments corresponding to the target video. The candidate video segments that belong to both the target clip tag and the target supplementary clip tag are combined according to the initial segment pattern to obtain the initial video segment. The user can choose to further edit the initial video segment, or the user can stop editing. In response to the editing confirmation operation on the initial video segment, the terminal displays the target video segment obtained based on the initial video segment.

[0232] In the above embodiment, after the user selects the target clip editing tag, a supplementary editing tag set matching the target clip editing tag is further displayed to the user. The user can further select supplementary editing tags of other dimensions from the supplementary editing tag set. Intelligent video editing is performed by integrating the tags of different dimensions selected by the user, which can effectively meet the user's editing needs and ensure video editing efficiency.

[0233] In one embodiment, in response to a clip confirmation operation on an initial video segment, displaying a target video segment obtained based on the initial video segment includes:

[0234] In response to a confirmation operation on the initial video segment, the initial video segment is presented as the target video segment.

[0235] The confirmation operation refers to an operation for confirming the completion of the clipping. For example, the confirmation operation may be a triggering operation of a confirmation control.

[0236] Specifically, after the terminal displays the initial video clip, the user can check whether the initial video clip meets the editing requirements. If it meets the editing requirements, the user can trigger a confirmation operation. In response to the confirmation operation on the initial video clip, the terminal uses the initial video clip as the target video clip and displays the target video clip.

[0237] In the above embodiment, the user can trigger a confirmation operation for the initial video clip, use the initial video clip as the target video clip, and then trigger the target video clip to be released. The confirmation operation can reduce or avoid the user from mistakenly releasing a video clip.

[0238] In one embodiment, in response to a clip confirmation operation on an initial video segment, displaying a target video segment obtained based on the initial video segment includes:

[0239] A cropping frame for the initial video segment is displayed; in response to an adjustment operation on the cropping frame, a first updated video segment obtained by cropping the initial video segment based on the adjusted cropping frame is displayed; in response to a confirmation operation on the first updated video segment, the first updated video segment is displayed as the target video segment.

[0240] The cropping frame is a toolbox for trimming the video length. Users can adjust the cropping frame to determine which video content to discard. Adjustment is the process of resizing the cropping frame.

[0241] Specifically, after the terminal displays the initial video clip, the user can further crop the initial video clip, delete unsatisfactory video frames in the initial video clip, and obtain the target video clip. The terminal displays a cropping frame for the initial video clip, and in response to an adjustment operation on the cropping frame, displays a first updated video clip obtained by cropping the initial video clip based on the adjusted cropping frame. The user can check whether the first updated video clip meets the editing requirements. If it does meet the editing requirements, the user can trigger a confirmation operation. In response to the confirmation operation on the first updated video clip, the terminal displays the first updated video clip as the target video clip. It is understandable that if it does not meet the editing requirements, the user can perform other editing operations until the user is satisfied and then triggers the confirmation operation.

[0242] In one embodiment, a cropping frame for the initial video segment is displayed in the editing effect adjustment area. The user can adjust the video length of the initial video segment by adjusting the cropping frame in the editing effect adjustment area.

[0243] In the above embodiment, after the user selects a tag, they can further crop the initial video clip intelligently generated based on the selected tag to obtain a more satisfactory target video clip. Combining intelligent editing and manual editing can achieve personalized editing results while ensuring video editing efficiency.

[0244] In one embodiment, in response to a clip confirmation operation on an initial video segment, displaying a target video segment obtained based on the initial video segment includes:

[0245] Display the initial segment mode; in response to the segment mode switching operation for the initial segment mode, display the target segment mode, and display the second updated video segment obtained by combining the candidate video segments according to the target segment mode from the candidate video segment set based on the target segment clip tag and the target supplementary clip tag; in response to the confirmation operation for the second updated video segment, display the second updated video segment as the target video segment.

[0246] The initial segment mode is the initial segment mode, which may be a preset default segment mode. The target segment mode is the adjusted segment mode. For example, a segment mode set is displayed, and the user can select a desired segment mode from the segment mode set as the target segment mode.

[0247] Specifically, after the terminal displays the initial video clip, the user can further adjust the initial clip mode corresponding to the initial video clip to obtain a target video clip generated based on the target clip mode. The terminal displays the initial clip mode, and the user can change the initial clip mode to another clip mode. In response to the clip mode switching operation for the initial clip mode, the terminal displays the selected target clip mode, and displays the second updated video clip obtained by combining the candidate video clips according to the target clip mode from the candidate video clip set based on the target clip clip tag and the target supplementary clip tag. The user can check whether the second updated video clip meets the editing requirements. If it meets the editing requirements, the user can trigger a confirmation operation. In response to the confirmation operation for the second updated video clip, the terminal displays the second updated video clip as the target video clip. It can be understood that if it does not meet the editing requirements, the user can perform other editing operations until the user is satisfied and then triggers the confirmation operation.

[0248] In one embodiment, in response to a trigger operation on an initial segment mode, a segment mode set is displayed; in response to a segment mode selection operation on the segment mode set, a target segment mode is selected.

[0249] In the above embodiment, after the user selects a tag, an initial video clip intelligently generated based on the selected tag and the initial clip mode is displayed to the user. The user can then change the clip mode, and the target video clip intelligently generated based on the selected tag and the target clip mode is displayed to the user. By selecting a tag and a clip mode, the user triggers automatic editing to generate the target video clip, effectively simplifying the video editing process and improving video editing efficiency.

[0250] In one embodiment, reference Figure 10After the user selects the "High Sweet Plot" tag from the plot tag set, the terminal can further display the character tag set for the user to select. After the user selects the "Female Lead" tag and the "Male Lead" tag from the character tag set, the background performs AI processing based on the user-selected tags to generate the initial video clip. During the background AI processing, the terminal can display a prompt message to the user to prompt the user to wait for the AI processing results. The prompt message can specifically be an interface element with the words "AI Processing". After the background AI processing is completed, the terminal displays the initial video clip to the user. The user can preview the initial video clip to check whether it meets the editing requirements.

[0251] refer to Figure 11 After AI processing is completed in the background, the terminal displays the initial video clip to the user. The initial video clip can be displayed in the video clip preview area or in the editing effect adjustment area. In the video clip preview area, the user can trigger the playback of the initial video clip. Figure 11 As shown in 1102, the editing effect adjustment area displays the initial video clip in a frame view. Frame view displays video in frame units, with each frame arranged in the order in which it is played. A cropping box 11022 for the initial video clip is displayed in the editing effect adjustment area. The user can adjust the cropping box to shorten the length of the initial video clip by trimming the beginning and end frames of the initial video clip. A playback progress bar 11024 for the initial video clip is displayed in the editing effect adjustment area. If the user triggers playback of the initial video clip in the video clip preview area, the playback progress bar in the editing effect adjustment area will indicate the playback progress in real time. By dragging the playback progress bar, the user can quickly jump to different locations in the initial video clip. After the cropping box, the remaining candidate video clips (i.e., candidate video clips not used to form the initial video clip) are displayed in the editing effect adjustment area. A segment addition control 1104 is displayed in the editing effect adjustment area. The user can trigger the segment addition control to add new video frames to the initial video clip.

[0252] like Figure 11 As shown in 1106, the editing effect adjustment area displays a clip mode selection control, which can be a specific interface element with the words "default mode". The user can trigger the clip mode selection control to select a new clip mode. After the user selects a tag, the initial video clip is obtained by combining the candidate video clips from the candidate video clip set corresponding to the target video based on the selected tag and the default mode (i.e., the initial clip mode). Figure 12As shown, if the user wants to change the clip mode, the user can trigger the clip mode selection control, and the terminal will display a set of clip modes (including default mode, pure enjoyment mode, funny mode, and high-energy mode) for the user to choose. The user can select the clip mode of interest from it, and then the terminal will display a new video clip generated based on the new clip mode and the selected tag.

[0253] In one embodiment, in response to a publishing operation on a target video segment, publishing the target video segment corresponding to the target video includes:

[0254] In response to a confirmation operation on a target video clip, a clip introduction configuration control is displayed; in response to a configuration operation on the clip introduction configuration control, the clip introduction information configured for the target video clip through the clip introduction configuration control is displayed; in response to a publishing operation on the target video clip and the clip introduction information, the target video clip with the clip introduction information as an introduction is published to the video clip viewing interface corresponding to the target video.

[0255] The segment introduction configuration control is used to configure segment introduction information. Configuration operations involve configuring segment introduction information through the segment introduction configuration control. For example, the segment introduction configuration control can be a text box in which users can enter segment introduction information. Alternatively, the segment introduction configuration control can contain multiple options, each corresponding to a candidate introduction. The candidate introduction information is intelligently generated for the user based on the target video segment. Users can select the desired segment introduction information from the multiple candidate introduction information as the final segment introduction information corresponding to the target video segment.

[0256] Specifically, after the user confirms that the target video clip meets the editing requirements, the user can further configure the clip introduction information corresponding to the target video clip. In response to the confirmation operation on the target video clip, the terminal displays the clip introduction configuration control, and the user can configure the clip introduction information corresponding to the target video clip through the clip introduction control. In response to the configuration operation on the clip introduction configuration control, the terminal displays the clip introduction information configured for the target video clip through the clip introduction configuration control. For example, the clip introduction configuration control can be a clip title configuration control, and the user can configure the clip title corresponding to the target video clip through the clip title configuration control; the clip introduction configuration control can be a clip topic configuration control, and the user can configure the topic tag corresponding to the target video clip through the clip topic configuration control; and so on. After configuring the clip introduction information corresponding to the target video, the user can trigger the release of the target video clip and the corresponding clip introduction information. In response to the release operation on the target video clip and the clip introduction information, the terminal releases the target video clip with the clip introduction information as an introduction to the video clip viewing interface corresponding to the target video.

[0257] In one embodiment, in response to a confirmation operation on a target video clip, a clip introduction configuration interface is displayed, where a clip introduction configuration control and a publish control are displayed. The user can use the clip introduction configuration control to configure the clip introduction information corresponding to the target video. The user can use the publish control to trigger the publish operation.

[0258] In the above embodiment, after completing the editing operation to obtain the target video segment, the user can further configure the segment description information corresponding to the target video segment through the segment description configuration control, thereby triggering the release of the target video segment with the segment description information as the introduction to the video segment viewing interface corresponding to the target video. Subsequently, other users can quickly understand the target video segment through the segment description information on the video segment viewing interface.

[0259] In one embodiment, the segment introduction configuration control includes a segment title configuration control and a segment topic configuration control.

[0260] In response to a configuration operation on a segment introduction configuration control, displaying segment introduction information configured for a target video segment through the segment introduction configuration control, including:

[0261] In response to the entry operation for the segment title configuration control, the segment title entered through the segment title configuration control is displayed; in response to the editing operation for the segment topic configuration control, the topic tag edited through the segment topic configuration control is displayed; the segment title and topic tag are used as segment introduction information configured for the target video segment.

[0262] The segment title configuration control is used to configure the segment title of a video segment. The entry operation refers to the operation of entering a segment title. The segment topic configuration control is used to configure the topic tag of a video segment. The editing operation refers to the operation of editing the topic tag. It can be understood that the editing operation can be an entry operation, a selection operation, or other operations. The topic tag of a video segment refers to the keywords of the subject or topic of the video segment content, which is used to describe and categorize the video segment content and attract relevant users to click and watch.

[0263] Specifically, the segment introduction configuration control includes a segment title configuration control. The terminal displays the segment title configuration control, and the user can enter the segment title through the segment title configuration control. In response to the entry operation on the segment title configuration control, the terminal displays the segment title entered through the segment title configuration control. For example, the segment title configuration control is a text box for entering the segment title, and the user can enter the segment title in the text box.

[0264] The segment introduction configuration control includes a segment topic configuration control. The terminal displays the segment topic configuration control, and the user can edit the topic tag through the segment topic configuration control. In response to the editing operation on the segment topic configuration control, the terminal displays the topic tag edited through the segment topic configuration control. For example, the segment topic configuration control is a text box for entering the topic tag, and the user can enter the topic tag in the text box; the segment topic configuration control is an intelligently generated candidate topic tag, and the user can select at least one candidate topic tag from multiple candidate topic tags as the final topic tag.

[0265] Finally, the terminal uses the entered segment title and edited topic tags as segment introduction information configured for the target video segment.

[0266] In the above embodiment, when configuring segment introduction information for the target video segment, the user can quickly enter the segment title through the segment title configuration control, quickly edit the topic tag through the segment topic configuration control, and combine the segment title and topic tag to form the segment introduction information.

[0267] In one embodiment, the video editing method further includes:

[0268] Candidate content platforms for the target video segment are displayed; in response to a selection operation for the candidate content platform, a supplementary content platform is selected; in response to a publishing operation, the target video segment with the segment introduction information as an introduction is published to the supplementary content platform.

[0269] The candidate content platform refers to the platform for users to choose to publish videos, and the supplementary content platform refers to the platform selected by users to publish videos.

[0270] Specifically, in addition to publishing the target video clip corresponding to the target video to the video clip viewing interface corresponding to the target video, the target video clip can also be published to other content platforms. The terminal displays at least one candidate content platform for the target video clip, and the user can select at least one content platform from them as a supplementary content platform, thereby triggering the release of the target video clip to the supplementary content platform. In response to the selection operation for the candidate content platform, the terminal uses the candidate content platform selected by the user as the supplementary content platform, and in response to the publishing operation triggered by the user, not only publishes the target video clip with the clip introduction information as the introduction to the video clip viewing interface corresponding to the target video, but also publishes the target video clip with the clip introduction information as the introduction to the supplementary content platform.

[0271] In the above embodiment, if the user triggers the publishing operation, the target video clip corresponding to the target video will be published to the video clip viewing interface corresponding to the target video by default. Before the user triggers the publishing operation, the user can further choose whether to publish the target video clip to other content platforms, and publish the target video clip to the video clip viewing interface and other content platforms at the same time, enriching the publishing path and improving the publishing efficiency.

[0272] In one embodiment, the video clip viewing interface is an interface in a video application that provides a target video, and the supplementary content platform is a platform in the video application that provides target type videos, where the target type videos are videos whose duration is less than a preset duration.

[0273] Specifically, within a video application that provides a target video, a series of operations are performed to obtain a target video clip corresponding to the target video. The target video clip can then be published to the video clip viewing interface corresponding to the target video within the video application. Alternatively, the target video clip can be published to a platform within the video application that provides videos of the target type. Within a video application, a supplementary content platform is a platform that provides videos shorter than a preset duration. For example, a supplementary content platform is a short video channel within a video application, and users can choose whether to publish the target video clip to the short video channel within the video application.

[0274] In the above embodiment, when performing video editing in a video application, the user can choose to publish the edited target video clips on different platforms in the video application, thereby enriching the publishing channels and improving the publishing efficiency.

[0275] In one embodiment, the video editing method further includes:

[0276] After triggering the publishing operation, enter the publishing result interface; on the publishing result interface, display the video clip viewing entrance corresponding to the target video; in response to the triggering operation for the video clip viewing entrance, switch from the publishing result page to the video clip viewing interface.

[0277] The publishing result interface is used to display the publishing results.

[0278] Specifically, after the user triggers the publishing operation, the terminal enters the publishing results interface, which displays a video clip viewing entry corresponding to the target video. The user can access the video clip viewing interface corresponding to the target video through the video clip viewing entry. In response to the triggering operation on the video clip viewing entry, the terminal switches from the publishing results page to the video clip viewing interface. The user can view the published videos corresponding to the target video in the video clip viewing interface. The multiple published videos corresponding to the target video include the video clip just published by the user.

[0279] In the above embodiment, after the publishing operation is triggered, the publishing result page is entered, and a video clip viewing entrance is added to the publishing result page. The user can quickly return to the video clip viewing interface through the video clip viewing entrance.

[0280] In one embodiment, the video editing method further includes:

[0281] On the publishing result interface, a set of candidate sharing objects is displayed; in response to a sharing operation on a target sharing object in the candidate sharing object set, a target video segment with the segment introduction information as an introduction is shared with the target sharing object.

[0282] The candidate sharing object set includes at least one candidate sharing object. The candidate sharing object refers to a candidate sharing object. The target sharing object refers to a selected sharing object. The sharing operation refers to the operation of sharing the published video clip.

[0283] Specifically, after publishing a target video clip, the user can further share the target video clip. The terminal displays a set of candidate sharing objects on the publishing result interface, and the user can select at least one candidate sharing object from the set as the target sharing object. In response to the sharing operation on the target sharing object in the candidate sharing object set, the terminal shares the target video clip with the target sharing object, using the clip introduction information as an introduction.

[0284] For example, a user publishes a target video clip in a video application, and the user can also choose to share the target video clip to other applications so as to show the target video clip to users in other applications.

[0285] In the above embodiment, a sharing function is added to the publishing result page to share the published target video clip with the selected target sharing object, thereby increasing the exposure of the target video clip and further improving the resource utilization of video editing.

[0286] In one embodiment, reference Figure 13On the video clip editing interface, if the user is satisfied with the editing results, they can click the "Next" control (i.e., the confirmation control) to enter the clip description configuration interface. On the clip description configuration interface, users can enter the clip title in the text box, select the hashtag of interest from the candidate hashtags, and choose whether to publish the editing results to the short video channel. On the clip description configuration interface, if the user's configuration is complete, the user can click the "Next" control (i.e., the Publish control) to enter the publishing results interface. On the publishing results interface, users can view the publishing progress in real time. For details, please refer to the interface element with the words "AI Generated 69%". After the user completes the editing and configuration, the backend will package the target video clip and the corresponding clip description information and convert the format for publishing. On the publishing results page, users can click the "Continue Watching" control (i.e., the video clip viewing interface) to return to the video clip viewing interface. On the publishing results page, users can choose to share the published video clip to other platforms.

[0287] In one embodiment, Figure 14 As shown, a video editing method is provided, which is applied to Figure 1 The following example illustrates the server in the example.

[0288] Step S1402: receiving a video clip editing request for a target video sent by a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video.

[0289] The target video's corresponding segment clip tag set includes multiple segment clip tags corresponding to the target video. The target video's segment clip tags are tags describing candidate video segments corresponding to the target video and are used to classify the multiple candidate video segments corresponding to the target video. The target segment clip tags are selected from the segment clip tag set.

[0290] Specifically, the terminal displays a set of clip tags corresponding to the target video. The user can select a clip tag of interest from the set to trigger a video clip request for the target video. The clip tag selected by the user from the set is the target clip tag. The terminal then sends the video clip request for the target video to the server, carrying the target clip tag.

[0291] It is understandable that the clip tag sets corresponding to different videos are usually different.

[0292] In one embodiment, the terminal displays a video clip editing entry for the target video on a video clip viewing interface corresponding to the target video, where the video clip viewing interface is used to view published video clips corresponding to the target video. In response to a triggering operation on the video clip editing entry, the terminal displays a clip editing tag set corresponding to the target video. In response to a selection operation on a target clip editing tag in the clip editing tag set, the terminal generates a video clip editing request for the target video and sends the video clip editing request to a server.

[0293] Step S1404 : From a set of candidate video segments corresponding to the target video, the candidate video segments are combined based on the target segment clip tags to obtain the target video segment.

[0294] The candidate video segment set corresponding to the target video includes multiple candidate video segments corresponding to the target video. The candidate video segment set corresponding to the target video is obtained by splitting the target video, which can be manually split into multiple candidate video segments in advance or split into multiple candidate video segments using a video splitting algorithm.

[0295] Specifically, the server responds to a video clip editing request and intelligently generates a corresponding target video clip for the user based on the target clip clip tag and the set of candidate video clips corresponding to the target video. The server obtains the set of candidate video clips corresponding to the target video, obtains candidate video clips with the target clip clip tag from the set of candidate video clips corresponding to the target video, and combines the candidate video clips with the target clip clip tag to obtain the target video clip corresponding to the target video.

[0296] Step S1406: Send the target video segment corresponding to the target video to the terminal, so that the terminal displays the target video segment.

[0297] Specifically, after the server generates the target video segment corresponding to the target video, it can return the target video segment to the terminal. The terminal can display the target video segment so that the user can understand the smart editing effect.

[0298] Step S1408: receiving a video segment publishing request for the target video segment sent by the terminal.

[0299] Specifically, after the terminal displays the target video segment corresponding to the target video, the user may trigger the generation of a video segment publishing request for the target video segment, and the terminal sends the video segment publishing request to the server.

[0300] In one embodiment, the terminal displays the target video segment, generates a video segment publishing request for the target video segment in response to a publishing operation for the target video segment, and sends the video segment publishing request to the server.

[0301] Step S1410: publishing the target video clip to the target content platform.

[0302] Specifically, the server responds to the video clip publishing request for the target video clip and publishes the target video clip to a target content platform, which may be a default content platform or a content platform selected by the user.

[0303] The above-mentioned video editing method triggers a video clip editing request for the target video by selecting a target clip tag from a set of clip tags corresponding to the target video. In response to the video clip editing request, the target video clip is automatically generated by combining corresponding candidate video clips from a set of candidate video clips corresponding to the target video based on the target clip tags. Automatic editing to generate the target video clip is triggered by selecting a clip tag, thereby effectively simplifying the video editing operation and improving video editing efficiency. Subsequently, in response to a video clip publishing request for the target video clip, the target video clip obtained by intelligent editing is published for other users to view.

[0304] In one embodiment, the target video segment is obtained by combining the candidate video segments from a set of candidate video segments corresponding to the target video based on the target segment clip tags, including:

[0305] Obtain a segment annotation label set corresponding to each candidate video segment in the candidate video segment set corresponding to the target video; obtain a candidate video segment containing a target segment clip label in the segment annotation label set as a first video segment; and obtain a target video segment based on each first video segment.

[0306] Each candidate video segment has its own corresponding segment annotation tag set. The segment annotation tag set corresponding to a candidate video segment includes at least one segment annotation tag. The segment annotation tag is a tag that describes the candidate video segment. For example, the segment annotation tag can be a tag that describes the type, plot, story, character, etc. of the candidate video segment. For example, Figure 15 , the target video is split into 7 segments (i.e., 7 candidate video segments), and the 7 segments are arranged according to the segment playback time. Among them, segment 1, segment 2 and segment 5 belong to the first type of plot, segment 3 and segment 4 belong to the second type of plot, and segment 6 and segment 7 belong to the third type of plot.

[0307] In one embodiment, a target video is input into a video segmentation model to obtain a set of candidate video segments corresponding to the target video and a set of segment annotation labels corresponding to each candidate video segment in the candidate video segment set. The video segment segmentation model is a machine learning model that is used to segment a video and label the segmentation results. The video segment segmentation model can be obtained through supervised training based on a training sample set, wherein the training sample set includes multiple training videos and training labels corresponding to each training video. The training labels include a set of standard video segments corresponding to the training videos and a set of standard segment labels corresponding to each standard video segment in the standard video segment set.

[0308] Specifically, when generating a target video segment based on a set of candidate video segments corresponding to a target video and the target segment clip tags, the server can obtain a segment annotation tag set corresponding to each candidate video segment in the candidate video segment set, and select the candidate video segment in the segment annotation tag set that includes the target segment clip tag as the first video segment, thereby obtaining multiple first video segments. The server can obtain the target video segment based on each first video segment. For example, the target video segment can be obtained by sequentially combining the first video segments according to their playback time.

[0309] In the above embodiment, from the candidate video segments corresponding to the target video, candidate video segments in the segment annotation tag set that contain the target segment's clip tag are selected as first video segments, and the target video segments corresponding to the target video are obtained based on each of the first video segments. In this way, after the user determines the target segment's clip tag, the target video segment that meets the user's requirements can be quickly generated by automatically combining the candidate video segments that meet the user's requirements, thereby improving video editing efficiency.

[0310] In one embodiment, obtaining a target video segment based on each first video segment includes:

[0311] Based on the segment annotation label set corresponding to the first video segment, each first video segment is classified to obtain a plurality of first video segment sets corresponding to the segment annotation labels; from each first video segment set, based on the segment weight corresponding to the first video segment on the corresponding segment annotation label, the first video segment is obtained as the second video segment to obtain a plurality of second video segments; and each second video segment is combined to obtain a target video segment.

[0312] Among them, the segment weight corresponding to the video segment on the segment annotation label is used to represent the excitement of the video segment on the segment annotation label. The higher the excitement, the higher the segment weight. The segment weight can be a fixed value. For example, the matching degree between the video segment and the segment annotation label is used as the excitement of the video segment on the segment annotation label. The higher the matching degree, the higher the excitement. The matching degree between the candidate video segment and its corresponding segment annotation label can be output through a machine learning model. The segment weight can also be a dynamic value. For example, the initial segment weight corresponding to the candidate video segment on the segment annotation label is first determined, and the video segment is intelligently generated based on the initial segment weight for release. Subsequently, based on the interactive information corresponding to the released video segment, the segment weight corresponding to the candidate video segment involved in the released video segment on the segment annotation label is updated. If the released video segment has more interactive information, it means that the released video segment is more popular. To a certain extent, the excitement of the released video segment is higher, and the segment weight can be increased.

[0313] Specifically, when obtaining the target video segment based on each first video segment, in order to further improve the excitement of the target video segment, the server may screen each first video segment to obtain a second video segment, and combine each second video segment to obtain the target video segment.

[0314] After obtaining each first video segment, the server can further divide each first video segment into multiple segment groups. Specifically, the server can classify each first video segment based on the segment annotation tag set corresponding to the first video segment, and group each first video segment with the same segment annotation tag into a first video segment set, thereby obtaining first video segment sets corresponding to multiple segment annotation tags. Furthermore, at least one first video segment can be selected from each first video segment set as the second video segment, thereby obtaining multiple second video segments. Alternatively, the server can randomly select several first video segment sets from each first video segment set, and select at least one first video segment from each selected first video segment set as the second video segment, thereby obtaining multiple second video segments. For any first video segment set, based on the segment weights corresponding to the segment annotation tags of the first video segment in the first video segment set, first video segments with higher segment weights can be selected from the first video segment set as the second video segment. For example, based on a preset clip length, first video segments with higher segment weights can be randomly selected from each first video segment set as the second video segment. Finally, the server combines the second video segments in an orderly manner according to their playback time to obtain the target video segment.

[0315] For example, the target clip editing label is a "martial arts plot" label. First, the first video clips belonging to the "martial arts plot" label are obtained from the candidate video clip set. The first video clips belonging to the "martial arts plot" label can be further divided into multiple first video clip sets according to labels such as characters and locations. The first video clips with higher clip weights are randomly obtained from each first video clip set as the second video clip, and the second video clips are orderly combined to obtain the target video clip.

[0316] In the above embodiment, after determining each first video segment, each first video segment is further subdivided into different segment groups. Highly exciting first video segments are selected from each segment group as second video segments, and the target video segment is then combined with the second video segments. This results in the target video segment including multiple highly exciting candidate video segments that have the target segment clip tag, thereby improving the quality of the target video segment and the quality of intelligent editing.

[0317] In one embodiment, from each set of first video segments, based on the segment weights corresponding to the first video segments on the corresponding segment annotation tags, obtaining the first video segments as the second video segments, and obtaining a plurality of second video segments, includes:

[0318] Determine a reference video segment set from each first video segment set; obtain a first video segment from the reference video segment set as a reference video segment based on the segment weight corresponding to the first video segment on the segment annotation tag corresponding to the reference video segment set; use the reference video segment set as the current video segment set, and use the reference video segment as the first current segment; obtain a first video segment from other first video segments as the second current segment based on the segment association between the first current segment and other first video segments in the current video segment set; obtain a first video segment set from other first video segments to which the second current segment belongs as the current video segment set, use the second current segment as the first current segment, return the step of obtaining the first video segment from other first video segments as the second current segment based on the segment association between the first current segment and other first video segments in the current video segment set, and obtain multiple second current segments; use the reference video segment and the multiple second current segments as second video segments respectively.

[0319] The segment correlation between two video segments is used to represent the degree of correlation between the two video segments. The segment correlation between two video segments can be calculated in various ways, such as based on content similarity, tag similarity, or user feedback statistics.

[0320] The reference video segment set is a first video segment set from each first video segment set. The reference video segment set can be randomly selected or selected according to a certain rule. For example, the first video segment set containing the first video segment with the earliest playback time is selected as the reference video segment set; or the first video segment set containing the first video segment with the highest segment weight is selected from each first video segment set containing the first video segment with the earliest playback time as the reference video segment set.

[0321] Specifically, the server obtains a first video segment set from each first video segment set as a reference video segment set. Based on the segment weights corresponding to the segment annotation tags of the first video segments in the reference video segment set, the server obtains first video segments with higher segment weights from the reference video segment set as reference video segments. Furthermore, the server uses the reference video segment set as the current video segment set, the reference video segment as the first current segment, and, based on the segment associations between the first current segment and other first video segments in the current video segment set, obtains first video segments with higher segment associations from other first video segments as second current segments. The server obtains a first video segment set from other first video segments to which the second current segment belongs as a new current video segment set, uses the second current segment as the new first current segment, and, based on the segment associations between the new first current segment and other first video segments in the new current video segment set, obtains first video segments with higher segment associations from other first video segments as new second current segments. This process continues in this manner, obtaining second current segments from each first video segment set. Finally, the server uses the reference video segment and each second current segment as second video segments.

[0322] For example, reference Figure 16The target video is divided into multiple candidate video segments. If the user selects the "Martial Arts Plot" tag, candidate video segments with the "Martial Arts Plot" tag are obtained from the multiple candidate video segments. The candidate video segments with the "Martial Arts Plot" tag are then divided into four segments groups based on the tags in other dimensions. The four segments groups are sorted by segment playback time. From segment group 1, the candidate video segment with a high segment weight corresponding to the tag in segment group 1 is obtained as the first second video segment. From segment group 1, the candidate video segment with a high segment correlation with the first second video segment is obtained as the second second video segment. The second second video segment also belongs to segment group 2. From segment group 2, the candidate video segment with a high segment correlation with the second second video segment is obtained as the third second video segment. The third second video segment also belongs to segment group 3. From segment group 3, the candidate video segment with a high segment correlation with the third second video segment is obtained as the fourth second video segment. The fourth second video segment also belongs to segment group 4. From segment group 4, the candidate video segment with a high segment correlation with the fourth second video segment is obtained as the fifth second video segment. The target video segment is obtained by combining the five second video segments according to the segment playing time.

[0323] In the above embodiment, a first video clip with a higher clip weight is obtained from each set of first video clips as the second video clip, and a first video clip with a stronger correlation with the first video clip with a higher clip weight is used as the second video clip. This can ensure that the second video clips are relatively related and have a high degree of excitement. The target video clip obtained by combining such second video clips has a higher quality, which can ensure the quality of video editing.

[0324] In one embodiment, the video clip publishing request carries a topic tag configured for the target video clip.

[0325] The video editing method also includes:

[0326] For any second video segment, based on the tag association between the topic tag and each segment tag in the segment tag set corresponding to the second video segment, the segment weight corresponding to the second video segment in the corresponding segment tag set is updated.

[0327] The tag association degree between two tags is used to indicate the degree of association or similarity between the two tags.

[0328] Specifically, a large number of users can use the method of this application to publish video clips that they have edited using the smart editing function. When publishing a video clip, the user can configure clip introduction information for the video clip, and the clip introduction information includes topic tags. The topic tags configured by the user for the created video clip can accurately reflect the content presented in the video clip from the user's perspective. Therefore, the corresponding clip weights of the candidate video clips involved in the created video clip in the corresponding clip annotation tag set can be updated based on the topic tags.

[0329] The server responds to the video clip editing request for the target video, determines the second video clip from the candidate video clip set corresponding to the target video, combines the second video clips, and obtains the target video clip. The server responds to the video clip publishing request for the target video clip, and publishes the target video clip to the target content platform. The video clip publishing request carries the topic tag configured for the target video clip. For any second video clip, based on the tag association between the topic tag and each segment annotation tag in the segment annotation tag set corresponding to the second video clip, the segment weight corresponding to the second video clip on the corresponding segment annotation tag set is updated. For example, for a segment annotation tag corresponding to a second video clip, if the tag association between the topic tag and the segment annotation tag is greater than the preset association, the segment weight corresponding to the second video clip on the segment annotation tag is increased; otherwise, the segment weight corresponding to the second video clip on the segment annotation tag is reduced.

[0330] In the above embodiment, based on the topic tags configured for the target video clip, the corresponding clip weight of the second video clip involved in the target video clip on its own corresponding clip annotation tag set is updated, which can increase the corresponding clip weight of the second video clip on the clip annotation tag that the user is concerned about, so that subsequent users can quickly generate target video clips that are more in line with user demands when using the smart editing function, further simplifying the video editing operation and improving video editing efficiency.

[0331] In one embodiment, the video segment editing request carries a target segment mode selected from a segment mode set, where the segment mode set includes at least one of a default segment mode, a pure segment mode, a compact segment mode, and a high-energy segment mode.

[0332] Based on each first video segment, a target video segment is obtained, including:

[0333] When the target segment mode is the default segment mode, combining the first video segments to obtain the target video segment;

[0334] When the target segment mode is the pure sharing segment mode, the video frames corresponding to the pushed content are deleted from each first video segment to obtain the target video segment;

[0335] When the target segment mode is the simplified segment mode, filtering video frames from each first video segment to obtain a target video segment; the segment length of the target video segment is less than a preset length;

[0336] When the target segment mode is the high-energy segment mode, video segments with interactivity less than a preset threshold are deleted from each first video segment to obtain the target video segment.

[0337] Specifically, in addition to selecting a clip editing tag, the user can further select a clip mode to trigger a video clip editing request. The target clip mode is a clip mode selected from the clip mode set.

[0338] When the target segment mode is the default segment mode, the server sequentially combines the first video segments according to the segment playback time to obtain the target video segment.

[0339] When the target segment mode is the "Only Enjoyable Segment" mode, the server deletes the video frames corresponding to the pushed content from each first video segment to obtain the target video segment. The video frames corresponding to the pushed content are the video frames within the video segment used to push the item. For example, the pushed content could be an advertisement within the video segment. The "Only Enjoyable Segment" mode is used to delete the pushed content within the video segment. This pushed content is often poorly relevant to the content presented in the video segment, hindering the user's ability to watch the video segment.

[0340] When the target segment mode is the simplified segment mode, the server filters video frames from each first video segment to obtain the target video segment, and by filtering the video frames, makes the segment length of the target video segment shorter than the preset length. The simplified segment mode is used to control the segment length of the video segment.

[0341] When the target segment mode is high-energy segment mode, the server deletes the video segments with an interactivity less than a preset threshold from each first video segment to obtain the target video segment. The interactivity of a video segment can be determined based on interactive information such as the number of barrages, likes, and comments on the video segment. For example, when a user posts a barrage while watching a certain video segment, the barrage belongs to the video segment. The more barrages a video segment has, the more attractive it is. The high-energy mode is used to delete video segments with low interactivity, retain video segments with high interactivity, and highlight the wonderful segments or high-energy moments in the video.

[0342] It is understandable that if the user does not actively select a segment mode, the target segment mode may be automatically set as the default segment mode.

[0343] In the above embodiment, in addition to selecting tags from the clip editing tag set, you can also select clip modes from the clip mode set. Different clip modes correspond to different intelligent combination methods, which can enrich the intelligent editing effect and improve the quality and efficiency of video editing.

[0344] In a specific embodiment, the method of the present application can be applied to a video application. Users can use the intelligent editing function within the video application to create highlight clips of the videos provided by the video application and publish the created highlight clips within the video application for other users to view. Within the video application, users' likes and comments on the published highlight clips can be used to pre-recommend the published highlight clips, with highlight clips with higher likes and comments being recommended to users first.

[0345] Figure 17 This is a front-end logic flow chart for the "Highlights" recommendation feature. In a video app, a "Highlights" control is displayed on the video playback interface for a single episode. Users click the "Highlights" control to enter the "Highlights" page, where the "Highlights" clip data corresponding to the episode is displayed. This data includes the highlights created and published by each user using the intelligent editing function. When a user clicks the "Highlights" control, the terminal (i.e., the front-end) requests the "Highlights" clip data from the server (i.e., the back-end). The terminal first requests a portion of the "Highlights" clip data from the server to quickly display it. If the user stays on the "Highlights" page for more than X seconds, the terminal pre-requests more "Highlights" clip data from the server to quickly respond to user actions. On the "Highlights" page, users can swipe left or right to view different highlights from the episode. If the user wants to view more highlights, the terminal will request more "Highlights" clip data from the server. On the "Highlights" page, the currently located highlight plays automatically. Users can like or comment on the highlighted clips. The terminal and server will update the like information and comment information of the highlighted clips.

[0346] On the "Highlights" page, there is a "User Data" button (i.e. publisher information) corresponding to the highlight clips. Users can click the "User Data" button to enter the personal creation page of the highlight clip publisher, where the creation data of the highlight clip publisher (i.e. each highlight clip created) is displayed.

[0347] On the "Exciting Plot" page, there is a "Watch Main Film" button. Users click the "Watch Main Film" button to return to the video playback interface of a single episode.

[0348] On the "Highlights" page, a "Full Screen Play" button is displayed for the automatically played highlights. When the user clicks the "Full Screen Play" button, the automatically played highlights will switch to full screen playback.

[0349] On the "Exciting Plot" page, there is a "Go to AI Creation" button. Users click the "Go to AI Creation" button to enter the AI creation page. On the AI creation page, users can use the intelligent editing function to independently edit and create exciting clips of the video.

[0350] Figure 18 This is the front-end logic flow chart for the AI creation page. When a user clicks the "Go to AI Creation" button, the terminal requests the AI editing data for the current episode (i.e., a single video episode) from the server. This AI editing data includes a set of candidate video clips and a set of clip tags corresponding to the single video episode. The AI creation page displays the current episode's tag set (i.e., clip tag set), from which the user can select tags of interest to trigger AI intelligent editing. The AI creation page also displays a set of candidate video clips for the current episode. The terminal sends the user-selected tags to the server, requesting AI intelligent editing. The server then combines the corresponding candidate video clips from the candidate set based on the user-selected tags to generate a new highlight clip. The server returns the highlight clip generated by AI intelligent editing to the terminal and displays it on the AI creation page, where the user can preview it. If the user is satisfied with the highlight clip generated by AI intelligent editing, they can click the "Next" button to fill in the highlight clip's description. The terminal then submits the clip description to the AI backend (i.e., the server). The server packages the highlight clip and the clip description and publishes it. If the publication is successful, the terminal displays the publication results page. If the publication is unsuccessful, the terminal displays a failure message and returns to the AI creation page.

[0351] Figure 19 This is the backend logic flow chart for the "Highlight Plot" recommendation feature. When a user clicks the "Highlight Plot" control, the terminal requests the "Highlight Plot" data from the server. The server authenticates the request to confirm its validity. If authentication fails, an error message is returned to the terminal. For example, if the user is not logged into the video app, authentication fails. If authentication is valid, the server retrieves the corresponding "Highlight Clip" data (i.e., the published "Highlight Clips" corresponding to the current episode) based on the current episode information. The server sorts each "Highlight Clip" by the number of likes or comments received. The server returns the sorted results to the terminal, which then displays the "Highlight Plot" page in order based on the sorted results.

[0352] When a user clicks the "User Data" button, the terminal requests the user data of the highlight publisher from the server. The server authenticates the request to confirm its validity. If authentication fails, an error message is returned to the terminal. If authentication is valid, the server confirms whether the requesting user has permission to view the highlight publisher's user data. If not, an error message is returned to the terminal. For example, users can set the users to whom their personal creation page is open and who has access rights. If they have permission, the server retrieves the highlight publisher's creative content and packages the search results back to the terminal, allowing the terminal to display the content on their personal creation page.

[0353] Figure 20 This is the backend logic flow chart for the AI creation page. When the user clicks the "Go to AI Creation" button, the terminal requests the AI editing data for the current episode (i.e., a single episode) from the server. The server authenticates the request to confirm whether the request is valid. If authentication fails, an error message is returned to the terminal. If authentication is valid, the server searches the database to see if there are candidate video clips for the current episode. If so, the candidate video clips for the current episode are returned to the terminal. If not, the server decodes the current episode and processes the decoded current episode using an editing model (i.e., a video clip segmentation model) to obtain the clip editing results (i.e., the set of candidate video clips for the current episode), and returns the clip editing results to the terminal. The server can package the clip editing results and store them in a database.

[0354] The tag set of the current episode is displayed on the AI creation page, and users can select the tags of interest to trigger AI smart editing. The terminal sends the tags selected by the user to the server to request the server to perform AI video synthesis. The server authenticates the request to confirm whether the request is valid. If the authentication fails, an error message is returned to the terminal. If the authentication is valid, the candidate video clips corresponding to the tag of the current episode are retrieved from the database based on the tag selected by the user, and the retrieved candidate video clips are decoded. If the user does not configure a special mode on the AI creation page (that is, other modes except the default mode), the server directly synthesizes the retrieved candidate video clips into a highlight clip and returns the highlight clip to the terminal. If the user configures a special mode on the AI creation page, the server calls the algorithm corresponding to the special mode to synthesize the retrieved candidate video clips into a highlight clip and returns the highlight clip to the terminal. The server can package the highlight clips into a preset format and return it to the terminal for terminal display.

[0355] At present, most users watch videos in a short, frequent and fast manner to consume content of interest, and when consuming long videos, users will find that most of the content is heavily inflated / not interesting, which leads to users giving up consumption and causing a decrease in user consumption time of video applications. The present application method applies the exciting plot recommendation function to the long videos provided by the video application, which can meet the core demands of short, frequent and fast users and increase the user consumption time of the video application. The present application method applies the AI intelligent editing function to the long videos provided by the video application. Users can create exciting clips through the AI intelligent editing function, and recommend them to other users with the same interests through the dimensions of likes / comments, thereby increasing the stickiness and participation of users who create independently and satisfying the connection between users. For video applications, users consume through exciting clips, which on the one hand ensures the number of active users of the video application, and on the other hand can also bring more commercial opportunities. For users, while ensuring the refreshing content consumption, more inflated content can be filtered out, and users with the same interests can be found to ensure a pleasant video experience.

[0356] It can be understood that in addition to video applications, the method of the present application can also be applied to other applications that can provide videos, such as game applications and live broadcast applications.

[0357] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0358] Based on the same inventive concept, embodiments of the present application also provide a video editing device for implementing the aforementioned video editing method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more video editing device embodiments provided below can be found in the above-mentioned limitations of the video editing method and will not be repeated here.

[0359] In one embodiment, Figure 21 As shown, a video editing device 2100 is provided, comprising: a clip entry display module 2102, a clip entry trigger response module 2104, a tag selection response module 2106, and a video clip publishing module 2108, wherein:

[0360] The clip entry display module 2102 is used to display the video clip clip entry for the target video on the video clip viewing interface corresponding to the target video; the video clip viewing interface is used to view the published video clips corresponding to the target video.

[0361] The clip entry trigger response module 2104 is used to respond to the trigger operation on the video clip clip entry and display the clip clip tag set corresponding to the target video.

[0362] The tag selection response module 2106 is configured to respond to a selection operation on a target segment clip tag in the segment clip tag set and display a target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video.

[0363] The video segment publishing module 2108 is configured to publish the target video segment corresponding to the target video in response to a publishing operation on the target video segment.

[0364] The above-mentioned video editing device can trigger automatic editing to generate a target video clip by selecting a clip editing tag, thereby effectively simplifying the video editing operation and improving the video editing efficiency.

[0365] It can be understood that the specific definition of the video editing device 2100 can be found in the definition of the video editing method above, and will not be repeated here.

[0366] In one embodiment, Figure 22 As shown, a video editing device 2200 is provided, comprising: a request receiving module 2202, a segment editing module 2204, a segment feedback module 2206, and a segment publishing module 2208, wherein:

[0367] The request receiving module 2202 is configured to receive a video clip editing request for a target video sent by a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video.

[0368] The segment clipping module 2204 is configured to combine candidate video segments from a set of candidate video segments corresponding to a target video based on target segment clipping tags to obtain a target video segment.

[0369] The segment feedback module 2206 is configured to send the target video segment corresponding to the target video to the terminal, so that the terminal displays the target video segment.

[0370] The request receiving module 2202 is further configured to receive a video segment publishing request for a target video segment sent by a terminal.

[0371] The segment publishing module 2208 is used to publish the target video segment to the target content platform.

[0372] The above-mentioned video editing device can trigger automatic editing to generate a target video clip by selecting a clip editing tag, thereby effectively simplifying the video editing operation and improving the video editing efficiency.

[0373] It can be understood that the specific definition of the video editing device 2200 can be found in the definition of the video editing method above, and will not be repeated here.

[0374] Each module in the video editing device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0375] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 23 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as a set of candidate video clips and a set of clip clip tags corresponding to the target video. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a video editing method is implemented.

[0376] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 24As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be achieved via Wi-Fi, mobile cellular networks, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a video editing method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0377] Those skilled in the art will understand that Figure 23 、 24 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0378] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0379] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0380] In one embodiment, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0381] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0382] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0383] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0384] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A video editing method, characterized in that: The method comprises: On the video clip viewing interface corresponding to the target video, a video clip editing entry for the target video is displayed; the video clip viewing interface is used to view the published video clips corresponding to the target video; In response to a triggering operation on the video clip clip entry, displaying a clip clip tag set corresponding to the target video; In response to a selection operation on a target segment clip tag in the segment clip tag set, displaying a target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video; In response to a publishing operation on the target video segment, the target video segment corresponding to the target video is published.

2. The method according to claim 1, characterized in that The video clip viewing interface corresponding to the target video displays a video clip editing entry for the target video, including: In the video clip viewing interface corresponding to the target video, the first published video clip corresponding to the target video is played in full screen, and the video clip editing entrance for the target video is displayed.

3. The method according to claim 2, characterized in that The method further comprises: On the video clip viewing interface, displaying the clip publisher information corresponding to the first published video clip and interactive controls for the first published video clip; In response to a trigger operation on the segment publisher information, entering a publisher interface corresponding to the segment publisher information; the publisher interface is used to display a video segment set published by the segment publisher corresponding to the segment publisher information; In response to a triggering operation on the interactive control, a corresponding interactive result is displayed; the interactive result is used to update the interactivity corresponding to the first published video clip.

4. The method according to claim 1, wherein The video clip viewing interface corresponding to the target video displays a video clip editing entry for the target video, including: In the video clip viewing interface corresponding to the target video, multiple published video clips corresponding to the target video are displayed in separate windows; The second published video clip displayed in the target window is played, and a video clip clip entry for the target video is displayed in the target window.

5. The method according to claim 4, characterized in that The method further comprises: Displaying full-screen playback controls in the target window; In response to a triggering operation on the full-screen play control, playing the second published video clip in full screen; On the full-screen playback interface of the second published video clip, a video clip editing entry for the target video is displayed.

6. The method according to claim 1, characterized in that The method further comprises: On the video playback interface corresponding to the target video, a video clip viewing entrance corresponding to the target video is displayed; In response to a triggering operation on the video clip viewing entrance, the video playback interface is switched to a video clip viewing interface corresponding to the target video.

7. The method according to claim 1, characterized in that The displaying of the segment clip tag set corresponding to the target video in response to the triggering operation on the video segment clip entry includes: In response to a trigger operation on the video clip editing entry, a video clip editing interface corresponding to the target video is entered; the video clip editing interface includes a video clip preview area, a clip editing tag display area, and an editing effect adjustment area; the video clip preview area is used to preview the video clip to be published, and the editing effect adjustment area is used to adjust the editing effect of the video clip based on the selected clip editing tag; In the clip tag display area, the clip tag set corresponding to the target video is displayed.

8. The method according to claim 7, characterized in that The method further comprises: When the first clip tag in the clip tag set is selected, the candidate video clip set corresponding to the target video is displayed in the clip effect adjustment area; the first clip tag is the parent tag of other clip tags in the clip tag set; When any clip tag other than the first clip tag in the clip tag set is selected, the target video clip obtained by combining candidate video clips from the candidate video clip set based on the selected clip tag is displayed in the clip effect adjustment area.

9. The method according to claim 1, characterized in that In response to a selection operation on a target segment clip tag in the segment clip tag set, displaying a target video segment obtained by combining candidate video segments based on the target segment clip tag from a candidate video segment set corresponding to the target video, comprises: In response to a selection operation on a target segment clip tag in the segment clip tag set, displaying a supplementary clip tag set matching the target segment clip tag; In response to a selection operation on a target supplementary clip tag in the supplementary clip tag set, displaying an initial video segment obtained by combining candidate video segments according to an initial segment pattern based on the target segment clip tag and the target supplementary clip tag from a candidate video segment set corresponding to the target video; In response to a clip confirmation operation on the initial video segment, a target video segment obtained based on the initial video segment is displayed.

10. The method according to claim 1, characterized in that The step of publishing the target video segment corresponding to the target video in response to the publishing operation on the target video segment includes: In response to a confirmation operation on the target video segment, displaying a segment introduction configuration control; In response to a configuration operation on the segment introduction configuration control, displaying segment introduction information configured for the target video segment through the segment introduction configuration control; In response to a publishing operation for the target video segment and the segment introduction information, the target video segment with the segment introduction information as an introduction is published to a video segment viewing interface corresponding to the target video.

11. The method according to claim 10, characterized in that The method further comprises: After triggering the publishing operation, enter the publishing result interface; On the publishing result interface, a video clip viewing entrance corresponding to the target video is displayed; In response to a triggering operation on the video clip viewing entrance, switching is performed from the publishing result page to the video clip viewing interface.

12. A video editing method, characterized in that: The method comprises: A video clip editing request for a target video is received from a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video; Combining candidate video segments from a set of candidate video segments corresponding to the target video based on the target segment clip tags to obtain a target video segment; sending the target video segment corresponding to the target video to the terminal, so that the terminal displays the target video segment; receiving a video segment publishing request for the target video segment sent by the terminal; The target video clip is published to a target content platform.

13. The method according to claim 12, characterized in that The step of combining candidate video segments from a set of candidate video segments corresponding to the target video based on the target segment clip tags to obtain the target video segment includes: Obtain a segment annotation label set corresponding to each candidate video segment in the candidate video segment set corresponding to the target video; Obtaining a candidate video segment containing the target segment clip label in the segment annotation label set as the first video segment; Based on each first video segment, a target video segment is obtained.

14. The method according to claim 13, wherein: The step of obtaining a target video segment based on each of the first video segments includes: Classifying each first video segment based on a segment annotation label set corresponding to the first video segment to obtain a plurality of first video segment sets corresponding to the segment annotation labels; From each set of first video segments, based on segment weights corresponding to the first video segments on corresponding segment annotation tags, obtaining the first video segments as second video segments, thereby obtaining a plurality of second video segments; The second video segments are combined to obtain a target video segment.

15. The method according to claim 14, characterized in that The video clip publishing request carries a topic tag configured for the target video clip; The method further comprises: For any second video segment, based on the tag association between the topic tag and each segment tag in the segment tag set corresponding to the second video segment, the segment weight corresponding to the second video segment in the corresponding segment tag set is updated.

16. A video editing device, characterized in that: The device comprises: A clip entry display module is used to display a video clip clip entry for the target video on a video clip viewing interface corresponding to the target video; the video clip viewing interface is used to view the published video clips corresponding to the target video; A clip entry trigger response module, configured to display a clip tag set corresponding to the target video in response to a trigger operation on the video clip clip entry; A tag selection response module is configured to, in response to a selection operation on a target segment clip tag in the segment clip tag set, display a target video segment obtained by combining candidate video segments based on the target segment clip tag from the candidate video segment set corresponding to the target video; The video segment publishing module is configured to publish the target video segment corresponding to the target video in response to a publishing operation on the target video segment.

17. A video editing device, characterized in that: The device comprises: a request receiving module, configured to receive a video clip editing request for a target video sent by a terminal; the video clip editing request carries a target clip editing tag selected from a clip editing tag set corresponding to the target video; A segment editing module, configured to combine candidate video segments from a set of candidate video segments corresponding to the target video based on the target segment editing tags to obtain a target video segment; a segment feedback module, configured to send the target video segment corresponding to the target video to the terminal, so that the terminal displays the target video segment; The request receiving module is further configured to receive a video clip publishing request for the target video clip sent by the terminal; The segment publishing module is used to publish the target video segment to the target content platform.

18. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 15 are implemented.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 15 are implemented.

20. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 15 are implemented.

Images