A video editing method and apparatus

Abstract

Embodiments of the present application provide a video editing method and device, and relate to the technical field of video editing. The method comprises: obtaining at least one media content; performing content understanding on the at least one media content respectively to obtain content description information of each media content; determining a video editing link according to the content description information of each media content; the video editing link comprises at least one video editing function and an execution order between each video editing function; and performing video editing on the at least one media content through the video editing link to obtain a video editing result corresponding to the at least one media content. The embodiments of the present application are used to reduce the time cost and operation complexity of video creation.

Description

Technical Field

[0001] This application relates to the field of video editing technology, and in particular to a video editing method and apparatus. Background Technology

[0002] With the trend of intelligent multimedia content creation, using large-scale artificial intelligence (AI) models for video editing has become a cutting-edge trend in the industry.

[0003] Currently, video editing apps' AI-powered video creation features numerous independent tool entry points based on scenarios such as daily sharing and product promotion. However, users' creative motivations are not fixed or singular. The same user may have diverse needs at different times. This scenario-based functional breakdown forces users to frequently switch between different independent entry points, and the differences in the operating logic of each tool further increase the user's cognitive burden. This design contradicts the original intention of AI technology to lower the barrier to entry and improve creative efficiency. Users not only need to learn multiple sets of interaction rules, but also experience interruptions in the creative process due to the fragmentation of functional modules, increasing time costs and operational complexity. Summary of the Invention

[0004] In view of this, embodiments of this application provide a video editing method and apparatus to reduce the time cost and operational complexity of video creation.

[0005] To achieve the above objectives, the technical solutions provided in this application are as follows:

[0006] In a first aspect, embodiments of this application provide a video editing method, including:

[0007] Obtain at least one media content;

[0008] Perform content understanding on each of the at least one media content to obtain content description information for each media content;

[0009] The video editing chain is determined based on the content description information of each media content; the video editing chain includes at least one video editing function and the execution order between each video editing function;

[0010] The video editing process is used to edit the at least one media content to obtain the video editing result corresponding to the at least one media content.

[0011] As an optional implementation of this application, the step of determining the video editing link based on the content description information of each media content includes:

[0012] Obtain editorial intent based on the content description information of each media outlet;

[0013] Perform feature statistics on the content description information of various media to obtain media feature information;

[0014] The video editing chain is determined based on the editing intent and the media feature information.

[0015] As an optional implementation of this application, the step of determining the video editing link based on the content description information of each media content includes:

[0016] The content description information of each media content is input into a pre-trained editing intent prediction model, and the editing intent output by the editing intent prediction model is obtained.

[0017] As an optional implementation of this application, determining the video editing link based on the editing intent and the media feature information includes:

[0018] The editing intent and the media feature information are input into a pre-trained link routing model, and the link identifier output by the link routing model is obtained;

[0019] The video editing link is determined based on the link identifier.

[0020] As an optional implementation of this application, before determining the video editing link based on the editing intent and the media feature information, the method further includes:

[0021] Obtain the intent description information and video theme corresponding to the editing intent;

[0022] The intent description information and the video theme are displayed;

[0023] Receive feedback information from the user regarding the intent description information and / or the video topic;

[0024] The editing intent is updated based on the feedback information.

[0025] As an optional implementation of this application, updating the editing intent based on the feedback information includes:

[0026] The content description information of each media content, the editing intent, and the feedback information are input into the editing intent prediction model, and the updated editing intent output by the editing intent prediction model is obtained.

[0027] As an optional implementation of this application, the step of determining the video editing link based on the content description information of each media content includes:

[0028] Perform feature statistics on the content description information of each media content in the media content set to obtain media feature information;

[0029] The media feature information and the content description information of each media content are input into the pre-trained link prediction model, and the first link identifier output by the link prediction model is received.

[0030] The video editing link is determined based on the first link identifier.

[0031] As an optional implementation of this application, the method further includes:

[0032] Receive the editing intent corresponding to the video editing link output by the link prediction model;

[0033] Obtain the intent description information and video theme corresponding to the editing intent;

[0034] The intent description information and the video theme are displayed;

[0035] Receive user feedback on the intent description information and / or the video topic;

[0036] The video editing process is redefined based on the feedback information.

[0037] As an optional implementation of this application, the step of re-determining the video editing link based on the feedback information includes:

[0038] The feedback information, the first link identifier, the editing intent input, and the media feature information are fed into the link prediction model, and the second link identifier output by the link prediction model is obtained.

[0039] The video editing link is determined based on the second link identifier.

[0040] Secondly, this application provides a video editing device, including:

[0041] A media content acquisition unit is used to acquire at least one piece of media content.

[0042] A media content understanding unit is used to perform content understanding on the at least one media content respectively to obtain content description information of each media content;

[0043] The editing link determination unit is used to determine the video editing link based on the content description information of each media content; the video editing link includes at least one video editing function and the execution order between each video editing function;

[0044] The video editing unit is used to perform video editing on the at least one media content through the video editing link to obtain the video editing result corresponding to the at least one media content.

[0045] As an optional implementation of this application, the editing link determination unit is specifically used to obtain the editing intent based on the content description information of each media content; perform feature statistics on the content description information of each media content to obtain media feature information; and determine the video editing link based on the editing intent and the media feature information.

[0046] As an optional implementation of this application, the editing link determination unit is specifically used to input the content description information of each media content into a pre-trained editing intent prediction model, and obtain the editing intent output by the editing intent prediction model.

[0047] As an optional implementation of this application, the editing link determination unit is specifically used to input the editing intention and the media feature information into a pre-trained link routing model, and obtain the link identifier output by the link routing model;

[0048] The video editing link is determined based on the link identifier.

[0049] As an optional implementation of this application, the editing link determination unit is further configured to: obtain intent description information and video theme corresponding to the editing intent before determining the video editing link based on the editing intent and the media feature information; display the intent description information and the video theme; receive feedback information from the user on the intent description information and / or the video theme; and update the editing intent based on the feedback information.

[0050] As an optional implementation of this application, the editing link determination unit is specifically used to input the content description information of each media content, the editing intent, and the feedback information into the editing intent prediction model, and obtain the updated editing intent output by the editing intent prediction model.

[0051] As an optional implementation of this application, the editing link determination unit is specifically used to perform feature statistics on the content description information of each media content in the media content set to obtain media feature information; input the media feature information and the content description information of each media content into a pre-trained link prediction model, and receive the first link identifier output by the link prediction model; and determine the video editing link based on the first link identifier.

[0052] As an optional implementation of this application, the editing link determination unit is further configured to receive the editing intent corresponding to the video editing link output by the link prediction model; obtain the intent description information and video theme corresponding to the editing intent; display the intent description information and the video theme; receive user feedback information on the intent description information and / or the video theme; and re-determine the video editing link based on the feedback information.

[0053] As an optional implementation of this application, the editing link determination unit is specifically used to input the feedback information, the first link identifier, the editing intent, and the media feature information into the link prediction model, and obtain the second link identifier output by the link prediction model; and determine the video editing link based on the second link identifier.

[0054] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor, wherein the memory is used to store a computer program and the processor is used to cause the electronic device to implement the video editing method described in any of the above embodiments when executing the computer program.

[0055] Fourthly, embodiments of this application provide a computer-readable storage medium that, when executed by a computing device, causes the computing device to implement the video editing method described in any of the above embodiments.

[0056] Fifthly, embodiments of this application provide a computer program product that, when run on a computer, enables the computer to implement the video editing method described in any of the above embodiments.

[0057] The video editing method provided in this application, after acquiring at least one media content, first performs content understanding on each media content to obtain content description information for each media content; then, it determines a video editing link based on the content description information of each media content, and performs video editing on the at least one media content through the video editing link to obtain a video editing result corresponding to the at least one media content. Since the video editing method provided in this application can acquire the content description information of each media content, automatically determine the video editing link based on the content description information of each media content, and perform video editing on the media content through the determined video editing link to obtain a video editing result, users only need to select media content when editing videos, without needing to select AI-generated video functions or learn the rules of different AI-generated video interaction functions. Therefore, this application embodiment can reduce the time cost and operational complexity of video creation. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0059] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings that need to be called in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flowchart illustrating the steps of the video editing method provided in this application embodiment;

[0061] Figure 2 This is one of the interactive flowcharts of the video editing method provided in the embodiments of this application;

[0062] Figure 3 The second interactive flowchart of the video editing method provided in the embodiments of this application;

[0063] Figure 4 This is a schematic diagram of the structure of the video editing device provided in the embodiments of this application;

[0064] Figure 5 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0065] To better understand the above-mentioned objectives, features, and advantages of this application, the solution of this application will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0066] Many specific details are set forth in the following description in order to provide a full understanding of this application, but this application may also be implemented in other ways different from those described herein. Obviously, the embodiments in the specification are only some embodiments of this application, and not all embodiments.

[0067] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0068] This application provides a video editing method, the execution subject of which can be a video editing device. (Refer to...) Figure 1 As shown, the video editing method includes the following steps S11 to S14:

[0069] S11. Obtain at least one media content.

[0070] The media content in this application embodiment can be any type of media content, such as: pictures, videos, audio, text, animation, etc., and the at least one media content obtained can include multiple media content of the same type, or multiple types of media content. This application embodiment does not limit this.

[0071] It should be noted that, since videos typically involve large amounts of data, when the at least one media content includes video, frame extraction can be performed on the video first, and only the extracted frames can be used as media content. This reduces data transmission and processing pressure and improves interaction efficiency. Frame extraction can include extracting representative keyframes from the video. For example, this could involve extracting frames at fixed intervals, or based on content change detection, extracting video frames where the content change exceeds a preset threshold.

[0072] In some embodiments, the video editing method provided in this application is executed by a client device, and the acquisition of at least one media content includes: in response to a user's media content selection operation, acquiring the at least one media content.

[0073] In other embodiments, the video editing method provided in this application is executed by a server, and the acquisition of at least one media content includes: receiving the at least one media content sent by a client device.

[0074] S12. Perform content understanding on each of the at least one media content to obtain content description information for each media content.

[0075] In some embodiments, content understanding is performed on the at least one media content to obtain content description information for each media content, including: inputting the at least one media content into a pre-trained media content understanding model and obtaining the content description information of each media content output by the media content understanding model.

[0076] In some embodiments, the content description information of media content may include two parts: key phrases and metadata. The key phrases describe the content contained in the media, while the metadata represents the metadata information of the media content.

[0077] For example, when the media content is an image or video, the key phrases in the content description information of the media content can be as follows:

[0078] Detailed Description: The exhibition depicts a woman watching the sunset at the beach. The background is a beautiful sunset, with the sun slowly setting, the sky displaying a gradient of orange and other colors, and the calm sea reflecting the sunset's glow. There is a rock on the right side of the image, and the silhouette of the woman's profile on the left.

[0079] Keywords: sunset, seaside, rocks, evening glow, woman;

[0080] Filming location: AAA;

[0081] Types: Landscape photography, portrait photography, natural landscapes.

[0082] For example, when the media content is an image or video, the metadata in the content description information of the media content may include:

[0083] Identification number: 12345;

[0084] Type: Video;

[0085] ID in the resource server: 12121;

[0086] Duration: 1200ms;

[0087] Width: 720;

[0088] Height: 1080.

[0089] S13. Determine the video editing process based on the content description information of each media item.

[0090] The video editing chain includes at least one video editing function and the execution order of the various video editing functions.

[0091] The video editing chain in this application embodiment refers to the editing process obtained by a series of orderly processing steps and logical combinations from the original media content to the final product during the video editing process. For example, video editing functions may include: super resolution, noise reduction, editing, special effects addition, audio processing, color grading, adding subtitles, etc.

[0092] In some embodiments, determining the video editing link based on the content description information of each media content includes: selecting a video editing link that matches the content description information of each media content from the pre-configured video editing links corresponding to the AI-generated video function.

[0093] It should be noted that the video editing links determined based on the content description information of each media content can be one or multiple. When multiple video editing links are determined based on the content description information of each media content, the at least one media content can be edited separately through multiple video editing links to obtain multiple video editing results. Alternatively, one video editing link can be selected from the multiple video editing links to edit the at least one media content to obtain a single video editing result. The selection of a video editing link from multiple video editing links can be achieved by using a video editing link selection algorithm or by user selection.

[0094] S14. Perform video editing on the at least one media content through the video editing link to obtain the video editing result corresponding to the at least one media content.

[0095] When the execution entity of the video editing method is a server, the video editing method further includes: the client device sending the video editing result.

[0096] The video editing method provided in this application, after acquiring at least one media content, first performs content understanding on each media content to obtain content description information for each media content; then, it determines a video editing link based on the content description information of each media content, and performs video editing on the at least one media content through the video editing link to obtain a video editing result corresponding to the at least one media content. Since the video editing method provided in this application can acquire the content description information of each media content, automatically determine the video editing link based on the content description information of each media content, and perform video editing on the media content through the determined video editing link to obtain a video editing result, users only need to select media content when editing videos, without needing to select AI-generated video functions or learn the rules of different AI-generated video interaction functions. Therefore, this application embodiment can reduce the time cost and operational complexity of video creation.

[0097] As an extension and refinement of the above embodiments, this application provides another video editing method, referring to... Figure 2 As shown, this video editing method includes the following steps:

[0098] S201. The client device responds to the user's media content selection operation and obtains at least one media content.

[0099] In some embodiments, the client device acquires at least one media content, including: determining whether the media content selected by the user includes a video file; if not, using each media content selected by the user as the at least one media content; if so, extracting frames from the video file and using the extracted frames from the video file and other types of media content selected by the user as the at least one media content.

[0100] S202, The client device sends at least one type of media content to the server.

[0101] Accordingly, the server receives at least one type of media content sent by the client device.

[0102] S203. The server performs content understanding on each of the at least one media content to obtain content description information for each media content.

[0103] S204. The server obtains the editing intent based on the content description information of each media content.

[0104] It should be noted that the server can obtain one or more editing intents based on the content description information of each media content. When the server obtains multiple editing intents based on the content description information of each media content, subsequent steps can be executed separately for each editing intent to obtain multiple video editing results.

[0105] In some embodiments, the server obtains the editing intent based on the content description information of each media content, including: inputting the content description information of each media content into a pre-trained editing intent prediction model, and obtaining the editing intent output by the editing intent prediction model.

[0106] S205. The server parses the editing intent and obtains the intent description information and video theme corresponding to the editing intent.

[0107] In some embodiments, the server parses the editing intent to obtain the intent description information and video theme corresponding to the editing intent, including: inputting the editing intent into the intent parsing model and obtaining the intent description information and video theme corresponding to the editing intent output by the intent parsing model.

[0108] For example, the intent parsing model can be a Large Language Model (LLM).

[0109] The intent description information in this application embodiment can be the user's editing intent described in natural language. For example, the intent description information and video theme corresponding to the editing intent can be: Spring camping theme, highlighting the relaxed atmosphere of natural scenery and interaction with friends.

[0110] S206. The server sends the intent description information and video theme corresponding to the editing intent to the client device.

[0111] Accordingly, the client device receives the intent description information and video theme corresponding to the editing intent sent by the video editing device.

[0112] S207. The client device displays the intent description information and video theme corresponding to the editing intent.

[0113] S208. The client device receives feedback information from the user regarding the intent description information and / or the video topic input.

[0114] After the client device displays the intent description information and video theme corresponding to the editing intent, the user can see the intent description information and video theme corresponding to each predicted editing intent. If the intent description information and / or video theme do not match their own editing needs, they can edit the intent description information and / or video theme of the editing intent and generate feedback information on the input of the intent description information and / or video theme based on the editing operation.

[0115] It should be noted that when there are multiple editing intents, the server parses each editing intent separately, obtains the intent description information and video theme corresponding to each editing intent, and sends the intent description information and video theme corresponding to all editing intents to the client device. The client device will also display the intent description information and video theme corresponding to each editing intent. Users can input feedback information on the intent description information and / or video theme corresponding to one or more editing intents that are displayed.

[0116] S209. The client device sends the feedback information to the server.

[0117] Accordingly, the server receives the feedback information sent by the client device.

[0118] When there are multiple editing intentions, identification information corresponding to the editing intentions can be added to the feedback information, so that the server can determine the editing intention corresponding to the feedback information based on the identification information.

[0119] S210. The server updates the editing intent based on the feedback information.

[0120] It should be noted that, in some embodiments, after the video editing device updates the target editing intent based on the feedback information, it can further return to step S205 to parse the updated target editing intent, and send the parsed intent description information and video theme to the client device until the client device sends confirmation information to the video editing device.

[0121] In some embodiments, updating the editing intent based on the feedback information includes: inputting the content description information of each media content, the editing intent, and the feedback information into the editing intent prediction model, and obtaining the updated editing intent output by the editing intent prediction model.

[0122] S211. The server performs feature statistics on the content description information of each media content to obtain media feature information.

[0123] For example, media characteristic information may include: the average duration, duration distribution, total duration, average size, and other information of each media content in the media content collection.

[0124] S212. The server determines the video editing link based on the editing intent and the media feature information.

[0125] In some embodiments, the server determines the video editing link based on the editing intent and the media feature information, including: inputting the editing intent and the media feature information into a pre-trained link routing model and obtaining the link identifier output by the link routing model; and determining the video editing link based on the link identifier.

[0126] In some embodiments, the implementation of the link routing model outputting link identifiers based on the editing intent and the media feature information may include: determining whether the total duration of the media content is greater than a first threshold duration or less than a second threshold duration; if the total duration of the media content is greater than the first threshold duration, then outputting the link identifier corresponding to the first link; if the total duration of the media content is less than the second threshold duration, then outputting the link identifier corresponding to the second link; if the total duration of the media content is greater than or equal to the second threshold duration and less than or equal to the first threshold duration, then outputting the link identifier corresponding to the link matching the editing intent.

[0127] S213. The server performs video editing on the at least one media content through the video editing link to obtain the video editing result corresponding to the at least one media content.

[0128] S214. The server sends the video editing result to the client device.

[0129] Accordingly, the client device receives the video editing results sent by the server.

[0130] It should be noted that, in this embodiment of the application, the server can send the at least one video to the client device in the following ways: the server can directly send the at least one video to the client device through the data transmission link between the server and the client device, or the server can send the at least one video to the resource distribution server, obtain the unique address identifier of each video, and send the unique address identifier of each video to the client, and the client device can obtain each video from the resource distribution server according to the unique address identifier of each video.

[0131] It should also be noted that when there are multiple video editing links, since the video editing time of different video editing links is different, the video editing link with shorter time can send the corresponding video editing result to the client device immediately after obtaining the corresponding video editing result, without having to wait for all video editing links to obtain the corresponding video editing result before sending it to the client device.

[0132] S215. The client device displays the editing results.

[0133] In some embodiments, Figure 2 The editing intent prediction model, intent parsing model, and link routing model in the illustrated embodiments can all be models deployed on a server. The server can call the relevant models through the model call interface to achieve the relevant functions.

[0134] In some embodiments, Figure 2 In the illustrated embodiment, at least one of the editing intent prediction model, intent parsing model, and link routing model is a model deployed on another server. The server interacts with the server that deploys the relevant model to achieve the relevant function through the relevant model.

[0135] In other embodiments, the edit intent prediction model, intent parsing model, and link routing model can also be models deployed on the client device. Figure 2 In the illustrated embodiment, there are no longer steps that require interaction with the server. For example, the client device no longer needs to execute step S202 to send the at least one media content to the server. However, the principle and implementation of the client device executing other steps are similar to the principle and implementation of the server executing each step. To avoid redundancy, they will not be repeated here.

[0136] As an extension and refinement of the above embodiments, this application also provides another video editing method, referring to... Figure 3 As shown, this video editing method includes the following steps:

[0137] S301. The client device responds to the user's media content selection operation and obtains at least one media content.

[0138] S302, The client device sends at least one type of media content to the server.

[0139] Accordingly, the server receives at least one type of media content sent by the client device.

[0140] S303. The server performs content understanding on each of the at least one media content to obtain content description information for each media content.

[0141] The specific implementation of steps S301 to S303 can be referred to steps S201 to S203 above. To avoid redundancy, they will not be described in detail here.

[0142] S304. The server performs feature statistics on the content description information of each media content to obtain media feature information.

[0143] The specific implementation of step S304 can be referred to step S211 above. To avoid redundancy, it will not be described in detail here.

[0144] S305. The server inputs the media feature information and the content description information of each media content into the pre-trained link prediction model, and receives the first link identifier output by the link prediction model and the editing intent corresponding to the video editing link identified by the first link identifier.

[0145] S306. The server parses the editing intent and obtains the intent description information and video theme corresponding to the editing intent.

[0146] Similarly, the server can parse the editing intent using an intent understanding model to obtain the intent description information and video theme corresponding to the editing intent.

[0147] S307. The server sends the intent description information and the video theme to the client device.

[0148] Accordingly, the client device receives the intent description information and video topic sent by the server.

[0149] S308. The client device displays the intent description information and the video theme.

[0150] S309. The client device receives feedback information from the user regarding the intent description information and / or the video topic input.

[0151] S310, The client device sends the feedback information to the server.

[0152] Accordingly, the server receives the feedback information sent by the client device.

[0153] S311. The server inputs the feedback information, the link identifier of the first video editing link, the editing intent, and the media feature information into the link prediction model, and obtains the second link identifier output by the link prediction model and the editing intent corresponding to the video editing link identified by the second link identifier.

[0154] Similarly, after the server inputs the feedback information, the link identifier of the first video editing link, the editing intent, and the media feature information into the link prediction model, and obtains the second link identifier output by the link prediction model and the editing intent corresponding to the video editing link identified by the second link identifier, it can further return to step S306 to parse the editing intent corresponding to the re-determined video editing link, obtain the intent description information and video theme corresponding to the editing intent, and send the parsed intent description information and video theme to the client device until the client device sends confirmation information to the video editing device.

[0155] S312. The server determines the video editing link based on the second link identifier.

[0156] S313. The server performs video editing on the at least one media content through the video editing link to obtain the video editing result corresponding to the at least one media content.

[0157] S314. The server sends the video editing result to the client device.

[0158] S315. The client device displays the video editing results.

[0159] Based on the same inventive concept, as an implementation of the above method, this application also provides a video editing device. This embodiment corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the video editing device in this embodiment can implement all the contents of the aforementioned method embodiment.

[0160] This application provides a video editing device. Figure 4 This is a schematic diagram of the structure of the video editing device, such as... Figure 4 As shown, the video editing device 400 includes:

[0161] Media content acquisition unit 41 is used to acquire at least one type of media content;

[0162] The media content understanding unit 42 is used to perform content understanding on the at least one media content respectively to obtain content description information of each media content;

[0163] The editing link determination unit 43 is used to determine the video editing link based on the content description information of each media content; the video editing link includes at least one video editing function and the execution order between each video editing function;

[0164] The video editing unit 44 is used to perform video editing on the at least one media content through the video editing link to obtain the video editing result corresponding to the at least one media content.

[0165] As an optional implementation of this application, the editing link determination unit 43 is specifically used to obtain the editing intent based on the content description information of each media content; perform feature statistics on the content description information of each media content to obtain media feature information; and determine the video editing link based on the editing intent and the media feature information.

[0166] As an optional implementation of this application, the editing link determination unit 43 is specifically used to input the content description information of each media content into a pre-trained editing intent prediction model, and obtain the editing intent output by the editing intent prediction model.

[0167] As an optional implementation of this application, the editing link determination unit 43 is specifically used to input the editing intention and the media feature information into a pre-trained link routing model, and obtain the link identifier output by the link routing model; and determine the video editing link based on the link identifier.

[0168] As an optional implementation of this application, the editing link determination unit 43 is further configured to: obtain intent description information and video theme corresponding to the editing intent before determining the video editing link based on the editing intent and the media feature information; display the intent description information and the video theme; receive feedback information from the user on the intent description information and / or the video theme; and update the editing intent based on the feedback information.

[0169] As an optional implementation of this application, the editing link determination unit 43 is specifically used to input the content description information of each media content, the editing intent, and the feedback information into the editing intent prediction model, and obtain the updated editing intent output by the editing intent prediction model.

[0170] As an optional implementation of this application, the editing link determination unit 43 is specifically used to perform feature statistics on the content description information of each media content in the media content set to obtain media feature information; input the media feature information and the content description information of each media content into a pre-trained link prediction model, and receive the first link identifier output by the link prediction model; and determine the video editing link based on the first link identifier.

[0171] As an optional implementation of this application, the editing link determination unit 43 is further configured to receive the editing intent corresponding to the video editing link output by the link prediction model; obtain the intent description information and video theme corresponding to the editing intent; display the intent description information and the video theme; receive user feedback information on the intent description information and / or the video theme; and re-determine the video editing link based on the feedback information.

[0172] As an optional implementation of this application, the editing link determination unit 43 is specifically used to input the feedback information, the first link identifier, the editing intent, and the media feature information into the link prediction model, and obtain the second link identifier output by the link prediction model; and determine the video editing link based on the second link identifier.

[0173] The video editing device provided in this application embodiment can execute the video editing method provided in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0174] Based on the same inventive concept, embodiments of this application also provide an electronic device. Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application, such as... Figure 5 As shown, the electronic device provided in this embodiment includes a memory 501 and a processor 502. The memory 501 is used to store computer programs, and the processor 502 is used to execute the video editing method provided in the above embodiment when executing the computer programs.

[0175] Based on the same inventive concept, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the computing device to implement the video editing method provided in the above embodiments.

[0176] Based on the same inventive concept, this application also provides a computer program product that, when run on a computer, enables the computing device to implement the video editing method provided in the above embodiments.

[0177] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0178] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0179] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0180] Computer-readable media include both permanent and non-permanent, removable and non-removable storage media. Storage media can store information using any method or technology; the information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A video editing method, characterized in that, include: Obtain at least one media content; Perform content understanding on each of the at least one media content to obtain content description information for each media content; The video editing chain is determined based on the content description information of each media content; the video editing chain includes at least one video editing function and the execution order between each video editing function; The video editing process is used to edit the at least one media content to obtain the video editing result corresponding to the at least one media content.

2. The method according to claim 1, characterized in that, The process of determining the video editing chain based on the content description information of each media content includes: Obtain editorial intent based on the content description information of each media outlet; Perform feature statistics on the content description information of various media to obtain media feature information; The video editing chain is determined based on the editing intent and the media feature information.

3. The method according to claim 2, wherein determining the video editing link based on the content description information of each media content includes: The content description information of each media content is input into a pre-trained editing intent prediction model, and the editing intent output by the editing intent prediction model is obtained.

4. The method according to claim 2, characterized in that, Determining the video editing link based on the editing intent and the media feature information includes: The editing intent and the media feature information are input into a pre-trained link routing model, and the link identifier output by the link routing model is obtained; The video editing link is determined based on the link identifier.

5. The method according to claim 2, characterized in that, Before determining the video editing chain based on the editing intent and the media feature information, the method further includes: Obtain the intent description information and video theme corresponding to the editing intent; The intent description information and the video theme are displayed; Receive feedback information from the user regarding the intent description information and / or the video topic; The editing intent is updated based on the feedback information.

6. The method according to claim 5, characterized in that, The step of updating the editing intent based on the feedback information includes: The content description information of each media content, the editing intent, and the feedback information are input into the editing intent prediction model, and the updated editing intent output by the editing intent prediction model is obtained.

7. The method according to claim 1, characterized in that, The process of determining the video editing chain based on the content description information of each media content includes: Perform feature statistics on the content description information of each media content in the media content set to obtain media feature information; The media feature information and the content description information of each media content are input into the pre-trained link prediction model, and the first link identifier output by the link prediction model is received. The video editing link is determined based on the first link identifier.

8. The method according to claim 7, characterized in that, The method further includes: Receive the editing intent corresponding to the video editing link output by the link prediction model; Obtain the intent description information and video theme corresponding to the editing intent; The intent description information and the video theme are displayed; Receive user feedback on the intent description information and / or the video topic; The video editing process is redefined based on the feedback information.

9. The method according to claim 8, characterized in that, The step of re-determining the video editing link based on the feedback information includes: The feedback information, the first link identifier, the editing intent, the media feature information, and the media feature information are input into the link prediction model, and the second link identifier output by the link prediction model is obtained; The video editing link is determined based on the second link identifier.

10. A video editing device, characterized in that, include: A media content acquisition unit is used to acquire at least one piece of media content. A media content understanding unit is used to perform content understanding on the at least one media content respectively to obtain content description information of each media content; The editing link determination unit is used to determine the video editing link based on the content description information of each media content; the video editing link includes at least one video editing function and the execution order between each video editing function; The video editing unit is used to perform video editing on the at least one media content through the video editing link to obtain the video editing result corresponding to the at least one media content.

11. An electronic device, characterized in that, include: A memory and a processor, the memory being used to store a computer program and the processor being used to cause the electronic device to implement the video editing method according to any one of claims 1-9 when executing the computer program.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a computing device, causes the computing device to implement the video editing method according to any one of claims 1-9.

13. A computer program product, characterized in that, When the computer program product is run on a computer, the computer enables the computer to implement the video editing method according to any one of claims 1-9.

Images