Video generation method, video generation device, storage medium and electronic equipment

Abstract

The embodiment of the invention relates to a video generation method, a video generation device, a storage medium and electronic equipment, and relates to the technical field of video processing. The method comprises the steps of providing one or more first images matched with audio content of a first audio in response to a first preset instruction for the first audio; determining at least part of audio clips from the first audio as second audio; and displaying a target video generated by the second audio and the first image. According to the invention, the target video can be quickly and conveniently generated according to the first audio.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of video processing technology. More specifically, the embodiments of the present disclosure relate to a video generating method, a video generating device, a computer-readable storage medium, and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no description herein is admitted to be prior art by inclusion in this section.

[0003] With the widespread use of images, audio and video in various application scenarios, in some scenarios, users often have the need to edit or clip videos. For example, in order to meet personal preferences or sharing needs, users can clip a video that matches an audio clip. In the prior art, in order to obtain the video, users usually need to search, retrieve, or browse locally the audio-related images or videos and other content to collect materials and then perform video editing. However, this method has a high degree of operational complexity, requires a high level of user ability to use editing tools, and takes a long time. Therefore, how to simply, conveniently and quickly generate related videos based on audio is a problem that needs to be solved in the prior art. Summary of the invention

[0004] Currently, the operation of generating video content based on audio content is relatively complex and less user-friendly.

[0005] Therefore, there is a great need for a video generation method that can simply, conveniently and quickly generate relevant videos based on audio.

[0006] In this context, embodiments of the present disclosure are intended to provide a video generating method, a video generating device, a computer-readable storage medium, and an electronic device.

[0007] According to a first aspect of the present disclosure, a video generation method is provided, comprising: in response to a first preset instruction for a first audio, providing one or more first images matching the audio content of the first audio; determining at least a partial audio segment from the first audio as a second audio; and displaying a target video generated by the second audio and the first image.

[0008] In an exemplary embodiment, in response to a first preset instruction for a first audio, providing one or more first images matching the audio content of the first audio includes: in response to a sharing instruction for the first audio, providing multiple candidate sharing forms; in response to selecting a video sharing form from the multiple candidate sharing forms, providing one or more first images matching the audio content of the first audio.

[0009] In an exemplary embodiment, providing one or more first images matching the audio content of the first audio includes: determining one or more key audio segments according to the audio content of the first audio; and generating the first image according to the audio content of the key audio segments.

[0010] In an exemplary embodiment, extracting at least a portion of the audio segment from the first audio as the second audio includes: using the key audio segment as the second audio, or combining a plurality of the key audio segments to form the second audio.

[0011] In an exemplary embodiment, in response to a first preset instruction for a first audio, providing one or more first images matching the audio content of the first audio includes: in response to the first preset instruction for the first audio, displaying a video editing interface; the video editing interface includes a video track, and the video track corresponds to the timeline of the first audio; acquiring the first image corresponding to a key audio segment in the first audio; determining a time period of the key audio segment in the timeline based on the key audio segment, and displaying the first image in an area on the video track corresponding to the time period.

[0012] In an exemplary embodiment, in response to a first preset instruction for a first audio, providing one or more first images that match the audio content of the first audio includes: in response to the first preset instruction for the first audio, displaying a video editing interface, and displaying one or more first images that match the audio content of the first audio in the video editing interface.

[0013] In an exemplary embodiment, the video editing interface includes a video track, which corresponds to the timeline of a first audio; the first audio includes one or more audio clips; displaying one or more first images matching the audio content of the first audio in the video editing interface includes: acquiring a first image corresponding to each of the audio clips in the first audio; determining a first time period of the audio clip in the timeline based on the audio clip, and displaying the first image in an area on the video track corresponding to the first time period.

[0014] In an exemplary embodiment, the method also includes: replacing at least part of the first image in response to a second preset instruction in the video editing interface; and displaying the target video generated by the second audio and the first image includes: displaying the target video generated by the second audio and the replaced first image.

[0015] In an exemplary embodiment, the video editing interface includes a video track, and the first image is displayed on the video track; the replacing of at least part of the first image in response to a second preset instruction in the video editing interface includes: responding to an image selection instruction for the video track, selecting the first image to be replaced displayed on the video track, and providing an image replacement control; and replacing the first image to be replaced in response to a trigger instruction for the image replacement control.

[0016] In an exemplary embodiment, the first audio includes one or more audio clips, and the first image corresponds to the audio clips; the replacing of the first image to be replaced in response to a trigger instruction for the image replacement control includes: in response to a trigger instruction for the image replacement control, replacing the first image to be replaced with other images corresponding to the audio clip corresponding to the first image to be replaced, or replacing the first image to be replaced with an image selected from an image library.

[0017] In an exemplary embodiment, determining at least a partial audio segment from the first audio as the second audio includes: in response to a third preset instruction in the video editing interface, determining at least a partial audio segment from the first audio as the second audio.

[0018] In an exemplary embodiment, the video editing interface includes a video track and a video selection window located on the video track; the step of responding to a third preset instruction in the video editing interface and determining at least a portion of an audio segment from the first audio as the second audio comprises: adjusting a relative position relationship between the video track and the video selection window in response to a move instruction for at least one of the video track and the video selection window; determining a corresponding second time period on the video track according to the video selection window, and determining an audio segment of the second time period from the first audio as the second audio.

[0019] In an exemplary embodiment, the displaying of the target video generated by the second audio and the first image includes: determining, based on the second time period, from the first image a second image that matches the audio content of the second time period; and displaying the target video generated by the second audio and the second image.

[0020] In an exemplary embodiment, the first image corresponds to a first time period on the video track; and determining, based on the second time period, from the first image a second image that matches the audio content of the second time period includes: taking a first image corresponding to the first time period that intersects with the second time period as the second image.

[0021] In an exemplary embodiment, the video editing interface includes a video track and a video selection window located on the video track, and the first image is displayed on the video track; the response to a third preset instruction in the video editing interface, determining at least a partial audio segment from the first audio as the second audio, includes: in response to a move instruction for at least one of the video track and the video selection window, adjusting the relative position relationship between the video track and the video selection window; determining the second audio according to a second time period corresponding to the video selection window on the video track, and determining the first image located in the video selection window as the second image; the display of the target video generated by the second audio and the first image includes: displaying the target video generated by the second audio and the second image.

[0022] In an exemplary embodiment, the display of the target video generated by the second audio and the second image includes: if the number of the second image is one, playing the second audio and displaying the second image; if the number of the second image is multiple, playing the second audio and displaying the second images in sequence according to the third time period corresponding to the second image in the second audio.

[0023] In an exemplary embodiment, the video editing interface includes a preview area; the method further includes: in response to a video preview instruction, playing a current preview video in the preview area according to current editing information edited in the video editing interface.

[0024] In an exemplary embodiment, the method further includes: displaying a target first image among the first images in the preview area before receiving the video preview instruction or after playing the current preview video.

[0025] In an exemplary embodiment, displaying the target video generated by the second audio and the first image includes: publishing sharing information about the first audio, wherein the sharing information includes the target video generated by the second audio and the first image.

[0026] In an exemplary embodiment, providing one or more first images matching the audio content of the first audio includes: converting the audio content of the first audio into text information; identifying semantic information of the text information, and generating one or more first images matching the semantic information.

[0027] According to a second aspect of the present disclosure, a video generating device is provided, comprising: a first image providing module, used to provide one or more first images matching the audio content of the first audio in response to a first preset instruction for the first audio; a second audio determining module, used to determine at least a partial audio segment from the first audio as the second audio; and a target video display module, used to display a target video generated by the second audio and the first image.

[0028] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the video generation method of the first aspect and possible implementation methods thereof are implemented.

[0029] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the video generation method of the above-mentioned first aspect and its possible implementation method by executing the executable instructions.

[0030] In the scheme of the present disclosure, on the one hand, a new video generation method is proposed, which can generate a target video including a second audio and a first image according to a first image matching the audio content of the first audio and a second audio determined according to the first audio in response to a first preset instruction for the first audio. The video generation process does not require the user to search and find video materials. Compared with the prior art, the efficiency and convenience of video generation are improved, the time cost of video generation is reduced, and the user operation is highly friendly, which can provide users with a better video generation experience; on the other hand, in this exemplary embodiment, the first image used to generate the target video is matched based on the audio content of the first audio, which ensures that the generated target video has a high correlation with the first audio and improves the accuracy of video generation; on the other hand, in actual applications, this exemplary embodiment can generate corresponding target videos according to different first audios, realize the generation of diversified videos in a simple and convenient manner, and the generated video content has a high adaptability to the audio and has a wide range of application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram showing a system architecture in this exemplary embodiment.

[0032] Figure 2 A flowchart of a video generation method in this exemplary embodiment is shown.

[0033] Figure 3 A schematic diagram showing a video editing interface in this exemplary embodiment.

[0034] Figure 4 A schematic diagram showing another video editing interface in this exemplary embodiment.

[0035] Figure 5 A schematic diagram showing the structure of the editing area in the present exemplary embodiment.

[0036] Figure 6 A schematic diagram showing an editing area in this exemplary embodiment.

[0037] Figure 7 A schematic diagram showing an image replacement control in this exemplary embodiment.

[0038] Figure 8 to Figure 12 A schematic diagram of an interface in a video generation and sharing process in this exemplary implementation is shown.

[0039] Fig.13 An interactive flow chart of the video generation method in this exemplary embodiment is shown.

[0040] Fig.14 A schematic structural diagram of a video generating device in this exemplary embodiment is shown.

[0041] Fig.15 A schematic structural diagram of an electronic device in this exemplary embodiment is shown.

[0042] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0043] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0044] The embodiments of the present disclosure may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0045] The principle and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure. SUMMARY OF THE INVENTION

[0047] The inventors have found that when faced with the need to generate corresponding videos based on audio, the relevant technology often requires users to collect video materials by themselves, and perform video editing based on the audio and video materials to obtain the edited video. This method requires users to spend a long time and has high requirements on user operation.

[0048] In view of the above, the present disclosure provides a video generation method, a video generation device, a computer-readable storage medium and an electronic device. On the one hand, a new video generation method is proposed, which can generate a target video including a second audio and a first image according to a first image matching the audio content of the first audio and a second audio determined according to the first audio in response to a first preset instruction for a first audio. The video generation process does not require the user to search and find the video material. Compared with the prior art, the video generation efficiency and convenience are improved, the time cost of video generation is reduced, and the user operation is more friendly, which can provide users with a better video generation experience; on the other hand, in this exemplary embodiment, the first image used to generate the target video is matched based on the audio content of the first audio, which ensures that the generated target video has a high correlation with the first audio, and improves the accuracy of video generation; on the other hand, in practical applications, this exemplary embodiment can generate corresponding target videos according to different first audios, and realize the generation of diversified videos in a simple and convenient way, and the generated video content has a high adaptability to the audio, and has a wide range of application scenarios.

[0049] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0050] Application Scenario Overview

[0051] It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0052] The embodiments of the present disclosure can be applied to related scenarios of generating videos based on audio, such as generating adapted videos for audio of audio novels, etc. The application scenarios are described in detail below in conjunction with the system architecture.

[0053] Figure 1A schematic diagram of a system architecture of a video generation method is shown. The system architecture includes a user terminal 110 and a server 120. The user terminal 110 can be an electronic device such as a computer, a mobile phone, and a server. The server 120 can generate a matching first image based on the audio content of the first audio, and determine a key audio segment from the first audio to determine the second audio. The user can input a first preset instruction for the first audio on the user terminal 110. In response to the operation of the user 120, the user terminal 110 can display a video generated based on the second audio and the first image. The video can be a target video, and the user can also edit the video to obtain the target video.

[0054] Exemplary Methods

[0055] An exemplary embodiment of the present disclosure provides a video generation method. Figure 2 As shown, the method may include steps S210 to S230. Figure 2 Provide detailed instructions for each step.

[0056] refer to Figure 2 In step S210, in response to a first preset instruction for a first audio, one or more first images matching the audio content of the first audio are provided.

[0057] The first audio may be an audio to be processed, which may be any type of audio with audio content, such as an audio novel, a radio drama or music, etc. The first audio may be the original audio that has not been edited or otherwise processed, or may be the audio that has been preliminarily processed, such as the audio that has been denoised and effectively edited, etc. The present disclosure does not specifically limit this. The audio content refers to the content included in the first audio, which may be used to reflect the meaning or information included in the first audio. The audio content may be all the text information corresponding to the first audio, or may be extracted key semantic information, etc.

[0058] The first image refers to an image used to generate the target video. The first image matches the audio content, that is, it can be adapted to the audio content. For example, if a radio drama includes a dialogue between character A and character B, a first image matching character A and a first image matching character B can be provided. The first image matching the audio content of the first audio can be one or more images. For example, if an audio segment as a whole describes a scene, a picture matching the scene as a whole can be regarded as a first image matching the audio content of the first audio; or

[0059] The first audio includes audio clips corresponding to multiple scene dialogues, and each audio clip has one or more images corresponding to the scene dialogue. Then, multiple first images may match the audio content of the first audio. It should be noted that when a certain audio clip corresponds to multiple images, the image used to generate the target video can be used as the first image, and the image not used to generate the target video can be used as other images corresponding to the audio clip, which can be used to replace the first image. In other embodiments, the user can also use a custom image to replace the first image, such as downloading a specified image from the Internet or replacing the first image with an image in the local gallery, and so on.

[0060] The first preset instruction may be an interactive instruction input by the user. For example, when the user wishes to generate a first image related to the first audio or wishes to generate a target video based on the first audio, the user may perform specific operations in the display interface, such as clicking on options such as "video generation" and "video sharing" in the audio playback display interface. The first preset instruction may also be an instruction for generating the first image automatically triggered by a system program. That is, in this exemplary embodiment, one or more first images matching the audio content of the first audio may be provided based on the user's interactive operation, or the system may automatically provide one or more first images matching the audio content of the first audio to provide an image basis for generating the target video.

[0061] Step S220: determine at least a portion of the audio segment from the first audio as the second audio.

[0062] The second audio may be an audio determined based on the first audio for generating the target video. In this exemplary embodiment, at least a portion of the audio segments may be determined from the first audio as the second audio, for example, a certain audio segment in the first audio may be used as the second audio, a plurality of adjacent or non-adjacent audio segments in the first audio may be combined as the second audio, or the entire first audio may be used as the second audio, etc.

[0063] The second audio may be determined automatically by the system, or by user operation, or jointly by the system and the user. For example, the system may select one or more important audio segments from the audio content of the first audio as the second audio; or the user may make a selection or interception operation in the first audio to use at least part of the selected or intercepted audio segment as the second audio; or the system may first determine a portion of the audio from the first audio, and the user may then make a selection or interception in this portion of the audio to determine the second audio, etc. The present disclosure does not make any specific limitations on this.

[0064] In one implementation, determining at least a portion of the audio segment from the first audio as the second audio may include:

[0065] Obtain user interaction statistics at various time points in the first audio, and determine at least a portion of audio segments from the first audio as the second audio based on the user interaction statistics.

[0066] Among them, user interaction statistics may be data obtained based on statistics of users' interactive operation behaviors, such as the total number of likes, total number of comments, total number of shares, etc. corresponding to each time point. The user interaction statistics may reflect the user popularity at each time point in the first audio. Based on the user interaction statistics, at least part of the audio clips are determined from the first audio. This may be part of the audio whose user interaction statistics meet preset conditions determined from the first audio. For example, when the number of user comments or likes is high, it indicates that the corresponding clip is more likely to attract users' attention and has higher popularity. Therefore, the audio clip whose user interaction statistics exceed a preset threshold may be used as the second audio. The second audio thus determined may be more in line with the preferences of most users for the first audio.

[0067] Step S230: displaying a target video generated by the second audio and the first image.

[0068] Finally, this exemplary embodiment can generate a target video based on the second audio and the first image, that is, the target video can be composed of the second audio and the first image. When the first image is one image, the target video can be to display the one first image while playing the second audio. When the first image is multiple images, the target video can be to display multiple first images in sequence according to a preset order and a preset time interval while playing the second audio.

[0069] Before displaying the target video generated by the second audio and the first image, a preview video can be displayed in the display interface first, and the user can edit the preview video in the preview interface according to actual needs, and then display the edited video as the target video. After generating the target video, the user can also perform other interactive operations to realize the application of the target video, such as "share or forward", "status posting", "save", etc.

[0070] In an exemplary embodiment, in response to the first preset instruction for the first audio, providing one or more first images matching the audio content of the first audio may include:

[0071] In response to a sharing instruction for the first audio, providing a plurality of candidate sharing forms;

[0072] In response to selecting a video sharing format from among a plurality of candidate sharing formats, one or more first images matching the audio content of the first audio are provided.

[0073] The candidate sharing form refers to a sharing method that can be executed by the user, such as a video sharing form, a text sharing form, a picture sharing form, etc. In this exemplary embodiment, when a user's sharing instruction for the first audio is received, a plurality of candidate sharing forms for the first audio can be provided to the user, and the user can determine the sharing method of the first audio by selecting the candidate sharing form. When it is determined that the user selects the video sharing form, it means that the generation of the video requires image materials, and therefore, one or more first images matching the audio content of the first audio can be provided to the user.

[0074] In an exemplary embodiment, providing one or more first images matching the audio content of the first audio may include:

[0075] Determining one or more key audio segments according to the audio content of the first audio;

[0076] A first image is generated according to the audio content of the key audio segment.

[0077] Generally, audio can be composed of multiple audio clips, and the multiple audio clips may include important clips, such as the highlight clips in the first audio, or hot clips that are more likely to be popular or concerned by users, such as clips with a large number of listeners, clips with a large number of shares, clips with a large number of comments, clips with a large number of likes, etc.; they may include non-important clips, for example, in the audio of a dialogue between multiple characters, the clips describing the scene can be regarded as non-important clips, in the audio of an audio novel with a few core characters as the main characters, the content that passers-by or supporting characters say that is irrelevant to the main characters can be regarded as non-important clips, or the silent clips in the dialogue intervals between multiple characters can be regarded as non-important clips, etc. The importance of a specific clip is related to factors such as specific audio content or character attributes. The basis for determining important clips of different audios is different. Multiple audio clips may also include non-hot clips, such as clips with a low number of listeners, clips with a low number of shares, clips with a low number of comments, clips with a low number of likes, etc. The first audio may include one or more key audio clips. In this exemplary embodiment, the key audio segment can be automatically determined by the system program based on the audio content. For example, by using a large language model and based on business-customized semantic features, such as emotional resonance, philosophical nature, expression of opinions and other factors, semantic information can be extracted from the first audio, and key semantic content can be identified based on the semantic information. The audio segment corresponding to the key semantic content can be used as the key audio segment.

[0078] In this exemplary embodiment, first images matching the audio content of each key audio clip can be provided respectively, wherein each key audio clip corresponds to one or more matching images. For example, a key audio clip describing a scene can match one image related to the scene, or can match multiple images related to the scene, and so on. The image that matches the key audio clip and is used to generate the target video can be used as the first image.

[0079] In an exemplary embodiment, extracting at least a portion of the audio segment from the first audio as the second audio may include:

[0080] The key audio segment is used as the second audio, or a plurality of key audio segments are combined to form the second audio.

[0081] In this exemplary embodiment, after determining the key audio clip, the system can directly use the key audio clip as the second audio, or combine the key audio clips to obtain the second audio, wherein the key audio clips can be combined in a specific order, for example, according to the time sequence of the key audio clips in the first audio, or according to the category of the key audio clips, combining key audio clips of the same category together, such as combining key audio clips of character dialogues, combining key audio clips of scene descriptions, etc., and finally combining the whole, etc. The present disclosure does not make specific limitations on this.

[0082] In an exemplary embodiment, in response to a first preset instruction for a first audio, providing one or more first images matching the audio content of the first audio may include:

[0083] In response to a first preset instruction for a first audio, displaying a video editing interface; the video editing interface includes a video track, and the video track corresponds to a time axis of the first audio;

[0084] Acquire a first image corresponding to a key audio segment in the first audio;

[0085] According to the key audio segment, a time period of the key audio segment in the timeline is determined, and a first image is displayed in an area corresponding to the time period on the video track.

[0086] The video editing interface refers to an interface for performing video editing, and the video track may include a first image for generating a target video. In this exemplary embodiment, the video track may correspond to the time axis of the first audio, that is, a time axis corresponding to the entire first audio may be generated, for example, if the entire first audio is 1 minute, then the time axis = 60 seconds.

[0087] This exemplary embodiment can obtain a first image corresponding to a key audio segment in the first audio, and determine the time period of the key audio segment in the timeline based on the key audio segment, and display the first image in the area corresponding to the time period on the video track. For example, two key audio segments are determined from the 60s first audio, namely, the first key audio segment 00:00-00:20 and the second key audio segment 00:30-00:40. The first images corresponding to the first key audio segment and the second key audio segment can be determined, and then the corresponding time periods 00:00-00:20 and 00:30-00:40 on the timeline are determined, the first image corresponding to the first key audio segment is displayed in the time period 00:00-00:20, and the first image corresponding to the second key audio segment is displayed in the time period 00:30-00:40. Other time periods may be blank, black or others, and the present disclosure does not make specific limitations on this.

[0088] In an exemplary embodiment, in response to the first preset instruction for the first audio, providing one or more first images matching the audio content of the first audio may include:

[0089] In response to a first preset instruction for the first audio, a video editing interface is displayed, and one or more first images matching the audio content of the first audio are displayed in the video editing interface.

[0090] The video editing interface refers to a display interface provided to users for performing video editing functions, such as Figure 3 As shown, the image, audio or other functional options for generating the target video can be displayed in the video editing interface. Figure 4 Shows Figure 3 A schematic diagram indicating various areas within the video editing interface is shown. In this exemplary embodiment, the video editing interface may include a navigation area 410 for displaying a project name, etc., a video preview area 420 for displaying a preview video, and an editing area 430 for editing and adjusting video, audio and other content.

[0091] When the first preset instruction is received, a video editing interface can be displayed in the graphical user interface, and one or more first images matching the audio content of the first audio can be displayed in the video editing interface. The one or more first images can be used to generate the target video, and displaying the one or more first images matching the audio content of the first audio can be displaying the first images in the video editing interface in the form of a preview.

[0092] In an exemplary embodiment, the video editing interface includes a video track, the video track corresponds to the timeline of the first audio; the first audio includes one or more audio clips;

[0093] Displaying one or more first images matching the audio content of the first audio in the video editing interface may include:

[0094] Acquire a first image corresponding to each audio segment in the first audio;

[0095] According to the audio clip, a first time period of the audio clip in the timeline is determined, and a first image is displayed in an area corresponding to the first time period on the video track.

[0096] exist Figure 3 A video editing interface shown may include a video track in area A, and a timeline corresponding to the first audio in the video track. The timeline may correspond to the entire first audio. For example, if the first audio is 60s, the timeline is also 60s. The first audio may include one or more audio clips. The audio clips are clips used to constitute the complete first audio. The multiple audio clips may include key audio clips or non-key audio clips. This exemplary embodiment can obtain the first image corresponding to each audio segment in the first audio, for example, the audio segment when character A speaks corresponds to the first image of character A, the audio segment when character B speaks corresponds to the first image of character B, etc., and then the first time period of each audio segment in the timeline can be determined according to the audio segment. For example, the first audio segment is 00:00-00:15, the second audio segment is 00:15-00:25, and the third audio segment is 00:25-00:60, then it can be determined that the first time period includes 00:00-00:15, 00:15-00:25, and 00:25-00:60. Further, the first image can be displayed in the area corresponding to the first time period on the video track, for example, the first image corresponding to the first audio segment is displayed in the first time period 00:00-00:15, the first image corresponding to the second audio segment is displayed in the first time period 00:15-00:25, and the first image corresponding to the third audio segment is displayed in the first time period 00:25-00:60, etc.

[0097] In addition, it should be noted that when a first time period includes a first image, this first image can be repeatedly played when the audio clip in the first time period is played; when a first time period includes multiple first images, multiple first images can be played according to a preset strategy when the audio in the first time period is played, such as playing the first images in sequence with equal durations, or playing the first images with unequal durations according to other rules, etc. The present disclosure does not make specific limitations on this.

[0098] In an exemplary embodiment, the video generation method may further include:

[0099] In response to a second preset instruction in the video editing interface, replacing at least part of the first image;

[0100] The displaying of the target video generated by the second audio and the first image may include:

[0101] A target video generated by the second audio and the replaced first image is displayed.

[0102] Among them, the second preset instruction refers to an instruction for performing image replacement, which can be input by the user. For example, the user can perform a specific shortcut operation in the video editing interface, or operate options such as "Replace" and "Change Image", or perform preset operations such as single-clicking and long pressing on the first image that needs to be replaced, so as to input the second preset instruction. In this exemplary embodiment, the user can first select the first image that needs to be replaced in the video track, and then click the "Replace" option to replace the first image. The user can replace at least part of the images one by one, or can replace at least part of the images in batches, and the present disclosure does not make specific limitations on this. After replacing at least part of the first image, the target video generated by the second audio and the replaced first image can be displayed in the display interface.

[0103] In an exemplary embodiment, the video editing interface includes a video track, and the first image is displayed on the video track; in response to a second preset instruction in the video editing interface, replacing at least part of the first image may include:

[0104] In response to an image selection instruction for a video track, a first image to be replaced displayed on the video track is selected, and an image replacement control is provided;

[0105] In response to a trigger instruction for the image replacement control, the first image to be replaced is replaced.

[0106] The image selection instruction refers to an instruction for determining a first image to be replaced, and the video editing interface may include a video track, which may be located in an editing area in the video editing interface. Figure 5 The schematic diagram of the structure indication of the editing area in a video editing interface is shown. The editing area structure may include a title area 510, a timeline 520, an audio track 530, and a video track 540. The title area may display the duration, play options, and generation options of the selected target video; the timeline is used to display the audio time corresponding to the currently selected area; the audio track user displays the volume waveform corresponding to different timestamps; the video track is used to display the first image corresponding to the corresponding time period. When the duration exceeds the image width, the image may be displayed repeatedly. Figure 6As shown, a first image can be displayed in video track A, and the user can perform image selection instructions on the first image in the video track, such as single-clicking, double-clicking, or long-pressing the first image 610 to be replaced, so as to select the first image to be replaced displayed on the selected video track, and provide an image replacement control. The image replacement control refers to a control used for image replacement, which can be a control in any form such as a preset interface, a floating layer, a window, etc. When displayed, it can cover the original video editing interface, or it can be displayed in the video editing interface with a preset transparency. Then, in the image replacement control, in response to a trigger instruction for the image replacement control, the first image to be replaced is replaced, wherein the trigger instruction can be an instruction for executing image replacement of the first image to be replaced, which can be an operation for a specific option or any preset shortcut operation. For example, when in Figure 6 In the example, a preset operation is performed for a first image 610 in the video track A to input an image selection instruction, and after it is determined as the first image to be replaced, the following may be displayed: Figure 7 The display interface of the image replacement control shown in the figure can then operate the "change image" option 710 to input a trigger instruction to replace the first image to be replaced.

[0107] In an exemplary embodiment, the first audio includes one or more audio segments, and the first image corresponds to the audio segment; in response to a trigger instruction for an image replacement control, replacing the first image to be replaced may include:

[0108] In response to a trigger instruction for the image replacement control, the first image to be replaced is replaced with another image corresponding to the audio clip corresponding to the first image to be replaced, or the first image to be replaced is replaced with an image selected from an image library.

[0109] In this exemplary embodiment, the first audio includes one or more audio clips, and the first image corresponds to the audio content of the audio clip. In one embodiment, one audio clip may correspond to multiple images, wherein one or part of the images are used as the first image to generate the target video, and there are other images remaining that do not participate in the generation of the target video. When replacing the first image to be replaced, the optional replacement images may be these other images. When a trigger instruction for an image replacement control is received, the first image may be selected from other images corresponding to the audio clip corresponding to the first image to be replaced, and the first image to be replaced may be replaced. For example, multiple semantic images may be generated for each audio clip in the first audio, and the first image includes a semantic image corresponding to each audio clip. The first image to be replaced may be replaced with other semantic images.

[0110] In another embodiment, when a trigger instruction for an image replacement control is received, the first image to be replaced can be replaced with an image selected from an image library according to user preference or operation. The image library can be a local photo album or a network photo album, etc., and the present disclosure does not make specific limitations on this.

[0111] In an exemplary embodiment, determining at least a portion of the audio segment in the first audio as the second audio may include:

[0112] In response to a third preset instruction in the video editing interface, at least a partial audio segment is determined from the first audio as the second audio.

[0113] Among them, the third preset instruction can be an instruction for intercepting or selecting at least part of the audio segment from the first audio, and the third preset instruction can be a combination of one or more operations such as a drag operation, a single click operation, or a long press operation. For example, the user can determine at least part of the audio segment from the first audio as the second audio by moving a window of a preset size or adjusting the start or end position of the window. In this exemplary embodiment, the audio segment can be selected through an interval window control, which can change the size of the interval window by dragging the pull bar for selecting the start and end of the interval window. In addition, the video track can also include a play pointer, and the user can change the current play point by moving the play pointer.

[0114] In an exemplary embodiment, the video editing interface includes a video track and a video selection window located on the video track; in response to a third preset instruction in the video editing interface, determining at least a portion of the audio segment from the first audio as the second audio may include:

[0115] In response to a movement instruction for at least one of the video track and the video selection window, adjusting a relative position relationship between the video track and the video selection window;

[0116] A corresponding second time period is determined on the video track according to the video selection window, and an audio segment of the second time period is determined from the first audio as the second audio.

[0117] Among them, the video selection window refers to a window with a preset window size, which is used to frame the first image on the video track. The size of the video selection window can be used to control the length of the video content and can be determined by the starting point and the end point. The user can adjust the size of the video selection window by changing the starting point position or the end point position. In this exemplary embodiment, the initial video selection window can be determined based on the key audio segment in the first audio. For example, the system can select the time period where the key audio segment is located from the time axis where the first audio is located according to the semantic content of the first audio as the initial video selection window. That is, if the user has no other editing operations, the key audio segment determined by the system to be framed by the video selection window can be used as the second audio to generate the target video. The user can further perform editing operations on the video selection window, which can be regarded as a custom adjustment based on the key audio segment selected by the system to determine the second audio.

[0118] In this exemplary embodiment, the user can adjust the relative position relationship between the video track and the video selection window in response to the movement instructions of at least one of the video track and the video selection window. For example, the user can change the content selected in the video selection window by moving the video selection window, or move the video track so that it moves relative to the video selection window to change the content selected in the video selection window.

[0119] The second time period refers to the time period selected by the video selection window, and the content selected by the video selection window is also the content included in the target video. According to the second time period corresponding to the video selection window on the video track, an audio segment of the second time period can be determined from the first audio as the second audio. For example, if the video selection window selects the first image of the time period of 00:20 to 00:35, then 00:20 to 00:35 is the second time period. Furthermore, an audio segment of 00:20 to 00:35 can be determined from the first audio as the second audio.

[0120] In an exemplary embodiment, the displaying of the target video generated by the second audio and the first image may include:

[0121] According to the second time period, determining from the first image a second image that matches the audio content of the second time period;

[0122] A target video generated by the second audio and the second image is displayed.

[0123] The first image is an image that matches the audio content of the first audio, and the second time period is a time period selected for generating a target video, which may include a second image that matches the audio content of the second time period. In this exemplary embodiment, the second image may be determined from the first image, and a portion of the first image is used as the second image. Then, the target video may be generated based on the second audio and the second image, and the target video generated by the second audio and the second image may be displayed.

[0124] In an exemplary embodiment, the first image corresponds to a first time period on a video track; and according to the second time period, determining from the first image a second image that matches the audio content of the second time period may include:

[0125] The first image corresponding to the first time period that intersects with the second time period is used as the second image.

[0126] For example, the first time period on the video track includes 00:00-00:10, 00:10-00:20, and 00:20-00:30. Multiple first images are displayed on the video track, which may correspond to the first image a at 00:00-00:10, the first image b at 00:10-00:20, and the first image c at 00:20-00:30. The second time period is the time period selected by the video selection window, which may be 00:15-00:25. Then, the first image corresponding to the first time period that has an intersection with the second time period is used as the second image, that is, the first image b and the first image c are used as the second image. Then, the target video can be generated and displayed according to the first image b, the first image c, and the audio corresponding to the second time period 00:15-00:25.

[0127] In an exemplary embodiment, the video editing interface may include a video track, and the first image is displayed on the video track; and the step of determining at least a portion of the audio segment from the first audio as the second audio in response to a third preset instruction in the video editing interface may include:

[0128] In response to a movement instruction for at least one of the video track and the video selection window, adjusting a relative position relationship between the video track and the video selection window;

[0129] Determine the second audio according to the second time period corresponding to the video selection window on the video track, and determine the first image located in the video selection window as the second image;

[0130] The displaying of the target video generated by the second audio and the first image may include:

[0131] A target video generated by the second audio and the second image is displayed.

[0132] In this exemplary embodiment, when a move instruction for at least one of the video track and the video selection window is received, the relative position relationship between the video track and the video selection window is adjusted, and the content selected in the video selection window can be adjusted at this time, and the second audio is determined according to the second time period corresponding to the video selection window on the video track, for example, the audio segment corresponding to the second time period selected by the video selection window on the video track is used as the second audio, and at the same time, the first image located in the video selection window is determined as the second image, and further, the target video is generated and displayed according to the second audio and the second image. In the above manner, this exemplary embodiment can be used without separately determining the second audio and the second image according to different instructions, but when a move instruction is received, the second audio and the second image can be determined at the same time, and the target video generated by the second audio and the second image can be displayed, which can reduce the user's operation complexity, simplify the operation process, and improve the efficiency of generating the target video.

[0133] In an exemplary embodiment, the displaying of the target video generated by the second audio and the second image may include:

[0134] If the number of the second image is one, play the second audio and display the second image;

[0135] If there are multiple second images, the second audio is played, and the second images are displayed in sequence according to the third time period corresponding to the second image in the second audio.

[0136] If the number of the second image is one, when displaying the target video generated by the second audio and the second image, the second image may be displayed while the second audio is being played. For example, one second image may be repeatedly displayed within the time period of playing the second audio.

[0137] If there are multiple second images, when displaying the target video generated by the second audio and the second image, the second images may be displayed in sequence according to the third time period corresponding to the second image in the second audio when the second audio is played. The third time period is the time period after the intersection of the first time period corresponding to the second image and the second time period. For example, if the first time period originally corresponding to a certain image in the video track is 10s-15s, and the second audio intercepted by the user is 0-12s, then the third time period corresponding to the image is 10-12s.

[0138] In an exemplary embodiment, the video editing interface includes a preview area; the video generation method may further include:

[0139] In response to the video preview instruction, the current preview video is played in the preview area according to the current editing information edited in the video editing interface.

[0140] The current editing information may include information included in the video track, information included in the audio track, etc. When a video preview instruction is received, the current preview video may be played in the preview area according to the current editing information edited in the video editing interface, for example Figure 4 As shown, the current preview video can be played in the video preview area.

[0141] In an exemplary embodiment, the video generation method may further include:

[0142] Before receiving a video preview instruction, or after playing the current preview video, a target first image among the first images is displayed in the preview area.

[0143] Among them, the target first image may include the cover image, the first frame image, the last frame image, the first image corresponding to the current preview progress determined in the video track, or any frame image, etc. This exemplary embodiment can display the target first image in the first image in the preview area before receiving a video preview instruction or after playing the current preview video.

[0144] In an exemplary embodiment, the displaying of the target video generated by the second audio and the first image may include:

[0145] The sharing information about the first audio is released, where the sharing information includes a target video generated by the second audio and the first image.

[0146] This exemplary embodiment may also publish sharing information about the first audio when displaying the generated target video, and the sharing information may include the target video generated by the second audio and the first image, so as to provide users with a convenient and fast sharing experience.

[0147] In an exemplary embodiment, providing one or more first images matching the audio content of the first audio may include:

[0148] Converting the audio content of the first audio into text information;

[0149] Semantic information of the text information is identified, and one or more first images matching the semantic information are generated.

[0150] This exemplary embodiment can first convert the audio content of the first audio into text information, for example, by processing the first audio using a text-to-speech conversion model, and then generate one or more images matching the semantic information by identifying semantic information in the text information, for example, by processing the text information using a semantic analysis model or a large language model to determine the semantic information of the text information, and by processing the semantic information using a text-graph model to obtain one or more first images, and then associating the one or more first images with the first audio according to the audio content.

[0151] Figure 8 to Figure 12 A schematic diagram of a display interface in a video generation and sharing process is shown. Specifically, Figure 8 A schematic diagram of a playback interface for a first audio is shown. A user can play the first audio and browse the audio content of the first audio in the interface. A user can input a first preset instruction for the first audio in the interface, for example, click the “Share” option 810 to enter Fig. 9 The interface shown, Fig. 9 It provides multiple candidate sharing modes such as "video clip", "picture sharing", "one-click note posting", etc. When the user clicks "video clip" to confirm that the user needs to share the video, enter Fig.10 The interface shown, Fig.10 The video editing interface is shown, in which the user can edit the video, audio and other contents, and preview the currently edited video in the preview area. When the user needs to replace the first image in the video track, the user can click the first image 1010 to be replaced to jump to Fig.11 The image replacement control shown in the figure may be an image replacement floating layer. In the image replacement floating layer, the user may click the "Change Image" option 1110 to select the image to be replaced. After the image is changed, the user may return to the Fig.10 The display interface shown in the figure, then Fig.10 The preview area shows the preview video after the image is changed. When the user confirms that the video editing is complete, he can click the "Go to Generate" control to jump to Fig.12 The display interface shown publishes sharing information about the first audio, and the sharing information includes a target video generated by the second audio and the first image.

[0152] Fig.13 The interactive flow chart of a video generation method in this exemplary embodiment is shown, involving a server end 1310 and a user terminal 1320, and specifically may include the following steps:

[0153] Server 1310 executes:

[0154] Step S1311, obtaining a first audio, and converting the audio content of the first audio into text information;

[0155] Step S1312, identifying semantic information of the text information, and generating one or more first images matching the semantic information;

[0156] Step S1313, analyzing the semantic information, and determining a key audio segment from the first audio as the second audio;

[0157] The user terminal 1320 executes:

[0158] Step S1321, in response to a user inputting a first preset instruction for a first audio, providing one or more first images matching the audio content of the first audio;

[0159] Step S1322, displaying a preview video generated by the second audio and the first image;

[0160] Step S1323, in response to the user's editing instruction in the video editing interface, edit the preview video to obtain a target video;

[0161] Step S1324: in response to a publishing operation by the user, publishing sharing information about the first audio, where the sharing information includes a target video generated by the second audio and the first image.

[0162] Exemplary Devices

[0163] The exemplary embodiment of the present disclosure also provides a video generating device. Fig.14 As shown, the video generating device 1400 may include the following program modules: a first image providing module 1410, used to provide one or more first images matching the audio content of the first audio in response to a first preset instruction for the first audio; a second audio determining module 1420, used to determine at least a portion of the audio segment from the first audio as the second audio; and a target video display module 1430, used to display a target video generated by the second audio and the first image.

[0164] In one embodiment, the first image providing module 1410 includes: a candidate sharing form providing unit, used to provide multiple candidate sharing forms in response to a sharing instruction for the first audio; a first image providing unit, used to provide one or more first images matching the audio content of the first audio in response to selecting a video sharing form from multiple candidate sharing forms.

[0165] In one embodiment, the first image providing module 1410 includes: a key segment determining unit, which determines one or more key audio segments according to the audio content of the first audio; and a first image generating unit, which is used to generate a first image according to the audio content of the key audio segments.

[0166] In one implementation, the second audio determination module 1420 includes: a second audio first determination unit, configured to use a key audio segment as the second audio, or combine multiple key audio segments to form the second audio.

[0167] In one embodiment, the first image providing module 1410 includes: a video editing interface display unit, used to display a video editing interface in response to a first preset instruction for the first audio; the video editing interface includes a video track, and the video track corresponds to the time axis of the first audio; a first image acquisition unit, used to acquire a first image corresponding to a key audio clip in the first audio; a first image display unit, used to determine the time period of the key audio clip in the timeline according to the key audio clip, and display the first image in the area corresponding to the time period on the video track.

[0168] In one embodiment, the first image providing module 1410 includes: a video editing interface display unit, which is used to display a video editing interface in response to a first preset instruction for the first audio, and display one or more first images matching the audio content of the first audio in the video editing interface.

[0169] In one embodiment, a video editing interface includes a video track, which corresponds to the timeline of a first audio, and the first audio includes one or more audio clips; a video editing interface display unit includes: a first image acquisition unit, which is used to acquire a first image corresponding to each audio clip in the first audio; a first image display unit, which is used to determine a first time period of the audio clip in the timeline based on the audio clip, and display the first image in an area on the video track corresponding to the first time period.

[0170] In one embodiment, the video generating device also includes: an image replacement module, used to replace at least part of the first image in response to a second preset instruction in the video editing interface; a target video display module 1430, including: a replacement image display unit, used to display a target video generated by the second audio and the replaced first image.

[0171] In one embodiment, a video editing interface includes a video track, and a first image is displayed on the video track; an image replacement module includes: an image selection unit, which is used to respond to an image selection instruction for the video track, select the first image to be replaced displayed on the video track, and provide an image replacement control; an image replacement trigger unit, which is used to respond to a trigger instruction for the image replacement control to replace the first image to be replaced.

[0172] In one embodiment, the first audio includes one or more audio clips, and the first image corresponds to the audio clip; the image replacement trigger unit includes: an image replacement subunit, which is used to replace the first image to be replaced with other images corresponding to the audio clip corresponding to the first image to be replaced, or replace the first image to be replaced with an image selected from the image library in response to a trigger instruction for the image replacement control.

[0173] In one implementation, the second audio determination module 1420 includes: a second audio second determination unit, configured to determine at least a portion of the audio segment from the first audio as the second audio in response to a third preset instruction in the video editing interface.

[0174] In one embodiment, the video editing interface includes a video track and a video selection window located on the video track; the second audio second determination unit includes: a first move instruction response unit, used to adjust the relative position relationship between the video track and the video selection window in response to a move instruction for at least one of the video track and the video selection window; a second time period determination unit, used to determine the corresponding second time period on the video track according to the video selection window, and determine an audio segment of the second time period from the first audio as the second audio.

[0175] In one embodiment, the target video display module 1430 includes: a second image determination unit, used to determine, based on the second time period, from the first image a second image that matches the audio content of the second time period; and a target video display unit, used to display a target video generated by the second audio and the second image.

[0176] In one embodiment, the first image corresponds to a first time period on the video track; the second image determination unit includes: a second image determination subunit, which is used to use the first image corresponding to the first time period that intersects with the second time period as the second image.

[0177] In one embodiment, the video editing interface includes a video track, and the first image is displayed on the video track; the second audio second determination unit includes: a second movement instruction response unit, which is used to adjust the relative position relationship between the video track and the video selection window in response to a movement instruction for at least one of the video track and the video selection window; and determine the second audio according to the second time period corresponding to the video selection window on the video track, and determine the first image located in the video selection window as the second image; the target video display module 1430 includes: a target video display unit, which is used to display the target video generated by the second audio and the second image.

[0178] In one embodiment, the target video display unit includes: a first image playing subunit, used to play the second audio and display the second image if the number of the second image is one; a second image playing subunit, used to play the second audio if the number of the second image is multiple, and display the second images in sequence according to the third time period corresponding to the second image in the second audio.

[0179] In one embodiment, the video editing interface includes a preview area; the video generating device also includes: a preview video playing module, which is used to respond to the video preview instruction and play the current preview video in the preview area according to the current editing information edited in the video editing interface.

[0180] In one embodiment, the video generating device further includes: a target first image display module, configured to display the target first image in the first image in the preview area before receiving a video preview instruction or after playing the current preview video.

[0181] In one implementation, the target video display module 1430 includes: a sharing information publishing unit, configured to publish sharing information about the first audio, wherein the sharing information includes a target video generated by the second audio and the first image.

[0182] In one embodiment, the first image providing module 1410 includes: a text conversion unit, used to convert the audio content of the first audio into text information; a semantic recognition unit, used to recognize the semantic information of the text information and generate one or more first images matching the semantic information.

[0183] In addition, other specific details of the embodiments of the present disclosure have been described in detail in the embodiments of the above method and will not be repeated here.

[0184] Exemplary Storage Media

[0185] The exemplary embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned method of the present disclosure when the computer program is executed by a processor. The above-mentioned method can be implemented by a program product, such as a portable compact disk read-only memory (CD-ROM) and including program code, and can be run on a device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0186] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0187] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0188] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RE, etc., or any suitable combination of the foregoing.

[0189] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0190] Exemplary Electronic Devices

[0191] The exemplary embodiment of the present disclosure also provides an electronic device, which may be Figure 1 Any device in the present invention. The electronic device includes a processor and a memory, and the memory is used to store executable instructions of the processor. The processor is configured to execute the above method of the present invention by executing the executable instructions.

[0192] refer to Fig.15 An electronic device according to an exemplary embodiment of the present disclosure is described. Fig.15 The electronic device 1500 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0193] like Fig.15 As shown, the electronic device 1500 is in the form of a general computing device. The components of the electronic device 1500 may include, but are not limited to: at least one processing unit 1510, at least one storage unit 1520, and a bus 1530 connecting different system components (including the storage unit 1520 and the processing unit 1510).

[0194] The storage unit stores program codes, which can be executed by the processing unit 1510, so that the processing unit 1510 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 1510 can perform the following steps: Figure 2 The method steps shown, etc.

[0195] The storage unit 1520 may include a volatile storage unit, such as a random access storage unit (RAM) 1521 and / or a cache storage unit 1522 , and may further include a read-only storage unit (ROM) 1523 .

[0196] The storage unit 1520 may also include a program / utility 1524 having a set (at least one) of program modules 1525, such program modules 1525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0197] The bus 1530 may include a data bus, an address bus, and a control bus.

[0198] The electronic device 1500 may also communicate with one or more external devices 1600 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), and such communication may be performed via an input / output (I / O) interface 1540. The electronic device 1500 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 1550. As shown, the network adapter 1550 communicates with other modules of the electronic device 1500 via a bus 1530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0199] It should be noted that, although several modules or submodules of the device are mentioned in the above detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0200] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0201] Although the spirit and principle of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A video generation method, characterized in that: include: In response to a first preset instruction for a first audio, providing one or more first images matching the audio content of the first audio; Determine at least a portion of the audio segment from the first audio as the second audio; A target video generated by the second audio and the first image is displayed.

2. The method according to claim 1, characterized in that The providing, in response to a first preset instruction for a first audio, one or more first images matching the audio content of the first audio, comprises: In response to a sharing instruction for the first audio, providing a plurality of candidate sharing forms; In response to selecting a video sharing format from among the plurality of candidate sharing formats, one or more first images matching the audio content of the first audio are provided.

3. The method according to claim 1, characterized in that The providing one or more first images matching the audio content of the first audio comprises: Determining one or more key audio segments according to the audio content of the first audio; The first image is generated according to the audio content of the key audio segment.

4. The method according to claim 3, characterized in that: The step of extracting at least part of the audio segment from the first audio as the second audio comprises: The key audio segment is used as the second audio, or a plurality of the key audio segments are combined to form the second audio.

5. The method according to claim 3, characterized in that: The providing, in response to a first preset instruction for a first audio, one or more first images matching the audio content of the first audio, comprises: In response to a first preset instruction for a first audio, displaying a video editing interface; the video editing interface includes a video track, and the video track corresponds to a time axis of the first audio; Acquire the first image corresponding to the key audio segment in the first audio; According to the key audio segment, a time period of the key audio segment in the timeline is determined, and the first image is displayed in an area corresponding to the time period on the video track.

6. The method according to claim 1, characterized in that The providing, in response to a first preset instruction for a first audio, one or more first images matching the audio content of the first audio, comprises: In response to a first preset instruction for a first audio, a video editing interface is displayed, and one or more first images matching the audio content of the first audio are displayed in the video editing interface.

7. The method according to claim 6, characterized in that The video editing interface includes a video track, and the video track corresponds to the time axis of the first audio; the first audio includes one or more audio clips; The displaying, in the video editing interface, one or more first images matching the audio content of the first audio includes: Acquire a first image corresponding to each of the audio segments in the first audio; According to the audio clip, a first time period of the audio clip in the timeline is determined, and the first image is displayed in an area corresponding to the first time period on the video track.

8. A video generating device, characterized in that: include: A first image providing module, configured to provide one or more first images matching the audio content of the first audio in response to a first preset instruction for the first audio; A second audio determination module, configured to determine at least a portion of an audio segment from the first audio as a second audio; A target video display module is used to display a target video generated by the second audio and the first image.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

Images