CN118828141A - Video processing method, device, electronic device and storage medium - Google Patents

Abstract

The present disclosure relates to a video processing method, device, electronic device and storage medium, and belongs to the field of Internet technology. The method includes: displaying a first video clip on a video interface; in response to a request for continuation of the first video clip, displaying a first continuation text, the first continuation text is used to describe the content that the continued video clip needs to contain; in response to a modification operation on the first continuation text, modifying all words associated with the modification operation in the first continuation text to obtain a second continuation text; based on the first video clip and the second continuation text, generating a second video clip, the content of the second video clip is a continuation of the content of the first video clip, and the content of the second video clip is consistent with the content of the second continuation text. Since the continuation text can be modified in its entirety with one click, there is no need to search for the words to be modified one by one for manual modification, which can save operation time, improve modification efficiency, and improve the overall efficiency of the continuation video.

Description

Video processing method, device, electronic device and storage medium

Technical Field

The present disclosure relates to the field of Internet technology, and in particular to a video processing method, device, electronic device and storage medium.

Background Art

With the development of multimedia technology, more and more video applications have emerged. People can post videos on video applications and watch videos posted by others.

In related technologies, people can usually shoot videos by themselves, or use text-generated video technology to intelligently generate videos. However, if the content of the video is not rich enough, it is impossible to continue based on the content of the video, and they can only reshoot or generate a new video. Therefore, there is an urgent need for a solution to continue the video.

Summary of the invention

The present disclosure provides a video processing method, device, electronic device and storage medium, which can improve the convenience and efficiency of video processing.

According to one aspect of an embodiment of the present disclosure, a video processing method is provided, the method comprising:

Displaying a first video clip on a video interface;

In response to a request for continuing the first video segment, displaying a first continuation text, where the first continuation text is used to describe the content that the continued video segment needs to include;

In response to a modification operation on the first continued text, all words in the first continued text associated with the modification operation are modified to obtain a second continued text;

A second video segment is generated based on the first video segment and the second continuation text, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text.

Optionally, in response to the modification operation on the first continued text, all words associated with the modification operation in the first continued text are modified to obtain the second continued text, including:

Displaying a display area of multiple event elements, and displaying words belonging to the event elements in the first continued text in the display area of the event elements;

In response to a modification operation on a word in a display area of a target event element, obtaining a modified first word, wherein the target event element is any one of the multiple event elements;

All words belonging to the target event element in the first continuation text are replaced with the first words to obtain the second continuation text.

Optionally, in response to the modification operation on the first continued text, all words associated with the modification operation in the first continued text are modified to obtain the second continued text, including:

In response to a modification operation on a second word in the first continuation text, obtaining a modified third word;

All words in the first continued text that are identical to the second word are replaced with the third word to obtain the second continued text.

Optionally, the method further comprises:

If the content of the second continuation text does not match the content of the first video clip, a prompt message is displayed, where the prompt message is used to prompt that the content of the second continuation text does not match the content of the first video clip.

Optionally, the video interface further displays a progress bar of the first video segment; if the content of the second continuation text does not match the content of the first video segment, displaying a prompt message includes:

If the content of the second continuation text does not match the content of the target time period in the first video clip, the area corresponding to the target time period on the progress bar of the first video clip is highlighted to indicate that the content of the second continuation text does not match the content of the target time period.

Optionally, the video interface further displays a content text of the first video clip, where the content text is used to describe the content of the first video clip; if the content of the second continuation text does not match the content of the first video clip, displaying a prompt message includes:

If the content of the second continuation text does not match the content of the target segment in the content text, the target segment in the content text is highlighted to indicate that the content of the second continuation text does not match the content of the target segment.

Optionally, displaying the first continuation text includes any one of the following:

Continuing to write the content text of the first video clip to obtain the first continuation text, where the content text is used to describe the content of the first video clip;

Based on the text editing operation in the video interface, the first continuation text is obtained.

Optionally, the method further comprises:

Displaying a duration input area on the video interface, and acquiring the continuation duration based on an input operation in the duration input area; or acquiring the continuation duration based on a text length of the second continuation text;

The step of generating a second video segment based on the first video segment and the second continuation text includes:

Based on the first video segment, the second continuation text and the continuation duration, the second video segment is generated, the content of the second video segment is a continuation of the content of the first video segment, the content of the second video segment is consistent with the content described by the second continuation text, and the duration of the second video segment is equal to the continuation duration.

Optionally, the method further comprises:

Determine an image uploaded from a local photo album as a reference image; or determine at least one video frame among a plurality of video frames in the first video clip as the reference image;

The step of generating a second video segment based on the first video segment and the second continuation text includes:

Based on the first video segment, the second continuation text and the reference image, the second video segment is generated, the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text and the content of the reference image.

Optionally, generating a second video segment based on the first video segment and the second continuation text includes:

Acquire a content text of the first video clip, where the content text is used to describe the content of the first video clip;

The second video segment is generated based on the content text and the second continuation text.

Optionally, the method further comprises:

On the video interface, the first video clip and the second video clip are displayed in the order in which they are generated.

Optionally, the method further comprises:

Displaying an initial tag on the first video segment, where the initial tag is used to indicate that the video segment where the initial tag is located is an initial video segment;

A continuation tag is displayed on the second video segment, where the continuation tag is used to indicate that the video segment where the continuation tag is located is a continued video segment.

Optionally, the method further comprises at least one of the following:

In a case where at least one of the first video segment and the second video segment is selected, in response to a video playing operation, playing the selected at least one video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video editing operation, displaying an editing interface of the selected at least one video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video download operation, downloading the selected at least one video segment;

In the case where at least one of the first video segment and the second video segment is selected, in response to a video publishing operation, a video including the at least one selected video segment is published.

Optionally, in a case where at least one of the first video segment and the second video segment is selected, in response to a video publishing operation, publishing a video including the selected at least one video segment comprises:

In a case where the first video clip and the second video clip are selected, in response to the video publishing operation, generating a copy based on the first video clip and the second video clip;

Merging the first video segment and the second video segment into one video according to the generation order;

The video carrying the text is released; or, based on an editing operation on the text, an edited text is obtained, and the video carrying the edited text is released.

According to another aspect of the embodiments of the present disclosure, a video processing device is provided, the device comprising:

A display unit, configured to display the first video clip on the video interface;

The display unit is configured to display a first continuation text in response to a continuation request for the first video segment, wherein the first continuation text is used to describe the content that the continued video segment needs to include;

a modifying unit configured to execute, in response to a modification operation on the first continued text, modify all words in the first continued text associated with the modification operation to obtain a second continued text;

The generating unit is configured to generate a second video segment based on the first video segment and the second continuation text, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text.

Optionally, the modification unit is configured to execute:

Displaying a display area of multiple event elements, and displaying words belonging to the event elements in the first continued text in the display area of the event elements;

In response to a modification operation on a word in a display area of a target event element, obtaining a modified first word, wherein the target event element is any one of the multiple event elements;

All words belonging to the target event element in the first continuation text are replaced with the first words to obtain the second continuation text.

Optionally, the modification unit is configured to execute:

In response to a modification operation on a second word in the first continuation text, obtaining a modified third word;

All words in the first continued text that are identical to the second word are replaced with the third word to obtain the second continued text.

Optionally, the device further comprises:

The display unit is further configured to display prompt information if the content of the second continuation text does not match the content of the first video clip, wherein the prompt information is used to prompt that the content of the second continuation text does not match the content of the first video clip.

Optionally, the video interface further displays a progress bar of the first video clip; and the display unit is further configured to execute:

If the content of the second continuation text does not match the content of the target time period in the first video segment, the area corresponding to the target time period on the progress bar of the first video segment is highlighted to indicate that the content of the second continuation text does not match the content of the target time period.

Optionally, the video interface further displays content text of the first video segment, where the content text is used to describe the content of the first video segment; and the display unit is further configured to execute:

If the content of the second continuation text does not match the content of the target segment in the content text, the target segment in the content text is highlighted to indicate that the content of the second continuation text does not match the content of the target segment.

Optionally, the display unit is configured to perform any of the following:

Continuing to write the content text of the first video clip to obtain the first continuation text, where the content text is used to describe the content of the first video clip;

Based on the text editing operation in the video interface, the first continuation text is obtained.

Optionally, the device further comprises:

The display unit is configured to display a duration input area on the video interface, and obtain the continuation duration based on an input operation in the duration input area; or obtain the continuation duration based on a text length of the second continuation text;

The generating unit is configured to generate the second video segment based on the first video segment, the second continuation text and the continuation duration, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content described by the second continuation text, and the duration of the second video segment is equal to the continuation duration.

Optionally, the device further comprises:

The display unit is configured to determine an image uploaded from a local photo album as a reference image; or determine at least one video frame among a plurality of video frames in the first video clip as the reference image;

The generating unit is configured to generate the second video segment based on the first video segment, the second continuation text and the reference image, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text and the content of the reference image.

Optionally, the generating unit is configured to execute:

Acquire a content text of the first video clip, where the content text is used to describe the content of the first video clip;

The second video segment is generated based on the content text and the second continuation text.

Optionally, the device further comprises:

The display unit is configured to execute on the video interface and display the first video segment and the second video segment in a generated order.

Optionally, the device further comprises:

The display unit is configured to display an initial tag on the first video segment, where the initial tag is used to indicate that the video segment where the initial tag is located is an initial video segment;

The display unit is configured to display a continuation tag on the second video segment, where the continuation tag is used to indicate that the video segment where the continuation tag is located is a continued video segment.

Optionally, the device further comprises a control unit configured to perform at least one of the following:

In a case where at least one of the first video segment and the second video segment is selected, in response to a video playing operation, playing the selected at least one video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video editing operation, displaying an editing interface of the selected at least one video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video download operation, downloading the selected at least one video segment;

In the case where at least one of the first video segment and the second video segment is selected, in response to a video publishing operation, a video including the at least one selected video segment is published.

Optionally, the control unit is configured to execute:

In a case where the first video clip and the second video clip are selected, in response to the video publishing operation, generating a copy based on the first video clip and the second video clip;

Merging the first video segment and the second video segment into one video according to the generation order;

The video carrying the text is released; or, based on an editing operation on the text, an edited text is obtained, and the video carrying the edited text is released.

According to another aspect of the embodiments of the present disclosure, an electronic device is provided, the electronic device comprising:

processor;

a memory for storing instructions executable by the processor;

The processor is configured to execute the instructions to implement the video processing method as described in the above aspects.

According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the video processing method as described in the above aspects.

According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the video processing method as described in the above aspects is implemented.

According to the method provided by the embodiment of the present disclosure, if more content is to be continued on the basis of the first video clip, a request can be made to continue the first video clip, and the first continuation text is used to describe the content that the continued video clip needs to contain. If the user wants to modify the first continuation text, by performing a modification operation on the first continuation text, all words related to the modification operation in the first continuation text can be modified with one click, and then a second video clip after the continuation is generated based on the modified continuation text. In the present disclosure, when the user has the need to modify the continuation text, the entire text can be modified with one click, and the user does not need to search for the words to be modified one by one and modify them manually, which saves the user's operation time, improves the modification efficiency, and thus improves the overall efficiency of the continued video.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

FIG1 is a schematic diagram of an implementation environment according to an exemplary embodiment;

FIG2 is a flow chart of a video processing method according to an exemplary embodiment;

FIG3 is a flow chart of another video processing method according to an exemplary embodiment;

FIG4 is a schematic diagram of a video interface according to an exemplary embodiment;

FIG5 is a schematic diagram of another video interface according to an exemplary embodiment;

Fig. 6 is a schematic diagram showing another video interface according to an exemplary embodiment;

FIG7 is a schematic diagram showing a function introduction area according to an exemplary embodiment;

FIG8 is a schematic diagram showing a continued text editing area according to an exemplary embodiment;

FIG9 is a schematic diagram showing another type of continued text editing area according to an exemplary embodiment;

FIG10 is a schematic diagram of a display area according to an exemplary embodiment;

Fig. 11 is a schematic diagram showing a highlighted progress bar according to an exemplary embodiment;

FIG12 is a schematic diagram showing a method of highlighting a target segment according to an exemplary embodiment;

FIG13 is a schematic diagram showing a method of displaying a video clip according to an exemplary embodiment;

FIG14 is a schematic diagram showing another method of displaying video clips according to an exemplary embodiment;

Fig. 15 is a schematic diagram showing another method of displaying a video clip according to an exemplary embodiment;

FIG16 is a flowchart of another video processing method according to an exemplary embodiment;

FIG17 is a flowchart of yet another video processing method according to an exemplary embodiment;

FIG18 is a schematic diagram showing a task management interface according to an exemplary embodiment;

FIG19 is a schematic diagram showing another task management interface according to an exemplary embodiment;

FIG20 is a schematic diagram showing another task management interface according to an exemplary embodiment;

FIG21 is a schematic diagram showing a generation progress according to an exemplary embodiment;

FIG22 is a block diagram of a video processing device according to an exemplary embodiment;

FIG23 is a block diagram of another video processing device according to an exemplary embodiment;

Fig. 24 is a block diagram of an electronic device according to an exemplary embodiment.

DETAILED DESCRIPTION

In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned figure descriptions are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

It should be noted that the user information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties. The collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions. For example, the video clips, continuation information and content information involved in this disclosure are all obtained with full authorization.

Fig. 1 is a schematic diagram of an implementation environment of a video processing method according to an exemplary embodiment. Referring to Fig. 1, the implementation environment includes: a terminal 101 and a server 102. The terminal 101 can be connected to the server 102 via a wireless network or a wired network.

In the disclosed embodiment, the terminal 101 displays a first video clip, receives a continuation request for the first video clip, and obtains a continuation text. The terminal 101 then sends a continuation request for the first video clip to the server 102, and the continuation request includes the first video clip and the continuation text. In response to the continuation request, the server 102 generates a second video clip based on the first video clip and the continuation text, and returns the second video clip to the terminal 101. Then, the terminal 101 receives the second video clip and displays the second video clip to the user.

In some embodiments, the terminal 101 is installed with a target application, and the terminal 101 can implement functions such as video generation and video playback through the target application. For example, the target application is a short video application, a shopping application, a social application, or other applications, and the terminal 101 implements the video processing method provided by the embodiment of the present disclosure through the target application. Among them, the target application is associated with the server 102, and the server 102 is used to provide background services for the target application.

In some embodiments, the terminal 101 can be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, and a laptop computer.

Among them, terminal 101 may generally refer to one of multiple terminals, and the embodiment of the present disclosure is illustrated by terminal 101. Those skilled in the art can know that the number of the above terminals can be more or less. For example, the above terminals can be several, or the above terminals can be dozens or hundreds, or more. The embodiment of the present disclosure does not limit the number and device type of the terminals.

In some embodiments, server 102 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, but the embodiments of the present disclosure do not impose any restrictions on this.

In some embodiments, the server 102 undertakes the main computing work and the terminal 101 undertakes the secondary computing work; or, the server 102 undertakes the secondary computing work and the terminal 101 undertakes the main computing work; or, the server 102 and the terminal 101 adopt a distributed computing architecture to perform collaborative computing.

The video processing method provided by the embodiment of the present disclosure is applicable to any scenario of intelligently generating videos.

For example, in the scenario of Vincent video. The terminal runs a short video application, which provides the function of Vincent video, and the function of Vincent video includes the video continuation function provided by the method based on the embodiment of the present disclosure. The user first enters the content text in the short video application to obtain the first video clip intelligently generated according to the content text. For example, if the content text is "a puppy running on the grass", the picture in the first video clip is a puppy running on the grass. If the user feels that the content in the first video clip is not rich enough and wants to continue some other content based on the content in the first video clip, the video continuation function can be used to enter the first continuation text in the short video application. If the user wants to modify the first continuation text, the method provided by the embodiment of the present disclosure can be used to modify the first continuation text with one key to obtain the second continuation text, and then the second video clip is intelligently generated according to the first video clip and the second continuation text. For example, if the second continuation text is "the puppy fell down while running", the picture in the second video clip is that the puppy fell down while running, thereby obtaining a second video clip that continues the content of the first video clip.

The above scenarios are only examples. The video processing method provided in the embodiments of the present disclosure may also be applied to other scenarios, which are not limited in the embodiments of the present disclosure.

Fig. 2 is a flow chart showing a video processing method according to an exemplary embodiment, the method is executed by an electronic device, for example, the electronic device may be the terminal 101 shown in Fig. 1. Referring to Fig. 2, the method includes the following steps.

In step 201, the electronic device displays a first video clip on a video interface.

The electronic device displays a video interface, and the video interface displays a first video clip. The first video clip can be any video clip acquired by the electronic device, and the embodiment of the present disclosure does not limit the source and acquisition method of the first video clip.

Exemplarily, the first video clip may be a video clip generated based on artificial intelligence technology, such as a video clip generated based on text-generated video technology or image-generated video technology. Furthermore, the first video clip may be an initial video clip generated based on artificial intelligence technology, or may be a video clip obtained by continuing other video clips based on artificial intelligence technology.

Exemplarily, the first video clip may also be a video clip obtained by shooting, or a video clip obtained by editing, etc.

In step 202, the electronic device displays a first continuation text in response to a request for continuation of the first video segment, where the first continuation text is used to describe the content that the continued video segment needs to contain.

If the user wants to continue the first video clip, a continuation operation on the first video clip is performed to trigger a continuation request for the first video clip. In response to the continuation request, the electronic device obtains a corresponding first continuation text and displays the first continuation text. Optionally, the first continuation text can be generated based on artificial intelligence technology, or obtained based on a user's input operation.

In step 203, in response to the modification operation on the first continued text, the electronic device modifies all words in the first continued text that are associated with the modification operation to obtain a second continued text.

If the user is not satisfied with the first continued text and wants to modify the first continued text, the user can perform a modification operation on the first continued text to modify all words in the first continued text associated with the modification operation without the user having to modify each word one by one.

In step 204, the electronic device generates a second video segment based on the first video segment and the second continuation text, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text.

The electronic device generates a second video segment according to the content in the first video segment and the content described by the second continuation text. The second video segment is a video segment obtained by continuing the first video segment.

The content of the second video clip is a continuation of the content of the first video clip, that is, the content of the second video clip is expanded and added on the basis of the content of the first video clip, and is an extension or continuation of the content of the first video clip.

According to the method provided by the embodiment of the present disclosure, if more content is to be continued on the basis of the first video clip, a request can be made to continue the first video clip, and the first continuation text is used to describe the content that the continued video clip needs to contain. If the user wants to modify the first continuation text, by performing a modification operation on the first continuation text, all words related to the modification operation in the first continuation text can be modified with one click, and then a second video clip after the continuation is generated based on the modified continuation text. In the present disclosure, when the user has the need to modify the continuation text, the entire text can be modified with one click, and the user does not need to search for the words to be modified one by one and modify them manually, which saves the user's operation time, improves the modification efficiency, and thus improves the overall efficiency of the continued video.

The embodiment shown in FIG. 2 is only a brief description of the video processing method. Based on the embodiment shown in FIG. 2, the embodiment of the present disclosure further provides another video processing method. FIG. 3 is a flow chart of another video processing method according to an exemplary embodiment. The method is executed by an electronic device, for example, the electronic device may be the terminal 101 shown in FIG. 1. Referring to FIG. 3, the method includes the following steps.

In step 301, the electronic device displays a first video clip on a video interface.

In some embodiments, the first video clip is a locally stored video clip, and the first video clip can be a video clip obtained by shooting, a video clip obtained by editing, or a video clip generated and downloaded based on artificial intelligence technology. Then step 301 includes: the electronic device displays a video upload entrance on the video interface, and in response to a trigger operation on the video upload entrance, displays a local album, the local album includes at least one locally stored video clip, and in response to a trigger operation on the first video clip in the local album, displays the first video clip on the video interface.

In some embodiments, the first video clip is a video clip generated based on artificial intelligence technology in the video interface. Then step 301 includes: the electronic device displays an information editing area and a generation control in the video interface, obtains content information based on the editing operation in the information editing area, and the content information indicates the content required to be included in the video clip to be generated, generates a first video clip based on the content information in response to a triggering operation on the generation control, and displays the first video clip in the video interface. The content of the first video clip is consistent with the content indicated by the content information.

Optionally, the content information may be any type of information, for example, the content information may include text, image or audio.

Fig. 4 is a schematic diagram of a video interface according to an exemplary embodiment, and Fig. 4 takes the content information including content text as an example for display. As shown in Fig. 4, the video interface includes a first video clip 401 and content text 402, and the content text 402 belongs to the content information used to generate the first video clip 401.

Fig. 5 is a schematic diagram of another video interface according to an exemplary embodiment, and Fig. 5 takes the example of content information including a reference image for display. As shown in Fig. 5, the video interface includes a first video clip 401 and a reference image 403, and the reference image 403 belongs to the content information used to generate the first video clip 401.

Fig. 6 is a schematic diagram of another video interface according to an exemplary embodiment, and Fig. 6 takes the content information including content text and reference image as an example for display. As shown in Fig. 6, the video interface includes a first video clip 401, content text 402 and reference image 403, and the content text 402 and reference image 403 belong to the content information used to generate the first video clip 401.

In some embodiments, a short video application is running in the electronic device, and the electronic device displays a video interface in the short video application. The electronic device updates the video continuation function in the short video application. After the video continuation function in the short video application is updated, when the video interface is displayed for the first time, the continuation function introduction information is displayed on the video interface, and the continuation function introduction information is used to introduce the video continuation function in the short video application. The continuation function introduction information may include text, images, videos, etc.

Figure 7 is a schematic diagram of a function introduction area according to an exemplary embodiment. As shown in Figure 7, after the video continuation function in the short video application is updated, when the video interface is displayed for the first time, a function introduction area 701 is displayed on the video interface. The function introduction area 701 includes continuation function introduction information, an exit control and a confirmation control. The continuation function introduction information includes prompt text and a tutorial video. The tutorial video is used to introduce the video continuation function. For example, the tutorial video can show the process of using the video continuation function, etc., and "Got it" is displayed on the confirmation control.

In step 302, the electronic device displays a first continuation text in response to a request to continue the first video segment, where the first continuation text is used to describe the content that the continued video segment needs to include. The first continuation text is used to describe the content that the continued video segment needs to include.

If the user wants to continue the first video segment, a continuation operation on the first video segment is performed to trigger a continuation request for the first video segment. In response to the continuation request, the electronic device displays a first continuation text on the video interface.

In some embodiments, step 302 includes: obtaining a first continuation text based on a text editing operation in the video interface.

Optionally, the video interface displays a continuation text editing area, a text input box is displayed in the continuation text editing area, the user performs a text input operation in the text input box, and the electronic device obtains the input first continuation text based on the text input operation in the text input box.

Optionally, the text input box displays the content text of the first video clip, and the content text of the first video clip is used to describe the content in the first video clip. The content text of the first video clip can be the content text used when generating the first video clip, or the content text of the first video clip can be the content text obtained by performing content recognition on the first video clip. The electronic device obtains the edited first continuation text based on the editing operation of the content text of the first video clip. The electronic device displays the content text of the first video clip to the user, and the user can edit it based on the content text, such as continuing, deleting or modifying the content text, so as to obtain the first continuation text. Since the first continuation text is edited based on the content text, it can be considered that the first continuation text has a strong correlation with the content text.

Optionally, if the user does not perform an editing operation on the content text, the content text is directly determined as the first continuation text. That is, the content text of the first video clip can be directly used as the first continuation text.

Figure 8 is a schematic diagram of a continuation text editing area according to an exemplary embodiment. As shown in Figure 8, the video interface displays a continuation text editing area 801, and a text input box 802 and a confirmation control 803 are displayed in the continuation text editing area 801. The text input box 802 displays the content text of the first video clip "A super sports car is moving slowly in a beautiful city, and the city behind it is colorful, 8k picture quality, hyper-realistic style, cyberpunk".

Optionally, when the first video clip is generated based on the reference image, the electronic device displays a prompt text in the continuation text editing area, the prompt text is used to prompt the user to enter the continuation text according to the content of the reference image. Optionally, the continuation text editing area may also display a recommended text, which is intelligently generated based on the reference image, so that the user can edit the first continuation text based on the recommended text corresponding to the reference image.

FIG9 is a schematic diagram of another type of continuation text editing area according to an exemplary embodiment. As shown in FIG9 , the video interface displays a continuation text editing area 801, in which a text input box 802 and a confirmation control 803 are displayed. The text input box 802 displays a prompt text “Combine the picture and describe the content of the picture you want to generate” and a recommended text “For example: a super sports car, galloping in a colorful city”.

In the disclosed embodiment, the user can enter the first continuation text to describe what content is expected to be included in the video clip after the continuation, which is conducive to accurately conveying the content required to be included, thereby improving the accuracy of the generated video clip. Moreover, the content required to be included can be specified by editing the first continuation text, which is simple and flexible to operate, which is conducive to improving the convenience and flexibility of video production and reducing the cost of video production.

In addition, the content text of the first video clip is provided to the user, and the user can edit the content text of the first video clip to obtain the first continuation text. On the one hand, the user can be assisted in editing the first continuation text to avoid the situation where the user is at a loss, and a reference is provided for the user. On the other hand, since the first continuation text is edited on the basis of the content text, the correlation between the first continuation text and the content text is relatively strong, and the content text is used to indicate the content of the first video clip, and the first continuation text is used to indicate the content of the second video clip. Then, it can be ensured that the content of the second video clip is highly correlated with the first video clip, thereby improving the consistency and coherence between the continued video clip and the original video clip.

In some embodiments, step 302 includes: continuing to write the content text of the first video clip to obtain a first continuation text, where the content text is used to describe the content of the first video clip.

Optionally, the electronic device inputs the content text of the first video clip into a text continuation model, and the text continuation model continues to write the content text of the first video clip and outputs a first continuation text.

Exemplarily, the first video clip is a video clip generated based on artificial intelligence technology in the video interface. For example, in a Vincent video scene, the content text is information used to generate the first video clip. Then, the electronic device stores the content text of the first video clip, and the electronic device can directly obtain the stored content text.

Exemplarily, the first video clip in the video interface is a video clip uploaded locally. Then, the electronic device performs content recognition on the first video clip to obtain content text. For example, the electronic device performs subtitle recognition on the first video clip and uses the recognized subtitles as content text; or, the electronic device recognizes the screen of the first video clip and obtains content text for describing the screen; or, the electronic device converts the audio in the first video clip into text and uses the converted text as content text, etc.

In step 303, in response to the modification operation on the first continued text, the electronic device modifies all words in the first continued text that are associated with the modification operation to obtain a second continued text.

If the user is not satisfied with the first continued text and wants to modify the first continued text, the user can perform a modification operation on the first continued text to modify all words in the first continued text associated with the modification operation without the user having to modify each word one by one.

In some embodiments, step 303 includes: displaying a display area for multiple event elements, displaying words belonging to the event elements in the first continuation text in the display area for the event elements; obtaining the modified first word in response to a modification operation on a word in the display area for the target event element, wherein the target event element is any one of the multiple event elements; replacing all words belonging to the target event element in the first continuation text with the first word to obtain a second continuation text.

Event elements refer to the elements that constitute an event, such as time, place, subject, etc.

Exemplarily, FIG10 is a schematic diagram of a display area provided by an embodiment of the present disclosure. As shown in FIG10 , the video interface displays a display area 1001 of a time element, a display area 1002 of a location element, and a display area 1003 of a main element. The first continuation text is "In the evening, a super sports car moves slowly in a beautiful city, and the super sports car keeps passing through the road." The display area 1001 of the time element includes "evening," the display area 1002 of the location element includes "city," and the display area 1003 of the main element includes "super sports car." If the user wants to change the main body of the first continuation text from "super sports car" to "airplane," the "super sports car" in the display area 1003 of the main element is changed to "airplane." In response to the modification operation, the electronic device changes all the words belonging to the main body in the first continuation text to "airplane," and obtains the second continuation text "In the evening, a plane moves slowly in a beautiful city, and the plane keeps passing through the road."

In some embodiments, step 303 includes: in response to a modification operation on the second word in the first continuation text, obtaining a modified third word; replacing all words in the first continuation text that are identical to the second word with the third word to obtain a second continuation text.

That is, by modifying a certain word in the first continued text, all words in the first continued text that are the same as the word can be automatically modified in the same way with one click.

For example, the first continuation text is "In the evening, a super sports car moves slowly in the beautiful city, and the super sports car keeps passing through the road." If the user changes the first "super sports car" in the first continuation text to "airplane", the electronic device automatically changes the second "super sports car" in the first continuation text to "airplane", thereby obtaining the second continuation text "In the evening, a plane moves slowly in the beautiful city, and the plane keeps passing through the road."

In step 304, if the content of the second continuation text does not match the content of the first video clip, the electronic device displays a prompt message, where the prompt message is used to prompt that the content of the second continuation text does not match the content of the first video clip.

The second continuation text is used to indicate the content that the video segment obtained after the continuation of the first video segment must contain. If the content of the second continuation text does not match the content of the first video segment, it may cause the content of the video segment obtained after the continuation to be inconsistent with the content of the first video segment. In this case, the electronic device displays a prompt message to prompt the user that the content of the modified second continuation text does not match the content of the first video segment.

In some embodiments, the video interface also displays a progress bar of the first video segment. Step 304 includes: if the content of the second continuation text does not match the content of the target time period in the first video segment, highlighting the area corresponding to the target time period on the progress bar of the first video segment to indicate that the content of the second continuation text does not match the content of the target time period.

Optionally, the electronic device displays the area corresponding to the target period on the progress bar as a target color, thereby highlighting the area corresponding to the target period on the progress bar, for example, the target color is red, etc. Alternatively, the electronic device displays the area corresponding to the target period on the progress bar in a wider width, thereby highlighting the area corresponding to the target period on the progress bar.

For example, as shown in FIG11 , the content of the target time period in the first video clip is Xiao Ming holding a football, and the content of the second continuation text is Xiao Ming throwing the basketball in his hand. If the content of the second continuation text does not match the content of the target time period in the first video clip, the electronic device widens the area 1101 corresponding to the target time period on the progress bar.

In some embodiments, the video interface also displays a content text of the first video segment, and the content text is used to describe the content of the first video segment. Step 304 includes: if the content of the second continuation text does not match the content of the target segment in the content text, highlighting the target segment in the content text to indicate that the content of the second continuation text does not match the content of the target segment.

Optionally, the electronic device highlights, bolds or underlines the target segment in the content text, thereby highlighting the target segment in the content text.

For example, as shown in FIG12 , the content of the target segment in the content text 1201 is Xiao Ming holding a football, and the content of the second continuation text 1202 is Xiao Ming throwing the basketball in his hand. If the content of the second continuation text 1202 does not match the content of the target time period in the content text 1201, the electronic device will display the target segment in the content text 1201 in bold.

It should be noted that if the content of the second continuation text is consistent with the content of the first video clip, there is no need to display the prompt information, that is, there is no need to perform step 304.

In step 305, the electronic device generates a second video segment based on the first video segment and the second continuation text, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text.

After acquiring the second continuation text, the electronic device generates a second video segment according to the content in the first video segment and the content indicated by the second continuation text. The second video segment is a video segment obtained by continuing the first video segment.

In some embodiments, the video interface displays a continuation confirmation control, and the electronic device generates a second video segment based on the first video segment and the second continuation text in response to a trigger operation on the continuation confirmation control. That is, the electronic device starts executing the step of generating the second video segment in response to a trigger operation on the continuation confirmation control.

Optionally, in response to the triggering operation of the continuation confirmation control, the terminal sends a video generation request to the server, the video generation request including the video segment identifier of the first video segment and the second continuation text. The server receives the video generation request, searches for the first video segment based on the video segment identifier, generates a second video segment based on the first video segment and the second continuation text, sends the second video segment to the terminal, and the terminal receives the second video segment, thereby acquiring the second video segment that continues the first video segment.

In some embodiments, the process of generating a second video segment based on the first video segment and the second continuation text includes: inputting the first video segment and the second continuation text into a video generation model, generating the second video segment based on the first video segment and the second continuation text by the video generation model, and outputting the second video segment. The video generation model is a model trained based on artificial intelligence technology, for example, the video generation model is a large language model.

In the disclosed embodiment, a video generation model is utilized to automatically generate a second video segment that continues the first video segment based on the first video segment and the second continuation text, thereby realizing the intelligence and automation of the video generation process. There is no need for the user to manually perform editing operations, and the user only needs to upload the second continuation text used to generate the video. This simplifies user operations, lowers the threshold for video generation, and is conducive to improving the efficiency of video generation.

In some embodiments, step 305 includes: obtaining a content text of the first video segment, where the content text is used to describe the content of the first video segment; and generating a second video segment based on the content text and the second continuation text.

Optionally, the electronic device is a terminal, and the terminal sends a video generation request to the server, where the video generation request includes a video segment identifier of the first video segment and a second continuation text. The server receives the video generation request, and acquires a content text of the first video segment based on the video segment identifier of the first video segment. The server generates a second video segment based on the content text and the second continuation text, and sends the second video segment to the terminal, and the terminal receives the second video segment.

Optionally, the content text and the second continuation text of the first video clip are input into a video generation model, and the video generation model generates a second video clip based on the content text and the second continuation text of the first video clip, and outputs the second video clip.

Optionally, the method for obtaining the content text of the first video clip is related to the method for obtaining the first video clip. Exemplarily, the first video clip is a video clip generated based on artificial intelligence technology in the video interface, and the content text is information used to generate the first video clip. Then, the electronic device stores the content text of the first video clip, and the electronic device directly obtains the stored content text. Exemplarily, the first video clip in the video interface is a video clip uploaded locally. Then, the electronic device performs content recognition on the first video clip to obtain the content text.

In some embodiments, after generating the second video segment, the electronic device creates a correspondence between the second video segment and the second continuation text used to generate the second video segment, so as to indicate that the second continuation text belongs to the second video segment, and the second continuation text can indicate the content in the second video segment. The second continuation text of the second video segment can be used to continue the second video segment.

In step 306, the electronic device displays the first video segment and the second video segment on the video interface in the order in which they are generated.

After acquiring the second video segment, the electronic device displays the first video segment and the second video segment in the order of generation. Since the generation time point of the first video segment is earlier than the generation time point of the second video segment, the second video segment is displayed after the first video segment.

Since the second video clip is obtained by continuing the first video clip, displaying the second video clip after the first video clip can reflect that the content of the second video clip is a continuation of the content of the first video clip, which is conducive to highlighting the coherence and consistency between the first video clip and the second video clip.

FIG13 is a schematic diagram of displaying video clips according to an exemplary embodiment. As shown in FIG13 , the video interface displays a first video clip 401 and a second video clip 408. The second video clip 408 is displayed behind the first video clip 401, and the second video clip 408 is adjacent to the first video clip 401, that is, the second video clip 408 is displayed at the first position behind the first video clip 401. As shown in FIG4 , before the second video clip 408 is displayed, a continuation control 404 is displayed at the first position behind the first video clip 401. When the second video clip 408 is generated, the second video clip 408 is displayed at the first position behind the first video clip 401, and the continuation control 404 is moved backward by one position to ensure that the second video clip 408 is adjacent to the first video clip 401.

In the disclosed embodiment, the first video segment and the second video segment are displayed in the order of generation, so that the original video segment and the continued video segment are displayed in units of video segments, thereby decoupling the original video segment and the continued video segment, making it convenient for users to perform subsequent management and processing of the original video segment and the continued video segment respectively.

In some embodiments, the first video segment is an initial video segment, and the second video segment is a continued video segment. Then step 306 includes: displaying an initial tag on the first video segment, the initial tag is used to indicate that the video segment where the initial tag is located is the initial video segment; displaying a continued tag on the second video segment, the continued tag is used to indicate that the video segment where the continued tag is located is the continued video segment.

The initial video segment refers to a video segment that is not obtained by continuing other video segments, but is initially generated or initially shot. The continued video segment refers to a video segment that is obtained by continuing other video segments.

In the disclosed embodiment, an initial label is displayed on the first video segment, and a continuation label is displayed on the second video segment to indicate that the first video segment is the initial video segment and the second video segment is the continued video segment. This helps the user distinguish which video segment is the initial video segment and which video segment is the continued video segment, thereby improving the display effect.

In some embodiments, the first video segment is an initially generated video segment. After the second video segment is generated, it can be continued based on the multiple generated video segments to obtain the next continued video segment, and then the multiple generated video segments are displayed in the order of generation.

Exemplarily, the electronic device continues the first video clip and the second video clip to obtain the third video clip. Then, the electronic device displays the first video clip, the second video clip and the third video clip in the video interface in the order of generation. The process of the electronic device generating the third video clip includes: the electronic device obtains the second continuation information in response to the continuation request for the multiple video clips that have been generated, and generates the third video clip based on the first video clip, the second video clip and the second continuation information. The content of the third video clip is a continuation of the content of the first video clip and the second video clip, and the content of the third video clip is consistent with the content indicated by the second continuation information. Optionally, the electronic device generates the third video clip based on the content information of the first video clip, the continuation information of the second video clip and the second continuation information obtained this time. Optionally, after generating the third video clip, the electronic device creates a corresponding relationship between the third video clip and the second continuation information to indicate that the second continuation information belongs to the third video clip, and the second continuation information can indicate the content in the third video clip.

Furthermore, the electronic device continues the first video clip, the second video clip and the third video clip to obtain a fourth video clip. Then, the electronic device displays the first video clip, the second video clip, the third video clip and the fourth video clip in the video interface in the order of generation. By analogy, the electronic device can sequentially obtain multiple continued video clips, each of which is obtained by continuing the multiple video clips before the video clip.

FIG14 is a schematic diagram of another method for displaying video clips according to an exemplary embodiment. As shown in FIG14 , a first video clip 401 , a second video clip 408 , and a third video clip 409 are displayed on a video interface in the order in which they are generated, and a continuation control 404 is displayed after the multiple video clips that have been generated.

In some embodiments, when the number of the generated video clips is greater than a preset number, the preset number of video clips in the front in the generation order are displayed on the video interface, and the video interface also displays a target mark, which is used to indicate that there are still generated video clips that are not displayed in the video interface. Then, based on the sliding operation in the video interface, the electronic device replaces at least one video clip currently displayed in the video interface with at least one video clip that is not currently displayed. Alternatively, the electronic device replaces at least one video clip currently displayed in the video interface with at least one video clip that is not currently displayed in response to the triggering operation of the target mark in the video interface.

Optionally, the sum of the number of video clips displayed in the video interface and the number of continuation controls does not exceed a preset number. The continuation control is arranged at the end of the multiple video clips that have been generated. In the case where the video interface displays a preset number of video clips, the continuation control is canceled from being displayed in the video interface. The electronic device replaces at least one video clip currently displayed in the video interface with a continuation control based on a sliding operation in the video interface or in response to a triggering operation of a target mark in the video interface.

FIG15 is another schematic diagram of displaying video clips according to an exemplary embodiment, wherein the generated video clips include at least a first video clip 401, a second video clip 408, a third video clip 409 and a fourth video clip 410, and the video interface can display up to four video clips. As shown in FIG15 , the first video clip 401, the second video clip 408, the third video clip 409 and the fourth video clip 410 are displayed in the video interface in the order of generation, the continuation control is cancelled in the video interface, and a target mark 411 is also displayed on the right side of the video interface.

In some embodiments, the electronic device displays a delete control for the second video segment on the video interface, and the electronic device deletes the second video segment on the video interface in response to a triggering operation on the delete control.

Optionally, when the electronic device displays multiple generated video clips on the video interface, it also displays a deletion control for each generated video clip. In response to a triggering operation of the deletion control for any video clip, the electronic device deletes the video clip on the video interface.

For example, the electronic device first generates a first video clip, continues based on the first video clip to generate a second video clip, and continues based on the first video clip and the second video clip to generate a third video clip. The first video clip, the second video clip, and the third video clip are displayed on the video interface in the order in which they are generated. Exemplarily, if the user only wants to keep the second video clip and the third video clip, the first video clip can be deleted. Exemplarily, if the user believes that the content correlation between the first video clip and the third video clip is strong enough and does not want to keep the second video clip, but only wants to keep the first video clip and the third video clip, the second video clip can be deleted. Therefore, the process of deleting video clips will not be affected by the order in which the video clips are generated.

In the disclosed embodiment, after the video segment is continued to obtain the continued video segment, if the user is not satisfied with the continued content, the continued video segment can be deleted, which is convenient for the user to control the content quality of intelligent video creation and dynamically manage the generated video segments, thereby improving the freedom and flexibility of video processing and helping to enhance the user experience.

In the embodiment of the present disclosure, if more content is to be continued based on the first video clip, a request can be made to continue the first video clip. The first continuation text is used to describe the content that the continued video clip needs to contain. If the user wants to modify the first continuation text, by performing a modification operation on the first continuation text, all words related to the modification operation in the first continuation text can be modified with one click, and then a second video clip after the continuation is generated based on the modified continuation text. In the present disclosure, when the user has the need to modify the continuation text, the entire text can be modified with one click, without the user having to search for the words to be modified one by one and modify them manually, which saves the user's operation time, improves the modification efficiency, and thus improves the overall efficiency of the continued video.

Furthermore, the disclosed embodiment provides an intelligent solution for continuing the video, and the user can continue the video based on the original video clip according to his/her own needs, thereby improving the convenience and efficiency of video processing.

In addition, the continuation text is obtained based on user operations, so users can edit the continuation text according to their own needs, that is, they can specify what content should be included in the continued video clip, so as to flexibly continue the video content, meet the diverse creative needs of users, and enhance the freedom and flexibility of intelligent creation. Since the continuation content can be directly specified, users do not need to repeatedly perform the generation process to try to generate a satisfactory video, which improves the convenience of video processing.

Moreover, in the related art, it is impossible to continue on the basis of an existing video, and a new video can only be regenerated, and the generated video is discarded, which is cumbersome to operate and prone to doing a lot of repetitive work. However, in the embodiment of the present disclosure, after generating the first video segment, if the user wants to generate a specified video segment associated with the content of the first video segment, it is only necessary to provide a continuation text to continue on the basis of the first video segment to obtain a second video segment after the continuation. The first video segment and the second video segment can be subsequently merged into a complete video, thereby simplifying the video creation process and improving processing efficiency.

Based on the embodiment of FIG. 3 , after executing step 306 , any one of the following four operations may be performed.

First, when at least one of the first video segment and the second video segment is selected, the electronic device plays the selected at least one video segment in response to a video playing operation.

In some embodiments, the video interface displays a video playback control, and when at least one of the first video segment and the second video segment is selected, the electronic device plays the selected at least one video segment in response to a triggering operation on the video playback control.

For example, when one of the first video clip or the second video clip is selected, in response to the triggering operation of the video playback control, the electronic device plays the selected video clip. For another example, when both the first video clip and the second video clip are selected, in response to the triggering operation of the video playback control, the electronic device plays the first video clip and the second video clip in the order in which they are generated. That is, the first video clip is played first, and after the first video clip is played, the second video clip is played.

In some embodiments, the video interface displays multiple generated video clips in the order of generation, and the multiple video clips include the first video clip, the second video clip, and other video clips (such as the third video clip, the fourth video clip, etc.). When at least two video clips among the multiple video clips are selected, in response to the video play operation, the at least two selected video clips are played in the order of generation.

For example, the video interface displays the generated first video clip, the second video clip, and the third video clip in the order of generation. When the first video clip and the third video clip are selected, in response to the video playback operation, the first video clip is played first, and after the first video clip is played, the third video clip is played next. That is, even if the generation order of at least two video clips is not adjacent, the at least two non-adjacent video clips can be played sequentially to preview the connection effect between the at least two video clips that are not adjacent in generation order. It can be seen that the embodiment of the present disclosure decouples the continued video clips and displays and manages them in units of video clips, which is conducive to improving the freedom and flexibility of users to operate video clips.

Second, when at least one of the first video segment and the second video segment is selected, the electronic device displays a clipping interface of the selected at least one video segment in response to a video clipping operation.

In some embodiments, the video interface displays a video clip control, and when at least one of the first video segment and the second video segment is selected, the electronic device displays a clipping interface of the selected at least one video segment in response to a triggering operation on the video clip control. As shown in FIG. 4 , the video interface displays a video clip control 405.

For example, when one of the first video clip or the second video clip is selected, in response to the triggering operation of the video clipping control, the electronic device displays a clipping interface, the clipping interface includes the selected video clip, and the user can clip the selected video clip in the clipping interface. For another example, when the first video clip and the second video clip are selected, in response to the triggering operation of the video clipping control, the electronic device displays a clipping interface, the clipping interface includes the first video clip and the second video clip, and the user can clip the first video clip and the second video clip respectively in the clipping interface.

In some embodiments, the video interface displays multiple generated video clips in the order of generation, and the multiple video clips include the above-mentioned first video clip, the second video clip, and other video clips (such as the third video clip, the fourth video clip, etc.). When at least two video clips among the multiple video clips are selected, in response to the video editing operation, the editing interface of the at least two selected video clips is displayed. The generation order of the at least two selected video clips can be adjacent or non-adjacent.

Third, when at least one of the first video segment and the second video segment is selected, the electronic device downloads the selected at least one video segment in response to a video downloading operation.

In some embodiments, the video interface displays a video download control, and when at least one of the first video segment and the second video segment is selected, the electronic device downloads the selected at least one video segment in response to a triggering operation on the video download control. As shown in FIG4 , the video interface displays a video download control 406.

In some embodiments, when both the first video segment and the second video segment are selected, in response to a video download operation, the first video segment and the second video segment are downloaded separately, or the first video segment and the second video segment are merged into one video in the order of generation, and the merged video is downloaded.

In some embodiments, the video interface displays multiple generated video clips in the order of generation, and the multiple video clips include the above-mentioned first video clip, the second video clip, and other video clips (such as the third video clip, the fourth video clip, etc.). When at least two video clips among the multiple video clips are selected, in response to the video editing operation, the at least two selected video clips are downloaded. Optionally, the electronic device downloads the at least two video clips separately, or merges the at least two video clips into one video in the order of generation, and downloads the merged video. Among them, the generation order of the at least two selected video clips can be adjacent or non-adjacent.

Fourthly, when at least one of the first video segment and the second video segment is selected, the electronic device publishes a video including the at least one selected video segment in response to a video publishing operation.

In some embodiments, the video interface displays a video publishing control, and the electronic device, in response to a triggering operation on the video publishing control, publishes a video containing the selected at least one video segment when at least one of the first video segment and the second video segment is selected. As shown in FIG. 4 , the video interface displays a video publishing control 407.

In some embodiments, when both the first video segment and the second video segment are selected, in response to a video publishing operation, the electronic device merges the first video segment and the second video segment in the order of generation to obtain a video, and publishes the video.

Optionally, when the first video clip and the second video clip are selected, the electronic device generates a copy based on the content text of the first video clip and the continuation text of the second video clip in response to a video publishing operation, wherein the content text of the first video clip is used to indicate the content in the first video clip; merges the first video clip and the second video clip into one video in the order of generation; publishes the video carrying the copy; or, based on an editing operation on the copy, obtains the edited copy and publishes the video carrying the edited copy.

The copy is integrated and summarized on the basis of the content text and the continuation text, and the semantics of the copy are associated with the semantics of the content text and the semantics of the continuation text.

Optionally, the electronic device inputs the content text of the first video clip and the continuation text of the second video clip into a copywriting generation model, and the copywriting generation model generates a copywriting based on the content text of the first video clip and the continuation text of the second video clip. The copywriting generation model is a model trained based on artificial intelligence technology, for example, the copywriting generation model is a large language model.

In the disclosed embodiment, when publishing a video composed of a first video clip and a second video clip, a text for the video can be intelligently generated based on the content text of the first video clip and the continuation text of the second video clip. The user can use the intelligently generated text for publishing, or edit the intelligently generated text before publishing, thereby automatically providing the user with the video text or assisting the user in editing the video text, thereby improving the convenience and efficiency of determining the video text.

According to the method provided by the embodiment of the present disclosure, the user can flexibly choose to play, edit, download and publish any one of the first video segment and the second video segment, or batch select to play, edit, download and publish both the first video segment and the second video segment, thereby realizing batch management in units of video segments and improving the convenience of video management.

Moreover, in the related art, when users publish videos, there is often a time limit, for example, it is impossible to publish a video whose time is less than a specified time. In the embodiment of the present disclosure, if the time of the first video segment is insufficient, the second video segment can be obtained by continuing the first video segment, and the first video segment and the second video segment can be merged to obtain a video with coherent content and longer time, which solves the problem of insufficient time of the first video segment and meets the needs of users to share videos.

Furthermore, the disclosed embodiment decouples the continued video segments, and displays and manages the generated multiple video segments in units of video segments. In the series of video segments generated and continued, each video segment exists as an independent individual. The user can arbitrarily select one or more video segments from the generated video segments for management, such as playing, editing, downloading and publishing. The process of managing the selected one or more video segments is not restricted by the generation order, and the management process of any video segment will not be affected by other video segments, which is conducive to improving the freedom and flexibility of users in operating video segments.

Fig. 16 is a flow chart of yet another video processing method according to an exemplary embodiment. The method is executed by an electronic device. Referring to Fig. 16 , the method includes the following steps.

In step 1601, the electronic device displays a first video clip on a video interface.

In step 1602, the electronic device displays a first continuation text in response to a request for continuation of the first video segment, where the first continuation text is used to describe the content that the continued video segment needs to include.

In step 1603, in response to the modification operation on the first continued text, the electronic device modifies all words associated with the modification operation in the first continued text to obtain a second continued text.

In step 1604, the electronic device obtains the continuation duration.

In some embodiments, the electronic device displays a duration input area on the video interface, and obtains the continuation duration based on the input operation in the duration input area.

The electronic device determines the set duration based on the input operation in the duration input area, and updates the currently displayed duration to the set duration. That is, the user can flexibly control the duration of the extended video clip, further improving the flexibility and convenience of video production.

In some embodiments, the electronic device obtains the continuation duration based on the text length of the second continuation text.

Optionally, the continuation duration is positively correlated with the text length of the second continuation text. That is, the longer the text length of the second continuation text is, the longer the continuation duration is. The shorter the text length of the second continuation text is, the shorter the continuation duration is.

In some embodiments, the video interface displays a first video clip, a continuation control, and a continuation duration, and the electronic device obtains the continuation duration currently displayed on the video interface. The continuation control is used to trigger a continuation request for the video clip, and the continuation duration refers to the duration of the video clip obtained after the continuation. As shown in FIG4 , the video interface is displayed on the continuation control 404, and the continuation duration is displayed on the continuation control 404, for example, the continuation duration is 5 seconds.

In step 1605, the electronic device generates a second video segment based on the first video segment, the second continuation text and the continuation duration, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content described by the second continuation text, and the duration of the second video segment is equal to the continuation duration.

After acquiring the second continuation text, the electronic device generates a second video segment according to the content in the first video segment, the content indicated by the second continuation text, and the continuation duration.

In some embodiments, the electronic device is a terminal, and the terminal sends a video generation request to a server, and the video generation request includes a video segment identifier, a second continuation text, and a continuation duration of the first video segment. The server receives the video generation request, searches for the first video segment based on the video segment identifier, generates a second video segment based on the first video segment, the second continuation text, and the continuation duration, and sends the second video segment to the terminal, and the terminal receives the second video segment, thereby obtaining a second video segment that continues the first video segment.

In some embodiments, the first video segment, the second continuation text and the continuation duration are input into the video generation model, and the video generation model generates the second video segment based on the first video segment, the second continuation text and the continuation duration.

In some embodiments, the electronic device obtains content information of the first video segment, the content information is used to indicate the content in the first video segment, and generates a second video segment based on the content information of the first video segment, the second continuation text and the continuation duration. The method of obtaining the content information is the same as the method of obtaining the content information in step 304, which will not be repeated here.

The method provided by the embodiment of the present disclosure also provides a continuation duration when generating the second video segment, so that the duration of the continued second video segment is equal to the continuation duration, thereby accurately controlling the length of the continued video segment and ensuring that the continued video segment can be displayed within the specified duration, which is conducive to improving the controllability of the intelligent video creation process.

Fig. 17 is a flow chart of yet another video processing method according to an exemplary embodiment. The method is executed by an electronic device. Referring to Fig. 17 , the method includes the following steps.

In step 1701, the electronic device displays a first video clip on a video interface.

In step 1702, the electronic device displays a first continuation text in response to a request for continuation of the first video segment, where the first continuation text is used to describe the content that the continued video segment needs to contain.

In step 1703, in response to the modification operation on the first continued text, the electronic device modifies all words associated with the modification operation in the first continued text to obtain a second continued text.

In step 1704, the electronic device acquires a reference image.

The electronic device displays an image upload entry on the video interface, and obtains a reference image based on the image upload entry. The reference image is used to display the content that needs to be included in the continued video segment.

In some embodiments, the electronic device determines an image uploaded from a local photo album as a reference image.

Optionally, the image upload portal includes a local image upload portal, which is used to upload images in a local album. The electronic device displays the local album in response to a trigger operation on the local image upload portal, and determines the at least one selected image as a reference image in response to a selection operation on at least one image in the local album.

That is, the user can use the images in the local album as reference images for generating the second video clip. Therefore, the user can flexibly choose to use the images in the local album to generate video according to their own needs, which improves the flexibility and convenience of video production.

In some embodiments, the electronic device determines at least one video frame among a plurality of video frames in the first video segment as a reference image.

The image upload entry includes a captured image upload entry, and the captured image upload entry is used to upload a video frame captured in the first video segment. In response to a trigger operation on the captured image upload entry, the electronic device displays multiple video frames in the first video segment, and in response to a selection operation on at least one of the multiple video frames, determines the selected at least one video frame as a reference image.

In the disclosed embodiment, video frames in a first video clip can be provided to a user, and the user selects at least one video frame in the first video clip to generate a reference image of a second video clip. Since the video frames in the first video clip contain the content in the first video clip, when the second video clip is generated based on the video frames in the first video clip, it can be ensured that the content of the generated second video clip is consistent with the content displayed in the video frames in the first video clip, and further it can be ensured that the content of the second video clip is strongly correlated with the content of the first video clip, thereby improving the consistency and coherence between the continued video clip and the original video clip.

In step 1705, the electronic device generates a second video segment based on the first video segment, the second continuation text and the reference image, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text and the content of the reference image.

In the disclosed embodiment, the user can provide a reference image and use the reference image to show what content is included in the video segment that is expected to be continued. Since the reference image can intuitively display the picture, generating a video segment using the reference image can ensure that the content in the generated video segment is consistent with the content in the reference image, which is conducive to improving the accuracy of the generated video segment.

Based on the above embodiments, the electronic device can create a video generation task and generate at least one video segment according to the video generation task. The following takes the creation of a video generation task to which the second video segment belongs as an example to introduce the management method of the video generation task.

The electronic device displays a task management interface, which is used to display the created video generation tasks; in the task management interface, the video generation tasks to which the second video clip belongs and the status of the video generation tasks are displayed, and the statuses include generated status, generating status and generation failure status.

In the disclosed embodiment, a video generation task includes at least one video segment. When the video generation task includes multiple video segments, the multiple video segments include an initially generated video segment and at least one subsequent video segment. Optionally, the multiple video segments in the video generation task are arranged in sequence according to the generation order. For example, for the video generation task to which the second video segment belongs, the video generation task includes the first video segment and the second video segment.

Among them, the generated state means that each video segment requested to be generated in the video generation task has been generated, the generating state means that there is at least one video segment requested to be generated in the video generation task that is currently being generated, and the generation failed state means that there is at least one video segment requested to be generated in the video generation task that has failed to be generated.

As shown in FIG. 18 or FIG. 19, the task management interface displays a video generation task 1801, a video generation task 1802, and a video generation task 1803. The status of the video generation task 1801 is a generating status, the status of the video generation task 1802 is a generated status, and the status of the video generation task 1803 is a generation failure status. The video generation task 1801 includes a first video segment 1811 and a second video segment 1821, so the second video segment 1821 in the video generation task 1801 is being generated. After the second video segment 1821 is generated, as shown in FIG. 20, the status of the video generation task 1801 changes to a generated status.

In some embodiments, the electronic device may also perform at least one of the following based on the video generation task displayed in the task management interface.

(1) When the video generation task to which the second video segment belongs is in the generating state, the generating progress of the second video segment is displayed.

Optionally, the electronic device displays a thumbnail of the second video clip in the area where the video generation task is located, and displays the generation progress of the second video clip in response to a triggering operation on the thumbnail of the second video clip. When the second video clip is being generated, the thumbnail of the second video clip includes a prompt text, and the prompt text is used to prompt that the second video clip is being generated.

As shown in Figure 18 or 19, a thumbnail of the second video clip 1821 is displayed in the area where the video generation task 1801 is located. In response to the triggering operation of the thumbnail of the second video clip 1821, the generation progress of the second video clip 1821 is displayed. As shown in Figure 21, the generation progress of the second video clip 1821 has reached 27%.

(2) When the video generation task to which the second video clip belongs is in a generated state, a preview control is displayed, where the preview control is used to request to play the generated second video clip.

Optionally, the video generation task to which the second video segment belongs also includes a first video segment, and the preview control is used to request to play the generated first video segment and second video segment in a generation order.

As shown in Figure 20, for a video generation task 1801 in a generated state, a preview control is displayed in the area where the video generation task 1801 is located. For a video generation task 1802 in a generated state, a preview control is also displayed in the area where the video generation task 1802 is located, and the preview control is used to request to play the generated video clips in the video generation task 1802 in the generation order.

In other embodiments, the video generation task to which the second video clip belongs also includes a first video clip. When the video generation task is in a generating state, a preview control is displayed in the area where the video generation task is located. At this time, the preview control is used to request to play the generated first video clip.

As shown in FIG. 18 or FIG. 19 , for a video generation task 1801 in a generating state, a preview control is displayed in the area where the video generation task 1801 is located.

(3) When the video generation task to which the second video segment belongs is in a generation failure state, a regeneration control is displayed, and the regeneration control is used to request regeneration of the second video segment that has failed to be generated.

If the generation of the second video clip fails, the video generation task to which the second video clip belongs is in a generation failure state, and a regeneration control is displayed at this time to regenerate the second video clip.

As shown in FIG. 18 or FIG. 19 , for a video generation task 1803 that is in a generation failure state, a regeneration control is displayed in the area where the video generation task 1803 is located.

In the disclosed embodiment, for video generation tasks in different states, generation progress, preview controls, and regeneration controls can also be displayed accordingly, so that users can intuitively view the specific conditions of video generation tasks in different states, further improving the convenience of users managing created video generation tasks, which is conducive to improving the efficiency of human-computer interaction. The generated results support batch export or direct batch import of advanced editing functions for modification, further enhancing the user's video creation experience and management efficiency.

(4) In the area where the video generation task to which the second video segment belongs is located, the continuation information of the second video segment is displayed.

In some embodiments, when the video generation task to which the second video segment belongs is in a generating state, that is, when the second video segment is being generated, continuation information of the second video segment is displayed.

Optionally, the continuation information includes a continuation text or a reference image. In the case where the continuation information of the second video segment includes a continuation text, as shown in FIG18 , the area where the video generation task 1801 to which the second video segment belongs is located is displayed with a continuation text 1831. In the case where the continuation information of the second video segment includes a reference image, as shown in FIG19 , the area where the video generation task 1801 to which the second video segment belongs is located is displayed with a prompt text 1841, and the prompt text 1841 is used to prompt that the second video segment being generated is generated based on the image.

In some embodiments, when the video generation task to which the second video clip belongs is in a generated state, the video generation task is displayed in a folded state, and the area where the folded video generation task is located no longer displays the continuation information of the second video clip. If the user wants to view the continuation information of the second video clip, an expansion operation is performed on the video generation task to which the second video clip belongs. The electronic device responds to the expansion operation, displays the expanded video generation task, and displays the continuation information of the second video clip in the area where the expanded video generation task is located.

As shown in Figure 20, when the video generation task 1801 to which the second video clip belongs is in a generated state, the video generation task 1801 is displayed in a folded state, and the continuation text 1831 of the second video clip is not displayed. After the video generation task 1801 is expanded and displayed, the continuation text 1831 of the second video clip is redisplayed.

In the disclosed embodiment, by displaying the continuation information used by the continued video segment in the area where the video generation task is located, it is convenient for users to quickly understand the content of the video segment on the one hand, and on the other hand, it is convenient for users to trace the continuation information of the video segment, thereby improving the display effect.

(5) In the area where the video generation task to which the second video segment belongs is located, a thumbnail of the generated second video segment is displayed.

In some embodiments, when the video generation task to which the second video clip belongs is in a generated state, the video generation task is displayed in a folded state, and the area where the folded video generation task is located no longer displays the thumbnail of the second video clip. If the user wants to view the thumbnail of the second video clip, the video generation task to which the second video clip belongs is expanded, and the electronic device displays the expanded video generation task in response to the expansion operation, and displays the thumbnail of the second video clip in the area where the expanded video generation task is located. Wherein, when the second video clip has been generated, the thumbnail of the second video clip is a video frame in the second video clip.

As shown in Figure 20, when the video generation task 1801 to which the second video clip belongs is in a generated state, the video generation task 1801 is displayed in a folded state, and the thumbnail of the second video clip 1821 is not displayed. After the video generation task 1801 is expanded and displayed, the thumbnail of the second video clip 1821 is redisplayed.

In the disclosed embodiment, by displaying thumbnails of the continued video clips in the area where the video generation task is located, the user can intuitively understand the general style and content of the video clips by viewing the thumbnails, thereby improving the display effect.

The method provided by the embodiment of the present disclosure displays the created video generation tasks and the status of each video generation task, so that the user can understand the status of the video generation task according to the displayed status, and then the user can manage the created video generation tasks, thereby improving the visualization effect of the status of the video generation task.

In addition, the initial video clip and at least one video clip based on the initial video clip are displayed in the form of a collection on the task management interface, so that the user can manage multiple video clips with associated content as a continuous series. The user can view each generated video clip on the task management interface, which is convenient for management in units of video clips.

Moreover, multiple video clips in a video generation task are arranged in sequence according to the generation order. Since the multiple video clips are obtained by continuing in sequence, the multiple video clips can be arranged according to the content logic, ensuring the coherence and consistency of the video content, making it easy for users to clearly see the continuation process and content change process of the entire video, thereby enhancing the user's video creation experience and management efficiency.

Fig. 22 is a block diagram of a video processing device according to an exemplary embodiment. Referring to Fig. 22 , the device includes a display unit 2201 , a modification unit 2202 and a generation unit 2203 .

The display unit 2201 is configured to display the first video clip on the video interface;

The display unit 2201 is configured to display a first continuation text in response to a continuation request for the first video segment, where the first continuation text is used to describe the content that the continued video segment needs to include;

The modifying unit 2202 is configured to execute, in response to the modifying operation on the first continued text, modify all words in the first continued text associated with the modifying operation to obtain a second continued text;

The generating unit 2203 is configured to generate a second video segment based on the first video segment and the second continuation text, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text.

In the device provided by the embodiment of the present disclosure, if more content is to be continued on the basis of the first video clip, the first video clip can be requested to be continued. The first continuation text is used to describe the content that the continued video clip needs to contain. If the user wants to modify the first continuation text, by performing a modification operation on the first continuation text, all words related to the modification operation in the first continuation text can be modified with one click, and then the continued second video clip is generated based on the modified continuation text. In the present disclosure, when the user has the need to modify the continuation text, the entire text can be modified with one click, and the user does not need to search for the words to be modified one by one and modify them manually, which saves the user's operation time, improves the modification efficiency, and thus improves the overall efficiency of the continued video.

In some embodiments, referring to FIG. 23 , the modification unit 2202 is configured to perform:

Displaying a display area for multiple event elements, and displaying words belonging to the event elements in the first continuation text in the display area for the event elements;

In response to a modification operation on a word in a display area of a target event element, obtaining a modified first word, wherein the target event element is any one of a plurality of event elements;

All words belonging to the target event element in the first continuation text are replaced with the first word to obtain a second continuation text.

In some embodiments, referring to FIG. 23 , the modification unit 2202 is configured to perform:

In response to a modification operation on a second word in the first continuation text, obtaining a modified third word;

All words in the first continued text that are identical to the second word are replaced with the third word to obtain a second continued text.

In some embodiments, referring to FIG. 23 , the apparatus further comprises:

The display unit 2201 is further configured to display a prompt message if the content of the second continuation text does not match the content of the first video clip, where the prompt message is used to prompt that the content of the second continuation text does not match the content of the first video clip.

In some embodiments, referring to FIG. 23 , the video interface further displays a progress bar of the first video segment; the display unit 2201 is further configured to execute:

If the content of the second continuation text does not match the content of the target period in the first video segment, the area corresponding to the target period on the progress bar of the first video segment is highlighted to indicate that the content of the second continuation text does not match the content of the target period.

In some embodiments, referring to FIG. 23 , the video interface further displays a content text of the first video segment, where the content text is used to describe the content of the first video segment; the display unit 2201 is further configured to execute:

If the content of the second continuation text does not match the content of the target segment in the content text, the target segment in the content text is highlighted to indicate that the content of the second continuation text does not match the content of the target segment.

In some embodiments, referring to FIG. 23 , the display unit 2201 is configured to perform any of the following:

Continuing to write the content text of the first video clip to obtain a first continuation text, where the content text is used to describe the content of the first video clip;

Based on the text editing operation in the video interface, a first continuation text is obtained.

In some embodiments, referring to FIG. 23 , the apparatus further comprises:

The display unit 2201 is configured to display a duration input area on the video interface, and obtain the continuation duration based on the input operation in the duration input area; or obtain the continuation duration based on the text length of the second continuation text;

The generation unit 2203 is configured to generate a second video segment based on the first video segment, the second continuation text and the continuation duration, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content described in the second continuation text, and the duration of the second video segment is equal to the continuation duration.

In some embodiments, referring to FIG. 23 , the apparatus further comprises:

The display unit 2201 is configured to determine an image uploaded from a local photo album as a reference image; or determine at least one video frame among a plurality of video frames in a first video segment as a reference image;

The generating unit 2203 is configured to generate a second video segment based on the first video segment, the second continuation text and the reference image, wherein the content of the second video segment is a continuation of the content of the first video segment, and the content of the second video segment is consistent with the content of the second continuation text and the content of the reference image.

In some embodiments, referring to FIG. 23 , the generating unit 2203 is configured to execute:

Obtaining a content text of the first video clip, where the content text is used to describe the content of the first video clip;

Based on the content text and the second continuation text, a second video segment is generated.

In some embodiments, referring to FIG. 23 , the apparatus further comprises:

The display unit 2201 is configured to be executed on the video interface and display the first video segment and the second video segment in the order of generation.

In some embodiments, referring to FIG. 23 , the apparatus further comprises:

The display unit 2201 is configured to display an initial tag on the first video segment, where the initial tag is used to indicate that the video segment where the initial tag is located is an initial video segment;

The display unit 2201 is configured to display a continuation tag on the second video segment, where the continuation tag is used to indicate that the video segment where the continuation tag is located is a continued video segment.

In some embodiments, referring to FIG. 23 , the apparatus further includes a control unit 2204 configured to perform at least one of the following:

In a case where at least one of the first video segment and the second video segment is selected, in response to a video playing operation, playing the selected at least one video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video editing operation, displaying an editing interface of the at least one selected video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video download operation, downloading the selected at least one video segment;

In a case where at least one of the first video segment and the second video segment is selected, in response to a video publishing operation, a video including the at least one selected video segment is published.

In some embodiments, referring to FIG. 23 , the control unit 2204 is configured to execute:

In a case where the first video clip and the second video clip are selected, in response to a video publishing operation, generating a copy based on the first video clip and the second video clip;

Merging the first video segment and the second video segment into one video according to the generation order;

Release a video with the text; or, based on an editing operation on the text, obtain the edited text and release a video with the edited text.

Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

FIG24 is a block diagram of an electronic device according to an exemplary embodiment. In some embodiments, the electronic device 2400 includes: a mobile phone, a desktop computer, a laptop computer, a tablet computer or other electronic devices. The electronic device 2400 may also be called a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

Typically, the electronic device 2400 includes: a processor 2401 and a memory 2402 .

In some embodiments, the processor 2401 includes one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 2401 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

In some embodiments, the memory 2402 includes one or more computer-readable storage media, which are non-transitory. The memory 2402 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 2402 is used to store executable instructions, which are used to be executed by the processor 2401 to implement the video processing method provided by the method embodiment of the present disclosure.

In some embodiments, the electronic device 2400 may further include: a peripheral device interface 2403 and at least one peripheral device. In some embodiments, the processor 2401, the memory 2402 and the peripheral device interface 2403 are connected via a bus or a signal line. In some embodiments, each peripheral device is connected to the peripheral device interface 2403 via a bus, a signal line or a circuit board. Optionally, the peripheral device includes: at least one of a radio frequency circuit 2404, a display screen 2405, a camera assembly 2406, an audio circuit 2407 and a power supply 2408.

In some embodiments, the electronic device 2400 further includes one or more sensors 2409 , including but not limited to: an acceleration sensor 2410 , a gyroscope sensor 2411 , a pressure sensor 2412 , an optical sensor 2413 , and a proximity sensor 2414 .

Those skilled in the art will appreciate that the structure shown in FIG. 24 does not limit the electronic device 2400 , and may include more or fewer components than shown, or combine certain components, or adopt a different component arrangement.

In an exemplary embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the steps in the above-mentioned video processing method. For example, the computer-readable storage medium can be a ROM (Read Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor of an electronic device, the steps in the above-mentioned video processing method are implemented.

Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (18)

1. A method of video processing, the method comprising:

displaying a first video clip on a video interface;

In response to a continuation request for the first video segment, displaying a first continuation text for describing content required to be contained by the continued video segment;

Responding to the modification operation of the first continuous text, and modifying all words associated with the modification operation in the first continuous text to obtain a second continuous text;

A second video clip is generated based on the first video clip and the second continuation text, the content of the second video clip being a continuation of the content of the first video clip, and the content of the second video clip conforming to the content of the second continuation text.

2. The method according to claim 1, wherein said modifying, in response to the modification operation on the first continued text, all words associated with the modification operation in the first continued text to obtain a second continued text includes:

displaying a display area of a plurality of event elements, and displaying words belonging to the event elements in the first continuous text in the display area of the event elements;

Responding to the modification operation of the words in the display area of the target event element, and acquiring a modified first word, wherein the target event element is any one of the event elements;

and replacing all words belonging to the target event element in the first continuous text with the first words to obtain the second continuous text.

3. The method according to claim 1, wherein said modifying, in response to the modification operation on the first continued text, all words associated with the modification operation in the first continued text to obtain a second continued text includes:

responding to the modification operation of the second word in the first continuation text, and acquiring a modified third word;

And replacing all words which are the same as the second words in the first continuous text with the third words to obtain the second continuous text.

4. The video processing method of claim 1, wherein the method further comprises:

and if the content of the second continuous text does not accord with the content of the first video segment, displaying prompt information, wherein the prompt information is used for prompting that the content of the second continuous text does not accord with the content of the first video segment.

5. The method of claim 4, wherein the video interface further displays a progress bar for the first video clip; and if the content of the second continuous text does not accord with the content of the first video segment, displaying prompt information, wherein the prompt information comprises:

And if the content of the second continuous text does not accord with the content of the target time period in the first video segment, highlighting the area corresponding to the target time period on the progress bar of the first video segment so as to prompt that the content of the second continuous text does not accord with the content of the target time period.

6. The video processing method according to claim 4, wherein the video interface further displays content text of the first video clip, the content text describing content of the first video clip; and if the content of the second continuous text does not accord with the content of the first video segment, displaying prompt information, wherein the prompt information comprises:

And if the content of the second continuous text does not accord with the content of the target segment in the content text, highlighting the target segment in the content text to prompt that the content of the second continuous text does not accord with the content of the target segment.

7. The video processing method of claim 1, wherein the displaying the first continuation text comprises any one of:

writing the content text of the first video segment to obtain the first continuation text, wherein the content text is used for describing the content of the first video segment;

and acquiring the first continuous text based on text editing operation in the video interface.

8. The video processing method of claim 1, wherein the method further comprises:

Displaying a duration input area on the video interface, and acquiring duration based on input operation in the duration input area; or acquiring the duration based on the text length of the second continuous text;

The generating a second video clip based on the first video clip and the second continuation text includes:

Generating the second video segment based on the first video segment, the second continuation text and the duration, wherein the content of the second video segment is a continuation of the content of the first video segment, the content of the second video segment accords with the content described by the second continuation text, and the duration of the second video segment is equal to the duration of the continuation.

9. The video processing method of claim 1, wherein the method further comprises:

determining an image uploaded from the local album as a reference image; or determining at least one video frame of a plurality of video frames in the first video segment as the reference image;

The generating a second video clip based on the first video clip and the second continuation text includes:

The second video clip is generated based on the first video clip, the second continuation text, and the reference image, the content of the second video clip is a continuation of the content of the first video clip, and the content of the second video clip coincides with the content of the second continuation text and the content of the reference image.

10. The video processing method of claim 1, wherein the generating a second video clip based on the first video clip and the second continuation text comprises:

Acquiring a content text of the first video segment, wherein the content text is used for describing the content of the first video segment;

The second video clip is generated based on the content text and the second continuation text.

11. The video processing method according to any one of claims 1 to 10, characterized in that the method further comprises:

And displaying the first video clip and the second video clip on the video interface according to the generation sequence.

12. The video processing method of claim 11, wherein the method further comprises:

Displaying an initial tag on the first video segment, wherein the initial tag is used for indicating that the video segment where the initial tag is positioned is an initial video segment;

and displaying a continuation tag on the second video segment, wherein the continuation tag is used for indicating that the video segment where the continuation tag is located is a continued video segment.

13. The video processing method of claim 11, wherein the method further comprises at least one of:

Playing at least one selected video clip in response to a video playing operation in the case that at least one of the first video clip and the second video clip is selected;

In response to a video clip operation, displaying a clip interface of at least one of the first video clip and the second video clip when the selected video clip is selected;

Downloading at least one video clip selected in response to a video downloading operation in the event that at least one of the first video clip and the second video clip is selected;

in response to a video publishing operation, publishing a video containing at least one of the first video clip and the second video clip that is selected.

14. The video processing method according to claim 13, wherein, in a case where at least one of the first video clip and the second video clip is selected, in response to a video publishing operation, publishing a video containing the selected at least one video clip, comprising:

generating a document based on the first video clip and the second video clip in response to the video publishing operation if the first video clip and the second video clip are selected;

merging the first video segment and the second video segment into one video according to the generation sequence;

Publishing the video carrying the document; or based on the editing operation of the document, acquiring the edited document and releasing the video carrying the edited document.

15. A video processing apparatus, the apparatus comprising:

a display unit configured to perform displaying the first video clip on the video interface;

The display unit is configured to execute a display of a first continuation text for describing content required to be contained by the continued video clip in response to a continuation request for the first video clip;

A modification unit configured to perform modification of all words associated with the modification operation in the first continuous text in response to the modification operation of the first continuous text, so as to obtain a second continuous text;

And a generation unit configured to perform generation of a second video clip based on the first video clip and the second continuation text, the content of the second video clip being a continuation of the content of the first video clip, and the content of the second video clip conforming to the content of the second continuation text.

16. An electronic device, the electronic device comprising:

A processor;

A memory for storing the processor-executable instructions;

Wherein the processor is configured to execute the instructions to implement the video processing method of any one of claims 1 to 14.

17. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the video processing method of any one of claims 1 to 14.

18. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the video processing method of any one of claims 1 to 14.