Video editing method and device, equipment and storage medium

Abstract

The invention provides a video editing method and device, equipment and a storage medium. The method comprises the following steps: acquiring a to-be-edited video; key frames are extracted from the video, subtitles in the key frames are extracted and analyzed, and subtitle character cards of the key frames are generated; generating a caption character card time axis of the video based on the caption character card of each key frame; and editing the video based on the time axis of the subtitle character card. According to the method and the device, the position of the specific knowledge point can be quickly and accurately positioned through the subtitle character card, and the to-be-edited fragment containing the specific knowledge point is edited, so that the accuracy and the efficiency of video editing are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of video processing technology, and in particular to a video editing method, device, equipment and storage medium. Background Art

[0002] The traditional video editing process requires the editor to watch the original video content many times and replay it repeatedly to locate the appropriate split time point. After determining the split time point, it is necessary to repeatedly drag on the traditional timeline to select the appropriate video entry point and exit point position to ensure the integrity and accuracy of the edited content. This traditional video editing process not only has low editing efficiency but also easily misses important information. Therefore, how to improve the accuracy and efficiency of video editing is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0003] In view of this, the present disclosure proposes a video editing method, apparatus, device and storage medium, which can improve the accuracy and efficiency of video editing.

[0004] According to a first aspect of the present disclosure, there is provided a video editing method, comprising: Get the video to be edited; Extracting key frames from the video, extracting and analyzing the subtitles in each key frame, and generating subtitle text cards for each key frame; Based on the subtitle text cards of each of the key frames, generating a subtitle text card timeline of the video; The video is edited based on the subtitle text card timeline.

[0005] In a possible implementation, when extracting and analyzing the subtitles in the key frame to generate the subtitle text card of the key frame, it includes: Extracting subtitles from the key frames; Segment processing is performed on the subtitles to obtain all sentences constituting the subtitles; Traversing all sentences constituting the subtitles, determining the appearance time of the current sentence in the video for the traversed current sentence, and generating a subtitle text card corresponding to the current sentence based on the current sentence and the appearance time of the current sentence in the video; After the traversal is completed, the subtitle text cards corresponding to all the sentences constituting the subtitle are used as the subtitle text cards of the key frame.

[0006] In a possible implementation, when determining the appearance time of the traversed current sentence in the video, the method further includes: Determining a display position of the current sentence in the key frame; After generating the subtitle text card corresponding to the current sentence, the method further includes: The display position is associated with the subtitle text card corresponding to the current sentence.

[0007] In a possible implementation, when generating a subtitle text card timeline of the video based on the subtitle text cards of each of the key frames, the method includes: Arranging the subtitle text cards of the key frames in the order of their appearance time in the video; The arranged subtitle text cards are sequentially associated with the corresponding time on the video timeline to obtain the subtitle text card timeline of the video.

[0008] In a possible implementation, when the video is edited based on the subtitle text card timeline, the process includes: Acquire the screening conditions of the clip to be edited, and select the subtitle text cards that meet the screening conditions from the subtitle text card timeline as target subtitle text cards, and display the target subtitle text cards on the subtitle text card timeline; Based on each target subtitle text card on the subtitle text card timeline, setting the in point position and the out point position of the to-be-cut segment; Based on the in point position and the out point position, the segment to be edited is cut out from the video.

[0009] In a possible implementation, the screening condition includes at least one of a keyword, a preset word, and a display position.

[0010] In a possible implementation, the method further includes: Extracting an audio file from the video; Based on the audio file, generate an audio text card of the video; Based on the audio and text cards, generate an audio and text card timeline of the video; The audio text card timeline is merged with the subtitle text card timeline to obtain a multi-dimensional text card timeline.

[0011] According to a second aspect of the present disclosure, there is provided a video editing device, comprising: A video acquisition module, used to acquire the video to be edited; A subtitle text card generation module is used to extract key frames from the video, extract and analyze the subtitles in each key frame, and generate a subtitle text card for each key frame; A subtitle text card timeline generation module, used to generate a subtitle text card timeline of the video based on the subtitle text cards of each key frame; The video editing module is used to edit the video based on the subtitle text card timeline.

[0012] According to a third aspect of the present disclosure, a video editing device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the method described in the first aspect of the present disclosure.

[0013] According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, implement the method described in the first aspect of the present disclosure.

[0014] The present disclosure provides a video editing method, device, equipment and storage medium, the method comprising: obtaining a video to be edited; extracting key frames from the video, extracting and analyzing the subtitles in each key frame, generating subtitle text cards for each key frame; generating a subtitle text card timeline for the video based on the subtitle text cards for each key frame; and editing the video based on the subtitle text card timeline. In the present disclosure, the subtitle text card can be used to quickly and accurately locate the position of a specific knowledge point, and the clip to be edited containing the specific knowledge point can be edited, thereby improving the accuracy and efficiency of video editing.

[0015] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0017] Figure 1 A flowchart of a video editing method according to an embodiment of the present disclosure is shown; Figure 2 A display diagram of a video editing interface according to an embodiment of the present disclosure is shown; Figure 3 A diagram showing a video editing interface according to another embodiment of the present disclosure is shown; Figure 4 A schematic block diagram showing a video editing device according to an embodiment of the present disclosure; Figure 5 A schematic block diagram of a video editing device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0018] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0019] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0020] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0021] <Method Example> Figure 1 FIG. 1 is a flow chart showing a video editing method according to an embodiment of the present disclosure. Figure 1 As shown, the method includes steps S1100-S1400.

[0022] S1100, obtaining a video to be edited. The video to be edited is the video to be edited currently. For the convenience of description, the video to be edited is referred to as a video in the following. When editing a video, it is necessary to first upload the video to an editing system that executes the video editing method disclosed in the present invention, so that the editing system can obtain the video and execute step S1200.

[0023] S1200, extract key frames from the video, extract and analyze the subtitles in each key frame, and generate subtitle text cards for each key frame. A key frame refers to a frame where a key action is located in the motion change of a character or object, which is equivalent to an original painting in a two-dimensional animation. The subtitles in a key frame refer to all texts present in the key frame image, and all the texts may include at least one of the presentation text presented in the key frame and the lyrics used to explain the content of the key frame.

[0024] For each extracted key frame, it is necessary to extract and analyze the subtitles in the key frame to generate a subtitle text card for each key frame. Since the generation process of the subtitle text card for each key frame is the same, the generation process of the subtitle text card for the key frame is described below by taking a key frame as an example. Specifically, when extracting and analyzing the subtitles in the key frame to generate the subtitle text card for the key frame, the following steps may be included: First, extracting subtitles from key frames. Specifically, when extracting subtitles from key frames, it can be implemented based on an OCR recognition algorithm.

[0025] Second, the subtitles are processed into sentences to obtain all the sentences constituting the subtitles. Specifically, the identified subtitles can be input into a natural language processing model to implement sentence processing of the subtitles through the natural language processing model to obtain all the sentences constituting the subtitles.

[0026] Third, traverse all the sentences that make up the subtitles, and for the current sentence that has been traversed, determine the appearance time of the current sentence in the video, and generate the subtitle text card corresponding to the current sentence based on the current sentence and the appearance time of the current sentence in the video. Specifically, when traversing to the current sentence, the appearance time of the frame in which the current sentence is located in the video can be determined according to the frame rate of the video. Then, fill the current sentence and the appearance time of the current sentence in the video into the preset text card rendering template, and then generate the subtitle text card corresponding to the current sentence based on the filled text card rendering template. Among them, the subtitle text card corresponding to the current sentence includes the appearance time of the current sentence and the current sentence in the video (the appearance time is composed of the start time and the end time). Through the subtitle text card corresponding to the current sentence, the user can quickly understand the appearance time of the knowledge content involved in the current sentence in the video clip.

[0027] In a possible implementation, when the subtitles in the same key frame are divided into multiple sentences, the appearance time of the key frame in the video can be used as the appearance time of each sentence in the key frame in the video. In another possible implementation, all sentences appearing in the same key frame can be merged into a subtitle text card for display, and the appearance time of the key frame in the video can be used as the appearance time of the merged subtitle text card in the video.

[0028] Fourth, after the traversal is completed, the subtitle file card of each sentence will be obtained, and the subtitle text cards of all the sentences obtained will be used as the subtitle text cards of the key frame. In other words, if the subtitle of the key frame includes several sentences, then the key frame will have several letter text cards. For example, when the subtitle of the key frame is processed by sentence segmentation, 4 sentences are obtained, and 4 subtitle text cards will be generated for each of the 4 sentences, and these 4 subtitle text cards constitute the subtitle text card of the key frame.

[0029] In a possible implementation, when determining the appearance time of the current sentence in the video for the current sentence that has been traversed, it also includes: determining the display position of the current sentence in the key frame. Specifically, when extracting subtitles from the key frame, the display position of each character in the subtitle in the key frame will also be identified and recorded at the same time. In this way, when traversing the current sentence, the display position of each character that makes up the current sentence in the key frame can be obtained, and then the display position of the current sentence in the key frame can be determined based on the display position of each character in the key frame. In this implementable method, after generating the subtitle text card corresponding to the current sentence, the display position of the current sentence is also associated with the subtitle text card corresponding to the current sentence. This is to facilitate the subsequent screening of subtitle text cards according to the display position set by the user.

[0030] By processing each key frame in the video in accordance with the above method, the subtitle text card of each key frame can be obtained.

[0031] After obtaining the subtitle text cards of each key frame, step S1300 may be executed to generate a subtitle text card timeline of the video based on the subtitle text cards of each key frame.

[0032] In a possible implementation, when generating a subtitle text card timeline of a video based on the subtitle text cards of each key frame, the following steps may be included: First, the subtitle text cards of each key frame are arranged in order according to the order of appearance time in the video. Specifically, the subtitle text cards include the appearance time of the recorded sentence in the video, and the appearance time of the recorded sentence in the video is the appearance time of the subtitle text card in the video. After determining the appearance time of each subtitle text card in the video, they can be arranged in order according to the order of appearance time.

[0033] Second, associate each arranged subtitle text card with the corresponding time on the video timeline in turn to obtain the subtitle text card timeline of the video. Specifically, first generate the video timeline, and then associate each subtitle text card to the corresponding position of the video timeline according to the appearance time of each subtitle text card in the video, so as to obtain a subtitle text card timeline composed of the video timeline and the subtitle text card bound to the video timeline. After obtaining the subtitle text card timeline, slide on the video timeline, locate the time point of the video according to the sliding position, and locate the subtitle text card that appears at the time point according to the located video time point, so as to understand the subtitles that appear at the time point in the video through the subtitle text card that appears at the time point.

[0034] In a possible implementation, the interval associated with the subtitle text card on the video timeline can also be highlighted to facilitate the user to quickly locate the valid area associated with the subtitle text card on the video timeline.

[0035] It should be noted here that the video timeline generated in this step is a new timeline independent of the original video timeline. After associating each subtitle text card to the newly generated video timeline, a new subtitle text card timeline independent of the original video timeline will be generated. In other words, after executing this step, two timelines will be presented in the editing interface, one is the original video timeline, and the other is the subtitle text card timeline including multiple subtitle text cards. In a specific video editing example, the generated subtitle text card timeline can be seen in Figure 2 In this way, in the subsequent video editing process, after the in-point position and out-point position of the to-be-edited segment are determined through the subtitle text cards on the subtitle text timeline, the corresponding in-point position and out-point position can be displayed on the original video timeline, so that the user can view the position information of the to-be-edited segment in the video.

[0036] After the subtitle text card timeline is generated, step S1400 can be executed to edit the video based on the subtitle text card timeline. Specifically, the following steps can be included when editing the video: First, the screening conditions of the clip to be edited are obtained, and the subtitle text cards that meet the screening conditions are screened out from the subtitle text card timeline as target subtitle text cards, and the target subtitle text cards are displayed on the subtitle text card timeline to improve the display of effective subtitle text cards on the subtitle text card timeline. The screening conditions may include at least one of keywords, preset words, display positions, and hidden lyrics.

[0037] When filtering based on keywords, users can Figure 3 Enter a keyword in the keyword filtering area shown in , so that when filtering the target subtitle text cards, the subtitle text cards including the keyword will be filtered out from all the subtitle text cards as the target subtitle text cards, and the filtered target subtitle text cards will be displayed in sequence on the subtitle text card timeline, and other subtitle text cards that do not meet the filtering conditions will be hidden.

[0038] When filtering based on preset words, it is necessary to first obtain the preset word information configured by the user. When obtaining the preset word information configured by the user, it includes: responding to the triggering of the preset word setting control, pushing and displaying the preset word configuration interface, and obtaining the preset word information configured by the user through the preset word configuration interface. Among them, the preset word information may include preset words and preset word types. The preset word can be a text (such as a conclusion) or a symbol (such as "()") specified by the user. The type of the preset word is used to indicate the position of the preset word in the sentence. For example, the type of the preset word may include at least one of starting with a preset word and ending with a preset word.

[0039] In a possible implementation, the preset word configuration interface displayed by the push is as follows: Figure 3 As shown in the window interface in the middle of the figure, it includes a preset word information display area on the upper side and a preset word configuration area on the lower side. The user can enter the preset word to be searched in the preset word configuration area on the lower side and set the type of the preset word. After completing the input of the preset word and the configuration of the preset word type, click the Add control to add the preset word information just configured to the preset word information display area. After completing the configuration of the preset word, close the preset word configuration interface, and the editing system can obtain all the preset word information configured by the user through the preset word configuration interface.

[0040] After obtaining the preset word information configured by the user, the preset word is extracted from the preset word information, and the extracted preset word is pushed and displayed to the Figure 3 The preset word filtering area shown. In this way, when the user performs preset word filtering, the user can select the desired preset word in the preset word filtering area. When the preset word is selected, the preset word and the type of the preset word will be obtained, and then the subtitle text cards including the selected preset word and the position of the preset word in the sentence consistent with the type of the preset word will be filtered out from all the subtitle text cards as the target subtitle text cards, and the filtered target subtitle text cards will be displayed in sequence on the subtitle text card timeline, and other subtitle text cards that do not meet the filtering conditions will be hidden.

[0041] In addition, when the user needs to adjust the preset words, the user can trigger the preset word setting control again to call out the preset word configuration interface, and add, reduce and modify the preset words based on the preset word configuration interface.

[0042] When filtering based on display location, users can Figure 3Enter the specified display position in the coordinate filtering area shown in , so that when filtering the target subtitle text cards, the subtitle text cards whose display position of the bound sentence is the same as the display position specified by the user will be filtered out from all the subtitle text cards as the target subtitle text cards. It should be noted here that in different videos, the display position of the key knowledge points in the video frame is different. Therefore, the user can filter out the target subtitle text cards including the key knowledge points by setting the display position of the key knowledge points, and display the filtered target subtitle text cards in sequence on the subtitle text card timeline. Other subtitle text cards that do not meet the filtering conditions will be hidden, thereby improving the accuracy of the target subtitle text card filtering.

[0043] When filtering based on hidden lyrics, users can Figure 3 In the hidden lyrics area shown, it is set whether to hide the lyrics. If the user chooses to hide the lyrics, the pre-configured lyrics display position will be obtained, and the subtitle text cards whose display positions of the bound sentences are the same as the lyrics display position in all subtitle text cards will be hidden, and other subtitle text cards that are not hidden will be displayed as target subtitle text cards. It should be noted here that the sentences contained in the lyrics text cards are the content of the explanation of the demonstration courseware in the key frame (i.e. the subtitles of the audio explanation). When the courseware content displayed in the key frame is used as the knowledge point for video editing, you can choose to hide the lyrics, and then hide the subtitle text cards including the lyrics, so that only the subtitle text cards related to the displayed courseware are displayed, so as to facilitate the user to perform video editing operations based on the knowledge points in the displayed courseware content.

[0044] After filtering out the target subtitle text cards, you can proceed to the second step.

[0045] Second, based on each target subtitle text card on the subtitle text card timeline, set the in point position and out point position of the clip to be edited. Figure 3As shown, the selected target subtitle text cards are displayed in the subtitle text card timeline in the order of appearance. In addition to the sentences and the appearance time of the sentences, each subtitle text card also includes an entry point position setting control (i.e., a circular control including a left arrow) and an exit point position setting control (i.e., a circular control including a right arrow). The user can determine the start subtitle text card and the end subtitle text card corresponding to the clip to be edited from the target subtitle text card, and then click the entry point position setting control on the start subtitle text card. When the entry point position control is clicked, the start time in the appearance time will be extracted from the start subtitle text card as the entry point position of the clip to be edited. Click the exit point position setting control on the end subtitle text card. When the exit point position setting control is clicked, the end time in the appearance time will be extracted from the end subtitle text card as the exit point position of the clip to be edited.

[0046] In one possible implementation, in order to clearly display the entry point and exit point of the clip to be edited, the corresponding entry point and exit point will be marked on the original video timeline, and the area between the entry point and the exit point will be highlighted, so that the user can clearly understand the position of the clip to be edited in the video.

[0047] Third, based on the in-point position and the out-point position, the clip to be edited is cut out from the video. Specifically, how to cut out the clip to be edited from the video based on the in-point position and the out-point position is common knowledge in the art and will not be described in detail here.

[0048] In a possible implementation, after the target subtitle text cards are screened out, the subtitle text cards including useless sentences in the target subtitle text cards can also be deleted. After the subtitle text cards are deleted, the corresponding time segments in the video are deleted based on the appearance time on the deleted subtitle text cards. In this way, after the entry point and the exit point of the segment to be edited are identified based on the remaining target text cards, the video segment between the entry point and the exit point can be cut out from the edited video as the segment to be edited, thereby improving the simplicity of the segment to be edited.

[0049] In one possible implementation, after screening out the target subtitle text cards, the order of appearance of the target subtitle text cards can also be set. When the order of appearance of the target subtitle text cards is set, corresponding video clips will be edited from the video according to the appearance time of each target subtitle text card, and then the edited video clips will be combined in sequence according to the order of appearance of each target subtitle text card, so as to obtain an edited video that conforms to the order of appearance of each target subtitle text card.

[0050] In a possible implementation, while generating the subtitle text card timeline of the video, the following steps are also included: First, extract the audio file from the video.

[0051] Second, based on the audio file, generate the audio text card of the video. Specifically, first use the ASR algorithm to recognize the audio text, then input the audio text into the natural language processing model to process the audio text, obtain the sentences that make up the audio text, and then generate the corresponding audio text card for each sentence that makes up the audio text. All the audio text cards obtained constitute the audio text cards of the video.

[0052] Third, based on the audio text card, generate the audio text card timeline of the video. The specific generation method refers to the generation process of the subtitle text card timeline, which will not be repeated here.

[0053] Fourth, merge the audio text card timeline with the subtitle text card timeline to obtain a multi-dimensional text card timeline including subtitle text cards and audio text cards. Specifically, merge the timeline of the audio text card and the timeline of the subtitle text card into one timeline, associate the subtitle text cards and audio text cards that appear at the same time point through one timeline, and highlight the positions on the timeline associated with the subtitle text cards and audio text cards. When sliding on the multi-dimensional text card timeline, the subtitle text cards and audio text cards associated with the video time point will be linked and displayed according to the time point in the video at the sliding position and the located video time point. Based on the associated subtitle text cards and audio text cards, the subtitles and voices that appear in the video at the located time point can be clearly understood, which is convenient for users to screen subtitle and voice knowledge points at the same time. In a specific example, the multi-dimensional text card timeline can be as follows: Figure 3 shown.

[0054] After generating the multi-dimensional text card timeline, the user can choose to edit the video based on the subtitle text card or the audio text card according to the needs, thereby further improving the flexibility of video editing. Among them, the method of editing the video based on the audio text card refers to the process of editing the video based on the subtitle text card, which will not be repeated here.

[0055] The present disclosure provides a video editing method, including: obtaining a video to be edited; extracting key frames from the video, extracting and analyzing the subtitles in each key frame, generating subtitle text cards for each key frame; generating a subtitle text card timeline for the video based on the subtitle text cards for each key frame; and editing the video based on the subtitle text card timeline. In the present disclosure, the subtitle text card can be used to quickly and accurately locate the position of a specific knowledge point, and the clip to be edited containing the specific knowledge point can be edited, thereby improving the accuracy and efficiency of video editing.

[0056] <Device Example> Figure 4 FIG. 1 is a schematic block diagram of a video editing device according to an embodiment of the present disclosure. Figure 4 As shown, the device 100 includes: The video acquisition module 110 is used to acquire the video to be edited; The subtitle text card generation module 120 is used to extract key frames from the video, extract and analyze the subtitles in each key frame, and generate a subtitle text card for each key frame; A subtitle text card timeline generation module 130 is used to generate a subtitle text card timeline of a video based on the subtitle text cards of each key frame; The video editing module 140 is used to edit the video based on the subtitle text card timeline.

[0057] <Equipment Embodiment> Figure 5 FIG. 1 is a schematic block diagram of a video editing device according to an embodiment of the present disclosure. Figure 5 As shown, the video editing device 200 includes: a processor 210 and a memory 220 for storing executable instructions of the processor 210. The processor 210 is configured to implement any of the above-mentioned video editing methods when executing the executable instructions.

[0058] Here, it should be noted that the number of processors 210 can be one or more. Meanwhile, in the video editing device 200 of the embodiment of the present disclosure, an input device 230 and an output device 240 may also be included. The processor 210, the memory 220, the input device 230 and the output device 240 may be connected via a bus or in other ways, which are not specifically limited here.

[0059] The memory 220 is a computer-readable storage medium that can be used to store software programs, computer executable programs, and various modules, such as the program or module corresponding to the video editing method of the embodiment of the present disclosure. The processor 210 executes various functional applications and data processing of the video editing device 200 by running the software programs or modules stored in the memory 220.

[0060] The input device 230 may be used to receive input numbers or signals. The signals may be key signals related to user settings and function control of the device / terminal / server. The output device 240 may include display devices such as display screens.

[0061] <Storage Medium Embodiment> According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium is also provided, on which computer program instructions are stored. When the computer program instructions are executed by the processor 210, any of the above-mentioned video editing methods is implemented.

[0062] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A video editing method, characterized in that: include: Get the video to be edited; Extracting key frames from the video, extracting and analyzing the subtitles in each key frame, and generating subtitle text cards for each key frame; Based on the subtitle text cards of each of the key frames, generating a subtitle text card timeline of the video; The video is edited based on the subtitle text card timeline.

2. The method according to claim 1, characterized in that When extracting and analyzing the subtitles in the key frame to generate the subtitle text card of the key frame, it includes: Extracting subtitles from the key frames; Segment processing is performed on the subtitles to obtain all sentences constituting the subtitles; Traversing all sentences constituting the subtitles, determining the appearance time of the current sentence in the video for the traversed current sentence, and generating a subtitle text card corresponding to the current sentence based on the current sentence and the appearance time of the current sentence in the video; After the traversal is completed, the subtitle text cards corresponding to all the sentences constituting the subtitle are used as the subtitle text cards of the key frame.

3. The method according to claim 2, characterized in that When determining the appearance time of the current sentence in the video for the traversed current sentence, the method further includes: Determining a display position of the current sentence in the key frame; After generating the subtitle text card corresponding to the current sentence, the method further includes: The display position is associated with the subtitle text card corresponding to the current sentence.

4. The method according to claim 1, characterized in that: When generating the subtitle text card timeline of the video based on the subtitle text cards of each of the key frames, it includes: Arranging the subtitle text cards of the key frames in the order of their appearance time in the video; The arranged subtitle text cards are sequentially associated with the corresponding time on the video timeline to obtain the subtitle text card timeline of the video.

5. The method according to claim 1, characterized in that When the video is edited based on the subtitle text card timeline, it includes: Acquire the screening conditions of the clip to be edited, and select the subtitle text cards that meet the screening conditions from the subtitle text card timeline as target subtitle text cards, and display the target subtitle text cards on the subtitle text card timeline; Based on each target subtitle text card on the subtitle text card timeline, setting the in point position and the out point position of the to-be-cut segment; Based on the in point position and the out point position, the segment to be edited is cut out from the video.

6. The method according to claim 5, characterized in that The screening condition includes at least one of a keyword, a preset word and a display position.

7. The method according to claim 1, characterized in that Also includes: Extracting an audio file from the video; Based on the audio file, generate an audio text card of the video; Based on the audio and text cards, generate an audio and text card timeline of the video; The audio text card timeline is merged with the subtitle text card timeline to obtain a multi-dimensional text card timeline.

8. A video editing device, characterized in that: include: A video acquisition module, used to acquire the video to be edited; A subtitle text card generation module is used to extract key frames from the video, extract and analyze the subtitles in each key frame, and generate a subtitle text card for each key frame; A subtitle text card timeline generation module, used to generate a subtitle text card timeline of the video based on the subtitle text cards of each key frame; The video editing module is used to edit the video based on the subtitle text card timeline.

9. A video editing device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 7 when executing the executable instructions.

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

Images