Video processing method and device, electronic equipment and computer storage medium

Abstract

The invention discloses a video processing method and device, electronic equipment and a computer storage medium, and aims to improve the video processing efficiency. The method comprises the following steps: an equipment side terminal determines a target video recording mode in response to a first control instruction of a user; in response to a second control instruction of the user, starting video recording in the target video recording mode; in response to a third control instruction of the user, generating a highlight video tag for marking a highlight moment in the video; and in response to a fourth control instruction of the user, ending video recording, and sending the video and the video tag carried by the video to the system side terminal. The system side terminal obtains the video sent by the device side terminal and the video tag carried by the video; displaying a video selection page; the video selection page comprises a first historical video shot by the device side terminal within a preset time period; and in response to a first trigger operation input by the user based on the video selection page, generating a first initial video based on the first historical video and the video tags carried by the videos in the first historical video.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a video processing method, device, electronic device and computer storage medium. Background Art

[0002] With the advancement of technology, the ways of video processing are becoming more and more diverse. In some solutions, video recording devices such as outdoor recorders support the video export function. Users can edit the videos exported by the video recording devices and make videos such as Vlog to record the wonderful moments in the outdoor environment.

[0003] However, in the related art, the videos exported by outdoor recorders are generally in units of days. Users need to spend a lot of time browsing these exported videos and manually selecting wonderful clips from each video to make a video, which is time-consuming and labor-intensive, and there is a problem of low video processing efficiency. Summary of the invention

[0004] The embodiments of the present application provide a video processing method, device, electronic device and computer storage medium, which can improve the efficiency of video processing.

[0005] In a first aspect, an embodiment of the present application provides a video processing method, which is applied to a system-side terminal, and the method includes:

[0006] Obtain the video sent by the device terminal and the video tag carried in the video;

[0007] Displaying a video selection page; the video selection page includes a first historical video shot by the device-side terminal within a preset time period, and the first historical video includes a video;

[0008] In response to a first trigger operation input by a user based on a video selection page, a first initial video is generated based on the first historical video and video tags carried by each video in the first historical video.

[0009] In one possible implementation, the video tag includes a highlight video tag for marking a highlight moment in the video;

[0010] In response to a first trigger operation input by a user based on a video selection page, generating a first initial video based on a first historical video and video tags carried by each video in the first historical video, including:

[0011] In response to a first trigger operation input by a user based on a video selection page, inputting the first historical video into a video content recognition model to obtain recognition results of each video in the first historical video;

[0012] Extracting a first key video segment from the first historical video based on the recognition results of each video in the first historical video and the video tags carried by each video in the first historical video; the first key video segment includes a highlight video segment corresponding to the highlight moment;

[0013] Removing the jittery images in the first key video segment to obtain a first initial video segment;

[0014] Based on the first initial video segment, a first initial video is generated.

[0015] In a possible implementation, after displaying the video selection page, the method further includes:

[0016] In response to a second trigger operation input by the user based on the video selection page, a second initial video is generated based on a second historical video selected by the user on the video selection page and a video tag carried by each video in the second historical video.

[0017] In a possible implementation, in response to a second trigger operation input by a user based on a video selection page, generating a second initial video based on a second historical video selected by the user on the video selection page and a video tag carried by each video in the second historical video includes:

[0018] In response to a second trigger operation input by the user based on the video selection page, the second historical video is input into the video content recognition model to obtain a recognition result of each video in the second historical video;

[0019] Extracting a second key video segment from the second historical video based on the recognition result of each video in the second historical video and the video tag carried by each video in the second historical video;

[0020] Removing the jittery images in the second key video segment to obtain a second initial video segment;

[0021] Based on the second initial video segment, a second initial video is generated.

[0022] In a possible implementation, in response to a first trigger operation input by a user based on a video selection page, after generating a first initial video based on a first historical video and a video tag carried by each video in the first historical video, the method further includes:

[0023] The video editing page is displayed; the video editing page includes a video preview area, and the video preview area is used to display a preview video associated with the first initial video.

[0024] In a possible implementation, the video editing page further includes a segment editing area, where the segment editing area is used to display the first initial video segment in the first initial video;

[0025] After displaying the video editing page, the method further includes:

[0026] In response to a user's clip cropping operation on any one of the first initial video segments in the segment editing area, adjusting the video duration of any one of the first initial video segments;

[0027] and / or

[0028] In response to a user's speed adjustment operation on any one of the first initial video segments in the segment editing area, adjusting the playback speed of any one of the first initial video segments;

[0029] and / or

[0030] In response to a segment replacement operation of a user on any first initial video segment in the segment editing area, replacing any first initial video segment with a target video segment;

[0031] and / or

[0032] In response to a user's order adjustment operation on any first initial video segment in the segment editing area, the appearance order of any first initial video segment in the first initial video is adjusted.

[0033] In a possible implementation, the video editing page further includes a template editing area, which is used to display multiple video templates, each of which has a different video output duration and video presentation effect.

[0034] After displaying the video editing page, the method further includes:

[0035] In response to a third trigger operation by the user on any one of the video templates in the template editing area, the first initial video is adjusted based on the any one of the video templates.

[0036] In a possible implementation, the method further includes:

[0037] In response to a fourth trigger operation input by the user based on the video editing page, the preview video displayed in the video preview area is used as the target video.

[0038] In a second aspect, an embodiment of the present application provides a video recording processing method, which is applied to a device-side terminal, and the method includes:

[0039] In response to a first control instruction from a user, determining a target video recording mode;

[0040] In response to a second control instruction of the user, starting recording in a target recording mode;

[0041] In response to a third control instruction of the user, generating a highlight video tag for marking a highlight moment in the video;

[0042] In response to a fourth control instruction of the user, the video recording is ended, and the video recording and the video tag carried by the video recording are sent to the system side terminal, the video tag including a highlight video tag for marking a highlight moment in the video recording, so that the system side terminal obtains the video recording and the video tag carried by the video recording, and displays a video recording selection page, the video recording selection page including a first historical video recording taken by the device side terminal within a preset time period, the first historical video recording including the video recording, and in response to a first trigger operation input by the user based on the video recording selection page, a first initial video is generated based on the first historical video recording and the video tags carried by each video recording in the first historical video recording;

[0043] Among them, the control forms of the first control instruction, the second control instruction, the third control instruction and the fourth control instruction include voice control forms.

[0044] In a third aspect, an embodiment of the present application provides a video processing device, which is applied to a system-side terminal, and the device includes:

[0045] An acquisition module is used to acquire the video sent by the device-side terminal and the video tag carried by the video;

[0046] A display module is used to display a video selection page; the video selection page includes a first historical video shot by the device side terminal within a preset time period, and the first historical video includes a video;

[0047] The response module is used to generate a first initial video based on the first historical video and the video tags carried by each video in the first historical video in response to a first trigger operation input by the user based on the video selection page.

[0048] In a fourth aspect, an embodiment of the present application provides a video processing device, which is applied to a device-side terminal, and the device includes:

[0049] A first response module, used to determine a target recording mode in response to a first control instruction of a user;

[0050] A second response module, responding to a second control instruction of the user, starts recording in a target recording mode;

[0051] A third response module, in response to a third control instruction of the user, generates a highlight video tag for marking a highlight moment in the video;

[0052] a fourth response module, in response to a fourth control instruction of the user, ending the video recording, and sending the video recording and the video tag carried by the video recording to the system side terminal, wherein the video tag includes a highlight video tag for marking a highlight moment in the video recording, so that the system side terminal obtains the video recording and the video tag carried by the video recording, and displays a video recording selection page, wherein the video recording selection page includes a first historical video recording taken by the device side terminal within a preset time period, wherein the first historical video recording includes the video recording, and in response to a first trigger operation input by the user based on the video recording selection page, generating a first initial video based on the first historical video recording and the video tags carried by each video recording in the first historical video recording;

[0053] Among them, the control forms of the first control instruction, the second control instruction, the third control instruction and the fourth control instruction include voice control forms.

[0054] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps provided in the first aspect or the second aspect of the embodiment of the present application.

[0055] In a sixth aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the method steps provided in the first aspect or the second aspect of the embodiment of the present application.

[0056] The above-mentioned video processing method, device, electronic device and computer storage medium, at the device side terminal, by responding to the first control instruction input by the user in the form of voice control or the like, determine the target video mode, which helps the device side terminal configure the recording parameters corresponding to the target video mode and improves the recording effect; by responding to the second control instruction input by the user in the form of voice control or the like, start the video recording in the target video recording mode, which is convenient for the user to start the recording at any time according to actual needs, and improves the flexibility of recording; by responding to the third control instruction input by the user in the form of voice control or the like, generate a highlight video tag for marking the highlight moment in the video recording, which can instantly mark the highlight moment in the video recording without affecting the shooting, and simplifies the subsequent video recording processing flow; by responding to the fourth control instruction input by the user in the form of voice control or the like, end the video recording, and send the video recording and the video tag carried by the video recording to the system side terminal, which is convenient for the user to stop the recording at any time according to actual needs, and improves the effectiveness of the video recording content. The video recording processing process of the entire device side terminal not only improves the quality of the video recording, but also simplifies the subsequent video recording processing flow of the system side terminal and improves the video recording processing efficiency.

[0057] The video processing method, device, electronic device and computer storage medium described above, at the system side terminal, by acquiring the video sent by the device side terminal and the video tag carried by the video, helps the system side terminal to automatically select the wonderful clips in the video according to the video and the tag carried by the video; by displaying the video selection page, the video selection page includes the first historical video shot by the device side terminal within the preset time period, and the first historical video includes the video, so that the user can intuitively see all the videos shot by the device side terminal within the preset time period, thereby improving the efficiency of the user viewing the video; by responding to the first trigger operation input by the user based on the video selection page, the first initial video is generated based on the first historical video and the video tags carried by each video in the first historical video, thereby greatly reducing the time and energy of the user to manually edit the video, effectively simplifying the video processing process, and realizing the intelligent generation of the video. The video processing process of the entire system side terminal does not require the user to spend a lot of time and energy to make a video based on the video exported by the device side terminal. The user only needs to perform a simple trigger operation, and the system side terminal can automatically process the video and intelligently generate the video, thereby effectively improving the video processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A schematic diagram of a video processing system provided by an exemplary embodiment of the present application;

[0060] Figure 2 A flowchart of a video processing method provided by an exemplary embodiment of the present application;

[0061] Figure 3 A schematic diagram of a main interface of a recorder APP provided by an exemplary embodiment of the present application;

[0062] Figure 4 A schematic diagram of a video selection page provided by an exemplary embodiment of the present application;

[0063] Figure 5 A flowchart of another video processing method provided by an exemplary embodiment of the present application;

[0064] Figure 6 A schematic diagram of a video editing page provided for an exemplary embodiment of the present application;

[0065] Figure 7A schematic diagram of a segment editing pop-up window provided by an exemplary embodiment of the present application;

[0066] Figure 8 A flowchart of another video processing method provided by an exemplary embodiment of the present application;

[0067] Fig. 9 A schematic diagram of the structure of a video processing device provided by an exemplary embodiment of the present application;

[0068] Fig.10 A schematic diagram of the structure of another video processing device provided by an exemplary embodiment of the present application;

[0069] Fig.11 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0070] First, an application scenario applicable to the embodiment of the present application is introduced: a certain outdoor recorder has both the function of a driving recorder and the function of a sports camera, and the user can use the outdoor recorder to shoot in the car or outdoors. During the shooting process, the user can input control instructions in the form of voice control, thereby realizing the selection of recording modes (such as normal recording mode, slow recording mode, Selfie recording mode, etc.), turning recording on or off, marking highlight moments in the recording, and other functions.

[0071] The outdoor recorder is equipped with a recorder APP (Application) installed on the mobile phone. Users can not only view the videos uploaded by the outdoor recorder through the APP, but also process the videos through the APP to quickly generate valuable videos (such as highlight video clips corresponding to highlight moments marked by users), allowing users to record and share beautiful moments more easily and efficiently.

[0072] The video processing method provided in the embodiment of the present application can be applied to Figure 1In the video processing system shown. The video processing system includes a device side terminal 11 and a system side terminal 12. The device side terminal 11 can be connected to the system side terminal 12 by wireless means (such as Bluetooth, Wi-Fi, etc.) or by wire. Among them, the device side terminal 11 is provided with at least two cameras and at least two microphones in different directions, and the device side terminal 11 can be but not limited to various outdoor recorders, sports cameras, monitoring terminals, etc. The system side terminal 12 is installed with an APP that matches the device side terminal 12, and the system side terminal 12 can be but not limited to various smart phones, tablet computers, laptops, personal computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0073] Specifically, the device-side terminal 11 determines the target recording mode in response to the user's first control instruction; starts recording in the target recording mode in response to the user's second control instruction; generates a highlight video tag for marking the highlight moment in the recording in response to the user's third control instruction; ends the recording in response to the user's fourth control instruction, and sends the recording and the video tag carried by the recording (including the highlight video tag for marking the highlight moment in the recording) to the system-side terminal 12 in a wireless or wired manner. The control form of the above-mentioned first control instruction, second control instruction, third control instruction and fourth control instruction includes a voice control form. The system-side terminal 12 obtains the recording and the video tag carried by the recording sent by the device-side terminal 11; displays a recording selection page, the recording selection page includes a first historical recording shot by the device-side terminal within a preset time period, and the first historical recording includes recordings; in response to a first trigger operation input by the user based on the recording selection page, generates a first initial video based on the first historical recording and the video tags carried by each recording in the first historical recording.

[0074] In one embodiment, Figure 2 As shown, a video processing method is provided, which is applied to Figure 1 Taking the device side terminal 11 and the system side terminal 12 as an example, the following steps are included:

[0075] S201: The device-side terminal 11 determines a target recording mode in response to a first control instruction from a user.

[0076] The first control instruction is used to specify the target recording mode selected by the user; the control form of the first control instruction includes but is not limited to voice control form, button control form, gesture control form, touch screen control form, etc.

[0077] Optionally, the device-side terminal 11 has a plurality of different video recording modes built in (including but not limited to normal video recording mode, slow-motion video recording mode, selfie video recording mode, etc.) to meet the needs of users in different scenarios, and the target video recording mode is one of the above-mentioned various different video recording modes. After the user sends a first control instruction to the device-side terminal 11 in the form of voice control, the device-side terminal 11 collects the user's first control instruction through the built-in microphone, and then uses automatic speech recognition technology (ASR, Automatic Speech Recognition) to convert the first control instruction into text to parse the user's intention, thereby determining the target video recording mode that the user wants to use. Then, the recording parameters corresponding to the target video recording mode are obtained, including but not limited to the camera to be turned on in the target video recording mode (such as the front camera or the rear camera), the resolution in the target video recording mode, the frame rate in the target video recording mode, the focus mode in the target video recording mode, etc.

[0078] Exemplarily, after the user inputs "selfie video mode" by voice, the device-side terminal 11 responds to the first control instruction input by the user's voice, determines that the target video mode the user wants to use is the selfie video mode, and then obtains the recording parameters corresponding to the selfie video mode, including the camera to be turned on in the selfie video mode (front camera), the resolution in the selfie video mode, the frame rate in the selfie video mode, the focus mode in the selfie video mode, etc.

[0079] In this embodiment, by responding to the first control instruction input by the user in the form of voice or other control, the target recording mode is determined, which helps the device side terminal configure the recording parameters corresponding to the target recording mode, ensures that the recording mode meets user needs, and improves the recording effect and user experience.

[0080] S202: The device-side terminal 11 starts recording in the target recording mode in response to the second control instruction of the user.

[0081] Among them, the second control instruction is used to control the device side terminal 11 to start recording in the target recording mode specified by the user; the control form of the second control instruction includes but is not limited to voice control form, button control form, gesture control form, touch screen control form, etc.

[0082] Optionally, the user may send a second control instruction to the device-side terminal 11 in the form of voice control and / or button control. After the user sends the second control instruction to the device-side terminal 11 in the form of voice control, the device-side terminal 11 collects the user's second control instruction through a built-in microphone, and uses automatic speech recognition technology to convert the second control instruction into text to analyze the user's intention, thereby starting the recording in the target recording mode selected by the user, that is, starting the recording with the recording parameters corresponding to the target recording mode.

[0083] Exemplarily, after the user inputs "selfie video mode" and "start video recording" by voice, the device-side terminal 11 responds to the second control instruction input by the user's voice and starts video recording with the recording parameters corresponding to the selfie video mode.

[0084] In this embodiment, by responding to the second control instruction input by the user in the form of voice control or the like, recording is started in the target recording mode, so that the user can start recording at any time according to actual needs, thereby improving the flexibility of recording.

[0085] S203: The device-side terminal 11 generates a highlight video tag for marking highlight moments in the video in response to the user's third control instruction.

[0086] Among them, the third control instruction is used to mark the highlight moment in the video; the control form of the third control instruction includes but is not limited to voice control form, button control form, gesture control form, touch screen control form, etc.

[0087] Optionally, during the recording process of the device-side terminal 11, the user can send a third control instruction to the device-side terminal 11 in the form of voice control to mark the highlight moment in the recording, that is, generate a highlight video tag for marking the highlight moment in the recording, so that the subsequent system-side terminal 12 can quickly locate the wonderful clips in the recording to generate a video according to the highlight video tag generated by the device-side terminal 11. It can be understood that the same recording can correspond to multiple highlight video tags for marking the highlight moment in the recording.

[0088] Specifically, after the user sends the third control instruction to the device side terminal 11 in the form of voice control, the device side terminal 11 collects the user's third control instruction through the built-in microphone, and uses automatic speech recognition technology to convert the third control instruction into text to parse the user's intention, thereby generating a highlight video tag containing the highlight moment timestamp information. It is worth noting that the highlight video tag is not limited to including the timestamp information of the highlight moment, and it can also include descriptive information of the highlight moment, etc.

[0089] Exemplarily, after the user inputs "mark highlight moment" or "lock video" by voice, the device-side terminal 11 generates a highlight video tag containing the timestamp information of the highlight moment (such as 10:25:32) in response to the third control instruction input by the user's voice. In addition, after the user inputs "mark highlight moment: goal moment" or "lock video, lock goal moment" by voice, the device-side terminal generates a highlight video tag containing the timestamp information of the highlight moment and the descriptive information of the highlight moment (such as goal moment) in response to the third control instruction input by the user's voice.

[0090] In this embodiment, by responding to a third control instruction input by the user in a control form such as voice, a highlight video tag for marking the highlight moment in the video is generated, so that the highlight moment in the video can be marked instantly without affecting the shooting, thereby simplifying the subsequent video processing flow.

[0091] S204: the device-side terminal 11 ends the video recording in response to the fourth control instruction of the user, and sends the video recording and the video tag carried by the video recording to the system-side terminal 12.

[0092] Among them, the fourth control instruction is used to control the device side terminal 11 to end the current recording; the control form of the fourth control instruction includes but is not limited to voice control form, button control form, gesture control form, touch screen control form, etc.

[0093] Optionally, the user may send a fourth control instruction to the device-side terminal 11 in the form of voice control and / or button control. After the user sends the fourth control instruction to the device-side terminal 11 in the form of voice control, the device-side terminal 11 collects the user's fourth control instruction through a built-in microphone, and uses automatic speech recognition technology to convert the fourth control instruction into text to parse the user's intention, thereby ending the currently ongoing video recording. Exemplarily, after the user inputs "end video recording" by voice, the device-side terminal 11 responds to the second control instruction input by the user's voice and ends the currently ongoing video recording.

[0094] In this embodiment, the recording is ended in response to the fourth control instruction input by the user in the form of voice or other control, and the recording and the video tag carried by the recording are sent to the system side terminal, so that the user can stop recording at any time according to actual needs, thereby improving the effectiveness of the recording content and further improving the subsequent recording processing efficiency of the system side terminal.

[0095] S205: The system-side terminal 12 obtains the video sent by the device-side terminal 11 and the video tag carried in the video.

[0096] Optionally, the system-side terminal 12 can be connected to the device-side terminal 11 by wireless means (such as Bluetooth, Wi-Fi, etc.) or wired means, so as to obtain the video sent by the device-side terminal 11 and the video tag (including the highlight video tag) carried by the video. In addition, after the system-side terminal 12 obtains the video sent by the device-side terminal 11 and the video tag carried by the video, it will also push the video generation prompt information in the APP matched with the device-side terminal 11.

[0097] Take the device side terminal 11 as an outdoor recorder and a smart phone as an example for explanation. It can be understood that the system side terminal 12 can be connected to the device side terminal 11 (outdoor recorder) by wireless means (such as Bluetooth, Wi-Fi, etc.) and / or wired means. The system side terminal 12 is installed with a recorder APP that matches the outdoor recorder.

[0098] For example, see Figure 3 After the user opens the recorder APP on the system side terminal 12, he can click the setting control 31 in the upper right corner of the recorder APP main interface 30 to complete the connection between the system side terminal 12 and the outdoor recorder. After the system side terminal 12 is successfully connected to the outdoor recorder, the recorder APP main interface 30 will display a video generation prompt message 32, prompting the user that a new video has been generated, and can create a film based on the generated video with one click.

[0099] In this embodiment, the system side terminal obtains the video sent by the device side terminal and the video tags carried by the video, and displays the video generation prompt information. This not only helps the system side terminal automatically select wonderful clips in the video according to the video and the tags carried by the video, but also helps the user to start the one-click film-making process based on the video generation prompt, thereby improving the video processing efficiency.

[0100] S206: The system-side terminal 12 displays a video recording selection page.

[0101] The video selection page includes the first historical video shot by the device-side terminal 11 within a preset time period (such as the last day, the last week, the last month, etc.), and the first historical video includes the above video. It can be understood that the video selection page can also include other historical videos shot by the device-side terminal 11 within other preset time periods (i.e., not the first preset time period) and videos selected for generating videos.

[0102] Optionally, the preset time period is the most recent day, and the system terminal 12 displays the first historical video shot by the device terminal 11 within the most recent day on the video selection page. In addition, the system terminal 12 can also display other historical videos shot by the device terminal 11 before the most recent day on the video selection page.

[0103] For example, when a user clicks Figure 3 After clicking the "View" button 33 in the main interface 30 of the recorder APP, the system side terminal 12 displays the following Figure 4The video selection page 40 shown. The video selection page 40 displays multiple groups of historical videos 41 captured by the device side terminal 11 and the video shooting dates 42 corresponding to each of the multiple groups of historical videos in reverse order of days. The first historical video 43 is all the videos captured by the outdoor recorder in the most recent day (shown as "Today, February 23"). In addition, the bottom of the video selection page 40 also displays the video 44 selected for generating the video. It is worth noting that the above-mentioned video 44 selected for generating the video can be automatically determined by the system side terminal 12, or can be selected by the user. By default, the system side terminal 12 uses the first historical video (i.e., all the videos captured by the device side terminal 11 in the most recent day) as the video 44 for generating the video.

[0104] In this embodiment, the system side terminal displays multiple groups of historical videos taken by the device side terminal and the video shooting dates corresponding to the multiple groups of historical videos in reverse order of days on the video selection page. This not only makes it convenient for users to intuitively see the videos taken by the device side terminal and improves the efficiency of users viewing videos, but also makes it convenient for users to select and combine different historical videos to generate videos based on the video selection page, thereby speeding up video processing and saving users' creation time.

[0105] S207: The system-side terminal 12 generates a first initial video based on the first historical video and the video tags carried by each video in the first historical video in response to the first trigger operation input by the user based on the video selection page.

[0106] The first trigger operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0107] For example, see Figure 4 The system terminal 12 responds to the user's click operation on the confirmation button 45 in the video selection page 40, based on the first historical video (i.e. Figure 4 The video 44 selected for video generation and the video tags (including highlight video tags) carried by each video in the first historical video are used to generate the first initial video. It is worth noting that in this embodiment, the video 44 selected for video generation is automatically selected by the system-side terminal 12, that is, in the process of generating the first initial video, there is no need for manual video selection, and the user only needs to perform a simple click operation to generate the video with one click.

[0108] In this embodiment, by responding to the first trigger operation input by the user based on the video selection page, a first initial video is generated based on the first historical video automatically selected by the system side terminal and the video tags carried by each video in the first historical video, which greatly reduces the time and energy of the user to manually edit the video, effectively simplifies the video processing flow, and realizes the intelligent generation of video.

[0109] The above-mentioned video recording processing method, at the device side terminal, determines the target video recording mode by responding to the first control instruction input by the user in the form of voice control or the like, which helps the device side terminal configure the recording parameters corresponding to the target video recording mode and improves the recording effect; starts the video recording in the target video recording mode by responding to the second control instruction input by the user in the form of voice control or the like, which facilitates the user to start the recording at any time according to the actual needs and improves the flexibility of the recording; generates a highlight video tag for marking the highlight moments in the video recording by responding to the third control instruction input by the user in the form of voice control or the like, which can instantly mark the highlight moments in the video recording without affecting the shooting and simplifies the subsequent video recording processing flow; ends the video recording by responding to the fourth control instruction input by the user in the form of voice control or the like, and sends the video recording and the video tag carried by the video recording to the system side terminal, which facilitates the user to stop the recording at any time according to the actual needs and improves the effectiveness of the video recording content. At the system side terminal, by obtaining the video sent by the device side terminal and the video tags carried by the video, the system side terminal can automatically select the wonderful clips in the video according to the video and the tags carried by the video; by displaying the video selection page, the video selection page includes the first historical video shot by the device side terminal within the preset time period, and the first historical video includes the video, so that the user can intuitively see all the videos shot by the device side terminal within the preset time period, thereby improving the efficiency of the user viewing the video; by responding to the first trigger operation input by the user based on the video selection page, the first initial video is generated based on the first historical video and the video tags carried by each video in the first historical video, which greatly reduces the time and energy of the user to manually edit the video, effectively simplifies the video processing process, and realizes the intelligent generation of the video. The entire video processing process improves the video quality while eliminating the need for the user to spend a lot of time and energy to make a video based on the exported video. The user only needs to perform a simple trigger operation, and the system can automatically process the video and intelligently generate the video, effectively improving the video processing efficiency.

[0110] In one embodiment, Figure 5 As shown, another video processing method is provided, which is applied to Figure 1 Taking the device side terminal 11 and the system side terminal 12 as an example, the following steps are included:

[0111] S501: The device-side terminal 11 determines a target recording mode in response to a first control instruction from a user, and generates a video type tag corresponding to the target recording mode.

[0112] Among them, the control form of the first control instruction includes but is not limited to voice control form, button control form, gesture control form, touch screen control form, etc.

[0113] Optionally, the device side terminal 11 has multiple different video recording modes (including but not limited to normal video recording mode, slow video recording mode, self-timer video recording mode, etc.) built in to meet the needs of users in different scenarios, and the target video recording mode is one of the above multiple different video recording modes. After the user sends a first control instruction to the device side terminal 11 in the form of voice control, the device side terminal 11 collects the user's first control instruction through the built-in microphone, and then uses automatic voice recognition technology to convert the first control instruction into text to analyze the user's intention, thereby determining the target video recording mode that the user wants to use, and correspondingly generates a video type label corresponding to the target video recording mode, such as a normal video recording label, a slow video recording label, a Selfie video recording label, etc., so that the system side terminal 12 can then intelligently extract key video clips in the video based on the video type label. Then the device side terminal 11 obtains the recording parameters corresponding to the target video recording mode, including but not limited to the camera to be turned on in the target video recording mode (such as a front camera or a rear camera), the resolution in the target video recording mode, the frame rate in the target video recording mode, the focus mode in the target video recording mode, etc.

[0114] Exemplarily, after the user inputs "selfie video mode" by voice, the device-side terminal 11 responds to the first control instruction input by the user's voice, determines that the target video mode the user wants to use is the selfie video mode, and generates a selfie video tag corresponding to the selfie video mode, so that the subsequent system-side terminal 12 can intelligently extract key video clips in the video based on the selfie video tag. Then the device-side terminal 11 obtains the recording parameters corresponding to the selfie video mode, including the camera to be turned on in the selfie video mode (front camera), the resolution in the selfie video mode, the frame rate in the selfie video mode, the focus mode in the selfie video mode, etc.

[0115] In this embodiment, by responding to the first control instruction input by the user in the form of voice or other control, the target recording mode is determined, which not only helps the system side terminal configure the recording parameters according to the target recording mode and ensures that the recording mode meets the user's needs, but also helps the device side terminal generate a video type label based on the target recording mode selected by the user, so that the system side terminal can subsequently intelligently extract key video clips in the recording based on the video type label, thereby improving the recording effect and simplifying the subsequent recording processing process, thereby effectively improving the recording processing efficiency.

[0116] S502: The device-side terminal 11 starts recording in the target recording mode in response to the second control instruction of the user.

[0117] Specifically, S502 is consistent with S202 and will not be described in detail here.

[0118] S503: The device-side terminal 11 generates a highlight video tag for marking highlight moments in the video in response to the user's third control instruction.

[0119] Specifically, S503 is consistent with S203 and will not be described in detail here.

[0120] S504: the device-side terminal 11 ends the video recording in response to the fourth control instruction of the user, and sends the video recording and the video tag carried by the video recording to the system-side terminal 12.

[0121] The video tags include a video type tag corresponding to the target video recording mode, a highlight video tag for marking highlight moments in the video recording, a video scene tag for marking video scenes in the video recording, etc. The video scenes in the above-mentioned video recordings include one or more of human figures, scenery (such as natural landscapes, urban scenery, etc.), vehicles, and sports scenes (such as walking, cycling, skiing, etc.).

[0122] It can be understood that the above-mentioned video type label and highlight video label are generated based on the above-mentioned first control instruction and the third control instruction, respectively. The above-mentioned video scene label is intelligently generated based on the scene recognition model of the device side terminal 11, and is used to identify the video scenes corresponding to different video clips. The above-mentioned video scene label can be generated during the recording process of the device side terminal 11, or after the device side terminal finishes recording, which is not limited in the embodiment of the present application.

[0123] It is worth noting that the highlight video tag and video scene tag carried by the above-mentioned video recording can be one or more. For example, if the user issues the third control instruction multiple times during the video recording process of the device-side terminal 11, the device-side terminal 11 will generate multiple highlight video tags for marking the highlight moments in the video recording in response to all the third control instructions issued by the user. If the video recorded by the device-side terminal 11 contains a variety of different video scenes, the device-side terminal 11 will generate a plurality of video scene tags for marking the video scenes in the video recording based on the above-mentioned variety of different video scenes. In addition, the above-mentioned highlight video tag contains the timestamp information corresponding to the highlight moment, which is used to mark the specific time point when the highlight moment appears in the video recording; the above-mentioned video scene tag contains the timestamp information corresponding to the video scene, which is used to mark the specific time period when the video scene appears in the video recording.

[0124] In this embodiment, the device side terminal sends the video and the video type tag, highlight video tag and video scene tag carried by the video to the system side terminal, so that the subsequent system side terminal can quickly locate the valuable segments in the video according to the above-mentioned multiple different dimensional tags, thereby generating a video based on the valuable segments, effectively simplifying the video processing flow and improving the video processing efficiency.

[0125] S505: The system-side terminal 12 obtains the video sent by the device-side terminal 11 and the video tag carried in the video.

[0126] The video tags include a video type tag corresponding to the target video recording mode, a highlight video tag for marking highlight moments in the video recording, a video scene tag for marking video scenes in the video recording, etc. The video scenes in the above-mentioned video recordings include one or more of human figures, scenery (such as natural landscapes, urban scenery, etc.), vehicles, and sports scenes (such as walking, cycling, skiing, etc.).

[0127] Specifically, S505 is consistent with S205 and will not be repeated here.

[0128] S506: The system-side terminal 12 displays a video selection page.

[0129] The video selection page includes the first historical video shot by the device-side terminal within a preset time period, and the first historical video includes a video.

[0130] Specifically, S506 is consistent with S206 and will not be described in detail here.

[0131] S507: In response to the first trigger operation input by the user based on the video selection page, the system-side terminal 12 inputs the first historical video into the video content recognition model to obtain the recognition result of each video in the first historical video.

[0132] The first trigger operation includes, but is not limited to, a custom interactive action such as clicking, sliding, and long pressing. The recognition results of each video in the first historical video include, but are not limited to, a voice recognition result obtained after performing voice recognition on each video in the first historical video, a face recognition result obtained after performing face recognition on each video in the first historical video, and the like.

[0133] Optionally, the system side terminal 12 responds to the first trigger operation input by the user based on the video selection page, inputs the first historical video into the video content recognition model, and obtains the video content recognition results of each video in the first historical video, and the video content recognition results include the voice recognition results obtained after performing voice recognition on each video in the first historical video and the face recognition results obtained after performing face recognition on each video in the first historical video. The video content recognition model can be deployed in the cloud or in the system side terminal 12, which is not limited in the embodiment of the present application.

[0134] Specifically, the system-side terminal 12 responds to the first trigger operation input by the user based on the video selection page, and after the first historical video is input into the video content recognition model, the video content recognition model extracts the audio and video frames of each video in the first historical video. Then, voice recognition is performed on the audio of each extracted video, and the audio is converted into text to obtain the voice recognition result corresponding to each video. Face recognition is performed on the video frames of each extracted video, and the video frames with the target face are marked as target video frames, and the face recognition results corresponding to each video are obtained. Among them, the target face is a clear and unobstructed face in the video.

[0135] S508: The system-side terminal 12 extracts a first key video segment from the first historical video based on the recognition results of each video in the first historical video and the video tags carried by each video in the first historical video.

[0136] The recognition results of each video in the first historical video include the voice recognition results corresponding to each video in the first historical video and the face recognition results corresponding to each video in the first historical video. The video tags carried by each video in the first historical video include the video type tag corresponding to the target video mode, the highlight video tag for marking the highlight moment in the video, and the video scene tag for marking the video scene in the video. The first key video clip includes the highlight video clip corresponding to the highlight moment.

[0137] Optionally, the first key video clip also includes a phase video clip corresponding to valuable audio in the first historical video, a phase video clip corresponding to a video frame (target video frame) in which a target face exists in the first historical video, and a phase video clip corresponding to a video scene label marked in the video whose video type label in the first historical video is a slow-motion video label and a selfie video label.

[0138] Specifically, the system-side terminal 12 performs semantic analysis on the speech recognition results corresponding to each video in the first historical video, and retains the stage video segments whose audio contains important information, dialogues or other meaningful content as the stage video segments corresponding to the valuable audio. For example, during the filming process of the device-side terminal 11, the user said a paragraph to describe the beautiful scenery captured by the device-side terminal 11, then the system-side terminal 12 will correspondingly retain the stage video segment containing the user's words. For the face recognition results corresponding to each video in the first historical video, the system-side terminal 12 retains a segment of video before and after each target video frame in the first historical video, for example, retains a video segment of a preset length (such as 3 seconds) before and after the target video frame as the stage video segment corresponding to the target video frame.

[0139] In addition, the system side terminal 12 uses the timestamp information corresponding to the highlight moment in the highlight video tag for the video in the first historical video to extract the highlight video segment corresponding to the highlight moment in the first historical video, for example, retaining the video segment of a preset length (such as 5 seconds) before and after the highlight moment as the highlight video segment corresponding to the highlight moment. The system side terminal 12 also screens out the videos with the video type tags of the slow-motion video tag and the Selfie video tag according to the video type tags carried by each video in the first historical video, that is, screens out the slow-motion video and the self-timer video in the first historical video. Then, for the video scene tags carried by the screened slow-motion video and the self-timer video, the timestamp information corresponding to the video scene in the video scene tag is used to extract the stage video segments in the slow-motion video and the Selfie video.

[0140] It can be understood that the system side terminal 12 can extract the phase video clips corresponding to the valuable audio in the first historical recording, the phase video clips corresponding to the target video frame, the highlight video clips corresponding to the highlight moment, and the phase video clips in the slow-motion recording and the selfie recording as the first key video clip in the first historical recording.

[0141] S509: The system-side terminal 12 removes the jittery image in the first key video segment to obtain a first initial video segment.

[0142] Optionally, the system side terminal 12 extracts video frames frame by frame from the first key video clip, and uses motion estimation technology (such as optical flow method, feature point matching, etc.) to detect the motion changes between each frame, and calculates the displacement of each frame relative to a reference frame (such as the first frame or the middle frame) based on the motion estimation result, and then uses a motion compensation algorithm to correct the position of each video frame to eliminate the jitter effect, and uses a filter to smooth the corrected frames, and then recombines the processed frames into a new video clip, i.e., the first initial video clip.

[0143] S510: The system-side terminal 12 generates a first initial video based on the first initial video segment.

[0144] Optionally, the system-side terminal 12 removes the jittered first video clips and splices the videos in chronological order to generate a first initial video.

[0145] In this embodiment, the user only needs to perform a simple trigger operation, and the system side terminal can extract the first key video clip in the first historical video based on the first historical video and the video tags carried by each video in the first historical video, and remove the jittery image in the first key video clip, thereby intelligently generating the first initial video, which improves the video processing efficiency while ensuring the video processing effect.

[0146] S511: The system-side terminal 12 displays a video editing page.

[0147] The video editing page includes a video preview area, a segment editing area, and a template editing area. The video preview area is used to display a preview video associated with the first initial video, the segment editing area is used to display the first initial video segment in the first initial video, and the template editing area is used to display multiple video templates, each of which has a different video output duration and video presentation effect.

[0148] For example, see Figure 6 The video editing page 60 includes a video preview area 61, a segment editing area 62, and a template editing area 63. The system-side terminal 12 displays the first initial video generated above in the video preview area 61. The user can edit the first initial video based on the segment editing area 62 and the template editing area 63. Each time an editing operation is performed, the edited video will be displayed in real time in the video preview area 61 for the user to browse and view the editing effect.

[0149] In this embodiment, the system side terminal divides the video editing page into a video preview area, a clip editing area and a template editing area, which not only makes it convenient for users to edit the initial video based on the video editing page, but also ensures that users can preview the edited video effects in real time based on the video editing page, making the video editing process more personalized, efficient and convenient, and improving the efficiency of video recording processing.

[0150] S512: The system-side terminal 12 adjusts the video duration of any first initial video segment in the segment editing area in response to the user's segment cropping operation on any first initial video segment.

[0151] The clip cropping operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0152] For example, see Figure 6 In response to the user's click and progress bar cropping operation on one of the first initial video segments 64 in the segment editing area 62, the system side terminal 12 adjusts the video duration of the first initial video segment 64 in the first initial video. It can be understood that the user can also perform segment cropping operations on other first initial video segments in the segment editing area 62, such as the first initial video segment 65, the first initial video segment 66, the first initial video segment 67, etc., so as to adjust the video duration accordingly.

[0153] Specifically, in response to the user's click operation on one of the first initial video segments 64 in the segment editing area 62, the system side terminal 12 displays the following Figure 7The segment editing pop-up window 70 is shown. The user can adjust and view the playback progress of the first initial video segment 64 based on the video progress bar 71 in the segment editing pop-up window 70, select a video interval for cropping, and click the confirmation control 72 in the upper right corner of the segment editing pop-up window 70 to save the edited first initial video segment 64, thereby adjusting the video duration of the first initial video segment 64.

[0154] It is worth noting that in response to the user's clip cropping operation on any first initial video clip in the clip editing area, after adjusting the video length of any first initial video clip, the complete video obtained after clip cropping will be displayed in the video preview area of ​​the video editing page.

[0155] S513: The system-side terminal 12 adjusts the playback speed of any first initial video segment in the segment editing area in response to the user's speed adjustment operation on any first initial video segment.

[0156] The speed adjustment operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0157] For example, see Figure 6 , the system-side terminal 12 adjusts the playback speed of the first initial video segment 64 in response to the user's click and speed change type selection operation on one of the first initial video segments 64 in the segment editing area 62. It can be understood that the user can also perform speed adjustment operations on other first initial video segments in the segment editing area 62, such as the first initial video segment 65, the first initial video segment 66, the first initial video segment 67, etc., so as to adjust the playback speed accordingly.

[0158] Specifically, in response to the user's click operation on one of the first initial video segments 64 in the segment editing area 62, the system side terminal 12 displays the following Figure 7 The clip editing pop-up window 70 is shown. The user can click the linear speed change control 73 or the curve speed change control 74 in the clip editing pop-up window 70 to select the corresponding speed change type. For example, after clicking the curve speed change control 74, the user can select the montage speed change type, jump speed change type, bullet time speed change type, etc. under the curve speed change in the clip editing pop-up window 70, and click the confirmation control 72 in the upper right corner of the clip editing pop-up window 70 to save the first initial video clip 64 obtained after editing, thereby adjusting the playback speed of the first initial video clip.

[0159] In addition, the system side terminal 12 can also adjust the background sound of any first initial video segment in response to the user's background sound adjustment operation on any first initial video segment in the segment editing area. Specifically, the system side terminal 12 displays the following in response to the user's click operation on one of the first initial video segments 64 in the segment editing area 62: Figure 7 After the segment editing pop-up window 70 is shown, the user can click on the background sound adjustment control 75 in the segment editing pop-up window 70 to choose to turn off or on the original sound in the first initial video segment 64, and click on the confirmation control 72 in the upper right corner of the segment editing pop-up window 70 to save the edited first initial video segment 64, thereby adjusting the background sound of the first initial video segment.

[0160] It is worth noting that in response to the user's speed adjustment operation on any first initial video clip in the clip editing area, after adjusting the playback speed of any first initial video clip, or in response to the user's background sound adjustment operation on any first initial video clip in the clip editing area, the complete video obtained after adjusting the playback speed or the complete video obtained after adjusting the background sound will be displayed accordingly in the video preview area of ​​the video editing page.

[0161] S514: The system-side terminal 12 replaces any first initial video segment in the segment editing area with a target video segment in response to the user's segment replacement operation on the first initial video segment.

[0162] The fragment replacement operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0163] For example, see Figure 6 In response to the user's long press operation on one of the first initial video segments 64 in the segment editing area 62, the system side terminal 12 displays a video segment replacement pop-up window. The user can select the target video segment he wants based on the multiple video segments displayed in the video segment replacement pop-up window and click it, so that the system side terminal 12 replaces the first initial video segment 64 with the target video segment selected by the user. It can be understood that the user can also perform segment replacement operations on other first initial video segments in the segment editing area 62, such as the first initial video segment 65, the first initial video segment 66, the first initial video segment 67, etc., so as to adjust the playback speed accordingly.

[0164] It is worth noting that the multiple video clips displayed in the above video clip replacement pop-up window can be captured from the first historical video and / or other historical videos, which is not limited in the embodiments of the present application. In response to the user's clip replacement operation on any first initial video clip in the clip editing area, after any first initial video clip is replaced with the target video clip, the complete video obtained after the clip replacement will be displayed in the video preview area of ​​the video editing page.

[0165] S515: The system-side terminal 12 adjusts the appearance order of any first initial video segment in the first initial video in response to the user's order adjustment operation on any first initial video segment in the segment editing area.

[0166] The sequence adjustment operation includes but is not limited to customized interactive actions such as clicking, sliding, and long pressing. The segment editing area is used to display the initial video segments in the order in which the initial video segments appear in the initial video.

[0167] For example, see Figure 6 , the system-side terminal 12 adjusts the order of appearance of the first initial video segment 64 in the first initial video in response to the user's click and slide operation on the first initial video segment 64 in the segment editing area 62. It can be understood that the first initial video segment 64 appears before the first initial video segment 65 in the first initial video, and the first initial video segment 65 appears before the first initial video segment 66 in the first initial video. When the user clicks on the first initial video segment 64 and drags the first initial video segment 64 between the first initial video segment 65 and the first initial video segment 67 through a slide operation, the order of appearance of the first initial video segment 64 in the first initial video is also changed to be between the first initial video segment 65 and the first initial video segment 67.

[0168] It is worth noting that in response to the user's order adjustment operation on any first initial video segment in the segment editing area, after adjusting the appearance order of any first initial video segment in the first initial video, the complete video after the segment order is adjusted will be displayed in the video preview area of ​​the video editing page.

[0169] In this embodiment, the user can perform editing operations such as clip cropping, speed adjustment, clip replacement, and order adjustment on each first initial video clip in the clip editing area of ​​the video editing page according to actual needs, ensuring that the video content can be presented in the desired manner, thereby improving the flexibility of video processing. In addition, each time the user completes a clip editing operation, the edited video will be automatically displayed in the video preview area of ​​the video editing page, making it convenient for the user to view the editing results in a timely manner, thereby improving the convenience and intelligence of the operation. The above method improves the efficiency of video processing while ensuring the quality of video processing.

[0170] S516: The system-side terminal 12 adjusts the first initial video based on any video template in the template editing area in response to the user's third trigger operation on any video template.

[0171] The third trigger operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0172] Optionally, the multiple video templates displayed in the template editing area all predefine the video output duration, video background music, video trimming rules, video speed change strategy, the time and position of the video description text, etc., that is, the multiple video templates each correspond to different video output durations and video presentation effects. In response to the user's click operation on any video template in the template editing area, the system side terminal 12 adjusts the first initial video according to the video template selected by the user.

[0173] See also Figure 6 The template editing area 63 of the video editing page 60 displays multiple video templates, and the video output duration corresponding to the video template is marked under each video template. The user can select a video template based on the video output duration according to personal needs to adjust the first initial video.

[0174] Exemplarily, in response to a user clicking operation on a video template 68 in the template editing area 63 , the system-side terminal 12 applies the video template 68 to the initial video, and displays the complete video obtained after template editing in the video preview area 61 of the video editing page 60 .

[0175] In this embodiment, the user can adjust the first initial video based on any video template in the template editing area through a simple trigger operation. Since each video template contains elements such as the output duration of the video, the background music of the video, the cutting rules of the video, the speed change strategy of the video, the time and position of the video description text, etc., the user does not need to manually adjust these video elements one by one, which greatly simplifies the user's editing process and improves the efficiency of video generation. In addition, this embodiment is based on the strategy of starting from the end, allowing users to select video templates based on the expected final output video duration, effectively meeting the personalized needs of users. The above method improves the efficiency of video processing while ensuring the quality of video processing.

[0176] S517: The system-side terminal 12 responds to the fourth trigger operation input by the user based on the video editing page, and uses the preview video displayed in the video preview area as the target video.

[0177] The fourth trigger operation includes but is not limited to customized interactive actions such as clicking, sliding, and long pressing. The target video is a video that the user expects to obtain, which can be an unedited initial video or a video generated by the user editing the initial video through the video editing page.

[0178] Optionally, in response to a fourth trigger operation input by the user based on the video editing page, the system side terminal 12 uses the unedited initial video in the video preview area or the video generated after the user edits the initial video through the video editing page as the target video.

[0179] For example, see Figure 6 In response to the user clicking the save button 68 in the video editing page 60, the system side terminal 12 saves the unedited initial video in the video preview area 61 or the video generated after the user edits the initial video through the video editing page 60 as the target video.

[0180] In this embodiment, by responding to the fourth trigger operation input by the user based on the video editing page, the video associated with the initial video in the video preview area is saved as the target video, thereby avoiding data loss and improving the efficiency of video recording processing.

[0181] The above-mentioned video processing method makes the entire video processing process more efficient and convenient through a series of processes such as video mode selection, video start and stop control, video marking, video transmission, video content recognition, key content extraction, removal of jitter images, first initial video generation, video clip editing, video template editing, and target video saving. Users can not only quickly obtain high-quality first initial videos, but also personalize the first initial videos according to their own needs and preferences, thereby generating high-quality target video content. In addition, during the video editing process, users can also intuitively view the edited video based on the video preview area of ​​the video editing page, making the video editing process more efficient and intuitive; after the editing is completed, the user only needs to click to save the target video, which simplifies the video processing process and improves the user experience. The above-mentioned method improves the efficiency of video processing, ensures the quality of video processing, and effectively meets the personalized needs of users.

[0182] In one embodiment, Figure 8 As shown, another video processing method is provided, which is applied to Figure 1 Taking the device side terminal 11 and the system side terminal 12 as an example, the following steps are included:

[0183] S801: The device-side terminal 11 determines a target recording mode in response to a first control instruction from a user, and generates a video type tag corresponding to the target recording mode.

[0184] Specifically, S801 is consistent with S501 and will not be described in detail here.

[0185] S802: The device-side terminal 11 responds to the user's second control instruction and starts recording in the target recording mode.

[0186] Specifically, S802 is consistent with S202 and will not be repeated here.

[0187] S803: The device-side terminal 11 generates a highlight video tag for marking highlight moments in the video in response to the user's third control instruction.

[0188] Specifically, S803 is consistent with S203 and will not be described in detail here.

[0189] S804: The device-side terminal 11 ends the video recording in response to the fourth control instruction of the user, and sends the video recording and the video tag carried by the video recording to the system-side terminal.

[0190] Specifically, S804 is consistent with S504 and will not be described in detail here.

[0191] S805: The system-side terminal 12 obtains the video sent by the device-side terminal 11 and the video tag carried in the video.

[0192] The video tags include a video type tag corresponding to the target video recording mode, a highlight video tag for marking highlight moments in the video recording, a video scene tag for marking video scenes in the video recording, etc. The video scenes in the above-mentioned video recordings include one or more of human figures, scenery (such as natural landscapes, urban scenery, etc.), vehicles, and sports scenes (such as walking, cycling, skiing, etc.).

[0193] Specifically, S505 is consistent with S205 and will not be repeated here.

[0194] S806: The system-side terminal 12 displays a video recording selection page.

[0195] The video selection page includes the first historical video shot by the device-side terminal within a preset time period, and the first historical video includes a video.

[0196] Specifically, S806 is consistent with S206 and will not be described in detail here.

[0197] S807: In response to the second trigger operation input by the user based on the video selection page, the system-side terminal 12 generates a second initial video based on the second historical video selected by the user on the video selection page and the video tags carried by each video in the second historical video.

[0198] The second trigger operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0199] It can be understood that the video selection page includes the first historical video shot by the device-side terminal 11 within a preset time period (such as the most recent day, the most recent week, the most recent month, etc.) and other historical videos shot by the device-side terminal 11 within other preset time periods (i.e., not the first preset time period). Specifically, assuming that the above-mentioned preset time period is the most recent day, the video selection page includes both the first historical video shot by the device-side terminal 11 within the most recent day and other historical videos shot by the device-side terminal 11 before the most recent day. The user can select the video to be used for generating the video based on all the videos displayed on the video selection page.

[0200] For example, see Figure 4 The user can click the selection control 46 in the upper right corner of the video selection page 40 to start the video selection. When the user clicks any one or more videos in the multiple groups of historical videos 41, the system side terminal 12 responds to the user's click operation based on the video selection page input, and displays the second historical video selected by the user at the bottom of the video selection page 40 (corresponding to Figure 4The video 44 is selected for generating the video, and a second initial video is generated based on the second historical video selected by the user on the video selection page and the video tags carried by each video in the second historical video.

[0201] In one embodiment, the system side terminal 12 responds to a second trigger operation input by the user based on the video selection page, inputs the second historical video into the video content recognition model, and obtains the recognition result of each video in the second historical video; based on the recognition result of each video in the second historical video and the video tag carried by each video in the second historical video, extracts the second key video clip in the second historical video; the second key video clip includes the highlight video clip corresponding to the highlight moment; removes the jittery image in the second key video clip to obtain the second initial video clip; and generates the second initial video based on the second initial video clip.

[0202] The recognition results of each video in the second historical video include the voice recognition results corresponding to each video in the second historical video and the face recognition results corresponding to each video in the second historical video. The video tags carried by each video in the second historical video include the video type tag corresponding to the target video mode, the highlight video tag for marking the highlight moment in the video, and the video scene tag for marking the video scene in the video. The second key video clip includes the highlight video clip corresponding to the highlight moment.

[0203] Optionally, the second key video clip also includes the stage video clip corresponding to the valuable audio in the second historical video, the stage video clip corresponding to the video frame (target video frame) in which the target face exists in the second historical video, and the stage video clip corresponding to the video scene label marked in the video with the video type label of slow motion video label and selfie video label in the second historical video.

[0204] Specifically, the system-side terminal 12 performs semantic analysis on the speech recognition results corresponding to each video in the second historical video, and retains the stage video segments whose audio contains important information, dialogues or other meaningful content as the stage video segments corresponding to the valuable audio. For example, during the filming process of the device-side terminal 11, the user said a paragraph to describe the beautiful scenery captured by the device-side terminal 11, then the system-side terminal 12 will correspondingly retain the stage video segment containing the user's words. For the face recognition results corresponding to each video in the second historical video, the system-side terminal 12 retains a segment of video before and after each target video frame in the second historical video, for example, retains a video segment of a preset length (such as 3 seconds) before and after the target video frame as the stage video segment corresponding to the target video frame.

[0205] In addition, the system side terminal 12 uses the timestamp information corresponding to the highlight moment in the highlight video tag to extract the highlight video segment corresponding to the highlight moment in the second historical video for the video with the highlight video tag in the second historical video, for example, retaining the video segment of a preset length (such as 5 seconds) before and after the highlight moment as the highlight video segment corresponding to the highlight moment. The system side terminal 12 also screens out the videos with the video type tags of the slow-motion video tag and the Selfie video tag according to the video type tags carried by each video in the second historical video, that is, screens out the slow-motion video and the self-timer video in the second historical video. Then, for the video scene tags carried by the screened slow-motion video and the self-timer video, the timestamp information corresponding to the video scene in the video scene tag is used to extract the stage video segments in the slow-motion video and the Selfie video.

[0206] It can be understood that the system side terminal 12 can extract the phase video clips corresponding to the valuable audio in the second historical recording, the phase video clips corresponding to the target video frame, the highlight video clips corresponding to the highlight moment, and the phase video clips in the slow-motion recording and the selfie recording as the second key video clips in the second historical recording.

[0207] In addition, the system side terminal 12 extracts video frames from the second key video clip frame by frame, uses motion estimation technology to detect the motion changes between each frame, calculates the displacement of each frame relative to the reference frame based on the result of motion estimation, and then uses a motion compensation algorithm to correct the position of each video frame to eliminate the jitter effect, uses a filter to smooth the corrected frames, and then reassembles the processed frames into a new video clip, i.e., the second initial video clip. Then, the second initial video clip after removing the jittered image is spliced ​​in chronological order to generate a second initial video.

[0208] In this embodiment, the user only needs to perform a simple trigger operation, and the system side terminal can extract the second key video clip in the second historical video based on the second historical video and the video tags carried by each video in the second historical video, and remove the jittery image in the second key video clip, thereby intelligently generating the second initial video, thereby improving the video processing efficiency while ensuring the video processing effect.

[0209] S808: The system-side terminal 12 displays a video editing page.

[0210] Specifically, S808 is consistent with S511 and will not be described in detail here.

[0211] S809: The system-side terminal 12 adjusts the video duration of any second initial video segment in the segment editing area in response to the user's segment cropping operation on any second initial video segment.

[0212] The clip cropping operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0213] For example, see Figure 6 The system-side terminal 12 adjusts the video duration of the second initial video segment 64 in the second initial video in response to the user's click and progress bar cropping operation on one of the second initial video segments 64 in the segment editing area 62. It can be understood that the user can also perform segment cropping operations on other second initial video segments in the segment editing area 62, such as the second initial video segment 65, the second initial video segment 66, the second initial video segment 67, etc., so as to adjust the video duration accordingly.

[0214] Specifically, in response to the user's click operation on one of the second initial video segments 64 in the segment editing area 62, the system side terminal 12 displays the following Figure 7 The segment editing pop-up window 70 is shown. The user can adjust and view the playback progress of the second initial video segment 64 based on the video progress bar 71 in the segment editing pop-up window 70, select a video interval for cropping, and click the confirmation control 72 in the upper right corner of the segment editing pop-up window 70 to save the edited second initial video segment 64, thereby adjusting the video duration of the second initial video segment 64.

[0215] It is worth noting that in response to the user's clip cropping operation on any second initial video clip in the clip editing area, after adjusting the video length of any second initial video clip, the complete video obtained after clip cropping will be displayed in the video preview area of ​​the video editing page.

[0216] S810: The system-side terminal 12 adjusts the playback speed of any second initial video segment in the segment editing area in response to the user's speed adjustment operation on any second initial video segment.

[0217] The speed adjustment operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0218] For example, see Figure 6 , the system-side terminal 12 adjusts the playback speed of the second initial video segment 64 in response to the user's click and speed change type selection operation on one of the second initial video segments 64 in the segment editing area 62. It can be understood that the user can also perform speed adjustment operations on other second initial video segments in the segment editing area 62, such as the second initial video segment 65, the second initial video segment 66, the second initial video segment 67, etc., so as to adjust the playback speed accordingly.

[0219] Specifically, in response to the user's click operation on one of the second initial video segments 64 in the segment editing area 62, the system side terminal 12 displays the following Figure 7 The clip editing pop-up window 70 is shown. The user can click the linear speed change control 73 or the curve speed change control 74 in the clip editing pop-up window 70 to select the corresponding speed change type. For example, after clicking the curve speed change control 74, the user can select the montage speed change type, jump speed change type, bullet time speed change type, etc. under the curve speed change in the clip editing pop-up window 70, and click the confirmation control 72 in the upper right corner of the clip editing pop-up window 70 to save the edited second initial video clip 64, thereby adjusting the playback speed of the second initial video clip.

[0220] In addition, the system side terminal 12 can also adjust the background sound of any second initial video segment in response to the user's background sound adjustment operation on any second initial video segment in the segment editing area. Specifically, the system side terminal 12 displays the following in response to the user's click operation on one of the second initial video segments 64 in the segment editing area 62: Figure 7 After the segment editing pop-up window 70 is shown, the user can click on the background sound adjustment control 75 in the segment editing pop-up window 70 to choose to turn off or on the original sound in the second initial video segment 64, and click on the confirmation control 72 in the upper right corner of the segment editing pop-up window 70 to save the edited second initial video segment 64, thereby adjusting the background sound of the second initial video segment.

[0221] It is worth noting that in response to the user's speed adjustment operation on any second initial video clip in the clip editing area, after adjusting the playback speed of any second initial video clip, or in response to the user's background sound adjustment operation on any second initial video clip in the clip editing area, the complete video obtained after adjusting the playback speed or the complete video obtained after adjusting the background sound will be displayed accordingly in the video preview area of ​​the video editing page.

[0222] S811: The system-side terminal 12 replaces any second initial video segment in the segment editing area with a target video segment in response to a segment replacement operation performed by the user.

[0223] The fragment replacement operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0224] For example, see Figure 6In response to the user's long press operation on one of the second initial video segments 64 in the segment editing area 62, the system side terminal 12 displays a video segment replacement pop-up window, and the user can select the target video segment he wants based on the multiple video segments displayed in the video segment replacement pop-up window and click it, so that the system side terminal 12 replaces the second initial video segment 64 with the target video segment selected by the user. It can be understood that the user can also perform segment replacement operations on other second initial video segments in the segment editing area 62, such as the second initial video segment 65, the second initial video segment 66, the second initial video segment 67, etc., so as to adjust the playback speed accordingly.

[0225] It is worth noting that the multiple video clips displayed in the above video clip replacement pop-up window can be captured from the second historical video and / or other historical videos, which is not limited in the embodiments of the present application. In response to the user's clip replacement operation on any second initial video clip in the clip editing area, after any second initial video clip is replaced with the target video clip, the complete video obtained after the clip replacement will be displayed in the video preview area of ​​the video editing page.

[0226] S812: The system-side terminal 12 adjusts the appearance order of any second initial video segment in the second initial video in response to the user's order adjustment operation on any second initial video segment in the segment editing area.

[0227] The sequence adjustment operation includes but is not limited to customized interactive actions such as clicking, sliding, and long pressing. The segment editing area is used to display the initial video segments in the order in which the initial video segments appear in the initial video.

[0228] For example, see Figure 6 , the system-side terminal 12 adjusts the order of appearance of the second initial video segment 64 in the second initial video in response to the user's click and slide operation on the second initial video segment 64 in the segment editing area 62. It can be understood that the second initial video segment 64 appears before the second initial video segment 65 in the second initial video, and the second initial video segment 65 appears before the second initial video segment 66 in the second initial video. When the user clicks on the second initial video segment 64 and drags the second initial video segment 64 between the second initial video segment 65 and the second initial video segment 67 by sliding, the order of appearance of the second initial video segment 64 in the second initial video is also changed to be between the second initial video segment 65 and the second initial video segment 67.

[0229] It is worth noting that in response to the user's order adjustment operation on any second initial video segment in the segment editing area, after adjusting the appearance order of any second initial video segment in the second initial video, the complete video after the segment order is adjusted will be displayed in the video preview area of ​​the video editing page.

[0230] In this embodiment, the user can perform editing operations such as clip cropping, speed adjustment, clip replacement, and sequence adjustment on each second initial video clip in the clip editing area of ​​the video editing page according to actual needs, ensuring that the video content can be presented in the desired manner, thereby improving the flexibility of video processing. In addition, each time the user completes a clip editing operation, the edited video will be automatically displayed in the video preview area of ​​the video editing page, making it convenient for the user to view the editing results in a timely manner, thereby improving the convenience and intelligence of the operation. The above method improves the efficiency of video processing while ensuring the quality of video processing.

[0231] S813: The system-side terminal 12 adjusts the second initial video based on any video template in the template editing area in response to the user's third trigger operation on any video template.

[0232] The third trigger operation includes but is not limited to custom interactive actions such as clicking, sliding, and long pressing.

[0233] Optionally, the multiple video templates displayed in the template editing area all predefine the video output duration, video background music, video trimming rules, video speed change strategy, the time and position of the video description text, etc., that is, the multiple video templates each correspond to different video output durations and video presentation effects. In response to the user's click operation on any video template in the template editing area, the system side terminal 12 adjusts the second initial video according to the video template selected by the user.

[0234] See also Figure 6 The template editing area 63 of the video editing page 60 displays multiple video templates, and the video output duration corresponding to the video template is marked under each video template. The user can select a video template based on the video output duration according to personal needs to adjust the second initial video.

[0235] Exemplarily, in response to a user clicking operation on a video template 68 in the template editing area 63 , the system-side terminal 12 applies the video template 68 to the initial video, and displays the complete video obtained after template editing in the video preview area 61 of the video editing page 60 .

[0236] In this embodiment, the user can adjust the second initial video based on any video template in the template editing area through a simple trigger operation. Since each video template contains elements such as the output duration of the video, the background music of the video, the cutting rules of the video, the speed change strategy of the video, the time and position of the video description text, etc., the user does not need to manually adjust these video elements one by one, which greatly simplifies the user's editing process and improves the efficiency of video generation. In addition, this embodiment is based on the strategy of starting from the end, allowing users to select video templates based on the expected final output video duration, effectively meeting the personalized needs of users. The above method improves the efficiency of video processing while ensuring the quality of video processing.

[0237] S814: The system-side terminal 12 responds to the fourth trigger operation input by the user based on the video editing page, and uses the preview video displayed in the video preview area as the target video.

[0238] Specifically, S814 is consistent with S517 and will not be repeated here.

[0239] The above-mentioned video processing method makes the entire video processing process more efficient and convenient through a series of processes such as video mode selection, video start and stop control, video marking, video transmission, video content recognition, key content extraction, removal of jitter images, second initial video generation, video clip editing, video template editing, and target video saving. Users can not only quickly obtain high-quality second initial videos, but also personalize the second initial videos according to their own needs and preferences, thereby generating high-quality target video content. In addition, during the video editing process, users can also intuitively view the edited video based on the video preview area of ​​the video editing page, making the video editing process more efficient and intuitive; after the editing is completed, the user only needs to click to save the target video, which simplifies the video processing process and improves the user experience. The above-mentioned method improves the efficiency of video processing, ensures the quality of video processing, and effectively meets the personalized needs of users.

[0240] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0241] Based on the inventive concept of the above-mentioned video processing method, Fig. 9 As shown, the embodiment of the present application further provides a video processing device 900 for implementing the video processing method applied to the system side terminal. The video processing device 900 includes:

[0242] The acquisition module 901 is used to acquire the video sent by the device side terminal and the video tag carried by the video;

[0243] Display module 902, used to display a video selection page; the video selection page includes a first historical video shot by the device side terminal within a preset time period, and the first historical video includes a video;

[0244] The response module 903 is used to generate a first initial video based on the first historical video and the video tags carried by each video in the first historical video in response to a first trigger operation input by the user based on the video selection page.

[0245] In one possible implementation, the video tag includes a highlight video tag for marking highlight moments in the video; the response module 903 is specifically used to respond to a first trigger operation input by the user based on the video selection page, input the first historical video into the video content recognition model, and obtain recognition results of each video in the first historical video; based on the recognition results of each video in the first historical video and the video tags carried by each video in the first historical video, extract the first key video clip in the first historical video; the first key video clip includes a highlight video clip corresponding to the highlight moment; remove the jittery image in the first key video clip to obtain a first initial video clip; based on the first initial video clip, generate a first initial video.

[0246] In a possible implementation, the response module 903 is further configured to generate a second initial video in response to a second trigger operation input by the user based on the video selection page, based on a second historical video selected by the user on the video selection page and a video tag carried by each video in the second historical video.

[0247] In one possible implementation, the response module 903 is also used to respond to a second trigger operation input by the user based on the video selection page, input the second historical video into the video content recognition model, and obtain the recognition result of each video in the second historical video; based on the recognition result of each video in the second historical video and the video tag carried by each video in the second historical video, extract the second key video clip in the second historical video; remove the jittery image in the second key video clip to obtain a second initial video clip; and generate a second initial video based on the second initial video clip.

[0248] In a possible implementation, the display module 902 is further used to display a video editing page; the video editing page includes a video preview area, and the video preview area is used to display a preview video associated with the first initial video.

[0249] In a possible implementation, the second acquisition module 802 is specifically configured to acquire user binding information; and generate video description information corresponding to the multiple video clips according to the video capture dates corresponding to the multiple video clips and the user binding information.

[0250] In one possible implementation, the video editing page also includes a segment editing area, which is used to display the first initial video segment in the first initial video; the response module 903 is also used to adjust the video length of any first initial video segment in response to a user's segment cropping operation on any first initial video segment in the segment editing area; and / or adjust the playback speed of any first initial video segment in response to a user's speed adjustment operation on any first initial video segment in the segment editing area; and / or replace any first initial video segment with a target video segment in response to a user's segment replacement operation on any first initial video segment in the segment editing area; and / or adjust the appearance order of any first initial video segment in the first initial video in response to a user's order adjustment operation on any first initial video segment in the segment editing area.

[0251] In one possible implementation, the video editing page also includes a template editing area, which is used to display multiple video templates, and the multiple video templates each have a different corresponding video output duration and video presentation effect; the response module 903 is also used to respond to the user's third trigger operation on any video template in the template editing area, and adjust the first initial video based on any video template.

[0252] In a possible implementation, the response module 903 is further configured to respond to a fourth trigger operation input by the user based on the video editing page, and use the preview video displayed in the video preview area as the target video.

[0253] Based on the inventive concept of the above-mentioned video processing method, Fig.10 As shown, the embodiment of the present application further provides a video processing device 1000 for implementing the video processing method applied to the device side terminal. The video processing device 1000 includes:

[0254] The first response module 1001 is used to determine a target recording mode in response to a first control instruction of a user;

[0255] The second response module 1002 starts recording in a target recording mode in response to a second control instruction of the user;

[0256] The third response module 1003 generates a highlight video tag for marking a highlight moment in the video in response to a third control instruction of the user;

[0257] The fourth response module 1004, in response to a fourth control instruction of the user, ends the video recording, and sends the video recording and the video tag carried by the video recording to the system side terminal, wherein the video tag includes a highlight video tag for marking a highlight moment in the video recording, so that the system side terminal obtains the video recording and the video tag carried by the video recording, displays a video recording selection page, wherein the video recording selection page includes a first historical video recording taken by the device side terminal within a preset time period, wherein the first historical video recording includes the video recording, and generates a first initial video based on the first historical video recording and the video tags carried by each video recording in the first historical video recording in response to a first trigger operation input by the user based on the video recording selection page;

[0258] Among them, the control forms of the first control instruction, the second control instruction, the third control instruction and the fourth control instruction include voice control forms.

[0259] Each module in the video processing device 900 and the video processing device 1000 can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0260] The embodiment of the present application also provides an electronic device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.11As shown. The electronic device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the electronic device is used to exchange information between the processor and an external device. The communication interface of the electronic device is used to communicate with an external user terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a video processing method is implemented. The display unit of the electronic device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the electronic device casing, or an external keyboard, touchpad or mouse.

[0261] Those skilled in the art will understand that Fig.11 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0262] The present application also provides a computer storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in the above embodiment. If the components of the above electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer readable storage medium.

[0263] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer storage medium or transmitted through the computer storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer storage medium can be any available medium that a computer can access or a data storage device such as a server, data center, etc. that contains one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0264] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0265] The embodiments described above are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements made to the technical solutions of the present application by ordinary technicians in this field should fall within the protection scope determined by the claims.

[0266] The above describes a specific embodiment of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A video recording processing method, applied to a system side terminal, characterized in that: The method comprises: Obtaining the video sent by the device-side terminal and the video tag carried by the video; Displaying a video selection page; the video selection page includes a first historical video shot by the device-side terminal within a preset time period, the first historical video including the video; In response to a first trigger operation input by a user based on the video selection page, a first initial video is generated based on the first historical video and video tags carried by each video in the first historical video.

2. The method according to claim 1, characterized in that The video tags include highlight video tags for marking highlight moments in the video; The step of generating a first initial video based on the first historical video and video tags carried by each video in the first historical video in response to a first trigger operation input by the user based on the video selection page includes: In response to a first trigger operation input by a user based on the video selection page, inputting the first historical video into a video content recognition model to obtain recognition results of each video in the first historical video; Extracting a first key video segment from the first historical video based on the recognition results of each video in the first historical video and the video tags carried by each video in the first historical video; the first key video segment includes a highlight video segment corresponding to the highlight moment; Removing the jittery images in the first key video segment to obtain a first initial video segment; A first initial video is generated based on the first initial video segment.

3. The method according to claim 1, characterized in that After displaying the video selection page, the method further includes: In response to a second trigger operation input by the user based on the video selection page, a second initial video is generated based on a second historical video selected by the user on the video selection page and video tags carried by each video in the second historical video.

4. The method according to claim 3, characterized in that In response to the second trigger operation input by the user based on the video selection page, generating a second initial video based on the second historical video selected by the user on the video selection page and the video tags carried by each video in the second historical video, includes: In response to a second trigger operation input by the user based on the video selection page, inputting the second historical video into a video content recognition model to obtain recognition results of each video in the second historical video; Extracting a second key video segment from the second historical video based on the recognition result of each video in the second historical video and the video tag carried by each video in the second historical video; removing the jittery images in the second key video segment to obtain a second initial video segment; Based on the second initial video segment, a second initial video is generated.

5. The method according to claim 1, characterized in that After generating the first initial video based on the first historical video and the video tags carried by each video in the first historical video in response to the first trigger operation input by the user based on the video selection page, the method further includes: A video editing page is displayed; the video editing page includes a video preview area, and the video preview area is used to display a preview video associated with the first initial video.

6. The method according to claim 5, characterized in that The video editing page further includes a segment editing area, wherein the segment editing area is used to display a first initial video segment in the first initial video; After displaying the video editing page, the method further includes: In response to a segment cropping operation performed by the user on any one of the first initial video segments in the segment editing area, adjusting the video duration of the any one of the first initial video segments; and / or In response to a speed adjustment operation by the user on any one of the first initial video segments in the segment editing area, adjusting the playback speed of the any one of the first initial video segments; and / or In response to a segment replacement operation of the user on any one of the first initial video segments in the segment editing area, replacing the any one of the first initial video segments with a target video segment; and / or In response to the user's operation of adjusting the order of any one of the first initial video segments in the segment editing area, the appearance order of the any one of the first initial video segments in the first initial video is adjusted.

7. The method according to claim 5, characterized in that The video editing page also includes a template editing area, which is used to display multiple video templates, each of which has different corresponding video output durations and video presentation effects; After displaying the video editing page, the method further includes: In response to a third trigger operation by the user on any one of the video templates in the template editing area, the first initial video is adjusted based on the any one of the video templates.

8. The method according to claim 5, characterized in that The method further comprises: In response to a fourth trigger operation input by the user based on the video editing page, the preview video displayed in the video preview area is used as a target video.

9. A video recording processing method, applied to a device side terminal, characterized in that: The method comprises: In response to a first control instruction from a user, determining a target video recording mode; In response to a second control instruction of the user, starting recording in the target recording mode; In response to a third control instruction of the user, generating a highlight video tag for marking a highlight moment in the video; In response to a fourth control instruction of the user, the video recording is ended, and the video recording and the video tag carried by the video recording are sent to the system side terminal, the video tag including a highlight video tag for marking a highlight moment in the video recording, so that the system side terminal obtains the video recording and the video tag carried by the video recording, and displays a video recording selection page, the video recording selection page including a first historical video recording taken by the device side terminal within a preset time period, the first historical video recording including the video recording, and in response to a first trigger operation input by the user based on the video recording selection page, a first initial video is generated based on the first historical video recording and the video tags carried by each video recording in the first historical video recording; Among them, the control forms of the first control instruction, the second control instruction, the third control instruction and the fourth control instruction include voice control forms.

10. A video processing device, applied to a system-side terminal, characterized in that: The device comprises: An acquisition module, used to acquire the video sent by the device-side terminal and the video tag carried by the video; A display module, configured to display a video selection page; the video selection page includes a first historical video shot by the device-side terminal within a preset time period, the first historical video including the video; The response module is used to generate a first initial video based on the first historical video and the video tags carried by each video in the first historical video in response to a first trigger operation input by the user based on the video selection page.

11. A video processing device, applied to a device side terminal, characterized in that: The device comprises: A first response module, used to determine a target recording mode in response to a first control instruction of a user; A second response module, in response to a second control instruction of the user, starts recording in the target recording mode; A third response module, in response to a third control instruction of the user, generates a highlight video tag for marking a highlight moment in the video; a fourth response module, in response to a fourth control instruction of the user, ending the video recording, and sending the video recording and the video tag carried by the video recording to the system side terminal, wherein the video tag includes a highlight video tag for marking a highlight moment in the video recording, so that the system side terminal obtains the video recording and the video tag carried by the video recording, displays a video recording selection page, wherein the video recording selection page includes a first historical video recording taken by the device side terminal within a preset time period, wherein the first historical video recording includes the video recording, and generates a first initial video based on the first historical video recording and the video tags carried by each video recording in the first historical video recording in response to a first trigger operation input by the user based on the video recording selection page; Among them, the control forms of the first control instruction, the second control instruction, the third control instruction and the fourth control instruction include voice control forms.

12. An electronic device, characterized in that: include: A processor and a memory; the memory stores a computer program, and the processor implements the method steps of any one of claims 1-8 or 9 when executing the computer program.

13. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1-8 or 9.

Images