Video editing methods, apparatus, electronic devices, and storage media

Abstract

Embodiments of this disclosure provide a video editing method, apparatus, electronic device, and storage medium. The method includes determining a target video material specified in a target editing task, and generating a target text material corresponding to the target video material in the target editing task based on related information of the target video material, wherein the editing operation instructed in the target editing task includes at least displaying the target text material on the image of the target video material, and, in response to a video generation command, performing an editing process on the material in the target editing task by the editing operation instructed in the target editing task to obtain a target video. This embodiment allows for auxiliary and rapid editing and input of text material for a target video by text rewriting, thereby improving video editing efficiency.

Description

Technical Field

[0001] This application claims the priority of a Chinese patent application filed on August 28, 2023, with an application number of 202311094468.7 and an invention title of "Video Editing Method, Apparatus, Electronic Device, and Storage Medium", and all the contents of the application are incorporated herein by reference.

[0002] Embodiments of the present disclosure relate to the technical field of video processing, and in particular, to a video editing method, apparatus, electronic device, and storage medium.

Background Art

[0003] With the development of video technology, videos have become an important medium in daily communication. In video editing, a text editing process is involved, and by adding text materials to the video, text suitable for the video is generated. However, when actually performing text editing on a video, excellent text materials and text can only be created when having good text editing capabilities. Without good text editing capabilities, the edited text does not meet the requirements, re-editing is required, and the efficiency of text editing for videos decreases.

Summary of the Invention

[0004] The present disclosure provides a video editing method, apparatus, electronic device, and storage medium, which can quickly edit and input appropriate text materials for a target video, and improve text editing efficiency and text adsorption.

[0005] In a first embodiment, an embodiment of the present disclosure provides a video editing method. The method includes determining a target video material specified in a target editing task, and generating a target text material corresponding to the target video material in the target editing task based on related information of the target video material, wherein the editing operation instructed in the target editing task includes at least displaying the target text material on the image of the target video material, and, in response to a video generation command, performing editing processing on the material in the target editing task by the editing operation instructed in the target editing task to obtain a target video.

[0006] In a second embodiment, embodiments of the present disclosure further provide a video editing apparatus. The apparatus includes: a determination module used to determine a target video material specified in a target editing task; a text generation module that generates a target text material corresponding to the target video material in the target editing task based on relevant information of the target video material, wherein the editing operation instructed in the target editing task is at least for displaying the target text material on an image of the target video material; and a video generation module that responds to a video generation command and performs editing processing on the material in the target editing task based on the editing operation instructed in the target editing task, and obtains a target video.

[0007] In a third embodiment, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising one or more processors and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute, for example, the video editing method described in any one of the embodiments described above.

[0008] In a fourth embodiment, an embodiment of the present disclosure provides a storage medium containing computer executable instructions, which, when executed by a computer processor, executes, for example, the video editing method described in any one of the embodiments described above.

[0009] It should be understood that the information contained herein is not intended to mark any core or important features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure are readily apparent from the following specification. [Brief explanation of the drawing]

[0010] The above and other features, advantages, and aspects of each embodiment of this disclosure will become more apparent by referring to the following specific embodiments in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals indicate the same or similar elements. It should be understood that the accompanying drawings are schematic diagrams and that parts and elements are not necessarily drawn to scale. [Figure 1] This is a flowchart of the video editing method provided in the embodiments of this disclosure. [Figure 2] This is a flowchart of another video editing method provided in the embodiments of this disclosure. [Figure 3] This is a flowchart of the process provided in the embodiments of this disclosure for generating candidate text materials corresponding to the target video material in a target editing task based on relevant information about the target video material. [Figure 4a] This is a schematic diagram of an interface transition to which text rewriting is triggered, to which an embodiment of the present disclosure is applied. [Figure 4b] This is a schematic diagram of an interface transition to which text editing is triggered, to which an embodiment of the present disclosure applies. [Figure 4c] This is a schematic diagram of an interface transition triggered by another text edit, to which an embodiment of the present disclosure applies. [Figure 5]This is a schematic diagram of an interface transition that displays text material after text rewriting is triggered, to which an embodiment of the present disclosure applies. [Figure 6] This is a schematic diagram of the interface transitions after selecting text material obtained by triggering text rewriting, to which an embodiment of the present disclosure is applied. [Figure 7] This is a schematic diagram of an interface for re-editing text material within a text preview area, to which an embodiment of the present disclosure is applied. [Figure 8] This is a schematic diagram of the interface transitions for recovering text material within a text preview area, to which an embodiment of the present disclosure is applied. [Figure 9] This is a schematic diagram of an interface transition to which the embodiments of the present disclosure apply, where text rewriting is performed after switching text styles to generate text material. [Figure 10] This is a schematic diagram of an interface transition to which more text material is loaded, to which an embodiment of the present disclosure applies. [Figure 11] This is a schematic diagram of the configuration of a video editing device provided in the embodiments of this disclosure. [Figure 12] This is a schematic diagram of the configuration of an electronic device that implements a video editing method, as provided in the embodiments of this disclosure. [Modes for carrying out the invention]

[0011] The embodiments of this disclosure will be described in more detail below with reference to the attached drawings. While the drawings show several embodiments of this disclosure, it should be understood that this disclosure is achievable in various forms and should not be construed as being limited to the embodiments described herein. Rather, these embodiments are provided to provide a more complete and thorough understanding of this disclosure. The drawings and embodiments of this disclosure are for illustrative purposes only and should not be used to limit the scope of protection of this disclosure.

[0012] It should be understood that each step described in the embodiments of the method of this disclosure may be performed in a different order and / or in parallel. Furthermore, embodiments of the method may include additional steps and / or omit the performance of the indicated steps. The scope of this disclosure is not limited in this respect.

[0013] As used herein, the expression “including” and its variations thereof are open inclusions, meaning “including but not limited to XXX.” The expression “based on XXX” means “at least partially based on XXX.” The expression “one embodiment” means “at least one embodiment.” The expression “another embodiment” means “at least one other embodiment.” The expression “several embodiments” means “at least several embodiments.” Related definitions of other terms are given below.

[0014] It should be noted that the concepts such as “first,” “second,” etc., as used in this disclosure are used solely to distinguish different devices, modules, or units, and do not limit the order or interdependence of the functions performed by these devices, modules, or units.

[0015] It should be noted that the modifiers “one” and “multiple” as used in this disclosure are illustrative and non-exclusive, and should be understood by those skilled in the art as “one or more” unless otherwise specified in the context.

[0016] The names of messages or information exchanged between multiple devices in embodiments of this disclosure are used solely for illustrative purposes and do not limit the scope of such messages or information.

[0017] Before using the technical forms disclosed in each embodiment of the present disclosure, it should be understood that the types, scope of use, usage scenarios, etc. of the personal information related to the present disclosure should be notified to the user by appropriate methods based on relevant laws and regulations, and the user's consent should be obtained.

[0018] For example, in response to receiving a voluntary request from the user, by sending presentation information to the user, it is clearly presented to the user that the operation to be executed requires the acquisition and use of the user's personal information. Thereby, based on the presentation information, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application, a server, or a storage medium that executes operations in the technical form of the present disclosure.

[0019] As a selective and non-limiting implementation method, the method of sending presentation information to the user in response to receiving a voluntary request from the user is, for example, the method of a pop-up window. In the pop-up window, the presentation information can be displayed by text. Furthermore, in the pop-up window, by displaying "Agree" or "Disagree" for the user to select, a selection control of personal information can be provided to the electronic device.

[0020] The process of notifying and obtaining the user's consent as described above is merely exemplary and does not limit the embodiments of the present disclosure. It should be understood that other methods that meet relevant laws and regulations are also applicable to the implementation methods of the present disclosure.

[0021] It should be understood that the data related to this technical form (including but not limited to the data itself, the acquisition and use of the data) should comply with relevant laws, regulations and related regulations.

[0022] Figure 1 is a flowchart of a video editing method provided by an embodiment of the present disclosure. The embodiment of the present disclosure applies when adding text material to target video material and editing the video. The method can be performed by a video editing device, which can be implemented by software and / or hardware and is generally integrated into any electronic device having network communication capabilities. The electronic device may be a mobile terminal, a PC terminal, or a server, etc.

[0023] As shown in Figure 1, the video editing method of the embodiment of this disclosure includes the following processes S101, S102, and S103.

[0024] In S101, the target video material specified in the target editing task is determined.

[0025] In S102, based on the relevant information of the target video material, target text material corresponding to the target video material in the target editing task is generated, and of these, the editing operation instructed in the target editing task is at least for displaying the target text material on the image of the target video material.

[0026] The target editing task is used to instruct the text material to be edited to the target video material, and the target video material and the text material provided by the editor are used to generate a target video with text effects. After obtaining the target video material, auxiliary text rewriting is performed using the target material, and automatic text rewriting generates target text material that matches the target video material in the target editing task.

[0027] Selectively, the editing operations instructed in a target editing task include trigger operations to ensure that the target text material is displayed on the image of the target video material by the target text material in the target editing task. For example, after generating target text material corresponding to the target video material in a target editing task, the target text element is placed and displayed on the image of the target video material in response to a trigger operation for selecting the generated target text material.

[0028] In S103, in response to the video generation command, editing is performed on the material within the target editing task according to the editing operations instructed in the target editing task, and the target video is obtained.

[0029] The target video material within the target editing task is added to a video track fragment that implements the target editing task, and the target text material, which is placed and displayed on the image of the target video material, is added to a text track fragment that implements the target editing task. The time of the track fragments of the text track fragment where the target text material is placed and the video track fragment where the target video material is placed is synchronized, and the target video is generated based on the material recorded in the time-synchronized text track fragment and video track fragment.

[0030] In the technical embodiment of the present disclosure, when executing a target editing task for target video material, target text material corresponding to the target video material in the target editing task is intelligently generated based on relevant information of the target video material, and the editing operations instructed in the target editing task are used to display the target text material on the image of the video material, and when a video generation command is triggered, the editing operations instructed in the target editing task execute editing processing on the material in the target editing task, thereby obtaining the target video. This embodiment can ensure the rapid organization of text material for video material even without high text creation ability, and can provide different text material according to different editing requests, thereby improving the editing efficiency of the target editing task for target video material.

[0031] Figure 2 is a flowchart of another video editing method provided by an embodiment of the present disclosure. Building upon the above-described embodiment, the technical embodiment of this embodiment further optimizes the process of generating target text material corresponding to the target video material in a target editing task based on relevant information of the target video material in the above embodiment. This embodiment can be combined with any selective aspect of one or more of the above-described embodiments.

[0032] As shown in Figure 2, the video editing method of the embodiment of this disclosure includes the following processes S201, S202, S203 and S204.

[0033] In S201, the target video material specified in the target editing task is determined.

[0034] In S202, candidate text materials corresponding to the target video material in the target editing task are generated based on the relevant information of the target video material. These candidate text materials are text materials generated by performing auxiliary text rewriting based on the relevant information of the target video material.

[0035] Selectively, the relevant information for the target video material may be the video frame image of the target video material or the audio material corresponding to the target video material, or it may be the initial text material introduced after selecting a text template based on the target video material, or the text material obtained by adjusting and modifying the introduced initial text material. Alternatively, the relevant information for the target video material may be the text material, image material, or audio material that has been edited, entered, adjusted, or modified in the input area corresponding to the target editing task, based on the target video material.

[0036] As a selective and non-restrictive implementation method, generating candidate text material corresponding to the target video material in a target editing task, based on relevant information about the target video material, includes the following steps A1-A2.

[0037] In step A1, the reference text material corresponding to the target video material is identified from the related information of the target video material, and the related information of the target video material is either the video frame image of the target video material or the audio material corresponding to the target video material.

[0038] If the information related to the target video material includes only the video frame images of the target video material or the audio material corresponding to the target video material, the reference text material corresponding to the target video material in the target editing task is obtained by identifying and analyzing the screen content contained in the still images of the target video material or the audio content of the audio material corresponding to the target video material.

[0039] Selectively, a text recognition model can identify screen content contained in one or more still images of the video frames of the target video material, or audio content of audio material corresponding to the target video material, and the acquired text material is used for text rewriting as reference text material corresponding to the target video material in the target editing task. In some embodiments, the text recognition model is used to extract the main content of the screen from the image screen and generate text material that matches the screen content of the image, or to extract the main content of the screen from the audio content of audio material corresponding to the target video material and generate text material that matches the screen content of the image.

[0040] In step A2, text rewriting is performed on the reference text material corresponding to the target video material to generate candidate text material corresponding to the target video material in the target editing task.

[0041] As a selective and impractical implementation method, generating candidate text material corresponding to the target video material in a target editing task, based on relevant information about the target video material, includes the following steps B1-B2.

[0042] In step B1, the reference text material corresponding to the target video material is identified from the relevant information of the target video material. The relevant information of the target video material may be initial text material introduced after selecting a text template based on the target video material, or text material that has been adjusted and modified based on the introduced initial text material. Alternatively, the relevant information of the target video material may be text material, image material, or audio material that has been edited, entered, adjusted, or modified in the input area corresponding to the target editing task based on the target video material.

[0043] In step B2, text rewriting is performed on the reference text material corresponding to the target video material to generate candidate text material corresponding to the target video material in the target editing task.

[0044] The relevant information for the target video footage may include initial text material introduced after selecting a text template based on the target video footage, or text material adjusted and modified based on the introduced initial text material. Alternatively, if the relevant information for the target video footage is text material, image material, or audio material edited, entered, adjusted, or modified in the input area corresponding to the target editing task based on the target video footage, the recorded text material can be directly read from the relevant information for the target video footage. The read text material can be used as reference text material corresponding to the target editing task, eliminating the need to obtain the text material by identifying the video frame image of the target video footage or the audio material corresponding to the target video footage.

[0045] As a selective and impractical implementation method, performing text rewriting on reference text material corresponding to the target video material and generating candidate text material corresponding to the target video material in the target editing task is: This includes using a text generator to perform text rewriting on reference text material corresponding to the target editing task, thereby generating candidate text material corresponding to the target video material in the target editing task. The text generator is generated by pre-configuring a natural language processing model or a machine learning model.

[0046] Selectively performing text rewriting on reference text material corresponding to a target editing task by a text generator involves sending a text rewriting request to the text generator to perform text rewriting on reference text material corresponding to the target video material in the target editing task. The text generator responds to the text rewriting request, performs text rewriting on the reference text material, and returns multiple candidate text materials obtained. In some embodiments, the text generator is used to obtain multiple candidate text materials by rewriting the reference text material, such as by changing the sentence order of the reference text material or by substituting with other synonyms, while ensuring semantic consistency, thereby making the text material more fluent and enabling more diverse expressions.

[0047] In S203, based on candidate text materials, target text materials corresponding to the target video material in the target editing task are generated, and of these, the editing operations instructed in the target editing task are used to display the target text material on the image of the target video material.

[0048] After the text rewriting process in the target editing task is completed, multiple candidate text materials generated can be displayed, which can trigger the selection of each displayed candidate text material. In response to the trigger operation for selecting multiple candidate text materials, the selected candidate text material is set as the target text material corresponding to the target video material in the target editing task, and the target text material is displayed on the image of the target video material by the editing operation instructed in the target editing task, thereby realizing the display effect of the text material and the target video material.

[0049] In S204, in response to a video generation command, editing is performed on the material within the target editing task according to the editing operations instructed in the target editing task, and the target video is obtained.

[0050] In the technical embodiment of the present disclosure, when performing a target editing task on target video material, a text assistance editing function is activated to perform text rewriting, and then, based on the relevant information of the target video material, candidate text materials corresponding to the target video material in the target editing task are intelligently generated and each of the generated candidate text materials is displayed. As a result, by performing a selection operation on the target text material among the displayed candidate text materials, the selected target text material can be displayed on the image of the target video material, and the target editing task can be completed. Text rewriting can assist in the rapid execution of editing input of text material for the target video, and multiple candidate text materials can be displayed to select the appropriate text material and execute the target editing task. Even without excellent text creation ability, it is possible to provide different text materials according to different editing requests while ensuring the rapid organization of text materials, thereby improving the editing efficiency of the target editing task.

[0051] Figure 3 is a flowchart of the process provided in the embodiments of this disclosure for generating candidate text materials corresponding to the target video material in a target editing task, based on relevant information about the target video material. This embodiment can be combined with any of the selective aspects of one or more embodiments described above.

[0052] As shown in Figure 3, in this embodiment, the process of generating candidate text materials corresponding to the target video material in the target editing task based on related information of the target video material may further include the following processes S301 and S302.

[0053] In S301, a first editing interface corresponding to the target editing task is displayed, and the first editing interface includes text assistance editing controls and a first text preview area.

[0054] Referring to Figure 4a, the first editing interface corresponding to the target editing task displays a text assistance editing control 210, a first text preview area 220, and an input area 230. In some embodiments, when the text assistance editing control 210 is triggered, it initiates text rewriting, the first text preview area 220 is used to display the text material generated after text rewriting, and the input area 230 has an editing input function for text material, image material, or audio material, and allows text material, image material, or audio material entered by the input keyboard to form the text material displayed in the first text preview area 220.

[0055] In S302, in response to a trigger operation for the text assistance editing function on the first editing interface, a second editing interface corresponding to the target editing task is displayed. The second editing interface includes a second text preview area and a text generation result selection area, where the text generation result selection area displays candidate text materials corresponding to the target video material in the target editing task. When the text assistance editing function is triggered, an operation is performed to generate candidate text materials corresponding to the target video material in the target editing task, based on the relevant information of the target video material.

[0056] Referring to Figure 4a, when performing a target editing task, text material that matches the target video material in the target editing task can typically be edited and input in the input area of ​​the first editing interface. However, when actually editing text material, if one does not have excellent text editing skills, the edited text material may not meet the requirements, increasing the likelihood of needing to re-edit, and thus reducing the efficiency of text editing for video material.

[0057] To this end, referring to Figure 4a, a text assistance editing control can be pre-added to the first editing interface corresponding to the target editing task. This allows the text assistance editing function to be activated by triggering the text assistance editing control, thereby executing text rewriting. In the process of triggering the text assistance editing function and executing text rewriting, the user jumps from the first editing interface to the second editing interface, where the second text preview area 240 and the text generation result selection area 250 are displayed. The text assistance editing function activated on the first editing interface can perform text rewriting based on the relevant information of the target video material, thereby generating multiple candidate text materials corresponding to the target video material in the target editing task. Furthermore, the multiple candidate text materials generated after text rewriting are sequentially displayed in the text generation result selection area 250 of the second editing interface.

[0058] In some embodiments, when the text assistance editing function is activated to perform text rewriting, an icon named "AI Ghostwriting" is displayed in the second editing interface to indicate the activation of the text assistance editing function for text rewriting; however, other names may be used.

[0059] Selectively, referring to Figure 4a, if the relevant information for the target video material includes only video frame images within the target video material, or audio material corresponding to the target video material, for example, if the input area of ​​the first editing interface is empty and does not contain any text material, the reference text material corresponding to the target video material in the target editing task is obtained by identifying and analyzing the screen content contained in the still image of the target video material, or the audio content of the audio material corresponding to the target video material.

[0060] Selectively, referring to Figure 4a, if the relevant information for the target video material includes initial text material introduced after selecting a text template based on the target video material, or text material that has been adjusted and modified from the introduced initial text material, or if the relevant information for the target video material is text material, image material, or audio material that has been edited, entered, adjusted, or modified in the input area corresponding to the target editing task based on the target video material, for example, if the input area of ​​the first editing interface includes text material, image material, or audio material, i.e., is not available, the recorded text material is directly read from the relevant information for the target video material, and the read text material is used as the reference text material corresponding to the target editing task.

[0061] According to the method described above, when performing a target video editing task, a text assistance editing control is provided to assist in the input of text material by displaying a first editing interface. When the text assistance editing control on the first editing interface is triggered, the text assistance editing function is activated to perform text rewriting, and the text rewriting is performed based on the target video material of the target editing task, generating candidate text material. Then, the second editing interface is displayed, and each candidate text material generated after text rewriting is displayed in the text generation result selection area of ​​the second editing interface. As a result, by performing a selection operation on the target text material among the candidate text materials displayed in the text generation result selection area, the selected target text material is placed and displayed in the second text preview area on the second editing interface, and the target editing task is completed. Text rewriting can assist in the rapid editing input of text material for the target video, and multiple candidate text materials are displayed in the text generation result selection area so that the appropriate text material can be selected to perform the target editing task. Even without extensive text manipulation skills, it ensures the rapid organization of text materials while providing different text materials according to different editing requests, thereby improving the editing efficiency of target editing tasks.

[0062] As a selective and non-restrictive implementation method, displaying a first editing interface corresponding to a target editing task includes displaying the first editing interface corresponding to the target editing task in response to a trigger operation on a text addition control on a third editing interface corresponding to the target editing task. The first video preview area of ​​the first editing interface displays the video frame screen of the target video material, and the first text preview area of ​​the first editing interface displays preset suggestion text. The preset suggestion text suggests text material, image material, or audio material edited in the input area of ​​the first editing interface based on the target video material. Alternatively, the preset suggestion text includes adjusted and modified text material, image material, or audio material.

[0063] Referring to Figure 4b, a third editing interface is created and displayed for the target editing task. The third editing interface displays a text addition control, and when the text addition control is triggered, the user jumps from the third editing interface to the first editing interface corresponding to the target editing task. When the first editing interface is displayed, the first text preview area of ​​the first editing interface displays the preset suggested text synchronously. Selectively, the preset suggested text does not require custom editing based on the screen content within the target video material corresponding to the target editing task, and inputs text material that is consistent with the target video material. Alternatively, the preset suggested text is the adjusted and modified text material, image material, or audio material. Referring to Figure 4b, the text addition control of the third editing interface corresponding to the target editing task displays an icon indicating whether or not it has a text assistance editing function for performing text rewriting. When performing text rewriting with a pre-set language type, the icon displayed on the text addition control of the third editing interface corresponding to the target editing task, indicating whether or not it has a text assistance editing function for performing text rewriting, is visible. If text rewriting is not performed using a pre-configured language type, the icon indicating whether or not a text auxiliary editor is available for performing text rewriting, which is displayed in the text addition control of the third editing interface corresponding to the target editing task, is hidden and invisible.

[0064] Referring to Figure 4b, when you selectively click the text addition control on the third editing interface corresponding to the target editing task for the first time to trigger it, a text rewriting introduction popup window for the text assistance editing function will be displayed on the third editing interface corresponding to the target editing task. The text rewriting introduction popup window includes a video to inquire about text rewriting using the text assistance editing function, the function name, a highlight introduction, and a button to confirm a trial. After clicking the button to confirm a trial in the text rewriting introduction popup window, a text rewriting permission popup window will be displayed on the third editing interface corresponding to the target editing task, requesting authorization to obtain video and text materials through text rewriting. Clicking "Confirm" to proceed to the next step, or clicking "Deny" to close the popup window.

[0065] As a selective and non-restrictive implementation, displaying a first editing interface corresponding to a target editing task includes displaying the first editing interface corresponding to the target editing task in response to a trigger operation on the text editing controls on a third editing interface corresponding to the target editing task. The third text preview area of ​​the third editing interface is displayed above the third video preview area of ​​the third editing interface. The first text preview area of ​​the first editing interface displays initial text material introduced after a text template is selected based on the target video material, or text material adjusted and modified based on the introduced initial text material, or text material, image material, or audio material edited or adjusted in the input area based on the target video material.

[0066] Referring to Figure 4c, the third editing interface corresponding to the target editing task displays a third text preview area, which contains text delete controls, text edit controls, and text rotation controls. When the text delete control is triggered, it deletes the text displayed in the third text preview area. When the text rotation control is triggered, it rotates and adjusts the third text preview area of ​​the third editing interface. When the text edit control is triggered, it initiates access to the first editing interface corresponding to the target editing task, enabling text rewriting in the first editing interface.

[0067] Referring to Figure 4c, the third text preview area of ​​the third editing interface is positioned and displayed above the third video preview area of ​​the third editing interface. In one example, after selecting an appropriate text template according to the target video material corresponding to the target editing task on the third editing interface, the text material recorded in the selected text template is imported into the third text preview area. Alternatively, the third video preview area of ​​the third editing interface displays the text material that has been edited, entered, or modified in the third text preview area according to the target video material corresponding to the target editing task. When a text editing operation is triggered and the user jumps from the third editing interface to the first editing interface, the text material in the third text preview area can be positioned and displayed in the first text preview area 220 of the first editing interface. This allows the text auxiliary editing control 210 to be triggered, activating the text auxiliary editing function and performing text rewriting on the text material recorded in the first text preview area 220.

[0068] As a selective and non-restrictive implementation method, displaying a second editing interface corresponding to the target editing task includes the following steps C1-C2.

[0069] In step C1, the reference text material corresponding to the target editing task is identified and retrieved from the material recorded in the first editing interface, text rewriting is performed on the reference text material corresponding to the target video material, and candidate text material corresponding to the target video material in the target editing task is generated. The material recorded in the first editing interface is related information of the target video material corresponding to the target editing task.

[0070] In step C2, a second editing interface corresponding to the target editing task is displayed, and candidate text materials corresponding to the target editing task are placed and displayed in the text generation result selection area of ​​the second editing interface. The second editing interface includes a second text preview area and a text generation result selection area. The text generation result selection area is used to display candidate text materials.

[0071] Referring to Figure 4a, if the first text preview area 220 displays text material that has been edited, entered, or modified for the target video material corresponding to the target editing task, the text input area 230 on the first editing interface records the text material that has been edited, entered, or modified for the target video material corresponding to the target editing task. In the first video preview area 270 of the first editing interface, a preview of the video material can be played, and after the preview playback ends, a static video frame screen is displayed in the first video preview area 270. The static video frame screen contains the main content represented by the target video material in the first editing interface, thereby enabling the conceptualization of text material that is consistent with the video material.

[0072] Referring to Figure 4a, the input area of ​​the first editing interface can directly read text material, image material, or audio material recorded from the input area of ​​the first editing interface if the target video material corresponding to the target editing task contains edited, entered, or modified text material. The read text material, image material, or audio material can be used as reference text material corresponding to the target editing task, eliminating the need to acquire text material by identifying the screen content contained in the static video frame of the target video material.

[0073] Referring to Figure 5, when multiple candidate text materials are obtained by performing text rewriting on the reference text material corresponding to the target editing task, the multiple obtained candidate text materials are transmitted to the text generation result selection area 250, and the different candidate text materials are displayed sequentially in the text generation result selection area 250.

[0074] Referring to Figure 5, the text generation result selection area 250 selectively contains multiple text style controls, each text style control corresponding to a candidate text material of that text style. The candidate text materials displayed in the text generation result selection area 250 are arranged to be grouped and displayed in the text generation result selection area 250 according to the text style to which the supplementary text material belongs.

[0075] Referring to Figure 5, when a target text style control is selectively selected in the text generation result selection area 250, candidate text materials corresponding to the target text style control are displayed in the text generation result selection area 250, and candidate text materials corresponding to other text style controls that have not been selected are not displayed in the text generation result selection area 250. Selectively, at least some of the text style controls displayed in the text generation result selection area 250 are visible, or at least some of the text style controls are invisible.

[0076] In the above-described embodiment, selectively generating target text material corresponding to the target video material in the target editing task based on candidate text material includes responding to a selection operation on the target text material within the candidate text material displayed in the text generation result selection area, and placing and displaying the target text material in the second text preview area.

[0077] Referring to Figure 5, after the text rewriting process of the target editing task is completed, multiple candidate text materials can be displayed in the text generation result selection area 250 of the second editing interface, and each candidate text material displayed in the text generation result selection area 250 can be triggered to be selected. After the target text material is selected from among the multiple candidate text materials, the selected target text material is embedded and displayed in the second text preview area 240 of the second editing interface, thereby realizing the display of the text material effect.

[0078] In addition to the embodiments described above, the present invention further includes selectively displaying a second editing interface corresponding to a target editing task, responding to a trigger operation in the second editing interface to confirm that the target editing task has adopted the target text material, jumping from the second editing interface to a third editing interface, and displaying the target text material in the third text preview area of ​​the third editing interface.

[0079] Referring to Figure 6, the first editing interface further includes confirmation controls to verify that the target editing task for the selected target text material has been completed. Triggering these confirmation controls allows the user to jump from the second editing interface to the third editing interface, and when the third editing interface is displayed, the target text material is synchronized and displayed in the third text preview area 260 of the third editing interface. Furthermore, a target video with text effects can be generated based on the target text material and target video material placed in the third text preview area of ​​the third editing interface corresponding to the target editing task.

[0080] As a selective and non-restrictive implementation method, when displaying a second editing interface corresponding to a target editing task, the first candidate text material displayed sequentially in the text generation result selection area of ​​the second editing interface is automatically selected, thereby automatically triggering the selection of the target text material among the candidate text materials displayed in the text generation result selection area.

[0081] Referring to Figure 5, when multiple candidate text materials generated by text rewriting are displayed sequentially in the text generation result selection area 250, the first candidate text material in order is automatically selected, and then the first candidate text material is selected as the target text material. The selected target text material is then placed and displayed in the second text preview area of ​​the second editing interface. If a candidate text material is to be re-selected as the target text material, the target text material placed in the second text preview area of ​​the second editing interface is replaced.

[0082] As a selective and non-restrictive implementation method, the process of generating candidate text material corresponding to the target video material in a target editing task, based on relevant information of the target video material, further includes obtaining text rewriting progress data that performs text rewriting based on relevant information of the target video material, and displaying a text rewriting progress icon in the text generation result selection area of ​​a second editing interface based on the text rewriting progress data. The text rewriting progress icon is a dynamic icon and is used to dynamically indicate the progress of performing text rewriting based on relevant information of the target video material.

[0083] Referring to Figure 5, in the process of performing text rewriting on reference text material corresponding to a target editing task using a text generator, a second editing interface including a text generation result selection area can be displayed in advance while waiting for candidate text material generation. Furthermore, since no candidate text material has been generated, the text rewriting progress data of the reference text material can be read, and then a text rewriting progress icon that dynamically displays the text rewriting progress can be displayed in the text generation result selection area.

[0084] Referring to Figure 5, displaying a text rewriting progress icon in the text generation result selection area of ​​the second editing interface further includes cyclically displaying text rewriting suggestions in the text generation result selection area of ​​the second editing interface. The text rewriting suggestions are used to indicate that a text rewriting operation is in progress. The text rewriting suggestions are displayed below the text rewriting progress icon.

[0085] As a selective and non-restrictive implementation method, the target text material is placed and displayed in a second text preview area, followed by the following steps D1-D2.

[0086] In step D1, in response to a trigger operation on the text editing function corresponding to the second text preview area on the second editing interface, the input area corresponding to the second text preview area is displayed on the second editing interface.

[0087] In step D2, in response to an editing input operation in the input area corresponding to the second text preview area, the target text material placed in the second text preview area of ​​the second editing interface is adjusted.

[0088] Referring to Figure 7, the second editing interface displays text editing controls. The text editing controls corresponding to the second text preview area are the edit button 280 located in the second text preview area, or the input button 290 displayed in the second editing interface. When the edit button 280 or input button 290 is triggered, the second editing interface displays the input area corresponding to the second text preview area. Editing input operations in the input area corresponding to the second text preview area allow for re-editing and adjustment of the target text material in the second text preview area.

[0089] As a selective and non-restrictive implementation method, the target text material is placed and displayed in a second text preview area, and then the following steps E1-E2 are included.

[0090] In step E1, in response to a selection operation on the candidate text material displayed in the text generation result selection area, the second editing interface displays text recovery controls corresponding to the second text preview area.

[0091] In step E2, in response to a trigger operation on the text recovery control corresponding to the second text preview area, the text material displayed in the second text preview area of ​​the second editing interface is restored.

[0092] Referring to Figure 8, in a scenario where text rewriting is performed, after clicking on a candidate text material displayed in the text generation result selection area, a text recovery control corresponding to the second text preview area, such as the "revert" button shown in Figure 8, is immediately displayed in the second editing interface. By triggering the text recovery control, the text material displayed in the second text preview area of ​​the second editing interface can be restored. For example, when opening an input area, text material A is displayed in the second text preview area, then text material B or C is selected, and text material B or C is displayed in the second text preview area. After triggering the text recovery control and restoring, the display of text material A is restored in the second text preview area. Of course, if too much text material is generated by adjusting the text material, it may affect the typesetting in the second text preview area, and it may be necessary to temporarily avoid special typesetting processing and adjust the second text preview area by manually zooming and dragging.

[0093] As a selective and non-restrictive implementation method, after displaying a second editing interface corresponding to the target editing task, the text assistance editing function is triggered again in response to a trigger operation on the text style switching function on the second editing interface, and candidate text materials are switched and displayed in the text generation result selection area of ​​the second editing interface, and candidate text materials corresponding to the target video material in the switched and displayed target editing task are displayed in the text generation result selection area. When the text assistance editing function is triggered again, the operation to generate candidate text materials corresponding to the target video material in the target editing task is re-executed based on the relevant information of the target video material.

[0094] Referring to Figure 9, the text generation result selection area 250 contains multiple text style controls. Each text style control corresponds to a candidate text material for that text style, and when rewriting text, the generation of candidate text materials for different text styles is permitted. When displaying text style controls in the text generation result selection area, the text style control selected at the time of the last exit is re-selected by default.

[0095] Referring to Figure 9, when switching between text style controls in the text generation result selection area, the text rewriting and generation for the reference text material of the target editing task, and the candidate text material that matches the text style corresponding to the switched-selected text style control are triggered again, and the candidate text material can be switched and displayed in the text generation result selection area of ​​the second editing interface. Of course, if text rewriting has already been performed on the reference text material corresponding to the target editing task and text material has been generated before the switching selection operation, when switching and selecting the text style control, it is sufficient to simply display the acquired candidate text material in the text generation result selection area, and it is not necessary to re-execute the text rewriting.

[0096] Selectively displaying candidate text materials in the text generation result selection area means synchronously displaying the suggested text materials below the text generation result selection area. This indicates that the content generated by rewriting the reference text material is for reference purposes only and encourages users to review it before sharing.

[0097] As a selective and non-restrictive implementation method, after displaying a second editing interface corresponding to the target editing task, the text assistance editing function is triggered again in response to a trigger operation on the text loading function on the text generation result selection area, and candidate text materials corresponding to the target video material in the target editing task are added to the text generation result selection area of ​​the second editing interface. When the text assistance editing function is triggered again, the operation to generate candidate text materials corresponding to the target video material in the target editing task is re-executed based on the relevant information of the target video material, and the additional candidate text materials are placed in the text generation result selection area and displayed after the position of the originally displayed candidate text materials.

[0098] Referring to Figure 10, a text loading control is located in the text generation result selection area 250 of the second editing interface. When the text loading control is triggered, it triggers text rewriting of the reference text material corresponding to the target editing task on top of the candidate text material originally displayed in the text generation result selection area, thereby generating new text material. Subsequently, the newly acquired candidate text material is displayed sequentially behind the position of the originally displayed candidate text material in the text generation result selection area.

[0099] Referring to Figure 10, additional text can be loaded by clicking the text loading control within the same text style control (for example, a loading button corresponding to the text loading control is placed after the candidate text material, and when switching batches, a request for text rewriting is generated, and after a predetermined number of loads, further additional loading is not possible. Even if loading fails, the loading button state is restored and the message "Loading failed, please try again" is displayed).

[0100] According to the above-described technical embodiment of the present disclosure, text rewriting can assist in the rapid editing and input of text material for the target video, and multiple candidate text materials can be displayed in the text generation result selection area, thereby allowing the user to select the appropriate text material and execute the target editing task. Even without extensive text creation capabilities, it is possible to provide different text materials according to different editing requests while ensuring the rapid organization of text material, thereby improving the editing efficiency of the target editing task.

[0101] Figure 11 is a schematic diagram of the configuration of a video editing device provided by an embodiment of the present disclosure. The embodiment of the present disclosure applies when video editing is performed by adding text material to target video material. The video editing device can be implemented by software and / or hardware and is generally integrated into any electronic device having network communication capabilities. The electronic device may be a mobile terminal, a PC terminal, or a server, etc.

[0102] As shown in Figure 11, the video editing apparatus of the embodiment of the present disclosure includes a decision module 1101, a text generation module 1102, and a video generation module 1103. The decision module 1101 is used to confirm the target video material specified in the target editing task. The text generation module 1102 is used to generate target text material corresponding to the target video material in the target editing task based on the relevant information of the target video material, and of which, the editing operations instructed in the target editing task are used to display at least the target text material on the image of the target video material. The video generation module 1103 is used to respond to a video generation command and perform editing processing on the material in the target editing task by editing operations instructed in the target editing task, and to obtain a target video.

[0103] In the above-described embodiment, selectively generating target text material corresponding to the target video material in the target editing task based on the relevant information of the target video material includes generating candidate text material corresponding to the target video material in the target editing task based on the relevant information of the target video material, wherein the candidate text material is text material generated by auxiliaryly performing text rewriting based on the relevant information of the target video material, and generating target text material corresponding to the target video material in the target editing task based on the candidate text material.

[0104] In the embodiments described above, selectively generating candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material includes identifying a reference text material corresponding to the target video material from the relevant information of the target video material, wherein the relevant information of the target video material is a video frame image of the target video material or audio material corresponding to the target video material, and performing text rewriting on the reference text material corresponding to the target video material to generate candidate text materials corresponding to the target video material in the target editing task.

[0105] In the above-described embodiment, selectively generating candidate text material corresponding to the target video material in the target editing task based on the relevant information of the target video material includes identifying reference text material corresponding to the target video material from the relevant information of the target video material, wherein the relevant information of the target video material is initial text material introduced after selecting a text template based on the target video material, or text material adjusted and modified based on the introduced initial text material, or text material, image material, or audio material edited, entered, adjusted, or modified in the input area corresponding to the target editing task based on the target video material, and performing text rewriting on the reference text material corresponding to the target video material to generate candidate text material corresponding to the target video material in the target editing task.

[0106] In the above-described embodiment, selectively performing text rewriting on reference text material corresponding to the target video material and generating candidate text material corresponding to the target video material in the target editing task includes a text generator performing text rewriting on reference text material corresponding to the target editing task and generating candidate text material corresponding to the target video material in the target editing task, wherein the text generator generates the text by pre-configuring a natural language processing model.

[0107] In the embodiments described above, selectively, the editing operations instructed in the target editing task include, specifically, trigger operations in the target editing task to confirm that the target text material is displayed on the image of the target video material by the target text material.

[0108] In the above-described embodiment, selectively generating candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material includes displaying a first editing interface corresponding to the target editing task, wherein the first editing interface includes a text assistance editing control and a first text preview area; and displaying a second editing interface corresponding to the target editing task in response to a trigger operation on the text assistance editing function on the first editing interface, wherein the second editing interface includes a second text preview area and a text generation result selection area, the text generation result selection area displays candidate text materials corresponding to the target video material in the target editing task, and when the text assistance editing function is triggered, an operation is performed to generate candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material.

[0109] In the above-described embodiment, selectively generating target text material corresponding to the target video material in the target editing task based on the candidate text material includes, in response to a selection operation for the target text material among the candidate text materials displayed in the text generation result selection area, arranging and displaying the target text material in the second text preview area.

[0110] In the above-described embodiment, selectively displaying a first editing interface corresponding to a target editing task means displaying the first editing interface corresponding to a target editing task in response to a trigger operation on a text addition control on a third editing interface corresponding to a target editing task, wherein the first editing interface displays a video frame screen of the target video material in the first video preview area of ​​the first editing interface, and the first text preview area of ​​the first editing interface displays preset suggestion text, which is used to suggest editing and inputting text material, image material, or audio material in the input area of ​​the first editing interface based on the target video material, or the preset suggestion text indicates adjusted and modified text material, Including image or audio material, or in response to a trigger operation on a text editing control on a third editing interface corresponding to a target editing task, the first editing interface corresponding to the target editing task is displayed, wherein the third text preview area of ​​the third editing interface is displayed above the third video preview area of ​​the third editing interface, and the first text preview area of ​​the first editing interface displays initial text material introduced after a text template has been selected based on the target video material, or displays text material that has been adjusted and modified on top of the introduced initial text material, or displays text material, image material, or audio material that has been edited, entered, adjusted, or modified in an input area based on the target video material.

[0111] In the above-described embodiment, if a second editing interface corresponding to a target editing task is selectively displayed, the first candidate text material displayed sequentially in the text generation result selection area of ​​the second editing interface is automatically selected, thereby automatically triggering the selection of the target text material among the candidate text materials displayed in the text generation result selection area.

[0112] In the embodiment described above, the following are further included: selectively displaying a second editing interface corresponding to a target editing task; in response to a trigger operation for a text style switching function on the second editing interface, triggering the text assistance editing function again; switching and displaying candidate text materials in the text generation result selection area of ​​the second editing interface; displaying candidate text materials corresponding to the target video material in the switched-displayed target editing task in the text generation result selection area; and when the text assistance editing function is triggered again, performing the operation to generate candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material.

[0113] In the above-described embodiment, the invention further includes selectively displaying a second editing interface corresponding to a target editing task, then, in response to a trigger operation on the text loading function on the text generation result selection area, triggering the text assistance editing function again, adding candidate text materials corresponding to the target video material in the target editing task to the text generation result selection area of ​​the second editing interface, and when the text assistance editing function is triggered again, performing the operation to generate candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material, and placing the added candidate text materials in the text generation result selection area, displaying them behind the position of the originally displayed candidate text materials.

[0114] In the above-described embodiment, the candidate text materials that are selectively displayed in the text generation result selection area are grouped and displayed in the text generation result selection area according to the text style to which the candidate text material belongs.

[0115] In the embodiment described above, the method includes: selectively placing and displaying the target text material in the second text preview area; responding to a trigger operation for a text editing function corresponding to the second text preview area on the second editing interface, displaying an input area corresponding to the second text preview area on the second editing interface; and adjusting the target text material placed in the second text preview area of ​​the second editing interface in response to an editing input operation in the input area corresponding to the second text preview area.

[0116] The embodiment described above further includes, after selectively placing and displaying the target text material in the second text preview area, displaying a text recovery control corresponding to the second text preview area on the second editing interface in response to a selection operation on the candidate text material displayed in the text generation result selection area, and restoring the text material displayed in the second text preview area of ​​the second editing interface in response to a trigger operation on the text recovery control corresponding to the second text preview area.

[0117] In the above-described embodiment, the process of selectively generating candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material further includes obtaining text rewriting progress data that performs text rewriting based on the relevant information of the target video material, displaying a text rewriting progress icon in the text generation result selection area of ​​the second editing interface according to the text rewriting progress data, and the text rewriting progress icon being a dynamic icon that dynamically displays the progress of performing text rewriting based on the relevant information of the target video material.

[0118] In the above-described embodiment, if a text rewriting progress icon is selectively displayed in the text generation result selection area of ​​the second editing interface, the text rewriting suggestion content is cyclically displayed in the text generation result selection area of ​​the second editing interface, the text rewriting suggestion content is used to indicate that a text rewriting operation is being performed, and the text rewriting suggestion content is displayed below the text rewriting progress icon.

[0119] In the technical embodiments provided by the embodiments of this disclosure, text rewriting can assist in the rapid editing and input of text material for the target video, and multiple candidate text materials can be displayed in the text generation result selection area, thereby allowing the user to select the appropriate text material and execute the target editing task. Even without extensive text creation capabilities, it is possible to provide different text materials according to different editing requests while ensuring the rapid organization of text material, thereby improving the editing efficiency of the target editing task.

[0120] The video editing apparatus provided in the embodiments of this disclosure can perform the video editing method provided in any embodiment of this disclosure and comprises a functional module and beneficial effects corresponding to the performance of the method.

[0121] It should be noted that the units and modules included in the above-described apparatus are merely categorized based on functional logic and are not limited to such classifications, as long as they can realize the corresponding functions. Furthermore, the specific names of each functional unit are merely for distinguishing purposes and do not limit the scope of protection of the embodiments of this disclosure.

[0122] Figure 12 is a schematic diagram of the configuration of an electronic device provided by an embodiment of the present disclosure. Below, Figure 12 shows a schematic diagram of a configuration suitable for realizing the electronic device (e.g., terminal device or server in Figure 12) 500 of an embodiment of the present disclosure. The terminal devices in the embodiment of the present disclosure include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in Figure 12 is merely an example and should not impose any limitations on the functions and scope of use of the embodiment of the present disclosure.

[0123] As shown in Figure 11, the electronic device 500 includes a processing unit (e.g., a central processing unit, a graphics processor, etc.) 501 and can perform various appropriate operations and processes based on programs stored in read-only memory (ROM) 502 or programs read from storage device 508 into random access memory (RAM) 503. RAM 503 further stores various programs and data necessary for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An edit / output (I / O) interface 505 is also connected to the bus 504.

[0124] Typically, the I / O interface 505 can be connected to input devices 506 such as touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, and gyroscopes; output devices 507 such as liquid crystal displays (LCDs), speakers, and vibrators; storage devices 508 such as magnetic tape and hard disks; and communication devices 509. The communication device 509 allows the electronic device 500 to communicate with other equipment wirelessly or via wired connections to exchange data. Figure 12 shows an electronic device 500 with various devices, but it should be understood that it is not necessary to implement or include all of the devices shown. More or fewer devices may be implemented or included as alternatives.

[0125] In particular, according to embodiments of the present disclosure, the processes described with reference to the flowchart described above can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-temporary computer-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When executed by a processing unit 501, the computer program performs the functions limited to the methods of embodiments of the present disclosure.

[0126] The names of messages or information exchanged between multiple devices in embodiments of this disclosure are for illustrative purposes only and do not limit the scope of such messages or information.

[0127] The electronic devices provided in the embodiments of this disclosure belong to the same inventive concept as the video editing method provided in the above-described embodiments. Technical features not described in detail in these embodiments can be referred to in the above-described embodiments, and these embodiments have the same beneficial effects as the above-described embodiments.

[0128] The embodiments of this disclosure provide a computer storage medium that stores a program, when executed by a processor, that implements the video editing method provided by the embodiments.

[0129] The computer-readable medium described herein may be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium is, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium is any physical medium that contains or stores a program used by or in combination with an instruction execution system, apparatus, or device. On the other hand, in this disclosure, a computer-readable signal medium includes a data signal transmitted in baseband or as part of a carrier wave, wherein a computer-readable program code is carried on the data signal. The data signals transmitted in this manner can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may be any computer-readable medium other than a computer-readable storage medium, and is used to transmit, transmit or communicate programs used by or in combination with instruction execution systems, apparatus, or devices. The program code contained in the computer-readable medium is transmittable by any suitable medium, including but not limited to cables, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0130] In some embodiments, clients and servers may communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and may connect to digital data communications (e.g., communication networks) in any form or medium. Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad-hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0131] The computer-readable media described above may be included in the electronic device described above, or it may exist independently and not be incorporated into the electronic device.

[0132] The computer-readable medium described above carries one or more programs, and when the one or more programs described above are executed by the electronic device, the electronic device is instructed to determine a target video material specified in a target editing task, and to generate a target text material corresponding to the target video material in the target editing task based on the relevant information of the target video material, wherein the editing operation instructed in the target editing task includes at least displaying the target text material on the image of the target video material, and, in response to a video generation command, performing editing processing on the material in the target editing task according to the editing operation instructed in the target editing task, and obtaining a target video.

[0133] Computer program code for performing the operations described herein can be organized using one or more programming languages ​​or a combination thereof, and the programming languages ​​described herein include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, but may also include conventional procedural programming languages ​​such as the "C" language, or similar programming languages. The program code may run entirely on the user's computer, partially on the user's computer, run as a standalone software package, run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer or an external computer (for example, via the Internet using an Internet service provider) via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0134] The flowcharts and block diagrams in the drawings illustrate the architecture, functions, and operations that can be realized by the systems, methods, and computer program products in each embodiment of the present disclosure. In this regard, each block in the flowchart or block diagram represents a module, program segment, or part of code containing one or more executable instructions for realizing a given logical function. It should also be noted that in some alternative embodiments, the functions described in the blocks may occur in a different order than that shown. For example, two consecutively shown blocks may actually be executed nearly parallel or in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and any combination of blocks in the block diagram and / or flowchart, can be realized by a dedicated system based on hardware that performs a given function or operation, or by a combination of dedicated hardware and computer instructions.

[0135] The units described in the embodiments of this disclosure can be implemented by software or by hardware. The names of the units are not limiting to the units themselves. In some embodiments, the names of the units are not limiting to the units themselves. For example, the first acquisition unit may be described as "a unit for acquiring at least two Internet Protocol addresses."

[0136] The functions described above may be performed, at least in part, by one or more hardware logic components. For example, typical types of hardware logic components that can be used include, but are not limited to, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chips (SOCs), and complex programmable logic devices (CPLDs).

[0137] In this disclosure, a device-readable medium is a physical medium containing or storing a program used in a command execution system, apparatus or equipment, or a combination of command execution systems, apparatus or equipment. A device-readable medium is a device-readable signal medium or a device-readable storage medium. A device-readable medium is an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof, but is not limited to these. More specific examples of device-readable storage media include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0138] The above description is merely a description of preferred embodiments and applicable technical principles of the present disclosure. Those skilled in the art will understand that the scope of the disclosure is not limited to technical modes comprising specific combinations of the above-described technical features, but should also encompass other technical modes comprising arbitrary combinations of the above-described technical features or equivalent features, without departing from the spirit of the disclosure. For example, it should be understood that it should encompass technical modes comprising the mutual substitution of the above-described features with similar functional technical features disclosed herein (but not limited to these).

[0139] Furthermore, although each operation is described in a specific order, it should not be understood that these operations must necessarily be performed in the specific order or sequence shown. In certain environments, multitasking and parallel processing may be advantageous. Similarly, the foregoing statements should not be construed as limitations on the scope of this disclosure, including some specific implementation details. Certain features described in the context of individual embodiments may also be realized by combining them in a single embodiment. Conversely, various features described in the context of a single embodiment may also be realized individually in multiple embodiments or by any appropriate sub-combination.

[0140] Although the present invention has been described in a language specific to structural features and / or methodological logic, it should be understood that the subject matter limited by the appended claims is not necessarily limited to the specific features or operations described above. Conversely, the specific features and operations described above are merely exemplary forms of realizing the claims.

Claims

1. This is a video editing method, This involves determining the target video footage specified in the target editing task, Based on the relevant information of the target video material, a target text material corresponding to the target video material in the target editing task is generated, wherein the editing operation instructed in the target editing task is at least to display the target text material on the image of the target video material. A video editing method comprising: responding to a video generation command, performing editing operations on materials within the target editing task according to the editing operations instructed in the target editing task, and obtaining a target video.

2. Based on the relevant information of the target video material, generating target text material corresponding to the target video material in the target editing task is: Based on the relevant information of the target video material, the process involves generating candidate text material corresponding to the target video material in the target editing task, wherein the candidate text material is text material generated by performing auxiliary text rewriting based on the relevant information of the target video material. The method according to claim 1, comprising generating target text material corresponding to the target video material in the target editing task based on the candidate text material.

3. Based on the relevant information of the target video material, generating candidate text material corresponding to the target video material in the target editing task is: Identifying a reference text material corresponding to the target video material from the related information of the target video material, wherein the related information of the target video material is a video frame image within the target video material, or an audio material corresponding to the target video material. The method according to claim 2, comprising performing text rewriting on a reference text material corresponding to the target video material, and generating a candidate text material corresponding to the target video material in the target editing task.

4. Based on the relevant information of the target video material, generating candidate text material corresponding to the target video material in the target editing task is: Identifying reference text material corresponding to the target video material from the related information of the target video material, wherein the related information of the target video material is initial text material introduced after selecting a text template based on the target video material, or text material adjusted and modified on the introduced initial text material, or text material, image material, or audio material edited, entered, adjusted, or modified in the input area corresponding to the target editing task based on the target video material. The method according to claim 2, comprising performing text rewriting on a reference text material corresponding to the target video material, and generating a candidate text material corresponding to the target video material in the target editing task.

5. Performing text rewriting on the reference text material corresponding to the target video material and generating candidate text material corresponding to the target video material in the target editing task is: The method according to claim 3 or 4, comprising using a text generator to perform text rewriting on reference text material corresponding to a target editing task and generating candidate text material corresponding to a target video material in the target editing task, wherein the text generator is generated by pre-configuring a natural language processing model.

6. The editing operations instructed in the aforementioned target editing task are, specifically, The method according to claim 1, wherein the target editing task includes a trigger operation to confirm that the target text material is displayed on the image of the target video material by the target text material.

7. Based on the relevant information of the target video material, generating candidate text material corresponding to the target video material in the target editing task is: Displaying a first editing interface corresponding to a target editing task, wherein the first editing interface includes text assistance editing controls and a first text preview area. The method according to any one of claims 2 to 6, comprising: displaying a second editing interface corresponding to a target editing task in response to a trigger operation for a text assistance editing function on a first editing interface, wherein the second editing interface includes a second text preview area and a text generation result selection area, the text generation result selection area displays candidate text materials corresponding to a target video material in the target editing task, and when the text assistance editing function is triggered, an operation is performed to generate candidate text materials corresponding to the target video material in the target editing task based on relevant information of the target video material.

8. Based on the candidate text materials, generating target text materials corresponding to the target video materials in the target editing task is: The method according to claim 7, further comprising: responding to a selection operation for a target text material among the candidate text materials displayed in the text generation result selection area, arranging and displaying the target text material in the second text preview area.

9. Displaying the first editing interface corresponding to the target editing task is: In response to a trigger operation on a text addition control on a third editing interface corresponding to a target editing task, the first editing interface corresponding to the target editing task is displayed, wherein the first video preview area of ​​the first editing interface displays a video frame screen of the target video material, the first text preview area of ​​the first editing interface displays preset suggestion text, the preset suggestion text is used to suggest editing and inputting text material, image material, or audio material in the input area of ​​the first editing interface based on the target video material, or the preset suggestion text includes adjusted and modified text material, image material, or audio material, or The method according to claim 7, wherein, in response to a trigger operation on a text editing control on a third editing interface corresponding to a target editing task, the first editing interface corresponding to the target editing task is displayed, wherein the third text preview area of ​​the third editing interface is displayed above the third video preview area of ​​the third editing interface, and the first text preview area of ​​the first editing interface displays initial text material introduced after a text template has been selected based on the target video material, or displays text material adjusted and modified on the introduced initial text material, or displays text material, image material, or audio material edited, entered or adjusted or modified in an input area based on the target video material.

10. When displaying a second editing interface corresponding to a target editing task, The method according to claim 7, further comprising automatically selecting the first candidate text material displayed sequentially in the text generation result selection area of ​​the second editing interface, thereby automatically triggering a selection for a target text material among the candidate text materials displayed in the text generation result selection area.

11. After displaying the second editing interface corresponding to the target editing task, The method according to claim 7, further comprising: in response to a trigger operation for a text style switching function on a second editing interface, triggering a text assistance editing function again, switching and displaying candidate text materials in the text generation result selection area of ​​the second editing interface, displaying candidate text materials corresponding to the switched and displayed target video material in the target editing task in the text generation result selection area, and when the text assistance editing function is triggered again, again performing an operation to generate candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material.

12. After displaying the second editing interface corresponding to the target editing task, The method according to claim 7, further comprising: in response to a trigger operation on the text loading function on the text generation result selection area, triggering the text assistance editing function again, adding candidate text materials corresponding to the target video material in the target editing task to the text generation result selection area of ​​the second editing interface, and when the text assistance editing function is triggered again, performing the operation to generate candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material, and placing the added candidate text materials in the text generation result selection area and displaying them behind the position of the originally displayed candidate text materials.

13. The method according to claim 7, wherein the candidate text materials displayed in the text generation result selection area are grouped and displayed in the text generation result selection area according to the text style to which the candidate text materials belong.

14. After placing and displaying the target text material in the second text preview area, In response to a trigger operation on the text editing function corresponding to the second text preview area on the second editing interface, the input area corresponding to the second text preview area is displayed on the second editing interface. The method according to claim 8, further comprising adjusting target text material placed in the second text preview area of ​​the second editing interface in response to an editing input operation in an input area corresponding to a second text preview area.

15. After placing and displaying the target text material in the second text preview area, In response to a selection operation on the candidate text material displayed in the text generation result selection area, a text recovery control corresponding to the second text preview area is displayed on the second editing interface. The method according to claim 8, further comprising: restoring text material displayed in the second text preview area of ​​the second editing interface in response to a trigger operation on a text recovery control corresponding to the second text preview area.

16. In the process of generating candidate text materials corresponding to the target video material in the target editing task based on the relevant information of the target video material, The method according to claim 7, further comprising: obtaining text rewriting progress data for performing text rewriting based on relevant information of the target video material; displaying a text rewriting progress icon in the text generation result selection area of ​​the second editing interface according to the text rewriting progress data; and the text rewriting progress icon being a dynamic icon, which dynamically presents the progress of performing text rewriting based on relevant information of the target video material.

17. When displaying a text rewriting progress icon in the text generation result selection area of ​​the second editing interface, The method according to claim 16, further comprising the following: displaying text rewriting suggestions in a cyclical manner in the text generation result selection area of ​​the second editing interface; using the text rewriting suggestions to indicate that a text rewriting operation is being performed; and displaying the text rewriting suggestions below the text rewriting progress icon.

18. It is a video editing device, A decision module used to determine the target video material specified in the target editing task, A text generation module that generates target text material corresponding to the target video material in the target editing task based on the relevant information of the target video material, wherein the editing operation instructed in the target editing task is at least for displaying the target text material on the image of the target video material, A video editing apparatus comprising: a video generation module that responds to a video generation command, performs editing processing on material within the target editing task based on editing operations instructed in the target editing task, and acquires a target video.

19. It is an electronic device, One or more processors, A storage device for storing one or more programs, An electronic device that, when the one or more programs described above are executed by the one or more processors, causes the one or more processors to execute the video editing method described in any one of claims 1 to 17.

20. A storage medium that, when executed by a computer processor, includes a computer-executable instruction causing the computer to perform the video editing method described in any one of claims 1 to 17.

Images