Video generation method, apparatus, device, and medium

Abstract

Embodiments of the present disclosure relate to a video generation method, device, equipment and medium. The method comprises: displaying a dialogue interface; the dialogue interface displays an information input area and at least one creation guide example, the content of the creation guide example comprising a prompt text example and a material example corresponding to the prompt text example; in response to the information input area receiving first dialogue content, generating and displaying second dialogue content based on the first dialogue content; the first dialogue content comprises: the content of a target guide example triggered in the at least one creation guide example or the content adjustment result of the target guide example, or a material and a prompt text input through an input operation; the second dialogue content comprises a clip result corresponding to the material in the first dialogue content; and a target video is generated based on the clip result in the second dialogue content. The present disclosure helps to accurately obtain video creation appeals and obtain a target video that meets user needs.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a video generation method, apparatus, device, and medium. Background Technology

[0002] With the development of artificial intelligence technology, AI models are widely used in the field of multimedia editing to assist users in multimedia editing, such as helping users create videos quickly and conveniently. However, the inventors have found that although some multimedia editing software can provide users with a one-click video creation function, that is, automatically generate videos based on user-provided materials, this function requires users to select materials and confirm the template before proceeding with the subsequent process. Moreover, the videos generated by the model directly based on the user's selections often fail to meet user needs, resulting in a poor user experience. Summary of the Invention

[0003] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a video generation method, apparatus, device, and medium.

[0004] In a first aspect, embodiments of this disclosure provide a video generation method, the method comprising: displaying a dialogue interface; wherein the dialogue interface displays an information input area and at least one creation guidance example, the content of the creation guidance example including a prompt text example and a material example corresponding to the prompt text example; responding to the information input area receiving first dialogue content, generating and displaying second dialogue content based on the first dialogue content; wherein the first dialogue content includes: the content of a target guidance example triggered in the at least one creation guidance example or the content adjustment result of the target guidance example, or, material and prompt text input through an input operation; the second dialogue content includes at least the editing result corresponding to the material in the first dialogue content; and generating a target video based on the editing result of the second dialogue content.

[0005] Secondly, embodiments of this disclosure provide a video generation apparatus, comprising: an interface display module for displaying a dialogue interface; wherein the dialogue interface displays an information input area and at least one creation guidance example, the content of the creation guidance example including a prompt text example and a material example corresponding to the prompt text example; a content display module for generating and displaying second dialogue content based on the first dialogue content in response to the information input area receiving first dialogue content; wherein the first dialogue content includes: the content of a target guidance example triggered by the at least one creation guidance example or the content adjustment result of the target guidance example, or, material and prompt text input through an input operation; the second dialogue content includes at least the editing result corresponding to the material in the first dialogue content; and a video generation module for generating a target video based on the editing result in the second dialogue content.

[0006] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the video generation method provided in embodiments of this disclosure.

[0007] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program for performing the video generation method provided in embodiments of this disclosure.

[0008] Fifthly, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the video generation method provided in embodiments of this disclosure.

[0009] The technical solution provided in this disclosure can display creation guidance examples (including prompt text examples and corresponding material examples) and information input areas through a dialog interface. Furthermore, it can generate second dialog content containing material editing results based on the first dialog content received in the information input area, thereby generating a target video based on the editing results in the second dialog content. This dialog creation method is not only easy for users to understand and accept, but also guides users to directly apply or adjust the example content through the creation guidance examples displayed in the dialog interface. This makes it easier for users to understand and clarify their video creation needs. Users can also directly input materials and prompt text through input operations, which helps to accurately obtain video creation requirements and thus obtain a target video that meets the user's needs.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0012] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a video generation method provided in this embodiment of the present disclosure;

[0014] Figures 2-9 This is a schematic diagram of the interface provided for an embodiment of the present disclosure;

[0015] Figure 10 This is a schematic diagram of the structure of a video generation device provided in an embodiment of the present disclosure;

[0016] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0017] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0018] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0020] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0021] Figure 1 This is a flowchart illustrating a video generation method provided in an embodiment of the present disclosure. The method can be executed by a video generation device, which can be implemented using software and / or hardware, and is generally integrated into an electronic device. Figure 1 As shown, the method mainly includes the following steps S102 to S106:

[0022] Step S102: Display the dialog interface; wherein the dialog interface displays an information input area and at least one creation guidance example, the creation guidance example includes a prompt text example and a material example corresponding to the prompt text example.

[0023] A dialog interface is an interface that allows interaction with the user in a conversational format. For example, this interface can display both user-side and system-side dialogue content, achieving a dialogue interaction effect between the user and the AI ​​system used for video editing. In some examples, the dialog interface can be displayed in response to a dialog creation entry or a dialog creation control. The dialog interface can always display an information input area and can initially display at least one creative guidance example. Each creative guidance example can correspond to a video creation theme. Multiple creative guidance examples can be displayed simultaneously on the dialog interface, or only one creative guidance example can be displayed, with other creative guidance examples displayed in a horizontal or vertical switching manner. The user can switch between the creative guidance examples displayed on the dialog interface by swiping.

[0024] The creation guidance examples include sample prompt text and sample materials. Different creation guidance examples correspond to different video creation themes, and the theme categorization methods can be flexibly set. For example, they can be categorized based on video editing type, such as atmospheric short videos, videos with added subtitles, narrative videos, and long-to-short videos; or they can be categorized based on material content, such as travel videos, food videos, and snippets of daily life. Corresponding prompt text examples can be preset for each creation guidance example, and corresponding system sample materials can be preset as material examples, or user materials dynamically selected from the user's album can be used as material examples; there are no restrictions here. Compared with the existing method of directly showing users a material selection page and prompting them to choose materials, the above-mentioned method of first providing creation guidance examples on the dialog interface provides users with video creation theme references, better assists users in clarifying their current video creation needs, and also helps users understand and refer to the required prompt text and materials. In practical applications, users can also directly apply creation guidance examples or edit creation guidance examples to quickly generate their own dialog content; that is, creation guidance examples help users accurately and conveniently express their video creation needs.

[0025] Step S104: In response to receiving the first dialogue content in the information input area, generate and display the second dialogue content based on the first dialogue content; wherein, the first dialogue content includes: the content of at least one target guidance example triggered in the creation guidance example or the content adjustment result of the target guidance example, or the material and prompt text input through the input operation; the second dialogue content includes at least the editing result corresponding to the material in the first dialogue content.

[0026] The first dialogue content can also be understood as the user-side dialogue content, and the second dialogue content can also be understood as the system-side dialogue content. The first and second dialogue contents can be displayed on opposite sides of the dialogue interface, respectively, with right and left alignment, or they can be displayed on one side of the dialogue interface. The first and second dialogue contents can be distinguished by differences in text, corresponding avatars, and positions on the dialogue interface, which are not restricted here.

[0027] In practical applications, users can trigger the desired creation guidance example, using its content directly as the user's first dialogue content. Alternatively, users can adjust the creation guidance example, using the adjusted content as the user's first dialogue content. Furthermore, users can input materials and / or prompt text in the information input area through text input, voice input, or material upload, using this as their first dialogue content. During video creation in a dialogue format, prompt text or materials added by the user at any time through the information input area can also serve as the first dialogue content. The second dialogue content is generated by the system for automatically creating videos, and it can include responses to the first dialogue content or proactive inquiries. This embodiment can edit materials based on the first dialogue content to obtain an editing result, which is then used as the second dialogue content. The second dialogue content can also include other information generated by the system, such as one or more intermediate information like content parsing results, material editing schemes, and material editing processes generated before the editing result is generated. It can also include inquiry information generated based on the user's first dialogue content or the aforementioned intermediate information, without limitation.

[0028] Step S106: Generate the target video based on the editing results in the second dialogue content.

[0029] In practical applications, the final target video can be generated directly based on the editing results, or the editing results can be adjusted again to generate the target video from the adjusted editing results.

[0030] The dialogue-based video creation method provided in this embodiment is not only easy for users to understand and accept, but also guides users to directly apply or adjust the example content through the creation guidance examples displayed in the dialogue interface. This makes it easier for users to understand and clarify their own video creation needs. Users can also directly input materials and prompt text through input operations, which simplifies the steps for users to provide the materials and prompt text required for video creation, simplifies the intelligent video creation process, and helps to accurately obtain video creation needs, thereby obtaining target videos that meet user requirements.

[0031] The method provided in this disclosure further includes: selecting material examples based on preset material selection criteria corresponding to the video creation theme; wherein, the material selection criteria are used to indicate the material type and / or the material duration range; and generating a creation guidance example corresponding to the video creation theme based on the material examples and preset prompt text examples for the video creation theme. Different material selection criteria correspond to different video creation themes. For example, if the video creation theme is a narrative video, the corresponding material selection criteria include: selecting multiple videos from recent materials, where the total duration of the multiple videos is greater than 90 seconds; if the video creation theme is a video with subtitles, the corresponding material selection criteria include: selecting multiple images and videos from recent materials, where the total duration is greater than 40 seconds, wherein images and GIFs can both be considered as 3 seconds. Alternatively, if the video creation theme is a travelogue theme, the corresponding material selection criteria include: selecting photos and videos containing food, etc. These are all examples and are not intended to limit the scope of the discussion. This disclosure does not limit the source of the material examples. For example, the material examples can be selected from a designated album or material library with access rights. In this way, preprocessing can be performed before the user creates a video, selecting materials that match the specific video creation theme and showing them to the user as creation guidance examples for reference. This makes it easier for the user to understand the current video creation requirements and accurately provides prompt text and materials that meet their own video creation needs. Users can also directly apply the prompt text and materials in the creation guidance examples, improving the convenience of the user's video creation.

[0032] For ease of understanding, please refer to Figure 2 The diagram shown illustrates an interface that can initially display a creation guidance example and an information input area. Figure 2 Taking the example of displaying a creation guide example on the interface, this example can be presented in card format. In practice, users can switch between different creation guide examples using methods such as horizontal swiping. The creation guide example can specifically present prompt text examples such as "Create a short film with narration and subtitles," as well as material examples such as images / videos. In practice, multiple material examples can be displayed simultaneously on the interface, or only one material example can be selected as the cover image, with the others displayed only after a trigger. The specific settings are flexible and not limited here. This method allows users to set prompt text and select materials based on the creation guide example for subsequent video creation. Additionally, Figure 2 The information input area allows users to input prompt text via keyboard or handwriting, as well as voice input, which can be automatically converted into prompt text. In addition, the information input area also allows users to directly upload images, videos and other materials, providing great convenience for users.

[0033] In some implementation examples, the above-described method provided in this disclosure further includes the following (1) to (3):

[0034] (1) In response to the triggering of at least one creation guide example, the content of the target guide example is filled into the information input area; and, in response to the content adjustment operation of the target guide example, the content of the target guide example filled into the information input area is adjusted.

[0035] By automatically populating the information input area with the content of the target guidance examples that users are interested in, the system provides users with convenient input of prompt text / materials. Users can also directly adjust the example content in the information input area, such as adjusting the prompt text examples in the target guidance examples or adding, deleting, or modifying the material examples in the target guidance examples.

[0036] (2) In response to the input operation in the information input area, fill the information input area with the material and prompt text entered in the input operation.

[0037] For example, the information input area includes a text input area and a material input area. Users can fill the text input area with prompts describing the video creation needs through input operations such as keyboard text input and voice-to-text input. Users can also fill the material input area with image materials and / or video materials to be created.

[0038] (3) In response to the confirmation control corresponding to the information input area being triggered, the current content filled in the information input area is used as the first dialog content. Specifically, the current content filled in the information input area can be displayed as the first dialog content on the dialog interface, and then the information input area can be cleared so that other information entered by the user can be received through the cleared information input area.

[0039] The above methods facilitate the convenient and flexible acquisition of initial dialogue content to guide users' video creation needs.

[0040] For easier understanding, please refer to Figure 3 The diagram illustrates an interface showing the initial dialogue content, including three user-uploaded materials and the user's prompt text, "Create a short film based on my video materials." In practical application, the send button in the information input area can be considered a confirmation control. When the user clicks the send button, it indicates that they have confirmed sending all information from the information input area as the initial dialogue content to the system. At this point, the information input area can be cleared. The initial dialogue content may be user-uploaded content or automatically filled content based on a user-triggered creation guide example; this is not a limitation. Furthermore, Figure 3The text also shows the newly added dialog control and the history dialog control, which will be explained in detail later.

[0041] In some implementations, the second dialogue content also includes content parsing results, material editing schemes, and material editing processes. The steps described above for generating and displaying the second dialogue content based on the first dialogue content can be performed with reference to steps a to d below:

[0042] Step a: Perform content parsing processing based on the first dialogue content to generate and display the content parsing results of the first dialogue content. For example, the first dialogue content can be understood based on a large language model, such as understanding the content of various images, videos, and other materials, thereby obtaining the content parsing results.

[0043] Step b: Based on the content analysis results, generate and display a material editing scheme for the first dialogue content. This material editing scheme includes, but is not limited to, the construction ideas for key elements such as the opening, main content, and ending based on the material.

[0044] Step c: If the material editing scheme meets the editing conditions, edit the material of the first dialogue content based on the material editing scheme, show the material editing process, and generate and display the editing results corresponding to the material in the first dialogue content.

[0045] The above editing conditions are used to indicate the elements that need to be met in the editing of the material, such as style preferences and voice-over. If the user's prompt text is rich and specific, and the material editing scheme covers the elements required for editing, then the material of the first dialogue content can be edited directly based on the material editing scheme. The material editing process can be displayed, such as the selection of highlight segments in the material, splicing of different materials, adding special effects, and other material editing processes. The final editing result can be displayed on the dialogue interface.

[0046] Step d: If the material editing scheme does not meet the editing conditions, generate and display the query content corresponding to the material editing scheme, adjust the material editing scheme based on the feedback information of the received query content, and edit the material of the first dialogue content based on the adjusted material editing scheme, display the material editing process, and generate and display the editing result corresponding to the material in the first dialogue content.

[0047] If the user's prompts are simple and general, and the editing plan lacks necessary editing elements, in order to ensure that the final edited result meets the user's needs, a query can be generated and displayed corresponding to the editing plan. Specifically, based on the editing conditions, the missing target editing elements in the editing plan can be identified; based on the target editing elements, a query can be generated corresponding to the editing plan and displayed in a preset format; the preset format includes form options and / or text queries. For example, if the missing target editing elements in the editing plan include background music, a query can be generated regarding background music style preferences, and this query can also be displayed to the user as a secondary dialogue through the dialog interface to more accurately understand the user's needs.

[0048] By presenting the content analysis results, material editing scheme, and material editing process to the user in the above manner, the user can better understand how the editing results are generated. This also encourages the user to wait patiently for the video to be generated, which can significantly improve the fun during the waiting period and avoid the user's boredom, thereby effectively improving the user experience.

[0049] Furthermore, considering the different needs of different users—for example, some users prefer a simple interface and are not concerned with intermediate information during video creation, while others want the interface to present more detailed information—in some implementation examples, the target content displayed on the dialog interface is associated with a collapse control. This collapse control is used to fully collapse, partially collapse, or fully expand the target content. The target content includes the content parsing results and the material editing process. In this way, users can choose to fully display, partially display, or not display the content parsing results and the material editing process based on their needs.

[0050] For easier understanding, please refer to Figure 4 and Figure 5 The diagrams shown illustrate different aspects of the interface, illustrating the information displayed at various video creation stages. Figure 4 The text first demonstrates that after receiving the initial dialogue containing materials and prompt text, the system displays a "thinking" dialogue. It then further illustrates the content parsing process of the user-selected video materials, presenting the parsing results to the user on the interface. Further, in... Figure 5 The text also illustrates the material editing schemes and processes provided by the system, such as... Figure 4 and Figure 5As can be seen, the system presents the content parsing results, material editing plan, and material editing process sequentially, from beginning to end. This allows users to clearly understand the system's current operation while waiting for the video to be generated, reducing the boredom of waiting and the probability of users canceling their production due to long waiting times. Furthermore, in Figure 4 and Figure 5 The diagram illustrates a folding control. This embodiment of the disclosure sets up folding controls for two entirely system-generated contents: the content parsing results and the material editing process. Users can choose to fold all, partially, or not fold based on their needs. However, for the material editing solution, there may be content that interacts with the user, such as… Figure 5 The content shown is queried through form options, so there is no need to set a collapse control; instead, it can be displayed as a whole for easy user interaction and viewing.

[0051] Considering that the automatically generated editing results may not be entirely satisfactory to users, and users still have needs to adjust the editing results, the editing results are also associated with result editing controls and result feedback controls to facilitate further adjustments by users; to generate the target video based on the editing results in the second dialogue content, you can refer to the following steps a and b:

[0052] Step a: In response to the triggering of the result editing control, display the editing page corresponding to the editing result in the second dialogue content, and adjust the editing result based on the editing operation corresponding to the editing page; or, in response to the triggering of the result feedback control, obtain the feedback information of the editing result, and adjust the editing result based on the feedback information of the editing result; or, in response to the receipt of result adjustment information in the information input area, adjust the editing result based on the result adjustment information.

[0053] In other words, users can directly jump to the editing page of the edited result through the result editing control, and use the editing tools provided on the editing page to edit the result, such as adding, deleting, and modifying materials, replacing music, modifying text, and adding special effects. Users can also directly provide feedback through the result feedback control. For example, when a user triggers the feedback control to indicate dissatisfaction with the result, the system provides form options for the user to select factors that are unsatisfactory, such as style factors or background music factors. Users can also directly send result adjustment information through the information input area, such as instructing to add subtitles to the edited result or to change background music A in the edited result to background music B. Users can adjust the edited result based on any one or more of the above three methods, which is highly convenient.

[0054] Step b: Display the adjusted editing result and, in response to the confirmation instruction for the adjusted editing result, obtain the target video based on the adjusted editing result.

[0055] Using the methods described above, users can flexibly adjust the editing results generated by the system to ensure that the final target video meets their needs.

[0056] For easier understanding, please refer to Figure 6 and Figure 7 The diagram shown is an interface schematic. Figure 6 The system displays a feedback control. If a user triggers the feedback control and is dissatisfied with the result, the system will initiate further inquiries to adjust the editing result based on the user's feedback. In addition, users can also directly express their dissatisfaction or requests for modification in the information input area of ​​the dialog interface. Figure 7 The middle section illustrates the result editing control, allowing users to access the editing page and perform flexible editing as needed. Furthermore, Figure 7 The document also demonstrates a result-changing control, which users can directly trigger to allow the system to regenerate other edit results. These methods effectively lower the barrier to entry for video editing, enhancing the convenience and flexibility of video creation.

[0057] Considering the large amount of content on the dialog interface and the user's need to find specific content, in some specific examples, the dialog interface also includes a quick jump control. The method provided in this disclosure embodiment further includes: in response to the triggering of the quick jump control, displaying multiple content title items on the dialog interface; and in response to the triggering of a target title item among the multiple content title items, jumping to display the content corresponding to the target title item on the dialog interface. For example, content parsing results, material editing schemes and material editing processes, editing results V1, editing results V2, and editing results V3, etc., allow users to quickly locate the content they need to view through the quick jump control, eliminating the need to scroll up and down to find the required content, greatly improving the convenience for users to view the content they need. For ease of understanding, refer to... Figure 8 The diagram illustrates an interface where a quick navigation control is provided on the side. Users can use this control to quickly find content titles on the interface and select the desired title, enabling rapid content location. This method helps users quickly locate the content they need and improves the user's interactive experience.

[0058] In some implementation examples, a history dialog control is also provided at a designated location on the dialog interface; the above method also includes the following steps 1 and 2:

[0059] Step 1: In response to the triggering of the history dialogue control, the history information interface is displayed. This interface includes a history dialogue showcase area, which displays the prompt text used in creating the dialogue and the corresponding generated video (i.e., the edited result). Different history dialogue showcase areas correspond to different dialogue creation times. For example, multiple history dialogue showcase areas can be displayed in chronological order from most recent to oldest, allowing users to quickly understand the historical video creation process.

[0060] Step 2: In response to the target section in the historical dialogue exhibition area being triggered, the corresponding content of the target section is displayed on the dialogue interface for viewing or editing. This method facilitates users' further review and editing of their historical video creation results.

[0061] For ease of understanding, Figure 3 The diagram shows that there are "Add Chat" and "History Chat" controls in the upper right corner of the chat interface. Users can use the "Add Chat" control to start a new chat, which means starting to create a new video. Activating this control allows users to return to the previous screen. Figure 2 The dialog interface is shown in its initial state. Users can also view historical dialog records using the history dialog control. See [link / reference]. Figure 9 The diagram illustrates a simplified version of the historical dialogue display area 1 and historical dialogue display area 2. It can display the dialogue date, specifically the dialogue end date, and user-input prompt text, typically only the first prompt text. If a line is too long, it automatically wraps; after N lines, an ellipsis is used. It can also display all generated clipping results, arranged sequentially from last to first. Users can click on a target display area to view or edit further. The dialogue interface then displays the corresponding dialogue content, allowing users to navigate to the end of the dialogue content in the target area. Users can also click on a clipping result in the target display area to view a preview page for further editing.

[0062] In summary, the video generation method provided in this disclosure can interact with users in a dialog-like manner, which is not only easy for users to understand and accept, but also allows users to directly apply or adjust the example content through the creation guidance examples displayed in the dialog interface. This makes it easier for users to understand and clarify their own video creation needs. Users can also directly input materials and prompt text through input operations, which helps to accurately obtain video creation requirements, thereby obtaining a target video that meets the user's needs. Furthermore, during the creation process, it can further demonstrate the content analysis results, material editing schemes, and material editing processes to users, making it easier for users to understand how the editing results are generated and to patiently wait for the video to be generated. During the creation period, users can also be asked about their needs through dialogue, which helps to generate a video that satisfies the user. Moreover, it provides multiple ways to adjust the editing results, further simplifying the threshold for users to further edit and adjust the editing results, and comprehensively improving the user experience.

[0063] Corresponding to the aforementioned video generation method, this disclosure further provides a video generation apparatus. Figure 10 This is a schematic diagram of a video generation device provided in an embodiment of the present disclosure. The device can be implemented by software and / or hardware, and is generally integrated into an electronic device, such as... Figure 10 As shown, the video generation device includes:

[0064] The interface display module 1000 is used to display the dialog interface; the dialog interface displays an information input area and at least one creation guidance example, the creation guidance example includes a prompt text example and a material example corresponding to the prompt text example;

[0065] The content display module 1010 is used to respond to the information input area receiving the first dialogue content, generate and display the second dialogue content based on the first dialogue content; wherein, the first dialogue content includes: the content of at least one creation guidance example triggered by the target guidance example or the content adjustment result of the target guidance example, or the material and prompt text input through the input operation; the second dialogue content includes at least the editing result corresponding to the material in the first dialogue content;

[0066] The video generation module 1020 is used to generate the target video based on the editing results in the second dialogue content.

[0067] The dialogue creation method provided in this embodiment is not only easy for users to understand and accept, but also guides users to directly apply or adjust the example content through the creation guidance example displayed in the dialogue interface. This makes it easier for users to understand and clarify their own video creation needs. Users can also directly input materials and prompt text through input operations, which helps to accurately obtain video creation needs and thus obtain the target video that meets the user's needs.

[0068] In some embodiments, the device further includes a guidance example generation module, used to select material examples based on preset material selection criteria corresponding to a video creation theme; wherein the material selection criteria are used to indicate the material type and / or the material duration range; and to generate a creation guidance example corresponding to the video creation theme based on the material examples and preset prompt text examples of the video creation theme.

[0069] In some embodiments, the apparatus further includes a content determination module, configured to fill the information input area with the content of the target guidance example in response to the triggering of the target guidance example in the at least one creation guidance example; and to adjust the content of the target guidance example filled in the information input area in response to a content adjustment operation of the target guidance example; to fill the information input area with the material and prompt text entered in the input operation in response to an input operation in the information input area; and to use the current content filled in the information input area as the first dialogue content in response to the triggering of the confirmation control corresponding to the information input area.

[0070] In some implementations, the second dialogue content further includes content parsing results, material editing schemes, and material editing processes. The content display module 1010 is specifically used for: performing content parsing processing on the first dialogue content to generate and display the content parsing results of the first dialogue content; generating and displaying the material editing scheme of the first dialogue content based on the content parsing results; if the material editing scheme meets the editing conditions, editing the materials of the first dialogue content based on the material editing scheme, displaying the material editing process, and generating and displaying the editing results corresponding to the materials in the first dialogue content; if the material editing scheme does not meet the editing conditions, generating and displaying the query content corresponding to the material editing scheme, adjusting the material editing scheme based on the feedback information received from the query content, and editing the materials of the first dialogue content based on the adjusted material editing scheme, displaying the material editing process, and generating and displaying the editing results corresponding to the materials in the first dialogue content.

[0071] In some implementations, the editing conditions are used to indicate the material editing elements that need to be satisfied; the content display module 1010 is specifically used to: obtain the target material editing elements missing in the material editing scheme based on the editing conditions; generate the query content corresponding to the material editing scheme based on the target material editing elements, and display the query content in a preset format; wherein, the preset format includes form option format and / or text query format.

[0072] In some implementations, the target content displayed on the dialog interface is associated with a folding control, which is used to fold the target content completely, partially, or fully; wherein, the target content includes the content parsing result and the material editing process.

[0073] In some implementations, the editing result is further associated with a result editing control and a result feedback control; the video generation module 1020 is specifically used to: in response to the triggering of the result editing control, display the editing page corresponding to the editing result in the second dialogue content, and adjust the editing result based on the editing operation corresponding to the editing page; or, in response to the triggering of the result feedback control, obtain feedback information of the editing result, and adjust the editing result based on the feedback information of the editing result; or, in response to the information input area receiving result adjustment information, adjust the editing result based on the result adjustment information; display the adjusted editing result, and in response to the confirmation instruction of the adjusted editing result, obtain the target video based on the adjusted editing result.

[0074] In some embodiments, the dialog interface is further provided with a quick jump control, and the device further includes a jump display module, which is used to display multiple content title items of the dialog interface in response to the triggering of the quick jump control; and to jump to display the content corresponding to the target title item on the dialog interface in response to the triggering of the target title item among the multiple content title items.

[0075] In some embodiments, a historical dialogue control is further provided at a designated location on the dialogue interface; the device also includes a historical information display module, used to display a historical information interface in response to the triggering of the historical dialogue control; wherein the historical information interface displays a historical dialogue exhibition area; wherein the historical dialogue exhibition area displays the prompt text used in the creation of the historical dialogue and the corresponding generated video, and different historical dialogue exhibition areas correspond to different dialogue creation times; in response to the triggering of a target exhibition area in the historical dialogue exhibition area, the content corresponding to the target exhibition area is displayed on the dialogue interface for viewing or editing.

[0076] The video generation apparatus provided in this disclosure can execute the video generation method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device embodiments can be referred to the corresponding process in the method embodiments, and will not be repeated here.

[0078] This disclosure provides an electronic device, which includes: a storage device storing a computer program thereon; and a processing device for executing the computer program in the storage device to implement the steps of any method of this disclosure.

[0079] The following is for reference. Figure 11 The diagram illustrates a structural schematic of an electronic device 1100 suitable for implementing embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Devices), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital televisions and desktop computers. Figure 11 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0080] like Figure 11 As shown, electronic device 1100 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1102 or a program loaded from storage device 1108 into random access memory (RAM) 1103. The RAM 1103 also stores various programs and data required for the operation of electronic device 1100. The processing unit 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. An input / output (I / O) interface 1105 is also connected to bus 1104.

[0081] Typically, the following devices can be connected to I / O interface 1105: input devices 1106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1109. Communication device 1109 allows electronic device 1100 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 11 An electronic device 1100 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0082] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1109, or installed from storage device 1108, or installed from ROM 1102. When the computer program is executed by processing device 1101, it performs the functions defined in the methods of embodiments of this disclosure.

[0083] In addition to the methods and devices described above, embodiments of this disclosure can also be computer program products, comprising computer program instructions that, when executed by a processor, cause the processor to perform the methods provided in the embodiments of this disclosure. The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0084] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the methods provided in embodiments of this disclosure.

[0085] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0086] This disclosure also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the methods described in this disclosure.

[0087] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0088] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0089] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0090] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A video generation method, characterized in that, include: The interface displays a dialog box; wherein the dialog box displays an information input area and at least one creation guidance example, the creation guidance example includes a prompt text example and a corresponding material example; the creation guidance example is presented in card form, and the creation guidance example is switched by swiping; different creation guidance examples correspond to different video creation themes, and different video creation themes correspond to different material selection criteria, the material selection criteria are used to indicate the material type and / or the material duration range, and the material examples in the creation guidance examples are selected based on the material selection criteria of the video creation theme corresponding to the creation guidance example; In response to receiving first dialogue content in the information input area, second dialogue content is generated and displayed based on the first dialogue content; wherein, the first dialogue content includes: the content adjustment result of the target guidance example triggered in at least one creation guidance example; the second dialogue content includes at least the editing result corresponding to the material in the first dialogue content; The target video is generated based on the editing results of the second dialogue content.

2. The method according to claim 1, characterized in that, The method further includes: Based on the preset material selection criteria corresponding to the video creation theme, select material examples; Based on the material examples and the preset prompt text examples for the video creation theme, a creation guidance example corresponding to the video creation theme is generated.

3. The method according to claim 1, characterized in that, The method further includes: In response to the triggering of a target guidance example in at least one creation guidance example, the content of the target guidance example is filled into the information input area; and in response to the content adjustment operation of the target guidance example, the content of the target guidance example filled into the information input area is adjusted; In response to an input operation in the information input area, the material and prompt text input in the input operation are filled into the information input area; In response to the confirmation control corresponding to the information input area being triggered, the current content filled in the information input area is used as the first dialogue content.

4. The method according to claim 1, characterized in that, The second dialogue content also includes content parsing results, material editing schemes, and material editing processes. The generation and display of the second dialogue content based on the first dialogue content includes: Based on the content of the first dialogue, perform content parsing processing to generate and display the content parsing results of the first dialogue content; Based on the content parsing results, a material editing scheme for the first dialogue content is generated and displayed; If the material editing scheme meets the editing conditions, the material of the first dialogue content is edited based on the material editing scheme, the material editing process is displayed, and the editing result corresponding to the material in the first dialogue content is generated and displayed; If the material editing scheme does not meet the editing conditions, generate and display the query content corresponding to the material editing scheme, adjust the material editing scheme based on the feedback information of the received query content, and edit the material of the first dialogue content based on the adjusted material editing scheme, display the material editing process, and generate and display the editing result corresponding to the material in the first dialogue content.

5. The method according to claim 4, characterized in that, The editing conditions are used to indicate the editing elements of the material that must be met; The generation and display of the query content corresponding to the material editing scheme includes: Based on the editing conditions, the missing target material editing elements in the material editing scheme are obtained; Based on the target material editing elements, generate the corresponding query content for the material editing scheme, and display the query content in a preset format; wherein, the preset format includes form option format and / or text query format.

6. The method according to claim 4, characterized in that, The target content displayed on the dialog interface is associated with a folding control, which is used to fold the target content completely, partially, or fully; wherein, the target content includes the content parsing result and the material editing process.

7. The method according to claim 1, characterized in that, The editing result is also associated with a result editing control and a result feedback control; The step of generating the target video based on the editing results in the second dialogue content includes: In response to the triggering of the result editing control, the editing page corresponding to the editing result in the second dialogue content is displayed, and the editing result is adjusted based on the editing operation corresponding to the editing page; or, in response to the triggering of the result feedback control, feedback information of the editing result is obtained, and the editing result is adjusted based on the feedback information of the editing result; or, in response to the receipt of result adjustment information in the information input area, the editing result is adjusted based on the result adjustment information. The adjusted editing result is displayed, and in response to a confirmation command for the adjusted editing result, the target video is obtained based on the adjusted editing result.

8. The method according to claim 1, characterized in that, The dialog interface also includes a quick jump control, and the method further includes: In response to the triggering of the quick jump control, multiple content title items of the dialog interface are displayed; In response to the triggering of a target title item among the plurality of content title items, the content corresponding to the target title item is displayed on the dialog interface.

9. The method according to claim 1, characterized in that, The dialog interface also includes a history dialog control at a designated location; the method further includes: In response to the triggering of the historical dialogue control, a historical information interface is displayed; wherein, the historical information interface displays a historical dialogue exhibition area; wherein, the historical dialogue exhibition area displays the prompt text used in the creation of the historical dialogue and the corresponding generated video, and different historical dialogue exhibition areas correspond to different dialogue creation times; In response to the target exhibition area in the historical dialogue exhibition area being triggered, the content corresponding to the target exhibition area is displayed on the dialogue interface for viewing or editing.

10. A video generation apparatus, characterized in that, include: The interface display module is used to display the dialogue interface. The dialogue interface displays an information input area and at least one creation guidance example. The creation guidance example includes a prompt text example and a corresponding material example. The creation guidance example is presented in card format and can be switched via a swipe operation. Different creation guidance examples correspond to different video creation themes, and different video creation themes correspond to different material selection criteria. The material selection criteria indicate the material type and / or the material duration range. The material examples in the creation guidance examples are selected based on the material selection criteria of the video creation theme corresponding to the creation guidance example. The content display module is used to respond to the information input area receiving first dialogue content, generate and display second dialogue content based on the first dialogue content; wherein, the first dialogue content includes: the content adjustment result of the target guidance example triggered in at least one creation guidance example; the second dialogue content includes at least the editing result corresponding to the material in the first dialogue content; The video generation module is used to generate a target video based on the editing results in the second dialogue content.

11. An electronic device, characterized in that, The electronic device includes: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the video generation method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the video generation method according to any one of claims 1-9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the video generation method according to any one of claims 1-9.

Images