Video generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a video generation method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a user demand of a video editing task, wherein the user demand comprises at least one video shot, demand keywords in one-to-one correspondence with the at least one video shot, and a video script; performing association analysis on the demand keyword and the video script based on AIGC, and generating retrieval keywords in one-to-one correspondence with the at least one video shot; aiming at each video shot, searching a target video material of which the added video material label is matched with the retrieval keyword corresponding to the video shot in a video material library, and generating a sub mixed video corresponding to the video shot based on AIGC according to the target video material corresponding to the video shot; and according to the sub-mixed-cut videos corresponding to the at least one video shot one by one, generating a mixed-cut video meeting user requirements based on the AIGC. Therefore, the creation efficiency and creation quality of the mixed and clipped video can be improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of artificial intelligence technology. More specifically, the embodiments of the present disclosure relate to a video generation method, device, electronic device and storage medium. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] In recent years, the promotion of products through video content has brought huge gross merchandise volume (GMV) and user growth to e-commerce businesses. Among them, promoting products through short videos is an important promotion channel.

[0004] Currently, in the entire creation process of short videos, there are problems such as high labor costs and time costs, and low creation efficiency. Summary of the invention

[0005] In a first aspect of the disclosed embodiments, a video generation method is provided, comprising: obtaining user requirements for a video editing task, the user requirements comprising at least one video shot, requirement keywords corresponding one-to-one to the at least one video shot, and a video script; performing association analysis on the requirement keywords and the video script based on AIGC, and generating retrieval keywords corresponding one-to-one to the at least one video shot; for each video shot, searching the video material library for target video materials whose added video material tags match the retrieval keywords corresponding to this video shot, and generating a sub-mixed video corresponding to this video shot based on AIGC according to the target video material corresponding to this video shot; and generating a mixed video that meets the user requirements based on AIGC according to the sub-mixed videos corresponding one-to-one to the at least one video shot.

[0006] In a second aspect of the disclosed embodiment, a video generation device is provided, comprising: an acquisition module, for obtaining user requirements for a video editing task, the user requirements including at least one video shot, requirement keywords corresponding one-to-one to the at least one video shot, and a video script; an analysis module, for performing association analysis on the requirement keywords and the video script based on AIGC, and generating retrieval keywords corresponding one-to-one to the at least one video shot; a retrieval module, for searching, for each video shot, in a video material library, for target video materials whose added video material tags match the retrieval keywords corresponding to this video shot; a generation module, for each video shot, for generating, based on AIGC, a sub-mixed video corresponding to this video shot according to the target video material corresponding to this video shot; the generation module is also used to generate, based on AIGC, a mixed video that meets the user requirements according to the sub-mixed videos corresponding one-to-one to the at least one video shot.

[0007] In a third aspect of the embodiments of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the video generating method.

[0008] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the video generating method is implemented.

[0009] In a fifth aspect of the embodiments of the present disclosure, a program product is provided, including a program code. When the program code is run on an electronic device, the program code is used to enable the electronic device to execute the video generation method.

[0010] The above embodiments of the present disclosure have at least the following beneficial effects: on the one hand, in the process of secondary creation based on existing video materials, compared with the method of manually retrieving materials and manually editing videos, automatically analyzing based on AIGC to obtain search keywords, automatically retrieving target video materials, and automatically generating mixed-cut videos can not only reduce the requirements for the user's technical level and improve the creation efficiency of mixed-cut videos, which is conducive to saving manpower costs and time costs, but also can support the rapid generation of massive mixed-cut videos, which is conducive to adapting to the rapid growth of mixed-cut video demand. On the other hand, based on the multi-lens creation mechanism, while automatically generating mixed-cut videos based on AIGC, it can ensure that the automatically generated mixed-cut videos meet the user's personalized customization needs, which is conducive to improving the creation quality of mixed-cut videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0012] Figure 1 is a flow chart of a video generation method provided by an exemplary embodiment;

[0013] Figure 2 is a schematic diagram of a video editing task details page provided by an exemplary embodiment;

[0014] Figure 3 is a schematic diagram of a video editing task list provided by an exemplary embodiment;

[0015] Figure 4 is a schematic diagram of a video material retrieval task creation page provided by an exemplary embodiment;

[0016] Figure 5 is a schematic diagram of an intelligent search service provided by an exemplary embodiment;

[0017] Figure 6 is a schematic diagram of a subtitle elimination process provided by an exemplary embodiment;

[0018] Figure 7 is a block diagram of a video generating device provided by an exemplary embodiment;

[0019] Figure 8 is a schematic diagram of a readable storage medium corresponding to a video generation method provided by an exemplary embodiment;

[0020] Fig. 9 It is a schematic diagram of an electronic device capable of implementing the above method provided by an exemplary embodiment.

[0021] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0022] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0023] Those skilled in the art will appreciate that the embodiments of the present disclosure may be implemented as a system, device, apparatus, method, computer-readable storage medium, or program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0024] According to an embodiment of the present disclosure, a video generation method, device, electronic device and storage medium are proposed.

[0025] In this document, it should be understood that any number of elements in the drawings is for illustration and not limitation, and any naming is only for distinction and does not have any limiting meaning. In addition, the data involved in this disclosure may be data authorized by the user or fully authorized by all parties.

[0026] The principle and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure.

[0027] Application Scenario Overview

[0028] In recent years, the use of video content to promote products has brought huge gross merchandise volume (GMV) and user growth to e-commerce businesses. Video content can include but is not limited to product promotion videos provided by manufacturers, product selling point videos created by sellers, live streaming videos that promote products, etc. Due to factors such as different creators of these video contents and various promotion and distribution platforms, these video contents are usually scattered in different business lines or in the hands of interface personnel, lacking effective management.

[0029] In some embodiments, if a short video is re-created for a product based on existing video content, it is usually necessary to manually collect and filter video content related to the product, and then manually edit the filtered video content using a video editing tool. Manual editing may include but is not limited to: manually importing the filtered original video into a video editing tool, manually splitting the original video, manually splicing a new secondary video, manually adjusting transition effects, manually adjusting subtitles, and manually adjusting dubbing.

[0030] It can be seen that in the above embodiment, in the secondary creation process of short videos, there are problems such as high labor costs and time costs, and low creation efficiency, which makes it difficult to cope with the rapid growth of short video demand, resulting in restrictions on product promotion.

[0031] It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principle of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario. SUMMARY OF THE INVENTION

[0033] In view of this, this specification provides a technical solution for creating remixed videos based on artificial intelligence generated content (AIGC).

[0034] The core concept of this manual is: based on the multi-lens creation mechanism and AIGC technology, you only need to determine the user needs of the video editing task, you can automatically retrieve the video materials that meet the user needs, and generate a mixed video that meets the user needs based on the retrieved video materials based on AIGC.

[0035] In some embodiments of the present disclosure, user requirements for a video editing task can be obtained, and the user requirements include at least one video shot, requirement keywords corresponding one-to-one to the at least one video shot, and a video script; further, the requirement keywords and the video script can be associated with each other based on AIGC to generate search keywords corresponding one-to-one to the at least one video shot; for each video shot, the video material library is searched for target video materials whose added video material tags match the search keywords corresponding to this video shot, and a sub-mixed video corresponding to this video shot is generated based on AIGC according to the target video material corresponding to this video shot; based on the sub-mixed videos corresponding one-to-one to the at least one video shot, a mixed video that meets the user requirements is generated based on AIGC.

[0036] Through the above methods, on the one hand, in the process of secondary creation based on existing video materials, compared with the method of manually retrieving materials and manually editing videos, AIGC automatically analyzes the search keywords, automatically retrieves the target video materials, and automatically generates mixed-cut videos. This can not only reduce the requirements for the user's technical level and improve the efficiency of mixed-cut video creation, which is conducive to saving manpower and time costs, but also supports the rapid generation of massive mixed-cut videos, which is conducive to adapting to the rapid growth of mixed-cut video demand. On the other hand, based on the multi-lens creation mechanism, while automatically generating mixed-cut videos based on AIGC, it can ensure that the automatically generated mixed-cut videos meet the user's personalized customization needs, which is conducive to improving the creation quality of mixed-cut videos.

[0037] Exemplary Methods

[0038] The technical concept of this specification is described in detail below through specific embodiments.

[0039] One or more embodiments shown in the present disclosure may be applied to a server, which may provide intelligent video editing services, script polishing services, subtitle adding services, dubbing adding services, video anti-duplicate services, video material retrieval services, video slicing services, subtitle removal services, etc. for the terminal used by the user. For the specific contents of the above services, please refer to one or more embodiments shown in the following text, which will not be described in detail here.

[0040] In the embodiments of the present disclosure, the server may include a server, a server cluster formed by multiple servers, or a cloud server. The server may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0041] In the embodiments of the present disclosure, the terminal may be an electronic device used by a user, and may specifically include but is not limited to a smart phone, a desktop computer, a tablet computer, a laptop computer, an e-book reader, a smart watch, a smart bracelet, and other electronic devices with certain computing capabilities.

[0042] In the implementation manner of the present disclosure, the terminal and the server may be directly or indirectly connected via wired communication or wireless communication, and the present disclosure does not impose any special limitation thereto.

[0043] The following first describes the intelligent remix service involved in the present disclosure. The intelligent remix service may specifically include at least one of a video retrieval service, a video editing service, a script extraction service, a script polishing service, a subtitle adding service, a dubbing adding service, and a video duplication prevention service.

[0044] See also Figure 1 , Figure 1 1 is a flowchart of a video generation method provided by an exemplary embodiment. The method may include the following steps:

[0045] Step S101: obtaining user requirements for a video editing task, where the user requirements include at least one video shot, a requirement keyword corresponding to the at least one video shot, and a video script.

[0046] For example, Figure 2 FIG. 1 is a schematic diagram of a video editing task details page provided by an exemplary embodiment. Figure 2As shown, the server can obtain user requirements for one or more video editing tasks. Among them, the task name of video editing task #1 is "Raw Coconut, Highland Barley, and Taro Paste-1"; video editing task #1 includes 6 shots, which are recorded as "Shot 0", "Shot 1", "Shot 2", "Shot 3", "Shot 4", and "Shot 5", among which the demand keyword corresponding to shot 0 is packaging, the demand keyword corresponding to shot 1 is inner packaging, the demand keyword corresponding to shot 2 is close-up, the demand keyword corresponding to shot 3 is close-up, the demand keyword corresponding to shot 4 is ingredients, and the demand keyword corresponding to shot 5 is exterior; the video script can be based on natural language description, such as "A certain merchant has launched a new product - Raw Coconut, Highland Barley, and Thick Taro Paste! The taste is simply amazing! This is a sticky and delicious taste that has been slowly boiled! There are large pieces of taro, highland barley rice, konjac rice and many other good ingredients in it, which is absolutely clean! You will definitely make money after eating it! Moreover, it is fat-free! No added sucrose! A bowl for breakfast will definitely satisfy you! Come and try it!".

[0047] It should be noted that in the above embodiment, the specific content of the demand keyword is only an exemplary description, and the present disclosure does not specifically limit this. For example, the demand keyword can also describe the trial record, spokesperson oral broadcast, user feedback and other content, or the demand keyword can also describe the camera movement type classification of video shots such as panning, zooming, and pulling.

[0048] In addition, it should be noted that in the above embodiment, describing the video script based on natural language is only an exemplary implementation, and the present disclosure does not specifically limit this. For example, the video script can also be described based on images, audio, video, etc.

[0049] In some possible implementations, the video script may be described in video form. In this case, a sample video specified by a user may be obtained; the content of the sample video may be analyzed based on AIGC to extract the video script.

[0050] For example, if a user wants to create a mixed-cut video that is similar to the main content of a sample video based on a variety of video materials, he or she can specify a sample video so that the server can analyze the content of the sample video based on AIGC and extract the video script of the sample video as a user requirement for the video editing task.

[0051] In some possible implementations, text adjustments may be made to the video script based on AIGC.

[0052] For example, Figure 2In the video editing task details page shown, in response to the trigger operation of the "AI Editing" button, the video script can be adjusted in text based on the OpenAI ChatGPT technology to obtain an automatically adjusted video script.

[0053] In the above embodiments, on the one hand, compared with the method of manually modifying the video script, automatically adjusting the text of the video script based on AIGC is conducive to reducing the requirements for the user's writing skills, improving the efficiency of video script creation, and saving labor costs and time costs. On the other hand, since the video script included in the video editing task may not be able to adapt to the remixed video automatically generated based on AIGC, by adjusting the text of the video script based on AIGC, a large number of video scripts can be quickly generated to adapt to the demand for quickly generating a large number of remixed videos.

[0054] In some possible implementations, at least one video lens included in the user's needs may be flexibly set by the user, or may be a video lens combination selected by the user from a plurality of preset video lens combinations, or may be obtained by further adjusting the selected video lens combination by the user, and the present disclosure does not specifically limit this.

[0055] In some possible implementations, the user requirement may further include a duration interval of each video shot, and the duration of each sub-mixed video is within the duration interval of the video interval corresponding to the sub-mixed video.

[0056] For example, Figure 2 As shown, the duration range of shot 0 is 0.40 to 8.37 seconds, the duration range of shot 1 is 0.61 to 7.53 seconds, the duration range of shot 2 is 0.59 to 8.54 seconds, the duration range of shot 3 is 0.59 to 8.54 seconds, the duration range of shot 4 is 0.97 to 13.67 seconds, and the duration range of shot 5 is 0.59 to 8.54 seconds.

[0057] In some possible implementations, the user requirement may also include the number of mashup videos that are expected to be generated.

[0058] For example, Figure 2 As shown, the number of mixed-cut videos expected to be generated included in the video editing task #1 is 20, so the server can execute the video editing task #1 to obtain 20 mixed-cut videos generated based on AIGC.

[0059] In some possible implementations, the user requirements may further include configuration information of subtitles, wherein the configuration information of subtitles includes at least one of whether to add subtitles to the mixed video, the style of the subtitles, and the display area of ​​the subtitles in the mixed video.

[0060] In some possible implementations, the user demand may further include configuration information of the dubbing audio, wherein the configuration information of the dubbing audio includes at least one of the style of the dubbing audio and the duration interval of the dubbing audio.

[0061] Step S102: performing association analysis on the demand keywords and the video script based on AIGC, and generating search keywords corresponding to at least one video shot.

[0062] For example, after obtaining the user needs of the video editing task, the demand keywords and video scripts corresponding to the six shots can be associated analyzed based on AIGC to generate search keywords corresponding to the six shots, among which the search keywords corresponding to shot 0 are "raw coconut, barley, and taro paste and product outer packaging and limited packaging", the search keywords corresponding to shot 1 are "raw coconut, barley, and taro paste and close-up and brewing", the search keywords corresponding to shot 2 are "raw coconut, barley, and taro paste and close-up", the search keywords corresponding to shot 3 are "raw coconut, barley, and taro paste and product inner packaging and new packaging", the search keywords corresponding to shot 4 are "raw coconut, barley, and taro paste and product ingredients taro and barley rice and konjac rice and zero fat and zero sucrose", and the search keywords corresponding to shot 5 are "raw coconut, barley, and taro paste and exterior and breakfast".

[0063] It should be noted that since the demand keywords involved in the embodiments of the present disclosure are described by users, there may be problems such as colloquialism, inaccuracy, and incompleteness. It may also be impossible to directly retrieve suitable video materials in the video material library based on the demand keywords. Therefore, by performing association analysis on the demand keywords and video scripts based on AIGC, more comprehensive and accurate search keywords can be generated, which is conducive to the subsequent retrieval of video materials that meet user needs in the video material library based on the search keywords.

[0064] Step S103: for each video shot, search the video material library for target video materials whose added video material tags match the search keywords corresponding to this video shot, and generate a sub-mixed video corresponding to this video shot based on AIGC according to the target video material corresponding to this video shot.

[0065] For example, the video material library can maintain video material tags for each video material, and the video material tags can be used to describe the content, camera type, etc. of the corresponding video material. After determining the search keywords corresponding to each shot, for shot 0, the video material library can be searched for the target video material whose added video material tags match "raw coconut, barley, thick taro paste and product outer packaging and limited packaging", such as Figure 2As shown, 144 target video materials corresponding to shot 0 are found; further, based on the 144 target video materials corresponding to shot 0, a sub-mixed video #1_0 corresponding to shot 0 is generated based on AIGC. Based on a similar process, target video materials corresponding to other shots can be retrieved, and sub-mixed videos corresponding to other videos can be generated based on the target video materials corresponding to other shots, which will not be described in detail here.

[0066] Step S104: Generate a mixed video that meets user needs based on AIGC according to the sub-mixed videos corresponding to at least one video shot.

[0067] For example, after generating sub-mixed video #1_0 corresponding to shot 0, sub-mixed video #1_1 corresponding to shot 1, sub-mixed video #1_2 corresponding to shot 2, sub-mixed video #1_3 corresponding to shot 3, sub-mixed video #1_4 corresponding to shot 4, and sub-mixed video #1_5 corresponding to shot 5 based on AIGC, mixed video #1 can be generated based on AIGC.

[0068] It should be noted that, since AIGC technology can utilize deep learning, natural language processing, computer vision and other technologies to enable machines to understand, generate and optimize content, and realize an automated and intelligent content production process, the "generating sub-mixed videos based on AIGC" and "generating mixed videos based on AIGC" involved in this disclosure refer to generating new mixed video content based on existing video materials, which may include but are not limited to automatically selecting and automatically cropping material clips from video materials, automatically determining the splicing order of material clips, automatically setting transition special effects, generating new video pictures and other links, and therefore should be distinguished from the traditional simple splicing of existing videos.

[0069] In some possible implementations, the user requirements may further include configuration information of subtitles, wherein the configuration information of subtitles includes at least one of whether to add subtitles to the mixed video, the style of the subtitles, and the display area of ​​the subtitles in the mixed video.

[0070] In some possible implementations, subtitles are generated based on AIGC according to the video script and configuration information of subtitles, and subtitles are added to the mixed video.

[0071] For example, Figure 2 As shown, the video editing task #1 sets "Show subtitles: Yes", so in the process of generating the mixed-cut video, subtitles can be generated according to the video script based on AIGC, and subtitles can be added to the generated mixed-cut video.

[0072] In the above embodiments, compared with the method of manually adding subtitles, automatically generating subtitles based on AIGC and automatically adding subtitles to the remixed video automatically generated based on AIGC can reduce the requirements on the user's technical level and improve the efficiency of creating remixed videos, which is conducive to saving labor costs and time costs, and is also conducive to adapting to the needs of quickly generating massive remixed videos.

[0073] In some possible implementations, the user demand may further include configuration information of the dubbing audio, wherein the configuration information of the dubbing audio includes at least one of the style of the dubbing audio and the duration interval of the dubbing audio.

[0074] In some possible implementations, the dubbing audio is generated based on AIGC according to the configuration information of the video script and the dubbing audio, and the dubbing audio is added to the mixed video.

[0075] For example, Figure 2 In the video editing task details page shown, the duration range of the desired dubbing audio is "4 to 55 seconds", and the style of the dubbing audio is "promotional female voice". In response to the trigger operation of the "Try It" button, the video script can be converted into dubbing audio based on text-to-speech (TTS) technology. Furthermore, the automatically generated dubbing audio can be added to the mixed video automatically generated based on AIGC.

[0076] In the above embodiments, compared with the method of manually dubbing and manually adding dubbing audio, automatically generating dubbing audio based on AIGC and automatically adding dubbing audio to the mixed video automatically generated based on AIGC can reduce the requirements on the user's technical level and improve the efficiency of creating mixed videos, which is conducive to saving labor costs and time costs, and is also conducive to adapting to the needs of quickly generating massive mixed videos.

[0077] In an embodiment of the present disclosure, in a scenario where a large amount of remixed videos are generated based on existing video materials, in order to avoid a situation where the remixed video being released has content duplication with existing videos, the remixed video may be checked for duplication after it is generated and before it is released. If it is found that the remixed video has content duplication with existing videos, the remixed video is processed to prevent duplication, and then the remixed video after the anti-duplication processing is checked for duplication for a second time and released.

[0078] In some possible implementations, video features of the mixed video are extracted from the mixed video; the video features of the mixed video are matched with video features of existing videos; if the video features of the mixed video successfully match the video features of any existing video, video anti-duplication processing is performed on the mixed video.

[0079] Among them, video features can include global or local features, such as inter-frame texture, color distribution, motion trajectory, etc., combined with perceptual hashing algorithm, deep learning model and other technical means to build a unique fingerprint identification for mixed videos or existing videos.

[0080] Among them, the video anti-duplication processing of the mixed video includes at least one of the following: replacing the video special effects used in the mixed video; replacing the first frame image of the mixed video; extracting some frame images from the mixed video; adding noise to the mixed video; performing micro-deformation processing on the mixed video.

[0081] In some possible implementations, after the mixed video is generated, the mixed video may be sent to a terminal.

[0082] For example, after the server completes video editing task #1, it can send 20 mixed-cut videos generated based on AIGC to the terminal.

[0083] For example, Figure 3 FIG. 1 is a schematic diagram of a video editing task list provided by an exemplary embodiment. Figure 3 As shown, after the server completes the execution of video editing task #1, it can update the execution status of video editing task #1 from "pending" to "completed", and send a notification of the completion of video editing task #1 to the terminal; in response to receiving a mixed video download request for video editing task #1 sent by the terminal, the server can send the execution result of video editing task #1 to the terminal, that is, 20 mixed videos generated based on AIGC.

[0084] In some possible implementations, in addition to combining a multi-lens creation mechanism for AIGC-based video editing, AIGC-based video editing may also be combined with elements such as emotion, theme, and rhythm, which will not be elaborated here.

[0085] In the embodiment of the present disclosure, in addition to the intelligent remix service, the server can also provide an intelligent retrieval service separately. The intelligent retrieval service can specifically include at least one of a video material retrieval service and a video material download service.

[0086] In some possible implementations, the video material library maintains metadata of each video material. The metadata of the video material includes but is not limited to the video material tag, the creator of the video material, the source platform of the video material, the release time of the video material, the title of the video material, and the browsing data of the video material (such as the number of likes, the number of collections, the number of reposts, the number of comments, etc.).

[0087] In some possible implementations, a video material retrieval task may be obtained, the video material retrieval task includes a retrieval keyword; the video material retrieval task is executed to obtain a video material retrieval result, the video material retrieval result includes at least one piece of metadata of the video material. Among them, executing the video material retrieval task to obtain the video material retrieval result includes: searching for a video material tag matching the retrieval keyword in a video material library; and using the metadata matching the included video material tag and the retrieval keyword as the video material retrieval result.

[0088] In some possible implementations, the video material retrieval task also includes constraints. Executing the video material retrieval task to obtain video material retrieval results includes: searching the video material library for video material tags that match the retrieval keyword; and taking metadata including the video material tags that match the retrieval keyword and the video material tags that meet the constraints as the video material retrieval results.

[0089] For example, Figure 4 FIG. 1 is a schematic diagram of a video material retrieval task creation page provided by an exemplary embodiment. Figure 4 As shown in the figure, the search keyword is "Coconut Plant Extract Dishwashing Liquid", and the constraint condition is "the source platform of the video material is platform A"; execute as follows Figure 4 The video material retrieval task shown in the figure can find metadata in the video material library whose video material tags match the retrieval keywords and whose video material tags meet the constraint conditions as the video material retrieval result. Figure 4 As shown, the video material retrieval task may also include the start execution time of the video material retrieval task, the estimated execution time of the video material retrieval task, the execution method of the video material retrieval task (such as regular execution, only once, etc.), the execution cycle of the video material retrieval task (such as daily, weekly, etc.), and the sorting method of the video material retrieval results (such as comprehensive sorting, sorting by release time, sorting by browsing data).

[0090] In some possible implementations, after the video material retrieval task is completed, the video material retrieval result may be sent to the terminal.

[0091] For example, the server completes the execution Figure 4 After completing the video material retrieval task shown, metadata of the video material matching the retrieval keyword may be sent to the terminal.

[0092] For example, the server completes the execution Figure 4After completing the video material retrieval task shown, the execution status of the video material retrieval task can be updated from "pending" to "completed", and a notification of the completion of the video material retrieval task is sent to the terminal; in response to receiving a video material retrieval result query request sent by the terminal, the server can send the video material retrieval result to the terminal.

[0093] In some possible implementations, a video material download task may be obtained, the video material download task including metadata of a specified video material; the video material download task is executed to obtain the specified video material, wherein the specified video material includes the video material selected by the user for download.

[0094] For example, the server completes the execution Figure 4 After completing the video material retrieval task shown, the metadata of the video material matching the retrieval keyword can be sent to the terminal; the terminal can select the video material to be downloaded on demand based on the video material retrieval results returned by the server, that is, the specified video material; further, the server can obtain and execute the video material downloading task to obtain the specified video material.

[0095] In some possible implementations, after obtaining the specified video material, the specified video material may be saved in a cloud storage space, which may be used by a user who creates a video material download task; and / or the specified video material may be sent to a terminal.

[0096] For example, the server can provide independent cloud storage spaces for different users and save the downloaded designated video materials in the cloud storage spaces of the corresponding users.

[0097] For example, after completing the video material download task, the server may send the specified video material to the terminal so that the terminal may save the specified video material locally.

[0098] For example, after completing the video material download task, the server may send a notification of the completion of the video material download task to the terminal; in response to receiving a video material download request sent by the terminal, the server may send the specified video material to the terminal.

[0099] Combine the following Figure 5 An exemplary description of the intelligent retrieval service is given. Figure 5 This is a schematic diagram of an intelligent retrieval service provided by an exemplary embodiment. In some embodiments, the video material retrieval task and / or the video material download task can be fully automatically executed through robotic process automation (RPA) technology, eliminating the need for users to manually perform heavy video material collection and download tasks, allowing users to devote more energy to video content creation and optimization.

[0100] like Figure 5 As shown, the tasks to be executed in the task center may include video material retrieval tasks to be executed and / or video material download tasks to be executed. The robot can query the video material retrieval tasks to be executed, execute these video material retrieval tasks, obtain video material retrieval results, that is, obtain the metadata of the video material, and then call back the video material retrieval results to the task center. The robot can also query the video material download tasks to be executed, execute these video material download tasks, obtain video material download results, that is, download the specified video material, and then call back the video material download results to the task center.

[0101] In the embodiments of the present disclosure, in addition to the intelligent remixing service and the intelligent retrieval service, the server can also provide a video material management service. The video material management service can include at least one of an intelligent video slicing service, an intelligent video material tagging service, and an intelligent subtitle removal service.

[0102] In some possible implementations, a video to be sliced ​​is obtained; key video frames in the video to be sliced ​​are identified, where the key video frames are used to characterize scene switching in the video to be sliced; the video to be sliced ​​is sliced ​​according to the key video frames to obtain at least one video slice; the content of each video slice is analyzed based on AIGC, content keywords of each video slice are extracted, and video material tags are added to each video slice according to the content keywords of each video slice; and at least one video slice is saved as video material in a video material library.

[0103] For example, after obtaining the video to be sliced, the PySceneDetect technology can be used to automatically identify the key video frames in the video to be sliced, and the video to be sliced ​​can be automatically segmented according to the key video frames to obtain multiple video slices; the OpenAI Whisper technology can also be used for intelligent script extraction to obtain the content keywords of these video slices, and video material labels can be added to each video slice according to the extracted content keywords, such as "packaging", "dialogue", "action scene", etc.

[0104] Among them, PySceneDetect technology can use scene recognition algorithms based on visual features (such as content threshold, brightness change detection, edge feature capture, etc.) to perform high-precision recognition of shot switching, accurately divide expressive independent scenes, and flexibly process whether it is a high-speed switching action clip or a long-shot literary expression to form sliced ​​materials with independent narratives. It should be noted that video slicing based on PySceneDetect technology is only an exemplary description, and this disclosure does not specifically limit this. For example, video slicing can also be based on technologies such as OpenCV.

[0105] In the above embodiments, through intelligent slicing and intelligently adding video material tags to each video slice, an efficiently managed and digitized video material library can be constructed, which is convenient for subsequent users to retrieve video materials according to video material tags, which is beneficial to improving the reuse efficiency of video materials and also beneficial to improving the efficiency of video mixing.

[0106] In some possible implementations, a first image sequence is extracted frame by frame from the video to be sliced, the first image sequence comprising a plurality of video frame images from which subtitles have not been eliminated; a subtitle region in each video frame image is determined; subtitle elimination processing is performed on the first image sequence according to the subtitle region to obtain a second image sequence, the second image sequence comprising a plurality of video frame images from which subtitles have been eliminated; and the second image sequence is spliced ​​into the video to be sliced ​​from which the subtitles have been eliminated.

[0107] For example, Figure 6 FIG. 1 is a schematic diagram of a subtitle removal process provided by an exemplary embodiment. Figure 6 As shown, the server can first extract a first image sequence frame by frame from the video to be sliced, the first image sequence comprising a plurality of video frame images from which subtitles have not been eliminated, and then perform subtitle elimination processing on each video frame image from which subtitles have not been eliminated based on the Lama-cleaner technology according to the determined subtitle area, to obtain video frame images from which subtitles have been eliminated, that is, the second image sequence, and finally splice the video frame images from which subtitles have been eliminated into the video to be sliced ​​from which subtitles have been eliminated.

[0108] In some possible implementations, the subtitle area is selected by a user. Alternatively, the subtitle area is identified based on image processing technology. Alternatively, the subtitle area is identified based on a pre-trained machine learning model.

[0109] For example, the user selects a subtitle area where the subtitles to be deleted are located on the terminal, and submits the subtitle area to the server.

[0110] For example, since the subtitle region usually has fixed morphological features and positional features, the subtitle region can be identified based on image processing technology. In some embodiments, through morphological operations such as corrosion and expansion, small noise points are removed and the overall connected area of ​​the subtitle is retained. In some embodiments, an optical character recognition (OCR) model is used to detect the text area of ​​the image to identify the location of the subtitle text, that is, to identify the region of interest (ROI).

[0111] For example, neural network-based segmentation models or detection models such as U-Net and YOLO can automatically identify the boundaries of subtitle areas after training.

[0112] For example, considering that subtitle styles and subtitle positions may be different in different videos or different segments of the same video, cluster analysis can be performed based on the subtitle region positions detected in continuous video frame images to obtain the subtitle region.

[0113] For example, the subtitle area is usually the same in multiple consecutive video frame images, so the subtitle area can be determined through temporal consistency analysis to avoid misjudgment.

[0114] In some possible implementations, if the subtitle area is automatically identified based on image recognition technology or a machine learning model, in order to improve the recognition accuracy of the subtitle area, the video frame image may be preprocessed before identifying the subtitle area. Image preprocessing may include, but is not limited to, color space conversion, binarization, etc. Color space conversion refers to converting the video frame image from an RGB image to a grayscale image, or to a color space such as HSV, YCbCr, etc., so as to facilitate subsequent detection of the edge and brightness features of the subtitle area. Binarization refers to using the fact that the subtitle color is usually significantly different from the surrounding image, and using threshold segmentation, edge detection, and other means to distinguish the subtitle area from the surrounding image.

[0115] In some possible implementations, not only can the subtitles be removed, but also the image at the location of the subtitles can be restored to ensure that the video frame image after the subtitles are removed is visually natural and coherent.

[0116] For example, after identifying the subtitle area, a mask can be generated, that is, the subtitle area is filled with white or black, and the surrounding image remains unchanged; further, the mask and the video frame image without subtitles can be input into the Lama-cleaner model. The Lama-cleaner model can generate and fill the content of the subtitle area blocked by the mask by learning the contextual features of the image and the pixel features of the surrounding image, and output the video frame image with the subtitles removed and the subtitle area repaired. In addition, after filling the subtitle area with content, the repaired subtitle area can be made more closely matched and naturally transitioned with the surrounding image through edge smoothing, color adjustment, detail enhancement and other technologies, avoiding possible distortion.

[0117] It should be noted that the subtitle removal and image restoration based on the Lama-cleaner technology is only an exemplary description, and the present disclosure does not specifically limit this. For example, subtitle removal and image restoration can also be performed based on technologies such as PatchMatch and DeepFill.

[0118] It should be noted that in the above embodiments, the video to be sliced ​​can be sliced ​​first and then the subtitles can be eliminated from the video slices. Alternatively, the video to be sliced ​​can be sliced ​​first and then the subtitles can be eliminated from the video slices. The present disclosure does not make any special limitations on this.

[0119] In the above embodiment, by intelligently eliminating subtitles while intelligently slicing the video, the video material without subtitles is saved in the video material library, so that subsequent users can directly use the video material without subtitles for secondary creation, which is beneficial to improving the reuse efficiency of video materials and also beneficial to improving the efficiency of video mixing.

[0120] It should be noted that, in the above embodiment, embedding the intelligent subtitle elimination service in the intelligent video slicing service is merely an exemplary description. In addition, the intelligent subtitle elimination service can also be provided separately, which will not be elaborated here.

[0121] Exemplary Devices

[0122] In an exemplary embodiment of the present disclosure, a video generating device is also provided.

[0123] See also Figure 7 , Figure 7 It is a block diagram of a video generating device provided by an exemplary embodiment.

[0124] like Figure 7 As shown, the video generation device 700 may include: an acquisition module 701, an analysis module 702, a retrieval module 703 and a generation module 704. Among them:

[0125] In some embodiments, an acquisition module is used to obtain user requirements for a video editing task, where the user requirements include at least one video shot, requirement keywords corresponding one-to-one to the at least one video shot, and a video script; an analysis module is used to perform association analysis on the requirement keywords and the video script based on AIGC, and generate search keywords corresponding one-to-one to the at least one video shot; a search module is used to search the video material library for target video materials whose added video material tags match the search keywords corresponding to the video shot for each video shot; a generation module is used to generate, for each video shot, a sub-mixed video corresponding to the video shot based on AIGC according to the target video material corresponding to the video shot; the generation module is also used to generate a mixed video that meets the user requirements based on AIGC according to the sub-mixed videos corresponding one-to-one to the at least one video shot.

[0126] In some embodiments, the obtaining module is used to: obtain a sample video specified by a user; analyze the content of the sample video based on AIGC to extract a video script.

[0127] In some embodiments, user requirements also include at least one of the following: the duration interval of each video shot, the duration of each sub-mixed video is within the duration interval of the video interval corresponding to this sub-mixed video; the number of mixed videos expected to be generated; subtitle configuration information, the subtitle configuration information includes whether to add subtitles to the mixed video, the style of the subtitles, and at least one of the display area of ​​the subtitles in the mixed video; dubbing audio configuration information, the dubbing audio configuration information includes at least one of the style of the dubbing audio and the duration interval of the dubbing audio.

[0128] In some embodiments, the device 700 further includes an adjustment module. The adjustment module is used to adjust the text of the video script based on AIGC; the generation module is also used to generate subtitles based on AIGC according to the configuration information of the video script and subtitles, and add subtitles to the mixed video; the generation module is also used to generate dubbing audio based on AIGC according to the configuration information of the video script and dubbing audio, and add dubbing audio to the mixed video.

[0129] In some embodiments, the device 700 further includes an anti-duplication module. The anti-duplication module is used to: extract video features of the mixed video from the mixed video; match the video features of the mixed video with video features of existing videos; if the video features of the mixed video successfully match the video features of any existing video, perform video anti-duplication processing on the mixed video.

[0130] In some embodiments, the anti-graft module is used to replace the video effects used in the mixed video; the anti-graft module is used to replace the first frame image of the mixed video; the anti-graft module is used to extract some frame images from the mixed video; the anti-graft module is used to add noise to the mixed video; the anti-graft module is used to perform micro-deformation processing on the mixed video.

[0131] In some embodiments, the apparatus 700 further includes a transceiver module, which is configured to send the mixed video to a terminal.

[0132] In some embodiments, the device 700 further includes an identification module, a slicing module, and a storage module. The acquisition module is also used to obtain the video to be sliced; the identification module is used to identify the key video frames in the video to be sliced, and the key video frames are used to indicate that the video to be sliced ​​has a scene switch; the slicing module is used to slice the video to be sliced ​​according to the key video frames to obtain at least one video slice; the analysis module is used to analyze the content of each video slice based on AIGC, extract the content keywords of each video slice, and add a video material tag to each video slice according to the content keywords of each video slice; the storage module is used to save at least one video slice as a video material to the video material library.

[0133] In some embodiments, the device 700 further includes a subtitle removal module. The subtitle removal module is used to: extract a first image sequence frame by frame from any video slice, the first image sequence including multiple video frame images from which subtitles have not been removed; determine the subtitle area in each video frame image; perform subtitle removal processing on the first image sequence according to the subtitle area to obtain a second image sequence, the second image sequence including multiple video frame images from which subtitles have been removed; and splice the second image sequence into a video slice from which subtitles have been removed.

[0134] In some embodiments, the subtitle area is selected by a user; or, the subtitle area is identified based on image processing technology; or, the subtitle area is identified based on a pre-trained machine learning model.

[0135] The specific details of each module of the above-mentioned video generating device 700 have been described in detail in the previous description of the video generating method process, and therefore, they will not be repeated here.

[0136] It should be noted that although several modules or units of the video generating device 700 are mentioned in the above detailed description, such division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0137] Exemplary Media

[0138] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes a program code, and when the program product is run on an electronic device, the program code is used to enable the electronic device to perform the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0139] See also Figure 8 , Figure 8 It is a schematic diagram of a readable storage medium corresponding to a video generating method provided by an exemplary embodiment.

[0140] refer to Figure 8As shown, a readable storage medium 800 for implementing the above method according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the readable storage medium of the present disclosure is not limited thereto. In the present disclosure, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0141] The readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0142] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0143] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0144] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0145] Exemplary Electronic Devices

[0146] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above-mentioned video generating method is also provided.

[0147] See also Fig. 9 , Fig. 9 It is a schematic diagram of an electronic device capable of implementing the above method provided by an exemplary embodiment.

[0148] Refer to the following Fig. 9 hereinafter describes an electronic device 900 according to such an embodiment of the present disclosure. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0149] like Fig. 9 As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include but are not limited to: at least one processing unit 901, at least one storage unit 902, and a bus 903 connecting different system components (including the storage unit 902 and the processing unit 901).

[0150] The storage unit stores program codes, and the program codes can be executed by the processing unit 901, so that the processing unit 901 executes the steps of the above-mentioned various embodiments of this specification.

[0151] The storage unit 902 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9021 and / or a cache storage unit 9022 , and may further include a read-only storage unit (ROM) 9023 .

[0152] The storage unit 902 may also include a program / utility 9024 having a set (at least one) of program modules 9025, such program modules 9025 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the reality of a network environment.

[0153] Bus 903 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0154] The electronic device 900 may also communicate with one or more external devices 904 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 905. Furthermore, the electronic device 900 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 906. As shown, the network adapter 906 communicates with other modules of the electronic device 900 via a bus 903. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0155] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0156] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0157] It should be noted that, although several units / modules or subunits / modules of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0158] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0159] Although the spirit and principle of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A video generation method, the method comprising: Obtaining user requirements for a video editing task, wherein the user requirements include at least one video shot, a requirement keyword corresponding to the at least one video shot, and a video script; Based on artificial intelligence generated content AIGC, the demand keywords and the video script are analyzed for correlation, and a search keyword corresponding to the at least one video shot is generated; For each video shot, search the video material library for the target video material whose added video material tag matches the search keyword corresponding to the video shot, and generate a sub-mixed video corresponding to the video shot based on AIGC according to the target video material corresponding to the video shot; According to the sub-mixed videos corresponding one-to-one to the at least one video shot, a mixed video that meets the user's needs is generated based on AIGC.

2. The method according to claim 1, wherein the user demand further comprises at least one of the following: The duration interval of each video shot, the duration of each sub-mixed video is within the duration interval of the video interval corresponding to the sub-mixed video; The expected number of mixed-cut videos to be generated; Configuration information of subtitles, the configuration information of subtitles including at least one of whether to add subtitles to the mixed video, the style of the subtitles, and the display area of ​​the subtitles in the mixed video; Configuration information of the dubbing audio, wherein the configuration information of the dubbing audio includes at least one of a style of the dubbing audio and a duration interval of the dubbing audio.

3. The method according to claim 2, further comprising at least one of the following: Performing text adjustment on the video script based on AIGC; Generate subtitles based on AIGC according to the video script and the configuration information of the subtitles, and add the subtitles to the mixed video; According to the configuration information of the video script and the dubbing audio, the dubbing audio is generated based on AIGC, and the dubbing audio is added to the mixed video.

4. The method according to claim 1, further comprising: Extracting video features of the mixed video from the mixed video; Matching video features of the mixed video with video features of existing videos; If the video feature of the mixed video successfully matches the video feature of any existing video, video anti-duplication processing is performed on the mixed video.

5. The method according to claim 1, further comprising: Get the video to be sliced; Identifying a key video frame in the video to be sliced, where the key video frame is used to indicate that a scene switch occurs in the video to be sliced; Slicing the video to be sliced ​​according to the key video frame to obtain at least one video slice; Analyze the content of each video slice based on AIGC, extract the content keywords of each video slice, and add video material tags to each video slice according to the content keywords of each video slice; The at least one video slice is saved as video material in the video material library.

6. The method according to claim 5, further comprising: Extracting a first image sequence frame by frame from any video slice, wherein the first image sequence comprises a plurality of video frame images from which subtitles have not been eliminated; Determine the subtitle area in each video frame image; Performing subtitle removal processing on the first image sequence according to the subtitle area to obtain a second image sequence, wherein the second image sequence includes a plurality of video frame images from which subtitles have been removed; The second image sequence is spliced ​​into a video slice from which subtitles have been removed.

7. A video generation device, the device comprising: An acquisition module, used to acquire user requirements for a video editing task, wherein the user requirements include at least one video shot, a requirement keyword corresponding to the at least one video shot, and a video script; An analysis module, configured to perform association analysis on the demand keyword and the video script based on AIGC, and generate a search keyword corresponding to the at least one video shot; A retrieval module is used to search, for each video shot, in the video material library for a target video material whose added video material tag matches the retrieval keyword corresponding to the video shot; A generation module, for generating, for each video shot, a sub-mixed video corresponding to the video shot based on AIGC according to a target video material corresponding to the video shot; The generation module is further used to generate a mixed video that meets the user's needs based on AIGC according to the sub-mixed videos corresponding one-to-one to the at least one video shot.

8. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 1 to 6.

10. A program product, comprising a program code, wherein when the program code is run on an electronic device, the program code is used to enable the electronic device to execute any one of the methods of claims 1-6.

Images