A method and device for generating a media file

Abstract

The embodiment of the present application discloses a method and device for generating a media file, and relates to the field of Internet application technology. The main technical scheme includes: displaying more than one recommended content on an interactive interface; in response to a user selecting a target recommended content from the more than one recommended content, sending the target recommended content to a server, so that the server generates a script using the target recommended content, and the script includes control variable information for generating a media file; in response to a user inputting material information on the interactive interface, sending the material information to the server; in response to receiving a media file sent by the server, the media file is generated using the script and the material information, and displaying the media file on the interactive interface. The use of this application can simplify user operations, improve user experience, and help users grasp the generation direction of media files.

Description

Technical Field

[0001] The present application relates to the field of Internet application technology, and in particular to a method and device for generating a media file. Background Art

[0002] With the popularization of the Internet and computer technology, more and more people use various applications to play media files. In particular, with the rapid development of self-media, a large number of media files use the Internet as a platform to disseminate information to the public. For the producers of media files, how to generate media files conveniently and quickly has become an urgent problem for major service providers. Summary of the invention

[0003] In view of this, the present application provides a method and device for generating a media file, so as to help a user generate a media file conveniently and quickly.

[0004] This application provides the following solutions:

[0005] In a first aspect, a method for generating a media file is provided, which is applied to a user terminal, and the method includes:

[0006] Display more than one recommended content on the interactive interface;

[0007] In response to a user selecting a target recommended content from the one or more recommended contents, sending the target recommended content to a server, so that the server generates a script using the target recommended content, the script including control variable information for generating a media file;

[0008] In response to the user inputting material information using the interactive interface, sending the material information to the server;

[0009] In response to receiving a media file sent by the server, the media file is generated by using the script and the material information, and displaying the media file on the interactive interface.

[0010] Optionally, the recommended content includes: recommended media files, media templates, recommended script themes or recommended script templates.

[0011] Optionally, the recommended content is obtained based on user account information.

[0012] Optionally, the interactive interface includes a first interface element;

[0013] The displaying of more than one recommended content on the interactive interface includes:

[0014] In response to the user inputting demand information using the first interface element, sending the demand information to the server, so that the server obtains one or more recommended contents using the demand information;

[0015] The one or more recommended contents are displayed on the interactive interface.

[0016] Optionally, the interactive interface further includes a second interface element, and the method further includes:

[0017] In response to the user inputting requirement information using the second interface element, the requirement information is sent to the server, so that the server generates a script using the requirement information.

[0018] Optionally, the demand information is in natural language form.

[0019] Furthermore, the interactive interface further includes a third interface element, and the method further includes:

[0020] In response to the user triggering the third interface element, one or more recommended contents displayed on the interactive interface are refreshed.

[0021] Furthermore, the method further comprises:

[0022] Obtaining the script;

[0023] The script is displayed using a fourth interface element of the interactive interface.

[0024] Optionally, there are multiple scripts;

[0025] The method further comprises: displaying the plurality of scripts using a fifth interface element of the interactive interface;

[0026] The using the fourth interface element of the interactive interface to display the script comprises: in response to a user selecting a script from the plurality of scripts, using the fourth interface element to display the selected script;

[0027] Sending the material information to the server includes: sending the selected script and the material information to the server.

[0028] Optionally, the fourth interface element is a text editing box, and the fifth interface element is a card component.

[0029] Furthermore, in response to the user editing the script using the fourth interface element;

[0030] The edited script is sent to the server.

[0031] Optionally, in response to the user inputting material information using the interactive interface, sending the material information to the server includes:

[0032] In response to a sixth interface element on the interactive interface being triggered, acquiring material information input by a user;

[0033] In response to the seventh interface element on the interactive interface being triggered, the material information is sent to the server.

[0034] Optionally, there are multiple media files, and displaying the media files on the interactive interface includes:

[0035] A plurality of the media files are displayed on the interactive interface.

[0036] Furthermore, the method further comprises:

[0037] In response to the user selecting a target media file from the plurality of media files, the selected target media file is played, or the selected target media file is stored, or information of the selected target media file is sent to the server.

[0038] In a second aspect, a method for generating a media file is provided, which is applied to a server, and the method comprises:

[0039] Sending one or more recommended contents to the user terminal;

[0040] Generate a script according to the target recommended content selected by the user from the one or more recommended contents, wherein the script includes control variable information for generating a media file;

[0041] Generate a media file using the script and the material information input by the user;

[0042] The media file is sent to the client.

[0043] In a third aspect, a device for generating a media file is provided, which is arranged at a user end, and the device includes:

[0044] An interface display unit, configured to display one or more recommended contents on the interactive interface;

[0045] The service-side interaction unit is configured to, in response to a user selecting a target recommended content from the one or more recommended contents, send the target recommended content to a server side, so that the server side generates a script using the target recommended content, the script including control variable information for generating a media file; in response to a user inputting material information using the interaction interface, send the material information to the server side; and receive a media file sent by the server, the media file being generated using the script and the material information;

[0046] The interface display unit is further configured to display the media file on the interactive interface.

[0047] In a fourth aspect, a device for generating a media file is provided, which is arranged on a server side, and the device comprises:

[0048] A user-side interaction unit configured to send one or more recommended contents to the user terminal;

[0049] a script generating unit configured to generate a script according to a target recommended content selected by a user from the one or more recommended contents, wherein the script includes control variable information for generating a media file;

[0050] The user-side interaction unit is further configured to obtain material information input by the user from the user terminal;

[0051] A media generation unit, configured to generate a media file using the script and material information input by a user;

[0052] The user-side interaction unit is further configured to send the media file to the user terminal.

[0053] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the first aspect or the second aspect are implemented.

[0054] In a sixth aspect, an electronic device is provided, including:

[0055] one or more processors; and

[0056] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in the first aspect or the second aspect above.

[0057] In a seventh aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0058] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0059] 1) With the technical solution provided by this application, users only need to select target recommended content from one or more recommended content displayed on the interactive interface and input material information to conveniently and quickly generate media files, which simplifies user operations and improves user experience.

[0060] In addition, in the present application, more than one recommended content is first displayed on the interactive interface to provide a reference for the user, so that the user can select one of the more than one recommended content as the target recommended content to guide the generation of the script, thereby controlling the generation of the media file. This method can help the user better grasp the generation direction of the media file, improve the generation effect of the media file, and avoid the user from constantly trying to re-enter the requirements, thereby improving the user's operating efficiency and thus improving the user experience.

[0061] 2) In the present application, a variety of intuitive forms such as recommended media files, media templates, recommended script themes or recommended script templates can be displayed on an interactive interface to provide users with references, so that users can choose from them to guide the generation of scripts.

[0062] 3) In the present application, recommended content can be obtained based on user account information, so that more than one recommended content can be displayed to the user for selection without user operation, and the user can select the recommended content to control the generation direction of the media file.

[0063] 4) In the present application, a first interface element may also be provided on the interactive interface, and the user may use the first interface element to input demand information, so that one or more recommended contents may be obtained based on the demand information actually input by the user, thereby providing the user with more accurate choices, and also providing a flexible way for the user to accurately express their needs.

[0064] 5) In the present application, a second interface element may also be provided on the interactive interface, and the user may use the second interface element to input demand information, which is sent to the server so that the server can use the demand information input by the user as a guide to more accurately generate script information, thereby improving the accurate control of the generated media content.

[0065] 6) In this application, users can input their demand information in the form of natural language on the interactive interface. Compared with the traditional method in which users need to input their demand information one by one according to the form requirements, users can express their needs in a more natural way, which is more flexible and provides a better user experience.

[0066] 7) In this application, if the user is not satisfied with the recommended content, the user can use the third interface element on the interactive interface to refresh one or more recommended contents displayed. The operation is simple, and the user can use simple operations to find recommended content that meets his or her needs, further improving the user experience.

[0067] 8) In the present application, the generated script can also be displayed on the interactive interface so that the user can intuitively know whether the control variables for generating the media file are accurate, thereby further improving the user experience.

[0068] 9) There may be multiple scripts generated and displayed in this application, and users can select the script that best meets their needs from multiple scripts to generate media files. This method can provide users with more refined script selection, thereby controlling the generation direction of media files.

[0069] 10) In this application, card components can be used to display multiple scripts, and text boxes can be used to display the script selected by the user, which can intuitively display and effectively distinguish the scripts, thereby facilitating user operations and improving user experience.

[0070] 11) In this application, the user can use the fourth interface element to edit the script, so that the user can more finely adjust the control variables of the generated media file, improve the controllability of the generated media file, make the generated media file more accurate, and improve the user experience.

[0071] 12) In the present application, the user can use the sixth interface element on the interactive interface to input material information, and use the triggering seventh interface element to send the material information to the server. This method allows the user to flexibly input material information and send it to the server after confirmation. On the one hand, it ensures the convenience and flexibility of material information input, and on the other hand, it also ensures the reliability of material information input.

[0072] 13) In this application, there may be multiple media files generated, that is, batch production of media files is achieved, which is more efficient and more selective for users.

[0073] 14) In this application, the user can select a target media file from multiple media files, and then play, store or send the information of the target media file to the server to facilitate subsequent applications. The user only needs to select from them, which is simple to operate and more visual.

[0074] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0076] Figure 1 is a system architecture diagram applicable to the embodiments of the present application.

[0077] Figure 2 A flowchart of an information display method executed by a user terminal provided in Example 1 of the present application.

[0078] Figure 3 An interactive flow chart for generating a media file provided in Embodiment 2 of the present application.

[0079] Figure 4a , Figure 4b , Figure 4c , Figure 4d , Figure 4e and Figure 4f They are respectively example diagrams of the interactive interface provided in Example 2 of the present application at different stages.

[0080] Figure 5 Another interactive flow chart for generating a media file provided in Embodiment 3 of the present application.

[0081] Figure 6a , Figure 6b , Figure 6c , Figure 6d , Figure 6e and Figure 6f They are respectively example diagrams of the interactive interface provided in Example 3 of the present application at different stages.

[0082] Figure 7 This is a flowchart of a method for generating a media file executed by a server provided in Embodiment 4 of the present application.

[0083] Figure 8 This is a schematic block diagram of a media file generation device provided at a user terminal according to Embodiment 5 of the present application.

[0084] Fig. 9 This is a schematic block diagram of a media file generation device provided on a server side according to Embodiment 6 of the present application.

[0085] Fig.10 A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0087] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0088] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0089] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0090] With the continuous development of AIGC (Artificial Intelligence Generated Content) technology, generative models can automatically generate media files for users based on certain demand information. Therefore, there are already some traditional methods that provide users with an interface. After the user enters demand information such as industry, product name, characteristics, etc. in the form of a form on the interface and uploads the material, the generative model uses the demand information to generate media files such as videos, and then associates the generated media files with the user account and publishes them. However, this traditional method has the following defects;

[0091] 1) AIGC is highly random. Although users input their demand information, it is difficult to grasp the direction of media file generation, and the controllability is very poor. Therefore, the generated media files often fail to meet user needs, and users need to keep trying to re-enter their demand information to regenerate media files, which is inefficient and has a poor user experience.

[0092] 2) Users need to input required information according to the requirements in the form, which is cumbersome, inefficient and has a poor user experience.

[0093] In view of this, the present application provides a new idea. In order to facilitate the understanding of the present application, the system architecture on which the present application is based is first described. Figure 1 An exemplary system architecture to which the embodiments of the present application can be applied is shown. Figure 1 As shown in , the system architecture may include: a terminal device of a content producer and a user terminal running on the terminal device, a terminal device of a content consumer and a user terminal running on the terminal device, a server terminal, a server, and a media library.

[0094] The user end involved in the embodiments of the present application may be a client running on a terminal device, a small program, or a Web application running using a browser, etc.

[0095] Terminal devices may include but are not limited to smart mobile terminals, wearable devices, PCs (Personal Computers), smart home devices, etc. Smart mobile devices may include mobile phones, tablet computers, laptops, PDAs (Personal Digital Assistants), Internet car terminals, etc. Wearable devices may include smart watches, smart glasses, smart bracelets, VR (Virtual Reality) devices, AR (Augmented Reality), mixed reality devices (i.e., devices that can support both virtual reality and augmented reality), etc. Smart home devices may include smart TVs, smart refrigerators with display screens, etc.

[0096] The server side is set on the server, and may be an application program running on the server, or may also be a functional unit such as a plug-in or a software development kit (SDK) set in the application program.

[0097] The server provides media services and can be a single server, a server group consisting of multiple servers, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a host product in the cloud computing service system to solve the defects of difficult management and weak service scalability in traditional physical hosts and virtual private servers (VPS) services.

[0098] In the embodiment of the present application, the user as the content producer can use the user end on the terminal device to interact with the server end to realize the generation of media files. The media library can be used to store and maintain the generated media files.

[0099] Users who are content consumers can use the user end on the terminal device to interact with the server end, request and obtain media files and play them.

[0100] It should be understood that Figure 1 The number of the user terminals, terminal devices, server terminals, servers and media libraries in the embodiment is only for illustration. According to the implementation requirements, there can be any number of user terminals, terminal devices, server terminals, servers and media libraries.

[0101] Embodiment 1

[0102] Figure 2 A flowchart of a method for generating a media file executed by a user terminal provided in an embodiment of the present application, which method can be applied to Figure 1 The user end of the content producer in the system shown is executed. Figure 2 As shown in , the method may include the following steps:

[0103] Step 201: Display one or more recommended contents on the interactive interface.

[0104] In the embodiment of the present application, after the user who is the content producer logs in to the service, the user terminal can display the interactive interface to the user. Alternatively, the user uses a specified link to access the interactive interface, and the user terminal displays the interactive interface to the user. Alternatively, after the user opens the user terminal, the user terminal displays the interactive interface by default.

[0105] The interface (or page) involved in the embodiments of the present application refers to a collection of visual elements provided to users, and users can use the interface to interact with information, so it is called an interactive interface. The elements on the interface are interface elements, which may include fonts, icons, components, etc. Among them, the components on the interface refer to objects obtained by simply encapsulating data and methods, which may also be called controls. They may include buttons, input boxes, drop-down menus, dialog boxes, navigation bars, cards, etc.

[0106] The recommended content involved in the embodiments of the present application can represent the general "direction" of generating a media file. The so-called "direction" of generating a media file is usually reflected by style, theme, effect, etc. The user can select one from the recommended content as a reference for subsequent script generation and then media file generation. The recommended content can include but is not limited to: recommended media files, media templates, recommended script themes or recommended script templates, etc.

[0107] Among them, the recommended media files actually recommend instances of some media files to users as recommended content, so that users can use instances of specific media files as references. Media templates refer to pre-designed templates of media layout and style, and templates usually provide a structured framework for the generation of media files. The scripts involved in the embodiments of the present application are important texts that guide the generation of media files, mainly including control variable information for generating media files. Accordingly, the so-called script theme refers to the main information expressed by the script, which is a description of the control variable information contained in the script. The script template is a structured framework, which refers to a pre-designed control variable information template that embodies the media layout and style.

[0108] Step 203: In response to the user selecting a target recommended content from more than one recommended content, the target recommended content is sent to the server, so that the server generates a script using the target recommended content, the script including control variable information for generating a media file.

[0109] Step 205: In response to the user inputting material information using the interactive interface, the material information is sent to the server.

[0110] The so-called material refers to the original material used to generate media files, which is usually unorganized and scattered, but the material is the basis and main content of generating media files.

[0111] The media files involved in the embodiments of the present application may be videos, animations, pictures, audio, etc. For example, if the media file is a video, the above-mentioned material information may be text, pictures, audio, etc. For another example, if the media file is audio, the above-mentioned material information may be audio clips, text, etc. For another example, if the media file is a picture, the above-mentioned material information may be icons, text, graphic elements, etc. For the convenience of description, the subsequent embodiments all take the generation of videos as an example, and the implementation methods of other forms of media files are similar.

[0112] Step 207: In response to receiving the media file sent by the server, the media file is generated by using the script and the above-mentioned material information, and the media file is displayed on the interactive interface.

[0113] It can be seen from the above process that with the technical solution provided by the present application, users only need to select target recommended content from one or more recommended content displayed on the interactive interface and enter material information to conveniently and quickly generate media files, which simplifies user operations and improves user experience.

[0114] In addition, in the present application, more than one recommended content is first displayed on the interactive interface to provide a reference for the user, so that the user can select one of the more than one recommended content as the target recommended content to guide the generation of the script, thereby controlling the generation of the media file. This method can help the user better grasp the generation direction of the media file, improve the generation effect of the media file, and avoid the user from constantly trying to re-enter the requirements, thereby improving the user's operating efficiency and thus improving the user experience.

[0115] The above steps are described in detail below in conjunction with the embodiments. It should be noted that the "first" and "second" limitations involved in this application do not have limitations in terms of size, order, and quantity, and are only used to distinguish them in name. For example, "first interface element", "second interface element", etc. are only used to distinguish each interface element in name.

[0116] Embodiment 2

[0117] In order to facilitate the understanding of the entire interaction process, Figure 3 Taking the interactive process shown in the figure as an example, a preferred interactive process provided by the embodiment of the present application is described. Figure 3 As shown in , the method may include the following process:

[0118] In step 301, a user logs into a service using a client.

[0119] In the embodiment of the present application, the user can use the account login service, and the server obtains the user account information.

[0120] In step 302, the server obtains user account information, generates one or more video instances according to the user account information, and sends the one or more video instances to the user.

[0121] After the user logs in, the server obtains the user account information, which may be attribute information such as the user account number, the industry to which the user belongs, and the user's product information.

[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0123] The server determines the recommended content based on the user account information, that is, it can display more than one recommended content to the user without user operation. In this embodiment, a video instance is taken as an example. The so-called video instance refers to a video that already exists in the video library as an example for the user to refer to and select. The video instance recommended by the server can reflect different video generation "directions" as much as possible. Videos of different generation "directions" usually have control variable information with large differences.

[0124] In step 303, the user terminal displays one or more video instances on the interactive interface.

[0125] like Figure 4a In the interactive interface shown in , a total of 10 video instances can be displayed, namely, video instance 1, video instance 2, ..., video instance 10. The number of video instances shown in the figure is for illustration only, and the present application does not impose any particular limitation thereto.

[0126] In addition to generating recommended content (video examples in this embodiment) based on user account information, users can also input demand information on their own, and the server generates video examples based on the demand information and sends them to the user. Figure 4a As shown in , the interactive interface may include a first page element, and the first page element shown in the figure is a text input box, and the user can use the text input box to input the required information, and click "Send" to trigger the user end to send the required information to the server end. In addition to the text input box, other forms of first page elements can also be used, such as a voice input component, an option component, etc.

[0127] The required information input by the user can be video theme, style, object, industry, etc. Figure 4a In the text input box shown in , users can flexibly input demand information in the form of natural language. The server can use a large language model to understand the demand information in the form of natural language and generate recommended video instances.

[0128] In this embodiment, the user inputs the demand information using the first interface element, so that more than one recommended content can be obtained according to the demand information actually input by the user, which provides a flexible way for the user to accurately express the demand. Moreover, compared with the traditional method in which the user needs to input the demand information one by one according to the form requirements, the user can express the demand in a more natural way, which is more flexible and has a better user experience.

[0129] In step 304, in response to the user selecting a target video instance from more than one video instance, the target video instance is sent to the server.

[0130] The user can play the video instance by clicking the play component to check whether it meets his needs. If there is a video instance that meets his needs, he can select it as the target video instance.

[0131] Furthermore, if the user is not satisfied with all the video instances on the interactive interface, the third interface element on the interactive interface can be used to refresh the displayed video instances. Figure 4a As shown in , the third interface element can send a refresh request to the server, and the server regenerates one or more video instances and sends them to the user, and the user refreshes the displayed video instance.

[0132] In step 305, the server generates a script using the target video instance and returns it to the user end. The script includes control variable information for generating a media file.

[0133] In an embodiment of the present application, the script mainly includes control variable information for generating media files. The control variable information may include, but is not limited to, content-related variables, technology-related variables, effect-related variables, interaction-related variables, audio-related variables, and the like. Content-related variables may include, for example, scene information, story structure, material location, arrangement style, and the like. Technology-related variables may include, for example, frame rate, frame size, duration, and the like. Effect-related variables may include brightness, contrast, saturation, transition effects, special effects, and the like. Interaction-related variables may include, for example, variables that embody interaction effects, such as hot zone elements and icons. Audio-related variables may include, for example, background music, dubbing, and the like.

[0134] When the server generates a script using the target video instance, it can extract the script from the target video instance using a script generation model, for example. The script generation model can be implemented in a variety of ways, such as a deep learning model and a large model, and this application does not limit this.

[0135] In this embodiment, the generated script is sent to the user end for display. In addition, the script may not be sent to the user end.

[0136] In step 306, the user terminal displays the script on the interactive interface.

[0137] In this embodiment, the generated script can also be displayed on the interactive interface so that the user can intuitively know whether the control variables for generating the media file are accurate, thereby further improving the user experience. Figure 4b As shown in , the interactive interface may include a fourth interface element, and the script is displayed using the fourth interface element. The fourth interface element in the figure is a text editing box. In addition, other forms of interface elements may also be used. The "XXXXXX..." in the fourth interface element represents the content of the script.

[0138] In this embodiment, if the user is not satisfied with the content of the script, the user can edit the script using the fourth interface element. In response to the user editing the script using the fourth interface element, the user terminal sends the edited script to the server terminal. For example, the user can click Figure 4b In the "Edit" component shown in the figure, you can add, modify, delete, and other editing operations on the script content in the text editing box. In this way, users can adjust the control variables of the generated media files more finely, improve the controllability of the generated media files, make the generated media files more accurate, and improve the user experience.

[0139] In step 307, in response to the user inputting material information on the interactive interface, the user end sends the material information to the server end.

[0140] A sixth interface element may be provided to the user on the interactive interface, such as Figure 4b As shown in , in response to the sixth interface element on the interactive interface being triggered, the material information input by the user is obtained. Figure 4c As shown in , after the user triggers the sixth interface element, a window may pop up on the interactive interface. The user may use the window to select materials from, for example, a local storage space or a server-side material library for input. After clicking the "OK" component, the input of the material is completed, and the user returns to the interactive interface as shown in FIG. Figure 4d The interactive interface shown in .

[0141] The interactive interface may further include a seventh interface element, and in response to the seventh interface element on the interactive interface being triggered, the material information is sent to the server. Figure 4d As shown in , the user triggers the seventh interface element, namely the "Generate Video" component, and sends the input material information to the server.

[0142] In step 308, the server generates one or more video files using the script and the material information, and sends the generated video files to the user end.

[0143] In this step, the server can use AIGC technology to generate a video file using scripts and material information. The generated video file can be one or more. In addition, since AIGC technology takes a certain amount of time to generate a video file, the user clicks Figure 4d After you create a Generate Video component as shown in Figure 4e The interactive interface shown in , displays prompt information such as "Video is being generated" to prompt the user to wait.

[0144] In step 309, the user terminal displays one or more video files on the interactive interface.

[0145] like Figure 4fAs shown, a total of five generated video files, namely video 1, video 2, ..., video 5, are displayed on the interactive interface.

[0146] In step 310, in response to the user selecting a target video file from more than one video file, information of the target video file is sent to a server.

[0147] For more than one video file displayed on the interactive interface, the user can select a target video file for different subsequent processing. For example, the player component corresponding to the target video file can be selected to play the target video file. For another example, the target video file can be stored using a trigger storage component. For another example, the information of the selected target media file can be sent to the server.

[0148] like Figure 4f As shown in , the user can click on video 4 as the target video file, and then select "Publish to Home Page" to send the target video file to the server side in the publishing request.

[0149] In step 311, the target video file is associated with the user account and then published.

[0150] For example, publish to the homepage of the media service, publish to the user's home page, publish to the page under a specific subject, and so on.

[0151] Figure 3 The process shown actually provides users with a capability to "generate the same video", that is, using the existing video instance as a reference, and generating a video that is the same as the video instance selected by the user based on the material information provided by the user.

[0152] Embodiment 3

[0153] Below Figure 5 Taking the interactive process shown in the figure as an example, another preferred interactive process provided by the embodiment of the present application is described. Figure 5 As shown in , the method may include the following process:

[0154] In step 501, a user logs into a service using a client.

[0155] In the embodiment of the present application, the user can use the account login service, and the server obtains the user account information.

[0156] In step 502, the server obtains user account information, generates one or more script themes according to the user account information, and sends the one or more script themes to the user.

[0157] After the user logs in, the server obtains the user account information, which may be attribute information such as the user account number, the industry to which the user belongs, and the user's product information.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0159] The server determines the recommended content based on the user account information, that is, it can display more than one recommended content to the user without user operation. In this embodiment, the script theme is taken as an example. The so-called script theme refers to the main information expressed by the script, which is a description of the control variable information contained in the script. The script theme recommended by the server can reflect different video generation "directions" as much as possible. Videos of different generation "directions" usually have control variable information with large differences.

[0160] In step 503, the user terminal displays one or more script themes on the interactive interface.

[0161] like Figure 6a In the interactive interface shown in , script theme 1, script theme 2, script theme 3 and script theme 4 can be displayed. The fields, keywords, etc. of each script theme can be specifically displayed for users to understand and select. The number of script themes shown in the figure is schematic, and this application does not impose any special restrictions on this.

[0162] In addition, in addition to generating recommended content (script themes in this embodiment) based on user account information, users can also input demand information on their own, and the server generates a video instance using the demand information and sends it to the user. This part is similar to that in Embodiment 2 and will not be described in detail here.

[0163] The demand information input by the user can be video themes, styles, objects, industries, etc. The server can use a large language model to understand the demand information in natural language form and generate recommended script topics.

[0164] In step 504, in response to a target script theme selected by the user from more than one script theme, the target script theme is sent to the server.

[0165] In step 505, the server generates multiple scripts using the target video instance and returns them to the user end. The scripts include control variable information for generating media files.

[0166] In an embodiment of the present application, the script mainly includes control variable information for generating media files. The control variable information may include, but is not limited to, content-related variables, technology-related variables, effect-related variables, interaction-related variables, audio-related variables, and the like. Content-related variables may include, for example, scene information, story structure, material location, arrangement style, and the like. Technology-related variables may include, for example, frame rate, frame size, duration, and the like. Effect-related variables may include brightness, contrast, saturation, transition effects, special effects, and the like. Interaction-related variables may include, for example, variables that embody interaction effects, such as hot zone elements and icons. Audio-related variables may include, for example, background music, dubbing, and the like.

[0167] When the server generates a script using the target video instance, it can extract the script from the target video instance using a script generation model, for example. The script generation model can be implemented in a variety of ways, such as a deep learning model and a large model, and this application does not limit this.

[0168] In this embodiment, taking the generation of multiple scripts as an example, only one script may be generated. In addition, the script generated in this embodiment may not be sent to the user end for display.

[0169] In step 506, the user terminal displays multiple scripts on the interactive interface.

[0170] The fifth interface element can be used to display multiple scripts on the interactive interface. Figure 6b As shown in , the fifth interface element may be in the form of a card component, for example, to display script 1, script 2, and script 3. In addition to the card component, other forms of interface elements may also be used, such as a text box.

[0171] If the user is not satisfied with the generated script, the user can use the second interface element on the interactive interface to input the required information. In response to the user inputting the required information using the second interface element, the user terminal sends the required information to the server terminal, so that the server terminal generates a script using the required information and resends the generated script to the user terminal for display.

[0172] The required information input by the user can be the video theme, style, object, industry, etc., or even specific control variable information. Figure 6b In the text input box shown in , users can flexibly input demand information in natural language. The server can use a large language model to understand the demand information in natural language and generate a script. This method can use the demand information input by the user as a guide to generate script information more accurately, thereby improving the effect of the generated media content.

[0173] In step 507, in response to the user terminal selecting one of the scripts, the script is displayed in an editable form on the interactive interface.

[0174] In this embodiment, if the user selects one of the scripts from the multiple scripts, the selected script can be displayed in an editable form using the fourth interface element on the interactive interface. Figure 6b Script 2 in the interactive interface is as follows Figure 6c The text edit box shown in the figure displays the contents of the script.

[0175] If the user is not satisfied with the content of the script, the user can edit the script using the fourth interface element. In response to the user editing the script using the fourth interface element, the user terminal sends the edited script to the server terminal. For example, the user can click Figure 6c In the "Edit" component shown in the figure, you can add, modify, delete, and other editing operations on the script content in the text editing box. In this way, users can adjust the control variables of the generated media files more finely, improve the controllability of the generated media files, make the generated media files more accurate, and improve the user experience.

[0176] In step 508, in response to the user inputting material information on the interactive interface, the user end sends the material information and the selected script information to the server end.

[0177] A sixth interface element may be provided to the user on the interactive interface, such as Figure 6c As shown in , in response to the sixth interface element on the interactive interface being triggered, the material information input by the user is obtained. Figure 6d As shown in , after the user triggers the sixth interface element, a window may pop up on the interactive interface. The user may use the window to select materials from, for example, a local storage space or a server-side material library for input. After clicking the "OK" component, the material input is completed. Figure 6e The interactive interface shown in .

[0178] The interactive interface may further include a seventh interface element, and in response to the seventh interface element on the interactive interface being triggered, the material information and the script information selected by the user are sent to the server. Figure 6e As shown in , the user triggers the seventh interface element, namely the "Generate Video" component, and sends the input material information and the script information selected by the user to the server.

[0179] In step 509, the server generates one or more video files using the script and material information selected by the user, and sends the generated video files to the user.

[0180] In this step, the server can use AIGC technology to generate a video file using scripts and material information. The generated video file can be one or more. In addition, since AIGC technology takes a certain amount of time to generate a video file, the user clicks Figure 6e After the "Generate Video" component shown in , a prompt message such as "Video is being generated" can be displayed in the interactive interface to prompt the user to wait.

[0181] In step 510, the user terminal displays one or more video files on the interactive interface.

[0182] like Figure 6f As shown, a total of five generated video files, namely video 1, video 2, ..., video 5, are displayed on the interactive interface.

[0183] In step 511, in response to the user selecting a target video file from more than one video file, information of the target video file is sent to a server.

[0184] For more than one video file displayed on the interactive interface, the user can select a target video file for different subsequent processing. For example, the player component corresponding to the target video file can be selected to play the target video file. For another example, the target video file can be stored using a trigger storage component. For another example, the information of the selected target media file can be sent to the server.

[0185] like Figure 6f As shown in , the user can click on video 4 as the target video file, and then select "Publish to Home Page" to send the target video file to the server side in the publishing request.

[0186] In step 512, the target video file is associated with the user account and then published.

[0187] For example, publishing to the homepage of the media service, publishing to the user's homepage, publishing to a page under a specific subject, etc. It can be seen that by associating the target video file with the user account, the user can publish the target video file with a simple selection operation, which is simple to operate and improves the user experience.

[0188] Embodiment 4:

[0189] Figure 7 The flowchart of the method for generating a media file executed by the server side is provided in the embodiment of the present application. Figure 7 As shown in , the method may include the following steps:

[0190] Step 701: Send one or more recommended contents to the user terminal.

[0191] The recommended content may include recommended media files, media templates, recommended script themes or recommended script templates.

[0192] The user can use the account to log in to the service, and the server obtains the user account information. The user account information can be obtained based on the user account information. As one of the achievable methods, the recommended content is obtained based on the user account information. The server determines the recommended content based on the user account information, that is, it can display more than one recommended content to the user without the user's operation.

[0193] As another achievable method, the above-mentioned recommended content can be obtained based on the demand information input by the user. For example, the user can use the first page element on the interactive interface to input the demand information, and the user terminal sends it to the server terminal. The server terminal obtains more than one recommended content based on the demand information.

[0194] As one of the feasible ways, the server can use a large language model to obtain recommended content using user account information or demand information. The generative model based on the large language model has powerful language understanding and generation capabilities, so the above demand information can be in the form of natural language, allowing users to express their needs in a more natural way, achieving more flexibility and better user experience.

[0195] If the user is not satisfied with the recommended content, the third interface element on the interactive interface can be used to refresh the displayed recommended content, and the user terminal sends a refresh instruction to the server terminal. In response to the refresh instruction sent by the user terminal, more than one recommended content is regenerated and sent to the user terminal.

[0196] Step 703: Generate a script based on the target recommended content selected by the user from one or more recommended contents, where the script includes control variable information for generating a media file.

[0197] In an embodiment of the present application, the script mainly includes control variable information for generating media files. The control variable information may include, but is not limited to, content-related variables, technology-related variables, effect-related variables, interaction-related variables, audio-related variables, and the like. Content-related variables may include, for example, scene information, story structure, material location, arrangement style, and the like. Technology-related variables may include, for example, frame rate, frame size, duration, and the like. Effect-related variables may include brightness, contrast, saturation, transition effects, special effects, and the like. Interaction-related variables may include, for example, variables that embody interaction effects, such as hot zone elements and icons. Audio-related variables may include, for example, background music, dubbing, and the like.

[0198] When the server generates a script using the target video instance, it can extract the script from the target video instance using a script generation model, for example. The script generation model can be implemented in a variety of ways, such as a deep learning model and a large model, and this application does not limit this.

[0199] In the embodiment of the present application, the server side may send the generated script to the client side for display, or may not send the script to the client side.

[0200] In addition, if the user inputs the demand information using the second interface element on the interactive interface, the user terminal sends the demand information to the server terminal. In response to the demand information, the server terminal may also generate a script using the demand information and send the script information to the user terminal.

[0201] In addition, the server side can also generate multiple scripts and send them to the client side, and the user selects a script from them, and the client side sends the selected script to the server side.

[0202] Step 705: Generate a media file using the script and the material information input by the user.

[0203] In this step, the server can use AIGC technology to generate a video file using scripts and material information. The generated video file can be one or more.

[0204] Step 707: Send the media file to the user terminal.

[0205] Furthermore, if the user selects a target media file from multiple media files, the user terminal sends the information of the target media file to the server terminal, and the server terminal can further associate the target video file with the user account and publish it, for example, to the homepage of the media service, to the user's homepage, to a page under a specific subject, and so on.

[0206] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0207] Embodiment 5

[0208] Figure 8This is a schematic block diagram of a media file generation device provided at a user end according to an embodiment of the present application. The device may be a functional unit such as a program, a plug-in, or an SDK (Software Development Kit) provided at the user end. Figure 8 As shown, the device 800 may include: an interface display unit 801 and a service-side interaction unit 802, wherein the main functions of each component unit are as follows:

[0209] The interface display unit 801 is configured to display one or more recommended contents on the interactive interface.

[0210] The service-side interaction unit 802 is configured to, in response to a user selecting a target recommended content from one or more recommended contents, send the target recommended content to the server side, so that the server side generates a script using the target recommended content, the script including control variable information for generating a media file; in response to a user inputting material information using an interactive interface, send the material information to the server side; and receive the media file sent by the server, the media file being generated using the script and the material information.

[0211] The interface display unit 801 is further configured to display media files on the interactive interface.

[0212] The above-mentioned recommended content may include: recommended media files, media templates, recommended script themes or recommended script templates.

[0213] As one possible implementation method, the above-mentioned recommended content is obtained based on user account information.

[0214] As another achievable method, the above-mentioned interactive interface may include a first interface element; when the interface display unit 801 displays more than one recommended content on the interactive interface, it may be specifically configured as follows: in response to the user inputting demand information using the first interface element, the demand information is sent to the server side, so that the server side obtains more than one recommended content using the demand information; and more than one recommended content is displayed on the interactive interface.

[0215] Furthermore, the above-mentioned interactive interface may also include a second interface element, and the service-side interactive unit 802 may be further configured to: in response to the user inputting demand information using the second interface element, send the demand information to the server side, so that the server side generates a script using the demand information.

[0216] As one of the more preferred implementations, the demand information may be in the form of natural language.

[0217] Furthermore, the above-mentioned interactive interface may also include a third interface element, and the interface display unit 801 may be further configured to: in response to the user triggering the third interface element, refresh one or more recommended contents displayed on the interactive interface. Specifically, in response to the user triggering the third interface element, the interface display unit 801 may trigger the service-side interactive unit 802 to send a refresh request to the server. After the service-side interactive unit 802 receives one or more recommended contents again, it provides one or more recommended contents to the interface display unit 801 for refreshing display.

[0218] Furthermore, the service-side interaction unit 802 is further configured to: obtain a script. Correspondingly, the interface display unit 801 is further configured to: display the script using the fourth interface element of the interaction interface.

[0219] As one of the possible implementations, there are multiple scripts; the interface display unit 801 is further configured to: display multiple scripts using the fifth interface element of the interactive interface; in response to the user selecting a script from the multiple scripts, display the selected script using the fourth interface element. Then, the service-side interaction unit 802 sends the selected script and material information to the server.

[0220] As a more preferred implementation method, the fourth interface element may be a text editing box, and the fifth interface element may be a card component.

[0221] Furthermore, the service-side interaction unit 802 may also be configured to: in response to the user editing the script using the fourth interface element; send the edited script to the server.

[0222] As one of the achievable methods, when the service-side interaction unit 802 sends material information to the server in response to the user inputting material information on the interaction interface, it can be specifically configured as follows: in response to the sixth interface element on the interaction interface being triggered, the material information input by the user is obtained; in response to the seventh interface element on the interaction interface being triggered, the material information is sent to the server.

[0223] As a preferred implementation, there are multiple media files, and the interface display unit 801 displays the multiple media files on the interactive interface.

[0224] Embodiment 6

[0225] Fig. 9 This is a schematic block diagram of a media file generation device provided on a server side according to an embodiment of the present application. The device may be a program, a plug-in, or a functional unit such as a SDK (Software Development Kit) provided on the server side. Fig. 9As shown, the device 900 may include: a user-side interaction unit 901, a script generation unit 902, and a media generation unit 903, and may further include a recommended content generation unit 904. The main functions of each component unit are as follows:

[0226] The user-side interaction unit 901 is configured to send one or more recommended contents to the user terminal.

[0227] The script generating unit 902 is configured to generate a script according to a target recommended content selected by a user from one or more recommended contents, wherein the script includes control variable information for generating a media file.

[0228] The user-side interaction unit 901 is further configured to obtain material information input by the user from the user terminal.

[0229] The media generation unit 903 is configured to generate a media file using a script and material information input by a user.

[0230] The user-side interaction unit 901 is further configured to send a media file to the user terminal.

[0231] As one possible implementation, the recommended content generation unit 904 can be obtained based on the user account information. The server determines the recommended content based on the user account information, that is, more than one recommended content can be displayed to the user without user operation.

[0232] As another achievable manner, the recommended content generating unit 904 may obtain one or more recommended contents according to the demand information input by the user.

[0233] As one of the implementable ways, when the recommended content generating unit 904 obtains the recommended content by using the user account information or the demand information, it can be implemented by using a large language model.

[0234] Furthermore, in response to the user-side interaction unit 901 receiving a refresh instruction from the user terminal, the recommended content generation unit 904 regenerates one or more recommended contents and provides them to the user-side interaction unit 901 , which then sends them to the user terminal.

[0235] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0236] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0237] And an electronic device, comprising:

[0238] one or more processors; and

[0239] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0240] The present application also provides a computer program product, including a computer program, which implements the steps of any one of the methods in the aforementioned method embodiments when executed by a processor.

[0241] in, Fig.10 The electronic device architecture is shown as an example, which may include a processor 1010, a video display adapter 1011, a disk drive 1012, an input / output interface 1013, a network interface 1014, and a memory 1020. The processor 1010, the video display adapter 1011, the disk drive 1012, the input / output interface 1013, the network interface 1014, and the memory 1020 may be communicatively connected via a communication bus 1030.

[0242] Among them, the processor 1010 can be implemented by a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., to execute relevant programs to implement the technical solutions provided in this application.

[0243] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store an operating system 1021 for controlling the operation of the electronic device 1000, and a basic input and output system (BIOS) 1022 for controlling the low-level operation of the electronic device 1000. In addition, a web browser 1023, a data storage management system 1024, and a media file generation device 1025, etc. can also be stored. The above-mentioned media file generation device 1025 can be an application program that specifically implements the aforementioned steps in the embodiment of the present application. In short, when the technical solution provided by the present application is implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0244] The input / output interface 1013 is used to connect the input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0245] The network interface 1014 is used to connect to a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WIFI, Bluetooth, etc.).

[0246] The bus 1030 comprises a pathway for transmitting information between the various components of the device (eg, the processor 1010 , the video display adapter 1011 , the disk drive 1012 , the input / output interface 1013 , the network interface 1014 , and the memory 1020 ).

[0247] It should be noted that, although the above device only shows a processor 1010, a video display adapter 1011, a disk drive 1012, an input / output interface 1013, a network interface 1014, a memory 1020, a bus 1030, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.

[0248] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a computer program product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0249] The technical solution provided by the present application is described in detail above. The principle and implementation method of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for generating a media file, applied to a user terminal, characterized in that: The method comprises: Display one or more recommended content and third interface elements on the interactive interface; In response to the user triggering the third interface element, refreshing one or more recommended contents displayed on the interactive interface; In response to a user selecting a target recommended content from the one or more recommended contents, sending the target recommended content to a server, so that the server generates a script using the target recommended content, the script including control variable information for generating a media file; Acquire the scripts, where there are multiple scripts, and display the multiple scripts using the fifth interface element of the interactive interface; in response to a user selecting a script from the multiple scripts, display the selected script using the fourth interface element of the interactive interface; In response to the user editing the script using the fourth interface element, sending the edited script to the server; In response to the user inputting material information using the interactive interface, sending the material information to the server; In response to receiving a media file sent by the server, the media file is generated by using the script and the material information, and displaying the media file on the interactive interface.

2. The method according to claim 1, characterized in that The recommended content includes: recommended media files, media templates, recommended script themes or recommended script templates.

3. The method according to claim 1, characterized in that The recommended content is obtained based on user account information.

4. The method according to claim 1, characterized in that: The interactive interface includes a first interface element; The displaying of more than one recommended content on the interactive interface includes: In response to the user inputting demand information using the first interface element, sending the demand information to the server, so that the server obtains one or more recommended contents using the demand information; The one or more recommended contents are displayed on the interactive interface.

5. The method according to claim 1, characterized in that The interactive interface further includes a second interface element, and the method further includes: In response to the user inputting requirement information using the second interface element, the requirement information is sent to the server, so that the server generates a script using the requirement information.

6. The method according to claim 4 or 5, characterized in that: The demand information is in natural language form.

7. The method according to claim 1, characterized in that The fourth interface element is a text editing box, and the fifth interface element is a card component.

8. The method according to any one of claims 1 to 5, characterized in that In response to the user inputting material information using the interactive interface, sending the material information to the server includes: In response to a sixth interface element on the interactive interface being triggered, acquiring material information input by a user; In response to the seventh interface element on the interactive interface being triggered, the material information is sent to the server.

9. The method according to any one of claims 1 to 5, characterized in that There are multiple media files, and displaying the media files on the interactive interface includes: A plurality of the media files are displayed on the interactive interface.

10. The method according to claim 9, characterized in that The method further comprises: In response to the user selecting a target media file from the plurality of media files, the selected target media file is played, or the selected target media file is stored, or information of the selected target media file is sent to the server.

11. A method for generating a media file, applied to a server, characterized in that: The method comprises: Sending one or more recommended contents to a user terminal, so that the user terminal displays one or more recommended contents and a third interface element on an interactive interface; In response to a refresh instruction sent by a user terminal, regenerate the one or more recommended contents and send them to the user terminal, wherein the refresh instruction is sent by the user terminal in response to a user triggering the third interface element; Generate a script according to the target recommended content selected by the user from the one or more recommended contents, wherein the script includes control variable information for generating a media file, and the script is multiple, so that the user terminal can display the multiple scripts using a fifth interface element of the interactive interface; Receiving an edited script sent by the user terminal, wherein the edited script is sent by the user terminal in response to a user editing a script displayed by a fourth interface element on the interactive interface, wherein the fourth interface element displays a script selected by the user from the plurality of scripts; Generate a media file using the script and the material information input by the user; The media file is sent to the client.

12. A device for generating a media file, arranged at a user end, characterized in that: The device comprises: an interface display unit, configured to display one or more recommended contents and a third interface element on the interactive interface, and to refresh the one or more recommended contents displayed on the interactive interface in response to a user triggering the third interface element; The service-side interaction unit is configured to, in response to a user selecting a target recommended content from the one or more recommended contents, send the target recommended content to a server side, so that the server side generates a script using the target recommended content, the script including control variable information for generating a media file; and obtain the script, wherein the script is multiple; The interface display unit is further configured to display the multiple scripts using a fifth interface element of the interactive interface; in response to a user selecting a script from the multiple scripts, display the selected script using a fourth interface element of the interactive interface; The service-side interaction unit is further configured to, in response to the user editing the script using the fourth interface element, send the edited script to the server; in response to the user inputting material information using the interaction interface, send the material information to the server; receive a media file sent by the server, the media file being generated using the script and the material information; The interface display unit is further configured to display the media file on the interactive interface.

13. A device for generating a media file, arranged on a server side, characterized in that: The device comprises: The user-side interaction unit is configured to send one or more recommended contents to the user terminal, so that the user terminal displays one or more recommended contents and a third interface element on the interaction interface; in response to a refresh instruction sent by the user terminal, regenerate the one or more recommended contents and send them to the user terminal, wherein the refresh instruction is sent by the user terminal in response to the user triggering the third interface element; a script generating unit configured to generate a script according to a target recommended content selected by a user from the one or more recommended contents, wherein the script includes control variable information for generating a media file, and the script is multiple, so that the user terminal can display the multiple scripts using a fifth interface element of the interactive interface; The user-side interaction unit is further configured to receive an edited script sent by the user terminal, wherein the edited script is sent by the user terminal in response to the user editing a script displayed by a fourth interface element on the interaction interface, wherein the fourth interface element displays a script selected by the user from the plurality of scripts; and obtain material information input by the user from the user terminal; A media generation unit, configured to generate a media file using the script and material information input by a user; The user-side interaction unit is further configured to send the media file to the user terminal.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

15. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the steps of the method according to any one of claims 1 to 11 are executed.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images