Media content generation method and device, storage medium, and program product

Abstract

Embodiments of the present disclosure provide a media content generation method and device, a storage medium, and a program product. The method comprises: displaying dialogue content in a dialogue window of a first interface, the dialogue content being used for indicating a creation intention of a user for media content; generating target media content on the basis of the dialogue content; and presenting a trigger control for the target media content in the dialogue window, the trigger control being at least used for triggering presentation of the target media content. According to the media content generation method provided in the embodiments of the present disclosure, information interaction between a user and a system is implemented by means of a dialogue, and then target media content conforming to the creation intention of the user is generated on the basis of the obtained dialogue content, thereby reducing the learning cost of users, making the operation simple, and improving the intelligent level of media content generation.

Description

Media content generation method, device, storage medium and program product

[0001] This application claims priority to Chinese Patent Application No. 202311022568.9 filed on August 14, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] The embodiments of the present disclosure relate to a method, device, storage medium, and program product for generating media content. Background Art

[0003] In existing media content software, function controls are provided at fixed locations on the creation page. Users need to be familiar with the locations of these function controls and master their operation methods during the creation process. The operation is complicated, the learning cost is high, and the intelligence level is low, which is not conducive to user operation.

[0004] Summary of the Invention

[0005] The embodiments of the present disclosure provide a media content generation method, device, storage medium, and program product to simplify operations and improve the intelligence level during the media content creation process.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for generating media content, including:

[0007] Displaying the conversation content in the conversation window of the first interface; the conversation content is used to indicate the user's creative intention for the media content;

[0008] generating target media content according to the conversation content;

[0009] A trigger control for presenting the target media content in the dialog window, wherein the trigger control is at least used to trigger presentation of the target media content.

[0010] In a second aspect, an embodiment of the present disclosure provides a media content generation device, including:

[0011] A display module, configured to display the conversation content in the conversation window of the first interface; the conversation content is used to indicate the user's creative intention for the media content;

[0012] A generating module, configured to generate target media content according to the conversation content;

[0013] The display module is further configured to present a trigger control for the target media content in the dialog window, wherein the trigger control is at least configured to trigger presentation of the target media content.

[0014] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0015] The memory stores computer-executable instructions;

[0016] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the media content generation method as described in the first aspect and various possible designs of the first aspect.

[0017] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the media content generation method described in the first aspect and various possible designs of the first aspect is implemented.

[0018] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the media content generation method described in the first aspect and various possible designs of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] FIG1 is a flow chart of a method for generating media content according to an embodiment of the present disclosure;

[0021] 2a and 2b are schematic diagrams of the interface of the conversation content of the smart video editing function provided by an embodiment of the present disclosure;

[0022] 3a to 3d are schematic diagrams of the interface of the conversation content of the text-to-film function provided by an embodiment of the present disclosure;

[0023] 4a to 4d are schematic diagrams of interfaces for a conversation content of a function for generating a picture provided by an embodiment of the present disclosure;

[0024] FIG5 is a schematic diagram of an interface of an entry control of a first interface provided by an embodiment of the present disclosure;

[0025] FIG6 is a structural block diagram of a media content generating device provided by an embodiment of the present disclosure; and

[0026] FIG7 is a schematic diagram of the hardware structure of a media content generating device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0028] In response to the aforementioned issues of high operational difficulty and low intelligence in existing media content generation methods, the inventors of the present disclosure have discovered that a human-computer dialogue approach can be used to determine the user's creative intent and, in turn, generate target media content that meets the user's creative intent. Based on this, the present disclosure provides a media content generation method.

[0029] The media content generation method provided by the present disclosure can be implemented by an electronic device, or an application (APP) in the electronic device, a web page, etc. The electronic device may include a mobile phone, a tablet computer, a wearable electronic device, an in-vehicle device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), an electronic device including smart home devices such as a smart TV, a smart screen, a high-definition TV, a 4K TV, a smart speaker, a smart projector, etc. The embodiment of the present disclosure does not impose any restrictions on the specific type of the electronic device. The embodiment of the present disclosure does not limit the type of operating system of the electronic device, for example, Android system, Linux system, Windows system, iOS system, etc.

[0030] 1, which is a flow chart of a method for generating media content according to an embodiment of the present disclosure. The method comprises:

[0031] 101. Displaying conversation content in a conversation window of a first interface; the conversation content is used to indicate the user's creative intention for media content.

[0032] Specifically, the conversation content may include user conversation information from the user and system conversation information from the system. Conversation information may include text, numbers, symbols, links, emoticons, images, audio, video clips, and other data types, without limitation. Display parameters such as the size, color, display position, and transparency of the conversation window are also not limited.

[0033] There are many ways to input user dialogue information.

[0034] In one implementation, to facilitate guidance for users with less creative experience, an operation control can be displayed within the first interface, allowing the user to express their creative intent by triggering the operation control. Specifically, the conversation content can include first user conversation information, and the method can further include: displaying a target function control within the first interface; and generating the first user conversation information corresponding to the target function control in response to a touch operation on the target function control.

[0035] The target function control can be a control set for the content type of the media content, such as generating an image, generating graphic text, or generating a video. It can also be a control for importing materials, inputting text requirements, inputting video requirements, etc., which is used to guide the user to input reference information for generating the target media content. This embodiment of the present disclosure is not limited to this. The target function control can be displayed in the form of icons, text, symbols, pictures, etc., or it can also be displayed in a combination of multiple forms.

[0036] In another possible implementation, to increase user flexibility in inputting user conversation information, an input area can be provided in the first interface, allowing the user to enter user conversation information within the input area. Specifically, the conversation content can include second user conversation information, the first interface can include a conversation input area, and the method can further include: obtaining the second user conversation information in response to an input operation performed on the conversation input area. The presently disclosed embodiment does not limit display parameters such as the input area size, color, display position, and display transparency.

[0037] In another possible implementation, to expand the user's creative ideas, creative suggestion information can be presented in the conversation window of the first interface, allowing the user to enter user conversation information based on the creative suggestion information. The creative suggestion information can be information such as popular creative styles and themes obtained through big data analysis.

[0038] It should be noted that the above-mentioned various user dialogue information input methods can be implemented separately or in any combination, and the embodiments of the present disclosure do not limit this.

[0039] The conversation information from different objects in the conversation content can be set on the same side or on different sides. For example, the user conversation information from the user can be set on the right side of the conversation window, aligned on the right side, and the system conversation information from the system can be set on the left side of the conversation window, aligned on the left side. The conversation information of both parties can also be aligned on the left side or right side. This is not limited in the embodiments of the present disclosure.

[0040] 102. Generate target media content according to the conversation content.

[0041] Specifically, after obtaining the conversation content, the creative intent of the conversation content can be identified and processed, and target media content can be generated based on this creative intent. This identification process can include natural language processing of the conversation content to obtain multiple tags representing the creative intent. Based on these multiple tags, the source material and editing method are determined to obtain the target media content. The target media content can be video, graphic, image, or other data types.

[0042] For example, the user can enter the user dialogue message "Help me create a happy birthday themed video", and the system can find a video draft template related to happy birthday for the user based on the dialogue message (including editing information, that is, editing operations on the imported material). The user can import his own video material into the video draft template to complete the creation of the target video.

[0043] 103. Present a trigger control for the target media content in the dialog window, where the trigger control is at least used to trigger presentation of the target media content.

[0044] Specifically, after generating the target media content, a trigger control can be set to facilitate viewing the editing effect of the target media content, so that the user can trigger the trigger control to play or enlarge the target media content. If the user is satisfied with the editing effect of the target media content, the target media content can be exported, shared, etc. If the user is not satisfied with the editing effect of the target media content, the user can enter dialogue information in the dialogue window to regenerate the media content or continue to improve the target media content.

[0045] In some embodiments, to facilitate editing of the target media content if the user is dissatisfied with the editing effect of the target media content, an editing control may be provided on the first interface so that after the user triggers the editing control, the user enters the editing interface. For example, in one implementation, the editing interface may be provided with multiple editing function controls so that after the user triggers a relevant editing function control, a corresponding editing operation is performed on the target media content. In another implementation, the editing interface may include an editing dialogue window. By obtaining the dialogue content in the editing dialogue window, the user's editing intent is determined, and then the target media content is edited based on the editing intent to obtain new target media content.

[0046] From the above description, it can be seen that the media content generation method provided by the present disclosure realizes information interaction between the user and the system by adopting a dialogue method, and then generates target media content that meets the user's creative intention based on the acquired dialogue content, thereby reducing the user's learning cost, simplifying the operation, and improving the intelligence level of media content generation.

[0047] In one embodiment of the present disclosure, based on the embodiment of FIG. 1 , the target media content may be a video draft; the video draft includes video material and editing information; the editing information is used to indicate the editing operation performed on the video material.

[0048] There are several ways to generate a draft of your video.

[0049] In one implementation, the video draft may be a "pure image video draft" that includes only image and video materials but no text. Generating this type of video draft and generating target media content based on the conversation content may include: obtaining first requirement information input by the user based on the conversation content; the first requirement information is used to indicate the content requirements of the media content; determining multiple candidate video drafts based on the first requirement information; the candidate video drafts include a video draft template and target materials; the video draft template includes editing operations performed on the target materials; and selecting a video draft from the multiple candidate video drafts.

[0050] Specifically, the first requirement information may be data of types such as text, video, picture, audio, etc. The first requirement information may include requirements for the style, theme, time, location, event, etc. of the media content.

[0051] Exemplarily, the first requirement information may include only the required expression information (such as the requirement that the text be presented in the form of text, audio or video), or may include only the video material imported by the user, or may include both the required expression information and the video material imported by the user. The embodiments of the present disclosure are not limited to this.

[0052] Correspondingly, if the first requirement information only includes the required expression information, such as a text requirement, multiple candidate video drafts can be determined based on the text requirement. The candidate video drafts include a video draft template and original materials (for example, selected from a material library) determined based on the text requirement. Different candidate video drafts may have different video draft templates or original materials, so that the user can select a target video draft from multiple candidate video drafts as the target media content.

[0053] If the first requirement information only includes video material, multiple video draft templates can be matched based on the video material, and then the video material can be imported into the multiple video draft templates to obtain multiple candidate video drafts, from which a video draft can be selected as the target media content.

[0054] If the first requirement information includes both a textual requirement and a user-input video material, multiple video draft templates can be obtained based on the textual requirement and the video material. The video material can then be imported into each of the multiple video draft templates to obtain multiple candidate video drafts. A video draft can then be selected from the multiple candidate video drafts as the target media content.

[0055] Furthermore, in order to facilitate obtaining the user's requirement information for the above-mentioned "pure image video draft", the dialogue content in the dialogue window may include a control provided by the system for inputting the first requirement information, so as to obtain the user's requirement information in response to the user triggering the control. Specifically, the first requirement information may include a first text requirement and / or a first video material selected by the user; the displaying of the dialogue content in the dialogue window of the first interface may include: displaying the first system dialogue information in the dialogue window of the first interface; the first system dialogue information presenting a material import control and / or a first input box; the material import control is used to obtain the first video material selected by the user, and the first input box is used to obtain the first text requirement entered by the user.

[0056] For example, the material import control and the first input box can be presented simultaneously in the dialog window, or in a certain order, such as presenting the first input box after the user completes the touch operation on the material import control. In addition, for ease of operation, a skip control can be provided in both the material import control and the first input box to facilitate user cancellation of the touch operation on the corresponding control. For example, the material import control includes a skip control, and upon receiving a touch operation on the skip control, the user can skip the material import control and receive a touch operation on another control, such as the input box, in response to the touch operation, without acquiring the input content corresponding to the material import control. The user can then receive a touch operation on another control, such as the input box, to acquire the content entered in the input box.

[0057] Furthermore, in the process of the user importing materials, in order to facilitate the user's operation, the dialogue content is displayed in the dialogue window of the first interface, and it can also include: if the first system dialogue information presents the material import control, in response to the material import control, a material selection interface is displayed in the dialogue window; in response to the user's selection instruction in the material selection interface, the first video material selected by the user is obtained.

[0058] Specifically, the material selection interface can be displayed on an upper layer of the first interface, or embedded in the first interface. This embodiment does not limit the display mode, size, and transparency setting of the material selection interface.

[0059] Furthermore, after the user selects and imports materials in the material interface, in order to make further choices on the imported materials, obtaining the first video material selected by the user can include: obtaining the second video material selected by the user; displaying the slot to be filled and the filled slot filled with the second video material in the dialog window; the slot to be filled is used to fill the video material that the user continues to select after being triggered, forming a new filled slot and displaying it; and obtaining the first video material selected by the user based on the video material filled in the filled slot.

[0060] Specifically, multiple slots to be filled can be set, or one slot can be set. When one slot to be filled is set, when the slot to be filled is filled with new material to form a filled slot, another slot to be filled will be displayed so that the user can continue to add materials.

[0061] Optionally, the filled slot includes a delete control, and the delete control is used to delete the corresponding filled slot after being triggered.

[0062] The following example illustrates the generation process of the “pure image video draft” with reference to FIG. 2 a and FIG. 2 b .

[0063] After the application is started, the user interface 21 shown in FIG. 2 a may be displayed on the mobile phone, wherein the user interface 21 is a conversation page (ie, a first interface), which is mainly used to present and obtain the conversation content between the user and the system.

[0064] As shown in FIG2 a , the user interface 21 includes a dialog window displaying functional controls such as smart video editing, text-to-film, and image generation. When the application receives a trigger operation (e.g., a click or long press) for the smart video editing control, the dialog window of the user interface 22 displays a user dialog message "Help me edit a video" in response to the trigger operation of the smart video editing control. Based on this user dialog message, the dialog window continues to display system dialog messages, including operation controls such as importing materials and filling in requirements, as well as corresponding operation prompts ("Please import your materials first, or fill in the requirements for making a video"). The import material control is used to jump to the material import page after being triggered to receive material selection instructions, and the fill in requirements control is used to display an input box after being triggered for entering the requirements for the target media content. Exemplarily, as shown in the user interface 22, the application receives a trigger operation (such as a click operation or a long press operation) for the import material operation control, and in response to the user's trigger operation on the import material operation control, jumps to the material import page. The user interface 23 is the material import page. The user interface 23 includes a first-level directory such as recent projects and material library. Under the recent project, second-level directories such as videos, photos, and live photos are displayed. After the video is selected, multiple video materials such as material 1 to material 12 are displayed. The user interface 23 also includes an add control. The add control is used to add the material selected by the user on the page after being triggered, that is, a confirmation control for the currently selected material. As shown in the user interface 23, the add control can include the text "add" and the number of added materials "2". After the user selects material 8 and material 9, in response to the user's trigger operation on the add control, it jumps to the dialogue interface, that is, the first interface.

[0065] 2b, the user interface 24 displays the user dialogue message "Import material" and the system dialogue message "Your material has been received", and displays multiple slots, wherein the filled slot 201 is filled with the selected material 8 and material 9, and the slot to be filled 202 is used to add new material after being triggered (for example, after the slot to be filled is triggered, the material import page shown in the user interface 23 in FIG2a can be displayed, and then new material can be added). The filled slot 201 can be provided with a delete control 2011, so that after receiving the trigger operation of the delete control 2011, the application deletes the corresponding material or the filled slot in response to the trigger operation. In addition, as shown in the user interface 24, the system dialogue information can also include an input box 203 for entering text requirements. The input box 203 displays a confirmation control and a skip control. The confirmation control is used to indicate confirmation of the input content after the text requirement is entered in the text input box, and the skip control is used to indicate skipping the input operation, not performing text input, and only performing subsequent steps for the received material. The user triggers the skip control, and in response to the trigger, the user dialogue information "Use the above content to generate a video" is displayed in the user interface 25, and the system dialogue message is displayed, including progress information and a cancel control. The cancel control is used to cancel the current generation after being triggered. After the progress is completed, the system dialogue message is displayed in the user interface 26. The system dialogue message includes multiple candidate video draft contents 1 to 4, so that the user can select the target media content from them. The system dialogue message also includes a change operation control and a continue to improve operation control. The change operation control is used to regenerate multiple candidate video drafts based on the previous dialogue content. The continue to improve operation control is used to continue to input the dialogue message, add dialogue content, and then generate multiple candidate video drafts based on the added dialogue content for the user to select.

[0066] It should be noted that the embodiments shown in Figures 2a and 2b are only examples of the media content generation method provided by the embodiments of the present disclosure. In actual scenarios, the display method, presentation form, related control setting method of the conversation content, and the layout, display parameters, and implementation methods of controls and entrances of some pages can be flexibly set according to needs.

[0067] In another possible implementation, the video draft may include text, for example, it may be a video draft generated based on the text. Accordingly, for a "graphic-text video draft" containing text, generating target media content based on the conversation content may include: determining the target text based on the conversation content; dividing the target text into multiple text sentences; for each text sentence, determining the video material and audio clip corresponding to the text sentence; the video material is obtained based on semantic matching of the text sentence; the audio clip is obtained by converting the text sentence based on text-to-speech technology; generating a video draft based on the video materials and audio clips corresponding to the multiple text sentences; and both the video material and the audio clip can be edited independently.

[0068] Specifically, in a video draft, the three parts of video material, audio clips, and text statements can be in a merged state, independent state, or in different combination states. For example, audio clips and text statements can be merged together.

[0069] There are many ways to obtain the target copy. The user can directly enter the target copy in the dialogue window in a dialogue manner, or the user can first enter the copy requirements of the target copy in the dialogue window in a dialogue manner, and then the system intelligently generates the target copy for the user based on the copy requirements.

[0070] Optionally, in order to help users obtain copywriting faster, an intelligent copywriting service can be provided to users, guiding users to input requirement information for the style, content, etc. of the copywriting, and then generating a target copywriting that meets the user's requirements based on the requirement information. Based on this, determining the target copywriting according to the content of the conversation can include: determining second requirement information according to the content of the conversation, and determining the target copywriting according to the second requirement information; the second requirement information is used to indicate the content requirements for the copywriting.

[0071] The second requirement information may include requirements for the style, purpose, structure, genre, etc. To facilitate expanding the user's thinking, some requirements may be provided to the user in the form of selection controls in the dialog window for the user to trigger and select.

[0072] Accordingly, to facilitate user input of the required information for the text, an input box can be displayed in the dialog window. Furthermore, to facilitate editing of the generated target text, an edit control and a switch control can be provided. Displaying the dialog content in the dialog window of the first interface may include: displaying second system dialog information in the dialog window of the first interface; presenting a second input box in the second system dialog information; presenting a first text generated according to the second required information in the second input box; responding to the edit control in the second input box, editing the first text to obtain a second text; or responding to the switch control in the second input box, switching the first text to obtain a third text.

[0073] The following is an example of the generation process of the "graphic and text video draft" with reference to FIG. 3a to FIG. 3d.

[0074] After the application is started, the user interface 31 shown in FIG3a may be displayed on the mobile phone, wherein the user interface 31 is a conversation page (ie, a first interface), which is mainly used to present and obtain the conversation content between the user and the system.

[0075] As shown in FIG3 a , user interface 31 includes a dialog window displaying control functions such as intelligent video editing, text-to-video editing, and image generation. The application receives a trigger operation (e.g., a click or long press) for the text-to-video editing control. In response to the trigger operation, the dialog window of user interface 32 displays the user dialog message "I want to create a text-to-video editing function." Based on this user dialog message, the dialog window continues to display system dialog messages, including control functions such as intelligent copywriting and custom copywriting, along with corresponding prompts. The system dialog message reads, "Please first determine the copy to be used in your video. I can intelligently generate it, or you can enter it yourself." The application receives a trigger operation (e.g., a click or long press) for the intelligent copywriting control. In response to the user triggering the intelligent copywriting control, user interface 33 displays the user dialog message "Intelligent copywriting" and continues to display system dialog messages. The system dialog message includes a text input box for entering the desired copy, and a copy type selection control (e.g., default, voiceover, marketing, etc.). The text input box is used to enter the copy requirement, and the copy type selection control is used to select the corresponding copy type upon being triggered.

[0076] As shown in Figure 3b, after the text input box is triggered, the keyboard control is called up to enable text information to be input through the keyboard control (for example, "write an article about film history"). As shown in the user interface 35, for the trigger operation of the copy generation control (such as a click operation or a long press operation), in response to the user's trigger operation on the copy generation operation control, the user interface 36 displays system dialogue information, which includes the material content used to generate the copy, and then continues to display the user dialogue information "Use the above content to generate an article", and continues to display the system dialogue information, which includes the progress information of the copy generation (for example, 48%), and a cancel control, which is used to cancel the generation of the copy.

[0077] As shown in Figure 3c, the user interface 37 continues to display system dialogue information, which includes a text input box, which displays the target copy generated based on the copy requirements, and also includes an edit control, a change control and a generate video control. The edit control is used to edit the target copy in the text input box after being triggered, the change control is used to re-generate a new target copy based on the copy requirements after being triggered, and the generate video control is used to generate target media content based on the target copy currently displayed in the text input box. When a trigger operation (such as a click operation or a long press operation) is received for the edit control, in response to the trigger operation of the edit control, the user interface 38, i.e., the text editing interface, is jumped to. The user interface 38 includes a target text to be edited, a keyboard control, and a completion control. The keyboard control is used to edit the target text after being triggered, and the completion control is used to close the current interface and jump to the dialogue interface after being triggered. When a trigger operation (such as a click operation or a long press operation) is received for the completion control, in response to the trigger operation of the completion control, the dialogue window of the user interface 39 continues to display the system dialogue information shown in interface 37, which will not be repeated here. When a trigger operation (such as a click operation or a long press operation) is received for the generate video control, in response to the trigger operation of the edit control, the dialogue window can continue to display the system dialogue information (not shown). The system dialogue information may include an intelligent matching material control and a self-import material control. The intelligent matching material control is used to match and obtain corresponding image materials from the material library based on the target text after being triggered. The self-import material control is used to jump to the material import page after being triggered to import the material selected by the user in this interface.

[0078] Referring to FIG3 d , upon receiving a trigger operation (e.g., a click or long press) for the smart matching material control, user interface 391 displays user dialog information "Smart Matching Material" in response to the trigger operation, and continues to display system dialog information, which includes a trigger control 301 for a "Graphic Type Video Draft" generated based on the target text and the smartly matched material. As shown in user interface 391 , the trigger control can be the cover video frame of the video draft. Upon receiving a trigger operation (e.g., a click or long press) for the cover video frame, the user interface jumps to a preview page, i.e., user interface 392, in response to the trigger operation on the cover video frame. User interface 392 includes an export control 302, an edit control 303, and a play control 304. The export control 302, when triggered, is used to generate a video clip based on the current video draft and export or share it. The edit control 303, when triggered, is used to jump to the edit page for editing the video draft. The play control 304, when triggered, is used to render and display the edited frame image in the video draft.

[0079] In the case where the target media content is a video draft, after the video draft is generated, there are multiple ways to present the video draft. In one embodiment of the present disclosure, in order to facilitate the user's further operations on the video draft (such as preview, edit, export, etc.), a trigger control for presenting the video draft can be set in the form of a video cover, and then the preview interface is transposed after being triggered to perform operations such as preview, editing or export. Specifically, presenting the trigger control of the target media content in the dialogue window may include: obtaining a preview frame image at a target timeline point in the video draft, and determining the preview frame image as a video cover; presenting the video cover in the dialogue window; the video cover is used to display the editing effect of the video draft when triggered.

[0080] Specifically, the preview frame image selected as the video cover can be the preview frame image corresponding to the first point in the timeline of the video draft, or it can be a preview frame image in the video draft that best reflects the theme of the video draft. This disclosed embodiment does not limit this.

[0081] Optionally, after presenting the trigger control of the target media content in the dialogue window, it may also include: responding to a touch operation on the trigger control, jumping to the preview playback interface, rendering the editing effect frame images of the video draft in sequence and displaying them on the preview playback interface.

[0082] For example, in order to save memory, the screen played in the preview playback interface can be obtained by real-time rendering, rather than synthesizing the video draft into video clips and then playing the video clips.

[0083] Optionally, the trigger control includes an export control; after presenting the trigger control of the target media content in the dialog window, it may also include: generating a target video according to the video draft in response to a touch operation acting on the export control.

[0084] For example, reference may be made to the embodiments of user interface 391 and user interface 392 shown in FIG3 d , which will not be described in detail here.

[0085] It should be noted that the embodiments shown in Figures 3a to 3d are only examples of the media content generation method provided by the embodiments of the present disclosure. In actual scenarios, the display method, presentation form, related control setting method of the conversation content, as well as the layout, display parameters, and implementation methods of controls and entrances of some pages can be flexibly set according to needs.

[0086] In one embodiment of the present disclosure, based on the embodiment of FIG. 1 above, the target media content may be an image, and user-provided requirement information for generating the image (such as textual requirements, reference images, and requirements for presentation in video or audio format) may be determined based on the conversation content. Specifically, generating the target media content based on the conversation content may include: determining third requirement information based on the conversation content; the third requirement information including a second textual requirement and / or a reference image; the second textual requirement being used to indicate content requirements for the media content; determining a target image based on the third requirement information, and determining the target image as the target media content.

[0087] The following is an example of the target image generation process with reference to FIG4a to FIG4d.

[0088] After the application is started, the user interface 41 shown in FIG. 4 a may be displayed on the mobile phone, wherein the user interface 41 is a conversation page (ie, a first interface), which is mainly used to present and obtain the conversation content between the user and the system.

[0089] As shown in Figure 4a, the user interface 41 includes a dialogue window, which displays functional controls such as smart video editing, text-to-film, and image generation. The application receives a trigger operation for the image generation control (such as a click operation or a long press operation). In response to the trigger operation for the image generation control, the dialogue window of the user interface 42 displays the user dialogue information "I want to generate an image". Based on the user dialogue information, the system dialogue information continues to be displayed in the dialogue window. The system dialogue information includes an input box, an add control 401, operation controls such as image generation, and corresponding operation prompt information "Please describe your creativity in detail". The application receives a trigger operation for the input box (such as clicking on a blank area of ​​the input box to determine the cursor position). In response to the user's trigger operation on the input box, as shown in the user interface 43, the keyboard control is called up to enter the requirement information for the image (the second text requirement).

[0090] As shown in Figure 4b, the application receives a trigger operation for the keyboard control, and in response to the trigger operation for the keyboard control, displays the input text information in the input box shown in the user interface 44 (for example, "an orange cat is lying on the sofa and stretching, and a little girl is sitting next to it eating jelly"). The application receives a trigger operation for the generate picture control (for example, a click operation or a long press operation). In response to the trigger operation for the generate picture control, the user interface 45 displays the user dialogue information "Use the above content to generate the picture", and continues to display the system dialogue information. The system dialogue information includes the progress information of the picture generation (for example, please wait patiently, the picture is being generated 48%) and the cancel control, which is used to terminate the current picture generation action. After the picture generation progress reaches 100%, a plurality of candidate pictures and a change control are displayed in the dialogue window of the user interface 46. The change control is used to regenerate the target picture based on the current requirement information after being triggered.

[0091] As shown in Figure 4c, the application receives a trigger operation (such as a click operation or a long press operation) for generating a picture control 401 in the user interface 47, and in response to the trigger operation for generating the picture control, jumps to the material import page. The user interface 48 is the material import page. The user interface 48 includes first-level directories such as recent projects and material libraries. Under the recent projects, second-level directories such as videos, photos, and live photos are displayed. After the picture is selected, multiple picture materials such as material 21 to material 32 are displayed. The user interface 48 also includes an add control (used to confirm the selected picture material after being triggered). After the user selects material 8 and material 9, in response to the user's trigger operation on the add control, it jumps to the dialogue interface, that is, the first interface. The user interface 49 displays system dialog information, which includes filled slots (filled with the material 28 added on the material import page). Of course, slots to be filled (not shown) can also be set for adding new materials after being triggered (for example, after the slots to be filled are triggered, the material import page shown in the user interface 48 can be displayed, and new materials can be added). The filled slots can be set with a delete control 402 so that the application deletes the corresponding material in response to the trigger operation of the delete control 402 after receiving the trigger operation. The application receives the user's trigger operation for the generate image control.

[0092] As shown in Figure 4d, in response to a trigger operation on the Generate Image control, a user dialog message "Use the above content to generate an image" is displayed in user interface 491. A system dialog message is also displayed, including progress information and a cancel control. The cancel control is used to cancel the current generation after being triggered. After the progress is 100% completed, a system dialog message is displayed in user interface 492. The system dialog message includes trigger controls for multiple candidate images, images 5 and 6, so that the user can select target media content from them. The system dialog message also includes a switch operation control. The switch operation control is used to regenerate multiple candidate videos based on the requirement information related to the previous dialog content. The application receives a trigger operation (e.g., a click operation or a long press operation) for image 6 in user interface 492. In response to the trigger operation on image 6, it jumps to the image preview page, i.e., user interface 493. In user interface 493, image 6 is displayed in an enlarged state. User interface 493 also includes a save control. The save control is used to save image 6 after being triggered.

[0093] It should be noted that the embodiments shown in Figures 4a to 4d are only examples of the media content generation method provided by the embodiments of the present disclosure. In actual scenarios, the display method, presentation form, related control setting method of the conversation content, as well as the layout of some pages, display parameters, and the implementation method of controls and entrances can be flexibly set according to needs.

[0094] In one embodiment of the present disclosure, in order to facilitate users in need to quickly find the entry control of the first interface, considering that users who search for materials, templates, and other content through the search box are likely to be users who have a demand for the content generation method provided by this solution, the entry control of the first interface can be set in a search-related position. Specifically, before displaying the dialogue content in the dialogue window of the first interface, it can also include: displaying the first interface in response to the first entry control in the second interface; the second interface presents a search box; the first entry control is located in the surrounding area of ​​the search box; the search box is used to input search information to search for media content templates that match the search information; the search information is used to indicate the user's creative intention for media content.

[0095] Furthermore, an entry control for the first interface can be set on the search results page to facilitate users to promptly discover and attempt to enter the first interface for intelligent creation. Specifically, before displaying the conversation content in the conversation window of the first interface, the following steps may be performed: displaying the first interface in response to a second entry control in the search results interface; the search results interface is triggered to display in response to a search operation in the search box; the search results interface presents a search results display area; and the second entry control is set in an area surrounding the search results display area.

[0096] For example, the setting position of the entry control of the first interface is illustrated below with reference to FIG5 .

[0097] After the application is started, the user interface 51 shown in Figure 5 can be displayed on the mobile phone, where the user interface 51 is the main page of the application (i.e., the second interface). The main page includes a search box 501, an entry control 502 of the first interface, and a display area 503. The display area 503 is mainly used to present various function controls (for example: editing, local drafts, shooting, screen recording, creative classes, messages, personal settings, etc.), various subject columns (such as industry templates, life challenges, rankings, etc.), and the entry control 502 is set on the right side of the search box 501. The entry control 502 is used to enter the first interface after being triggered.

[0098] The application receives a trigger operation (such as a click operation or a long press operation) for the search box 501. In response to the trigger operation on the search box, the keyboard control is called up in the user interface 52. The application receives a trigger operation (such as a click operation or a long press operation) for the keyboard control. In response to the trigger operation on the keyboard control, the search content "birthday record" entered is displayed in the search box 501. The application receives a trigger operation (such as a click operation or a long press operation) for the search control in the search box 501. In response to the trigger operation on the search control, it jumps to the search results page, that is, the user interface 53. The user interface 53 includes a search box 506, an entry control 504, and a search result display area 505. The entry control 504 is used to enter the first interface after being triggered.

[0099] In one embodiment of the present disclosure, in order to convey value to users and improve click-through rate, a guide bubble can be set near the entry control 502 when entering the user interface 51 as shown in Figure 5, and the guide bubble copy can be "Artificial intelligence makes video creation easier."

[0100] It should be noted that the embodiment shown in FIG5 is only an example of the information reply method provided in the present disclosure. In actual scenarios, the layout of some pages, display parameters, and implementation methods of controls and entrances can be flexibly set according to needs.

[0101] Corresponding to the media content generation method described in the above embodiment, FIG6 is a block diagram of a media content generation device provided by an embodiment of the present disclosure. For ease of illustration, only the portions relevant to the embodiment of the present disclosure are shown. Referring to FIG6 , the device includes: a display module 601 and a generation module 602.

[0102] The display module 601 is used to display the conversation content in the conversation window of the first interface; the conversation content is used to indicate the user's creative intention for the media content;

[0103] A generating module 602, configured to generate target media content according to the conversation content;

[0104] The display module 601 is further configured to present a trigger control for the target media content in the dialog window, where the trigger control is at least configured to trigger presentation of the target media content.

[0105] In one embodiment of the present disclosure, the display module 601 is further configured to: display a target function control in the first interface; and generate the first user dialogue information corresponding to the target function control in response to a touch operation on the target function control.

[0106] In one embodiment of the present disclosure, the display module 601 is further configured to: obtain the second user dialogue information in response to an input operation applied to the dialogue input area.

[0107] In one embodiment of the present disclosure, the target media content is a video draft; the video draft includes a video material and editing information; the editing information is used to indicate an editing operation performed on the video material.

[0108] In one embodiment of the present disclosure, the display module 601 is specifically used to: obtain a preview frame image at a target timeline point in the video draft, and determine the preview frame image as a video cover; present the video cover in the conversation window; and the video cover is used to display the editing effect of the video draft when triggered.

[0109] In one embodiment of the present disclosure, the display module 601 is also used to: respond to a touch operation on the trigger control, jump to the preview playback interface, render the editing effect frame images of the video draft in sequence and display them on the preview playback interface.

[0110] In one embodiment of the present disclosure, the trigger control includes an export control; the display module 601 is further used to: respond to a touch operation acting on the export control, and generate a target video according to the video draft.

[0111] In one embodiment of the present disclosure, the generation module 602 is specifically used to: obtain first requirement information input by the user based on the conversation content; the first requirement information is used to indicate the content requirements of the media content; determine multiple candidate video drafts based on the first requirement information; the candidate video drafts include a video draft template and a target material; the video draft template includes editing operations on the target material; and select a video draft from the multiple candidate video drafts.

[0112] In one embodiment of the present disclosure, the first requirement information includes a first text requirement and / or a first video material selected by the user; the display module 601 is specifically used to: display the first system dialogue information in the dialogue window of the first interface; the first system dialogue information presents a material import control and / or a first input box; the material import control is used to obtain the first video material selected by the user, and the first input box is used to obtain the first text requirement entered by the user.

[0113] In one embodiment of the present disclosure, the display module 601 is also used for: if the first system dialogue information presents the material import control, in response to the material import control, displaying the material selection interface in the dialogue window; in response to the user's selection instruction on the material selection interface, obtaining the first video material selected by the user.

[0114] In one embodiment of the present disclosure, the display module 601 is specifically used to: obtain the second video material selected by the user; display the slot to be filled and the filled slot filled with the second video material in the dialog window; the slot to be filled is used to fill the video material that the user continues to select after being triggered, forming a new filled slot and displaying it; and obtain the first video material selected by the user based on the video material filled in the filled slot.

[0115] In one embodiment of the present disclosure, the filled slot includes a delete control, and the delete control is used to delete the corresponding filled slot after being triggered.

[0116] In one embodiment of the present disclosure, the generation module 602 is specifically used to: determine the target copy based on the conversation content; divide the target copy into multiple copy sentences; for each copy sentence, determine the video material and audio clip corresponding to the copy sentence; the video material is obtained based on the semantic matching of the copy sentence; the audio clip is obtained by converting the copy sentence based on text-to-speech technology; generate a video draft based on the video materials and audio clips corresponding to the multiple copy sentences; both the video material and the audio clip can be edited independently.

[0117] In one embodiment of the present disclosure, the generation module 602 is specifically configured to: determine second requirement information according to the conversation content, and determine a target text according to the second requirement information; the second requirement information is used to indicate content requirements for the text.

[0118] In one embodiment of the present disclosure, the display module 601 is specifically used to: display the second system dialogue information in the dialogue window of the first interface; the second system dialogue information is presented with a second input box; the second input box presents a first text generated according to the second requirement information; in response to the editing control acting on the second input box, the first text is edited to obtain the second text; or, in response to the switching control acting on the second input box, the first text is switched to obtain the third text.

[0119] In one embodiment of the present disclosure, the generation module 602 is specifically used to: determine third requirement information based on the conversation content; the third requirement information includes a second text requirement and / or a reference picture; the second text requirement is used to indicate the content requirement for the media content; determine the target picture based on the third requirement information, and determine the target picture as the target media content.

[0120] In one embodiment of the present disclosure, the display module 601 is also used to: display the first interface in response to a first entry control acting on the second interface; the second interface presents a search box; the first entry control is located in the surrounding area of ​​the search box; the search box is used to input search information to search for a media content template that matches the search information; the search information is used to indicate the user's intention to create media content.

[0121] In one embodiment of the present disclosure, the display module 601 is also used to: display the first interface in response to a second entry control acting on the search results interface; the search results interface is triggered to display in response to a search operation acting on the search box; the search results interface presents a search results display area; the second entry control is set in the surrounding area of ​​the search results display area.

[0122] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0123] In order to implement the above embodiment, the embodiment of the present disclosure further provides an electronic device.

[0124] 7 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing an embodiment of the present disclosure. The electronic device 900 may be a terminal device or a server. The terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable media players (PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in FIG7 is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0125] As shown in FIG7 , the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the electronic device 900 are also stored in the RAM 903. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0126] Typically, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although FIG. 7 shows an electronic device 900 having various devices, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0127] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0128] It should be noted that the computer-readable medium described above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0129] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0130] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0131] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0134] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0135] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer 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 foregoing.

[0136] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0137] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0138] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for generating media content, comprising: Displaying the conversation content in the conversation window of the first interface; The conversation content is used to indicate the user's intention to create media content; generating target media content according to the conversation content; A trigger control for presenting the target media content in the dialog window, wherein the trigger control is at least used to trigger presentation of the target media content.

2. The method according to claim 1, wherein: The conversation content includes first user conversation information, and the method further includes: Displaying a target function control in the first interface; In response to the touch operation acting on the target function control, the first user dialogue information corresponding to the target function control is generated.

3. The method according to claim 1 or 2, wherein: The conversation content includes second user conversation information, the first interface includes a conversation input area, and the method further includes: In response to an input operation applied to the dialogue input area, second user dialogue information is acquired.

4. The method according to any one of claims 1 to 3, wherein: The target media content is a video draft; the video draft includes a video material and editing information; the editing information is used to indicate an editing operation performed on the video material.

5. The method according to claim 4, wherein: The trigger control for presenting the target media content in the dialog window includes: Obtain a preview frame image at a target timeline point in the video draft, and determine the preview frame image as the video cover; The video cover is presented in the dialog window; the video cover is used to display the editing effect of the video draft when triggered.

6. The method according to claim 4 or 5, wherein: After presenting the trigger control of the target media content in the dialog window, the method further includes: In response to the touch operation on the trigger control, jump to the preview playback interface, render the editing effect frame images of the video draft in sequence and display them on the preview playback interface.

7. The method according to any one of claims 4 to 6, wherein: The trigger control includes an export control; After presenting the trigger control of the target media content in the dialog window, the method further includes: In response to a touch operation applied to the export control, a target video is generated according to the video draft.

8. The method according to any one of claims 4 to 7, wherein: Generating target media content according to the conversation content includes: According to the conversation content, obtaining first requirement information input by the user; the first requirement information is used to indicate content requirements of the media content; Determine a plurality of candidate video drafts according to the first requirement information; the candidate video drafts include a video draft template and a target material; the video draft template includes an editing operation performed on the target material; A video draft is selected from the plurality of candidate video drafts.

9. The method according to claim 8, wherein: The first requirement information includes a first text requirement and / or a first video material selected by a user; The displaying of the conversation content in the conversation window of the first interface includes: The first system dialogue information is displayed in the dialogue window of the first interface; the first system dialogue information presents a material import control and / or a first input box; the material import control is used to obtain the first video material selected by the user, and the first input box is used to obtain the first text requirement input by the user.

10. The method according to claim 9, wherein: The displaying of the conversation content in the conversation window of the first interface also includes: If the first system dialogue information presents the material import control, in response to the material import control, a material selection interface is displayed in the dialogue window; In response to a selection instruction of the user in the material selection interface, a first video material selected by the user is obtained.

11. The method according to claim 10, wherein: The step of obtaining the first video material selected by the user includes: Obtaining a second video material selected by a user; Displaying the slot to be filled and the filled slot filled with the second video material in the dialog window; the slot to be filled is used to fill the video material selected by the user after being triggered, forming a new filled slot and displaying it; According to the video material filled in the filled slot, the first video material selected by the user is obtained.

12. The method according to claim 11, wherein: The filled slot includes a delete control, and the delete control is used to delete the corresponding filled slot after being triggered.

13. The method according to any one of claims 4 to 12, wherein: Generating target media content according to the conversation content includes: Determine the target copy based on the content of the conversation; Dividing the target text into multiple text sentences; For each copywriting sentence, determining the video material and audio clip corresponding to the copywriting sentence; the video material is obtained based on the semantic matching of the copywriting sentence; the audio clip is obtained by converting the copywriting sentence based on the text-to-speech technology; A video draft is generated according to the video materials and audio clips respectively corresponding to the plurality of text sentences; the video materials and the audio clips can be edited independently.

14. The method according to claim 13, wherein: Determining the target copy according to the conversation content includes: The second requirement information is determined according to the conversation content, and the target copy is determined according to the second requirement information; the second requirement information is used to indicate the content requirement for the copy.

15. The method according to claim 14, wherein: The displaying of the conversation content in the conversation window of the first interface includes: The second system dialogue information is displayed in the dialogue window of the first interface; the second system dialogue information presents a second input box; the second input box presents a first copy generated according to the second requirement information; In response to the editing control acting on the second input box, the first text is edited to obtain the second text; or, in response to the switching control acting on the second input box, the first text is switched to obtain the third text.

16. The method according to any one of claims 1 to 15, wherein: Generating target media content according to the conversation content includes: Determine third requirement information according to the conversation content; the third requirement information includes a second text requirement and / or a reference picture; the second text requirement is used to indicate a content requirement for media content; A target picture is determined according to the third requirement information, and the target picture is determined as the target media content.

17. The method according to any one of claims 1 to 16, wherein: Before displaying the conversation content in the conversation window of the first interface, the method further includes: In response to a first entry control acting on a second interface, the first interface is displayed; the second interface presents a search box; the first entry control is located in the surrounding area of ​​the search box; the search box is used to input search information to search for a media content template that matches the search information; the search information is used to indicate the user's creative intention for media content.

18. The method according to claim 17, wherein: Before displaying the conversation content in the conversation window of the first interface, the method further includes: The first interface is displayed in response to a second entry control acting on the search results interface; the search results interface is triggered to display in response to a search operation acting on the search box; the search results interface presents a search results display area; the second entry control is set in the surrounding area of ​​the search results display area.

19. A media content generating device, comprising: A display module, used to display the conversation content in the conversation window of the first interface; The conversation content is used to indicate the user's intention to create media content; A generating module, used for generating target media content according to the conversation content; The display module is further used to present a trigger control of the target media content in the dialog window, and the trigger control is at least used to trigger the presentation of the target media content.

20. An electronic device, comprising: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the media content generation method according to any one of claims 1 to 18.

21. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the media content generation method according to any one of claims 1 to 18 is implemented.

22. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method for generating media content according to any one of claims 1 to 18 is implemented.

Images