Video generation method, device, electronic device and storage medium

Abstract

The present disclosure relates to a video generation method, apparatus, electronic device, and storage medium, belonging to the field of Internet technologies. The method includes: in response to a video creation request for an object, displaying a video creation interface for the object; in the video creation interface, displaying a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category, where the material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories; generating a video associated with the object based on the materials uploaded through the plurality of material upload entries. Since it is possible to guide the user to upload materials under the material category associated with the object category of the object, the operation burden of the user is reduced, which is beneficial to improving the efficiency of video generation. Since the uploaded materials have a high adaptability to the object, it is beneficial to ensure that the generated video has a stronger relevance to the object and improve the accuracy of video generation.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technologies, and in particular, to a video generation method, apparatus, electronic device, and storage medium. Background Art

[0002] With the development of Internet technologies, users can share the videos they made on various platforms. For example, they can recommend a certain store or scenic spot by shooting a video.

[0003] In related technologies, when editing a video, usually users need to judge by themselves which type of video materials are more suitable, screen out the appropriate video materials for editing to generate a video. Therefore, the operation burden on users is relatively large, time-consuming, and the efficiency of video generation is low. Summary of the Invention

[0004] The present disclosure provides a video generation method, apparatus, electronic device, and storage medium, which can improve the accuracy of video generation.

[0005] According to one aspect of the embodiments of the present disclosure, a video generation method is provided. The method includes:

[0006] Responding to a video creation request for an object, and displaying a video creation interface of the object;

[0007] In the video creation interface, displaying a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories;

[0008] Generating a video associated with the object based on the materials uploaded through the plurality of material upload entries.

[0009] Optionally, the object is a store, and the video creation interface further displays a plurality of items provided by the store. The plurality of material upload entries include an item material upload entry and a store material upload entry; the method further includes:

[0010] Responding to a selection operation on any one of the plurality of items, and determining a selected target item;

[0011] Obtaining item materials of the target item based on the item material upload entry;

[0012] Obtaining store materials of the store based on the store material upload entry;

[0013] The generating a video associated with the object based on the materials uploaded through the plurality of material upload entries includes:

[0014] Edit the item material and the store material to obtain a first video, which is associated with the store and the target item.

[0015] Optionally, in response to a video creation request for an object, display a video creation interface for the object, including:

[0016] Display a store interface of the store, where the store interface includes video creation options and a plurality of candidate items provided by the store;

[0017] Based on a selection operation on at least one candidate item among the plurality of candidate items, determine the selected candidate item;

[0018] In response to a trigger operation on the video creation option, display the video creation interface, and the video creation interface displays the selected candidate item.

[0019] Optionally, the method further includes:

[0020] Based on an image upload operation performed on the video creation interface, obtain a reference image, and the reference image includes a person;

[0021] Based on a plurality of the material upload entrances, obtain the materials;

[0022] Generating a video associated with the object based on the materials uploaded through the plurality of material upload entrances includes:

[0023] Based on the materials and the reference image, generate a second video, which is associated with the object, and the second video includes a virtual image corresponding to the person in the reference image.

[0024] Optionally, the method further includes:

[0025] Based on a configuration information setting operation performed on the video creation interface, obtain video configuration information, and the video configuration information is used to indicate at least one of video style, background music, size, playing duration, or dubbing timbre;

[0026] Based on a plurality of the material upload entrances, obtain the materials;

[0027] Generating a video associated with the object based on the materials uploaded through the plurality of material upload entrances includes:

[0028] Process the materials according to the video configuration information to obtain a third video, which is associated with the object, and the third video conforms to the video configuration information.

[0029] Optionally, the video configuration information includes a reference voice, and the reference voice is used to indicate the dubbing timbre of the video; obtaining the video configuration information based on the configuration information setting operation on the video creation interface includes:

[0030] Obtaining the reference voice based on the voice upload operation performed on the video creation interface;

[0031] Processing the material according to the video configuration information to obtain a third video, including:

[0032] Dubbing the material according to the timbre of the reference voice to obtain the third video, and the dubbing timbre of the third video is the same as that of the reference voice.

[0033] Optionally, the method further includes:

[0034] Generating a description text of the video based on the materials uploaded through multiple material upload ports, and the description text is used to describe the video;

[0035] In response to the publishing operation of the video, publishing the video carrying the description text.

[0036] Optionally, the responding to the publishing operation of the video and publishing the video carrying the description text includes:

[0037] Displaying a publishing interface of the video, where the publishing interface includes the description text and publishing options;

[0038] In response to the editing operation on the description text, displaying the edited description text;

[0039] In response to the triggering operation on the publishing options, publishing the video carrying the edited description text.

[0040] Optionally, the method further includes:

[0041] Displaying a video generation task of the object, where the video generation task refers to generating a video associated with the object based on the materials uploaded through multiple material upload ports;

[0042] If the video is successfully generated and the video has been published, in response to the triggering operation on the video generation task, displaying a video interface of the video; or, if the video is not successfully generated, in response to the triggering operation on the video generation task, displaying the video creation interface.

[0043] Optionally, the method further includes:

[0044] Display each created video generation task and the status of each video generation task, where the status includes an unpublished status, a published status, a generating status, and a failed status. The unpublished status means that the video is successfully generated and the generated video is not published. The published status means that the video is successfully generated and the generated video is published.

[0045] Optionally, the method further includes at least one of the following:

[0046] In the area where the video generation task in the generating status is located, display the generation progress;

[0047] In the area where the video generation task in the failed status is located, display the reason for failure;

[0048] In the area where the video generation task in the unpublished status is located, display the number of unpublished videos. Among them, the number of videos generated by any video generation task is at least one.

[0049] Optionally, the method further includes:

[0050] Detect the materials uploaded based on multiple material upload entrances to obtain a detection result, where the detection result indicates whether the material belongs to the target material category;

[0051] Generating a video associated with the object based on the materials uploaded based on multiple material upload entrances includes:

[0052] If the detection result indicates that the material belongs to the target material category, generate a video associated with the object based on the material.

[0053] Optionally, the method further includes:

[0054] If the detection result indicates that the material does not belong to the target material category, display a prompt message for prompting that the currently uploaded material does not belong to the target material category, and re-upload the material belonging to the target material category.

[0055] According to another aspect of the embodiments of the present disclosure, there is provided a video generation device, where the device includes:

[0056] A display unit configured to execute in response to a video creation request for an object, and display the video creation interface of the object;

[0057] The display unit is further configured to execute in the video creation interface, display a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category, and the material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories;

[0058] The generation unit is configured to execute generating a video associated with the object based on the materials uploaded through the plurality of material upload entries.

[0059] Optionally, the object is a store, the video creation interface further displays a plurality of items provided by the store, and the plurality of material upload entries include an item material upload entry and a store material upload entry; the apparatus further includes a setting unit configured to execute:

[0060] In response to a selection operation on any one of the plurality of items, determine the selected target item;

[0061] Based on the item material upload entry, obtain the item material of the target item;

[0062] Based on the store material upload entry, obtain the store material of the store;

[0063] The generation unit is configured to execute:

[0064] Edit the item material and the store material to obtain a first video, and the first video is associated with the store and the target item.

[0065] Optionally, the display unit is configured to execute:

[0066] Display the store interface of the store, and the store interface includes a video creation option and a plurality of candidate items provided by the store;

[0067] Based on a selection operation on at least one of the plurality of candidate items, determine the selected candidate item;

[0068] In response to a trigger operation on the video creation option, display the video creation interface, and the video creation interface displays the selected candidate item.

[0069] Optionally, the apparatus further includes a setting unit configured to execute:

[0070] Based on an image upload operation performed in the video creation interface, obtain a reference image, and the reference image includes a person;

[0071] Based on the plurality of material upload entries, obtain the materials;

[0072] The generating unit is configured to perform:

[0073] Generate a second video based on the material and the reference image, the second video is associated with the object, and the second video includes a virtual image corresponding to the person in the reference image.

[0074] Optionally, the device further includes a setting unit configured to perform:

[0075] Obtain video configuration information based on a configuration information setting operation performed on the video creation interface, where the video configuration information is used to indicate at least one of the style, background music, size, playing duration, or dubbing timbre of the video;

[0076] Obtain the material based on a plurality of the material upload entrances;

[0077] The generating unit is configured to perform:

[0078] Process the material according to the video configuration information to obtain a third video, the third video is associated with the object, and the third video conforms to the video configuration information.

[0079] Optionally, the video configuration information includes a reference voice, and the reference voice is used to indicate the dubbing timbre of the video; the setting unit is configured to perform:

[0080] Obtain the reference voice based on a voice upload operation performed on the video creation interface;

[0081] The generating unit is configured to perform:

[0082] Dub the material according to the timbre of the reference voice to obtain the third video, and the dubbing timbre of the third video is the same as the timbre of the reference voice.

[0083] Optionally, the device further includes:

[0084] The generating unit is further configured to generate a description text of the video based on the material uploaded through a plurality of the material upload entrances, where the description text is used to describe the video;

[0085] The publishing unit is configured to perform publishing the video carrying the description text in response to a publishing operation on the video.

[0086] Optionally, the publishing unit is configured to perform:

[0087] Display a publishing interface of the video, where the publishing interface includes the description text and publishing options;

[0088] In response to an editing operation on the description text, display the description text after editing the description text;

[0089] In response to a triggering operation on the publishing option, publish the video carrying the edited description text.

[0090] Optionally, the device further includes a task management unit configured to execute:

[0091] Display a video generation task of the object, where the video generation task refers to generating a video associated with the object based on materials uploaded through a plurality of the material upload entrances;

[0092] If the video is successfully generated and the video has been published, in response to a triggering operation on the video generation task, display a video interface of the video; or, if the video is not successfully generated, in response to a triggering operation on the video generation task, display a video creation interface.

[0093] Optionally, the device further includes a task management unit configured to execute:

[0094] Display each created video generation task and the status of each video generation task, where the status includes an unpublished status, a published status, a generating status, and a failed status. The unpublished status means that the video is successfully generated and the generated video has not been published, and the published status means that the video is successfully generated and the generated video has been published.

[0095] Optionally, the task management unit is configured to execute at least one of the following:

[0096] In the area where the video generation task in the generating status is located, display a generation progress;

[0097] In the area where the video generation task in the failed status is located, display a failure reason;

[0098] In the area where the video generation task in the unpublished status is located, display the number of unpublished videos, where the number of videos generated by any video generation task is at least one.

[0099] Optionally, the device further includes a detection unit configured to execute:

[0100] Detect the materials uploaded through a plurality of the material upload entrances to obtain a detection result, where the detection result indicates whether the materials belong to the target material category;

[0101] The generation unit is configured to execute:

[0102] If the detection result indicates that the material belongs to the target material category, generate a video associated with the object based on the material.

[0103] Optionally, the apparatus further includes:

[0104] A prompting unit configured to, if the detection result indicates that the material does not belong to the target material category, display a prompt message for prompting that the currently uploaded material does not belong to the target material category and re-upload a material belonging to the target material category.

[0105] According to another aspect of the embodiments of the present disclosure, an electronic device is provided, and the electronic device includes:

[0106] A processor;

[0107] A memory for storing executable instructions of the processor;

[0108] Wherein, the processor is configured to execute the instructions to implement the video generation method as described in the above aspect.

[0109] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the video generation method as described in the above aspect.

[0110] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program that implements the video generation method as described in the above aspect when executed by a processor.

[0111] The method provided by the embodiments of the present disclosure, when a video associated with an object needs to be generated, provides a plurality of target material categories associated with the object category of the object and corresponding material upload entrances on the video creation interface. The materials uploaded through the material upload entrances belong to the target material category. Since different object categories are associated with different material categories, different material upload entrances will be provided for different objects, thereby guiding the user to upload materials belonging to the target material category, without the user having to decide and screen which type of material to use by themselves, reducing the user's operation burden and being beneficial to improving the efficiency of video generation. And, since the material category of the uploaded material is associated with the object category of the object, the adaptability of the material to the object is improved, which is beneficial to ensuring that the generated video has a stronger association with the object, thereby improving the accuracy of video generation.

[0112] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0113] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0114] Figure 1 It is a schematic diagram of an implementation environment of a video generation method shown according to an exemplary embodiment.

[0115] Figure 2 It is a flowchart of a video generation method shown according to an exemplary embodiment.

[0116] Figure 3 It is a flowchart of another video generation method shown according to an exemplary embodiment.

[0117] Figure 4 It is a schematic diagram of a video creation interface shown according to an exemplary embodiment.

[0118] Figure 5 It is a schematic diagram of an object interface shown according to an exemplary embodiment.

[0119] Figure 6 It is a schematic diagram of an object display interface shown according to an exemplary embodiment.

[0120] Figure 7 It is a flowchart of another video generation method shown according to an exemplary embodiment.

[0121] Figure 8 It is a flowchart of another video generation method shown according to an exemplary embodiment.

[0122] Figure 9 It is a flowchart of another video generation method shown according to an exemplary embodiment.

[0123] Figure 10 It is a flowchart of another video generation method shown according to an exemplary embodiment.

[0124] Figure 11 It is a flowchart of another video generation method shown according to an exemplary embodiment.

[0125] Figure 12 It is a schematic diagram of a task management interface shown according to an exemplary embodiment.

[0126] Figure 13 It is a schematic diagram of another task management interface shown according to an exemplary embodiment.

[0127] Figure 14 It is a schematic diagram of another task management interface shown according to an exemplary embodiment.

[0128] Figure 15 It is a schematic diagram of another task management interface shown according to an exemplary embodiment.

[0129] Figure 16 It is a schematic diagram of another task management interface shown according to an exemplary embodiment.

[0130] Figure 17 It is a schematic diagram of an operation guidance information shown according to an exemplary embodiment.

[0131] Figure 18 It is a schematic diagram of a main interface shown according to an exemplary embodiment.

[0132] Figure 19 It is a schematic diagram of a video display interface shown according to an exemplary embodiment.

[0133] Figure 20 It is a schematic diagram of a publishing interface shown according to an exemplary embodiment.

[0134] Figure 21 It is a schematic diagram of a publishing time setting interface shown according to an exemplary embodiment.

[0135] Figure 22 It is a schematic diagram of a video interface shown according to an exemplary embodiment.

[0136] Figure 23 It is a block diagram of a video generation device shown according to an exemplary embodiment.

[0137] Figure 24 It is a block diagram of another video generation device shown according to an exemplary embodiment.

[0138] Figure 25 It is a block diagram of a terminal shown according to an exemplary embodiment. Detailed implementation manners

[0139] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0140] It should be noted that the terms "first", "second", etc. in the description, claims, and the above accompanying drawings description of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in the present disclosure are all authorized by the user or fully authorized by all parties. The collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions. For example, the materials, reference images, reference voices, etc. involved in the present disclosure are obtained under full authorization.

[0142] An embodiment of the present disclosure provides a video generation method, and the execution entity is an electronic device. Exemplarily, the electronic device is a terminal or a server. The terminal is a computer, a mobile phone, a tablet computer, or other terminals, and the server is a background server or a cloud server that provides services such as cloud computing and cloud storage. Among them, the electronic device displays a video creation interface for an object, and the user can upload materials of a target material category through a material upload entry associated with the object category of the object on the video creation interface. Since the target material category is associated with the object category, a video associated with the object can be generated based on these materials.

[0143] Figure 1 It is a schematic diagram of an implementation environment of a video generation method shown according to an exemplary embodiment. Refer to Figure 1 This implementation environment specifically includes: a terminal 101 and a server 102. The terminal 101 can be connected to the server 102 through a wireless network or a wired network.

[0144] The terminal 101 can be at least one of devices such as a smart phone, a smart watch, a desktop computer, a laptop computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, and a laptop portable computer. Optionally, a target application is installed and running on the terminal 101. Exemplarily, the target application is a target application in the operating system of the terminal 101, or a target application provided by a third party. Among them, the target application can be a video application. The user logs in to the target application through the terminal 101 and uses the video service provided by the target application. For example, the user can generate videos, publish videos, and watch videos through the target application. In addition, the target application can also have other functions, such as a network social function, a video sharing function, or a chat function. The server 102 is the background server of the target application, and the server 102 is used to provide background services for the target application.

[0145] The terminal 101 can generally refer to one of multiple terminals, and the embodiments of the present disclosure use the terminal 101 as an example for illustration. Those skilled in the art can know that the number of the above terminals can be more or less. For example, the above terminals can be several, or the above terminals can be dozens or hundreds, or a larger number. The embodiments of the present disclosure do not limit the number and device type of the terminals.

[0146] The server 102 is at least one of a server, multiple servers, a cloud computing platform, and a virtualization center. Optionally, the number of the above servers can be more or less, and the embodiments of the present disclosure do not limit this. Of course, the server 102 can also include other functional servers to provide more comprehensive and diverse services. In some embodiments, the server 102 undertakes the main computing work, and the terminal 101 undertakes the secondary computing work; or, the server 102 undertakes the secondary computing work, and the terminal 101 undertakes the main computing work; or, the server 102 and the terminal 101 adopt a distributed computing architecture for collaborative computing. The server 102 can be connected to the terminal 101 and other terminals through a wireless network or a wired network. Optionally, the number of the above servers can be more or less, and the embodiments of the present disclosure do not limit this.

[0147] In an embodiment of the present disclosure, the terminal 101 displays a video creation interface for an object. The video creation interface displays a target material category associated with the object category of the object and a material upload entry corresponding to the target material category. The user uploads materials through the material upload entry. The terminal 101 obtains the materials uploaded by the user and sends a video generation request for the object to the server 102. The video generation request carries the materials. The server 102 receives the video generation request, generates a video associated with the object based on the materials, and sends the video to the terminal 101. The terminal 101 receives the video and displays the video, thereby realizing the process of intelligent video generation without the user manually editing the video.

[0148] Figure 2 is a flowchart of a video generation method shown according to an exemplary embodiment. Refer to Figure 2 , this method is executed by an electronic device and includes the following steps:

[0149] In step 201, the electronic device displays a video creation interface for an object in response to a video creation request for the object.

[0150] The video creation request for the object is used to request the creation of a video associated with the object. The electronic device displays the video creation interface for the object in response to the video creation request.

[0151] Among them, the object can be any type of object. For example, the object can be a restaurant, a supermarket, a hotel, a scenic spot, etc. The embodiments of the present disclosure do not limit this.

[0152] Among them, the video creation interface for the object is used to create a video associated with the object.

[0153] In step 202, the electronic device displays a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category in the video creation interface. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category. Different object categories are associated with different material categories.

[0154] The video creation interface for the object displays a plurality of target material categories associated with the object category and a material upload entry corresponding to each target material category. Among them, the material upload entry corresponding to any material category is used to upload materials belonging to the material category. That is, the material category to which the materials uploaded by the material upload entry belong is associated with the object category to which the object belongs. Therefore, the material upload entry corresponding to the target material category is used to upload materials belonging to the target material category.

[0155] Among them, different object categories are associated with different material categories. Then, for different object categories, material upload entrances corresponding to different material categories are displayed, so as to provide personalized material upload entrances for objects of different object categories.

[0156] For example, if the object category includes catering stores, the material categories associated with this object category include storefront materials, store environment materials, dining area materials, kitchen area materials, food materials, etc. For another example, if the object category includes hotels, the material categories associated with this object category include hotel front desk area materials, hotel room environment materials, bedding materials, etc.

[0157] In step 203, the electronic device generates a video associated with the object based on the materials uploaded through multiple material upload entrances.

[0158] The user uploads materials belonging to the target material category through the multiple material upload entrances. After the electronic device obtains the materials uploaded by the user, it generates a video based on the materials. The video includes the materials, and the video is associated with the object.

[0159] Among them, the video being associated with the object means that the content of the video is related to the object. For example, the video is used to explain and recommend the object, etc.

[0160] Among them, the material can be a video clip or an image, etc. The video associated with the object is obtained by editing, dubbing, adding subtitles, and adding background music, etc. to the material.

[0161] When the method provided by the embodiments of the present disclosure needs to generate a video associated with an object, multiple target material categories associated with the object category of the object and corresponding material upload entrances are provided on the video creation interface. The materials uploaded through the material upload entrances belong to the target material category. Since different object categories are associated with different material categories, different material upload entrances will be provided for different objects, thereby guiding the user to upload materials belonging to the target material category, without the user having to decide and screen which category of materials to use by themselves, reducing the user's operation burden and being conducive to improving the efficiency of video generation. And because the material category of the uploaded material is associated with the object category of the object, the adaptability of the material to the object is improved, which is conducive to ensuring that the generated video has a stronger association with the object, thereby improving the accuracy of video generation.

[0162] The above Figure 2 shows a brief description of a video generation method of the present disclosure. Next, the video generation solution provided by the present disclosure will be further elaborated.

[0163] Figure 3It is a flowchart of another video generation method shown according to an exemplary embodiment. This method is executed by an electronic device. Refer to Figure 3 , and this method includes the following steps:

[0164] In step 301, in response to a video creation request for a store, the electronic device displays a video creation interface for the store. In the video creation interface, multiple target material categories, a material upload entry corresponding to each target material category, and multiple items provided by the store are displayed. The target material categories are associated with the store category of the store. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category. Different store categories are associated with different material categories. The material upload entries corresponding to the multiple target material categories include an item material upload entry and a store material upload entry.

[0165] In an embodiment of the present disclosure, the store provides multiple items. The video creation interface of this store, in addition to including multiple target material categories and corresponding material upload entries, also includes the multiple items provided by this store. Among them, the target material categories associated with the store category of this store include item materials and store materials. Item materials refer to materials related to items, and store materials refer to materials related to the store. Then, the multiple material upload entries include an item material upload entry and a store material upload entry. The item material upload entry is used to upload item materials, and the store material upload entry is used to upload store materials.

[0166] In some embodiments, the video creation interface further includes a video generation option, and this video generation option is used to trigger the execution of the step of obtaining a video based on the uploaded materials.

[0167] Figure 4 It is a schematic diagram of a video creation interface provided according to an exemplary embodiment. Taking a store as a restaurant as an example, the restaurant provides multiple food items. The target material categories include store materials and item materials. Store materials include facade materials and in-store environment materials, etc. Item materials refer to food item materials (that is, materials related to food items). Then as Figure 4 shown, the video creation interface of the restaurant displays multiple different material upload entries 401, a video generation option 402, and a food item selection area 403. The food item selection area 403 is used to display the food items provided by the restaurant.

[0168] In some embodiments, in response to a video creation request for a store, the electronic device displays a video creation interface for the store, including: displaying the store interface of the store, where the store interface includes a video creation option and multiple candidate items provided by the store; based on a selection operation on at least one candidate item among the multiple candidate items, determining the selected candidate item; in response to a trigger operation on the video creation option, displaying a video creation interface, and the video creation interface displays the selected candidate item.

[0169] The store interface displays multiple candidate items provided by the store. The user can perform a preliminary screening among the multiple candidate items. After the selection is completed, a trigger operation for the video creation option is executed, thereby jumping to the video creation interface of the store, and only the selected candidate items are displayed in the video creation interface. That is, by triggering the video creation option in the store interface, the user jumps from the store interface to the video creation interface.

[0170] Among them, the store interface refers to the interface that displays the store, and the store interface may further include the detailed information of the store, such as the name, address, and business hours of the store.

[0171] Optionally, if no selection operation for any of the multiple candidate items is detected, then in response to the trigger operation for the video creation option, the video creation interface is displayed, and all candidate items provided by the store are displayed in the video creation interface.

[0172] Optionally, the video creation option includes a first video creation option and a second video creation option. The first video creation option is used to request the automatic generation of a video associated with the store, and the second video creation option is used to request the manual editing of a video associated with the store. Then, in response to the trigger operation for the first video creation option, the electronic device displays the video creation interface of the store, which is used to automatically generate a video associated with the store. That is, after the user uploads the material, the electronic device can automatically generate a video associated with the store without the user manually editing the video. In addition, in response to the trigger operation for the second video creation option, the electronic device displays the video editing interface of the store, which is used to generate a video associated with the store according to the editing operations performed by the user. That is, the user needs to manually edit the video.

[0173] Figure 5 is a schematic diagram of a store interface provided according to an exemplary embodiment, as Figure 5 shown, the store interface includes multiple items 501 provided by the store, a first video creation option 502, and a second video creation option 503. The store interface also displays the detailed information of each item 501. For example, the detailed information of the item 501 includes the picture, name, and price of the item 501.

[0174] Optionally, the electronic device displays a store display interface, which includes multiple stores; in response to the selection operation for any of the multiple stores, the store interface of the selected store is displayed.

[0175] The store display interface shows multiple different stores, and the user can select among these multiple stores so that the electronic device displays the store interface of the selected store. That is, by selecting any store in the store display interface, the user can jump from the store display interface to the store interface of the selected store.

[0176] Figure 6 It is a schematic diagram of a store display interface provided according to an exemplary embodiment, as Figure 6 shown. The store display interface shows multiple different stores 601 and the detailed information of each store 601. For example, the detailed information of store 601 includes the name of the store, the distance, whether one-key video creation is supported, etc.

[0177] In the embodiments of the present disclosure, a secondary selection scheme is provided. In the first selection, the user can initially and quickly screen out the items of interest on the store interface, reducing the time consumed in repeatedly searching among a large number of items. In the second selection, on the video creation interface, the user only needs to select from the pre-screened items, thereby quickly determining which item to associate with, and the operation is more convenient. Therefore, the solution of the embodiments of the present disclosure can reduce the user's selection burden, improve the flexibility and adaptability of the selection process, and is beneficial to improving the efficiency of human-computer interaction.

[0178] In step 302, the electronic device determines the selected target item in response to a selection operation on any one of the multiple items.

[0179] The video creation interface shows multiple items provided by the store. If the user wants to generate a video associated with the target item, a selection operation on the target item is performed, and the electronic device determines the selected target item from the multiple items in response to this selection operation. Among them, the target item can be any one of the multiple items.

[0180] In some embodiments, the video creation interface shows an item selection area, which shows the currently selected item and selection options. The electronic device displays multiple items provided by the store in response to a trigger operation on the selection options, determines the selected target item in response to a selection operation on any one of the multiple items, and switches the item currently displayed in the item selection area to the target item. If the item currently displayed in the item selection area is the same as the target item, no switching is required. That is, the item selection area always shows the selected item, facilitating the user to know which item is currently selected.

[0181] In step 303, the electronic device obtains the item material of the target item based on the item material upload entry.

[0182] The item material upload entry is used to upload item materials. Therefore, the electronic device can obtain the uploaded item materials based on this item material upload entry.

[0183] In some embodiments, in response to a trigger operation on the item material upload entry, the electronic device displays a local album that stores videos or images. In response to a selection operation on the videos or images in the local album, the selected videos or images are uploaded and used as the item materials of the target item.

[0184] In some embodiments, a first prompt message is displayed at the location where the item material upload entry is located. This first prompt message is used to prompt the upload of the item materials of the target item through this item material upload entry, thereby guiding the user to upload the item materials of the target item through this item material upload entry.

[0185] In step 304, the electronic device obtains the store materials of the store based on the store material upload entry.

[0186] The store material upload entry is used to upload store materials. Therefore, the electronic device can obtain the uploaded store materials based on this store material upload entry.

[0187] In some embodiments, in response to a trigger operation on the store material upload entry, the electronic device displays a local album that stores videos or images. In response to a selection operation on the videos or images in the local album, the selected videos or images are uploaded and used as the store materials of the store.

[0188] In some embodiments, a second prompt message is displayed at the location where the store material upload entry is located. This second prompt message is used to prompt the upload of the store materials of the store through this store material upload entry, thereby guiding the user to upload the store materials of the store through this store material upload entry.

[0189] In step 305, the electronic device edits the item materials and the store materials to obtain a first video, which is associated with the store and the target item.

[0190] After the electronic device obtains the uploaded item materials and store materials, it edits the item materials and the store materials to obtain a first video. Since the item materials are associated with the target item and the store materials are associated with the store, this first video is associated with the store and the target item. For example, this first video is a video explaining the store and the target item provided by the store.

[0191] In some embodiments, a video creation interface displays video generation options. In response to a trigger operation on the video generation options, the electronic device clips item materials and store materials to obtain a first video. That is, in response to the trigger operation on the video generation options, the electronic device starts to execute the steps of generating the first video.

[0192] Optionally, the electronic device is a terminal. In response to the trigger operation on the video generation options, the terminal sends a video generation request to the server. The video generation request includes the item materials and the store materials. The server receives the video generation request, clips the item materials and the store materials based on this, obtains the first video, and sends the first video to the terminal. The terminal receives the first video, thereby obtaining the first video associated with the store and the target item.

[0193] Optionally, a video generation model is stored in the server. The video generation model is used to generate a video based on materials. The server inputs the item materials and the store materials into the video generation model, and the video generation model clips the item materials and the store materials and outputs the first video. Among them, the video generation model is a model trained based on artificial intelligence technology. For example, the video generation model is a large language model, etc.

[0194] In the embodiments of the present disclosure, by using the video generation model, a first video associated with the store and the target item is automatically generated based on the item materials and the store materials, realizing the intelligence and automation of the video generation process. There is no need for the user to manually perform editing operations. The user only needs to upload the materials used to generate the video, which simplifies the user operation, reduces the threshold of video generation, and is beneficial to improving the efficiency of video generation.

[0195] Optionally, each material upload entry corresponds to its own category label, and the category label indicates the material category to which the material uploaded by the material upload entry belongs. For example, the item material upload entry corresponds to an item label, and the store material upload entry corresponds to a store label. After the terminal obtains the material through the item material upload entry, it adds the item label to the material to indicate that the material belongs to the item material. After obtaining the material through the store material upload entry, it adds the store label to the material to indicate that the material belongs to the store material. Among them, in the video generation request sent by the terminal to the server, the item material carries the item label, and the store material carries the store label, so as to distinguish the material categories to which each material belongs. The server inputs the item material carrying the item label and the store material carrying the store label into the video generation model, and the video generation model can distinguish which material category each material belongs to according to the label, and then execute different processing methods for materials of different material categories, and finally output the first video.

[0196] Optionally, the video generation request sent by the terminal to the server further carries the store identifier of the store and the item identifier of the target item. For example, the store identifier is the name of the store, and the item identifier is the name of the item. The server inputs the item material, store material, item identifier, and store identifier into the video generation model, and the video generation model edits based on the item material, store material, item identifier, and store identifier to obtain a first video, where the first video includes the item material, store material, item identifier, and store identifier. For example, the item material and store material exist in the first video in the form of video clips, and the item identifier and store identifier exist in the first video in the form of subtitles or voiceovers, etc.

[0197] Optionally, in the case where the video generation request further carries the store identifier of the store and the item identifier of the target item, after generating the first video, the server associates the first video with the store identifier and the item identifier to indicate that the first video is associated with the store indicated by the store identifier and the target item indicated by the item identifier.

[0198] The method provided by the embodiments of the present disclosure, in the case where a store provides multiple items, the target item to be associated can be selected on the video creation interface, and the store material of the store and the item material of the target item can be uploaded, so as to generate a video associated with the store and the item. That is, for multiple items provided by the store, it is possible to flexibly select which item to generate an associated video, so that the generated video is associated with a specific item, improving the pertinence of video generation.

[0199] Figure 7 is a flowchart of another video generation method shown according to an exemplary embodiment. This method is executed by an electronic device. Refer to Figure 7 This method includes the following steps:

[0200] In step 701, in response to a video creation request for an object, the electronic device displays a video creation interface for the object. In the video creation interface, multiple target material categories associated with the object category of the object and a material upload entry corresponding to each target material category are displayed. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories.

[0201] In some embodiments, in response to a video creation request for an object, the electronic device displays a video creation interface for the object, including: displaying an object interface of the object, where the object interface includes a video creation option; in response to a trigger operation on the video creation option, displaying the video creation interface.

[0202] Among them, the process of step 701 is the same as that of step 301 above, and will not be elaborated here.

[0203] In step 702, the electronic device obtains a reference image based on an image upload operation performed on the video creation interface, and the reference image includes a person.

[0204] In the embodiments of the present disclosure, the user can also upload a reference image on the video creation interface, and the reference image is used to generate a virtual avatar. The reference image includes a person. For example, the reference image can be a real person image or an image of an anime character, etc.

[0205] In some embodiments, the video creation interface also displays a reference image upload entry, which is used to upload a reference image. The electronic device responds to a trigger operation on the reference image upload entry, displays the local album, and images are stored in the local album. In response to a selection operation on an image in the local album, the selected image is uploaded, and the uploaded image is used as the reference image.

[0206] In some embodiments, third prompt information is displayed at the position where the reference image upload entry is located. The third prompt information is used to prompt the upload of the reference image, and the reference image is used to generate a virtual avatar that appears in the video, so as to guide the user to upload the reference image through the reference image upload entry.

[0207] In step 703, the electronic device obtains materials based on a plurality of material upload entries.

[0208] The process of this step 703 is the same as that of the above step 303 or 304, and will not be elaborated here.

[0209] In step 704, the electronic device generates a second video based on the materials and the reference image. The second video is associated with the object, and the second video includes a virtual avatar corresponding to the person in the reference image.

[0210] After the electronic device obtains the uploaded reference image and materials, it uses digital human technology to generate a virtual avatar corresponding to the person in the reference image, integrates the virtual avatar into the materials, and obtains the second video. Then the second video includes the materials and the virtual avatar.

[0211] In some embodiments, the video creation interface displays a video generation option. The electronic device responds to a trigger operation on the video generation option and generates a second video based on the materials and the reference image. That is, the electronic device starts to execute the steps of generating the second video in response to a trigger operation on the video generation option.

[0212] Optionally, the electronic device is a terminal. The terminal sends a video generation request to the server in response to a trigger operation on the video generation option. The video generation request includes the reference image and the material. The server receives the video generation request, generates a second video based on the material and the reference image, and sends the second video to the terminal. The terminal receives the second video, thereby obtaining the second video associated with the object.

[0213] Optionally, a video generation model is stored in the server. The server inputs the reference image and the material into the video generation model. The video generation model generates a second video based on the material and the reference image and outputs the second video.

[0214] Optionally, the video generation request sent by the terminal to the server also carries the object identifier of the object. The server inputs the reference image, the material, and the object identifier into the video generation model. The video generation model edits based on the reference image, the material, and the object identifier to obtain a second video, where the second video includes the virtual image corresponding to the person in the reference image, the material, and the object identifier.

[0215] Optionally, when the video generation request also carries the object identifier of the object, after generating the second video, the server associates the second video with the object identifier to indicate that the second video is associated with the object indicated by the object identifier.

[0216] In the method provided by the embodiments of the present disclosure, when generating a video, the user can upload a reference image, generate a unique virtual image according to the reference image, and thus add the virtual image to the video. On the one hand, it can make the generated video more personalized and improve the realism and attractiveness of the video. On the other hand, using the intelligently generated virtual image instead of a real person appearing in the video eliminates the need to provide materials of a real person appearing in the video, saves the cost of video generation, simplifies the video generation process, and is conducive to improving the efficiency of video generation.

[0217] Figure 8 is a flowchart of another video generation method shown according to an exemplary embodiment. This method is executed by an electronic device. Refer to Figure 8 , and this method includes the following steps:

[0218] In step 801, the electronic device displays a video creation interface for the object in response to a video creation request for the object. In the video creation interface, multiple target material categories associated with the object category of the object and a material upload entry corresponding to each target material category are displayed. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories.

[0219] In some embodiments, in response to a video creation request for an object, the electronic device displays a video creation interface for the object, including: displaying an object interface for the object, the object interface including video creation options; and in response to a trigger operation on the video creation options, displaying a video creation interface.

[0220] Among them, the process of step 801 is the same as that of step 301 above, and will not be elaborated here.

[0221] In step 802, the electronic device obtains video configuration information based on a configuration information setting operation performed on the video creation interface, and the video configuration information is used to indicate at least one of the style, background music, size, playing duration, or dubbing tone of the video.

[0222] In the embodiments of the present disclosure, the user can also set video configuration information on the video creation interface. The video configuration information may include a style identifier, and the style identifier indicates the style of the video, such as funny or healing, etc. The video configuration information may include a music identifier, and the music identifier indicates the background music of the video. The video configuration information may include size parameters, and the size parameters indicate the size of the video. The video configuration information may include duration parameters, and the duration parameters indicate the duration of the video. The video configuration information may include a tone identifier or a reference voice, and the tone identifier or the reference voice indicates the dubbing tone of the video. When the video configuration information includes a reference voice, it means using the tone of the reference voice as the dubbing tone of the video.

[0223] In some embodiments, the video configuration information includes a style identifier. Among them, multiple candidate style identifiers are displayed on the video creation interface, and in response to a selection operation on any one of the candidate style identifiers, the selected style identifier is determined as the video configuration information.

[0224] In some embodiments, the video configuration information includes a music identifier. Among them, multiple candidate music identifiers are displayed on the video creation interface, and in response to a selection operation on any one of the candidate music identifiers, the selected music identifier is determined as the video configuration information.

[0225] In some embodiments, the video configuration information includes size parameters. Among them, multiple candidate size parameters are displayed on the video creation interface, and in response to a selection operation on any one of the candidate size parameters, the selected size parameter is determined as the video configuration information. For example, the size parameters may be 4*3, 3*4, 16*9, or 9*16, etc.

[0226] In some embodiments, the video configuration information includes duration parameters. Among them, a duration input box is displayed on the video creation interface, and in response to an input operation in the duration input box, the input duration parameter is determined as the video configuration information. For example, the duration parameters may be 1 minute, 2 minutes, etc.

[0227] In some embodiments, the video configuration information includes a tone color identifier. Among them, multiple candidate tone color identifiers are displayed on the video creation interface. In response to a selection operation on any one of the candidate tone color identifiers, the selected tone color identifier is determined as the video configuration information.

[0228] In some embodiments, the video configuration information includes a reference voice. The electronic device obtains the reference voice based on a voice upload operation performed on the video creation interface, and determines the reference voice as the video configuration information. Optionally, a reference voice collection entry is displayed on the video creation interface, and this reference voice upload entry is used to collect the reference voice. In response to a trigger operation on this reference voice collection entry, the electronic device starts voice collection and uses the currently collected voice as the reference voice.

[0229] In step 803, the electronic device obtains materials based on multiple material upload entries.

[0230] The process of this step 703 is the same as that of the above-mentioned step 303 or 304, and will not be elaborated here.

[0231] In step 804, the electronic device processes the materials according to the video configuration information to obtain a third video. The third video is associated with the object and conforms to the video configuration information.

[0232] After obtaining the video configuration information, the electronic device processes the materials according to the video configuration information to obtain a third video. The style, background music, size, playing duration, or dubbing tone color of the third video conforms to the style, background music, size, playing duration, or dubbing tone color indicated by the video configuration information.

[0233] In some embodiments, the video configuration information includes a reference voice, and the reference voice is used to indicate the dubbing tone color of the video. The electronic device dubs the materials according to the tone color of the reference voice to obtain a third video, and the dubbing tone color of the third video is the same as the tone color of the reference voice.

[0234] In the embodiments of the present disclosure, when generating a video, the user can upload a reference voice so that the dubbing tone color of the generated video is the same as the tone color of the reference voice. On the one hand, it can make the dubbing tone color of the video the same as any tone color, and the user can flexibly choose to generate a video with a certain tone color, improving the flexibility and personalization of the dubbing tone color of the video. On the other hand, in the scenario of generating a video with one key, automatic dubbing is performed by means of the tone color of the reference voice, without the need for a real person to dub, saving the cost of video generation, simplifying the video generation process, and being conducive to improving the efficiency of video generation.

[0235] In some embodiments, a video creation interface displays video generation options. In response to a trigger operation on the video generation options, the electronic device processes the materials according to the video configuration information to obtain a third video. That is, in response to the trigger operation on the video generation options, the electronic device starts to execute the steps of generating the third video.

[0236] Optionally, the electronic device is a terminal. In response to the trigger operation on the video generation options, the terminal sends a video generation request to the server. The video generation request includes the video configuration information and the materials. The server receives the video generation request, processes the materials according to the video configuration information to obtain a third video, and sends the third video to the terminal. The terminal receives the third video, thereby obtaining the third video associated with the object.

[0237] Optionally, a video generation model is stored in the server. The server inputs the video configuration information and the materials into the video generation model, and the video generation model performs editing based on the video configuration information and the materials to output a third video.

[0238] Optionally, the video generation request sent by the terminal to the server also carries the object identifier of the object. The server inputs the video configuration information, the materials, and the object identifier into the video generation model. The video generation model performs editing based on the video configuration information, the materials, and the object identifier to obtain a third video, where the third video includes the materials and the object identifier.

[0239] Optionally, in the case where the video generation request also carries the object identifier of the object, after generating the third video, the server associates the third video with the object identifier to indicate that the third video is associated with the object indicated by the object identifier.

[0240] The method provided by the embodiments of the present disclosure, by setting the video configuration information, enables the user to specify the style, background music, size, playing duration, or dubbing timbre of the video according to their own needs and preferences, making the generated video more in line with the user's requirements and improving the flexibility of video generation and the personalization effect of the generated video.

[0241] Moreover, in the scenario of generating a video with one click, by providing the user with customization functions such as video style, background music, size, playing duration, or dubbing timbre, a video that meets the user's needs can be generated without the user having to manually edit it, ensuring the simplicity of video generation and the effect of the intelligently generated video.

[0242] Figure 9 is a flowchart of another video generation method shown according to an exemplary embodiment. This method is executed by an electronic device. Refer to Figure 9 This method includes the following steps:

[0243] In step 901, in response to a video creation request for an object, the electronic device displays a video creation interface for the object. In the video creation interface, a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category are displayed. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories.

[0244] In some embodiments, in response to a video creation request for an object, the electronic device displays a video creation interface for the object, including: displaying an object interface of the object, where the object interface includes a video creation option; in response to a trigger operation on the video creation option, displaying the video creation interface.

[0245] Among them, the process of this step 901 is the same as that of the above step 301, and will not be elaborated here.

[0246] In step 902, the electronic device generates a video associated with the object and a description text of the video based on the materials uploaded through a plurality of material upload entries. The description text is used to describe the video.

[0247] In the embodiments of the present disclosure, while generating a video based on the materials, a description text of the video is also generated, eliminating the need for the user to manually edit the description text of the video, simplifying the user operation, saving time and effort, and improving the efficiency of human-computer interaction.

[0248] In some embodiments, a video generation option is displayed on the video creation interface. In response to a trigger operation on the video generation option, the electronic device generates a video associated with the object and a description text of the video based on the materials uploaded through a plurality of material upload entries. That is, in response to a trigger operation on the video generation option, the electronic device starts to execute the steps of generating the video and the description text.

[0249] Optionally, the electronic device is a terminal. In response to a trigger operation on the video generation option, the terminal sends a video generation request to the server, and the video generation request includes the materials. The server receives the video generation request and generates a video associated with the object and a description text of the video based on the materials, and sends the video and the description text to the terminal. The terminal receives the video and the description text.

[0250] Optionally, a video generation model is stored in the server. The server inputs the materials into the video generation model, and the video generation model generates a video associated with the object and a description text based on the materials, and the video generation model outputs the video and the description text.

[0251] In step 903, in response to a publishing operation on the video, the electronic device publishes the video carrying the description text.

[0252] If the user wants to publish the video, a publishing operation for the video is performed. In response to the publishing operation, the electronic device publishes the video carrying the description text, that is, publishes the video and the description text of the video simultaneously.

[0253] In some embodiments, the electronic device displays a video publishing interface. The publishing interface includes a description text and publishing options; in response to an editing operation on the description text, the edited description text is displayed; in response to a triggering operation on the publishing options, the video carrying the edited description text is published.

[0254] If the user is not satisfied with the intelligently generated description text, an editing operation on the description text can be performed to edit it based on the description text, so as to obtain the edited description text.

[0255] Optionally, in step 902 above, the electronic device creates and displays a video generation task. The video generation task refers to obtaining a video associated with the object and the description text of the video based on the materials uploaded through at least one material upload entry. After the video generation task is successfully executed (that is, the video and the description text are successfully generated), the electronic device jumps to the publishing interface of the video in response to a triggering operation on the video generation task.

[0256] The method provided by the embodiments of the present disclosure, when publishing a video, if the user is not satisfied with the intelligently generated description text, secondary editing can be performed based on the intelligently generated description text, so as to publish the edited description text together with the video. Therefore, a way to modify the description text can be provided for the user, the flexibility of adjusting the description text is improved, and it is beneficial to improve the quality and attractiveness of the description text.

[0257] It should be noted that the above Figure 3 、 Figure 7 、 Figure 8 and Figure 9Embodiments can be combined with each other, and the resulting solution is as follows. In response to a video creation request for a store, the terminal displays a video creation interface for the store. In the video creation interface, multiple target material categories associated with the store category of the store, a material upload entry corresponding to each target material category, multiple items provided by the store, and video generation options are displayed. The multiple material upload entries include an item material upload entry and a store material upload entry. The terminal determines a selected target item in response to a selection operation on any one of the multiple items. The terminal obtains the item material of the target item based on the item material upload entry. The terminal obtains the store material of the store based on the store material upload entry. The terminal obtains a reference image based on an image upload operation performed in the video creation interface. Based on a configuration information setting operation performed in the video creation interface, video configuration information is obtained, and the video configuration information is used to indicate at least one of the style, background music, size, playback duration, or dubbing tone of the video. The terminal sends a video generation request to the server in response to a trigger operation on the video generation option. The video generation request includes the item material, the store material, the reference image, and the video configuration information. The server receives the video generation request, inputs the item material, the store material, the reference image, and the video configuration information into the video generation model, outputs a video and a description text by the video generation model, and sends the video and the description text to the terminal. Further, the server can also associate the video with the store identifier and the item identifier to indicate that the video is associated with the store indicated by the store identifier and the target item indicated by the item identifier.

[0258] Figure 10 is a flowchart of another video generation method shown according to an exemplary embodiment. This method is executed by an electronic device. Refer to Figure 10 This method includes the following steps:

[0259] In step 1001, in response to a video creation request for an object, the electronic device displays a video creation interface for the object. In the video creation interface, multiple target material categories associated with the object category of the object and a material upload entry corresponding to each target material category are displayed. The material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories.

[0260] In some embodiments, in response to a video creation request for an object, the electronic device displays a video creation interface for the object, including: displaying an object interface of the object, where the object interface includes a video creation option; and in response to a trigger operation on the video creation option, displaying the video creation interface.

[0261] Among them, the process of step 1001 is the same as that of step 301 above and will not be elaborated here.

[0262] In step 1002, the electronic device detects the materials uploaded based on multiple material upload entrances to obtain a detection result, and the detection result indicates whether the material belongs to the target material category.

[0263] In the embodiments of the present disclosure, after the electronic device obtains the material uploaded based on the material upload entrance, it detects the material to determine whether the material belongs to the target material category.

[0264] Exemplarily, the target material category includes item materials, the multiple material upload entrances include item material upload entrances, and the item material upload entrances are used to upload item materials. After the electronic device obtains the material uploaded based on the item material upload entrance, it detects whether the material is related to an item. If the material is related to an item, it means the material belongs to the item material; if the material is not related to an item, it means the material does not belong to the item material. For example, if the material is a video, the electronic device detects whether the video includes an item. If it includes an item, it means the material belongs to the item material; if it does not include an item, it means the material does not belong to the item material.

[0265] Exemplarily, the target material category includes store materials, the multiple material upload entrances include store material upload entrances. Taking a restaurant as an example of the store, the store material upload entrances include storefront material upload entrances, in-store environment material upload entrances, dining area material upload entrances, etc. For example, after the electronic device obtains the material uploaded by the storefront based on the material upload entrance, it detects whether the material includes a storefront. If it includes a storefront, it means the material belongs to the storefront material; if it does not include a storefront, it means the material does not belong to the storefront material.

[0266] In step 1003, if the detection result indicates that the material belongs to the target material category, the electronic device generates a video associated with the object based on the material.

[0267] If the detection result indicates that the material belongs to the target material category, it means that the material uploaded based on the material upload entrance is correct. Then the electronic device generates a video associated with the object based on the material.

[0268] In the embodiments of the present disclosure, after uploading the material through the material upload entrance, by detecting the material to determine whether the material belongs to the target material category, it is ensured that the video is generated based on the material belonging to the target material category. Since the target material category is associated with the object category of the object, this can further ensure that the generated video has a stronger association with the object, thereby improving the accuracy of the generated video.

[0269] In step 1004, if the detection result indicates that the material does not belong to the target material category, the electronic device displays a prompt message, and the prompt message is used to prompt that the currently uploaded material does not belong to the target material category and to re-upload the material belonging to the target material category.

[0270] If the detection result indicates that the material does not belong to the target material category, it means that the material uploaded based on the material upload entry is incorrect. Then, the electronic device does not perform the step of generating a video associated with the object based on the material, but displays a prompt message to guide the user to re-upload the correct material.

[0271] In the embodiments of the present disclosure, if it is detected that the uploaded material does not belong to the target material category, a prompt message is displayed to prompt the user to re-upload the material belonging to the target material category, so as to guide the user to upload the correct material, avoid the situation that the video cannot be successfully generated or the generated video has a poor effect due to the use of inappropriate materials, thereby avoiding useless work, being beneficial to saving time, and improving the efficiency of video generation.

[0272] Figure 11 is a flowchart of another video generation method shown according to an exemplary embodiment. This method is executed by an electronic device. Refer to Figure 11 and this method includes the following steps:

[0273] In step 1101, in response to a video creation request for an object, the electronic device displays a video creation interface for the object. In the video creation interface, a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category are displayed. The material upload entry corresponding to the target material category is used to upload the material belonging to the target material category, and different object categories are associated with different material categories.

[0274] In some embodiments, in response to a video creation request for an object, the electronic device displays a video creation interface for the object, including: displaying an object interface of the object, where the object interface includes a video creation option; in response to a trigger operation on the video creation option, displaying the video creation interface.

[0275] Among them, the process of step 1101 is the same as that of step 301 above and will not be elaborated here.

[0276] In step 1102, the electronic device obtains materials based on a plurality of material upload entries.

[0277] The process of step 1102 is the same as that of step 303 or 304 above and will not be elaborated here.

[0278] In step 1103, the electronic device creates a video generation task for the object, executes the video generation task, and displays the video generation task. The video generation task refers to generating a video associated with the object based on the materials uploaded through a plurality of material upload entries.

[0279] It should be noted that after the electronic device creates the video generation task, it can display the video generation task and execute the video generation task. Therefore, when the video generation task is displayed, the video generation task can be in a successful state, a generating state, or a failed state.

[0280] Among them, the successful state means that the video is successfully generated (that is, the video generation task has been successfully executed and completed), the generating state means that the video is being generated (that is, the video generation task is in progress), and the failed state means that the video is not successfully generated (that is, the video generation task fails to execute).

[0281] In step 1104, if the video is successfully generated and the video has been published, the electronic device responds to the trigger operation on the video generation task and displays the video interface of the video.

[0282] If the video generated by the video generation task has been published, then when the user performs the trigger operation on the video generation task, the user can directly jump to the video interface of the video.

[0283] Among them, the video interface of the video is used to play the video. Exemplarily, the video interface further includes description text of the video, like options, comment options, favorite options, share options, and the like.

[0284] In the embodiments of the present disclosure, for a video generation task that successfully generates a video and the video has been published, the user can automatically jump to the video interface of the video by triggering the video generation task, without the user having to jump to the published work interface to view it, improving the effect of human-computer interaction.

[0285] In step 1105, if the video is not successfully generated, the electronic device responds to the trigger operation on the video generation task and displays the video creation interface.

[0286] If the video generation task fails to execute and the video is not successfully generated, then when the user performs the trigger operation on the video generation task, the user can directly jump to the video creation interface of the object.

[0287] Optionally, in the video creation interface, the materials uploaded last time are not retained, that is, it is necessary to re-upload materials in the video creation interface. Optionally, in the video creation interface, the target item selected last time is still retained. Optionally, in the video creation interface, the reference image uploaded last time and the set video configuration information are not retained.

[0288] In the embodiments of the present disclosure, for a video generation task that does not successfully generate a video, the user can automatically jump to the video creation interface by triggering the video generation task, facilitating the user to re-upload materials, without the user having to repeatedly perform the video creation operation on the object, improving the effect of human-computer interaction.

[0289] In the method provided by the embodiments of the present disclosure, since the states of the video generation tasks are different, the interfaces to which the video generation tasks jump after trigger operations are different, making the interface display process more flexible and capable of adapting to the different requirements of various scenarios.

[0290] It should be noted that in each of the above embodiments, when generating a video associated with an object, one video associated with the object can be generated based on the materials, or multiple videos associated with the object can be generated simultaneously based on the materials, and the contents of the multiple videos are different.

[0291] Based on the above embodiments, an electronic device can create a video generation task for any object, and then the electronic device can display each created video generation task and the state of each video generation task. The states include an unpublished state, a published state, a generating state, and a failed state.

[0292] Among them, both the unpublished state and the published state belong to the above-mentioned successful states. The unpublished state means that the video is successfully generated and not published, and the published state means that the video is successfully generated and published.

[0293] In some embodiments, the electronic device displays each created video generation task and the state of each video generation task in the task management interface. As Figure 12 shown, when requesting to display all tasks, the task management interface displays each created video generation task and the state of each video generation task. For example, video generation task 1201 in the generating state, video generation task 1202 in the unpublished state, video generation task 1203 in the published state, and video generation task 1204 in the failed state. As Figure 13 shown, when requesting to display the tasks in the generating state, the task management interface displays each video generation task in the generating state. As Figure 14 shown, when requesting to display the tasks in the unpublished state, the task management interface displays each video generation task in the unpublished state. As Figure 15 shown, when requesting to display the tasks in the published state, the task management interface displays each video generation task in the published state. As Figure 16 shown, when requesting to display the tasks in the failed state, the task management interface displays each video generation task in the failed state.

[0294] In the embodiments of the present disclosure, by displaying each created video generation task and the status of each video generation task, it is convenient for the user to understand the situation of each video generation task according to the displayed status, and further convenient for the user to manage the created video generation tasks, improving the visualization effect of the status of the video generation tasks.

[0295] In some embodiments, the electronic device further performs at least one of the following:

[0296] (1) Display the generation progress in the area where the video generation task in the generating state is located. As Figure 12 shown, the generation progress is displayed in the area where the video generation task 1201 in the generating state is located, such as "Expected waiting time: 30 minutes".

[0297] (2) Display the failure reason in the area where the video generation task in the failed state is located. As Figure 12 shown, the failure reason is displayed in the area where the video generation task 1204 in the failed state is located, such as "Lack of mixed editing materials".

[0298] (3) Display the number of unpublished videos in the area where the video generation task in the unpublished state is located, where the number of videos generated by any video generation task is at least one. As Figure 12 shown, the number of unpublished videos is displayed in the area where the video generation task 1202 in the unpublished state is located, such as "2 videos to be published".

[0299] In the embodiments of the present disclosure, for video generation tasks in different states, the generation progress, failure reason, and the number of unpublished videos can also be correspondingly displayed. The user can intuitively view the specific situation of the video generation tasks in different states, further improving the convenience for the user to manage the created video generation tasks and facilitating the improvement of the efficiency of human-computer interaction.

[0300] In some embodiments, the electronic device further performs at least one of the following:

[0301] (1) Display the thumbnail of the video generated by the video generation task in the area where the video generation task in the unpublished state or the published state is located. For example, the thumbnail of the video is the thumbnail of the video cover, etc. As Figure 12 shown, the thumbnail of the video cover is displayed in the area where the video generation task 1202 in the unpublished state is located, and the thumbnail of the video cover is displayed in the area where the video generation task 1203 in the published state is located.

[0302] (2) Display the first preset thumbnail in the area where the video generation task in the generating state is located. As Figure 12As shown, a first preset thumbnail is displayed in the area where the video generation task 1201 in the generating state is located, and the first preset thumbnail includes the logo of artificial intelligence.

[0303] (3) In the area where the video generation task in the failed state is located, a second preset thumbnail is displayed, and the second preset thumbnail is different from the first preset thumbnail. As Figure 12 shown, a second preset thumbnail is displayed in the area where the video generation task 1204 in the failed state is located, and the second preset thumbnail includes a warning sign.

[0304] In some embodiments, in response to an operation to exit the task management interface, the electronic device displays operation guide information for instructing to enter the task management interface on the main interface of the currently logged-in account.

[0305] If the user wants to exit the task management interface, the user is prompted that the user can enter the task management interface again from the main interface of the account later, so that the user can view the status of different video generation tasks.

[0306] Figure 17 is a schematic diagram of an operation guide information provided according to an exemplary embodiment. As Figure 17 shown, in response to an operation to exit the task management interface, the electronic device displays operation guide information 1701 on the task management interface. Figure 18 is a schematic diagram of a main interface provided according to an exemplary embodiment. As Figure 18 shown, an entry control 1801 for the task management interface is displayed on the main interface. In response to a trigger operation on the entry control 1801, the electronic device jumps from the main interface to the task management interface.

[0307] In some embodiments, in response to a trigger operation on a video generation task in the unpublished state, the electronic device displays a video display interface, and the video display interface includes the video generated by the video generation task. In response to a publish operation on the video, the video is published.

[0308] Among them, the video display interface displays at least one video generated by the video generation task and not published. In response to a selection operation on any one of the at least one video, the selected video is published.

[0309] Figure 19 is a schematic diagram of a video display interface provided according to an exemplary embodiment. As Figure 19 shown, the video display interface displays videos 1901, 1902, and 1903 generated by the video generation task and not published.

[0310] Optionally, the video display interface displays a batch publishing option, and the electronic device publishes all the videos generated by the video generation task that have not been published in response to a triggering operation on the batch publishing option. As Figure 19 shown, the video display interface also displays a batch publishing option 1904.

[0311] Optionally, the electronic device displays a video publishing interface in response to a triggering operation on the video. The publishing interface includes a description text of the video, a scheduled publishing option, and a one-click publishing option. Figure 20 is a schematic diagram of a publishing interface provided according to an exemplary embodiment. As Figure 20 shown, the publishing interface displays a description text 2001 of the video, a scheduled publishing option 2002, and a one-click publishing option 2003.

[0312] The electronic device displays the edited description text in response to an editing operation on the description text, and publishes the video carrying the edited description text in response to a triggering operation on the one-click publishing option.

[0313] Alternatively, the electronic device displays a publishing time setting interface in response to a triggering operation on the scheduled publishing option; determines the set publishing time point based on the publishing time setting interface; and publishes the video when the publishing time point is reached. Figure 21 is a schematic diagram of a publishing time setting interface provided according to an exemplary embodiment. As Figure 21 shown, the user can set the publishing time point on the publishing time setting interface.

[0314] In some embodiments, the electronic device displays a video interface of the videos generated by the video generation task that have been published in response to a triggering operation on the video generation task in a published state. This step is the same as step 1104 above and will not be described in detail here. Figure 22 is a schematic diagram of a video interface provided according to an exemplary embodiment. As Figure 22 shown, the video interface displays a published video 2201, a like option 2202, a comment option 2203, a favorite option 2204, and a share option 2205. In addition, the video interface also displays a description text 2206 of the video 2201.

[0315] In some embodiments, the electronic device displays a video creation interface of the object associated with the video generation task in response to a triggering operation on the video generation task in a failed state. The video generation task is used to generate a video associated with the object, and the object is the object associated with the video generation task. This step is the same as step 1105 above and will not be described in detail here.

[0316] Figure 23It is a block diagram of a video generation device shown according to an exemplary embodiment. Refer to Figure 23 , the device includes a display unit 2301 and a generation unit 2302.

[0317] The display unit 2301 is configured to execute in response to a video creation request for an object, and display a video creation interface of the object;

[0318] The display unit 2301 is further configured to execute in the video creation interface, display a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category, and the material upload entry corresponding to the target material category is used to upload materials belonging to the target material category, and different object categories are associated with different material categories;

[0319] The generation unit 2302 is configured to execute based on the materials uploaded through a plurality of material upload entries, and generate a video associated with the object.

[0320] When the device provided by the embodiment of the present disclosure needs to generate a video associated with an object, a plurality of target material categories associated with the object category of the object and corresponding material upload entries are provided in the video creation interface. The materials uploaded through the material upload entry belong to the target material category. Since different object categories are associated with different material categories, different material upload entries will be provided for different objects, thereby guiding the user to upload materials belonging to the target material category, without the user having to decide and screen which type of materials to use by themselves, reducing the user's operation burden, and being beneficial to improving the efficiency of video generation. And, since the material category of the uploaded material is associated with the object category of the object, the adaptability of the material to the object is improved, which is beneficial to ensuring that the generated video has a stronger association with the object, thereby improving the accuracy of video generation.

[0321] In a possible implementation manner, refer to Figure 24 , the object is a store, and the video creation interface further displays a plurality of items provided by the store. The plurality of material upload entries include an item material upload entry and a store material upload entry; the device further includes a setting unit 2303, which is configured to execute:

[0322] In response to a selection operation on any one of the plurality of items, determine the selected target item;

[0323] Based on the item material upload entry, obtain the item material of the target item;

[0324] Based on the store material upload entry, obtain the store material of the store;

[0325] The generation unit 2302 is configured to execute:

[0326] Edit the item material and store material to obtain a first video, which is associated with the store and the target item.

[0327] In a possible implementation, refer to Figure 24 , the display unit 2301 is configured to execute:

[0328] Display the store interface of the store, where the store interface includes a video creation option and multiple candidate items provided by the store;

[0329] Based on the selection operation on at least one of the multiple candidate items, determine the selected candidate item;

[0330] In response to the trigger operation on the video creation option, display the video creation interface, and the video creation interface displays the selected candidate item.

[0331] In a possible implementation, refer to Figure 24 , the device further includes a setting unit 2303, which is configured to execute:

[0332] Based on the image upload operation performed on the video creation interface, obtain a reference image, and the reference image includes a person;

[0333] Based on multiple material upload entrances, obtain materials;

[0334] The generation unit 2302 is configured to execute:

[0335] Based on the materials and the reference image, generate a second video, which is associated with the object, and the second video includes a virtual image corresponding to the person in the reference image.

[0336] In a possible implementation, refer to Figure 24 , the device further includes a setting unit 2303, which is configured to execute:

[0337] Based on the configuration information setting operation performed on the video creation interface, obtain video configuration information, which is used to indicate at least one of the style, background music, size, playing duration, or dubbing tone of the video;

[0338] Based on multiple material upload entrances, obtain materials;

[0339] The generation unit 2302 is configured to execute:

[0340] Process the materials according to the video configuration information to obtain a third video, which is associated with the object, and the third video conforms to the video configuration information.

[0341] In a possible implementation, refer to Figure 24, the video configuration information includes a reference voice, and the reference voice is used to indicate the dubbing timbre of the video; a setting unit 2303, configured to perform:

[0342] Obtain a reference voice based on a voice upload operation performed on the video creation interface;

[0343] A generation unit 2302, configured to perform:

[0344] Dub the material according to the timbre of the reference voice to obtain a third video, and the dubbing timbre of the third video is the same as that of the reference voice.

[0345] In a possible implementation manner, see Figure 24 , the apparatus further includes:

[0346] The generation unit 2302 is further configured to generate a description text of the video based on the materials uploaded through multiple material upload ports, and the description text is used to describe the video;

[0347] A publishing unit 2304, configured to publish the video carrying the description text in response to a publishing operation on the video.

[0348] In a possible implementation manner, see Figure 24 , the publishing unit 2304 is configured to perform:

[0349] Display a publishing interface of the video, and the publishing interface includes a description text and publishing options;

[0350] In response to an editing operation on the description text, display the description text after being edited;

[0351] In response to a triggering operation on the publishing option, publish the video carrying the edited description text.

[0352] In a possible implementation manner, see Figure 24 , the apparatus further includes a task management unit 2305, configured to perform:

[0353] Display a video generation task of an object, where the video generation task refers to generating a video associated with the object based on the materials uploaded through multiple material upload ports;

[0354] If the video is successfully generated and the video has been published, in response to a triggering operation on the video generation task, display the video interface of the video; or, if the video is not successfully generated, in response to a triggering operation on the video generation task, display the video creation interface.

[0355] In a possible implementation manner, see Figure 24 , the apparatus further includes a task management unit 2305, configured to perform:

[0356] Displays each created video generation task and the status of each video generation task. The status includes an unpublished status, a published status, a generating status, and a failed status. The unpublished status means that the video has been successfully generated and not published. The published status means that the video has been successfully generated and published.

[0357] In a possible implementation, referring to Figure 24 , the task management unit 2305 is configured to perform at least one of the following:

[0358] Displays the generation progress in the area where the video generation task is in the generating status;

[0359] Displays the reason for failure in the area where the video generation task is in the failed status;

[0360] Displays the number of unpublished videos in the area where the video generation task is in the unpublished status. Among them, the number of videos generated by any video generation task is at least one.

[0361] In a possible implementation, referring to Figure 24 , the device further includes a detection unit 2306, which is configured to perform:

[0362] Detects the materials uploaded based on multiple material upload entrances to obtain a detection result, and the detection result indicates whether the material belongs to the target material category;

[0363] The generation unit 2302 is configured to perform:

[0364] If the detection result indicates that the material belongs to the target material category, obtains the video associated with the object based on the material.

[0365] In a possible implementation, referring to Figure 24 , the device further includes:

[0366] The prompt unit 2307 is configured to perform: if the detection result indicates that the material does not belong to the target material category, display a prompt message, and the prompt message is used to prompt that the currently uploaded material does not belong to the target material category and re-upload the material belonging to the target material category.

[0367] Regarding the device in the above embodiments, the specific ways in which each unit performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0368] The embodiments of the present disclosure provide an electronic device, which includes: a processor and a memory for storing executable instructions of the processor. Among them, the processor is configured to execute the instructions to implement the video generation method as described above.

[0369] In some embodiments, the electronic device includes a terminal. Figure 25 FIG. 2500 is a block diagram of a terminal 2500 shown according to an exemplary embodiment. The terminal 2500 may be a portable mobile terminal, such as: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a notebook computer or a desktop computer. The terminal 2500 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

[0370] The terminal 2500 includes a processor 2501 and a memory 2502.

[0371] The processor 2501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 2501 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor 2501 may also include a main processor and a co-processor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the co-processor is a low-power processor for processing data in the standby state. The memory 2502 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 2502 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 2502 is used to store at least one program code, and the at least one program code is used to be executed by the processor 2501 to implement the video generation method provided in the method embodiments of the present disclosure.

[0372] In some embodiments, the terminal 2500 may further optionally include: a peripheral device interface 2503 and at least one peripheral device. The processor 2501, the memory 2502, and the peripheral device interface 2503 may be connected through a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 2503 through a bus, signal lines, or a circuit board. Optionally, the peripheral device includes at least one of: a radio frequency circuit 2504, a display screen 2505, a camera assembly 2506, an audio circuit 2507, and a power supply 2508.

[0373] The peripheral device interface 2503 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 2501 and the memory 2502. In some embodiments, the processor 2501, the memory 2502, and the peripheral device interface 2503 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 2501, the memory 2502, and the peripheral device interface 2503 can be implemented on a separate chip or circuit board, and this embodiment does not limit this.

[0374] The radio frequency circuit 2504 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 2504 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 2504 converts an electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 2504 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so on. The radio frequency circuit 2504 can communicate with other devices through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: a metropolitan area network, each generation of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 2504 may further include a circuit related to NFC (Near Field Communication), and this application does not limit this.

[0375] The display screen 2505 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 2505 is a touch display screen, the display screen 2505 also has the ability to collect touch signals on or above the surface of the display screen 2505. The touch signals can be input as control signals to the processor 2501 for processing. At this time, the display screen 2505 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 2505, which is provided on the front panel of the terminal 2500; in other embodiments, there may be at least two display screens 2505, which are respectively provided on different surfaces of the terminal 2500 or are in a folded design; in other embodiments, the display screen 2505 may be a flexible display screen, which is provided on the curved surface or the folding surface of the terminal 2500. Even further, the display screen 2505 can also be set to an irregular non-rectangular shape, that is, an irregular-shaped screen. The display screen 2505 can be prepared using materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0376] The camera module 2506 is used to collect images or videos. Optionally, the camera module 2506 includes a front camera and a rear camera. The front camera is provided on the front panel of the terminal 2500, and the rear camera is provided on the back of the terminal 2500. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth camera, a wide-angle camera, and a telephoto camera respectively, to achieve the function of background blurring by fusing the main camera and the depth camera, panoramic shooting by fusing the main camera and the wide-angle camera, and VR (Virtual Reality) shooting function or other fused shooting functions. In some embodiments, the camera module 2506 may further include a flash. The flash can be a single-color temperature flash or a two-color temperature flash. A two-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0377] The audio circuit 2507 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals for input to the processor 2501 for processing, or input to the radio frequency circuit 2504 to implement voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 2500. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert the electrical signals from the processor 2501 or the radio frequency circuit 2504 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into audible sound waves for humans, but also convert electrical signals into inaudible sound waves for humans for uses such as ranging. In some embodiments, the audio circuit 2507 may further include a headphone jack.

[0378] The power supply 2508 is used to supply power to each component in the terminal 2500. The power supply 2508 may be alternating current, direct current, a disposable battery or a rechargeable battery. When the power supply 2508 includes a rechargeable battery, the rechargeable battery may support wired charging or wireless charging. The rechargeable battery may also be used to support fast charging technology.

[0379] Those skilled in the art can understand that Figure 25 the structure shown in

[0380] does not constitute a limitation on the terminal 2500, and may include more or fewer components than shown in the figure, or combine some components, or adopt different component arrangements.

[0381] In an exemplary embodiment, there is also provided a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the steps in the above video generation method. For example, the computer-readable storage medium may be a ROM (Read Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0382] Other embodiments of the present disclosure will be readily apparent to those skilled in the art in view of the specification and practice of the disclosure herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0383] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A video generation method, characterized in that, The method includes: Displaying an object interface of an object, the object interface being used to display the object, and the object interface including detailed information of the object and a video creation option; In response to a trigger operation on the video creation option in the object interface, displaying a video creation interface of the object; In the video creation interface, displaying a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category, the material upload entry corresponding to the target material category being used to upload materials belonging to the target material category, and different object categories being associated with different material categories; Generating a video associated with the object based on the materials uploaded through the plurality of material upload entries.

2. The video generation method according to claim 1, wherein The object is a store, and the video creation interface further displays a plurality of items provided by the store, and the plurality of material upload entries include an item material upload entry and a store material upload entry; the method further includes: In response to a selection operation on any one of the plurality of items, determining a selected target item; Based on the item material upload entry, obtaining item materials of the target item; Based on the store material upload entry, obtaining store materials of the store; The generating a video associated with the object based on the materials uploaded through the plurality of material upload entries includes: Editing the item materials and the store materials to obtain a first video, the first video being associated with the store and the target item.

3. The video generation method according to claim 2, wherein The displaying an object interface of an object includes: Displaying a store interface of the store, the store interface including a video creation option and a plurality of candidate items provided by the store; Based on a selection operation on at least one of the plurality of candidate items, determining a selected candidate item, and the video creation interface displays the candidate item selected in the store interface.

4. The video generation method according to claim 1, wherein The method further includes: Based on an image upload operation performed in the video creation interface, obtaining a reference image, and the reference image includes a person; Based on the plurality of material upload entries, obtaining the materials; The generating a video associated with the object based on the materials uploaded through the plurality of material upload entries includes: Based on the materials and the reference image, generating a second video, the second video being associated with the object and including a virtual image corresponding to the person in the reference image.

5. The video generation method according to claim 1, wherein The method further includes: Based on a configuration information setting operation performed in the video creation interface, obtaining video configuration information, the video configuration information being used to indicate at least one of the style, background music, size, playing duration, or dubbing timbre of the video; Based on the plurality of material upload entries, obtaining the materials; The generating a video associated with the object based on the materials uploaded through the plurality of material upload entries includes: Processing the materials according to the video configuration information to obtain a third video, the third video being associated with the object and conforming to the video configuration information.

6. The video generation method according to claim 5, wherein The video configuration information includes a reference voice, and the reference voice is used to indicate the dubbing timbre of the video. The operation of setting based on the configuration information in the video creation interface to obtain video configuration information includes: Obtaining the reference voice based on the voice upload operation performed in the video creation interface; Processing the material according to the video configuration information to obtain a third video, including: Dubbing the material according to the timbre of the reference voice to obtain the third video, and the dubbing timbre of the third video is the same as that of the reference voice.

7. The video generation method according to claim 1, wherein The method further includes: Generating a description text for the video based on the materials uploaded through multiple material upload entrances, and the description text is used to describe the video; Responding to the publishing operation of the video, publishing the video carrying the description text.

8. The video generation method according to claim 7, wherein The responding to the publishing operation of the video and publishing the video carrying the description text includes: Displaying a publishing interface for the video, and the publishing interface includes the description text and publishing options; Responding to the editing operation on the description text and displaying the edited description text; Responding to the triggering operation on the publishing option and publishing the video carrying the edited description text.

9. The video generation method according to claim 1, wherein The method further includes: Displaying a video generation task for the object, where the video generation task refers to generating a video associated with the object based on the materials uploaded through multiple material upload entrances; If the video is successfully generated and has been published, responding to the triggering operation on the video generation task and displaying the video interface of the video; or, if the video is not successfully generated, responding to the triggering operation on the video generation task and displaying the video creation interface.

10. The video generation method according to claim 1, wherein The method further includes: Displaying each created video generation task and the status of each video generation task, where the status includes an unpublished status, a published status, a generating status, and a failed status. The unpublished status means that the video is successfully generated but not published, and the published status means that the video is successfully generated and has been published.

11. The video generation method according to claim 10, wherein The method further includes at least one of the following: Displaying a generation progress in the area where the video generation task in the generating status is located; Displaying a failure reason in the area where the video generation task in the failed status is located; Displaying the number of unpublished videos in the area where the video generation task in the unpublished status is located, where the number of videos generated by any video generation task is at least one.

12. The video generation method according to claim 1, wherein The method further includes: Detecting the materials uploaded through multiple material upload entrances to obtain a detection result, and the detection result indicates whether the materials belong to the target material category; Generating a video associated with the object based on the materials uploaded through multiple material upload entrances, including: If the detection result indicates that the materials belong to the target material category, generating a video associated with the object based on the materials.

13. The video generation method according to claim 12, characterized in that The method further includes: If the detection result indicates that the material does not belong to the target material category, a prompt message is displayed, and the prompt message is used to prompt that the currently uploaded material does not belong to the target material category, and a material belonging to the target material category is re-uploaded.

14. A video generation device, characterized in that, The device includes: A display unit configured to execute an object interface of a display object, the object interface being used to display the object, and the object interface including detailed information of the object and video creation options; The display unit is further configured to execute in response to a trigger operation on the video creation option in the object interface, and display a video creation interface of the object; The display unit is further configured to execute in the video creation interface, display a plurality of target material categories associated with the object category of the object and a material upload entry corresponding to each target material category, and the material upload entry corresponding to the target material category is used to upload a material belonging to the target material category, and different object categories are associated with different material categories; A generation unit configured to execute a video associated with the object based on the materials uploaded through the plurality of material upload entries.

15. An electronic device, characterized in that, The electronic device includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the instructions to implement the video generation method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is enabled to execute the video generation method according to any one of claims 1 to 13.

17. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the video generation method according to any one of claims 1 to 13.

Images