Media resource processing method and device, equipment and storage medium

Abstract

The invention provides a media resource processing method and device, equipment and a storage medium, and the method comprises the steps: firstly displaying at least one candidate recommendation object determined based on a target display object in a target display region when a selection operation for the target display region of a target media resource is received, the target display object is obtained by performing object recognition on a target display area; and then, when a trigger operation for any recommendation object in the at least one candidate recommendation object is received, replacing the target display object with the recommendation object to obtain an updated media resource. Visibly, according to the embodiment of the invention, after the user selects any display area of the target media resource, the at least one candidate recommendation object can be automatically displayed for the target display object in the area, so that rapid editing of the target media resource is realized, and the editing efficiency of the target media resource is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method, apparatus, device, and storage medium for processing media resources. Background Art

[0002] With the continuous development of data processing technology, media resource editing functions are attracting more and more attention from users. Currently, users mainly use media resource editing software (such as video editing software) to edit media resources. Because such software requires high editing skills, users need to go through a long period of learning and extensive practice to complete the editing of media resources, resulting in low editing efficiency.

[0003] Therefore, how to improve the editing efficiency of media resources is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] In order to solve the above technical problems, the embodiments of the present disclosure provide a media resource processing method, apparatus, device and storage medium. Specifically, after a user selects any display area of ​​a target media resource, at least one candidate recommendation object can be automatically displayed for the target display object in the area to achieve rapid editing of the target media resource, thereby improving the editing efficiency of the target media resource.

[0005] In a first aspect, the present disclosure provides a method for processing media resources, the method comprising:

[0006] In response to a selection operation on a target display area of ​​a target media resource, displaying at least one candidate recommendation object determined based on a target display object in the target display area; wherein the target display object is obtained by performing object recognition on the target display area;

[0007] In response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, the target display object in the target media resource is replaced with the target recommendation object to obtain an updated media resource.

[0008] In an optional embodiment, in response to a selection operation on a target display area of ​​a target media resource, displaying at least one candidate recommendation object determined based on a target display object in the target display area includes:

[0009] In response to a selection operation on a target display area of ​​a target media resource, performing object recognition on the target display area to obtain an object recognition result; wherein the object recognition result includes object description content and a target display object;

[0010] The object description content and at least one candidate recommended object determined based on the target display object are displayed.

[0011] In an optional implementation, displaying the object description content and at least one candidate recommended object determined based on the target display object includes:

[0012] Displaying the object description content; wherein the object description content includes stylized description content;

[0013] In response to a triggering operation on a target interactive control, a style material generation model corresponding to the stylized description content is called to generate at least one object material based on the target display object as a candidate recommended object for the target display object; wherein the style material generation model is trained using sample materials corresponding to the stylized description content;

[0014] Display candidate recommended objects for the target display object.

[0015] In an optional embodiment, in response to the selection operation of the target display area of ​​the target media resource, performing object recognition on the target display area to obtain the object recognition result includes:

[0016] In response to a selection operation for a target display area of ​​a target media resource, background removal is performed on the target display area, edges of a target display object within the target display area are identified, and the target display object is segmented from the target display area based on the edges, thereby obtaining an object recognition result for the target display area.

[0017] In an optional embodiment, the target media resource is a target animation or a target video, and in response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, replacing the target display object in the target media resource with the target recommendation object to obtain an updated media resource includes:

[0018] In response to a triggering operation on a target recommended object among the at least one candidate recommended object, replacing the target display object in the target media resource with the target recommended object to obtain a replaced frame;

[0019] Perform frame interpolation processing on the replaced frame to obtain updated media resources.

[0020] In an optional implementation, the method further includes:

[0021] In response to the export triggering operation for the updated media resource, frame supplementation is performed on the updated media resource according to the target frame rate information to obtain a frame-supplemented media resource, and the frame-supplemented media resource is exported to a target storage space.

[0022] In an optional implementation, the method further includes:

[0023] In response to a soundtrack generation operation for a target media resource, a soundtrack file corresponding to the target media resource is generated based on the soundtrack description information input by the user and / or the content tag information corresponding to the target media resource; wherein the soundtrack file includes sound effects and / or background music, and the soundtrack file is used to configure the updated media resource.

[0024] In a second aspect, the present disclosure further provides a media resource processing device, the device comprising:

[0025] A display module is configured to, in response to a selection operation on a target display area of ​​a target media resource, display at least one candidate recommendation object determined based on a target display object in the target display area; wherein the target display object is obtained by performing object recognition on the target display area;

[0026] The replacement module is configured to, in response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, replace the target display object in the target media resource with the target recommendation object to obtain an updated media resource.

[0027] In a third aspect, the present disclosure provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium. When the instructions are executed on a terminal device, the terminal device implements the above method.

[0028] In a fourth aspect, the present disclosure provides a media resource processing device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method when executing the computer program.

[0029] In a fifth aspect, the present disclosure provides a computer program product, which includes a computer program / instructions, and the computer program / instructions implement the above method when executed by a processor.

[0030] The technical solution provided by the embodiments of the present disclosure has at least the following advantages compared with the prior art:

[0031] The disclosed embodiment provides a media resource processing method, which, upon receiving a selection operation for a target display area of ​​a target media resource, first displays at least one candidate recommendation object determined based on a target display object in the target display area, the target display object being obtained by object recognition of the target display area; then, upon receiving a trigger operation for any one of the at least one candidate recommendation objects, replaces the target display object with the recommended object to obtain an updated media resource. It can be seen that, after the user selects any display area of ​​the target media resource, the disclosed embodiment can automatically display at least one candidate recommendation object for the target display object in the area, so as to achieve rapid editing of the target media resource, thereby improving the editing efficiency of the target media resource. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0033] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0034] Figure 1 A flowchart of a media resource processing method provided by an embodiment of the present disclosure;

[0035] Figure 2 A flowchart of another media resource processing method provided by an embodiment of the present disclosure;

[0036] Figure 3 A schematic diagram of a target media resource provided by an embodiment of the present disclosure;

[0037] Figure 4 A schematic diagram of another target media resource provided by an embodiment of the present disclosure;

[0038] Figure 5 A schematic diagram of an updated media resource provided in an embodiment of the present disclosure;

[0039] Figure 6 A schematic diagram of the structure of a media resource processing device provided in an embodiment of the present disclosure;

[0040] Figure 7 A structural diagram of a media resource processing device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0043] With the continuous development of data processing technology, media resource editing functions are attracting more and more attention from users. Currently, users mainly use media resource editing software (such as video editing software) to edit media resources. Because such software requires high editing skills, users need to go through a long period of learning and extensive practice to complete the editing of media resources, resulting in low editing efficiency.

[0044] To this end, an embodiment of the present disclosure provides a media resource processing method. Specifically, upon receiving a selection operation for a target display area of ​​a target media resource, at least one candidate recommendation object determined based on a target display object in the target display area is first displayed, where the target display object is obtained by performing object recognition on the target display area. Then, upon receiving a trigger operation for any one of the at least one candidate recommendation objects, the target display object is replaced with the recommended object to obtain an updated media resource. It can be seen that, after the user selects any display area of ​​the target media resource, the embodiment of the present disclosure can automatically display at least one candidate recommendation object for the target display object in the area, so as to achieve rapid editing of the target media resource, thereby improving the editing efficiency of the target media resource.

[0045] Specifically, the present disclosure provides a method for processing media resources. Figure 1 , is a flow chart of a media resource processing method provided by an embodiment of the present disclosure, specifically including:

[0046] S101: In response to a selection operation on a target display area of ​​a target media resource, display at least one candidate recommendation object determined based on a target display object in the target display area.

[0047] The target display object is obtained by performing object recognition on the target display area.

[0048] The media resource processing method provided by the embodiments of the present disclosure can be applied to a client. Specifically, the client can be deployed on a terminal such as a smart phone, a tablet computer, or a desktop computer.

[0049] In the disclosed embodiment, the target media resource may include any animation, video, picture, etc. The target media resource may also be any design document. By circling and replacing any display area of ​​the media resource, the media resource can be quickly edited.

[0050] In the disclosed embodiments, the target display area may be any display area circled by the user on the target media resource, such as the left area of ​​an image, the right area of ​​any video frame in a video clip, etc. The selection operation for the target display area may include a circle-and-confirm operation on the target display area, etc., to trigger the display of candidate recommendation objects determined based on the target display object within the target display area.

[0051] In the embodiment of the present disclosure, the target display object may be one or more display objects obtained by performing object recognition on the target display area. After the target display object is recognized, at least one candidate recommendation object may be determined based on the target display object and the at least one candidate recommendation object may be displayed.

[0052] In actual applications, since the target display object has characteristic information such as style, material, and style, after identifying the target display object, at least one candidate recommendation object can be determined based on any characteristic information of the target display object. Specifically, a recommendation object with a high degree of similarity to a certain characteristic information of the target display object can be determined as a candidate recommendation object corresponding to the target display object, such as shoes of different colors that are both cartoon-style like the circled shoes.

[0053] For example, assuming that the target media resource is an animation of a little tiger wishing a happy new year, when a user selects the lower limb area of ​​the little tiger image, the lower limb area of ​​the little tiger image is firstly identified as an object, for example, target display objects such as pants and shoes can be obtained, and then at least one candidate recommendation object is determined based on the pants and shoes respectively, such as trousers, shorts, long boots, sneakers, etc.

[0054] S102: In response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, the target display object in the target media resource is replaced with the target recommendation object to obtain an updated media resource.

[0055] In an embodiment of the present disclosure, during the process of displaying at least one candidate recommendation object corresponding to the target display object, a trigger operation for a target recommendation object among the at least one candidate recommendation object may be received, and the target media resource may be updated based on the target recommendation object.

[0056] In the embodiment of the present disclosure, the target recommendation object can be any recommendation object among at least one candidate recommendation object. The triggering operation for the target recommendation object can include a click operation on the target recommendation object, and can also include an interactive operation of dragging the target recommendation object to the target display area, etc.

[0057] In actual applications, since different types of devices have different screen refresh rates, videos or animations can only be displayed smoothly on the device screen when the frame rate of the video or animation meets the screen refresh rate requirements of the device.

[0058] Therefore, in order to enable the updated media resource to adapt to different screen refresh rates, the embodiment of the present disclosure may further perform a frame interpolation operation on the target media resource during the process of replacing the target display object in the target media resource with the target recommendation object.

[0059] Specifically, when the target media resource is a target animation or a target video, when a trigger operation is received for a target recommendation object among at least one candidate recommendation object, the target recommendation object is first used to replace the target display object in the target media resource to obtain a replaced frame image; then, frame interpolation processing is performed based on the replaced frame image to obtain an updated media resource.

[0060] It can be seen that after the target display object in the target media resource is replaced with the target recommendation object, the embodiment of the present disclosure performs frame interpolation processing on the entire replaced frame image containing the target recommendation object, so that the display of the updated media resource is smoother and can adapt to different screen refresh rates.

[0061] In practical applications, technologies such as automatic frame-filling algorithms can be used to analyze information such as the movement patterns of target media resources and the posture dynamics of target display objects, so as to make the updated media resources appear as smooth as possible visually.

[0062] In the media resource processing method provided by the embodiment of the present disclosure, upon receiving a selection operation for a target display area of ​​a target media resource, at least one candidate recommendation object determined based on a target display object in the target display area is first displayed, the target display object being obtained by performing object recognition on the target display area; then, upon receiving a trigger operation for any one of the at least one candidate recommendation objects, the target display object is replaced with the recommended object to obtain an updated media resource. It can be seen that the embodiment of the present disclosure can automatically display at least one candidate recommendation object for the target display object in any display area of ​​the target media resource after the user selects the area, so as to realize rapid editing of the target media resource, thereby improving the editing efficiency of the target media resource.

[0063] In an optional implementation, the target media resources can be generated based on 3D reverse modeling technology. Specifically, 3D reverse modeling technology is an algorithm that generates a three-dimensional model that can be used by the editor by constructing a geometry generator and a texture generator, and merging the geometric model generated by the geometry generator and the texture generated by the texture generator.

[0064] The construction method of the geometry generator may include: first, using the deep 3D conditional generative model to represent the 3D model as a deformable triangular tetrahedron (i.e., a geometric shape) and a signed distance field for each vertex to improve the differentiability and texture of the 3D model; then, deforming the geometric shape by moving the vertices to achieve a differentiable recovery from the tetrahedron to the 3D model surface. It can be seen that by using the deep 3D conditional generative model, the geometry generator can generate 3D models of arbitrary topology and category.

[0065] The method for constructing a texture generator may include: extracting a three-dimensional wireless mesh using a deep 3D conditional generative model and querying the texture field at surface points to obtain color.

[0066] After generating a 3D model and texture based on the geometric generator, the generated textured 3D model is converted to a 2D image through a differentiable grid, and a 2D discriminator is used to distinguish the projected image and real image of the model generated by the generator, as well as the projected outline and real outline of the model generated by the generator.

[0067] Based on the above embodiments, the present disclosure also provides a method for processing media resources. Figure 2 FIG. 1 is a flow chart of another method for processing media resources provided by an embodiment of the present disclosure, the method comprising:

[0068] S201: In response to a selection operation on a target display area of ​​a target media resource, object recognition is performed on the target display area to obtain an object recognition result.

[0069] The object recognition result includes object description content and target display object.

[0070] In the embodiment of the present disclosure, when a selection operation for a target display area of ​​a target media resource is received, object recognition may be performed on the selected target display area based on image recognition technology to obtain an object recognition result.

[0071] In an embodiment of the present disclosure, the object recognition result may include the target display object and the object description content corresponding to the target display object, wherein the object description content is used to describe information such as the characteristics of the target display object. The object description content may include, for example, the stylized description content, material description content, style description content, etc. of the target display object, such as "cartoon" shoes, "long boots", etc.

[0072] In an optional implementation, in order to improve the quality of image edge recognition, when a selection operation for a target display area of ​​a target media resource is received, three image recognition technologies of different granularities may be used to perform object recognition on the target display area to obtain an object recognition result.

[0073] Specifically, when a selection operation for a target display area of ​​a target media resource is received, background removal is performed on the target display area, edges of a target display object within the target display area are identified, and the target display object is segmented from the target display area based on the edges to obtain an object recognition result for the target display area.

[0074] In practical applications, a background removal algorithm based on saliency detection can be used to more accurately identify the edge of the target display object so that the target display object can be extracted from the target display area later.

[0075] After identifying the edge of the target display object, the target display object can be processed at the element level using a deep learning-based image segmentation algorithm to segment the target display object from the target display area.

[0076] Furthermore, based on the background removal algorithm and image segmentation algorithm, technical means such as the Hongfan method are used to optimize the edge smoothness of the segmented target display object, further improving the accuracy of image edge recognition.

[0077] S202: Display the object description content and at least one candidate recommended object determined based on the target display object.

[0078] In the embodiment of the present disclosure, after obtaining the object description content and the target display object, the object description content and at least one candidate recommendation object determined based on the target display object may also be displayed.

[0079] In an optional implementation, after obtaining the object recognition result including the object description content and the target display object, the object description content may be displayed so that the user can understand the detailed information of the recognized target display object based on the object description content.

[0080] In the embodiment of the present disclosure, the object description content may include stylized description content corresponding to the target display object, wherein the stylized description content may be used to describe the style characteristics of the target display object, such as cartoon style, sketch style, etc.

[0081] like Figure 3 As shown, a schematic diagram of a target media resource provided by an embodiment of the present disclosure is shown. When a selection operation is received for a target display area 301, object recognition is performed on the target display area 301 to obtain a target display object and object description content, and object description content 302, such as a description content of the word "cartoon", is displayed in a text description area corresponding to the target media resource.

[0082] In an optional embodiment, in the process of displaying the object description content corresponding to the target display object, it is also possible to call a style material generation model corresponding to the stylized description content in response to a trigger operation on the target interactive control, and generate at least one object material based on the target display object as a candidate recommended object for the target display object.

[0083] In the disclosed embodiments, the style material generation model is trained using sample materials corresponding to stylized description content. Specifically, based on a pre-trained model, sample materials with a fixed style are input into the pre-trained model, and the pre-trained model is trained to generate object materials capable of generating a fixed style. The input of the style material generation model is the target display object obtained based on target display area identification, and the output is at least one object material.

[0084] like Figure 4 As shown, it is a schematic diagram of another target media resource provided by an embodiment of the present disclosure. A target interactive control 401 is set in the preset right area corresponding to the target media resource. When a click operation is received on the target interactive control 401, the style material generation model corresponding to the stylized description content "cartoon" is called, and at least one object material is generated based on the target display object 402 as a candidate recommendation object corresponding to the target display object 402, and the candidate recommendation object is displayed in the area below the style description content.

[0085] When a trigger operation is received for the target recommendation object 403 in the candidate recommendation object, the target display object 402 in the target media resource is replaced with the target recommendation object 403 to obtain an updated media resource. Figure 5 , which is a schematic diagram of an updated media resource provided by an embodiment of the present disclosure.

[0086] S203: In response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, the target display object in the target media resource is replaced with the target recommendation object to obtain an updated media resource.

[0087] It can be seen that after the user selects any display area of ​​the target media resource, the embodiment of the present disclosure can automatically display at least one candidate recommendation object for the target display object in the area to achieve rapid editing of the target media resource, thereby improving the editing efficiency of the target media resource.

[0088] In addition, since the embodiment of the present disclosure uses three image recognition technologies of different granularities to perform object recognition on the target display object in the target display area, the accuracy of the object recognition result can be further improved.

[0089] In actual applications, after completing the replacement update of the target media resource, you can also receive an export trigger operation for the updated media resource, perform frame interpolation on the updated media resource according to the target frame rate information, obtain the interpolated media resource, and export the interpolated media resource to the target storage space.

[0090] In the embodiment of the present disclosure, a material export control may be further provided on the display page of the target media resource, and the export triggering operation for the updated media resource may include a click operation on the material export control.

[0091] In an embodiment of the present disclosure, the target frame rate information can be determined based on the display refresh rate of the client, or based on the frame rate actually selected by the user. Specifically, upon receiving a user selection operation for any frame rate in at least one frame rate option, the frame rate is determined as the target frame rate information, and then the updated media resource is supplemented with frames according to the target frame rate information.

[0092] For example, assuming that the current frame rate of the updated media resource is 1 second and 20 frames, and the target frame rate information is 1 second and 30 frames, when the export trigger operation for the updated media resource is received, the updated media resource information is supplemented according to the target frame rate information to obtain the supplemented media resource, and the frame rate of the supplemented media resource is 1 second and 30 frames.

[0093] In the embodiment of the present disclosure, after the updated media resource is frame-interpolated to obtain the frame-interpolated media resource, the frame-interpolated media resource is exported to a target storage space, which may include a local hard disk storage space, a remote cloud storage space, etc.

[0094] It can be seen that the embodiment of the present disclosure can automatically perform frame interpolation on the updated media resources based on the frame rate information set by the user, so that the media resources after frame interpolation can meet the user's frame rate requirements, thereby further improving the user's media resource editing experience.

[0095] In order to further improve the user's media resource editing efficiency, the embodiment of the present disclosure can also automatically generate a music file corresponding to the target media resource based on the music description information input by the user and / or the content tag information corresponding to the target media resource when receiving a music generation operation for the target media resource.

[0096] In the embodiment of the present disclosure, before generating a target media resource, the user usually adds a content tag to the target media resource. Specifically, the content tag may include a component content tag, a style content tag, a scene content tag, etc. of the target media resource, such as a New Year scene content tag.

[0097] In the embodiment of the present disclosure, the soundtrack file may include sound effects and / or background music, and the soundtrack file may be used to configure the updated media resources. Specifically, the user may configure information such as the duration, segmentation, and BPM beat of the soundtrack file to further improve the editing efficiency of the media resources.

[0098] In actual applications, the music description information entered by the user and the content tag information of the target media resource can be input into the preset music model, and the music file can be automatically generated through the preset music model. Based on the generated music file, the user can configure the duration and BPM and other data of the music file to make the generated updated media resource more in line with the user's needs.

[0099] Based on the above method embodiment, the present disclosure further provides a media resource processing device. Reference 6 is a structural diagram of a media resource processing device provided in an embodiment of the present disclosure, and the device includes:

[0100] Display module 601 is configured to, in response to a selection operation on a target display area of ​​a target media resource, display at least one candidate recommendation object determined based on a target display object in the target display area; wherein the target display object is obtained by performing object recognition on the target display area;

[0101] The replacement module 602 is configured to, in response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, replace the target display object in the target media resource with the target recommendation object to obtain an updated media resource.

[0102] In an optional implementation manner, the display module includes:

[0103] an identification submodule, configured to, in response to a selection operation on a target display area of ​​a target media resource, perform object identification on the target display area to obtain an object identification result; wherein the object identification result includes object description content and a target display object;

[0104] The display submodule is configured to display the object description content and at least one candidate recommended object determined based on the target display object.

[0105] In an optional implementation manner, the display submodule is specifically configured to:

[0106] Displaying the object description content; wherein the object description content includes stylized description content;

[0107] In response to a triggering operation on a target interactive control, a style material generation model corresponding to the stylized description content is called to generate at least one object material based on the target display object as a candidate recommended object for the target display object; wherein the style material generation model is trained using sample materials corresponding to the stylized description content;

[0108] Display candidate recommended objects for the target display object.

[0109] In an optional implementation manner, the identification submodule is specifically configured to:

[0110] In response to a selection operation for a target display area of ​​a target media resource, background removal is performed on the target display area, edges of a target display object within the target display area are identified, and the target display object is segmented from the target display area based on the edges, thereby obtaining an object recognition result for the target display area.

[0111] In an optional implementation manner, the target media resource is a target animation or a target video, and the replacement module includes:

[0112] a replacement submodule, configured to, in response to a triggering operation on a target recommended object among the at least one candidate recommended object, replace the target display object in the target media resource with the target recommended object to obtain a replaced frame;

[0113] The frame-filling submodule is used to perform frame-filling processing on the replaced frame to obtain updated media resources.

[0114] In an optional embodiment, the device further includes:

[0115] The export module is used to respond to the export trigger operation for the updated media resource, perform frame interpolation on the updated media resource according to the target frame rate information to obtain the frame-interpolated media resource, and export the frame-interpolated media resource to the target storage space.

[0116] In an optional embodiment, the device further includes:

[0117] A generation module is used to respond to a soundtrack generation operation for a target media resource and generate a soundtrack file corresponding to the target media resource based on the soundtrack description information input by the user and / or the content tag information corresponding to the target media resource; wherein the soundtrack file includes sound effects and / or background music, and the soundtrack file is used to configure the updated media resource.

[0118] In the media resource processing device provided by the embodiment of the present disclosure, specifically, upon receiving a selection operation for a target display area for a target media resource, at least one candidate recommendation object determined based on a target display object in the target display area is first displayed, the target display object being obtained by object recognition of the target display area; then, upon receiving a trigger operation for any one of the at least one candidate recommendation objects, the target display object is replaced with the recommendation object to obtain an updated media resource. It can be seen that the embodiment of the present disclosure can automatically display at least one candidate recommendation object for the target display object in any display area of ​​the target media resource after the user selects the area, so as to realize rapid editing of the target media resource, thereby improving the editing efficiency of the target media resource.

[0119] In addition to the above-mentioned method and apparatus, the embodiments of the present disclosure further provide a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal device, the terminal device implements the media resource processing method described in the embodiments of the present disclosure.

[0120] The embodiments of the present disclosure further provide a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the media resource processing method described in the embodiments of the present disclosure is implemented.

[0121] In addition, the present disclosure also provides a media resource processing device, see Figure 7 As shown, this may include:

[0122] Processor 701, memory 702, input device 703 and output device 704. The number of processors 701 in the media resource processing device can be one or more. Figure 7In some embodiments of the present disclosure, the processor 701, the memory 702, the input device 703 and the output device 704 may be connected via a bus or other means, wherein: Figure 7 The bus connection is taken as an example.

[0123] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing of the media resource processing device by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The input device 703 can be used to receive input digital or character information, and to generate signal input related to user settings and function control of the media resource processing device.

[0124] Specifically in this embodiment, the processor 701 will load the executable files corresponding to the processes of one or more applications into the memory 702 according to the following instructions, and the processor 701 will run the applications stored in the memory 702, thereby realizing the various functions of the above-mentioned media resource processing device.

[0125] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0126] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A media resource processing method, characterized in that: include: In response to a selection operation on a target display area of ​​a target media resource, displaying at least one candidate recommendation object determined based on a target display object in the target display area; wherein the target display object is obtained by performing object recognition on the target display area; In response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, the target display object in the target media resource is replaced with the target recommendation object to obtain an updated media resource.

2. The method according to claim 1, characterized in that In response to the selection operation of the target display area of ​​the target media resource, displaying at least one candidate recommendation object determined based on the target display object in the target display area includes: In response to a selection operation on a target display area of ​​a target media resource, performing object recognition on the target display area to obtain an object recognition result; wherein the object recognition result includes object description content and a target display object; The object description content and at least one candidate recommended object determined based on the target display object are displayed.

3. The method according to claim 2, characterized in that The displaying of the object description content and at least one candidate recommendation object determined based on the target display object includes: Displaying the object description content; wherein the object description content includes stylized description content; In response to a triggering operation on a target interactive control, a style material generation model corresponding to the stylized description content is called to generate at least one object material based on the target display object as a candidate recommended object for the target display object; wherein the style material generation model is trained using sample materials corresponding to the stylized description content; Display candidate recommended objects for the target display object.

4. The method according to claim 2, characterized in that In response to the operation of selecting the target display area of ​​the target media resource, performing object recognition on the target display area to obtain an object recognition result includes: In response to a selection operation for a target display area of ​​a target media resource, background removal is performed on the target display area, edges of a target display object within the target display area are identified, and the target display object is segmented from the target display area based on the edges, thereby obtaining an object recognition result for the target display area.

5. The method according to claim 1, characterized in that The target media resource is a target animation or a target video, and in response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, replacing the target display object in the target media resource with the target recommendation object to obtain an updated media resource includes: In response to a triggering operation on a target recommended object among the at least one candidate recommended object, replacing the target display object in the target media resource with the target recommended object to obtain a replaced frame; Perform frame interpolation processing on the replaced frame to obtain updated media resources.

6. The method according to claim 1, characterized in that The method further comprises: In response to the export triggering operation for the updated media resource, frame supplementation is performed on the updated media resource according to the target frame rate information to obtain a frame-supplemented media resource, and the frame-supplemented media resource is exported to a target storage space.

7. The method according to claim 1, characterized in that The method further comprises: In response to a soundtrack generation operation for a target media resource, a soundtrack file corresponding to the target media resource is generated based on the soundtrack description information input by the user and / or the content tag information corresponding to the target media resource; wherein the soundtrack file includes sound effects and / or background music, and the soundtrack file is used to configure the updated media resource.

8. A media resource processing device, characterized in that: The device comprises: A display module is configured to, in response to a selection operation on a target display area of ​​a target media resource, display at least one candidate recommendation object determined based on a target display object in the target display area; wherein the target display object is obtained by performing object recognition on the target display area; The replacement module is configured to, in response to a triggering operation on a target recommendation object among the at least one candidate recommendation object, replace the target display object in the target media resource with the target recommendation object to obtain an updated media resource.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device implements the method according to any one of claims 1 to 7.

10. A media resource processing device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program / instruction, and when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images