Media processing method and device, equipment and medium

Abstract

The invention provides a media processing method and device, equipment and a medium, and a specific implementation mode of the method comprises the steps that to-be-modified original media and guiding information are acquired, and the guiding information comprises text information used for modifying the original media; determining a first area to be modified in the original media; based on the guide information, obtaining reference features used for modifying the original media; and based on the reference feature, modifying the first area in the original media to obtain a target media. According to the embodiment, the to-be-modified area in the original media can be modified according to the guide information and the willingness of the user, the media modification effect is improved, and the user experience is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of image processing technology, and in particular, to a media processing method, apparatus, device, and medium. Background Art

[0002] With the continuous development of artificial intelligence technology, artificial intelligence technology is increasingly applied to the field of media processing. At present, it has been realized that the media (such as images or videos, etc.) desired by users can be generated through artificial intelligence models. However, in some cases, the media needs to be modified. For example, there are errors in the generated media, or the user wants to adjust the content of some areas in the media. In related technologies, it is usually necessary to manually modify the media, which is not only time-consuming and labor-intensive, but also difficult to meet the needs of users. Therefore, a media processing method is currently needed. Summary of the invention

[0003] The embodiments of the present disclosure describe a media processing method, apparatus, device, and medium.

[0004] According to a first aspect, a method is provided, the method comprising: obtaining original media to be modified and guide information, the guide information comprising text information for modifying the original media; determining a first area to be modified in the original media; based on the guide information, obtaining reference features for modifying the original media; based on the reference features, modifying the first area in the original media to obtain target media.

[0005] According to a second aspect, a media processing device is provided, which includes: a first acquisition unit, configured to acquire original media to be modified and guide information, wherein the guide information includes text information for modifying the original media; a determination unit, configured to determine a first area to be modified in the original media; a second acquisition unit, configured to acquire a reference feature for modifying the original media based on the guide information; and a modification unit, configured to modify the first area in the original media based on the reference feature to obtain a target media.

[0006] According to a third aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method as described above in any one of the first aspect is implemented.

[0007] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute any one of the methods in the first aspect.

[0008] According to a fifth aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, any one of the methods in the first aspect is implemented.

[0009] According to a media processing solution provided by an embodiment of the present disclosure, the original media to be modified and the guide information are obtained, the first area to be modified in the original media is determined, the reference features for modifying the original media are obtained based on the guide information, and the first area in the original media is modified based on the reference features to obtain the target media. Thus, the area to be modified in the original media can be modified according to the user's wishes based on the guide information, thereby improving the media modification effect and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a schematic diagram of a media processing scenario according to an exemplary embodiment;

[0011] Figure 2 A schematic diagram of an exemplary system architecture for applying an embodiment of the present disclosure;

[0012] Figure 3 is a flow chart of a media processing method according to an exemplary embodiment of the present disclosure;

[0013] Figure 4 is a scene schematic diagram of a media processing method according to an exemplary embodiment of the present disclosure;

[0014] Figure 5 is a schematic diagram of a scenario of another media processing method according to an exemplary embodiment of the present disclosure;

[0015] Figure 6 is a block diagram of a media processing device according to an exemplary embodiment of the present disclosure;

[0016] Figure 7 It is a schematic block diagram of an electronic device provided in some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0018] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0019] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0020] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0021] The technical solution provided by the present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the inventions. It should also be noted that, for ease of description, only the parts related to the relevant inventions are shown in the accompanying drawings. It should be noted that, in the absence of conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0022] With the continuous development of artificial intelligence technology, artificial intelligence technology is increasingly used in the field of media processing. At present, it has been realized that media (such as images, videos or animations, etc.) that meet the user's wishes are generated through artificial intelligence models. However, in some cases, the media needs to be modified. For example, there are errors in the generated media, or the user wants to adjust the content of some areas in the media. Especially for some media that include text (such as advertisements, posters, packaging designs, etc.), it is usually necessary to modify the text included in the media, such as adding text, replacing text, or deleting text. In the related art, it is necessary to manually modify the media, which is not only time-consuming and labor-intensive, but the effect of the modification is also difficult to meet the needs of users, especially some artistic text areas that are more naturally combined with image and video backgrounds.

[0023] The present disclosure provides a media processing solution, which obtains the original media to be modified and the guide information, determines the first area to be modified in the original media, obtains the reference features for modifying the original media based on the guide information, and modifies the first area in the original media based on the reference features to obtain the target media. Thus, the area to be modified in the original media can be modified according to the guide information and the user's wishes, thereby improving the media modification effect and user experience.

[0024] See also Figure 1 , is a schematic diagram of a media processing scenario according to an exemplary embodiment.

[0025] like Figure 1 As shown, take an image A including text as an example, image A includes the text "Happy Chinese New Year", and the user wants to change the "Chinese New Year" in the text to "New Year's Day". First, the user can import image A to the media processing client through the terminal device, and input a piece of guidance information B, which can include text information for describing the key semantics of image A, and the target text "New Year's Day" to be modified. The key semantics can be the preferred semantics that the user pays more attention to and wants to highlight.

[0026] Next, the media processing client can display an operation interface for image A to the user through the terminal device. The user can select the area C1 of the text "Spring Festival" in image A through the operation interface. For example, the area of ​​the text "Spring Festival" can be smeared, or the area of ​​the text "Spring Festival" can be framed. The media processing client can obtain the area C1 selected by the user as the area to be modified. The area C1 can also be blocked by a mask to obtain a mask image D, and the mask image D only displays the area C2 in image A except the area C1.

[0027] Then, the media processing client can first use the pre-trained model M1 to extract features from area C2 in image A except area C1, and obtain the media style reference feature Z1 of area C2. And use the pre-trained model M2 to extract semantic features from the guide information B, and obtain the semantic reference feature Z2. Then use the pre-trained model M3 to fuse the media style reference feature Z1 and the semantic reference feature Z2 to obtain the reference feature Z. Optionally, the media processing client can also use the pre-trained text style extraction model M4 to extract text style feature Z3 from the text in area C1. In addition, the media processing client can also obtain the target text "New Year's Day" to be generated from the guide information B.

[0028] Finally, the target text "New Year's Day", reference feature Z and text style feature Z3 can be input into the image generation model M5, so that the image generation model M5 generates the text "New Year's Day" in area C1 of the mask image D based on the text feature Z1, reference feature Z and text style feature Z3 to replace the text "Spring Festival" in image A, thereby obtaining the target image E. The target image E includes the text "Happy New Year's Day", and, except for the modified target text "New Year's Day", other areas in the target image E are the same as image A, and the text style of the target text "New Year's Day" is the same as the text style of the text "Spring Festival" in image A.

[0029] It should be noted that Figure 1 The embodiment is described by taking the media processing client directly processing image A as an example. In other embodiments, the media processing client can also transmit the information of image A, guide information B, mask image D and target text "New Year's Day" to the media processing server deployed on the service platform through the network, and the media processing server modifies image A to obtain target image E, and transmits target image E to the media processing client through the network to provide target image E to the user. For details, see Figure 2 .

[0030] Figure 2 The figure is a schematic diagram of an exemplary system architecture for applying an embodiment of the present disclosure.

[0031] like Figure 2 As shown, the system architecture 200 may include a terminal device 202, a network 203 and a server 204. It should be understood that Figure 2 The number or type of terminal devices, networks, and servers in the embodiment are merely illustrative. Any number or type of terminal devices, networks, and servers may be provided as required.

[0032] The network 203 is used to provide a medium for communication links between terminal devices and servers. The network 203 may include various connection types, such as wired or wireless communication links or optical fiber cables, etc.

[0033] The terminal device 202 is installed with a media processing client, and the terminal device 202 can interact with the server through the network 203 to receive or send requests or information, etc. The terminal device 202 can be various electronic devices, including but not limited to smart phones, tablet computers, laptops, desktop computers, and smart wearable devices, etc.

[0034] The server 204 is provided with a media processing server. The server 204 can store and analyze the received data, and can also send control commands or requests to the terminal device or other servers. The server can provide media processing services in response to the user's service request. It can be understood that a server can provide one or more services, and the same service can also be provided by multiple servers.

[0035] based on Figure 2 In the system architecture shown, in the embodiment of the present disclosure, the user 201 can input the original media and the guide information to be processed through the terminal device 202, and select the first area to be modified in the original media through the terminal device 202. Then, the terminal device 202 can transmit the original media, the guide information and the information of the first area to the server 204 through the network 203. After receiving the original media, the guide information and the information of the first area, the server 204 can modify the first area in the original media based on the original media, the guide information and the information of the first area to obtain the target media. Finally, the server 204 can return the target media to the terminal device 202 through the network 203, so that the user 201 can view and save the target media through the terminal device 202.

[0036] The present disclosure will be described in detail below in conjunction with specific embodiments.

[0037] Figure 3 The flowchart of a media processing method according to an exemplary embodiment is shown. The method can be applied to a media processing client or a media processing server. In this embodiment, the media processing client is installed in a terminal device, which may include but is not limited to a mobile terminal device such as a smart phone, a smart wearable device, a tablet computer, a laptop computer, and a desktop computer. The media processing server is deployed in a service platform, which can be implemented as any device, server, or device cluster with computing and processing capabilities. The method may include the following steps:

[0038] like Figure 3 As shown, in step 301, the original medium and boot information to be modified are obtained.

[0039] In this embodiment, the media involved may include but are not limited to images, videos, animated images, animations, etc., and this embodiment does not limit the specific types of media. The original media may be media that needs to be partially modified, and the user needs to modify the specified area in the original media. For example, the original media may include objects, animals, or people, and the user needs to modify the specified object area, the specified animal area, or the specified person area in the original media. For another example, the original media may include text, and the user needs to modify the specified text area in the original media by adding text, replacing text, or deleting text.

[0040] The guidance information may include text information for modifying the original media, and the original media may be modified according to the text information. For example, the text information may be the target content for modifying the first area. The guidance information may also include text description information for describing the original media. The text description information may be text information input by the user for describing the key semantics in the original media. The key semantics may be the preferred semantics that the user pays more attention to and wants to highlight. For example, the guidance information may also include the following information: "A digital <5> 18 as the central visual poster, balloon-textured fonts, e-commerce platform scenes, candy colors, clay textures, cartoon scenes, and exaggerated compositions" (see Figure 4 Embodiment). The content to be modified may be marked with a <> symbol (the <> symbol used here is only an example, and the embodiment does not limit the specific method for marking the content to be modified). It can be understood that the embodiment does not limit the specific form and content of the guidance information.

[0041] In step 302, a first region to be modified in the original medium is determined.

[0042] In this embodiment, the first area to be modified in the original media may be an area including the object to be modified. For example, if the object to be modified is a specified object, the first area may be an area including the specified object. For another example, if the object to be modified is a specified text, the first area may be an area including the specified text. In one implementation, the guidance information may also include a description of the object to be modified or the first area. Based on the description of the object to be modified or the first area in the guidance information, the original media may be parsed to determine the first area.

[0043] In another implementation, the media processing client can also display an operation interface for the original media to the user through the terminal device, and the original media is displayed in the operation interface. The user can select the area to be modified from the original media through the operation interface. For example, the user can select the area to be modified by a box selection operation, or can also perform a smear operation in the area to be modified. It can be understood that this embodiment does not limit the specific operation method of the user selecting the first area to be modified. Then, the media processing client can determine the first area selected in the original media according to the user's operation on the operation interface.

[0044] In step 303, based on the guidance information, reference features for modifying the original media are obtained.

[0045] In this embodiment, in some implementations, the guide information may include text information for modifying the original media. In other implementations, the guide information may further include description content of the original media. Therefore, reference features for modifying the original media may be obtained based on the guide information. The reference features may include some semantic information in the original media that needs to be focused on, that is, information that the user hopes to retain after modifying the original media. In one implementation, the guide information may be extracted with a pre-trained first model to obtain semantic reference features, and the semantic reference features may be directly used as reference features for modifying the original media. In another implementation, on the one hand, the guide information may be extracted with a pre-trained first model to obtain semantic reference features. On the other hand, the media style features of the second area other than the first area in the original media may be extracted with a pre-trained second model to obtain media style reference features. Specifically, the first area in the original media may be firstly shielded with a mask to obtain mask media, and the unshielded area in the mask media is the second area. The mask media may be input into the second model so that the second model extracts the media style features of the second area. Finally, the semantic reference features and the media style reference features are fused to obtain the reference features. Due to the present embodiment, not only the semantics described by the guide information is considered, but also the media style features of the area outside the area to be modified in the original media are considered, and the area to be modified is modified in combination with the context of the area to be modified in the original media, so that the modified area is better integrated with the surrounding areas, and the effect of modifying the media is improved.

[0046] Among them, the first model used to process the guidance information can be a model that can process natural language and extract semantic features in natural language. For example, the first model can be a large language model, etc. This embodiment does not limit the specific type of the first model. The second model used to process the second area in the original media can be a model that can extract media features. For example, the second model can be a variational autoencoder, etc. This embodiment does not limit the specific type of the second model. In addition, a neural network model that can fuse features can be used to fuse semantic reference features and media style reference features to obtain reference features.

[0047] In step 304, based on the reference features, the first region in the original media is modified to obtain the target media.

[0048] In this embodiment, the first region in the original media may be modified according to the reference feature to obtain the target media. Specifically, in one implementation, the reference feature and the original media with the first region blocked may be directly input into the media generation model, so that the media generation model generates the target media modified according to the first region in the original media based on the reference feature.

[0049] In another implementation, the original media includes text content, such as text, etc. The first area is in the text area corresponding to the text content, and the guide information also includes the target text content to be modified for the first area. The modification to the first area can be to modify the original text content in the first area to the target text content. The text style information corresponding to the text content to be modified in the original media can be first obtained. For example, a style extraction model can be used to process the text in the first area to extract the style information of the text in the first area. The style information of the text can include, for example, but is not limited to the font of the text, the color of the text, the size of the text, the decoration around the text, etc. It can be understood that the specific type of the style information of the text is not limited in this embodiment. Then, based on the reference feature, the original text content in the first area is modified according to the text style information. Specifically, the target text content to be modified for the first area can be first obtained, and the target text content can be replaced and modified with the original text content of the first area by the media generation model based on the target text content, the reference feature and the text style information to obtain the target media. Among them, the media generation model can be an artificial intelligence model that can generate media. For example, the media generation model can be a diffusion model, etc. It can be understood that this embodiment does not limit the specific type of the media generation model.

[0050] A media processing method provided by the present disclosure obtains an original media to be modified and guiding information, determines a first area to be modified in the original media, obtains reference features for modifying the original media based on the guiding information, and modifies the first area in the original media based on the reference features to obtain a target media. Thus, it is possible to modify the area to be modified in the original media according to the guiding information according to the user's意愿, improving the modification effect of the media and enhancing the user experience.

[0051] It should be noted that although in the above embodiments, the operations of the method of the embodiments of the present disclosure are described in a specific order, however, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can change the execution order. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0052] Next, a complete and specific application example is used to schematically illustrate the solution and effect of the present disclosure.

[0053] Reference Figure 4 , taking an image as an example, image 401 is the original media, and the text "618" is included in image 401. The user hopes to modify "618" to "518". Therefore, first, the user can input image 401 into the media processing client and input the following guiding information: "A poster centered visually on the number <5>18, balloon-textured font, e-commerce platform scene, candy colors, terracotta texture, cartoon scene, exaggerated composition". The guiding information includes the target text <5> to be modified and the text description information of some semantic features of image 401 by the user.

[0054] Next, the user can select the text "6" in image 401 that needs to be modified through the operation interface provided by the media processing client. The media processing client can block the area corresponding to the text "6" in image 401 to obtain image 402. Image 403 can be generated according to image 402 and the above guiding information. In image 403, the text "5" replaces the text "6" in image 401.

[0055] Refer to Figure 5 , still taking an image as an example, image 501 is the original media, and the text "Back to school and new season" is included in image 501. The user hopes to modify "换" to "焕" and enlarge "学". Therefore, first, the user can input image 501 into the media processing client and input guiding information that can indicate enlarging the character "学" and modifying "换" to "焕".

[0056] Next, the user can select the words "学" and "换" in the image 501 that need to be modified through the operation interface provided by the media processing client. The media processing client can obscure the areas corresponding to the words "学" and "换" in the image 501 to obtain the image 502. The image 503 can be generated based on the image 502 and the above guiding information. In the image 503, the word "焕" replaces the word "换" in the image 501, and the word "学" is enlarged.

[0057] Corresponding to the foregoing embodiment of the media processing method, the present disclosure also provides an embodiment of a media processing device.

[0058] As Figure 6 shown, Figure 6 FIG. is a block diagram of a media processing device according to an exemplary embodiment of the present disclosure. The device includes: a first acquisition unit 601, a determination unit 602, a second acquisition unit 603, and a modification unit 604.

[0059] Among them, the first acquisition unit 601 is configured to acquire the original media to be modified and guiding information, and the guiding information includes text description information for modifying the original media.

[0060] The determination unit 602 is configured to determine the first area to be modified in the original media.

[0061] The second acquisition unit 603 is configured to acquire a reference feature for modifying the original media based on the guiding information.

[0062] The modification unit 604 is configured to modify the first area in the original media based on the reference feature to obtain the target media.

[0063] In some embodiments, the determination unit 602 is configured to: display an operation interface for the original media, and determine the area selected from the original media through the operation interface as the first area.

[0064] In other embodiments, the second acquisition unit 603 is configured to: perform semantic feature extraction on the guiding information by using a pre-trained first model to obtain a semantic reference feature, and determine the reference feature based on the semantic reference feature.

[0065] In other embodiments, the second acquisition unit 603 determines the reference feature based on the semantic reference feature in the following manner: perform media style feature extraction on the second area other than the first area in the original media by using a pre-trained second model to obtain a media style reference feature, and perform feature fusion on the semantic reference feature and the media style reference feature to obtain the reference feature.

[0066] In other embodiments, the original media includes text content, the first area is in a text area corresponding to the text content, and the text information used to modify the original media also includes target text content to be modified for the first area, wherein the modification to the first area includes modifying the original text content in the first area to the target text content.

[0067] In other implementations, the modification unit 604 is configured to: obtain text style information corresponding to the original text content to be modified in the first area, and based on the reference features and in accordance with the text style information, modify the original text content in the first area into target text content.

[0068] In other embodiments, the modification unit 604 modifies the original text content in the first area into target text content based on reference features and text style information in the following manner: utilizing a media generation model to replace the original text content in the first area with the target text content based on the target text content, reference features and text style information to obtain target media.

[0069] In some other implementations, the guide information may further include text description information for describing at least part of the semantics of the original media.

[0070] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiment scheme of the present disclosure. A person of ordinary skill in the art can understand and implement it without paying creative labor.

[0071] Reference below Figure 7 , Figure 7 A schematic block diagram of an electronic device provided for some embodiments of the present disclosure. The electronic device 920 is suitable for implementing the media processing method provided in the embodiments of the present disclosure, for example. The electronic device 920 may be a terminal device, etc., and may be used to implement a client or a server. The electronic device 920 may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. It should be noted that Figure 7The electronic device 920 shown is only an example and does not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0072] like Figure 7 As shown, the electronic device 920 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 921, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 922 or a program loaded from a storage device 928 into a random access memory (RAM) 923. In the RAM 923, various programs and data required for the operation of the electronic device 920 are also stored. The processing device 921, the ROM 922, and the RAM 923 are connected to each other via a bus 924. An input / output (I / O) interface 925 is also connected to the bus 924.

[0073] Typically, the following devices may be connected to the I / O interface 925: an input device 926 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 927 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 928 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 929. The communication device 929 may allow the electronic device 920 to communicate with other electronic devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 920 is shown to have various devices, but it should be understood that it is not required to implement or possess all of the devices shown, and the electronic device 920 may alternatively implement or possess more or fewer devices. Figure 7 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0074] According to an embodiment of the present disclosure, the above-mentioned media processing method can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the above-mentioned media processing method. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 929, or installed from the storage device 928, or installed from the ROM 922. When the computer program is executed by the processing device 921, the functions defined in the media processing method provided in the embodiment of the present disclosure can be implemented.

[0075] The embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method provided by the present disclosure.

[0076] It should be noted that the computer-readable medium described in the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0077] Computer program code for performing the operations of the disclosed embodiments may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0078] Each embodiment in the present disclosure is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the storage medium and computing device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0079] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present disclosure can be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0080] The specific implementation methods described above further describe the purpose, technical solutions and beneficial effects of the embodiments of the present disclosure in detail. It should be understood that the above description is only the specific implementation method of the embodiments of the present disclosure, and is not intended to limit the scope of protection of the present invention. Any modification, equivalent replacement, improvement, etc. made on the basis of the technical solution of the present disclosure shall be included in the scope of protection of the present invention.

Claims

1. A media processing method, the method comprising: Acquire original media to be modified and guide information, wherein the guide information includes text information used to modify the original media; Determining a first region to be modified in the original media; Based on the guidance information, obtaining reference features for modifying the original media; Based on the reference feature, the first region in the original media is modified to obtain target media.

2. The method according to claim 1, wherein determining the first area to be modified in the original media comprises: Displaying an operation interface for the original media; An area selected from the original medium through the operation interface is determined as the first area.

3. The method according to claim 1, wherein: The acquiring, based on the guide information, a reference feature for modifying the original medium comprises: Extracting semantic features from the guidance information using a pre-trained first model to obtain semantic reference features; Based on the semantic reference feature, the reference feature is determined.

4. The method according to claim 3, wherein: The determining the reference feature based on the semantic reference feature includes: Using a pre-trained second model, extracting media style features from a second region other than the first region in the original media to obtain media style reference features; The semantic reference feature and the media style reference feature are subjected to feature fusion to obtain the reference feature.

5. The method according to claim 1, wherein: The original media includes text content; the first area is in a text area corresponding to the text content; the text information used to modify the original media includes target text content to be modified in the first area; wherein the modification to the first area includes modifying the original text content in the first area to the target text content.

6. The method according to claim 5, wherein: The modifying the first region in the original medium based on the reference feature includes: Acquire text style information corresponding to the original text content to be modified in the first area; Based on the reference features and in accordance with the text style information, the original text content in the first region is modified into the target text content.

7. The method according to claim 6, wherein: The modifying the original text content in the first area into the target text content based on the reference feature and according to the text style information includes: The media generation model is used to replace and modify the original text content of the first region with the target text content based on the target text content, the reference features and the text style information to obtain the target media.

8. The method according to any one of claims 1-7, wherein the guide information further comprises text description information for describing at least part of the semantics of the original media.

9. A media processing device, comprising: A first acquisition unit is configured to acquire original media to be modified and guide information, wherein the guide information includes text information for modifying the original media; a determining unit, configured to determine a first region to be modified in the original medium; a second acquisition unit, configured to acquire a reference feature for modifying the original medium based on the guide information; The modification unit is configured to modify the first region in the original media based on the reference feature to obtain a target media.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 8.

12. An electronic device comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method according to any one of claims 1 to 8 is implemented.

Images