Poster generation method and device

Abstract

The invention discloses a poster generation method and device, and belongs to the technical field of image processing, and the poster generation method comprises the steps: obtaining a target object in a first image and target image feature data of the target object; obtaining target identification information associated with the first image, wherein the target identification information can indicate the source of the first image; and performing image generation processing on the target object, the target image feature data and the target identification information according to a target display layout to obtain a target poster image.

Description

Technical Field

[0001] The present application belongs to the field of image processing technology, and in particular, relates to a poster generation method and device. Background Art

[0002] Some applications, such as game apps, will design and generate poster images to convey important information to users based on the concise and clear content presentation characteristics of poster images, while stimulating user interest through innovative and eye-catching design features. Traditional application poster design methods often rely on hand-drawn or limited templates, requiring a lot of manual design and typesetting work, which is time-consuming, laborious, inefficient, lacking flexibility and innovation, and it is difficult to ensure the quality of poster images. Summary of the invention

[0003] To this end, this application discloses the following technical solutions:

[0004] A poster generation method, comprising:

[0005] Obtaining a target object in a first image and target image feature data of the target object;

[0006] Obtaining target identification information associated with the first image, where the target identification information can indicate a source of the first image;

[0007] The target object, the target image feature data and the target identification information are processed for image generation according to a target display layout to obtain a target poster image.

[0008] Optionally, obtaining a target object in the first image and target image feature data of the target object includes:

[0009] Acquire a target interface image of a target application of the electronic device during operation as the first image, wherein the target interface image is an image frame including a target object;

[0010] Segmenting a first foreground image including only the target object from the target interface image; and

[0011] Target image feature data of the first foreground image is extracted.

[0012] Optionally, obtaining a target interface image of a target application of the electronic device during operation includes at least one of the following:

[0013] Monitoring the running process of the target application, and capturing the application interface presenting the target event as the target interface image;

[0014] Monitoring the behavior data of the target object in the application interface of the target application, and capturing the application interface where the target object performs the target behavior as the target interface image;

[0015] Monitoring the operation data of the target user acting on the electronic device, responding to the target operation of the target user, and intercepting the current application interface corresponding to the target operation as the target interface image;

[0016] An application interface of a target application at a target moment during its operation is captured as the target interface image.

[0017] Optionally, obtaining target identification information associated with the first image includes at least one of the following:

[0018] Obtaining first source information of the first image, and obtaining target identification information matching the first source information;

[0019] Obtaining target identification information associated with the target object in the first image;

[0020] Obtaining target identification information associated with a target user who performs a triggering operation for triggering generation of the first image;

[0021] The image content of the first image is obtained, and the image content is input into a first generation model to generate the target identification information.

[0022] Optionally, obtaining target identification information associated with the first image includes at least one of the following:

[0023] In the case where the first image is from a game application, obtaining a second image associated with the first image, the second image including at least one of an application icon, an application name, and a version of the game application;

[0024] In the case where the first image comes from a content playback application, the target identification information includes file information of a multimedia file to which the first image belongs and / or application information of the content playback application;

[0025] In the case where the first image comes from a live broadcast application, the target identification information includes description information of a live broadcast signal to which the first image belongs and / or application information of the live broadcast application;

[0026] In the case that the first image comes from a conference application, the target identification information includes conference theme information of the conference to which the first image belongs and / or application information of the conference application.

[0027] Optionally, performing image generation processing on the target object, the target image feature data and the target identification information according to a target display layout includes:

[0028] generating a third image having a first transparency based on the target image feature data;

[0029] fusing the target object with the third image according to the target display layout to obtain a fourth image; and

[0030] The target layer generated based on the target identification information is fused with the fourth image according to the target display layout to obtain the target poster image.

[0031] Optionally, the method further includes at least one of the following:

[0032] generating a fifth image with a second transparency based on the target image feature data, fusing the target object with the third image and the fifth image according to the target display layout to obtain the fourth image, wherein the first transparency and the second transparency are the same or different, and the fifth image has a different color value from the third image;

[0033] Obtain second source information of the target object and / or attribute information of the target identification information, and determine display layout information among the target object, the target image feature data and the target identification information based on the second source information and / or the attribute information.

[0034] Optionally, when the target identification information is a second image associated with the first image, the method further includes at least one of the following:

[0035] Segmenting a second foreground image including an application icon and / or an application name from the second image as a target layer;

[0036] performing rounding processing on the segmented second foreground image based on pixel information of the second image;

[0037] The second image is scaled.

[0038] Optionally, performing image generation processing on the target object, the target image feature data and the target identification information according to a target display layout includes:

[0039] Processing the target object, the target image feature data and the target identification information into a target user intention;

[0040] A target generation model is used to perform a generation processing operation based on the target user intention to obtain the target poster image.

[0041] A poster generating device, comprising:

[0042] A first acquisition module, used to obtain a target object in a first image and target image feature data of the target object;

[0043] A second acquisition module, configured to obtain target identification information associated with the first image, wherein the target identification information can indicate a source of the first image;

[0044] The generating module is used to perform image generating processing on the target object, the target image feature data and the target identification information according to the target display layout to obtain a target poster image.

[0045] An electronic device, comprising:

[0046] Memory, used to store computer instruction sets;

[0047] A processor is used to implement the poster generation method provided in any one of the above items by executing a computer instruction set.

[0048] A storage medium carries one or more computer instruction sets, and when the one or more computer instruction sets are executed by an electronic device, the electronic device can implement any of the poster generation methods described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0050] Figure 1 It is a flowchart of the poster generation method provided by this application;

[0051] Figure 2 This is an example of an application interface screenshot of a game highlight moment provided by this application;

[0052] Figure 3 It is a flow chart of the process of generating the target poster image provided by the present application;

[0053] Figure 4 is an example of the generated target poster image provided by this application;

[0054] Figure 5 is another flow chart of the process of generating the target poster image provided by the present application;

[0055] Figure 6 It is a structural diagram of the poster generating device provided by the present application;

[0056] Figure 7 It is a structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] The embodiment of the present application provides a poster generation method and device, which is used to solve at least some of the technical problems in a series of problems such as the time-consuming and laborious, low efficiency, lack of flexibility and innovation, and difficulty in ensuring the quality and effect of the poster image when generating posters due to the fact that the poster design relies on manual drawing or limited templates. The poster generation method provided in the embodiment of the present application can be applied to electronic devices in many general or special computing device environments or configurations, such as: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor devices, etc.

[0059] See also Figure 1 As shown in the method flow chart, the poster generation method provided in the embodiment of the present application may at least include the following steps 101 to 103, and these steps are described in detail below.

[0060] Step 101: Obtain a target object in a first image and target image feature data of the target object.

[0061] The first image, used as the basic image required to generate the poster image, may be, but is not limited to, a game interface image, a video playback screenshot, a video conference screenshot, a live broadcast interface screenshot, etc. Further, optionally, it may be a game interface image of a highlight moment, a video playback interface screenshot, a video conference interface screenshot, a live broadcast interface screenshot, such as a game interface image of a highlight moment formed by key events and wonderful performances during the game, a video playback interface screenshot of a movie character or game character releasing a big move, presenting a classic posture, or performing a specific action, etc.

[0062] Some applications or users have a need to generate a poster image to convey important information to the user based on the concise and clear content presentation characteristics of the poster image. When there is a need to generate a poster image for a target application, optionally, a target interface image of the target application of the electronic device during operation can be first obtained as the first image.

[0063] The target application may be a front-end application of the electronic device, or may be a designated application, such as a game application, a video playback application, a live broadcast application, a conference application, etc.

[0064] The target interface image is an image frame that includes the target object (such as an image frame that includes the highlight moment of the target object), and may specifically be a screenshot of the application interface of the target object during the running of the target application, and the application interface screenshot may be a screenshot image obtained by taking a screenshot of the target application, or may be a rendered image obtained from the bottom layer of the electronic device through an API (Application Programming Interface), such as an image rendered by a GPU (Graphics Processing Unit).

[0065] Optionally, the target object is a main object or element in the first image, such as an element or character in the foreground of the first image, and may specifically be, but not limited to, a game character in a game interface image, a protagonist in a video playback screenshot, or a speaker in a video conference screenshot, etc. The number of the target objects in the first image may be one or more, such as multiple elements or characters in the foreground area of ​​the first image, and is not limited thereto and may be determined according to actual application conditions.

[0066] The target image features of the target object may include, but are not limited to, the main color tone, theme style and / or image saturation of the target object in the first image.

[0067] After obtaining the target interface image of the target application of the electronic device during operation as the first image, a first foreground image that only includes the target object can be further segmented from the target interface image; and target image feature data of the first foreground image can be extracted as target image feature data of the target object.

[0068] Specifically, based on image segmentation technology, the first image can be segmented into foreground and background, and the foreground content of the first image including only the target object can be extracted to remove background interference and obtain the first foreground image, thereby highlighting the visual effect on the target object (such as the target object of a wonderful moment), and facilitating the subsequent image fusion and personalized processing for generating poster images.

[0069] On this basis, the extracted first foreground image may be further analyzed and extracted for image features such as main color tone, image style and / or saturation to obtain target image feature data of the first foreground image.

[0070] The main color of an image usually refers to the dominant color in the image and represents the overall color style of the image.

[0071] Taking the analysis of the main color tone of the first foreground image as an example, optionally, a clustering analysis can be performed on the RGBA (Red-Green-Blue-Alpha, red, green, blue and transparency channels) color features of the image pixels in the first foreground image based on a clustering algorithm to determine the main color components in the first foreground image, thereby providing a scientific basis for the extraction of the main color tone. At the same time, optionally, the main color tone analysis can be performed in combination with color psychology and application (such as game application) design principles to provide guidance for subsequent poster image generation processing.

[0072] In implementation, more advanced deep learning models and algorithms may be optionally used to improve the accuracy and efficiency of foreground extraction to obtain a more accurate first foreground image. At the same time, image enhancement and denoising techniques may be combined to remove noise and interference in the extracted first foreground image, thereby improving the quality and clarity of the first foreground image.

[0073] Step 102: Obtain target identification information associated with the first image, where the target identification information can indicate a source of the first image.

[0074] The target identification information may specifically be, but is not limited to, an application icon ICON such as a game ICON image, a live broadcast theme (such as basketball, football, tennis), a conference theme (such as a seminar on...), a poster or title of a played video (such as a movie poster or movie title), etc. As long as it is identification information associated with the first image and can indicate the source of the first image, it can be used as the target identification information in the embodiments of the present application.

[0075] The source of the first image indicated by the target identification information may be, but is not limited to, a game, a movie, a conference, a live broadcast, etc. from which the first image comes, depending on the actual application scenario.

[0076] Step 103: Perform image generation processing on the target object, the target image feature data and the target identification information according to the target display layout to obtain a target poster image.

[0077] Posters of different types of applications usually have different poster generation requirements, which may include but are not limited to layout requirements in any one or more of the following aspects:

[0078] a. Display position of the target identification information in the poster

[0079] For example, game posters need to place the game manufacturer in the middle of the front layer, some movie posters may need to place the movie title at the top or bottom, some anchor posters need to place the theme name on the left, and so on.

[0080] b. The foreground-background relationship, primary-secondary relationship, layer-level relationship, etc. between the target object and the image generated based on the target image feature data of the target object.

[0081] For example, when performing image fusion to generate a poster, the target object needs to be used as the background and the image generated based on the target image feature data of the target object as the foreground, or the target object needs to be used as the foreground and the image generated based on the target image feature data of the target object as the background, etc.

[0082] c. Symmetrical relationship and hierarchical relationship between the target object and the target identification information

[0083] For example, when performing image fusion to generate a poster, it is necessary to superimpose the target object and the target identification information according to a hierarchical relationship.

[0084] Based on this, the target display layout may include the display layout required by the actual layout requirements of the target application in any one or more of the above aspects. In implementation, a matching target display layout may be set based on the actual layout requirements of the target application in any one or more of the above aspects.

[0085] On the basis of step 102, this step 103 obtains a target poster image by performing image generation processing on the target object, the target image feature data and the target identification information according to the target display layout.

[0086] The image generation process may include, but is not limited to, generating a corresponding image based on the target image feature data, and performing image fusion processing on the generated image, the target object, and the target identification information. The image fusion process may further include, but is not limited to, image tiling, layered processing based on hierarchical relationships, etc. This part will be described in detail later.

[0087] To summarize, the poster generation method of the embodiment of the present application obtains the target object in the first image and the target image feature data of the target object, obtains the target identification information associated with the first image (the target identification information can indicate the source of the first image), and performs image generation processing on the target object, the target image feature data and the target identification information according to the target display layout, thereby realizing automatic and intelligent dynamic generation of poster images, without relying on manual drawing or limited templates, and without a large amount of manual design and typesetting work, thereby improving the generation efficiency of poster images and saving time.

[0088] At the same time, since there is no need to rely on manual drawing or limited templates, the limitations of manual design or limited templates in typesetting are eliminated. When generating posters, in addition to taking the target object as the basis, the target image feature data and target identification information are introduced into the poster generation to ensure that the generated poster has a consistent design style and standard, thereby ensuring the quality and effect of the poster image.

[0089] In an optional embodiment, obtaining a target interface image of a target application of an electronic device during operation (as the first image) may be implemented, but is not limited to, as at least one of the following 1-1 to 1-4:

[0090] 1-1. Monitor the running process of the target application, and capture the application interface presenting the target event as the target interface image.

[0091] The target event may be, but is not limited to, a key event or a highlight event during the operation of the target application, and may be an event caused or triggered by a user operation, or an event triggered by the application system of the target application, without limitation.

[0092] Taking the target applications as game applications, video playback applications, live broadcast applications or conference applications as examples, the target events may be, but are not limited to, key events or highlight moments such as game players killing monsters, defeating opponents, game players entering specific places or locations, game players receiving system rewards / standing on the podium during the running of the game application, or events such as movie characters releasing big moves, presenting classic postures or performing specific actions during the playback of movie videos, or events such as live broadcasting to specific process nodes, generating important interactions with the audience, and the number of viewers reaching a set number during the running of the live broadcast application, or events such as the speaker introducing a new product, performing specific gestures or actions during the running of the conference application.

[0093] During implementation, corresponding monitors such as event monitors can be pre-deployed, and the deployed monitors can be used to monitor the running process of the target application based on preset event detection strategies. When the target event is detected, the screenshot / screenshot function is called to capture the application interface presenting the target event as the target interface image.

[0094] See also Figure 2 , provides an example of a game highlight moment screenshot of the moment when the player kills or defeats the opponent.

[0095] 1-2. Monitor the behavior data of the target object in the application interface of the target application, and capture the application interface where the target object performs the target behavior as the target interface image.

[0096] The target behavior is a key behavior or an important behavior performed by the target object, and the type of the key behavior or the important behavior may depend on the type of the target application. For example, it may be an action performed by a game player to kill a monster or defeat an opponent, or an action performed by a movie character when releasing a big move or performing a specific action.

[0097] In the present implementation 1-2, the behavior data of the target object in the application interface of the target application can be monitored based on the deployed monitor, and in response to monitoring the target object implementing the target behavior, the screenshot / screen capture function is called to capture the application interface where the target object implements the target behavior as the target interface image.

[0098] 1-3. Monitor the operation data of the target user on the electronic device, respond to the target operation of the target user, and capture the current application interface corresponding to the target operation as the target interface image.

[0099] The target user may be, but is not limited to, a game player, a video viewer, a live broadcast host, a conference speaker, etc., depending on the current target application.

[0100] The operation data of the target user on the electronic device may be, but is not limited to, keyboard / mouse-based operations, gesture operations, and / or voice operations triggered by the target user.

[0101] The target operation may be an operation performed by the target user on the electronic device to trigger taking a screenshot / screenshot of the current application interface of the target application.

[0102] In this embodiment, when the target user believes that the content currently output by the target application is suitable for generating a poster, an instruction for triggering a screenshot / screenshot can be given by applying a target operation, such as giving a specific gesture or voice instruction to trigger the system to take a screenshot / screenshot of the current application interface, or the screenshot / screenshot operation can be directly performed manually to capture the current application interface corresponding to the target operation, and the captured current application interface can be used as the target interface image.

[0103] 1-4. Capturing the application interface of the target application at a target moment during its operation as the target interface image.

[0104] The target moment may be, but is not limited to, a highlight moment during the operation of the target application (such as the moment when a game player receives a reward or triggers a promotion), or a moment when the application reaches a critical / important process node (such as the moment when a conference speaker begins or completes an explanation of an important conference content, or the moment when the number of live broadcast participants reaches a set number), or a moment when a specific time interval is reached as determined by timing, etc.

[0105] In this implementation, the monitor can be used to monitor the target moment of the target application during operation based on a preset monitoring strategy. In response to monitoring the target moment, the application interface of the target application at the target moment is captured as the target interface image.

[0106] In this embodiment, the target interface images obtained by the above-mentioned methods are all used as the first image to participate in the subsequent poster generation process.

[0107] This embodiment obtains the target interface image used as the first image through corresponding monitoring and screenshot / screenshot processing, which can provide a basis for subsequent poster generation processing. In addition, this embodiment monitors the target application from any one or more dimensions such as events presented during the operation of the target application, the behavior of the target object in the application interface, the operations of the target user on the electronic device, and the target moment during the operation of the target application. When the monitoring target is reached, the application interface of the target application is screenshoted as the first image, which can meet the diversified poster generation needs in various scenarios during the operation of the target application, improve the flexibility and innovation of poster generation, and further improve the user experience.

[0108] In an optional embodiment, step 102 in the method provided in the present application, i.e., obtaining target identification information associated with the first image, may be implemented, but is not limited to, as including at least one of the following 2-1 to 2-4:

[0109] 2-1. Obtain first source information of the first image, and obtain target identification information matching the first source information.

[0110] The first source information of the first image may be, but is not limited to, the application, manufacturer, project, device (such as a server) and / or corresponding copyright holder to which the first image belongs. For example, which game, movie, live program, conference, etc. the first application comes from.

[0111] The target identification information matched with the first source information may be, but is not limited to, identification information of the application, manufacturer, project, device (such as a server) and / or copyright holder to which the first image belongs. For example, identification information representing a game manufacturer or a game name, identification information representing a movie name or copyright holder, identification information representing a live broadcast platform and / or live broadcast theme, identification information representing a conference application and / or conference theme, etc.

[0112] This embodiment directly takes the source of the first image as the starting point, and obtains the target identification information required in step 102 by obtaining the target identification information matching the first source information of the first image.

[0113] 2-2. Obtain target identification information associated with the target object in the first image.

[0114] The target identification information associated with the target object in the first image may specifically include, but is not limited to, identification information of an application, a project, a corresponding copyright holder, etc. associated with / to which the target object belongs.

[0115] For example, the game name or game manufacturer to which a game character belongs, the movie name or copyright owner to which a movie character belongs, the live broadcast project to which a live broadcast host belongs, or the conference schedule to which a conference speaker belongs, etc.

[0116] This embodiment takes the target object in the first image as the starting point, and obtains the target identification information associated with the target object in the first image as the target identification information required in step 102. It is easy to understand that in this embodiment, the target identification information associated with the target object in the first image, such as the identification information of the application, project, copyright holder, etc. associated with / to which the target object belongs, is used to characterize the source of the first image.

[0117] 2-3. Obtain target identification information associated with a target user who performs a triggering operation to trigger generation of the first image.

[0118] The target user may be, but is not limited to, a game player, a video viewer, a live broadcast host, a conference speaker, etc., depending on the current target application.

[0119] The triggering operation for generating the first image may be an operation applied by the target user to the electronic device to trigger a screenshot / screenshot (such as a voice operation in which the user issues a "please take a screenshot" command), or a screenshot / screenshot operation directly and manually performed by the target user.

[0120] The target identification information associated with the target user may include, but is not limited to, the identification name and / or account information of the target user, such as a nickname and / or game account of a game player.

[0121] This embodiment takes the target user who implements the triggering operation of triggering the generation of the first image as the starting point, and obtains the target identification information associated with the target user to obtain the target identification information required in step 102. In this embodiment, the target identification information such as the identification name and / or account information of the target user is used to characterize the source of the first image.

[0122] 2-4. Obtain image content of the first image, and input the image content into a first generation model to generate the target identification information.

[0123] Optionally, the first generation model is an AI (Artificial Intelligence) generation model, such as a generative artificial intelligence model, etc. Specifically, it can be a local model of the electronic device, or a network end / cloud model.

[0124] In this implementation manner, image content recognition may be performed on the first image first, including but not limited to performing text and / or image content recognition on a text area and / or image area in the first image.

[0125] Afterwards, the recognized image content (such as the recognized content of the text area and / or image area) and the guidance information for guiding the first generation model to generate the target identification information based on the image content can be further input into the first generation model, thereby obtaining the target identification information generated by the first generation model based on the image content under the guidance of the guidance information.

[0126] The generated target identification information may specifically be, but is not limited to, target image, target text, target LOGO, etc., generated by the first generation model based on the image content. In this implementation, the target image, target text, target LOGO, etc., generated based on the image content, is used to represent the source of the first image.

[0127] This embodiment realizes the acquisition of target identification information associated with the first image. By acquiring the target identification information, the target poster image generated subsequently can present the source of its basic image (first image), providing support for users or other viewers (such as the object with which the user shares the target poster image) to understand the source of the image (such as the name of the game, live broadcast, conference, video, movie, etc.). In addition, this embodiment sets a variety of different entry points around the first image (such as the source of the first image, the target user in the first image, the target user who implements the triggering operation to trigger the generation of the first image, the image content of the first image, etc.), supports the acquisition of target identification information based on the various different entry points, and correspondingly supports indicating the image source in different information identification methods that match different entry points, without having to stick to a specific method, thereby further improving the flexibility and innovation of poster generation and improving the user experience.

[0128] In an optional embodiment, step 102 in the method provided in the present application, i.e., obtaining target identification information associated with the first image, may also be implemented, but is not limited to, as including at least one of the following 3-1 to 3-4:

[0129] 3-1. In the case where the first image is from a game application, a second image associated with the first image is obtained, wherein the second image includes at least one of an application icon, an application name, and a version of the game application.

[0130] In this case, the game application to which the first image specifically belongs can be detected first, and then a second image including the application icon, application name and / or version information of the game application can be captured or extracted from the game application to which the first image belongs, and the captured or extracted second image can be used as the target identification information to indicate the source of the first image.

[0131] 3-2. In the case where the first image comes from a content playback application, the target identification information includes file information of a multimedia file to which the first image belongs and / or application information of the content playback application.

[0132] If the first image comes from a content playback application, the content playback application and / or the multimedia file to which the first image specifically belongs can be detected, such as a video playback application (a long video or short video playback application, etc.), an audio playback application and / or the audio and video file to which the first image belongs, and application information of the content playback application to which the first image belongs and / or file information of the multimedia file to which it belongs can be extracted as target identification information associated with the first image to indicate the source of the first image.

[0133] The extracted application information of the content playback application may include, but is not limited to, the type of the content playback application (such as audio, video), icon, manufacturer, application name and / or version information. The extracted file information of the multimedia file may include, but is not limited to, the type of the multimedia file (such as audio, video), icon, file name, theme description (such as movie name, short video name), cast name, summary (such as movie / short video introduction), tags (keywords), and other information.

[0134] 3-3. In the case where the first image comes from a live broadcast application, the target identification information includes description information of the live broadcast signal to which the first image belongs and / or application information of the live broadcast application.

[0135] If the first image comes from a content playback application, description information of the live broadcast signal to which the first image specifically belongs and / or application information of the live broadcast application may be extracted as target identification information associated with the first image to indicate the source of the first image.

[0136] The extracted description information of the live broadcast signal may include, but is not limited to, the live broadcast time, the type of live broadcast content (such as technology, education, food, shopping, entertainment, etc.) and / or the host's style, etc.

[0137] The extracted application information of the live broadcast application may include, but is not limited to, the application name / platform name, the manufacturer, the application icon and / or the version number, etc.

[0138] 3-4. In the case where the first image comes from a conference application, the target identification information includes conference theme information of the conference to which the first image belongs and / or application information of the conference application.

[0139] If the first image comes from a conference application, the conference application to which the first image belongs and / or the conference to which it specifically belongs under the conference application can be detected, and application information of the conference application and / or conference subject information of the conference can be extracted as target identification information associated with the first image to indicate the source of the first image.

[0140] The extracted application information of the conference application may include, but is not limited to, information such as the icon, name, manufacturer and / or version number of the conference application.

[0141] The extracted meeting theme information may include but is not limited to the theme introduction, keywords and other information of the meeting content. In addition, the meeting number, time and other information of the meeting to which the first image belongs may also be extracted, and the extracted information may be used as the target identification information associated with the first image to indicate the source of the first image.

[0142] This embodiment also realizes the acquisition of target identification information associated with the first image. By acquiring the target identification information that can indicate the source of the first image, the subsequently generated poster image can present the source of its basic image (first image), providing support for users or other viewers (such as the poster's sharing objects) to understand the image source information. Different from the previous embodiment, this embodiment takes the application from which the first image comes as the entry point, and supports the acquisition of the target identification information based on a variety of different types of applications from which it comes. Correspondingly, it supports indicating the source of the first image in an information identification method suitable for different applications, without having to stick to a specific identification method, thereby further improving the flexibility and innovation of poster generation and improving the user experience.

[0143] In an alternative embodiment, see Figure 3 The schematic diagram of the process of generating the target poster image shown in the figure, step 103 in the method provided by the present application can be specifically implemented as follows:

[0144] Step 301: Generate a third image with a first transparency based on the target image feature data.

[0145] As mentioned above, the target image feature data of the target object may include, but is not limited to, feature data such as the main color tone, theme style and / or image saturation of the target object in the first image.

[0146] In this embodiment, based on the target image features such as the main color, theme style and / or image saturation, a third image with a first transparency is generated, and the first transparency can be a preset transparency value, such as 30% or 50% transparency.

[0147] It is easy to understand that, in addition to having a certain degree of transparency (first transparency), the third image also has image features that are consistent with the target image feature data.

[0148] The third image has image features that are consistent with the target image feature data, which may mean that the third image has the same main color tone, theme style and / or image saturation as the main color tone, theme style and / or image saturation represented by the target image feature data, or the main color tone, theme style and / or image saturation possessed by the third image satisfies a close relationship with the main color tone, theme style and / or image saturation represented by the target image feature data, such as the absolute value of the difference in the main color tone value is lower than a threshold value.

[0149] The generated third image with the first transparency may specifically be an enlarged image generated based on the target image feature data (eg, enlarged to the size required for the poster to be generated), or a transparent black image with the first transparency (eg, 50%).

[0150] The generated enlarged image or the transparent black image, i.e., the third image, is used as an auxiliary image in the subsequent poster generation process of the target object. Optionally, the image size of the enlarged image or the transparent black image can be the size required for the poster image to be generated, which is of course not limited to this in the implementation, and can also be smaller than the size required for the poster image to be generated.

[0151] Step 302: Fusing the target object with the third image according to the target display layout to obtain a fourth image.

[0152] The fusion process may be, but is not limited to, a stacking process based on a foreground-background relationship and / or a primary-secondary relationship, or a tiling process based on a primary-secondary relationship, depending on the target display layout. The tiling process may be tiling the target object and the third image based on a set fixed tiling mode / layout mode, or may be dynamically filling the vacant part of the target object formed by the third image relative to the poster image size based on the size of the poster image to be generated.

[0153] For example, the target object is used as the background and the third image is used as the foreground (when the third image is used as the foreground, the third image is used to play a role similar to a mask with transparency), and the target object and the third image are superimposed. Alternatively, the target object is used as the main component object of the poster and the third image is used as the secondary component object, and the target object is tiled in a preset tiling mode / layout mode, or based on the size of the poster image to be generated, the third image is used to dynamically fill the vacant part of the target object relative to the poster image size.

[0154] Step 303: According to the target display layout, the target layer generated based on the target identification information is merged with the fourth image to obtain the target poster image.

[0155] In this embodiment, a target layer is also generated based on the target identification information for subsequent poster generation.

[0156] The generated target layer can be an image layer generated based on the image content in the target identification information, or a text layer generated based on the text information in the target identification information, or an image and text layer generated based on the image content and text information in the target identification information. There is no limitation to this and it can be determined according to the actual application situation.

[0157] For example, an image layer generated based on the ICON icon image of the game application to which the first image belongs, a text layer generated based on the application name of the video application to which the first image belongs and / or the file name of the audio and video file to which it belongs, or an image and text layer generated based on the ICON icon image of the video application to which the first image belongs and the file name of the audio and video file to which it belongs, etc.

[0158] On the basis of the above processing, the target layer generated based on the target identification information may be further fused with the fourth image according to the target display layout to obtain a target poster image.

[0159] In step 303, the target display layout is mainly used to determine the fusion position of the target identification information (such as the ICON icon of the game application).

[0160] Specifically, the target layer generated based on the target identification information can be fused at the corresponding position of the fourth image according to the fusion position of the target identification information indicated by the target display layout. For example, the target layer can be fused at the middle area of ​​the fourth image, or the target layer and the target object in the fourth image can be fused at the corresponding position of the fourth image according to a relative position relationship such as a symmetrical relationship, so as to obtain the target poster image.

[0161] See also Figure 4 , provides an example of the generated target poster image.

[0162] The target display layout can not only indicate the fusion position of the target identification information, but also indicate the hierarchical relationship between the target identification information and the corresponding image to be fused, such as the fourth image, for example, indicating that the target identification information is at the top layer or at the second top layer, etc. Correspondingly, when performing the fusion processing, the hierarchical relationship required by the target display layout can also be considered to fuse the target layer with the fourth image.

[0163] Regardless of the fusion method, it is necessary to be able to visually display the target identification information in the target layer, so that when the generated target poster image is displayed, shared or disseminated, the source of the image content in the poster image can be understood based on the target identification information, such as the game application, live broadcast application, conference application, or multimedia file to which it belongs.

[0164] This embodiment generates a target poster image by generating a third image with a first transparency based on the target image feature data, generating a target layer based on the target identification information, and performing corresponding fusion processing on the target object, the third image and the target layer according to the target display layout. This not only realizes the automatic and intelligent dynamic generation of poster images, but also improves the efficiency of poster generation and saves time. In addition, by introducing the target image feature data and target standard information into the poster image, it ensures that the generated poster has a consistent design style and standard, and accordingly ensures the quality and effect of the generated poster image.

[0165] In an optional embodiment, step 103 in the method provided by the present application may further include at least one of the following:

[0166] 4-1. Generate a fifth image with a second transparency based on the target image feature data, and fuse the target object with the third image and the fifth image according to the target display layout to obtain the fourth image.

[0167] In this embodiment, a fifth image with a second transparency is generated based on the target image feature data of the target object, such as the main color, theme style and / or image saturation. The second transparency can also be a preset transparency value, such as 30% or 50% transparency. The second transparency can be the same as or different from the first transparency, and there is no limitation on this.

[0168] And the generated fifth image has a different color value from the third image, that is, a different color.

[0169] Similar to the third image, in addition to having a certain degree of transparency (second transparency), the fifth image also has image features consistent with the target image feature data.

[0170] Similarly, the fifth image has image features that are consistent with the target image feature data, which may mean that the fifth image has the same main color tone, theme style and / or image saturation as the main color tone, theme style and / or image saturation represented by the target image feature data, or the main color tone, theme style and / or image saturation possessed by the fifth image satisfies a close relationship with the main color tone, theme style and / or image saturation represented by the target image feature data, such as the absolute value of the difference in main color tone value is lower than a threshold value.

[0171] The generated fifth image with the second transparency may be an enlarged image generated based on the target image characteristic data, or an image with a transparent blackness of the second transparency (such as 50%).

[0172] The generated enlarged image or the transparent black image, that is, the fifth image, is also used as an auxiliary image in the subsequent poster generation process of the target object. Optionally, in this embodiment, the image size of the enlarged image or the transparent black image can be the size required for the poster image to be generated, which is of course not limited to this in the implementation, and can also be smaller than the size required for the poster image to be generated.

[0173] It should be noted that the fifth image is different from the third image, for example, the color values ​​of the two are different, and even the transparency is different. Optionally, if the third image is an enlarged picture generated based on the target image feature data, the fifth image can be a transparent black picture with a second transparency. If the third image is a transparent black picture with a first transparency, the fifth image can be an enlarged picture generated based on the target image feature data.

[0174] After obtaining the fifth image, this embodiment fuses the target object with the third image and the fifth image according to the target display layout to obtain the fourth image, so as to facilitate subsequent generation of a poster based on the fourth image.

[0175] 4-2. Obtain second source information of the target object and / or attribute information of the target identification information, and determine display layout information among the target object, the target image feature data and the target identification information based on the second source information and / or the attribute information.

[0176] In this embodiment, the second source information of the target object and / or the attribute information of the target identification information is also obtained.

[0177] The second source information of the target object may include, but is not limited to, the icon / name of the application to which the target object belongs, the project to which it belongs, the identification information of the corresponding copyright holder, etc., such as the game icon and name of a game character, etc. The attribute information of the target identification information may include, but is not limited to, the color structure, shape, data volume and / or information type (such as text, image, or text and image), information layout and other information of the target identification information such as the application icon / name, such as the color structure, shape (such as round, rounded, square) and / or data volume of the game application icon.

[0178] Target objects from different sources (such as game characters, movie characters, conference speakers, etc.), or target identification information with different attributes, can affect the display layout between the images to be fused (such as the target object, the target image feature data and the image corresponding to the target identification information). After obtaining the second source information of the target object and / or the attribute information of the target identification information, this embodiment determines the display layout information between the target object, the target image feature data and the target identification information in combination with the second source information of the target object and / or the attribute information of the target identification information, so that the determined display layout information is compatible with the source of the target object, the attribute information of the target identification information, etc., thereby further improving the rationality and coordination of the generated target poster image in the display layout.

[0179] This embodiment further generates a fifth image with a second transparency different from the third image based on the target image feature data, and introduces the fifth image into the poster generation, which can further improve the flexibility and innovation of poster generation, thereby improving the visual effect and user experience of the poster. In addition, by obtaining the second source information of the target object and / or the attribute information of the target identification information, the display layout information between the target object, the target image feature data and the target identification information is determined based on the second source information and / or the attribute information, thereby improving the dynamic adaptability of the target display layout to the source of the target object and / or the attributes of the target identification information, and facilitating the acquisition of a poster image that is more reasonable and coordinated in display layout, thereby further improving the quality and effect of the poster image.

[0180] In an optional embodiment, when the target identification information is a second image associated with the first image, the method provided by the present application further includes at least one of the following:

[0181] 5-1. Segment a second foreground image including an application icon and / or an application name from the second image as a target layer.

[0182] First, the foreground and background in the second image can be determined based on foreground and background recognition of the second image. Then, the second foreground image including the application icon and / or application name can be segmented from the second image through foreground and background segmentation processing of the image, and the segmented second foreground image can be used as the target layer to participate in the subsequent poster generation processing.

[0183] 5-2. Perform rounding processing on the segmented second foreground image based on the pixel information of the second image.

[0184] Specifically, the shape of the second foreground image can be determined based on pixel information of the second image, such as pixel information of the second foreground image segmented from the second image. If the second foreground image is a non-rounded image or a non-circular image, such as a square image, the second foreground image is processed into a rounded image by performing rounding processing on the second foreground image, such as right-angle rounding processing.

[0185] If the second foreground image is a rounded-corner image or a circular image, the rounded-corner processing of the second foreground image may be omitted.

[0186] In implementation, optionally, the second foreground image may first be scaled to a predefined standard size, such as a standard size of 360*508, through a scaling process.

[0187] Optionally, an interpolation algorithm may be used to ensure that the clarity and details of the second foreground image are maintained during the scaling process to avoid jagged and blurring phenomena.

[0188] After the second foreground image is subjected to scaling-based normalization processing, a rounded corner image that meets the standard size (such as an ICON transparent rounded corner image that meets the standard size) can be used as a reference image to determine the second foreground image after the normalization processing, wherein, if the number of pixels of the second foreground image after the normalization processing is greater than the number of pixels of the reference image, the shape of the second foreground image after the normalization processing is determined to be non-rounded or non-circular, and accordingly, a rounded corner processing is performed on the second foreground image after the normalization processing, such as a right-angle rounded corner processing, to convert it into a rounded corner image, conversely, if the number of pixels of the second foreground image after the normalization processing is not greater than the number of pixels of the reference image, there is no need to perform a rounded corner processing on the second foreground image after the normalization processing, and its original shape is maintained.

[0189] In this embodiment 5-2, the image obtained by rounding the segmented second foreground image is used as the target layer to participate in the subsequent poster generation process.

[0190] 5-3. Scaling the second image.

[0191] In this embodiment 5-3, the second image may be specifically scaled to a predefined standard size, such as a standard size of 360*508, through scaling processing, and subsequent poster generation processing is performed based on the scaled second image.

[0192] For example, the second image after the scaling process is used as the target layer to participate in the image fusion process to generate a target poster image, etc.

[0193] This embodiment can achieve standardized processing of the target layer based on the target identification information such as the second image or the second foreground image by scaling the second image or the second foreground image to a standard size. This standardized processing can make the target layer have a consistent display effect on different devices and platforms, making it convenient for users to perform personalized settings and sharing.

[0194] In addition, this embodiment can make the image edge of the target layer smoother and more natural by rounding the corners of the second foreground image, such as automatically rounding the right angles, thereby optimizing its visual effect. In implementation, different visual effects can be flexibly achieved according to user needs and image characteristics to increase the aesthetics and personalization of the image.

[0195] In an alternative embodiment, see Figure 5 The schematic diagram of the process of generating the target poster image shown in FIG. 1 shows, step 103 in the method provided by the present application can also be implemented as follows:

[0196] Step 501: Process the target object, the target image feature data and the target identification information into a target user intention.

[0197] The target user intention may include the target object, the target image feature data and the target identification information, for example, specifically including the target object, a third image generated based on the target image feature data, and a target layer generated based on the target identification information. In addition, the target user intention may also include guidance information for instructing to generate a target poster image based on the target object, the target image feature data and the target identification information.

[0198] During implementation, the guidance information can be set based on the prompt word project of the target generation model. The set guidance information can specifically include but is not limited to the model roles, role functions, role tasks and / or task samples set around the above-mentioned guidance targets, so as to guide the target generation model to generate the corresponding target poster image based on the target object, the target image feature data and the target identification information by specifying the model roles, role functions, role tasks and / or providing corresponding task samples to the target generation model.

[0199] The target generation model may be a generative artificial intelligence model that can be used to generate images or videos, and the target generation model may be a local model of the electronic device, or a network / cloud model.

[0200] Step 502: Utilize the target generation model to perform a generation processing operation based on the target user intention to obtain the target poster image.

[0201] After the target user intention is obtained, the target user intention may be input into a target generation model, and the target poster image may be obtained by performing a generation processing operation based on the target user intention using the target generation model.

[0202] Based on this embodiment, the powerful processing capability of the target generation model can be used to quickly and accurately generate a poster image, further improving the efficiency and effect of generating the poster image.

[0203] In practical applications, it is also possible to achieve perfect fusion of multiple images (such as the target object, the third image generated based on the target image feature data, and the target layer generated based on the target identification information) by precise color adjustment and transparency control as needed, producing a unique visual effect, so that it can not only add a sense of hierarchy and three-dimensionality to the image of the target object, but also give new artistic charm to the enlarged picture and the black picture, making the poster image obtained after fusion more vivid and expressive. At the same time, it can also combine special effect generation technology, such as light and shadow effects, dynamic blur, etc., to add more artistic atmosphere and visual impact to the image.

[0204] Corresponding to the above poster generation method, the embodiment of the present application also provides a poster generation device, whose composition structure is as follows: Figure 6 As shown, including:

[0205] A first acquisition module 601 is used to obtain a target object in a first image and target image feature data of the target object;

[0206] A second acquisition module 602 is used to obtain target identification information associated with the first image, where the target identification information can indicate a source of the first image;

[0207] The generation module 603 is used to perform image generation processing on the target object, the target image feature data and the target identification information according to the target display layout to obtain a target poster image.

[0208] In an alternative embodiment,

[0209] In an optional implementation manner, the first acquisition module 601 is specifically configured to:

[0210] Acquire a target interface image of a target application of the electronic device during operation as the first image, wherein the target interface image is an image frame including a target object;

[0211] Segmenting a first foreground image including only the target object from the target interface image; and

[0212] Target image feature data of the first foreground image is extracted.

[0213] In an optional implementation manner, the first acquisition module 601, when acquiring the target interface image of the target application of the electronic device during operation, is specifically configured to perform at least one of the following:

[0214] Monitoring the running process of the target application, and capturing the application interface presenting the target event as the target interface image;

[0215] Monitoring the behavior data of the target object in the application interface of the target application, and capturing the application interface where the target object performs the target behavior as the target interface image;

[0216] Monitoring the operation data of the target user acting on the electronic device, responding to the target operation of the target user, and intercepting the current application interface corresponding to the target operation as the target interface image;

[0217] An application interface of a target application at a target moment during its operation is captured as the target interface image.

[0218] In an optional implementation manner, the second acquisition module 602 is specifically configured to perform at least one of the following:

[0219] Obtaining first source information of the first image, and obtaining target identification information matching the first source information;

[0220] Obtaining target identification information associated with the target object in the first image;

[0221] Obtaining target identification information associated with a target user who performs a triggering operation for triggering generation of the first image;

[0222] The image content of the first image is obtained, and the image content is input into a first generation model to generate the target identification information.

[0223] In an optional implementation manner, the second acquisition module 602 is specifically configured to perform at least one of the following:

[0224] In the case where the first image is from a game application, obtaining a second image associated with the first image, the second image including at least one of an application icon, an application name, and a version of the game application;

[0225] In the case where the first image comes from a content playback application, the target identification information includes file information of a multimedia file to which the first image belongs and / or application information of the content playback application;

[0226] In the case where the first image comes from a live broadcast application, the target identification information includes description information of a live broadcast signal to which the first image belongs and / or application information of the live broadcast application;

[0227] In the case that the first image comes from a conference application, the target identification information includes conference theme information of the conference to which the first image belongs and / or application information of the conference application.

[0228] In an optional implementation manner, the generating module 603 is specifically configured to:

[0229] generating a third image having a first transparency based on the target image feature data;

[0230] fusing the target object with the third image according to the target display layout to obtain a fourth image; and

[0231] The target layer generated based on the target identification information is fused with the fourth image according to the target display layout to obtain the target poster image.

[0232] In an optional implementation manner, the generating module 603 is further configured to perform at least one of the following:

[0233] generating a fifth image with a second transparency based on the target image feature data, fusing the target object with the third image and the fifth image according to the target display layout to obtain the fourth image, wherein the first transparency and the second transparency are the same or different, and the fifth image has a different color value from the third image;

[0234] Obtain second source information of the target object and / or attribute information of the target identification information, and determine display layout information among the target object, the target image feature data and the target identification information based on the second source information and / or the attribute information.

[0235] In an optional implementation, the apparatus further includes an auxiliary processing module, configured to, when the target identification information is a second image associated with the first image, perform at least one of the following:

[0236] Segmenting a second foreground image including an application icon and / or an application name from the second image as a target layer;

[0237] performing rounding processing on the segmented second foreground image based on pixel information of the second image;

[0238] The second image is scaled.

[0239] In an optional implementation manner, the generating module 603 is specifically configured to:

[0240] Processing the target object, the target image feature data and the target identification information into a target user intention;

[0241] A target generation model is used to perform a generation processing operation based on the target user intention to obtain the target poster image.

[0242] The present application also discloses an electronic device, the composition structure of the electronic device, such as Figure 7 As shown, including at least:

[0243] A memory 10, for storing a computer instruction set;

[0244] A set of computer instructions can be implemented in the form of a computer program.

[0245] The processor 20 is used to implement the poster generation method provided in any of the above method embodiments by executing a computer instruction set.

[0246] The processor 20 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a neural network processor (NPU), a deep learning processor (DPU) or other programmable logic devices, etc.

[0247] The electronic device includes a display device and / or includes a display interface and can be connected to an external display device.

[0248] Optionally, the electronic device also includes a camera assembly, and / or is connected to an external camera assembly.

[0249] In addition, the electronic device may also include components such as a communication interface and a communication bus. The memory, the processor and the communication interface communicate with each other through the communication bus.

[0250] The communication interface is used for communication between electronic devices and other devices. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0251] An embodiment of the present application also provides a storage medium, which carries one or more computer instruction sets. When the one or more computer instruction sets are executed by an electronic device, the electronic device can implement the poster generation method as described in any one of the above items.

[0252] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0253] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0254] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or the part that makes a creative contribution can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0255] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0256] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A poster generation method, comprising: Obtaining a target object in a first image and target image feature data of the target object; Obtaining target identification information associated with the first image, where the target identification information can indicate a source of the first image; The target object, the target image feature data and the target identification information are subjected to image generation processing according to a target display layout to obtain a target poster image.

2. The method according to claim 1, wherein: Obtaining a target object in a first image and target image feature data of the target object, including: Acquire a target interface image of a target application of the electronic device during operation as the first image, wherein the target interface image is an image frame including a target object; Segmenting a first foreground image including only the target object from the target interface image; and Target image feature data of the first foreground image is extracted.

3. The method according to claim 2, wherein: Acquiring a target interface image of a target application of an electronic device during operation includes at least one of the following: Monitoring the running process of the target application, and capturing the application interface presenting the target event as the target interface image; Monitoring the behavior data of the target object in the application interface of the target application, and capturing the application interface where the target object performs the target behavior as the target interface image; Monitoring the operation data of the target user acting on the electronic device, responding to the target operation of the target user, and intercepting the current application interface corresponding to the target operation as the target interface image; An application interface of a target application at a target moment during its operation is captured as the target interface image.

4. The method according to claim 1, wherein: Obtaining target identification information associated with the first image includes at least one of the following: Obtaining first source information of the first image, and obtaining target identification information matching the first source information; Obtaining target identification information associated with the target object in the first image; Obtaining target identification information associated with a target user who performs a triggering operation for triggering generation of the first image; The image content of the first image is obtained, and the image content is input into a first generation model to generate the target identification information.

5. The method according to claim 1 or 4, wherein: Obtaining target identification information associated with the first image includes at least one of the following: In the case where the first image is from a game application, obtaining a second image associated with the first image, the second image including at least one of an application icon, an application name, and a version of the game application; In the case where the first image comes from a content playback application, the target identification information includes file information of a multimedia file to which the first image belongs and / or application information of the content playback application; In the case where the first image comes from a live broadcast application, the target identification information includes description information of a live broadcast signal to which the first image belongs and / or application information of the live broadcast application; In the case that the first image comes from a conference application, the target identification information includes conference theme information of the conference to which the first image belongs and / or application information of the conference application.

6. The method according to claim 1, wherein: The target object, the target image feature data and the target identification information are subjected to image generation processing according to a target display layout, including: generating a third image having a first transparency based on the target image feature data; fusing the target object with the third image according to the target display layout to obtain a fourth image; and The target layer generated based on the target identification information is fused with the fourth image according to the target display layout to obtain the target poster image.

7. The method according to claim 6, further comprising at least one of the following: generating a fifth image with a second transparency based on the target image feature data, fusing the target object with the third image and the fifth image according to the target display layout to obtain the fourth image, wherein the first transparency and the second transparency are the same or different, and the fifth image has a different color value from the third image; Obtain second source information of the target object and / or attribute information of the target identification information, and determine display layout information among the target object, the target image feature data and the target identification information based on the second source information and / or the attribute information.

8. The method according to claim 6, wherein when the target identification information is a second image associated with the first image, further comprises at least one of the following: Segmenting a second foreground image including an application icon and / or an application name from the second image as a target layer; performing rounding processing on the segmented second foreground image based on pixel information of the second image; The second image is scaled.

9. The method according to claim 1, wherein: The target object, the target image feature data and the target identification information are subjected to image generation processing according to a target display layout, including: Processing the target object, the target image feature data and the target identification information into a target user intention; A target generation model is used to perform a generation processing operation based on the target user intention to obtain the target poster image.

10. A poster generating device, comprising: A first acquisition module, used to obtain a target object in a first image and target image feature data of the target object; A second acquisition module, configured to obtain target identification information associated with the first image, wherein the target identification information can indicate a source of the first image; The generating module is used to perform image generating processing on the target object, the target image feature data and the target identification information according to the target display layout to obtain a target poster image.

Images