Terminal theme generation method, terminal theme generation device and storage medium

Abstract

The invention relates to a terminal theme generation method, a terminal theme generation device and a storage medium. The terminal theme generation method comprises the following steps: generating target wallpaper based on a first image selected by a user; according to the first display attribute of the image content in the target wallpaper, a terminal theme is generated, the terminal theme comprises an application display icon, and the application display icon corresponds to a second display attribute. The second display attribute is determined based on the first display attribute. According to the invention, diversified wallpaper and themes with user personal styles and uniformity can be obtained based on the local image.

Description

Technical Field

[0001] The present disclosure relates to the field of terminal desktop display, and in particular to a terminal theme generation method, a terminal theme generation device and a storage medium. Background Art

[0002] When using mobile phones, tablets and other terminals, users often pursue the aesthetics and personalized style of the terminal interface (desktop icons and screen-off display interface, etc.). In the related art, the themes and wallpapers included in the terminal theme application are limited, which cannot meet the user's personalized needs. Moreover, after setting the terminal theme, users often customize the terminal wallpaper, resulting in a sense of separation between the terminal theme and the terminal wallpaper. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a terminal theme generating method, a terminal theme generating device and a storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a terminal theme generation method is provided, comprising: generating a target wallpaper based on a first image selected by a user; generating a terminal theme according to a first display attribute of image content in the target wallpaper, the terminal theme comprising an application display icon, the application display icon corresponding to a second display attribute; the second display attribute is determined based on the first display attribute.

[0005] In one embodiment, the first image is a picture including a target object; generating a target wallpaper based on the first image selected by a user includes: determining the first image as the target wallpaper; or preprocessing the first image to obtain a second image including at least some information elements in the target object, and generating a target wallpaper based on the second image, the preprocessing including: one or more of text removal processing, clarity processing and background weakening processing, and the target wallpaper includes at least some information elements in the target object.

[0006] In one embodiment, generating the target wallpaper includes: determining a style option selected by a user; performing stylization processing on the first image to obtain a third image matching the style option; and generating the target wallpaper based on the third image.

[0007] In one embodiment, generating a target wallpaper based on the third image includes: determining the third image as the target wallpaper; or performing AI conversion on the third image based on application data in the terminal, and determining the third image that has completed the AI ​​conversion as the target wallpaper.

[0008] In one embodiment, the application data includes one or more of album application data, calendar application data, weather application data and sports application data; the AI ​​conversion of the third image according to the application data in the terminal includes: obtaining a target image in the album application, adding some elements in the target image to the third image, and performing AI conversion on the third image with added elements, wherein the target image is an image of a predefined scene, an image with a shooting date associated with the current date; and / or obtaining date data in the calendar application, adding special date elements in the date data to the third image, and performing AI conversion on the third image with added elements, wherein the special date elements include holiday elements, birthday elements and anniversary elements; and / or obtaining weather data in the weather application, adding real-time weather elements in the weather data to the third image, and performing AI conversion on the third image with added elements; and / or obtaining sports data and body status data in the sports application, adding sports elements and body status elements in the sports data and the body status data to the third image, and performing AI conversion on the third image with added elements.

[0009] In one embodiment, the method further includes: performing one or more replacement processes of element replacement, scene replacement and style replacement on the third image that has completed the AI ​​conversion; and determining the third image after the replacement process as the target wallpaper.

[0010] In one embodiment, the first display attribute includes one or more of color, element and style, and the element includes one or more of character dress, character behavior, location scene and object; the second display attribute includes one or more of the color, element and style.

[0011] In one embodiment, the method further includes: based on an instruction issued by a user, storing the target wallpaper and the terminal theme as a theme template, and uploading the theme template to a cloud for sharing.

[0012] According to a second aspect of an embodiment of the present disclosure, a terminal theme generating device is provided, including: a generating unit, for generating a target wallpaper based on a first image selected by a user; a processing unit, for generating a terminal theme according to a first display attribute of an image content in the target wallpaper, the terminal theme including an application display icon, the application display icon corresponding to a second display attribute; the second display attribute is determined based on the first display attribute.

[0013] In one embodiment, the first image is a picture including a target object; the generation unit generates a target wallpaper based on the first image selected by the user in the following manner: determining the first image as the target wallpaper; or preprocessing the first image to obtain a second image including at least some information elements in the target object, and generating a target wallpaper based on the second image, wherein the preprocessing includes: one or more of text removal processing, clarity processing and background weakening processing, and the target wallpaper includes at least some information elements in the target object.

[0014] In one implementation, the generation unit generates the target wallpaper in the following manner: determining a style option selected by a user; performing stylization processing on the first image to obtain a third image matching the style option; and generating the target wallpaper based on the third image.

[0015] In one embodiment, the generating unit generates a target wallpaper according to the third image in the following manner: determining the third image as the target wallpaper; or performing AI conversion on the third image according to application data in the terminal, and determining the third image after the AI ​​conversion as the target wallpaper.

[0016] In one embodiment, the application data includes one or more of album application data, calendar application data, weather application data and sports application data; the generation unit performs AI conversion on the third image according to the application data in the terminal in the following manner: obtaining a target image in the album application, adding some elements in the target image to the third image, and performing AI conversion on the third image with added elements, wherein the target image is an image of a predefined scene and an image whose shooting date is associated with the current date; and / or obtaining date data in the calendar application, adding special date elements in the date data to the third image, and performing AI conversion on the third image with added elements, wherein the special date elements include holiday elements, birthday elements and anniversary elements; and / or obtaining weather data in the weather application, adding real-time weather elements in the weather data to the third image, and performing AI conversion on the third image with added elements; and / or

[0017] The motion data and the body state data are acquired in the motion application, and the motion elements and the body state elements in the motion data and the body state data are added to the third image, and the third image with the added elements is AI converted.

[0018] In one embodiment, the generating unit is further used to: perform one or more replacement processes of element replacement, scene replacement and style replacement on the third image that has completed the AI ​​conversion; and determine the third image after the replacement process as the target wallpaper.

[0019] In one embodiment, the first display attribute includes one or more of color, element and style, and the element includes one or more of character dress, character behavior, location scene and object; the second display attribute includes one or more of the color, element and style.

[0020] In one embodiment, the processing unit is further used to: based on an instruction issued by a user, store the target wallpaper and the terminal theme as a theme template, and upload the theme template to a cloud for sharing.

[0021] According to a third aspect of an embodiment of the present disclosure, a terminal theme generation device is provided, comprising: a processor; and a memory for storing processor executable instructions; wherein the processor is configured to: execute the terminal theme generation method described in the first aspect or any one of the implementations of the first aspect.

[0022] According to a fourth aspect of an embodiment of the present disclosure, a storage medium is provided, in which instructions are stored. When the instructions in the storage medium are executed by a processor, the processor is enabled to execute the terminal theme generation method described in the first aspect or any one of the embodiments of the first aspect.

[0023] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: obtaining the original image contained in the terminal album (a photo of a person or a screenshot of a video containing a person), obtaining the terminal wallpaper based on the original image, and generating a terminal theme associated with the terminal wallpaper. Through the present disclosure, a variety of wallpapers and themes with the user's personal style and unity can be obtained based on the terminal body picture.

[0024] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0026] Figure 1 The figure is a flow chart of a method for generating a terminal theme according to an exemplary embodiment.

[0027] Figure 2 The invention is a flowchart of a method for generating a target wallpaper according to an exemplary embodiment.

[0028] Figure 3A and Figure 3B It is a schematic diagram of the effects of an original image and a processed image in an image preprocessing method according to an exemplary embodiment of the present disclosure.

[0029] Figure 4 is a flowchart of a method for generating a target wallpaper according to yet another exemplary embodiment.

[0030] Figure 5A and Figure 5B The figure is a schematic diagram showing the effects of images of different styles after stylization processing according to an exemplary embodiment of the present disclosure.

[0031] Figure 6 The flowchart of a method for generating a target wallpaper is shown according to yet another exemplary embodiment.

[0032] Figure 7 is a flowchart of a method for generating a target wallpaper according to yet another exemplary embodiment.

[0033] FIG. 8A to FIG. 8D It is a schematic diagram showing the effects of different target wallpapers generated based on different application authorization data combined with stylized images according to an exemplary embodiment of the present disclosure.

[0034] Fig. 9 The figure is a flowchart of a method for generating a terminal theme according to another exemplary embodiment.

[0035] FIG. 10A to FIG. 10C It is a schematic diagram showing the effects of different wallpapers obtained after different replacement processes according to an exemplary embodiment of the present disclosure.

[0036] Fig.11 The figure is a flowchart of a wallpaper generating method according to an exemplary embodiment of the present disclosure.

[0037] Fig.12 The figure is a flowchart of a wallpaper generating method according to another exemplary embodiment of the present disclosure.

[0038] Fig.13 The figure is a schematic diagram showing a method for obtaining a wallpaper of a terminal theme according to an exemplary embodiment of the present disclosure.

[0039] FIG. 14A to FIG. 14D The figure is a schematic diagram showing an effect of a terminal theme generated based on wallpaper according to an exemplary embodiment of the present disclosure.

[0040] Fig.15 The figure is a flowchart of a method for generating a terminal theme according to another exemplary embodiment.

[0041] Fig.16 The figure is a schematic diagram showing the effect of a method for generating a terminal theme according to an exemplary embodiment of the present disclosure.

[0042] Fig.17 The figure is a flowchart of a method for generating a terminal theme according to an exemplary embodiment of the present disclosure.

[0043] Fig.18 The figure is a flowchart of a method for generating a terminal image style according to an exemplary embodiment of the present disclosure.

[0044] Fig.19 The figure is a flowchart of a picture sharing method according to an exemplary embodiment of the present disclosure.

[0045] Fig. 20 The figure is a block diagram of a terminal theme generating device according to an exemplary embodiment.

[0046] Fig.21 The present invention is a block diagram showing a device for generating a terminal theme according to an exemplary embodiment. DETAILED DESCRIPTION

[0047] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure.

[0048] The terminal theme generation method provided by the embodiment of the present disclosure is applied to the scenario where a user customizes the wallpaper and desktop theme of a terminal.

[0049] When using mobile phones, tablets and other terminals, users often pursue the aesthetics and personalized style of the terminal interface (desktop icons, screen-off display, etc.). In the related art, for terminal users, when setting the theme of the terminal, they select the theme that meets the needs from the given themes of the theme application and apply it, but the types and number of themes included in the terminal theme application are limited, which cannot meet the user's personalized needs. In addition, when setting the terminal wallpaper, the user will select wallpaper from the terminal application or select local pictures from the terminal local album as wallpaper. Due to the limited templates included in the theme application, after the user determines the wallpaper that meets the needs, there will be a situation where the user cannot find the theme of the corresponding style, resulting in a sense of separation between the terminal theme finally selected by the user and the terminal wallpaper, affecting the user's visual perception. In the related art, for terminal manufacturers, the themes in the theme application for users to download and use need to be designed by special designers, resulting in low output efficiency and high output cost of terminal themes.

[0050] In view of this, the present disclosure proposes a method for generating a terminal theme, which generates wallpapers based on local photos of the terminal and generates themes based on the content contained in the wallpapers, thereby increasing the user's freedom in setting the terminal theme and making the terminal theme and wallpaper unified.

[0051] Figure 1 FIG. 1 is a flow chart of a method for generating a terminal theme according to an exemplary embodiment. Figure 1 As shown, the method includes step S101 to step S102.

[0052] In step S101 , a target wallpaper is generated based on a first image selected by a user.

[0053] In step S102, a terminal theme is generated according to a first display attribute of the image content in the target wallpaper.

[0054] The terminal theme includes an application display icon, and the application display icon corresponds to a second display attribute, which is determined based on the first display attribute.

[0055] Among them, the terminal theme can also include an off-screen display interface. It is understandable that users often do not turn on the off-screen display function when using the terminal. Based on the user's usage habits, the user can choose whether to generate a corresponding off-screen display interface based on the target.

[0056] In the embodiment of the present disclosure, the first image is a to-be-processed picture (a photo of a person or a screenshot of a video containing a person) contained locally in the terminal, including pictures stored in an album application or other applications. The present disclosure processes the to-be-processed picture based on the first image by using artificial intelligence image generation technology to generate a wallpaper that satisfies the user's preferences, and further generates a terminal theme associated with the wallpaper based on the generated wallpaper. Through the present disclosure, users can obtain wallpapers with personalized styles based on their personal preferences, and obtain personalized themes that are consistent with the wallpaper. The user's autonomy in personalizing the terminal theme is improved.

[0057] In the embodiment of the present disclosure, processing is performed based on the original image (first image) selected by the user, and finally a new image is generated. In order to ensure the legality and compliance of the generated wallpaper, it is necessary to review the original image selected by the user and perform image compliance detection. In one example, the image compliance detection in the present disclosure includes two parts: 1. Use the Resnet50 classification model to determine whether the image is compliant based on the image content, and classify the image quality. If there is a non-compliant image, exit. 2. Use the face detection algorithm to perform face detection on the image. If there is no face, exit; if there is a face but the face area is too small to extract facial features, exit. 3. If there are multiple faces, exit. Images that meet the compliance test proceed to the next step.

[0058] It is understandable that the pictures and video screenshots contained in the local album of the terminal may have factors such as text coverage and low clarity that affect the wallpaper generation effect. Based on the above problems of the local album images, it is necessary to optimize the local album images to ensure the effect of the final generated wallpaper. The following embodiments of the present disclosure illustrate the method for optimizing the local album images.

[0059] Figure 2 FIG. 1 is a flow chart showing a method for generating a target wallpaper according to an exemplary embodiment. Figure 2 As shown, the method includes step S201, step S202A and step S202B.

[0060] In step S201, a first image is acquired.

[0061] The preprocessing includes one or more of text removal, clarity and background weakening.

[0062] In step S202A, the first image is determined as the target wallpaper.

[0063] In step S202B, the first image is preprocessed to obtain a second image including at least some information elements of the target object, and a target wallpaper is generated based on the second image.

[0064] The preprocessing includes: one or more of text removal processing, clarity processing and background weakening processing, and the target wallpaper includes at least part of the information elements of the target object.

[0065] Among them, step S202A and step S202B are alternative execution modes.

[0066] In the disclosed embodiment, the user can directly use the selected original image as the terminal wallpaper based on personal needs.

[0067] In the embodiments of the present disclosure, the original images contained in the local album of the terminal may have problems such as text occlusion and low clarity. Generating wallpaper directly based on the original images will affect the aesthetics of the wallpaper. Therefore, it is necessary to optimize the original images contained in the local album of the terminal. For example, when the images contained in the local album of the terminal are occluded by text, the images are processed to eliminate the text; when the images contained in the local album of the terminal are blurred and have low clarity, the images are processed to be clarified; further, when the characters in the image to be processed (i.e., the first image) are not prominent enough, the background is weakened to highlight the characters in the image. It can be understood that the preprocessing of the original images in the local album is not limited to the methods listed above, and the original images can also be optimized by other methods to highlight the main body of the target object.

[0068] In an exemplary embodiment of the present disclosure, Figure 3AThe video screenshots of the local album used to generate wallpaper are processed to be clear and text removed, and the main body of the characters is further highlighted to obtain the following Figure 3B The second image after preprocessing is shown.

[0069] In the embodiment of the present disclosure, after preprocessing the character image or video screenshot (i.e., the first image) in the album, the style of the preprocessed image (i.e., the second image) can be further changed according to the user's personal preference. The following embodiment of the present disclosure describes a method for stylizing the second image.

[0070] Figure 4 FIG. 1 is a flow chart of a method for generating a target wallpaper according to another exemplary embodiment. Figure 4 As shown, the method includes steps S301 to S303.

[0071] In step S301 , the style option selected by the user is determined.

[0072] In step S302, stylization processing is performed on the first image to obtain a third image matching the style option.

[0073] In step S303, a target wallpaper is generated according to the third image.

[0074] In the embodiment of the present disclosure, when the original image obtained in the terminal does not have interference such as low clarity and text occlusion, the first image can be directly stylized to obtain a stylized image (i.e., the third image). It is understandable that when the original image obtained in the terminal has interference such as low clarity and text occlusion, the original image can be optimized to obtain the second image, and then the second image can be stylized to obtain a stylized image (i.e., the third image).

[0075] In the disclosed embodiment, the terminal application includes multiple image styles such as cartoon style and semi-realistic style. Users can select an image style based on their personal preferences and obtain stylized images of the corresponding style. It is understandable that the terminal application for obtaining stylized images can update more optional image styles synchronously with the update of the application version.

[0076] It is understandable that the user can select an image style each time a wallpaper is generated, or can set a default image style based on personal preference, and when stylizing the second image, the default image style is given priority.

[0077] In the embodiment of the present disclosure, the image with the main body of the image as a person is mainly processed to obtain the target wallpaper. During the processing, most of the image content and image features of the original image need to be retained. In an example. The present disclosure uses the BLIP multimodal large model to extract static text elements (such as sunglasses, skirt color, grassland, suitcase, etc.) from the image, and uses the ResNet50 classification model to identify character actions (such as walking the dog, flying a kite, running, etc.). Among them, the static text includes two post-processing parts: 1. Filter the text elements according to the preset negative word list and delete the negative text to ensure that the generated wallpaper is compliant. 2. Classify the text elements according to the preset category word list to facilitate weighting of the text of different elements when generating the image. The present disclosure presets 3 types of static word lists, including dress (sunglasses, hairpins, yellow skirts, etc.), location scenes (such as grasslands, homes, etc.) and objects (such as suitcases, small trains, etc.), so as to retain the elements in the original image.

[0078] In the embodiment of the present disclosure, in the process of processing the original image, the action features of the characters in the image will be changed. In one example, for the character action elements extracted from the image, the present disclosure uses a multi-layer multi-layer perceptron (Multi Layer Perceptron, i.e., MLP) network to regress and predict the coordinates of 14 key human body points, such as the left and right elbows, left and right wrists, left and right shoulders, top of the head, neck, left and right ankles, left and right knees, and left and right hips, which are used to control the character posture in the generated image. In the MLP prediction process, the character action elements are first mapped to integer indexes (e.g., dog walking is mapped to 0, kite flying is mapped to 1, running is mapped to 2, ...). Secondly, the integer index is converted into a feature vector using sine and cosine position encoding. Finally, the encoded feature vector is input into the MLP to regress and predict the coordinates of 14 key human body points. The order of the human body key points is shown in the following table:

[0079] A B C D E 1 1 / Right shoulder 2 / right elbow 3 / right wrist 4 / Left shoulder 5 / left elbow 2 6 / left wrist 7 / Right hip 8 / right knee 9 / Right ankle 10 / Left hip 3 11 / Left knee 12 / Left ankle 13 / Top of head 14 / Neck

[0080] In the exemplary embodiment of the present disclosure, for facial gestures, in order to improve the diversity of generated facial angles of characters, the present disclosure samples an angle from each of the yaw angle (-45 degrees to +45 degrees, index values ​​0 to 90), the pitch angle (-20 degrees to +30 degrees, index values ​​0 to 90) and the roll angle (-45 degrees to +45 degrees, index values ​​0 to 90), and maps them to their index values, converts them into feature vectors using sine and cosine position encoding, and concatenates the feature vectors of the three angles. Use MLP network regression to predict the coordinates of 106 facial key points, convert the positions of the 106 facial key point coordinates and the 14 human body key point coordinates, align the top coordinates of the facial key points and the human body key points, and output a key point visualization image for the generation process of the control diffusion model, so that the control diffusion model can be generated quickly.

[0081] In an exemplary embodiment of the present disclosure, Figure 3B The second image (pre-processed image) shown in FIG. 1 is stylized, and when the user selects an anime style, the following is generated: Figure 5A The stylized image of the anime style shown in the figure; when the user selects the semi-realistic style, the generated Figure 5B Stylized image in semi-realistic style shown.

[0082] In the embodiment of the present disclosure, after the stylized image (third image) is obtained, additional information is added to the stylized image, and the target wallpaper is obtained. The following embodiment of the present disclosure further describes the method for obtaining the target wallpaper.

[0083] Figure 6 FIG. 1 is a flow chart of a method for generating a target wallpaper according to another exemplary embodiment. Figure 6 As shown, the method includes step S401, step S402A and step S402B.

[0084] In step S401, a third image is acquired.

[0085] In step S402A, the third image is determined as the target wallpaper.

[0086] In step S402B, AI conversion is performed on the third image according to the application data in the terminal, and the third image after AI conversion is determined as the target wallpaper.

[0087] Among them, step S402A and step S402B are alternative execution modes.

[0088] In the disclosed embodiment, after obtaining the stylized image, when the third stylized image meets the user's needs, the stylized image can be directly used as the target wallpaper and the processing flow can be stopped. When the user wants to further process the stylized image, personal elements associated with the user can be added to the stylized image based on the application data authorized by the user, so that the generated wallpaper fits the user's life and improves the user experience.

[0089] The following embodiments of the present disclosure further illustrate the method for obtaining the target wallpaper.

[0090] Figure 7 FIG. 1 is a flow chart of a method for generating a target wallpaper according to another exemplary embodiment. Figure 7 As shown, the method includes step S501, step S502A, step S502B, step S502C and step S502D.

[0091] In step S501, a second image including at least part of the information elements of the target object is obtained.

[0092] In step S502A, a target image is acquired in the photo album application, and some elements in the target image are added to the third image, and the third image with the added elements is AI converted.

[0093] The target image is an image of a predefined scene, and an image whose shooting date is associated with the current date.

[0094] In the disclosed embodiment, when the user grants the album application permission, the album data can be obtained. When there are photos of today's activities in the album, relevant elements such as activities and attractions can be added to the stylized image and further processed to obtain the target wallpaper. When there are historical photos of the same date in the album, elements of today's history can be added to the stylized image and further processed to obtain the target wallpaper.

[0095] In an exemplary embodiment of the present disclosure, for a stylized image in anime style, when obtaining the album application authorization data and there are photos of today's play in the album, a play scene can be added to the image background to obtain the following information: Fig. 8A Any of the target wallpapers shown.

[0096] In step S502B, date data is obtained in the calendar application, and the special date element in the date data is added to the third image, and the third image with the added element is AI converted.

[0097] Among them, special date elements include holiday elements, birthday elements and anniversary elements.

[0098] In the disclosed embodiment, when the user grants permission to the calendar application, it can be determined whether today is a special date, such as a holiday, a birthday, or a special anniversary preset in the calendar. When it is determined that today is a special date, corresponding elements are added to the stylized image, and further processing is performed to obtain the target wallpaper.

[0099] In an exemplary embodiment of the present disclosure, for a stylized image in anime style, when obtaining the calendar application authorization data and determining that today is the user's birthday, a birthday cake element may be added to the stylized image to obtain a birthday cake. Figure 8B Any of the target wallpapers shown.

[0100] In step S502C, weather data is obtained in a weather application, and real-time weather elements in the weather data are added to the third image, and the third image with the added elements is AI converted.

[0101] In the disclosed embodiment, when the user grants permission to the weather application, today's weather conditions can be obtained, weather elements (such as rain, snow, strong wind, sunny day, etc.) can be added to the stylized image, and further processed to obtain the target wallpaper.

[0102] In an exemplary embodiment of the present disclosure, for a stylized image of anime style, when obtaining weather application authorization data and determining today's weather, weather elements can be added to the stylized image to obtain the following information: Figure 8C Any of the target wallpapers shown.

[0103] In step S502D, motion data and body state data are obtained in the motion application, and motion elements and body state elements in the motion data and body state data are added to the third image, and the third image with the added elements is AI converted.

[0104] In the disclosed embodiment, when the user grants permission for a sports application, data of the sports application associated with the sports bracelet can be obtained, the user's health status data and sports data in the sports application can be obtained, corresponding sports elements and health status elements can be added to the stylized image, and further processed to obtain the target wallpaper.

[0105] In an exemplary embodiment of the present disclosure, for a stylized image of anime style, when obtaining sports application authorization data and determining that the user is exercising today, a sports element can be added to the stylized image to obtain the following information: Fig.8D Any of the target wallpapers shown.

[0106] Among them, step S502A, step S502B, step S502C and step S502D are executed in parallel, and one or more of them can be executed at the same time.

[0107] In the disclosed embodiment, based on the permissions of multiple terminal applications granted by the user, terminal application authorization data can be extracted, elements related to the user's daily life can be added to the stylized image, and a target wallpaper close to the user's life can be obtained to enhance the user experience.

[0108] It is understandable that users can limit the application permissions obtained by the theme application used to generate wallpaper according to personal needs, such as only authorizing the weather application permissions for the theme application. In this case, the theme application can only add weather elements to the stylized image based on the weather application authorization data and generate the target wallpaper.

[0109] It is further understood that the theme application can intelligently add new elements to the stylized image based on the application permissions authorized by the user. In one example, when the theme application has permissions for weather, photo album, calendar, and sports applications, the theme application can add one or more related elements to the stylized image based on the collected data. For example, when it is determined that the photo album does not have historical photos and today's travel photos, today is not a special date, and no sports are performed today, the theme application can only add weather elements to the stylized image.

[0110] In the disclosed embodiment, wallpaper is generated based on data manually collected by the user. To ensure the legality and compliance of the generated wallpaper, the data manually collected by the user needs to be reviewed. In one example, for data manually collected by the user (such as images in the album, settings in the calendar, and other information), the Resnet50 model and the Transformer model are used to determine whether the image is compliant based on the image data and text data, and classify the image quality. If there is non-compliant content or the image quality is too low, exit and stop generating wallpaper; if the data content is compliant and the image quality is high, proceed to the next step of data analysis and continue generating wallpaper.

[0111] In the embodiment of the present disclosure, after obtaining the target wallpaper that can be used as the terminal wallpaper, the target wallpaper can be further processed to obtain a wallpaper that better meets the user's needs. The following embodiment of the present disclosure further describes the method for obtaining the target wallpaper.

[0112] Fig. 9 FIG. 1 is a flow chart of a method for generating a terminal theme according to another exemplary embodiment. Fig. 9 As shown, the method includes step S601 to step S602.

[0113] In step S601, one or more replacement processes of element replacement, scene replacement and style replacement are performed on the third image that has completed AI conversion.

[0114] In step S602, the third image after replacement processing is determined as the target wallpaper.

[0115] In the disclosed embodiment, after obtaining the target wallpaper, the user can further issue a replacement instruction to replace the elements in the target wallpaper (such as butterflies, yellow ducks, rabbits, etc.), or replace the scenes other than the main characters in the target wallpaper (such as lakes, grasslands, gardens, etc.), or replace the style of the target wallpaper (such as aesthetic style, Q-version characters, campus style, etc.), and further process the target wallpaper to finally obtain the target wallpaper that meets the user's needs.

[0116] In an exemplary embodiment of the present disclosure, for a generated target wallpaper of a semi-realistic style, elements in the target wallpaper may be replaced to obtain Fig. 10A The target wallpaper after the elements shown in the figure are replaced; the style characteristics of the target wallpaper can be replaced (such as changing from a cute style to an aesthetic style), and the following are obtained: Fig. 10B The target wallpaper after the style is replaced as shown; the scene in the target wallpaper can be replaced to obtain Fig. 10C The scene shown is the target wallpaper after replacement.

[0117] In the disclosed embodiment, the user may further customize the generated target wallpaper, replace one or more of the scene, elements and style of the target wallpaper, and finally obtain the wallpaper that best suits the user's preferences.

[0118] In the embodiment of the present disclosure, in the process of generating wallpaper, the generation process needs to meet two conditions: 1. Ensure that the generated wallpaper has a high degree of similarity with the original image, and 2. The generated wallpaper needs to be modified and edited according to the parsing results of the user's authorization data. In one example, the present disclosure generates wallpaper based on the Stable Diffusion diffusion model. The Stable Diffusion model injects text information into the image denoising process through the cross-attention mechanism, and guides the image generation Inpainting method to achieve content editing and modification by adding a mask area to the image. The Prompt2Prompt method is used to modify the weight activation value of the text-image cross-attention of Stable Diffusion, which has the advantages of not requiring retraining and higher flexibility.

[0119] In an exemplary embodiment of the present disclosure, the user authorized data information is added based on the user's existing wallpaper to maintain the similarity between the original image and the new wallpaper. The initial noise is obtained by directly adding noise to the original image through the image-generated image diffusion model. The specific noise addition formula is as follows:

[0120]

[0121] This paper adopts the inverse process denoising method of diffusion model (Denoising Diffusion Implicit Models, DDIM) to obtain the initial noise image to ensure that the denoising process is reversible. The final generated wallpaper is too different from the original image content and cannot meet the actual use requirements. The denoising formula is as follows:

[0122]

[0123] in, is a hyperparameter used to control the noise intensity, x t-1 is the noise image at time t-1, x0=I, I represents the original image, ∈(x t-1 ,t-1) is the prediction noise of the diffusion model, x t Represents the initial noisy image obtained by the inverse process of DDIM.

[0124] In the embodiments of the present disclosure, the diffusion model denoising process will introduce random noise. In one example, in order to ensure the similarity between the generated wallpaper and the original image, while using the DDIM inverse process to add noise, the present disclosure also uses a softedge edge detection method to extract image edge information. The softedge edge detection method can extract details and contours in the image, and can better extract the edge features of hair, animals and curved objects. The present disclosure uses the softedge edge detection method to control the contour information of the generated wallpaper to be similar to the original image. Furthermore, the present disclosure combines ControlNet technology to inject the edge detection information extracted by softedge into the denoising process of the diffusion model, thereby enhancing the consistency between the wallpaper generation process and the original image.

[0125] In the exemplary embodiment of the present disclosure, the image generated by Stable Diffusion may have problems of low resolution and poor texture details. The Real-ESRGAN and GFPGAN generation models are used to generate wallpapers for super-resolution and face repair to improve the aesthetics of the final result and the quality of wallpaper generation.

[0126] In an exemplary embodiment of the present disclosure, Fig.11 The wallpaper generation method shown in the figure, according to the image processing method shown in the above exemplary embodiment, uses the following method to generate wallpaper: obtain and parse user authorization behavior data, and the user authorization behavior data is the application information of the terminal. The prompt word is added / modified / deleted by the Prompt2Prompt method to control the image editing area and content. For the original image used to generate the wallpaper, the initial noise image is obtained by the inverse process denoising method of the diffusion model (Denoising Diffusion Implicit Models, DDIM) to ensure that the denoising process is reversible. The image edge information is extracted by the softedge edge detection method, and the consistency of the edge information is maintained by the ControlNet technology. After completing the processing of the original image and obtaining the text information obtained based on the user authorization data, the text information obtained based on the user authorization data is injected into the image denoising process through the cross attention mechanism through the Stable Diffusion model, and the image generation is guided to complete the post-processing of the image and generate a new wallpaper combined with the user authorization data. It can be understood that when the original image meets the user's expectations, only the original image can be post-processed based on the user's choice to simply optimize the original image.

[0127] In the disclosed embodiment, in order to ensure the consistency between the final generated wallpaper and the face in the original image, it is necessary to fuse the face area in the input image. In one example, the method of fusing the face area includes three processes: 1. Use the face key point detection model for natural scenes (Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild, PIPNet) to detect the 5-point face key point coordinates (left and right pupils, nose tip, forehead, chin) in the original image, 2. Extract the 5-point face key point coordinates of the left and right pupils, nose tip, forehead, and chin from the generated 106-point face key point coordinates, 3. Calculate the affine transformation matrix based on the 5-point key point coordinates of the two groups of faces, and perform affine transformation on the face in the original image to make it close to the angle of the generated face. Using the VGG model as the image encoder, the 512-dimensional feature vectors output by the maximum pooling layer maxpool-5 are extracted from the original face area and the generated face area, and the Mixing of the style transfer adversarial network StyleGAN2 is used for feature fusion to generate the fused face and replace the face in the generated image to achieve the face-changing function, and the face-changing function can be realized quickly. Furthermore, Real-ESRGAN and GFPGAN are used to perform super-resolution and facial repair on the generated wallpaper to improve the details and generation quality of the image.

[0128] In an exemplary embodiment of the present disclosure, Fig.12 The wallpaper generation method shown generates wallpaper based on the original image input by the user in the following manner: the user inputs the original image in the local album, performs image compliance detection, extracts image elements after the detection, and generates human key nodes based on the human elements in the image. Generates an intermediate image based on the human key nodes and other elements in the image. Obtains face data based on the original image, performs face alignment and face fusion on the faces of the characters in the original image and the intermediate image based on the face data, and retains most of the facial features in the original image. Then, the face-fused image is post-processed to obtain and output a new wallpaper.

[0129] In the embodiment of the present disclosure, a terminal theme associated with the target wallpaper can be further obtained based on the target wallpaper, thereby obtaining a unified terminal theme and terminal wallpaper (ie, the target wallpaper). The following embodiment of the present disclosure describes a method for generating a terminal theme.

[0130] In one implementation of the disclosed embodiment, the first display attribute includes one or more of color, element and style, the element includes one or more of character dress, character behavior, location scene and object. The second display attribute includes one or more of color, element and style.

[0131] In the disclosed embodiment, after obtaining the target wallpaper that can be used as the terminal wallpaper, the corresponding application icons (including large icons and small icons) and the screen-off display interface are obtained according to the color, style, elements (character decorations, character behavior, location scenes, etc.) and other elements of the target wallpaper, thereby obtaining a terminal theme with the same identity.

[0132] It is understandable that the application icons and the screen-off display interface can contain limited elements. When generating the application icons and the screen-off display interface, the elements with prominent features in the target wallpaper are extracted, and the application icons and the screen-off display interface are generated based on the elements with prominent features.

[0133] In an exemplary embodiment of the present disclosure, according to the acquired Fig.13 The target wallpaper shown in the figure obtains the terminal theme. The color elements and style elements in the target wallpaper are extracted to generate Fig.14A The theme interface shown, such as Fig. 14B The small application icon shown in Fig. 14C The large application icon shown, such as Fig.14D The screen display interface shown.

[0134] In the disclosed embodiment, after the user obtains a terminal theme that meets personal needs, the generated terminal theme can be stored as a template to facilitate theme switching when the terminal is used, or the theme stored as a template can be uploaded to a sharing platform for other users to download and use.

[0135] Fig.15 FIG. 1 is a flow chart of a method for generating a terminal theme according to another exemplary embodiment. Fig.15 As shown, the method includes step S701 to step S702.

[0136] In step S701, the terminal theme is obtained.

[0137] In step S702, based on the instruction issued by the user, the target wallpaper and the terminal theme are stored as a theme template, and the theme template is uploaded to the cloud for sharing.

[0138] In the disclosed embodiment, the user will obtain a large number of wallpapers and corresponding themes based on personal needs. To ensure that the generated wallpapers and themes can be switched and reused in subsequent use, after obtaining the terminal theme that meets personal needs, the user can issue an instruction to store the generated terminal theme as a template.

[0139] Furthermore, users can also upload themes that have been stored as templates to the sharing platform for other users to download and use. It is understandable that when users upload themes to the sharing platform, they can set a payment window, and other users must pay to download, so that users who share themes can gain benefits and encourage users to create. By allowing users to design and upload theme templates themselves, the design cost of manufacturers can be reduced, thereby reducing the development cost of themes.

[0140] In an exemplary embodiment of the present disclosure, Fig.16 As shown in the effect diagram of the terminal theme generation method, the theme application of the terminal in the present disclosure processes the task picture to generate the terminal wallpaper: after obtaining the task picture, the Miyazaki style is selected from the realistic style, Japanese comic style, CG style, Chinese style and Miyazaki style, and then after selecting the scene and elements, an exclusive wallpaper is generated through AI, and then the exclusive wallpaper is processed again, the scene is modified, new elements (dog) are added, and the character's expression is changed to generate the final terminal wallpaper.

[0141] In an exemplary embodiment of the present disclosure, the target wallpaper is obtained by AI intelligent image generation technology, which involves multiple aspects such as image generation, image restoration, and image transformation. The most representative of these is the Generative Adversarial Networks (GAN) technology. The present disclosure can generate highly realistic images through the Generative Adversarial Networks. The present disclosure can generate higher resolution and more diverse images through large Generative Adversarial Networks (BigGAN); generate images with higher levels of detail and texture through Style Generative Adversarial Networks (StyleGAN); and achieve image style conversion through Cycle Generative Adversarial Networks (CycleGAN), converting the style of one picture to the style of another picture.

[0142] An exemplary embodiment of the present disclosure shows a method for generating a terminal theme, such as Fig.17 As shown in the flowchart of the method for generating a theme in a terminal, the method comprises the following steps: in response to completing the preprocessing of the original image, starting the theme generation process, in response to the user selecting a style, performing the style generation process, such as Fig.18As shown in the flowchart of the method for generating terminal image style, the style generation process is as follows: in response to passing the privacy / user agreement, the user uploads a picture in the theme application, and the theme application makes a compliance judgment on the uploaded picture. If the picture is not compliant, the user re-uploads the picture; if the picture is compliant, the image is processed based on the large model used for image processing in the cloud to generate a picture that can be used as the terminal wallpaper. After completing the style generation process, the picture sharing process can be carried out, such as Fig.19 As shown in the flowchart of the picture sharing method in , the image sharing process includes the following steps: returning the generated image to the local computer, the user storing the image as a template and uploading it to the cloud to share it with other users. After completing the picture sharing, determine whether the user selects additional functions. When the user does not select additional functions, the entire process ends; when the user selects additional functions, the wallpaper is further processed and a theme associated with the wallpaper is generated. When the wallpaper is reprocessed, based on the "surprise wallpaper" function, the style of the generated wallpaper is further generated, the wallpaper style is changed, and the final target wallpaper is obtained. Then, the wallpaper is applied, downloaded and shared according to user needs, and the reprocessing of the wallpaper ends. When generating a theme associated with the wallpaper, the user can customize the theme based on the generated wallpaper and the preset template through the "customize theme" function. After saving the theme, the user can choose whether to store the customized theme as a template. When the user does not choose to save the customized theme as a template, the theme customization process ends. When the user chooses to save the customized theme as a template, the customized theme is uploaded to the cloud and reviewed. After the review is completed, the theme customization process ends. Through the present disclosure, users can automatically generate a variety of wallpapers and themes based on the character images in the local album of the terminal, thereby improving the diversity of wallpapers and themes and better meeting user needs; in addition, the present disclosure automatically generates themes based on the generated wallpapers, and the wallpapers and corresponding themes are unified, thereby improving the visual experience of users when using the terminal; in addition, the present disclosure allows users to create templates for themes and wallpapers, and the templates can be uploaded to relevant platforms for other users to download and use, thereby improving the efficiency of creating theme templates and reducing the design costs of manufacturers.

[0143] Based on the same concept, the embodiment of the present disclosure also provides a terminal theme generating device 100.

[0144] It is understandable that the terminal theme generation device 100 provided in the embodiment of the present disclosure includes hardware structures and / or software modules corresponding to the execution of each function in order to realize the above functions. In combination with the units and algorithm steps of each example disclosed in the embodiment of the present disclosure, the embodiment of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present disclosure.

[0145] Fig. 20 1 is a block diagram of a terminal theme generating device 100 according to an exemplary embodiment. Fig. 20 The device includes a generating unit 101 and a processing unit 102.

[0146] The generating unit 101 is configured to generate a target wallpaper based on a first image selected by a user.

[0147] The processing unit 102 is configured to generate a terminal theme according to a first display attribute of the image content in the target wallpaper.

[0148] The terminal theme includes an application display icon, and the application display icon corresponds to a second display attribute; the second display attribute is determined based on the first display attribute.

[0149] In one embodiment, the first image is a picture including a target object. The generating unit 101 generates a target wallpaper based on the first image selected by the user in the following manner: the first image is determined as the target wallpaper. Or the first image is preprocessed to obtain a second image including at least some information elements in the target object, and the target wallpaper is generated based on the second image, wherein the preprocessing includes: one or more of text removal processing, clarity processing, and background weakening processing, and the target wallpaper includes at least some information elements in the target object.

[0150] In one implementation, the generating unit 101 generates the target wallpaper in the following manner: determining the style option selected by the user, performing stylization processing on the first image to obtain a third image matching the style option, and generating the target wallpaper based on the third image.

[0151] In one implementation, the generating unit 101 generates the target wallpaper according to the third image by: determining the third image as the target wallpaper. Or, according to the application data in the terminal, performing AI conversion on the third image, and determining the third image after AI conversion as the target wallpaper.

[0152] In one embodiment, the application data includes one or more of album application data, calendar application data, weather application data, and sports application data. The generation unit 101 performs AI conversion on the third image according to the application data in the terminal in the following manner: obtaining a target image in the album application, adding some elements in the target image to the third image, and performing AI conversion on the third image with added elements, the target image is an image of a predefined scene, an image with a shooting date associated with the current date. And / or obtaining date data in the calendar application, adding special date elements in the date data to the third image, and performing AI conversion on the third image with added elements, the special date elements include holiday elements, birthday elements, and anniversary elements. And / or obtaining weather data in the weather application, adding real-time weather elements in the weather data to the third image, and performing AI conversion on the third image with added elements. And / or

[0153] The motion data and the body status data are acquired in the motion application, and the motion elements and the body status elements in the motion data and the body status data are added to the third image, and the third image with the added elements is AI converted.

[0154] In one implementation, the generating unit 101 is further configured to: perform one or more replacement processes of element replacement, scene replacement, and style replacement on the third image that has completed the AI ​​conversion, and determine the third image after the replacement process as the target wallpaper.

[0155] In one embodiment, the first display attribute includes one or more of color, element and style, the element includes one or more of character dress, character behavior, location scene and object. The second display attribute includes one or more of color, element and style.

[0156] In one implementation, the processing unit 102 is further configured to: based on an instruction issued by a user, store the target wallpaper and the terminal theme as a theme template, and upload the theme template to a cloud for sharing.

[0157] Fig.21 1 is a block diagram of a device 200 for generating a terminal theme according to an exemplary embodiment. The device 200 may be provided as a terminal. For example, the device 200 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0158] Reference Fig.21 , the device 200 may include one or more of the following components: a processing component 202 , a memory 204 , a power component 206 , a multimedia component 208 , an audio component 210 , an input / output (I / O) interface 212 , a sensor component 214 , and a communication component 216 .

[0159] The processing component 202 generally controls the overall operation of the device 200, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 202 may include one or more processors 220 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 202 may include one or more modules to facilitate interaction between the processing component 202 and other components. For example, the processing component 202 may include a multimedia module to facilitate interaction between the multimedia component 208 and the processing component 202.

[0160] The memory 204 is configured to store various types of data to support operations on the device 200. Examples of such data include instructions for any application or method operating on the device 200, contact data, phone book data, messages, pictures, videos, etc. The memory 204 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0161] The power component 206 provides power to the various components of the device 200. The power component 206 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 200.

[0162] The multimedia component 208 includes a screen that provides an output interface between the device 200 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 208 includes a front camera and / or a rear camera. When the device 200 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0163] The audio component 210 is configured to output and / or input audio signals. For example, the audio component 210 includes a microphone (MIC), and when the device 200 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 204 or sent via the communication component 216. In some embodiments, the audio component 210 also includes a speaker for outputting audio signals.

[0164] I / O interface 212 provides an interface between processing component 202 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0165] The sensor assembly 214 includes one or more sensors for providing various aspects of the status assessment of the device 200. For example, the sensor assembly 214 can detect the open / closed state of the device 200, the relative positioning of components, such as the display and keypad of the device 200, the sensor assembly 214 can also detect the position change of the device 200 or a component of the device 200, the presence or absence of user contact with the device 200, the orientation or acceleration / deceleration of the device 200 and the temperature change of the device 200. The sensor assembly 214 can include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 214 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 214 can also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

[0166] The communication component 216 is configured to facilitate wired or wireless communication between the device 200 and other devices. The device 200 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 216 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 216 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0167] In an exemplary embodiment, the apparatus 200 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0168] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 204 including instructions, and the instructions can be executed by the processor 220 of the device 200 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0169] It is to be understood that in the present disclosure, "plurality" refers to two or more than two, and other quantifiers are similar. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. The singular forms "a", "the" and "the" are also intended to include plural forms, unless the context clearly indicates other meanings.

[0170] It is further understood that the terms "first", "second", etc. are used to describe various information, but such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other, and do not indicate a specific order or degree of importance. In fact, the expressions "first", "second", etc. can be used interchangeably. For example, without departing from the scope of the present disclosure, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information.

[0171] It will be further understood that the terms “center”, “longitudinal”, “lateral”, “front”, “back”, “up”, “down”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present embodiment and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation.

[0172] It can be further understood that, unless otherwise specified, “connection” includes a direct connection without other components between the two, and also includes an indirect connection with other components between the two.

[0173] It is further understood that, although the operations are described in a specific order in the drawings in the embodiments of the present disclosure, it should not be understood as requiring the operations to be performed in the specific order shown or in a serial order, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0174] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present solution, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure.

[0175] It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the scope of the appended claims.

Claims

1. A method for generating a terminal theme, characterized in that: include: generating a target wallpaper based on the first image selected by the user; generating a terminal theme according to the first display attribute of the image content in the target wallpaper, wherein the terminal theme includes an application display icon corresponding to the second display attribute; The second display attribute is determined based on the first display attribute.

2. The method according to claim 1, characterized in that The first image is a picture including a target object; The step of generating a target wallpaper based on the first image selected by the user comprises: determining the first image as the target wallpaper; or The first image is preprocessed to obtain a second image including at least some information elements in the target object, and a target wallpaper is generated based on the second image, wherein the preprocessing includes: one or more of text removal, clarity and background weakening, and the target wallpaper includes at least some information elements in the target object.

3. The method according to claim 1 or 2, characterized in that: The generating of the target wallpaper comprises: Determine the style option selected by the user; Performing stylization processing on the first image to obtain a third image matching the style option; A target wallpaper is generated according to the third image.

4. The method according to claim 3, characterized in that Generating a target wallpaper according to the third image includes: determining the third image as the target wallpaper; or According to the application data in the terminal, the third image is AI-converted, and the third image after the AI-converted is determined as the target wallpaper.

5. The method according to claim 4, characterized in that The application data includes one or more of album application data, calendar application data, weather application data and sports application data; The performing AI conversion on the third image according to the application data in the terminal includes: Acquire a target image in the photo album application, add some elements in the target image to the third image, and perform AI conversion on the third image with the added elements, wherein the target image is an image of a predefined scene and an image whose shooting date is associated with the current date; and / or Obtaining date data in the calendar application, adding special date elements in the date data to the third image, and performing AI conversion on the third image with the added elements, wherein the special date elements include holiday elements, birthday elements, and anniversary elements; and / or Acquire weather data in the weather application, add real-time weather elements in the weather data to the third image, and perform AI conversion on the third image with the added elements; and / or The motion data and the body state data are acquired in the motion application, and the motion elements and the body state elements in the motion data and the body state data are added to the third image, and the third image with the added elements is AI converted.

6. The method according to claim 4, characterized in that The method further comprises: Performing one or more replacement processes of element replacement, scene replacement and style replacement on the third image that has completed the AI ​​conversion; The third image after replacement processing is determined as the target wallpaper.

7. The method according to claim 1, characterized in that The first display attribute includes one or more of color, element and style, and the element includes one or more of character dress, character behavior, location scene and object; The second display attribute includes one or more of the color, element and style.

8. The method according to claim 1, characterized in that The method further comprises: Based on the instruction issued by the user, the target wallpaper and the terminal theme are stored as a theme template, and the theme template is uploaded to the cloud for sharing.

9. A terminal theme generating device, characterized in that: include: A generating unit, configured to generate a target wallpaper based on a first image selected by a user; A processing unit, configured to generate a terminal theme according to the first display attribute of the image content in the target wallpaper, wherein the terminal theme includes an application display icon corresponding to the second display attribute; The second display attribute is determined based on the first display attribute.

10. The device according to claim 9, characterized in that The first image is a picture including a target object; The generating unit generates a target wallpaper based on the first image selected by the user in the following manner: determining the first image as the target wallpaper; or The first image is preprocessed to obtain a second image including at least some information elements in the target object, and a target wallpaper is generated based on the second image, wherein the preprocessing includes: one or more of text removal, clarity and background weakening, and the target wallpaper includes at least some information elements in the target object.

11. The device according to claim 9 or 10, characterized in that The generation unit generates the target wallpaper in the following way: Determine the style option selected by the user; Performing stylization processing on the first image to obtain a third image matching the style option; A target wallpaper is generated according to the third image.

12. The device according to claim 11, characterized in that The generating unit generates the target wallpaper according to the third image in the following manner: determining the third image as the target wallpaper; or According to the application data in the terminal, the third image is AI-converted, and the third image after the AI-converted is determined as the target wallpaper.

13. The device according to claim 12, characterized in that The application data includes one or more of album application data, calendar application data, weather application data and sports application data; The generating unit performs AI conversion on the third image according to the application data in the terminal in the following manner: Acquire a target image in the photo album application, add some elements in the target image to the third image, and perform AI conversion on the third image with the added elements, wherein the target image is an image of a predefined scene and an image whose shooting date is associated with the current date; and / or Acquire date data in the calendar application, add special date elements in the date data to the third image, and perform AI conversion on the third image with the added elements, wherein the special date elements include holiday elements, birthday elements, and anniversary elements; and / or Acquire weather data in the weather application, add real-time weather elements in the weather data to the third image, and perform AI conversion on the third image with the added elements; and / or The motion data and the body state data are acquired in the motion application, and the motion elements and the body state elements in the motion data and the body state data are added to the third image, and the third image with the added elements is AI converted.

14. The device according to claim 12, characterized in that The generating unit is further configured to: Performing one or more replacement processes of element replacement, scene replacement and style replacement on the third image that has completed the AI ​​conversion; The third image after replacement processing is determined as the target wallpaper.

15. The device according to claim 9, characterized in that The first display attribute includes one or more of color, element and style, and the element includes one or more of character dress, character behavior, location scene and object; The second display attribute includes one or more of the color, element and style.

16. The device according to claim 9, characterized in that The processing unit is also used for: Based on the instruction issued by the user, the target wallpaper and the terminal theme are stored as a theme template, and the theme template is uploaded to the cloud for sharing.

17. A terminal theme generating device, characterized in that: include: processor: a memory for storing processor-executable instructions; Wherein, the processor is configured to: execute the terminal theme generation method according to any one of claims 1 to 8.

18. A storage medium, characterized in that: The storage medium stores instructions, and when the instructions in the storage medium are executed by a processor, the processor is enabled to execute the terminal theme generating method according to any one of claims 1 to 8.

Images