EP-4742031-A1 - IMAGE DISPLAY METHOD, IMAGE GENERATION METHOD, AND ELECTRONIC DEVICE

EP4742031A1EP 4742031 A1EP4742031 A1EP 4742031A1EP-4742031-A1

Abstract

This application relates to the terminal field, and provides an image display method, an image generation method, and an electronic device, to resolve a problem that a wallpaper is weakly associated with a user and diversity of the wallpaper is low. A specific solution is as follows: When a user starts a first application, for example, a desktop application, a lock screen application, a screen-off application, or a system application, a target image related to multimedia content browsed by the user in another application may be displayed, and target text related to usage data generated when the user browses the multimedia content in the another application may be displayed. The target image and the target text that are related to the multimedia content browsed by the user are displayed in an interface of the lock screen application, the desktop application, the screen-off application, the system application, or the like, to improve association between displayed content and the user. In addition, a plurality of target images and a plurality of pieces of target text may be generated based on a diverse browsing history of the user, to improve diversity of displayed content.

Inventors

WANG, GUOHUA

Assignees

Huawei Technologies Co., Ltd.

Dates

Publication Date: 20260513
Application Date: 20240830

Claims (20)

An image display method, applied to a terminal, wherein the method comprises: receiving a first operation of starting a first application by a user; and displaying a target image and target text in response to the first operation, wherein the target image is related to at least first data; the first data indicates multimedia content browsed by the user by using a second application; the first data comprises at least one of the following data: metadata of the multimedia content, and media data of the multimedia content; the media data comprises at least one of the following data of the multimedia content: text, audio, a video, and an image; the target text is related to at least second data; and the second data indicates usage data generated when the user browses the multimedia content by using the second application.
The method according to claim 1, wherein the target image is further related to a target display style, and/or the target text is further related to the target display style.
The method according to claim 2, wherein the target display style is a display style selected by the user from a plurality of displayed alternative display styles; or the target display style is a display style, among preset display styles, that is determined based on the multimedia content browsed by the user and that best matches the user.
The method according to any one of claims 1 to 3, wherein the method further comprises: displaying a second control; receiving a fourth operation of the user on the second control; and in response to the fourth operation, displaying, in the second application, multimedia content corresponding to the target image.
The method according to any one of claims 2 to 4, wherein the method further comprises: sending the target display style to a server.
The method according to any one of claims 1 to 5, wherein before displaying the target image and the target text, the method further comprises: receiving the target image and the target text from the server.
The method according to claim 5 or 6, wherein the method further comprises: displaying a first control; receiving a second operation of the user on the first control; and sending first information to the server in response to the second operation, wherein the first information indicates the server to delete the target image and the target text from an image library corresponding to the user, and the image library stores a plurality of images and a plurality of pieces of text that are generated based on the multimedia content browsed by the user and the usage data generated when the user browses the multimedia content.
The method according to any one of claims 2 to 4, wherein the method further comprises: obtaining the first data and the second data; and generating the target image and the target text through a target model by using the first data, the second data, and the target display style as inputs, wherein the target model has a function of generating a corresponding image and corresponding text based on input multimedia content that is browsed by the user and an input display style.
The method according to claim 8, wherein the target model comprises an image generation model and a text generation model, and generating the target image and the target text through the target model by using the first data, the second data, and the target display style as the inputs comprises: generating the target image through the image generation model by using the first data and the target display style as inputs; and generating the target text through the text generation model by using the second data as an input.
The method according to claim 9, wherein when the first data comprises at least the metadata, the method further comprises: obtaining a feature vector of the first data; and generating a first descriptor based on the metadata and the target display style, and generating a second descriptor based on the second data, wherein the first descriptor describes a feature of an image that needs to be generated, and the second descriptor describes a feature of text that needs to be generated; generating the target image through the image generation model by using the first data and the target display style as the inputs comprises: generating the target image through the image generation model by using the feature vector of the first data and the first descriptor as inputs; and generating the target text through the text generation model by using the second data as the input comprises: generating the target text through the text generation model by using the second descriptor as an input.
The method according to any one of claims 8 to 10, wherein the method further comprises: displaying a first control; receiving a second operation of the user on the first control; and in response to the second operation, deleting the target image and the target text from an image library corresponding to the user, wherein the image library stores a plurality of images and a plurality of pieces of text that are generated based on the multimedia content browsed by the user and the usage data generated when the user browses the multimedia content.
The method according to any one of claims 1 to 11, wherein the first application is a lock screen application, and displaying the target image and the target text comprises: displaying the target image in a lock screen interface; and receiving a third operation of the user in the lock screen interface, and displaying the target text.
The method according to any one of claims 1 to 11, wherein displaying the target image and the target text comprises: when the first application is a desktop application, displaying the target image and the target text on a desktop as a desktop wallpaper; or when the first application is a screen-off application, displaying the target image and the target text in a screen-off interface as widgets; or when the first application is a system application, displaying the target image and the target text are displayed in a startup interface of the first application as a startup image.
An image generation method, applied to a server, wherein the method comprises: obtaining first data and second data of a terminal, wherein the first data indicates multimedia content browsed by a user corresponding to the terminal by using a second application; the first data comprises at least one of the following data: metadata of the multimedia content, and media data of the multimedia content; the media data comprises at least one of the following data of the multimedia content: text, audio, a video, and an image; and the second data indicates usage data generated when the user browses the multimedia content by using the second application; generating a target image and target text based on the first data and the second data, wherein the target image is related to at least the first data, and the target text is related to at least the second data; and sending the target image and the target text to the terminal.
The method according to claim 14, wherein the target image is further related to a target display style, and/or the target text is further related to the target display style.
The method according to claim 15, wherein the method further comprises: receiving the target display style sent by the terminal, wherein the target display style is a display style selected by the user from a plurality of alternative display styles displayed on the terminal.
The method according to claim 15, wherein the target display style is a display style, among preset display styles, that is determined based on the multimedia content browsed by the user and that best matches the user.
The method according to any one of claims 15 to 17, wherein generating the target image and the target text based on the first data and the second data comprises: generating the target image and the target text through a target model by using the first data, the second data, and the target display style as inputs, wherein the target model has a function of generating a corresponding image and corresponding text based on input multimedia content that is browsed by the user and an input display style.
The method according to claim 18, wherein the target model comprises an image generation model and a text generation model, and generating the target image and the target text through the target model by using the first data, the second data, and the target display style as the inputs comprises: generating the target image through the image generation model by using the first data and the target display style as inputs; and generating the target text through the text generation model by using the second data as an input.
The method according to claim 19, wherein when the first data comprises at least the metadata, the method further comprises: obtaining a feature vector of the first data; and generating a first descriptor based on the metadata and the target display style, and generating a second descriptor based on the second data, wherein the first descriptor describes a feature of an image that needs to be generated, and the second descriptor describes a feature of text that needs to be generated; generating the target image through the image generation model by using the first data and the target display style as the inputs comprises: generating the target image through the image generation model by using the feature vector of the first data and the first descriptor as inputs; and generating the target text through the text generation model by using the second data as the input comprises: generating the target text through the text generation model by using the second descriptor as an input.

Description

This application claims priority to Chinese Patent Application No. 202311523564.9, filed with the China National Intellectual Property Administration on November 15, 2023 and entitled "IMAGE DISPLAY METHOD, IMAGE GENERATION METHOD, AND ELECTRONIC DEVICE", which is incorporated herein by reference in its entirety. TECHNICAL FIELD Embodiments of this application relate to the terminal field, and in particular, to an image display method, an image generation method, and an electronic device. BACKGROUND In the conventional technology, on a terminal, for example, a mobile phone or a tablet computer, a wallpaper of a lock screen interface of the terminal is usually an image selected by a user, or an image randomly selected by the terminal from a preset wallpaper image library. With regard to the method for using the image selected by the user as the lock screen wallpaper, because the lock screen wallpaper does not change after being selected by the user, diversity of the lock screen wallpaper is insufficient. With regard to the method for using the image randomly selected by the terminal from the preset wallpaper image library as the lock screen wallpaper, although this method can enable the lock screen wallpaper to continuously change to meet a diversity requirement, images serving as the lock screen wallpaper are usually weakly associated with the user, affecting use experience of the user. It can be learned that, in the methods in the conventional technology, the terminal cannot provide a wallpaper that is highly associated with the user and that meets a diversity requirement. SUMMARY Embodiments of this application provide an image display method, an image generation method, and an electronic device, to resolve a problem in the conventional technology that a wallpaper is weakly associated with a user and diversity of the wallpaper is low. According to a first aspect of embodiments of this application, this application provides an image display method, applied to a terminal, and including: receiving a first operation of starting a first application by a user; and displaying a target image and target text in response to the first operation. The target image is related to at least first data. The first data indicates multimedia content browsed by the user by using a second application. The first data includes at least one of the following data: metadata of the multimedia content, and media data of the multimedia content. The media data includes at least one of the following data of the multimedia content: text, audio, a video, and an image. The target text is related to at least second data. The second data indicates usage data generated when the user browses the multimedia content by using the second application. In the technical solution provided in the first aspect, when the user starts the first application, for example, a desktop application, a lock screen application, a screen-off application, or a system application, a target image related to multimedia content browsed by the user in another application may be displayed, and target text related to usage data generated when the user browses the multimedia content in the another application may be displayed. In this way, the target image and the target text that are related to the multimedia content browsed by the user can be displayed in an interface of the lock screen application, the desktop application, the screen-off application, the system application, or the like. That is, both the target image and the target text are related to the user. If the user has historically browsed a large amount of multimedia content, corresponding target images and target text may be respectively generated based on a plurality of pieces of multimedia content browsed by the user, to improve diversity of a lock screen interface, a desktop interface, a screen-off interface, or the like. Such target images and target text help avoid monotony of an image generated based on a template, to improve use experience of the user. In addition, a lock screen wallpaper, a desktop wallpaper, and a widget in the screen-off interface may actually serve as a traffic entry to divert traffic to an application on the terminal. Such target images and target text can also provide a good opportunity for traffic display. In a possible implementation, the target image is further related to a target display style, and/or the target text is further related to the target display style. In a possible implementation, the target display style is a display style selected by the user from a plurality of displayed alternative display styles; or the target display style is a display style, among preset display styles, that is determined based on the multimedia content browsed by the user and that best matches the user. In a possible implementation, the method further includes: displaying a second control; receiving a fourth operation of the user on the second control; and in response to the fourth operation,