AI-Generated Wallpaper Setting for Low-Power Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wallpaper applications provide limited personalized experiences, offering mainly static or simple dynamic images, failing to utilize artificial intelligence effectively for tailored wallpaper settings on devices with varying computing power.
Innovation Solution
A method involving an electronic device with a display, processor, and memory, utilizing a preset wallpaper generation model to match candidate wallpapers based on user input conditions, generating and displaying personalized wallpapers, and leveraging cloud resources for devices with low computing power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If AI-generated wallpapers are implemented on devices with limited computing power, then personalized wallpaper experience is improved, but device performance and response speed deteriorate
Solution Approach 1:
The system segments the wallpaper generation process into two parts: complex AI generation performed offline on powerful devices (cloud/server) to create the wallpaper database, and simple matching operations performed locally on terminal devices with limited computing power. This segmentation allows personalized wallpapers to be generated without burdening the terminal device's computing resources, thus maintaining fast response speed while achieving personalization.
Solution Approach 2:
A cloud server acts as an intermediary between the user's terminal device and the AI generation model. The server handles the computationally intensive wallpaper generation tasks and returns pre-generated wallpapers to the terminal, which then performs only lightweight matching operations. This intermediary approach resolves the contradiction by offloading heavy computation while maintaining personalized service delivery.
2Adaptability or versatility
If complex AI models are used for wallpaper generation, then wallpaper personalization is improved, but computational resource consumption increases
Solution Approach 1:
The system separates the computationally intensive AI generation task from the lightweight matching task. Complex AI models run on cloud servers with abundant computational resources to generate diverse personalized wallpapers, while terminal devices only perform simple matching operations against the pre-generated database. This segmentation dramatically reduces computational resource consumption on user devices while maintaining high personalization quality.
Solution Approach 2:
The system performs wallpaper generation in advance during an offline training phase, creating a pre-generated wallpaper database before users need them. This preliminary action allows complex AI computations to be performed when computational resources are available (on servers), rather than consuming terminal device resources during user interaction, thus reducing real-time computational resource consumption while maintaining personalization capability.
3Adaptability or versatility
If more wallpaper options are provided, then user personalization needs are better met, but device storage requirements increase
Solution Approach 1:
The system pre-generates a comprehensive wallpaper database on the cloud server during an offline training phase, creating diverse personalized wallpapers in advance. This preliminary generation allows the system to offer extensive wallpaper selection diversity without requiring terminal devices to store large quantities of wallpapers locally. Users receive only the matched results from the pre-generated database, significantly reducing storage requirements while maintaining diverse selection options.
Data Source
AI summary
The present disclosure provides a method for wallpaper setting, an electronic device, and a computer-readable storage medium. The method for wallpaper setting is applicable to the electronic device, the electronic device includes a display, and the method for wallpaper setting includes the following. At least two wallpaper setting conditions are obtained. The at least two wallpaper setting conditions are compared with information tags of wallpapers in a wallpaper database, and candidate wallpapers each of which has information tags including the at least two wallpaper setting conditions are matched out from the wallpaper database, where the candidate wallpapers are generated through a preset wallpaper generation model according to a wallpaper generation sentence associated with the at least two wallpaper setting conditions. At least part of the candidate wallpapers is displayed on the display of the electronic device.