Generating user interface components using large language models

By applying a large language model to the computing system to generate custom graphical components based on time parameters, the problem of time consumption for users to navigate to functionality and information in multiple applications is solved. Dynamic updates of custom graphical components are achieved, ensuring that information and functionality remain up-to-date over time and improving the user experience.

CN122284994APending Publication Date: 2026-06-26GOOGLE LLC
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
GOOGLE LLC
Filing Date
2025-12-25
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Users face challenges and time-consuming processes when navigating across multiple applications to access functionality and information, especially as information changes over time and is difficult to keep up-to-date and relevant.

Method used

By applying large language models to the computing system, custom graphical components based on time parameters are generated, dynamically updated to meet user intent, and instruction sets are generated using natural language input. Application content and user activity are monitored to generate custom graphical components that provide up-to-date information and functionality.

Benefits of technology

It reduces the time and complexity for users when accessing functionality and information, and provides automatically updated custom graphical components to ensure that information and functionality stay up-to-date over time, thus improving the user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122284994A_ABST
    Figure CN122284994A_ABST
Patent Text Reader

Abstract

This disclosure generally relates to generating user interface components using large language models. An example computing system retrieves information from one or more applications and receives instructions from natural language input. The computing system applies a machine learning model to at least a portion of the information and at least a portion of the instructions from the natural language input to generate instructions for generating at least one graphical component, such as a custom widget. The instructions may include a time parameter for the at least one graphical component, wherein the computing system may update the instructions for generating the at least one graphical component based on the time parameter to update the at least one graphical component.
Need to check novelty before this filing date? Find Prior Art