Dynamic UI Components for Faster Access to Relevant Content
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in navigating through large amounts of unorganized content on applications, making it difficult to find relevant actions or information, especially when they have simple queries or intents.
Innovation Solution
A computing system applies a large language model to user input and content of a graphical user interface to dynamically generate graphical components that suggest relevant outputs, such as applications, text, or links, based on user interactions and content analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If users manually navigate through large amounts of unorganized content in applications, then they can access all available information, but the time and effort required to find relevant actions or information increases significantly
Solution Approach 1:
The patent introduces an intermediary system comprising a machine learning model and graphical component generator that acts as a mediator between the user and the unorganized content. This intermediary automatically analyzes the content, user input, and context to generate relevant graphical components and suggestions, eliminating the need for users to manually search through large amounts of unorganized information while maintaining complete information access.
Solution Approach 2:
The system performs preliminary actions by automatically analyzing and organizing content before the user needs to access it. The machine learning model pre-processes the unorganized content, identifies relevant information, and generates appropriate graphical components in advance, so that when users provide input, they immediately receive curated suggestions rather than having to search through all content.
2Ease of operation
If the system provides detailed suggestions and generated graphical components, then user experience and ease of finding information improves, but the complexity of the system increases due to machine learning models and dynamic generation
Solution Approach 1:
The system implements self-service by enabling the machine learning model and graphical component generator to automatically perform the complex tasks of content analysis, suggestion generation, and UI component creation without requiring manual intervention. The system serves itself by using its own resources (processing power, algorithms) to handle the complexity internally while presenting a simplified interface to users.
3Adaptability or versatility
If the system dynamically generates custom graphical components based on user input and content analysis, then relevance and usefulness of suggestions improves, but the processing time and computational resources required increase
Solution Approach 1:
The system applies partial action by focusing its computational resources on generating only the most relevant graphical components and suggestions based on user input and context, rather than analyzing and generating all possible components. The machine learning model identifies and processes only the essential elements needed to provide relevant suggestions, avoiding unnecessary computation while maintaining high adaptability.
Data Source
AI summary
An example computing system receives an indication of an input detected at a location of an input device that corresponds to a graphical component from a first plurality of graphical components. The computing system retrieves information associated with at least a portion of content included in a current graphical user interface, and determines, based on one or more of the information associated with at least the portion of the content and the indication of the input, at least one prompt. The computing system determines, by applying the machine learning model to the at least one prompt and at least the portion of the content, one or more suggested outputs. The computing system generates instructions for generating a second plurality of graphical components, in which the second plurality of graphical components is associated with the one or more suggested outputs.