Predictive Storage Placement via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
User interfaces for cloud storage systems often result in unintended data placement due to user errors during 'drag and drop' operations, which can lead to data security breaches or organizational issues, especially for users with mobility disabilities who struggle with precise input.
Innovation Solution
A method using machine learning to predict the intended target storage location by analyzing attributes of the source object and user patterns, modifying the user interface with visual cues like gravity effects and confidence-weighted lines to assist users in accurate data placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If visual cues and gravity effects are added to guide users, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The patent introduces visual cues and gravity effects as intermediary elements between the user and the drag-and-drop operation. These visual indicators act as mediators that guide the user's intention without requiring complex underlying system changes. The gravity effect specifically serves as an intermediary force that naturally guides the dragged object toward the predicted target location.
Solution Approach 2:
The patent replaces traditional mechanical precision requirements with visual and computational guidance systems. Instead of relying on users to precisely position objects through manual manipulation, the system uses machine learning predictions and visual feedback to substitute for the precision that would otherwise be required in the mechanical interaction.
2Reliability
If machine learning prediction is implemented, then reliability is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary actions by predicting the user's intended target location before the user completes the drag-and-drop operation. The machine learning model analyzes the drag trajectory and object attributes in advance to determine the most likely destination, allowing the system to prepare and provide guidance before the final placement decision is made.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors the drag operation, provides visual feedback through gravity effects and highlighted indicators, and uses machine learning to refine predictions based on user behavior patterns. This feedback loop improves reliability by confirming the user's intention and correcting potential errors in real-time.
Data Source
AI summary
A method, computer system, and a computer program product for modifying a user interface. Attributes of a source object identified by a user in connection with a user input for storing the source object are determined. Attributes of one or more target storage locations are determined. A target storage location for storing the source object is predicted, along with a confidence value associated with the prediction. The prediction is made using a machine learning model that predicts the predicted target storage location and associated confidence value based on the determined attributes of the source object. A plurality of target storage location usage patterns are determined. The user interface is modified based on the predicted target storage location.