Storage Location Recommendations Using Content-Based Classifiers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional content storage systems require users to navigate through cumbersome hierarchies to find appropriate storage locations for digital content items, and systems relying on most recently used locations are limited in their effectiveness.
Innovation Solution
A machine-learning model is trained using classifiers to analyze user storage habits and content characteristics, providing intelligent storage location suggestions based on similarities and differences among content items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users navigate through file hierarchy from root node each time to store/move content items, then users can find appropriate storage locations, but the process becomes cumbersome and frustrating especially for deeply nested locations
Solution Approach 1:
The system performs preliminary analysis of content items and their characteristics before the user needs to store or move them. It pre-determines appropriate storage locations based on content type, size, and user preferences, so that when the user initiates a store/move operation, the recommended location is already prepared and suggested, eliminating the need to navigate from the root node each time.
Solution Approach 2:
The system introduces an intermediary layer between the user and the file hierarchy. Instead of directly navigating through the folder structure, the user interacts with the content item characteristics and the system's recommendations. This intermediary layer translates content metadata into appropriate storage location suggestions, mediating the connection between content and storage structure.
2Productivity
If the system presents the most recently used location, then users can quickly store content items that belong there, but users must navigate from the most recently used location to appropriate locations, which is inefficient when the content does not belong in the most recently used location
Solution Approach 1:
The system changes the parameters used for location recommendation from time-based (most recently used) to content-based parameters (content type, size, characteristics). By analyzing content item attributes and comparing them against historical storage patterns, the system determines the most appropriate location regardless of recent usage history, achieving both speed and accuracy.
Solution Approach 2:
The system incorporates feedback from user storage behavior patterns to continuously improve location recommendations. By analyzing how users have stored content items in the past and what characteristics they used, the system refines its recommendation algorithm, providing increasingly accurate suggestions that match user preferences and content characteristics.
3Adaptability or versatility
If conventional systems allow users to customize folder hierarchy, then users can organize content according to their preferences, but the complexity of managing and navigating the customized hierarchy increases
Solution Approach 1:
The system provides self-service by automatically analyzing content item characteristics and recommending appropriate storage locations without requiring users to manually navigate or manage the hierarchy. The customized folder structure remains in place, but the system handles the complexity of matching content to locations, allowing users to benefit from their customized structure without bearing the navigation burden.
Data Source
AI summary
One or more embodiments of a content system provide machine-learned storage location recommendations for storing content items. Specifically, an online content management system can train a machine-learning model to identify a storage pattern from previously stored content items in a plurality of storage locations corresponding to a user account of a user. Training the machine-learning model includes training a plurality of classifiers for the plurality of storage locations. The online content management system uses the classifiers to determine whether a content item is similar to the content items in any of the storage locations, and based on the output of the classifiers, provides graphical elements indicating recommended storage locations within a graphical user interface. The user can select a graphical element to move the content item to the corresponding storage location.