Device Pair Engagement Scoring for Cloud Storage Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud-based file storage systems lack personalized recommendations for users based on their device usage patterns, failing to effectively suggest complementary devices that align with their existing device usage habits.
Innovation Solution
A method and system that calculates engagement scores for device pairs based on file sizes and usage patterns, generating recommendation messages for users by identifying complementary devices they may find useful, leveraging data stored across all users to model user-device engagement and provide tailored suggestions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If cloud-based file storage systems store data from multiple device types, then the quantity of stored data increases, but the system lacks personalized recommendations for users based on device usage patterns
Solution Approach 1:
The system segments the aggregate stored data by device type, creating separate data structures for different device categories (e.g., cameras, smartphones, tablets). This segmentation enables the system to analyze usage patterns specific to each device type while maintaining the overall quantity of stored data from diverse sources.
Solution Approach 2:
The system transforms raw stored data into meaningful engagement scores by applying parameter changes - specifically, calculating engagement metrics based on file size, access frequency, and device type. This transformation converts the quantity of stored data into personalized recommendation capabilities through computed engagement scores that reflect actual usage patterns.
2Measurement precision
If the system analyzes usage patterns across all users to generate recommendations, then the accuracy of device recommendations improves, but the computational complexity increases
Solution Approach 1:
The system applies local quality by computing engagement scores specifically for device type pairs rather than analyzing all possible device combinations. This approach focuses computational resources on relevant comparisons - only calculating engagement metrics for pairs of devices that users actually own or use, thereby improving recommendation accuracy while reducing unnecessary computational complexity.
Solution Approach 2:
The system performs partial action by calculating engagement scores for only the necessary device type pairs - specifically, pairs where a user owns at least one device. This avoids the excessive computation of all possible device combinations in the system, achieving sufficient recommendation accuracy without the full computational burden of exhaustive analysis.
3Adaptability or versatility
If the system generates engagement scores for all device type pairs, then the personalization of recommendations improves, but the time required to process and generate recommendations increases
Solution Approach 1:
The system performs preliminary action by pre-calculating engagement scores for device type pairs and storing them in a data structure. This pre-computation allows the system to quickly retrieve and use engagement scores when generating recommendations, rather than calculating them in real-time, thus improving personalization while reducing the time required at recommendation generation moment.
Solution Approach 2:
The system applies partial action by computing engagement scores only for device type pairs that are relevant to actual users - specifically, pairs where at least one device type is owned by a user. This avoids computing scores for all possible device type combinations, reducing processing time while maintaining sufficient personalization for the actual user base.
Data Source
AI summary
A method includes receiving, at a storage device, a plurality of data files that each have a file size, and are each associated a respective device that corresponds to one of a plurality of device types and defining device type pairs each including a first device and a second device having different device types. The method also includes determining, by one or more computing devices and for each device type pair, an engagement score based at least in part on the file sizes for the data files associated with the first device and the second device, wherein the engagement score represents a degree of usage of the first device concurrent with usage of the second device, and generating, by the one or more computing devices.