Collaborative Mobility Model Synchronization via Cloud Intermediary
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for modeling mobility of multiple devices are incomplete as they rely on individual device data, failing to provide a comprehensive and accurate representation of user mobility patterns due to unique usage patterns across different devices.
Innovation Solution
A method for collaboratively modeling device mobility through cloud synchronization, where each device shares and updates a shared mobility model based on learning algorithms, merging changes with confidence scoring to ensure data accuracy and reliability across devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual device mobility models are used, then device-specific accuracy is improved, but comprehensive mobility representation deteriorates
Solution Approach 1:
The patent merges mobility models from multiple devices into a unified collaborative mobility model. Each device contributes its locally learned mobility patterns, and these are combined through cloud synchronization to create a comprehensive model that represents overall user mobility across all devices, resolving the contradiction between device-specific accuracy and comprehensive representation
Solution Approach 2:
The collaborative mobility model serves multiple functions: it maintains device-specific mobility patterns while also providing a universal comprehensive view of user mobility across all devices. This multi-functional approach allows the system to achieve both device-specific accuracy and comprehensive mobility representation simultaneously
2Measurement precision
If complete mobility models are shared across all devices, then comprehensive accuracy is improved, but data transmission overhead increases
Solution Approach 1:
The system extracts only the essential mobility pattern data needed for collaborative modeling and transmits this extracted information through cloud synchronization. By taking out only the necessary mobility characteristics rather than transmitting complete raw data, the system achieves comprehensive accuracy while minimizing data transmission overhead
Solution Approach 2:
The patent implements partial synchronization where devices share mobility model updates and changes rather than transmitting complete models continuously. This partial action approach provides sufficient comprehensive accuracy for mobility prediction while significantly reducing the quantity of data transmitted across the network
3Adaptability or versatility
If mobility data from multiple devices is aggregated, then model comprehensiveness is improved, but user privacy risks increase
Solution Approach 1:
The cloud server acts as an intermediary that aggregates and processes mobility data from multiple devices without exposing raw individual data. The server reconciles mobility patterns and generates unified models, providing comprehensiveness while protecting user privacy by preventing direct access to individual device data
Solution Approach 2:
The system creates abstracted copies of mobility patterns rather than sharing actual raw mobility data. These copied and processed mobility models maintain comprehensiveness for prediction purposes while eliminating direct privacy exposure by working with processed representations rather than original sensitive data
Data Source
AI summary
Methods are provided for modeling mobility based on one or more devices of the user. Methods may include: receiving at least a portion of a first mobility model from a first device, where the first mobility model may be established based on learning algorithms performed on the first device; updating a shared mobility model to become a first shared mobility model based on the at least a portion of the first mobility model; providing the first shared mobility model to the first device; receiving at least a portion of a second mobility model from a second device, where the second mobility model may be established based on learning algorithms performed on the second device; updating the first shared mobility model to become a second shared mobility model based on the at least a portion of the second mobility model; and providing the second shared mobility model to the second device.