Device Identification via Time-Domain Feature Decay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current device identification algorithms fail to accurately identify user devices with changing attributes, leading to increased misjudgment rates and the creation of multiple IDs for the same device, due to their assumption of consistent attributes and difficulty in determining similarity weights with limited feature information.
Innovation Solution
A method that calculates time-domain feature information, including leap time and stable time, to determine difference values of changed attributes, using a decay function to adjust similarity weights based on these values, thereby precisely identifying whether device records belong to the same device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current device identification algorithms use fixed similarity measurement functions to compare device attributes, then the identification process is simple and fast, but the misjudgment rate increases when device attributes change due to system updates or malicious modifications
Solution Approach 1:
The patent applies dynamics by transitioning from fixed similarity measurement functions to dynamic similarity weight determination. The system continuously adjusts similarity weights based on time-domain feature information (leap time and stable time) extracted from device attribute change sequences, allowing the identification algorithm to adapt to attribute changes while maintaining accuracy.
Solution Approach 2:
The patent implements feedback by using time-domain feature information derived from observed attribute changes to adjust similarity weights. The system extracts leap time (time between attribute changes) and stable time (time attribute remains unchanged) from device records, then feeds this information back to modify the similarity measurement process, creating a self-adjusting identification system.
2Ease of operation
If the system creates a new device ID whenever device attributes change, then the identification process is straightforward, but multiple IDs are generated for the same device increasing the misjudgment rate
Solution Approach 1:
The patent applies preliminary action by pre-extracting time-domain feature information (leap time and stable time) from device attribute change sequences before making identification decisions. This preliminary extraction of temporal patterns allows the system to prepare similarity weight adjustments in advance, enabling more precise device identity recognition without complicating the overall assignment process.
3Device complexity
If the system uses limited device attribute feature information for identification, then the implementation is simpler, but determining accurate similarity weights becomes difficult due to constant attribute changes
Solution Approach 1:
The patent applies parameter changes by transforming the determination of similarity weights from a static process to a dynamic one based on temporal parameters. Instead of relying on fixed weights, the system uses leap time and stable time as changing parameters to calculate difference values, which then determine similarity weights. This allows accurate weight determination even with limited attribute features by leveraging temporal patterns.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present application provides a method and a system for identifying a user device. The method comprises acquiring multiple device records ranked in chronological order; calculating time-domain feature information of a changed attribute value in the device records; calculating a difference value between values of an attribute before and after change according to the time-domain feature information of the changed attribute value in the device records; calculating a similarity of the device records according to difference values of all attributes in the device records; and identifying whether the device records belong to an identical device according to the similarity of the device records. As compared with current systems, the identification of a user device is done based on all the attributes of a device in which a similarity of device records is precisely calculated through a similarity weight that is constantly adjusted time sequences, thereby effectively reducing the misjudgment rate.