Cross-Device User Verification via Behavior Model Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile behavior biometric systems struggle to verify user identity across different devices with varying technical parameters, such as touchscreen dimensions and sampling rates, leading to inconsistent recognition of user interactions.
Innovation Solution
A method and system that calibrate and normalize device usage data using machine learning models, incorporating technical parameters like pixels per inch and touchscreen dimensions, to generate a user behavior model that can validate user actions on previously unverified devices by duplicating features relative to each touchscreen corner, enabling seamless universal user identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If behavior biometric models are trained on device-specific interaction patterns, then user verification accuracy on the training device is improved, but the model fails to recognize the same user on different devices with varying technical parameters
Solution Approach 1:
The patent transforms device-specific behavioral parameters into device-agnostic normalized parameters by applying calibration factors derived from technical parameters (screen resolution, touch sampling rate, etc.). This allows the behavior biometric model to maintain high verification accuracy across different devices by changing the parameter representation from absolute device coordinates to normalized interaction patterns that are independent of specific device characteristics.
Solution Approach 2:
The patent introduces technical parameters as intermediary variables that mediate between raw device-specific interaction data and the behavior biometric model. By using technical parameters to calibrate and normalize the interaction patterns, the system creates a bridge that enables cross-device recognition while maintaining the specificity of user behavior patterns.
2Adaptability or versatility
If the system collects and processes technical parameters from multiple devices, then cross-device verification capability is improved, but system complexity increases
Solution Approach 1:
The patent performs preliminary calibration by collecting technical parameters from devices during an initial setup phase and pre-computing calibration factors. This preliminary action stores the device characteristics in advance, so that during actual verification operations, the system only needs to apply the pre-computed calibration factors rather than performing complex real-time adaptations, thereby reducing operational complexity.
Solution Approach 2:
The patent segments the verification process into distinct modules: technical parameter collection, calibration factor computation, data normalization, and behavior pattern matching. This segmentation allows each module to be independently optimized and managed, reducing overall system complexity by breaking down the complex cross-device verification task into manageable, modular components.
Data Source
AI summary
A method for calibrating user behavior based models, in order to enable user validation across different devices (i.e. known and unknown devices), comprising: receiving device usage data generated by monitoring user-device interactions on one or more user devices; employing a user behavior model based on the device usage data and a plurality of values of technical parameters of the one or more devices; receiving a plurality of values of technical parameters of an additional device; receiving device usage data by monitoring user-device interactions on the additional device; and analyzing the device usage data of the additional device by employing the user behavior model to validate an action held using the additional device.