Implicit identity recognition and authentication method based on space-time diagram neural network and related device
By segmenting and modeling smartphone motion sensor data using a spatiotemporal graph neural network-based method, the problem of low accuracy in implicit identity recognition and authentication in smartphones is solved, achieving more efficient identity recognition and authentication.
CN120974469APending Publication Date: 2025-11-18XI AN JIAOTONG UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202511162240.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-19
- Publication Date
- 2025-11-18
Smart Images
Figure CN120974469A_ABST
Abstract
The invention provides an implicit identity recognition and authentication method based on a space-time diagram neural network and a related device, and belongs to the technical field of identity recognition and authentication. The method comprises the following steps: acquiring motion sensor data of a user in real time, and inputting the motion sensor data of the user acquired in real time into a space-time diagram neural network to obtain user behavior representation data; inputting the user behavior representation data into a multi-classification neural network to obtain an implicit identity recognition result; and inputting the implicit identity recognition result into the classifier to obtain an implicit identity authentication result. According to the invention, the problem of low accuracy of implicit identity recognition and authentication is solved.
Need to check novelty before this filing date? Find Prior Art