Title:
DETECTION DEVICE, DETECTION METHOD, AND DETECTION PROGRAM
Document Type and Number:
WIPO Patent Application WO/2024/079801
Kind Code:
A1
Abstract:
This detection device (10) trains a machine learning model (typing characteristic model) so as to minimize the degree of abnormality of typing by a user himself/herself, by performing machine learning (for example, unsupervised machine learning) that uses free typing by the user himself/herself. Thereafter, the detection device (10) uses the trained machine learning model and calculates the degree of abnormality of the typing to be detected, and when the calculated degree of abnormality exceeds a predetermined threshold, the typing is determined as performed by a person other than the user himself/herself, and an abnormality is detected.
Inventors:
HIWATARI JUNYA (JP)
Application Number:
PCT/JP2022/037937
Publication Date:
April 18, 2024
Filing Date:
October 11, 2022
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06F21/32
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: