US 12,450,321 B2
Authentication system for electronic device
Shigeru Tamaki, Kanagawa (JP); Kengo Akimoto, Kanagawa (JP); Hiromichi Godo, Kanagawa (JP); Koki Inoue, Kanagawa (JP); Yoshitaka Dozen, Kanagawa (JP); and Shunpei Yamazaki, Tokyo (JP)
Assigned to Semiconductor Energy Laboratory Co., Ltd., Kanagawa-ken (JP)
Appl. No. 17/615,257
Filed by SEMICONDUCTOR ENERGY LABORATORY CO., LTD., Atsugi (JP)
PCT Filed Jun. 9, 2020, PCT No. PCT/IB2020/055393
§ 371(c)(1), (2) Date Nov. 30, 2021,
PCT Pub. No. WO2020/254913, PCT Pub. Date Dec. 24, 2020.
Claims priority of application No. 2019-115195 (JP), filed on Jun. 21, 2019.
Prior Publication US 2022/0237275 A1, Jul. 28, 2022
Int. Cl. G06F 21/32 (2013.01); G06F 21/60 (2013.01); G06N 20/00 (2019.01)
CPC G06F 21/32 (2013.01) [G06F 21/604 (2013.01); G06N 20/00 (2019.01)] 10 Claims
OG exemplary drawing
 
1. An authentication system for an electronic device comprising an authentication means, a data acquisition means, and a data retention means comprising a memory element,
wherein the data retention means is configured to accumulate first data related to a state of the electronic device being used by a first user registered in advance and generating a first data group comprising a plurality of pieces of the first data,
wherein the data acquisition means is configured to acquire second data related to a state of the electronic device being used by a second user operating the electronic device,
wherein the authentication means is configured to authenticate the second user as the first user on the basis of the first data group and the second data, is configured to set the electronic device to a locked state when the second user is not authenticated, and is configured to maintain a login state of the electronic device and to output the second data to the data retention means when the second user is authenticated,
wherein the data retention means is configured to update the first data group by deleting the first data included in the first data group and by adding the second data into the first data group when the second data is output from the authentication means,
wherein the authentication means is configured to perform an anomaly detection on the basis of inference using a neural network,
wherein the neural network is configured to generate a new learning model or update an existing learning model, when the first data group is updated using the second data,
wherein each of the first data and the second data comprises information on a tilt angle of the electronic device and information on a distance between an eye and the electronic device,
wherein the tilt angle of the electronic device is measured using an acceleration sensor provided in the data acquisition means, and
wherein the distance between the eye and the electronic device is measured by a ranging method using infrared light.