IP Library › Granted Patent US 12,487,668
Granted Patent B2
US 12,487,668 · App. 18/555,978 · Granted Dec 2, 2025

Electronic device, method for controlling electronic device, and program

Inventors: Jungo Miyazaki (Kawasaki, JP); Yusuke Nishii (Yokohama, JP)
Assignee: KYOCERA Corporation
G06F3/013G06T7/77G06V10/764G06V20/597G06F2203/011G06T2207/20076G06T2207/30201G06T2207/30268
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,487,668
App. No.
18/555,978
Granted
Dec 2, 2025
Kind
B2
Abstract

An electronic device includes an encoder and a decoder. The encoder is configured to estimate an unknown value on the basis of first biological information including a line of sight of a subject extracted from an image of the subject, subject's attribute information representing an attribute of the subject, and subject's internal state information representing an internal state of the subject. The decoder is configured to estimate second biological information including the line of sight of the subject on the basis of the unknown value, the subject's attribute information, and the subject's internal state information. The electronic device adjusts parameters of the encoder and the decoder on the basis of reproducibility of the first biological information from the second biological information.

Claims (28)

1 . An electronic device comprising:

an encoder configured to estimate an unknown value, based on first biological information including a line of sight of a subject extracted from an image of the subject, subject's attribute information representing an attribute of the subject, and a value assumed to be subject's internal state information representing an internal state of the subject;

a decoder configured to estimate second biological information including the line of sight of the subject, based on the unknown value, the subject's attribute information, and the value assumed to be the subject's internal state information; and

an estimator configured to assume a plurality of values to be the subject's internal state information, and estimate a value of the plurality of values to be the subject's internal state information, the value corresponding to the highest reproducibility of the first biological information from the second biological information.

2 . The electronic device according to claim 1 , wherein the electronic device outputs a predetermined alarm when a value of the plurality of values satisfies a predetermined condition, the value corresponding to the highest reproducibility of the first biological information from the second biological information.

3 . The electronic device according to claim 1 , wherein the subject's internal state information includes information representing a concentration level of the subject.

4 . The electronic device according to claim 3 , wherein the subject's internal state information includes information representing a concentration level of the subject during driving of a vehicle.

5 . The electronic device according to claim 1 , wherein the estimator performs estimation based on a degree of distribution deviation representing a degree to which a probability distribution followed by the unknown value estimated by the encoder deviates from a predetermined probability distribution.

6 . The electronic device according to claim 1 , wherein the subject's internal state information includes information representing an emotion or mood of the subject.

7 . The electronic device according to claim 1 , wherein

the electronic device outputs a predetermined alarm when a value of the plurality of values satisfies a predetermined condition, the value corresponding to the highest reproducibility of the first biological information from the second biological information;

the subject's internal state information includes information representing an emotion or mood of the subject; and

an alarm appropriate for the subject's emotion or mood is output as the predetermined alarm.

8 . The electronic device according to claim 1 , wherein the subject's attribute information includes a sex of the subject.

9 . The electronic device according to claim 1 , wherein the subject's attribute information includes an age or age category of the subject.

10 . The electronic device according to claim 1 , wherein the subject's attribute information is estimated based on the image of the subject.

11 . The electronic device according to claim 1 , wherein the subject's attribute information includes information predicting the line of sight of the subject.

12 . The electronic device according to claim 11 , wherein the information predicting the line of sight of the subject is information predicted from a scene image in front of the subject.

13 . A method for controlling an electronic device, the method comprising:

estimating an unknown value, based on first biological information including a line of sight of a subject extracted from an image of the subject, subject's attribute information representing an attribute of the subject, and a value assumed to be subject's internal state information representing an internal state of the subject;

estimating second biological information including the line of sight of the subject, based on the unknown value, the subject's attribute information, and the value assumed to be the subject's internal state information; and

assuming a plurality of values to be the subject's internal state information, and estimating a value of the plurality of values to be the subject's internal state information, the value corresponding to the highest reproducibility of the first biological information from the second biological information.

14 . The method for controlling an electronic device according to claim 13 , wherein the estimating the subject's internal state information is performed, based on a degree of distribution deviation representing a degree to which a probability distribution followed by the unknown value estimated in the estimating an unknown value deviates from a predetermined probability distribution.

15 . A non-transitory computer-readable recording medium storing computer program instructions, which when executed by an electronic device, cause the electronic device to execute:

estimating an unknown value, based on first biological information including a line of sight of a subject extracted from an image of the subject, subject's attribute information representing an attribute of the subject, and a value assumed to be subject's internal state information representing an internal state of the subject;

estimating second biological information including the line of sight of the subject, based on the unknown value, the subject's attribute information, and the value assumed to be the subject's internal state information; and

assuming a plurality of values to be the subject's internal state information, and estimating a value of the plurality of values to be the subject's internal state information, the value corresponding to the highest reproducibility of the first biological information from the second biological information.

16 . The program according to claim 15 , wherein the estimating the subject's internal state information is performed, based on a degree of distribution deviation representing a degree to which a probability distribution followed by the unknown value estimated in the estimating an unknown value deviates from a predetermined probability distribution.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 18, 2023
From: MIYAZAKI, JUNGO; NISHII, YUSUKE
To: KYOCERA CORPORATION
Reel/Frame 065268/0482 →
Priority Claims (1)
JP 2021-075343 · Apr 27, 2021 · national
Continuity (1)
Related Publication 20240220011A1 · Jul 4, 2024
References Cited (9)
US 8085140B2 · Mochizuki et al. · 2011 [cited by applicant]
US 10628688B1 · Kim et al. · 2020 [cited by applicant]
US 20190370662A1 · Song · 2019 [cited by applicant]
US 20210357701A1 · Hyuga et al. · 2021 [cited by applicant]
JP 2019139277A · 2019 [cited by applicant]
JP 2020123343A · 2020 [cited by applicant]
WO 2008029802A1 · 2008 [cited by applicant]
Tatsunori Matsui et al.; “Study on Estimation of Learner's Mental States from Physiological Indexes Considering Time Dilation and Persistent Model of Mental States”; The 32nd Annual Conference of the Japanese Society fo… [cited by applicant]
Taiki Inoue et al.; “Diagnostic Classification of Chest X-Rays Pictures with Deep Learning Using Eye Gaze Data”; The 33rd Annual Conference of the Japanese Society for Artificial Intelligence, 2019; pp. 1-10. [cited by applicant]