IP Library › Granted Patent US 12,354,359
Granted Patent B2
US 12,354,359 · App. 17/678,864 · Granted Jul 8, 2025

Information processing system, control method of the system, and storage medium

Inventor: Yoshihiko Okamoto (Kanagawa, JP)
Assignee: Canon Kabushiki Kaisha
G06V20/52G06F18/214G06T7/70G06T2207/20081G06T2207/20084G06T2207/30196G06T2207/30232
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 12,354,359
App. No.
17/678,864
Granted
Jul 8, 2025
Kind
B2
Abstract

An information processing system includes an image capturing unit that captures an image of a visitor, an acquisition unit that acquires information about a response to a visit of the visitor, and a training data generation unit that generates training data for a learning model by using the image of the visitor captured by the image capturing unit and the information about the response acquired by the acquisition unit.

Claims (43)

1. An information processing system comprising:

an image capturing unit configured to capture an image of a visitor when the visitor comes for a visit;

a prompting unit configured to, prompt a user to input a response to a visit of a visitor, when the visitor comes to visit the user;

a detection unit configured to detect unlocking of a door;

an acquisition unit configured to acquire information about the response to the visit of the visitor input based on the prompt, the information about the input response includes information about whether the detection unit detects that the door is caused, by the user, to be unlocked or not; and

a training data generation unit configured to generate training data for a learning model by using the image of the visitor captured by the image capturing unit and the information about the type of input response provided by the user and acquired by the acquisition unit;

wherein the training data generation unit generates the training data indicating that reliability of the visitor is high in a case where the door is caused to be unlocked by the user, and generates the training data indicating that reliability of the visitor is low in a case where the door is not unlocked.

2. The information processing system according to claim 1 , further comprising a voice communication unit configured to perform voice communication with the visitor,

wherein the acquisition unit acquires data related to the voice communication performed by the voice communication unit as information about the response to the visit of the visitor.

3. The information processing system according to claim 2 , further comprising an inference unit configured to infer who the visitor is by using video information acquired from the image capturing unit and audio information acquired from the voice communication unit as input data.

4. The information processing system according to claim 3 , wherein the inference unit infers attribute information about the visitor.

5. The information processing system according to claim 1 , further comprising a notification unit configured to provide a notification of the visit of the visitor.

6. The information processing system according to claim 5 , wherein, in a case where no response is made to the visitor via the voice communication unit and the door is unlocked after the notification unit provides a notification of the visit of the visitor, training data indicating that reliability of the visitor is high is generated.

7. The information processing system according to claim 5 , wherein, in a case where a response is made to the visitor via the voice communication unit and the door is unlocked after the notification unit provides a notification of the visit of the visitor, training data indicating that reliability of the visitor is high is generated.

8. The information processing system according to claim 5 , wherein training data to be generated in a case where no response is made to the visitor via the voice communication unit and the door is unlocked after the notification unit provides a notification of the visit of the visitor has higher reliability than that of training data to be generated in a case where a response is made to the visitor via the voice communication unit and the door is unlocked after the notification unit makes a notification of the visit of the visitor.

9. The information processing system according to claim 5 , wherein, in a case where a response is made to the visitor via the voice communication unit and the door is not unlocked after the notification unit provides a notification of the visit of the visitor, training data indicating that reliability of the visitor is low is generated.

10. The information processing system according to claim 5 , wherein, in a case where no response is made to the visitor via the voice communication unit and the door is not unlocked after the notification unit provides a notification of the visit of the visitor, training data indicating that reliability of the visitor is low is generated.

11. The information processing system according to claim 5 , wherein the training data to be generated in a case where a response is made to the visitor via the voice communication unit and the door is not unlocked after the notification unit provides a notification of the visit of the visitor has higher reliability than that of training data to be generated in a case where the visitor is not responded to via the call unit, and the door is not unlocked after the notification unit provides a notification of the visit of the visitor.

12. The information processing system according to claim 1 , further comprising a unit configured to acquire a visit time of the visitor,

wherein the training data generation unit uses the visit time of the visitor for generation of the learning model.

13. The information processing system according to claim 1 , further comprising a schedule management unit configured to manage a visit schedule of the visitor,

wherein the training data generation unit uses schedule information included in the schedule management unit for generation of the learning model.

14. The information processing system according to claim 1 , further comprising a determination unit configured to determine a position of a door to be unlocked as a response to the visitor,

wherein the training data generation unit uses position information about the position of the door determined by the determination unit for generation of the learning model.

15. The information processing system according to claim 1 , further comprising a communication unit configured to communicate with a different intercommunication system,

wherein the training data generation unit uses training data of the different intercommunication system received by the communication unit for generation of the learning model.

16. The information processing system according to claim 1 , further comprising a detection unit configured to detect unlocking of a door,

wherein the acquisition unit acquires data related to unlocking of the door with respect to the visit of the visitor as information about the response.

17. The information processing system according to claim 1 , wherein, based on a user being absent, the training data generation unit does not generate training data.

18. A method for controlling an information processing system, the method comprising:

capturing an image of a visitor when the visitor comes for a visit;

prompting a user to input a response the visit by the visitor when the visitor comes to visit the user;

detecting unlocking of a door;

acquiring information about the response to the visit of the visitor input based on the prompt, the information about the input response includes information about whether the detecting detects that the door is caused, by the user, to be unlocked or not; and

generating training data for a learning model by using the captured image of the visitor and the acquired information about the type of input response provided by the user,

wherein the training data being generated indicates that the reliability of the visitor is high in a case where the door is caused to be unlocked by the user and the reliability of the visitor is low in a case where the door is not unlocked.

19. A non-transitory storage medium storing a computer readable program causing a computer to execute a method for controlling an information processing system, the method comprising:

capturing an image of a visitor when the visitor comes for a visit;

prompting a user to input a response the visit by the visitor when the visitor comes to visit the user;

detecting unlocking of a door;

acquiring information about the response to the visit of the visitor input based on the prompt, the information about the input response includes information about whether the detecting detects that the door is caused, by the user, to be unlocked or not; and

generating training data for a learning model by using the captured image of the visitor and the acquired information about the type of input response provided by the user,

wherein the training data being generated indicates that the reliability of the visitor is high in a case where the door is caused to be unlocked by the user and the reliability of the visitor is low in a case where the door is not unlocked.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 4, 2022
From: OKAMOTO, YOSHIHIKO
To: CANON KABUSHIKI KAISHA
Reel/Frame 059166/0083 →
Priority Claims (1)
JP 2021-028814 · Feb 25, 2021 · national
Continuity (1)
Related Publication 20220270372A1 · Aug 25, 2022
References Cited (22)
US 10389982B1 · Fu · 2019 [cited by examiner]
US 10389983B1 · Fu · 2019 [cited by examiner]
US 10402989B2 · Modestine · 2019 [cited by examiner]
US 10497236B2 · Lemberger · 2019 [cited by examiner]
US 10635303B2 · Coffman · 2020 [cited by examiner]
US 20160267760A1 · Trani · 2016 [cited by examiner]
US 20170214801A1 · Gaspard · 2017 [cited by examiner]
US 20170359189A1 · Smith · 2017 [cited by examiner]
US 20180365920A1 · Daly · 2018 [cited by examiner]
US 20190018588A1 · DeBates · 2019 [cited by examiner]
US 20190068792A1 · Gaspard · 2019 [cited by examiner]
US 20190089934A1 · Goulden · 2019 [cited by examiner]
US 20190130175A1 · Nakashima · 2019 [cited by examiner]
US 20190278976A1 · Khadloya · 2019 [cited by examiner]
US 20200082198A1 · Yao · 2020 [cited by examiner]
US 20200184053A1 · Kursun · 2020 [cited by examiner]
US 20200293756A1 · Ainsworth · 2020 [cited by examiner]
US 20210043018A1 · Zhang · 2021 [cited by examiner]
US 20220270372A1 · Okamoto · 2022 [cited by examiner]
JP 2019046018A · 2019 [cited by applicant]
JP 2019068360A · 2019 [cited by applicant]
JP 2020184657A · 2020 [cited by applicant]