Video communication device, video communication method, and video communication mediating method

Patent metadata

Field	Value
Publication number	US-11323659-B2
Application number	US-202117183890-A
Country	US
Kind code	B2
Filing date	Feb 24, 2021
Priority date	Apr 17, 2017
Publication date	May 3, 2022
Grant date	May 3, 2022

Abstract

One or more embodiment relates to a video communication device, video communication method, and a video communication mediating method, which are capable of preventing a user in a video communication from being exposed to an inappropriate image or sound from the other party. One or more embodiment may provide a video communication method comprising establishing a first video communication session with a first terminal, consecutively receiving images or sounds from the first terminal through the first video communication session, examining at least a portion of images or sounds received in a period of recent specific time among the received images or sounds, and blocking an output of at least a portion of the received images or sounds or reporting a user of the first terminal as an abusive user to a first server according to the result of the examining.

First claim

What is claimed is:

1. A video communication mediating method comprising:
receiving, by a server, a mediation request from a plurality of terminals;
mediating, by the server, a first video communication connection between a first terminal and a second terminal among the plurality of terminals;
receiving, by the server, a report from the first terminal, which indicates that a user of the first terminal or a user of the second terminal is an abusive user;
mediating, by the server, a second video communication connection between a terminal of the reported user and a terminal of a monitoring agent after ending the first video communication connection in response to the report; and
receiving, by the server, a result of verification on the reported user from the terminal of the monitoring agent.

2. The video communication mediating method of claim 1 , wherein the receiving comprises receive the report that the user of at least one of the first terminal and the second terminal is the abusive user according to an examining result of examining images or sounds received by the at least one of the terminal by running a machine learning model in the at least one of the terminal.

3. The video communication mediating method of claim 1 , wherein the method further comprises determining, by the server, whether to reject an additional mediation request from the reported user based on the received result of verification.

4. The video communication mediating method of claim 2 , the machine learning model, as a result of running, calculates result value of probability that the image to be examined does not include an abusive element, the probability that the image to be examined includes an abusive element, and the probability that the image to be examined includes a specific abusive element.

5. The video communication mediating method of claim 4 , wherein the receiving comprises receive the report that the user of the at least one terminal is the abusive user, if the number of times that the examining result includes the abusive element or the specific abusive element is more than the preset number.

6. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to:
receive a mediation request from a plurality of terminals;
mediate a first video communication connection between a first terminal and a second terminal among the plurality of terminals;
receive a report from the first terminal, which indicates that a user of the first terminal or a user of the second terminal is an abusive user;
mediate a second video communication connection between a terminal of the reported user and a terminal of a monitoring agent after ending the first video communication connection in response to the report; and
receive a result of verification on the reported user from the terminal of the monitoring agent.

7. A server for a video call mediation comprising at least one processor which is configured to:
receive a mediation request from a plurality of terminals;
mediate a first video communication connection between a first terminal and a second terminal among the plurality of terminals;
receive a report from the first terminal, which indicates that a user of the first terminal or a user of the second terminal is an abusive user;
mediate a second video communication connection between a terminal of the reported user and a terminal of a monitoring agent after ending the first video communication connection in response to the report; and
receive a result of verification on the reported user from the terminal of the monitoring agent.

8. The server of claim 7 , wherein processor is further configured to receive the report that the user of at least one of the first terminal and the second terminal is the abusive user according to an examining result of examining images or sounds received by the at least one of the terminal by running a machine learning model in the at least one of the terminal.

9. The server of claim 7 , wherein the processor is further configured to determine whether to reject an additional mediation request from the reported user based on the received result of verification.

10. The server of claim 8 , wherein the machine learning model, as a result of running, calculates result value of probability that the image to be examined does not include an abusive element, the probability that the image to be examined includes an abusive element, and the probability that the image to be examined includes a specific abusive element.

11. The server of claim 10 , wherein the processor is further configured to receive the report that the user of the at least one terminal is the abusive user, if the number of times that the examining result includes the abusive element or the specific abusive element is more than the preset number.

Assignees

• Hyperconnect Inc

Inventors

• Ahn Sangil
• Jung Kangsik
• Yong Hyountaek

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title

• H04N7/152 Primary

  Multipoint control units therefor · CPC title

• G06N20/00

  Machine learning · CPC title