公开(公告)号：US20230135163A1

公开(公告)日：2023-05-04

申请号：US17933821

申请日：2022-09-20

Applicant: Hyperconnect Inc.

Inventor： Jacob Richard Morton ,  Martin Kersner ,  Sang Il Ahn ,  Bu Ru Chang ,  Kwang Hee Choi

IPC: G06N3/08 ,  G06N3/04

Abstract: Provided is a method for training a model, including generating a plurality of attention maps by inputting training data into a previously trained teacher model, generating a set of attention weights of the teacher model based on the plurality of attention maps, generating a set of attention weights of a student model by inputting the training data into the student model, calculating a value of a first loss function based on the set of attention weights of the teacher model and the set of attention weights of the student model, calculating a value of a second loss function according to an inference of the student model with respect to the training data, and training the student model based on the value of the first loss function and the value of the second loss function.

公开(公告)号：US11615777B2

公开(公告)日：2023-03-28

申请号：US16987111

申请日：2020-08-06

Applicant: Hyperconnect Inc.

Inventor： Sang Il Ahn ,  Ju Young Hong ,  Yong Uk Jeong

IPC: G10L13/033 ,  G10L13/04 ,  G10L17/04 ,  H04L65/611

Abstract: A terminal may include a display that is divided into at least two areas, when a real time broadcasting, where a user of the terminal is a host, starts through a broadcasting channel, and of which one area of the at least two areas is allocated to the host; an input/output interface that receives a voice of the host; a communication interface that receives one item selected of at least one or more items and a certain text from a terminal of a certain guest, of at least one or more guests who entered the broadcasting channel; and a processor that generates a voice message converted from the certain text into the voice of the host or a voice of the certain guest.

公开(公告)号：US20230077528A1

公开(公告)日：2023-03-16

申请号：US17805191

申请日：2022-06-02

Applicant: Hyperconnect Inc.

Inventor： Enkhbayar Erdenee ,  Beom Su Kim ,  Seok Jun Seo ,  Sang Il Ahn ,  Bu Ru Chang ,  Seung Ju Han

IPC: G10L15/06 ,  G10L15/16

Abstract: A training method of a conversation model according to various example embodiments of the present disclosure may include identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset.

公开(公告)号：US20210074270A1

公开(公告)日：2021-03-11

申请号：US17013391

申请日：2020-09-04

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Seung Woo Choi ,  Seok Jun Seo ,  Beom Jun Shin

IPC: G10L15/16 ,  G10L25/24

Abstract: A keyword spotting apparatus, method, and computer-readable recording medium are disclosed. The keyword spotting method using an artificial neural network according to an embodiment of the disclosure may include obtaining an input feature map from an input voice; performing a first convolution operation on the input feature map for each of n different filters having the same channel length as the input feature map, wherein a width of each of the filters is w1 and the width w1 is less than a width of the input feature map; performing a second convolution operation on a result of the first convolution operation for each of different filters having the same channel length as the input feature map; storing a result of the second convolution operation as an output feature map; and extracting a voice keyword by applying the output feature map to a learned machine learning model.

公开(公告)号：US20210043187A1

公开(公告)日：2021-02-11

申请号：US16987111

申请日：2020-08-06

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Ju Young Hong ,  Yong Uk Jeong

IPC: G10L13/033 ,  G10L17/04 ,  G10L13/04

Abstract: A terminal may include a display that is divided into at least two areas, when a real time broadcasting, where a user of the terminal is a host, starts through a broadcasting channel, and of which one area of the at least two areas is allocated to the host; an input/output interface that receives a voice of the host; a communication interface that receives one item selected of at least one or more items and a certain text from a terminal of a certain guest, of at least one or more guests who entered the broadcasting channel; and a processor that generates a voice message converted from the certain text into the voice of the host or a voice of the certain guest.

公开(公告)号：US10733082B2

公开(公告)日：2020-08-04

申请号：US16364709

申请日：2019-03-26

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Sang Pil Yoon

IPC: G06F11/36 ,  H04L29/08

Abstract: A computer program is stored in a computer-readable recording medium to implement a test group distribution method in a server device. The test group distribution method includes: generating identification information of a first test to be performed, differently from identification information of at least one test that is registered in advance, wherein the first test is performed by a plurality of user terminals classified into a plurality of groups; generating a unique identifier of each of users by using a first key comprising identification information of each user and a second key comprising the identification information of the first test; and determining test group information of each user based on the unique identifier of each user, the test group information corresponding to a group to which each user belongs.

公开(公告)号：US10721437B2

公开(公告)日：2020-07-21

申请号：US16698371

申请日：2019-11-27

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Hyeok Choi

IPC: H04N7/14 ,  H04N5/44 ,  H04L29/06 ,  H04N5/232

Abstract: There is provided an application stored in a computer-readable storage medium and enabling a first terminal to perform a method of providing a video call service, the method includes: establishing a video call session between the first terminal and a second terminal; displaying an exposure control area for controlling an exposure area of an image of a first user displayed on the second terminal; receiving an input of the first user for controlling the exposure control area; and transmitting a signal for controlling the exposure area to the second terminal in response to the input of the first user.

公开(公告)号：US10560659B2

公开(公告)日：2020-02-11

申请号：US16223770

申请日：2018-12-18

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Hee Min Choi

IPC: H04N7/14 ,  G06K9/00 ,  G06F3/0481 ,  H04N5/445

Abstract: Provided is an application stored in a computer-readable storage medium to perform a method of providing a video call service using icon information corresponding to a facial expression of a user.

公开(公告)号：US20190199963A1

公开(公告)日：2019-06-27

申请号：US16223600

申请日：2018-12-18

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Hyeok Choi

IPC: H04N7/14 ,  H04N5/262 ,  G06F3/0481 ,  G06F3/01

Abstract: Provided is an application stored in a computer-readable storage medium to perform a method of providing a video call service, the method including, in a first terminal, establishing a video call session between the first terminal and a second terminal; modulating and displaying an area of an image of a second user, except for an exposure area, the image of the second user being displayed in the first terminal; detecting a predetermined event during the video call session; and controlling a size of the exposure area based on the predetermined event.

公开(公告)号：US20190188459A1

公开(公告)日：2019-06-20

申请号：US16219593

申请日：2018-12-13

Applicant: Hyperconnect, Inc.

Inventor： Sang Il Ahn ,  Hee Min Choi

IPC: G06K9/00 ,  G06F16/28 ,  G06F3/0481 ,  G06F3/0482 ,  H04M1/725

CPC classification number: G06K9/00315 ,  G06F3/04817 ,  G06F3/0482 ,  G06F16/287 ,  H04M1/72555

Abstract: There is provided an application stored in a computer-readable storage medium for a first terminal to perform a method of providing a video call service, the method including: establishing a video call session between the first terminal of a first user and a second terminal of a second user; preparing facial expression information of the second user accumulated in at least one video call session executed by the second terminal before the video call session; determining emotion information corresponding to the facial expression information of the second user based on the facial expression information of the second user; and providing the determined emotion information through an execution screen of the first terminal.