-
公开(公告)号：US20230154453A1
公开(公告)日：2023-05-18
申请号：US18046455
申请日：2022-10-13
Applicant: Hyperconnect Inc.
Inventor： Enkhbayar Erdenee , Beom Su Kim , Sang Bum Kim , Seok Jun Seo , Jin Yong Yoo , Bu Ru Chang , Seung Ju Han
Abstract: Systems and techniques to generate imitative responses are illustrated. response generation method performed in an electronic apparatus of the present disclosure includes acquiring at least one piece of utterance data, acquiring a first context corresponding to the utterance data from a context candidate set, generating one or more dialogue sets including the first context and the utterance data, receiving a second context from a user, and acquiring a response corresponding to the second context using a language model based on the one or more dialogue sets.
-
公开(公告)号：US20230080930A1
公开(公告)日：2023-03-16
申请号：US17807653
申请日：2022-06-17
Applicant: Hyperconnect Inc.
Inventor： Seok Jun Seo , Seung Ju Han , Beom Su Kim , Bu Ru Chang , Enkhbayar Erdenee
Abstract: Disclosed is a method of training a dialogue model in an electronic device, the method including selecting a first context from a first dialogue data set including at least one pair of a context and a response corresponding to the context, generating a first response corresponding to the first context through a first dialogue model, generating an augmented dialogue dataset by incorporating a pair of the first context and the first response corresponding to the first context into the first dialogue data set, and training a second dialogue model based on the augmented dialogue dataset.
-
公开(公告)号：US11854536B2
公开(公告)日：2023-12-26
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
CPC classification number: G10L15/16 , G10L25/24 , G10L2015/088
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：US20210075883A1
公开(公告)日：2021-03-11
申请号：US17016064
申请日：2020-09-09
Applicant: HYPERCONNECT, INC.
Inventor： Sang Il Ahn , Hyeong Keol Nam , Seok Jun Seo , Seok Hwan Choi , Jae Hyeuk Oh
IPC: H04L29/08
Abstract: A server may include a communication interface for receiving a plurality of profile information from a plurality of terminals; and a processor configured to divide users of the plurality of terminals into a plurality of groups based on a first criterion, to divide users of a first gender included in each group into a plurality of subgroups based on a second criterion different from the first criterion, to divide users of a second gender different from the first gender, included in each group into a plurality of matching groups to correspond to each of the plurality of subgroups, and to provide profile information of users included in each of the plurality of matching groups corresponding to each of the plurality of subgroups among the plurality of profile information to users included in each of the plurality of subgroups.
-
Patent Agency Ranking
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
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
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：USD1029868S1
公开(公告)日：2024-06-04
申请号：US35516356
申请日：2022-08-24
Applicant: HYPERCONNECT INC.
Designer： Beom Su Kim , Seung Ju Han , Enkhbayar Erdenee , Seok Jun Seo , Jin Yong Yoo , Yeon Woo Lee , Sang Bum Kim , Su Hyun Lee , Se Yeon Oh , Sun Young Bae
Abstract: The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.
1. Display screen or portion thereof with graphical user interface
1 : Front
Reproduction 1 is a front view of a display screen or portion thereof with graphical user interface showing our new design; the outer perimeter shown in a pair of broken lines in the reproduction illustrates a display screen or portion thereof and forms no part of the claimed design; the dot-dash broken lines define boundaries of the claimed design and form no part thereof.-
公开(公告)号：US20230162724A9
公开(公告)日：2023-05-25
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
CPC classification number: G10L15/16 , G10L25/24 , G10L2015/088
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：US11457077B2
公开(公告)日：2022-09-27
申请号：US17016064
申请日：2020-09-09
Applicant: Hyperconnect Inc.
Inventor： Sang Il Ahn , Hyeong Keol Nam , Seok Jun Seo , Seok Hwan Choi , Jae Hyeuk Oh
IPC: G06F15/173 , H04L67/306 , H04L67/1001
Abstract: A server may include a communication interface for receiving a plurality of profile information from a plurality of terminals; and a processor configured to divide users of the plurality of terminals into a plurality of groups based on a first criterion, to divide users of a first gender included in each group into a plurality of subgroups based on a second criterion different from the first criterion, to divide users of a second gender different from the first gender, included in each group into a plurality of matching groups to correspond to each of the plurality of subgroups, and to provide profile information of users included in each of the plurality of matching groups corresponding to each of the plurality of subgroups among the plurality of profile information to users included in each of the plurality of subgroups.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.014 seconds)
