公开(公告)号：US10360594B2

公开(公告)日：2019-07-23

申请号：US14163419

申请日：2014-01-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Je-hyok Ryu ,  Shin-il Kang ,  Hee-jun Song ,  Seung-yeol Yoo ,  Won-chang Jang ,  Gyu-tae Park ,  Hyun-sik Shim

IPC: G06Q30/00 ,  G06Q30/02

Abstract: A server for offering a service targeting a user and a service offering method thereof, the method including: collecting data from a plurality of user devices; determining a unit zone partitioned from a service zone based on geographic information; adjusting the unit zone based on the amount of data collectable according to the determined unit zones; performing modeling to parse the data collected according to the adjusted unit zones; and offering a service targeting a user of the unit zone, based on results from the modeling.

公开(公告)号：US10691886B2

公开(公告)日：2020-06-23

申请号：US15888442

申请日：2018-02-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seung-hak Yu ,  Nilesh Kulkarni ,  Hee-jun Song ,  Hae-jun Lee

IPC: G06F40/284 ,  G06F40/211 ,  G06F40/20 ,  G06N3/04 ,  G06N3/08 ,  G06F40/216 ,  G06N5/02

Abstract: An electronic apparatus for compressing a language model is provided, the electronic apparatus including a storage configured to store a language model which includes an embedding matrix and a softmax matrix generated by a recurrent neural network (RNN) training based on basic data including a plurality of sentences, and a processor configured to convert the embedding matrix into a product of a first projection matrix and a shared matrix, the product of the first projection matrix and the shared matrix having a same size as a size of the embedding matrix, and to convert a transposed matrix of the softmax matrix into a product of a second projection matrix and the shared matrix, the product of the second projection matrix and the shared matrix having a same size as a size of the transposed matrix of the softmax matrix, and to update elements of the first projection matrix, the second projection matrix and the shared matrix by performing the RNN training with respect to the first projection matrix, the second projection matrix and the shared matrix based on the basic data.

公开(公告)号：US11568240B2

公开(公告)日：2023-01-31

申请号：US16613317

申请日：2018-05-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hee-jun Song ,  Nilesh Kulkarni

IPC: G06N3/08 ,  G06F40/30 ,  G06N3/04

Abstract: Provided are a method and apparatus for classifying a sentence into a class by using a deep neural network. The method includes respectively training first and second sentences by using first and second neural networks, obtaining a contrastive loss based on first and second feature vectors generated as output data of the training, and information about whether classes to which the first and second sentences belong are the same, and repeating the training in such a manner that the contrastive loss has a maximum value.

公开(公告)号：US11115359B2

公开(公告)日：2021-09-07

申请号：US15798799

申请日：2017-10-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hee-jun Song ,  Seo-young Jo ,  Jung-wook Kim

IPC: G06F15/16 ,  H04L12/58 ,  G06N20/00 ,  G06N3/08

Abstract: An electronic apparatus for filtering a plurality of messages, via a user interface including a filtering bar. A display is for displaying a plurality of messages, and an input is to request a filtering of the plurality of messages based on importance.

公开(公告)号：US10423240B2

公开(公告)日：2019-09-24

申请号：US15444607

申请日：2017-02-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Won-ho Ryu ,  Hee-jun Song

IPC: G06F3/023 ,  G06F3/0488 ,  G06F17/28 ,  G06F17/27 ,  G06F3/01 ,  G06F17/22

Abstract: An approach, performed by a device, for recommending at least one word to be input through a keyboard is provided. The approach displays the keyboard to be used to input at least one character or text on the device. The approach selects at least one language model. The approach recommends the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the at least one selected language model, in which the at least one selected language model comprises at least one of a language model based on demographic properties of a user of the device, a language model based on text input histories of the user of the device, and a language model based on a context in which the keyboard is executed.

公开(公告)号：US12216995B2

公开(公告)日：2025-02-04

申请号：US17967924

申请日：2022-10-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hee-jun Song ,  Jung-wook Kim

IPC: G06F40/274 ,  G06F40/163 ,  G06F40/268 ,  G06F40/279

Abstract: A device and method for providing recommended words for a character input by a user are provided. The method by which the device provides recommended words includes: receiving an input for inputting a character in a character input window; recommending at least one pseudo-morpheme including the input character by analyzing the input character; recommending at least one extended word including a selected pseudo-morpheme in response to receiving an input for selecting one of the at least one pseudo-morpheme; and displaying a selected extended word in response to receiving an input for selecting one of the at least one extended word.

公开(公告)号：US11481551B2

公开(公告)日：2022-10-25

申请号：US16724641

申请日：2019-12-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hee-jun Song ,  Jung-wook Kim

IPC: G06F40/274 ,  G06F40/163 ,  G06F40/268 ,  G06F40/279

Abstract: A device and method for providing recommended words for a character input by a user are provided. The method by which the device provides recommended words includes: receiving an input for inputting a character in a character input window; recommending at least one pseudo-morpheme including the input character by analyzing the input character; recommending at least one extended word including a selected pseudo-morpheme in response to receiving an input for selecting one of the at least one pseudo-morpheme; and displaying a selected extended word in response to receiving an input for selecting one of the at least one extended word.

公开(公告)号：US10921903B2

公开(公告)日：2021-02-16

申请号：US16545198

申请日：2019-08-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Won-ho Ryu ,  Hee-jun Song

IPC: G06F3/023 ,  G06F3/01 ,  G06F40/40 ,  G06F40/274 ,  G06F3/0488 ,  G06F40/129

Abstract: An approach, performed by a device, for recommending at least one word to be input through a keyboard is provided. The approach displays the keyboard to be used to input at least one character or text on the device. The approach selects at least one language model. The approach recommends the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the at least one selected language model, in which the at least one selected language model comprises at least one of a language model based on demographic properties of a user of the device, a language model based on text input histories of the user of the device, and a language model based on a context in which the keyboard is executed.

公开(公告)号：US10540441B2

公开(公告)日：2020-01-21

申请号：US15789106

申请日：2017-10-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hee-jun Song ,  Jung-wook Kim

IPC: G06F17/27

Abstract: A device and method for providing recommended words for a character input by a user are provided. The method by which the device provides recommended words includes: receiving an input for inputting a character in a character input window; recommending at least one pseudo-morpheme including the input character by analyzing the input character; recommending at least one extended word including a selected pseudo-morpheme in response to receiving an input for selecting one of the at least one pseudo-morpheme; and displaying a selected extended word in response to receiving an input for selecting one of the at least one extended word.