Lg Electronics Inc.

Lg Innotek Co., Ltd.

Korea Institute of Science and Technology

Korea University Research and Business Foundation

Smart Sound Ltd.

Jungho Lee

Jongwoo Han

Seungmin Baek

Hyuksoo Lee

Eunjin Kim

Guntae Bae

Hyungyu Park

Shounan An

Haehyung Lee

Inhee Cho

Jaeman Park

Taehun Kim

Chulki Kim

Taikjin Lee

Sang Keun Lee

Seongsoo Lee

Kang-Min Kim

Jeonghwan Hwang

Jaehun Kim

Jeongsuk Yoon

Wonkeun Yang

Jinho Sohn

Jongpil Won

Beomju Shin

Junkwan Lee

Changsu Yu

Manchan Lee

The present disclosure relates to a method for performing vehicle position recognition using a geomagnetic sensor by calibrating the geomagnetic sensor on the basis of a geomagnetic sensor value stored in a database in advance before entrance to an area in which position recognition through a GPS is impossible. Thus, it is possible to accurately detect a position of a vehicle using the geomagnetic sensor even in a structure such as a tunnel.

Method for recognizing vehicle location using geomagnetic sensor

An electronic device includes a housing with a handle formed on one part of the housing, a display, a sound collecting part, and a controller. A handle is formed on one part of the housing and the display is positioned on another part of the housing and placed on one surface side of the housing. The sound collecting part is positioned on the housing on another surface side of the housing. The controller is configured to input first auscultation sound data obtained through the sound collecting part into a first AI model. The device obtains an abnormality analysis result corresponding to the first auscultation sound data and provides the abnormality analysis result through the display.

Electronic device for auscultation and method of operation thereof

According to an aspect of an embodiment, a method for a text classification using multi-task learning executed by a server, the method includes: a step of generating text classification learning data by executing a pre-processing process on raw data collected through a network; a step of learning a category classification in a first classification system preset through a first text classification model using the text classification learning data as an input; a step of learning a category classification in a second classification system preset through a second text classification model using the text classification learning data as an input; and a step of classifying the category in the second classification system by inputting text data received from a user terminal into the second text classification model.

Method and server for text classification using multi-task learning

A terminal and operating method thereof includes receiving a plurality of contents, classifying the plurality of received contents into a plurality of groups based on recipient information of a recipient corresponding to a user of the terminal, and outputting the plurality of contents classified into the plurality of groups in order corresponding to the recipient information. A thumbnail image represents each of the plurality of groups. The thumbnail image is displayed in accordance with the recipient information, such as a thumbnail image of a group considered to be more of interest to a user displayed in a larger size.

Terminal receiving content based on network environment and controlling method thereof

Provided are a mobile terminal including an artificial intelligent agent and a method for controlling a mobile terminal using machine learning. A mobile terminal comprises a microphone, a learning data unit configured to identify and store keywords and a controller configured to: activate the microphone in response to an activation event, receive a voice input via the microphone, extract vocabulary information from the received voice input and execute a control corresponding to command information included in the received voice input, wherein the executed control is varied by utilizing the keywords and the extracted vocabulary information.

Mobile terminal and method for controlling mobile terminal using machine learning

Disclosed are a mobile terminal and a method for controlling the same. The mobile terminal includes: a memory capable of storing video data therein; a touch screen capable of receiving a touch input related to the video data; and a controller capable of reducing a play time or a capacity of the video data based on a preset reference, such that a summary of the video data is generated based on the touch input, wherein the preset reference is established based on a restriction condition of a social network service or an application for sharing the video data.

Mobile terminal and control method for the same

An image photographing device for photographing images through a front camera and a rear camera, according to one embodiment of the present invention, comprises: a display unit; a feature extraction unit for extracting facial features from an image of a user's face which is displayed on a preview screen through the rear camera; a structure extraction unit for extracting the structure of the user's face by using the extracted facial features; an expression extraction unit for extracting the facial expression of the user by using the extracted facial features if the extracted structure of the face matches a standard facial structure; and an notification unit for outputting a photograph notification signal if the extracted facial expression of the user matches a standard facial expression.

Guidance based image photographing device and method thereof for high definition imaging

The present invention relates to a heat radiating printed circuit board (PCB) and a chassis assembly having the same, the heat-radiating PCB characterized by: a circuit pattern unit; and one or more mounting units bent from the circuit pattern unit to be fixed at a chassis providing a lightguide path of a backlight unit, where the circuit pattern unit includes a driving unit divided into a plurality of driving regions and at least one or more electrodes for supplying a power to the driving unit, and where, the mounting unit is arranged with an electrode line for connecting the driving unit and electrodes other than the electrode arranged on the circuit pattern unit, such that dimming and scanning functions can be performed whereby illumination can be finely controlled, the width of the circuit pattern unit can be narrowed and damage to the PCB caused by heat can be prevented.

Heat radiating printed circuit board and chassis assembly having the same

The present invention relates to a heat radiating printed circuit board (PCB) and a chassis assembly having the same, the heat-radiating PCB characterized by: a circuit pattern unit mounted with a light emitting diode; and one or more mounting units bent from the circuit pattern unit to be fixed at a chassis providing a lightguide path of a backlight unit, where one of the mounting units is mounted to the chassis via a thermal interface material to maximize the heat radiating characteristic of the PCB and to reduce the manufacturing cost.

Growing community of inventors

Seoul, South Korea

Jungho Lee