公开(公告)号：US20140280196A1

公开(公告)日：2014-09-18

申请号：US14205850

申请日：2014-03-12

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Il Gu JUNG ,  Chang Woo YOON ,  Jun Kyun CHOI ,  Jin Hong YANG

IPC: H04L29/08 ,  G06F17/30

CPC classification number: H04L67/02 ,  G06F17/30893 ,  H04L63/062 ,  H04L63/10

Abstract: A method of providing a service among heterogeneous services may include verifying whether a second web application associated with an external web service is installed in a user agent, when data of the external web service is requested from a first web application executed in the user agent, requesting key information to be used for accessing the requested data from a first server providing a web service associated with the first web application, when the second web application is installed in the user agent, receiving the key information from the first server, and accessing the requested data existing on the second web application, using the received key information, in the first web application.

Abstract translation: 在异构服务之间提供服务的方法可以包括：当从用户代理中执行的第一web应用请求外部web服务的数据时，验证与外部Web服务相关联的第二Web应用是否安装在用户代理中， 当所述第二Web应用安装在所述用户代理中时，从提供与所述第一web应用相关联的Web服务的第一服务器请求用于访问所请求的数据的密钥信息，从所述第一服务器接收所述密钥信息， 使用所接收的密钥信息在第二web应用中存在的所请求的数据在第一web应用中。

公开(公告)号：US20240169198A1

公开(公告)日：2024-05-23

申请号：US18242725

申请日：2023-09-06

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： MUHAMMAD ZUBAIR ,  Sung Pil WOO ,  Chang Woo YOON ,  Sun Hwan LIM

IPC: G06N3/08 ,  G06N3/0442 ,  G06N3/0464

CPC classification number: G06N3/08 ,  G06N3/0442 ,  G06N3/0464

Abstract: An apparatus for training a deep learning model for classifying emotions from biosignals includes: a memory configured to store a program for training the deep learning model; and a processor configured to train the deep learning model by executing the program, wherein, when the processor executes the program, the processor inputs an input matrix to an attention layer constituting the deep learning model, the input matrix being composed of a plurality of features each mapped to a plurality of channels and a plurality of feature groups as the biosignals are acquired from a plurality of channels and the biosignals acquired from each channel are divided into the plurality of feature groups, and the attention layer operates to mask the input matrix using an attention matrix in which an importance of features in each channel is reflected.