Patents by Inventor Hyung Jun Seo

Hyung Jun Seo has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Automatic prediction system for server failure and method of automatically predicting server failure
    Patent number: 10877863
    Abstract: The present invention relates to an automatic prediction system for a server failure, which monitors the status of a single server connected to a network and providing web, DB and network services, and predicts and warns a server failure of a target system by using the collected status data of the single server. The automatic prediction system for a server failure comprises: a data collection module to collect status information of a server and service of a target system; a model generation and optimization module to generate a CNN-based failure prediction model by using the collected data and to optimize model parameters and hyper-parameter values; and a prediction module to perform online failure prediction by using the optimized CNN-based failure prediction model.
    Type: Grant
    Filed: February 10, 2019
    Date of Patent: December 29, 2020
    Assignee: GLUESYS, CO, LTD.
    Inventors: Seung Ho Choi, Jae Chun No, Gyeong Hun Kim, Hyung Jun Seo, Jae Hwan Kim
  • AUTOMATIC PREDICTION SYSTEM FOR SERVER FAILURE AND METHOD OF AUTOMATICALLY PREDICTING SERVER FAILURE
    Publication number: 20200125465
    Abstract: The present invention relates to an automatic prediction system for a server failure, which monitors the status of a single server connected to a network and providing web, DB and network services, and predicts and warns a server failure of a target system by using the collected status data of the single server. The automatic prediction system for a server failure comprises: a data collection module to collect status information of a server and service of a target system; a model generation and optimization module to generate a CNN-based failure prediction model by using the collected data and to optimize model parameters and hyper-parameter values; and a prediction module to perform online failure prediction by using the optimized CNN-based failure prediction model.
    Type: Application
    Filed: February 10, 2019
    Publication date: April 23, 2020
    Inventors: Seung Ho Choi, Jae Chun No, Gyeong Hun Kim, Hyung Jun Seo, Jae Hwan Kim