Patents by Inventor Rodrigo Candido LEME

Rodrigo Candido LEME 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).

  • Root cause and predictive analyses for technical issues of a computing environment
    Patent number: 11449379
    Abstract: A process collects information about multiple systems of a computing environment from environmental tools web sources. The process builds and trains a classification model that extracts relevant information that classifies technical issues of the computing environment. The process performs root cause and predictive analyses, and identifies root causes of experienced technical issues and predicted technical issues. Based on identifying the root causes of the experienced technical issues, or identifying predicted issues, the process provides suggested corrective actions or optimization actions. Effectiveness of the suggested corrective actions and suggested optimization actions is tracked, and results of the tracking are fed into a training process that further trains the classification model.
    Type: Grant
    Filed: May 9, 2018
    Date of Patent: September 20, 2022
    Assignee: Kyndryl, Inc.
    Inventors: Edson Gomes Pereira, Alexandre Baltar, Thiago C. Rotta, Rodrigo Candido Leme
  • ROOT CAUSE AND PREDICTIVE ANALYSES FOR TECHNICAL ISSUES OF A COMPUTING ENVIRONMENT
    Publication number: 20190347148
    Abstract: A process collects information about multiple systems of a computing environment from environmental tools web sources. The process builds and trains a classification model that extracts relevant information that classifies technical issues of the computing environment. The process performs root cause and predictive analyses, and identifies root causes of experienced technical issues and predicted technical issues. Based on identifying the root causes of the experienced technical issues, or identifying predicted issues, the process provides suggested corrective actions or optimization actions. Effectiveness of the suggested corrective actions and suggested optimization actions is tracked, and results of the tracking are fed into a training process that further trains the classification model.
    Type: Application
    Filed: May 9, 2018
    Publication date: November 14, 2019
    Inventors: Edson GOMES PEREIRA, Alexandre BALTAR, Thiago C. ROTTA, Rodrigo Candido LEME