Patents by Inventor Kosuke Naruse

Kosuke Naruse 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).

  • Information processing device, information processing method, and computer program product for evaluating performance of machine learning model
    Patent number: 12602612
    Abstract: An information processing device includes a hardware processor. The processor functions to generate first data to be input to a model used for deducing an effect of a case where a measure is executed with input of observation data. The first data represents the observation data obtained without execution of the measure. The processor functions to receive first parameters affecting the effect. Each first parameter is used in an estimation process of estimating the observation data when the measure is executed. The processor functions to execute the estimation process and generate second data representing the observation data. The processor functions to estimate the effect by using the first/second data. The processor functions to learn the model by using the first/second data. The processor functions to evaluate performance of the learned model by comparing the effect estimated by using the first/second data and the effect estimated by the learned model.
    Type: Grant
    Filed: August 30, 2022
    Date of Patent: April 14, 2026
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Ryusei Shingaki, Takashi Koiso, Kosuke Naruse, Hideki Ueno, Yoshikazu Ooba
  • INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT
    Publication number: 20230237373
    Abstract: An information processing device includes a hardware processor. The processor functions to generate first data to be input to a model used for deducing an effect of a case where a measure is executed with input of observation data. The first data represents the observation data obtained without execution of the measure. The processor functions to receive first parameters affecting the effect. Each first parameter is used in an estimation process of estimating the observation data when the measure is executed. The processor functions to execute the estimation process and generate second data representing the observation data. The processor functions to estimate the effect by using the first/second data. The processor functions to learn the model by using the first/second data. The processor functions to evaluate performance of the learned model by comparing the effect estimated by using the first/second data and the effect estimated by the learned model.
    Type: Application
    Filed: August 30, 2022
    Publication date: July 27, 2023
    Applicants: KABUSHIKI KAISHA TOSHIBA, TOSHIBA INFRASTRUCTURE SYSTEMS & SOLUTIONS CORPORATION
    Inventors: Ryusei Shingaki, Takashi Koiso, Kosuke Naruse, Hideki Ueno, Yoshikazu Ooba