Patents by Inventor Masahiro FUCHIZAKI

Masahiro FUCHIZAKI 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).

  • Natural language processing apparatus, natural language processing method, and recording medium for deducing semantic content of natural language elements based on sign language motion
    Patent number: 10733381
    Abstract: A natural language processing apparatus configured to analyze a plurality of natural language elements, includes processing configured to input for each natural language element, multiple sign language images for a certain natural language together with the respective natural language, extract multiple feature points of a first sign language motion from the input sign language images and analyze a common point or a differing point between the first sign language motion and a second sign language motion, for each of the extracted feature points, deduce semantic content of the natural language element from the analyzed common point or the differing point, and a storage configured to store in association with the natural language element, information regarding the deduced semantic content. The processing circuitry analyzes the natural language using an artificial intelligence algorithm.
    Type: Grant
    Filed: October 11, 2017
    Date of Patent: August 4, 2020
    Assignee: The Japan Research Institute, Limited
    Inventor: Masahiro Fuchizaki
  • NATURAL LANGUAGE PROCESSING APPARATUS, NATURAL LANGUAGE PROCESSING METHOD, AND RECORDING MEDIUM
    Publication number: 20180101520
    Abstract: A natural language processing apparatus configured to analyze a plurality of natural language elements, includes processing configured to input for each natural language element, multiple sign language images for a certain natural language together with the respective natural language, extract multiple feature points of a first sign language motion from the input sign language images and analyze a common point or a differing point between the first sign language motion and a second sign language motion, for each of the extracted feature points, deduce semantic content of the natural language element from the analyzed common point or the differing point, and a storage configured to store in association with the natural language element, information regarding the deduced semantic content. The processing circuitry analyzes the natural language using an artificial intelligence algorithm.
    Type: Application
    Filed: October 11, 2017
    Publication date: April 12, 2018
    Applicant: The Japan Research Institute, Limited
    Inventor: Masahiro FUCHIZAKI