Patents by Inventor Kazumi Hasuko

Kazumi Hasuko 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).

  • Publication number: 20200202253
    Abstract: To construct a learned model exhibiting a high generalization capability. A data set is stored in a memory of a computer. A controller of the computer executes: sampling processing for sampling first learning data from the data set; clustering processing for generating a plurality of clusters by clustering data included in the data set; selection processing for selecting second learning data from a cluster not including the first learning data among the plurality of clusters; and configuration processing for configuring learning data set including the first learning data and at least a part of the second learning data as the learning data set.
    Type: Application
    Filed: October 2, 2019
    Publication date: June 25, 2020
    Inventors: Ryota TAMURA, Takafumi SEIMASA, Kazumi HASUKO, Akiteru HANATANI, Shinya IGUCHI
  • Publication number: 20200134680
    Abstract: To acquire an estimated price that is more accurate and capable of acquiring a sense of consent from a client more readily than the estimated price acquired by a conventional estimation method. A computer includes a memory and a controller. The memory stores data set, and the controller executes: prediction processing for predicting time required for review work of each piece of electronic data based on a feature amount of content included in the electronic data; evaluation processing for evaluating the number of steps required for the review work of the data set based on the time predicted in the prediction processing for each piece of electronic data; and estimation processing for estimating the cost required for the review work of the data set based on the number of steps evaluated in the evaluation processing.
    Type: Application
    Filed: October 2, 2019
    Publication date: April 30, 2020
    Inventors: Ryota TAMURA, Kazumi HASUKO, Shinya IGUCHI
  • Patent number: 10489427
    Abstract: The present invention includes: an extraction unit that extracts a specified quantity of documents, as targets to be classified by a user, from document information; a classification code accepting unit that accepts a classification code which is an identifier used when categorizing the documents, and is assigned by the user to each of the extracted documents; a database that records keywords selected from the extracted documents on the basis of the classification code; a score calculation unit that calculates a score which evaluates linkage strength between documents included in the document information, and the classification code on the basis of the keywords wherein the score calculation unit recalculates the score on the basis of a result of further extraction, by the extraction unit, of a specified quantity of documents, as targets to be classified by the user, from the document information according to the score.
    Type: Grant
    Filed: August 28, 2014
    Date of Patent: November 26, 2019
    Assignee: FRONTEO, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko
  • Patent number: 10467258
    Abstract: It is required to provide a method for classifying a set of data to be examined without a detailed analysis of the content of the set of data to be examined. A data classification system which solves the problem, the data classification system comprising: a data acquiring unit configured to acquire the plurality of data components of the data to be examined; an evaluation component extracting unit configured to extract a plurality of predetermined evaluation components from among the plurality of data components; a score value calculating unit configured to calculate score values for all of the plurality of known types based on the extracted plurality of evaluation components; and a classification determining unit configured to determine that the data to be examined belongs to a type with the highest value among the score values calculated by the score value calculating unit for all of the plurality of known types.
    Type: Grant
    Filed: October 18, 2016
    Date of Patent: November 5, 2019
    Assignee: FRONTEO, INC.
    Inventors: Hideki Takeda, Kazumi Hasuko
  • Patent number: 10445357
    Abstract: A document classification system is provided. The document classification system analyzes digital document information which is collected to be submitted as evidence in a lawsuit and classifies the digital document information.
    Type: Grant
    Filed: December 9, 2016
    Date of Patent: October 15, 2019
    Assignee: FRONTEO, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko
  • Patent number: 10204153
    Abstract: The present invention relates to data analysis for evaluating a plurality of pieces of object data; and the evaluation corresponds to the relation between each piece of object data and a specified case. An index that enables ranking of the plurality of pieces of object data is generated by the evaluation and the index changes based on an input entered by a user. A pattern is extracted that characterizes the reference data from the reference data according to the classification information assigned by the input. The index is determined by evaluating the relation between the object data and the specified case based on the extracted pattern and set to the object data. The plurality of pieces of object data are ranked according to the index and reported the user.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: February 12, 2019
    Assignee: FRONTEO, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko, Akiteru Hanatani, Jakob Halskov, Nanako Yoshida
  • Patent number: 10073891
    Abstract: A forensic system includes a result information receiving unit that receives result information which is a determination result of connection between a lawsuit and a document group including a predetermined number of documents, which is extracted from document data included in digital information, by a user, an element selection unit that calculates evaluation values of elements which commonly appear in the document group in each result information item from the characteristics of the elements and selects the elements on the basis of the evaluation values, a score calculation unit that calculates a score of each document in the document data from the selected elements included in each document of the document data and the evaluation values of the selected elements, and a recall ratio calculation unit that calculates a recall ratio related to the determination of the connection to the lawsuit on the basis of the score.
    Type: Grant
    Filed: April 29, 2016
    Date of Patent: September 11, 2018
    Assignee: FRONTEO, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko
  • Patent number: 9977825
    Abstract: Efficiency in monitoring documents is promoted by quantifying the priorities of the documents to be monitored. A document analysis system (1) includes: a score calculation unit (116) that calculates a score indicating strength of linkage between a document included in document information and a classification code indicating the relevance between the document information and a lawsuit or a fraud investigation; and a score report unit (701) that reports the score to a user according to the calculated score.
    Type: Grant
    Filed: February 4, 2014
    Date of Patent: May 22, 2018
    Assignee: UBIC, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko, Akiteru Hanatani
  • Publication number: 20180114093
    Abstract: Provided is a data analysis system that generates effective information affecting a user's tendency to buy a product and service. The data analysis system analyzes data to generate information on a tendency of a user, and includes: a memory that stores at least temporarily a plurality of evaluation data to be analyzed; and a controller that evaluates each of the plurality of evaluation data based on training data, wherein the controller extracts first information from the plurality of evaluation data based on results of the evaluation of the plurality of evaluation data, extracts second information from the training data based on a characteristic pattern included in the first information, and generates the information on the tendency of the user from the first information and the second information.
    Type: Application
    Filed: October 18, 2017
    Publication date: April 26, 2018
    Inventor: Kazumi HASUKO
  • Publication number: 20170358045
    Abstract: Regarding a data analysis system, a data acquisition unit acquires, as a training data set, a data set including a plurality of combinations of training data and classification information for classifying the training data. A relation evaluation unit that evaluates a relation between a data element included in the training data and the classification information. A partial data generation unit that divides each of a plurality of pieces of unknown data, which are analysis targets, into partial unknown data which constitute part of each pieces of the unknown data. A data evaluation unit that evaluates each piece of the partial unknown data on the basis of evaluation results by the relation evaluation unit.
    Type: Application
    Filed: February 6, 2015
    Publication date: December 14, 2017
    Inventors: Hideki TAKEDA, Kazumi HASUKO
  • Publication number: 20170293863
    Abstract: The present invention relates to data analysis whereby a plurality of components are extracted from learning data, each of the plurality of components constituting at least part of the learning data; a component to be utilized for evaluation of the plurality of pieces of evaluation data is selected, from among the plurality of components, on the basis of evaluation information about each of the plurality of extracted components; and the evaluation data is evaluated by utilizing the selected component.
    Type: Application
    Filed: April 7, 2017
    Publication date: October 12, 2017
    Inventor: Kazumi HASUKO
  • Patent number: 9690797
    Abstract: A digital information analysis system includes a target selection unit that selects target digital information, a combination storage unit that stores each of a plurality of word combinations related to a predetermined specific item, a search unit that searches whether the plurality of word combinations stored in the combination storage unit are included in the target digital information selected by the target selection unit, a relation determination unit that determines the relation of the target digital information to the predetermined specific item on the basis of a morphological analysis result when the plurality of word combinations stored in the combination storage unit are included in the target digital information, and a determination result setting unit that associates the determination result of the relation determination unit with the target digital information.
    Type: Grant
    Filed: March 17, 2014
    Date of Patent: June 27, 2017
    Assignee: UBIC, INC
    Inventors: Hideki Takeda, Kazumi Hasuko, Jakob Halskov
  • Publication number: 20170124179
    Abstract: It is required to provide a method for classifying a set of data to be examined without a detailed analysis of the content of the set of data to be examined. A data classification system which solves the problem, the data classification system comprising: a data acquiring unit configured to acquire the plurality of data components of the data to be examined; an evaluation component extracting unit configured to extract a plurality of predetermined evaluation components from among the plurality of data components; a score value calculating unit configured to calculate score values for all of the plurality of known types based on the extracted plurality of evaluation components; and a classification determining unit configured to determine that the data to be examined belongs to a type with the highest value among the score values calculated by the score value calculating unit for all of the plurality of known types.
    Type: Application
    Filed: October 18, 2016
    Publication date: May 4, 2017
    Inventors: Hideki Takeda, Kazumi Hasuko
  • Publication number: 20170097983
    Abstract: The present invention relates to data analysis for evaluating a plurality of pieces of object data; and the evaluation corresponds to the relation between each piece of object data and a specified case. An index that enables ranking of the plurality of pieces of object data is generated by the evaluation and the index changes based on an input entered by a user. A pattern is extracted that characterizes the reference data from the reference data according to the classification information assigned by the input. The index is determined by evaluating the relation between the object data and the specified case based on the extracted pattern and set to the object data. The plurality of pieces of object data are ranked according to the index and reported the user.
    Type: Application
    Filed: December 16, 2016
    Publication date: April 6, 2017
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko, Akiteru Hanatani, Jakob Halskov, Nanako Yoshida
  • Publication number: 20170091321
    Abstract: A document classification system is provided. The document classification system analyzes digital document information which is collected to be submitted as evidence in a lawsuit and classifies the digital document information.
    Type: Application
    Filed: December 9, 2016
    Publication date: March 30, 2017
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko, SR.
  • Publication number: 20170075986
    Abstract: Efficiency in monitoring documents is promoted by quantifying the priorities of the documents to be monitored. A document analysis system (1) includes: a score calculation unit (116) that calculates a score indicating strength of linkage between a document included in document information and a classification code indicating the relevance between the document information and a lawsuit or a fraud investigation; and a score report unit (701) that reports the score to a user according to the calculated score.
    Type: Application
    Filed: February 4, 2014
    Publication date: March 16, 2017
    Inventors: Masahiro MORIMOTO, Yoshikatsu SHIRAI, Hideki TAKEDA, Kazumi HASUKO, Akiteru HANATANI
  • Patent number: 9595071
    Abstract: A document classification and inspection system obtains digital information recorded in plural computers or servers, extracts a document from document information configured by plural documents, included in the obtained digital information, calculates a score indicating the strength of connection between the document and a classification code for the extracted document in a time-series manner, detects a time-series score change from the calculated score, and inspects the degree of relevance between an inspection case and the extracted document from the detected time-series score change.
    Type: Grant
    Filed: March 17, 2014
    Date of Patent: March 14, 2017
    Assignee: UBIC, Inc.
    Inventors: Masahiro Morimoto, Hideki Takeda, Kazumi Hasuko
  • Patent number: 9594757
    Abstract: It is possible to reduce a review load of a reviewer. A document management system acquires digital information recorded in a plurality of computers or a server and analyzes the acquired digital information for relevance to a lawsuit. The document management system includes a thread classification unit that verifies supplementary information of each piece of document data included in the digital information and classifies the document data into threads based on the supplementary information, a similarity analysis unit that extracts elements included in the supplementary information of the classified document data for each thread and analyzes similarity between the threads based on the extracted elements, and an integration unit that integrates the threads based on the similarity.
    Type: Grant
    Filed: November 22, 2013
    Date of Patent: March 14, 2017
    Assignee: UBIC, Inc.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko
  • Patent number: 9563652
    Abstract: The present invention relates to data analysis for evaluating a plurality of pieces of object data; and the evaluation corresponds to the relation between each piece of object data and a specified case. An index that enables ranking of the plurality of pieces of object data is generated by the evaluation and the index changes based on an input entered by a user. A pattern is extracted that characterizes the reference data from the reference data according to the classification information assigned by the input. The index is determined by evaluating the relation between the object data and the specified case based on the extracted pattern and set to the object data. The plurality of pieces of object data are ranked according to the index and reported the user.
    Type: Grant
    Filed: October 23, 2015
    Date of Patent: February 7, 2017
    Assignee: UBIC, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko, Akiteru Hanatani, Jakob Halskov, Nanako Yoshida
  • Patent number: 9552570
    Abstract: A document classification system is provided. The document classification system analyzes digital document information which is collected to be submitted as evidence in a lawsuit and classifies the digital document information.
    Type: Grant
    Filed: February 28, 2013
    Date of Patent: January 24, 2017
    Assignee: UBIC, INC.
    Inventors: Masahiro Morimoto, Yoshikatsu Shirai, Hideki Takeda, Kazumi Hasuko