公开(公告)号：US20140156692A1

公开(公告)日：2014-06-05

申请号：US14032381

申请日：2013-09-20

Applicant: FUJITSU LIMITED

Inventor： TAKASHI KATOH ,  Shinichiro TAGO ,  Tatsuya ASAI ,  Hiroaki MORIKAWA ,  Hiroya INAKOSHI ,  NOBUHIRO YUGAMI

IPC: G06F17/30

CPC classification number: G06F17/30654

Abstract: An extraction program causes a computer to execute a process. The process includes adding an event to a first pattern including the events according to the sequential order, thus generating a second pattern in such a manner that the second pattern is generated by adding the event when a first value is less than a predetermined threshold; when the event is added, adding a predetermined value to the first value, and adding the predetermined value to a second value in a column corresponding to an end of the added event among second values corresponding to respective columns of a table; extracting the second pattern that satisfies a predetermined condition; and when an event in a second or subsequent column in the table is added.

Abstract translation: 提取程序使计算机执行一个进程。 该过程包括将事件添加到包括根据顺序的事件的第一模式，从而产生第二模式，使得通过在第一值小于预定阈值时相加事件来生成第二模式; 当添加所述事件时，向所述第一值添加预定值，并将所述预定值添加到与对应于表的相应列的第二值中的所述相加事件的结束对应的列中的第二值; 提取满足预定条件的第二图案; 并且当表中的第二列或后续列中的事件被添加时。

公开(公告)号：US20230306306A1

公开(公告)日：2023-09-28

申请号：US18159106

申请日：2023-01-25

Applicant: Fujitsu Limited

Inventor： TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A non-transitory computer-readable storage medium storing a machine learning program that causes at least one computer to execute a process, the process includes estimating a first label distribution of unlabeled training data based on a classification model and an initial value of a label distribution of a transfer target domain, the classification model being trained by using labeled training data which corresponds to a transfer source domain and unlabeled training data which corresponds to the transfer target domain; acquiring a second label distribution based on the labeled training data; acquiring a weight of each label included in the labeled training data and the unlabeled training data based on a difference between the first label distribution and the second label distribution; and re-training the classification model by the labeled training data and the unlabeled training data reflected the weight of each label.

公开(公告)号：US20230186118A1

公开(公告)日：2023-06-15

申请号：US18157639

申请日：2023-01-20

Applicant: FUJITSU LIMITED

Inventor： Tomohiro HAYASE ,  TAKASHI KATOH ,  Suguru YASUTOMI ,  Kento UEMURA

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: A program for causing a computer to execute processing including: acquiring a plurality of datasets, each of which includes data values associated with a label, the data values having properties different for each dataset; calculating an index indicating a degree of a difference between first and second datasets by using a data value in the second dataset; calculating accuracy of a prediction result for the second dataset, predicted by a prediction model trained using the first dataset; specifying a relationship between the index and the accuracy of the prediction result from the prediction model, based on the index and the accuracy calculated for each of a plurality of combinations of the first and second datasets; and estimating accuracy of the prediction result from the prediction model for a third dataset including data values without labels based on the specified relationship and the index between the first and third datasets.

公开(公告)号：US20220245405A1

公开(公告)日：2022-08-04

申请号：US17727915

申请日：2022-04-25

Applicant: FUJITSU LIMITED

Inventor： TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI ,  Tomohiro Hayase ,  YUHEI UMEDA

IPC: G06K9/62 ,  G06N20/00

Abstract: A deterioration suppression device generates a plurality of trained machine learning models having different characteristics on the basis of each training data included in a first training data set and assigned with a label indicating correct answer information. In a case where estimation accuracy of label estimation with respect to input data to be estimated by any trained machine learning model among the plurality of trained machine learning models becomes lower than a predetermined standard, the deterioration suppression device generates a second training data set including a plurality of pieces of training data using an estimation result by a trained machine learning model with the estimation accuracy equal to or higher than the predetermined standard. The deterioration suppression device executes re-learning of the trained machine learning model with the estimation accuracy lower than the predetermined standard using the second training data set.

公开(公告)号：US20200160119A1

公开(公告)日：2020-05-21

申请号：US16680562

申请日：2019-11-12

Applicant: FUJITSU LIMITED

Inventor： Hiroya INAKOSHI ,  TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: An apparatus receives, at a discriminator within a generative adversarial network, first generation data from a first generator within the generative adversarial network, where the first generator has performed learning using a first data group. The apparatus receives, at the discriminator, a second data group, and performs learning of a second generator based on the first generation data and the second data group where the first generation data is handled as false data by the discriminator.

公开(公告)号：US20180018362A1

公开(公告)日：2018-01-18

申请号：US15598712

申请日：2017-05-18

Applicant: FUJITSU LIMITED

Inventor： Tatsuya Asai ,  TAKASHI KATOH ,  Junichi Shigezumi ,  Hiroya INAKOSHI ,  Yuiko OHTA

IPC: G06F17/30

CPC classification number: G06F16/2365 ,  G06F16/2379 ,  G06F16/2456 ,  G06F16/273

Abstract: A data processing apparatus includes a processor. The processor selects candidate tables corresponding to a first table. The respective candidate tables include a first data item included in the first table. The processor acquires a first coincidence degree of the first table for the respective candidate tables. The processor selects third tables corresponding to one of the candidate tables. The respective third tables include a second data item included in the one of the candidate tables. The processor acquires a second coincidence degree of the one of the candidate tables for the respective third tables. The processor acquires a reliability of the one of the candidate tables on basis of the first coincidence degree of the first table for the one of the candidate tables and the second coincidence degree of the one of the candidate tables for the respective third tables.

公开(公告)号：US20150026217A1

公开(公告)日：2015-01-22

申请号：US14308738

申请日：2014-06-19

Applicant: FUJITSU LIMITED

Inventor： TAKASHI KATOH ,  Shinichiro Tago ,  Tatsuya Asai ,  Hiroaki Morikawa ,  Junichi Shigezumi ,  Hiroya Inakoshi

IPC: G06F17/30

CPC classification number: G06F17/30958

Abstract: A data output method includes: generating, by a computer, (n−1) first conditions (n is an integer number of three or more) on a relationship between two data by dividing, in a sequential order, a common element condition in which an attribute of each of n data includes a common element, the attribute of each of the two data including the common element; extracting first data corresponding to each of n data to set the first data as a node under a condition; creating a first graph in which nodes are coupled with links based on the first condition; creating a second graph by repeatedly performing a first process, a second process and a third process; determining candidates of a combination of data from the second graph; and outputting a combination of data satisfying the common element condition from the candidates of a combination of data.

Abstract translation: 一种数据输出方法包括：通过计算机根据两个数据之间的关系，通过按照顺序依次划分公共元素条件（n-3）或n个以上的整数，生成（n-1）个公共元素条件，其中 n个数据中的每一个的属性包括公共元素，包括公共元素的两个数据中的每一个的属性; 提取与n个数据中的每一个相对应的第一数据，以将第一数据设置为条件下的节点; 创建第一图形，其中节点基于第一条件与链接耦合; 通过重复执行第一处理，第二处理和第三处理来创建第二图; 确定来自所述第二图的数据的组合的候选者; 以及从数据的组合的候选中输出满足公共元素条件的数据的组合。

公开(公告)号：US20200302611A1

公开(公告)日：2020-09-24

申请号：US16811108

申请日：2020-03-06

Applicant: FUJITSU LIMITED

Inventor： Kento UEMURA ,  Suguru YASUTOMI ,  TAKASHI KATOH

IPC: G06T7/11 ,  G06K9/62 ,  G06N3/08

Abstract: An estimation method implemented by a computer, the estimation method includes: executing learning processing by training an autoencoder with a data group corresponding to a specific task; calculating a degree of compression of each part regarding data included in the data group by using the trained autoencoder; and estimating a common part with another piece of data included in the data group regarding the data corresponding to the specific task based on the calculated degree of compression of each part.

公开(公告)号：US20200280525A1

公开(公告)日：2020-09-03

申请号：US16801165

申请日：2020-02-26

Applicant: FUJITSU LIMITED ,  National University Corporation KUMAMOTO UNIVERSITY

Inventor： Yasushi SAKURAI ,  Yasuko MATSUBARA ,  Yasuaki IRIFUNE ,  Saeru YAMAMURO ,  Kouki KAWABATA ,  Akira URA ,  TAKASHI KATOH ,  YUHEI UMEDA

IPC: H04L12/911 ,  H04L12/927 ,  H04L12/723 ,  H04L12/26

Abstract: An allocation method executed by a computer includes dividing each of a plurality of pieces of time-series data into a plurality of segments, allocating a label to each of the pieces of time-series data based on features of each segment in the pieces of time-series data, and allocating a predetermined segment in time-series data, included in the pieces of time-series data, with a label allocated to the time-series data to which the predetermined segment belongs.

公开(公告)号：US20200234081A1

公开(公告)日：2020-07-23

申请号：US16736911

申请日：2020-01-08

Applicant: FUJITSU LIMITED

Inventor： TAKASHI KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06K9/62

Abstract: A learning device learns at last one parameter of a learning model such that each intermediate feature quantity becomes similar to a reference feature quantity, the each intermediate feature quantity being calculated as a result of inputting a plurality of sets of augmentation training data to a first neural network in the learning model, the plurality of augmentation training data being generated by performing data augmentation based on same first original training data. The learning device learns at last one parameter of a second network, in the learning model, using second original training data, which is different than the first original training data, and using the reference feature quantity.