公开(公告)号：US20220156602A1

公开(公告)日：2022-05-19

申请号：US17477314

申请日：2021-09-16

Applicant: Hitachi, Ltd.

Inventor： Hiroyuki NAMBA ,  Masashi EGI ,  Masaki HAMAMOTO ,  Masakazu TAKAHASHI

IPC: G06N5/02

Abstract: In classification problems or regression problems, a prediction rule that is highly accurate, simple, and in match with the knowledge of experts is obtained. A system includes a prediction rule simplification unit that simplifies a prediction rule of a learning model using an evaluation metric and a restriction; a branch condition search unit that updates a part of the simplified branch condition for prediction rule based on calibration information expressing a request for a prediction value or a specific branch condition; and a threshold optimization unit that updates a part of a threshold of the simplified prediction rule based on the calibration information.

公开(公告)号：US20250053750A1

公开(公告)日：2025-02-13

申请号：US18791514

申请日：2024-08-01

Applicant: Hitachi, Ltd.

Inventor： Kohei MATSUSHITA ,  Masaki HAMAMOTO ,  Masayoshi MASE ,  Masashi EGI

IPC: G06F40/35

Abstract: A computer system stores a large-scale language model that receives an instruction sentence as an input and outputs an interpretation sentence for interpreting a result of an inference, and text template information that stores template data in which a characteristic of a contribution value of a feature in a group having features is associated with a template of the instruction sentence, calculates the contribution value of each of a plurality of the features, generates a plurality of groups each constituted with one or more of the features, acquires, for each of the plurality of groups, the template data by referring to the text template information based on the characteristic of the contribution value of the feature included in the group, generates, based on the template data and the feature included in the group, the instruction sentence to be input to the large-scale language model, and outputs the interpretation sentence obtained.

公开(公告)号：US20230410488A1

公开(公告)日：2023-12-21

申请号：US18036212

申请日：2021-11-22

Applicant: Hitachi, Ltd.

Inventor： Masaki HAMAMOTO ,  Masashi EGI ,  Masakazu TAKAHASHI ,  Hiroyuki NAMBA

IPC: G06V10/80 ,  G06V10/778

CPC classification number: G06V10/80 ,  G06V10/7788

Abstract: A predictor creation device including a processor configured to execute a program and a storage device that stores the program acquires a calibration target ensemble predictor obtained by combining a plurality of predictors based on a training data set which is a combination of training data and ground truth data, calculates a prediction basis characteristic related to a feature of the training data for each of the plurality of predictors, acquires an expected prediction basis characteristic related to the feature based on the prediction basis characteristic related to the feature as a result of outputting the prediction basis characteristic related to the calculated feature, determines a combination coefficient of each of the plurality of predictors based on the prediction basis characteristic related to the feature and the expected prediction basis characteristic related to the feature, and calibrates the calibration target ensemble predictor based on the combination coefficient.

公开(公告)号：US20220230119A1

公开(公告)日：2022-07-21

申请号：US17468797

申请日：2021-09-08

Applicant: Hitachi, Ltd.

Inventor： Yuxin LIANG ,  Masashi EGI ,  Yusuke FUNAYA ,  Masakazu TAKAHASHI

IPC: G06Q10/06 ,  G06F3/0482

Abstract: A computer has: a testing unit obtaining attribute values of attributes from an object to which a measure is implemented and an object to which the measure is not implemented, and calculating a change amount of the attribute values of the attributes due to the implementation of the measure and a test indicator for determining a significant difference of the change amount of the attribute values of the attributes due to the implementation of the measure; an experimental rule updating unit calculating a cumulative change amount indicating a temporal change amount of the attribute values of the attributes and a cumulative test indicator indicating a temporal test indicator of the attributes on the basis of a test result output from the testing unit, and accumulating data in which the identification information of the measure and the cumulative change amount and the cumulative test indicator are associated; and a display unit.

公开(公告)号：US20220129774A1

公开(公告)日：2022-04-28

申请号：US17469542

申请日：2021-09-08

Applicant: HITACHI, LTD.

Inventor： Naoaki YOKOI ,  Haruka YAMADA ,  Masashi EGI

IPC: G06N5/04 ,  G06N20/00

Abstract: An information processing system includes a predictor, a contribution calculator, and a supplemental base generator. The system accesses databases that store relevance between feature variables in case data and a contribution of a feature variable in the case data to a result of prediction. The contribution calculator calculates the contribution of each of the feature variables in the evaluation target data to the output of the predictor, and outputs the calculated contributions and the acquired evaluation target data. The supplemental reason generator extracts a group of data proximate to the value and the contribution of a first feature variable, identifies a second feature variable relevant to the first feature variable, generates supplemental reason data based on a distribution of the proximate data group within a distribution of the second feature variable by use of the case data, and outputs the generated supplemental reason data.

公开(公告)号：US20170270423A1

公开(公告)日：2017-09-21

申请号：US15532434

申请日：2015-06-17

Applicant: Hitachi, Ltd.

Inventor： Masashi EGI ,  Masashi KIGUCHI ,  Hirokazu ATSUMORI

IPC: G06N7/00

Abstract: A mood score calculation system includes a processor and a memory. The memory is configured to hold relationship information on a relationship between a mood score of a user and a statistical feature for indicating fluctuation of operational interval time of a user terminal. The processor is configured to acquire an operation log of a first user terminal. The processor is configured to calculate, from the operation log, a value of a statistical feature for indicating fluctuation of operational interval time of the first user terminal. The processor is configured to determine a mood score of a user of the first user terminal based on the value of the statistical feature and the relationship information and output the mood score.

公开(公告)号：US20240329627A1

公开(公告)日：2024-10-03

申请号：US18468247

申请日：2023-09-15

Applicant: Hitachi, Ltd.

Inventor： Naoaki YOKOI ,  Masashi EGI

IPC: G05B23/02

CPC classification number: G05B23/0221 ,  G05B23/0275 ,  G05B23/0286

Abstract: By using a time-series causal model stored in a time-series causal model storage unit and time-series data of an analysis target, a contribution degree restoration rate is calculated by evaluating how much a contribution degree of each time-series variable at each time is required to be restored to the contribution degree of another time-series variable at another time. Further, the contribution degree of each time-series variable at each time is restored, based on the calculated contribution degree restoration rate, to the contribution degree of the other time-series variable at the other time, and the transition of the contribution degree by a root factor with respect to an objective variable is calculated. Additionally, the contribution degree by the root factor with respect to the calculated objective variable is output.

公开(公告)号：US20220374801A1

公开(公告)日：2022-11-24

申请号：US17692237

申请日：2022-03-11

Applicant: Hitachi, Ltd.

Inventor： Yuta TSUCHIYA ,  Yasuhide MORI ,  Masashi EGI

IPC: G06Q10/06

Abstract: A plan evaluation apparatus, which evaluates a schedule planned by combining a plurality of plans, includes: a feature conversion unit that divides the schedule into plan components based on a predetermined conversion rule, and convert the divided plan components into features; a model learning unit that uses the features as an input and creates a machine learning model having a key performance indicator (KPI) of the schedule as an objective variable; a contribution rate calculation unit that calculates a contribution rate of each of the features with respect to the machine learning model; and an influence degree calculation unit that calculates an influence degree of influence, on the KPI of the schedule, of the plan component which is a conversion source of the feature, based on the contribution rate of the feature.

公开(公告)号：US20220004885A1

公开(公告)日：2022-01-06

申请号：US17206787

申请日：2021-03-19

Applicant: HITACHI, LTD.

Inventor： Haruka YAMADA ,  Naoaki YOKOI ,  Masashi EGI

IPC: G06N5/02

Abstract: A computer system includes a calculation unit for extracting specific reference data from a plurality of reference data, configured to calculate a contribution of the each feature amount of explanatory data regarding a predicted value using the specific piece of reference data, the explanatory data, and a predictor, and stores the contribution that has been calculated as a pair contribution in association with the specific piece of the reference data and the explanatory data, the pair contribution being a contribution that has been calculated with the one piece of the reference data and the explanatory data being a pair, for all pairs including each reference data and the explanatory data; and an aggregation unit for reading the pair contribution that has been calculated for the each feature amount of the explanatory data, and configured to calculate by aggregating the contribution of the each feature amount of the explanatory data.

公开(公告)号：US20200034738A1

公开(公告)日：2020-01-30

申请号：US16504897

申请日：2019-07-08

Applicant: Hitachi, Ltd.

Inventor： Masashi EGI ,  Yuxin LIANG ,  Naoaki YOKOI ,  Masayoshi MASE ,  Naofumi HAMA ,  Yasuhide MORI ,  Hiroyuki NAMBA

IPC: G06N20/00 ,  G06F16/22

Abstract: There is provided is a computer system that outputs a predicted value of data to be evaluated using a predictor generated using learning data. The computer system includes the predictor; an index calculation unit that calculates an interpretation index of the data to be evaluated; and an extraction unit that selects the learning data useful for a user to interpret the predicted value of the data to be evaluated, wherein index management information for managing an interpretation index of the learning data is stored, the index calculation unit calculates the interpretation index of the data to be evaluated, and the extraction unit calculates a selection index based on the interpretation index of the data to be evaluated and the interpretation index of the learning data, selects the learning data based on the selection index, and outputs display information for presenting information indicating a processing result.