公开(公告)号：US20240028982A1

公开(公告)日：2024-01-25

申请号：US18117561

申请日：2023-03-06

Applicant: Hitachi, Ltd.

Inventor： Yoshiyasu TAKAHASHI ,  Yuichi KOBAYASHI ,  Keitaro UEHARA ,  Tsukasa EIRAKU

IPC: G06Q10/0631 ,  G06Q50/04

CPC classification number: G06Q10/0631 ,  G06Q50/04

Abstract: Allowable constraint relaxation is achieved even when it is difficult to identify a constraint satisfaction solution. A production plan making device 1 that makes a plan related to a task has a production history DB2 that stores history information in the task, a past history reading unit 13 that reads the history information, a constraint relaxation unit 12 that identifies a deviation degree indicating a position relationship related to the constraint boundary of a constraint in making the plan of a history represented by the history information, calculates a weight indicating the degree of the constraint for constraint relaxation according to the deviation degree, and relaxes the weight when the plan cannot be made by an optimization process based on the weight, and a mathematical optimization unit 11 that makes the plan by the optimization process on the basis of the relaxed weight.

公开(公告)号：US20190220750A1

公开(公告)日：2019-07-18

申请号：US16156300

申请日：2018-10-10

Applicant: HITACHI, LTD.

Inventor： Yosuke FUJIWARA ,  Yoshiyasu TAKAHASHI ,  Yuichi KOBAYASHI ,  Tomoichi EBATA ,  Taichi ISHITOBI ,  Yasuharu NAMBA

IPC: G06N3/12 ,  G06N5/04

CPC classification number: G06N3/126 ,  G06N5/048

Abstract: An action-value function initializing unit inputs search information including a history of a solution, a constraint equation, and an initial state of a selectable domain of a decision variable, sets a decision variable selected in each step and a value of the decision variable as a policy, and initializes an action-value function including the policy, a selectable domain of a decision variable before policy decision, and a selectable domain of a decision variable after the policy decision as parameters. A search unit receives information of the action-value function initialized by the action-value function initializing unit, obtains a value of a corresponding action-value function from the policy, the domain of the decision variable before the policy decision, and a domain of the action-value function after the policy decision, searches for a policy in which the action-value function is largest, and searches for an optimum solution for the problem information.

公开(公告)号：US20190057065A1

公开(公告)日：2019-02-21

申请号：US16075275

申请日：2016-04-01

Applicant: Hitachi, Ltd.

Inventor： Yoshiyasu TAKAHASHI ,  Yumiko ISHIDO

IPC: G06F17/18 ,  G06N99/00

Abstract: A modeling device models observation data and includes a database unit that stores a mathematical model based on environment data obtained from the observation data, a statistical model based on a parameter, and region information including each point at which the observation data is obtained; a data reading unit that acquires the observation data and the environment data; and a modeling processing unit that applies the mathematical model or the statistical model. The modeling processing unit calculates a model output by applying the acquired environment data to the mathematical model at each point included in the region information. When a difference between the calculated model output and the acquired observation data is determined to be equal to or greater than a preset threshold, the modeling processing unit calculates a parameter from the acquired observation data and applies the statistical model using the calculated parameter.

公开(公告)号：US20240143837A1

公开(公告)日：2024-05-02

申请号：US18280800

申请日：2022-02-14

Applicant: Hitachi, Ltd.

Inventor： Akitoshi SHIMURA ,  Yoshiyasu TAKAHASHI ,  Miki YONEHARA

IPC: G06F21/62

CPC classification number: G06F21/6254

Abstract: In a data cooperation system in which information cooperates in a first system, a second system and a third system, the first system provides an already operating service and collects and publicizes behavior data as information for providing the service, the second system acquires the behavior data, generates a verification result applying the behavior data to a new technology as verification data, and publicizes the verification data, and the third system receives the behavior data and the verification data, supports decision of the determination result data, and publicizes the decided determination result data.

公开(公告)号：US20180121850A1

公开(公告)日：2018-05-03

申请号：US15795521

申请日：2017-10-27

Applicant: HITACHI, LTD.

Inventor： Jian ZHENG ,  Yasuharu NAMBA ,  Yuichi KOBAYASHI ,  Yoshiyasu TAKAHASHI

IPC: G06Q10/06 ,  G06Q10/08 ,  G05B19/418

Abstract: The system includes an ideal plan creation unit configured to create an ideal plan of the respective processes in a first process order based on a process knowledge information being a relationship between the product and an implementation time of the respective processes and on a predetermined indicator, a plan candidate planning unit configured to create a plurality of the plan candidates in the respective processes in an order opposite to the first process order based on a limitation condition being a limitation or condition which imposes on the respective processes, a plan candidate selection unit configured to calculate similarity between the ideal plan and each of the plurality of the plan candidates and to select the plan candidate having a high similarity to the ideal plan as an implementation plan, and a learning unit configured to reflect the selected implementation plan on the process knowledge information.

公开(公告)号：US20160267417A1

公开(公告)日：2016-09-15

申请号：US15032789

申请日：2013-11-07

Applicant: HITACHI, LTD.

Inventor： Tomoe TOMIYAMA ,  Tatsuhiro SATOU ,  Yoshiyasu TAKAHASHI

IPC: G06Q10/06

CPC classification number: G06Q10/06315 ,  B61L27/0016 ,  B61L27/0027 ,  G06Q10/06313 ,  G06Q50/30

Abstract: A plan coordination system includes a processing device configured to perform: processing that generates public data from definition data of plans, receives definitions by a user for information coordinated between plans among process procedures indicated by the public data, applies the definitions by the user to the definition data of the plan, and generates a plan coordination model; processing that notifies the data to a management device of another plan as a coordination destination in the coordination relation at a change event on the definition data, changes the plan coordination model based on a generation result of the other plan reflecting the change event, and notifies the changed data to the management device of the other plan having the coordination relation with the plan changed along with this change; and processing that outputs a generation result of each plan when planning is completed for all plans.

Abstract translation: 计划协调系统包括：处理装置，被配置为执行：从计划的定义数据生成公共数据的处理，接收由用户为由公共数据指示的处理过程之间的计划之间协调的信息的定义，将用户的定义应用于 计划的定义数据，并生成计划协调模型; 在定义数据上的改变事件上，将协调关系中作为协调关系的另一计划的管理装置通知数据的处理，基于反映变更事件的其他计划的生成结果来改变计划协调模型，并通知 具有与计划协调关系的另一计划的管理设备的更改数据随着此变更而改变; 以及对于所有计划完成规划时，输出每个计划的生成结果的处理。