公开(公告)号：US11043289B2

公开(公告)日：2021-06-22

申请号：US16366247

申请日：2019-03-27

Applicant: General Electric Company

Inventor： Bex George Thomas ,  Rajesh Tyagi ,  Nitish Umang ,  Aristotelis Emmanouil Thanos Filis ,  Andrew Day ,  Savanoor Pradeep Rai

IPC: G16H40/20 ,  G16H10/60 ,  G16H15/00 ,  G16H50/30 ,  G06N3/08 ,  G16H50/20 ,  G16H40/63 ,  G06N3/04

Abstract: Systems and techniques for monitoring, predicting and/or alerting for census periods in medical inpatient units are presented. A system can perform a first machine learning process to learn patterns in patient flow data related to a set of patient identities and a set of operations associated with a set of medical inpatient units. The system can also perform a second machine learning process to detect abnormalities associated with the patterns in the patient flow data. Furthermore, the system can determine patient census data associated with a prediction for a total number of patient identities in the set of medical inpatient units during a period of time based on the patterns and the abnormalities. The system can also generate an alert for a user interface in response to a determination that the patient census data satisfies a defined criterion.

公开(公告)号：US20200312430A1

公开(公告)日：2020-10-01

申请号：US16366247

申请日：2019-03-27

Applicant: General Electric Company

Inventor： Bex George Thomas ,  Rajesh Tyagi ,  Nitish Umang ,  Aristotelis Emmanouil Thanos Filis ,  Andrew Day ,  Savanoor Pradeep Rai

IPC: G16H10/60 ,  G06N3/08 ,  G16H15/00 ,  G16H50/30

Abstract: Systems and techniques for monitoring, predicting and/or alerting for census periods in medical inpatient units are presented. A system can perform a first machine learning process to learn patterns in patient flow data related to a set of patient identities and a set of operations associated with a set of medical inpatient units. The system can also perform a second machine learning process to detect abnormalities associated with the patterns in the patient flow data. Furthermore, the system can determine patient census data associated with a prediction for a total number of patient identities in the set of medical inpatient units during a period of time based on the patterns and the abnormalities. The system can also generate an alert for a user interface in response to a determination that the patient census data satisfies a defined criterion.

公开(公告)号：US20160231716A1

公开(公告)日：2016-08-11

申请号：US15019649

申请日：2016-02-09

Applicant: General Electric Company

Inventor： Christopher Donald Johnson ,  Rajesh Tyagi ,  Radhakrishnan Poomari ,  Ilkin Onur Dulgeroglu

IPC: G05B13/04

CPC classification number: G05B13/041 ,  Y02E20/16

Abstract: Aspects of the present disclosure relate to a system comprising a computer-readable storage medium storing at least one program and a method for optimizing and controlling the physical and business aspects of an industrial system. In example embodiments, the method may include assessing criteria to be applied to an industrial system, and generating simulation scenarios based on the criteria. The method may further include simulating each of the simulation scenarios over a period of time to generate simulated physical aspects and simulated business aspects of the industrial system for each of the plurality of simulation scenarios. The method may further include identifying at least one of the simulation scenarios for use with the industrial system based on a comparison of the simulated physical aspects and the simulated business aspects corresponding to each simulation scenario.

Abstract translation: 本公开的方面涉及包括存储至少一个程序的计算机可读存储介质和用于优化和控制工业系统的物理和业务方面的方法的系统。 在示例实施例中，该方法可以包括评估要应用于工业系统的标准，以及基于该标准生成模拟场景。 该方法还可以包括在一段时间内模拟每个模拟场景，以针对多个模拟场景中的每一个生成工业系统的模拟物理方面和模拟业务方面。 该方法可以进一步包括基于模拟物理方面与对应于每个模拟情景的模拟业务方面的比较来识别与工业系统一起使用的模拟场景中的至少一个。

公开(公告)号：US20140095410A1

公开(公告)日：2014-04-03

申请号：US13629827

申请日：2012-09-28

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Weiwei Chen ,  Jason Wayne Black ,  Rajesh Tyagi ,  Xing Wang

IPC: G06Q50/06

CPC classification number: G06Q50/06 ,  G06Q10/04 ,  H02J13/0013 ,  Y02E60/7807 ,  Y04S40/12

Abstract: A method for demand response management includes determining a number of available demand response events and a number of opportunities available to issue the available demand response events. A priority for each demand response event is provided and a threshold value for each demand response vent is determined. A highest priority demand response event among the available demand response events whose threshold value is lower than an observed value of a selected demand response trigger is selected and control signals to utilize the selected demand response event for a current opportunity are transmitted to customer sites.

Abstract translation: 一种用于需求响应管理的方法包括确定可用需求响应事件的数量以及可用于发布可用需求响应事件的多个机会。 提供每个需求响应事件的优先级，并且确定每个需求响应通风口的阈值。 选择其阈值低于所选择的需求响应触发的观察值的可用需求响应事件中的最高优先级需求响应事件，并将用于当前机会的所选择的需求响应事件的控制信号发送到客户站点。