公开(公告)号：US20160162543A1

公开(公告)日：2016-06-09

申请号：US14733693

申请日：2015-06-08

Applicant: General Electric Company

Inventor： Steven Matt Gustafson ,  Abha Moitra ,  Kareem Sherif Aggour ,  Luis Babaji Ng Tari ,  Aisha Yousuf

IPC: G06F17/30

CPC classification number: G06F17/30448 ,  G06F17/30353 ,  G06F17/30477 ,  G06F17/30548 ,  G06Q50/00

Abstract: A system and method for searching for and finding data across industrial time-series data is disclosed. A computer system receives a search query from a client system. The computer system accesses a database including a plurality of stored time-series data sets. For each stored time-series data set, the computer system determines whether the stored time-series data set includes one or more sections that match the received search query. In accordance with a determination that two or more of stored time-series data sets include at least one section that matches the received search query, the computer system determines whether the matching sections in each stored time-series data set have overlapping time periods. In accordance with a determination that the matching sections in each time-series data set have overlapping time periods, the computer system identifies a particular event that occurred during the overlapping time periods.

Abstract translation: 公开了一种用于在工业时间序列数据中搜索和查找数据的系统和方法。 计算机系统从客户端系统接收搜索查询。 计算机系统访问包括多个存储的时间序列数据集的数据库。 对于每个存储的时间序列数据集，计算机系统确定所存储的时间序列数据集是否包括与所接收的搜索查询匹配的一个或多个部分。 根据存储的时间序列数据集中的两个或更多个包括与所接收的搜索查询匹配的至少一个部分的确定，计算机系统确定每个存储的时间序列数据集中的匹配部分是否具有重叠的时间段。 根据每个时间序列数据集中的匹配部分具有重叠时间段的确定，计算机系统识别在重叠时间段期间发生的特定事件。

公开(公告)号：US20160110478A1

公开(公告)日：2016-04-21

申请号：US14517485

申请日：2014-10-17

Applicant: General Electric Company

Inventor： Kareem Sherif Aggour ,  Andrew Walter Crapo ,  Abha Moitra ,  Steven Matt Gustafson

IPC: G06F17/30 ,  G06F11/30 ,  G06F11/34

CPC classification number: G06F16/904 ,  G06F17/40

Abstract: Embodiments allow blocking and featurization of time-series data gathered from at least one sensor. The input time-series data is divided into blocks with common attributes (features) according to feature models that describe patterns in the data. The blocks may be overlapping or non-overlapping. The resultant feature blocks are annotated with feature information and semantic meaning. The feature blocks can be indexed to facilitate semantic search of the data. Feature blocks may be further analyzed to create semantic blocks that incorporate semantic meaning and features for multiple feature blocks, sensors and/or related time-series data. The semantic blocks can also be indexed to facilitate semantic search of the data.

Abstract translation: 实施例允许从至少一个传感器收集的时间序列数据的阻塞和特征化。 根据描述数据中的模式的特征模型，输入时间序列数据被划分为具有共同属性（特征）的块。 块可以是重叠的或不重叠的。 所得到的特征块用特征信息和语义来注释。 特征块可以索引，以便于数据的语义搜索。 可以进一步分析特征块以创建包含多个特征块，传感器和/或相关时间序列数据的语义和特征的语义块。 语义块也可以索引，以便于数据的语义搜索。

公开(公告)号：US20160019192A1

公开(公告)日：2016-01-21

申请号：US14336578

申请日：2014-07-21

Applicant: General Electric Company

Inventor： Andrew Walter Crapo ,  Abha Moitra

IPC: G06F17/22 ,  G06F17/30

CPC classification number: G06F16/93 ,  G06F17/2785

Abstract: According to some embodiments, a document associated with an artifact may be received, the document being at least partially unstructured. In an unstructured portion of the document, an extraction platform may automatically detect a first characteristic. The extraction platform may also automatically detect a second characteristic in the unstructured portion of the document. Using the first and second characteristics, a structured semantic model representing the artifact may automatically be created.

Abstract translation: 根据一些实施例，可以接收与工件相关联的文档，该文档至少部分地是非结构化的。 在文档的非结构化部分中，提取平台可以自动检测第一特征。 提取平台还可以自动检测文档的非结构化部分中的第二特性。 使用第一和第二特征，可以自动地创建表示伪像的结构化语义模型。

公开(公告)号：US20190108452A1

公开(公告)日：2019-04-11

申请号：US15726638

申请日：2017-10-06

Applicant: General Electric Company

Inventor： Abha Moitra ,  Andrew Walter Crapo ,  Marc Thomas Edgar ,  Ravi Kiran Reddy Palla

IPC: G06N5/04 ,  G06N5/02

Abstract: A method for knowledge management using concept rules includes receiving event data corresponding to an industrial application and generating at least one inference concept based on the event data. The method also includes obtaining a semantic model having a plurality of inference concepts, a plurality of relationships among the plurality of inference concepts, and a plurality of concept rules representative of domain knowledge. The plurality of concept rules is authored using the plurality of inference concepts and the plurality of relationships. Furthermore, the method includes processing the at least one inference concept based on the semantic model to generate inferential data. The inferential data is representative of an inference corresponding to the event data. In addition, the method includes controlling the industrial application based on the inferential data.

公开(公告)号：US20140324908A1

公开(公告)日：2014-10-30

申请号：US13872868

申请日：2013-04-29

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Michael Evans Graham ,  Andrew Walter Crapo ,  Abha Moitra ,  Gerald Bowden Wise ,  Steven Matt Gustafson ,  Victor Manuel Perez-Zarate ,  Luis Babaji Ng Tari

IPC: G06F17/30

CPC classification number: G06F16/215

Abstract: The present disclosure relates to the use of both semantic analysis and statistical text mining to process data records, improving the completeness and accuracy of records so processed. By way of example, a data record may be iteratively processed by text mining using seeds derived from a semantic template and by validating the results based on semantic reasoning based on the semantic template.

Abstract translation: 本公开涉及使用语义分析和统计文本挖掘来处理数据记录，提高如此处理的记录的完整性和准确性。 作为示例，可以通过使用从语义模板导出的种子的文本挖掘来迭代地处理数据记录，并且基于基于语义模板的语义推理来验证结果。

公开(公告)号：US10078664B2

公开(公告)日：2018-09-18

申请号：US14733693

申请日：2015-06-08

Applicant: General Electric Company

Inventor： Steven Matt Gustafson ,  Abha Moitra ,  Kareem Sherif Aggour ,  Luis Babaji Ng Tari ,  Aisha Yousuf

IPC: G06F17/30 ,  G06Q50/00

CPC classification number: G06F16/24534 ,  G06F16/2322 ,  G06F16/2455 ,  G06F16/2474 ,  G06Q50/00

Abstract: A system and method for searching for and finding data across industrial time-series data is disclosed. A computer system receives a search query from a client system. The computer system accesses a database including a plurality of stored time-series data sets. For each stored time-series data set, the computer system determines whether the stored time-series data set includes one or more sections that match the received search query. In accordance with a determination that two or more of stored time-series data sets include at least one section that matches the received search query, the computer system determines whether the matching sections in each stored time-series data set have overlapping time periods. In accordance with a determination that the matching sections in each time-series data set have overlapping time periods, the computer system identifies a particular event that occurred during the overlapping time periods.

公开(公告)号：US20170011301A1

公开(公告)日：2017-01-12

申请号：US14795611

申请日：2015-07-09

Applicant: General Electric Company

Inventor： Abha Moitra ,  Arvind Rangarajan ,  Ravi Kiran Reddy Palla

IPC: G06N5/04 ,  G06N99/00

CPC classification number: G06N5/046

Abstract: In various example embodiments, a semantic modeling server includes a semantic model and an inductive logic programming module. The semantic module includes underlying data that defines one or more characteristics of a part to be manufactured. The inductive logic programming module is provided with positive and negative examples of a feature to be identified and part data that defines the part to be manufactured. Given the examples of the feature and the semantic model, the inductive logic programming module determines various rules that can be used to identify whether the provided part data includes the feature defined by the semantic model. Using the determined rules the inductive logic programming module then identifies instances of the feature associated with the semantic model within the provided part data. The inductive logic programming can then be iteratively executed with the semantic model to refine the determined rules.

Abstract translation: 在各种示例实施例中，语义建模服务器包括语义模型和电感逻辑编程模块。 语义模块包括定义要制造的零件的一个或多个特性的底层数据。 电感逻辑编程模块具有要识别的特征的正和负的示例以及限定要制造的部件的零件数据。 给定特征和语义模型的示例，归纳逻辑编程模块确定可以用于识别所提供的部分数据是否包括由语义模型定义的特征的各种规则。 使用确定的规则，感应逻辑编程模块然后识别与所提供的部件数据内的语义模型相关联的特征的实例。 然后可以用语义模型迭代地执行归纳逻辑编程，以细化确定的规则。

公开(公告)号：US20160098033A1

公开(公告)日：2016-04-07

申请号：US14507195

申请日：2014-10-06

Applicant: General Electric Company

Inventor： Baljit Singh ,  Abha Moitra ,  Michael Evans Graham ,  Dean Michael Robinson ,  Tao Jia

IPC: G05B19/4097

CPC classification number: G05B19/4097 ,  G05B2219/35028 ,  G05B2219/35032 ,  G05B2219/35088 ,  G05B2219/35134 ,  G05B2219/35193 ,  G06F17/5086 ,  G06F2217/12 ,  Y02P90/265

Abstract: A dataset including boundary representations of shapes associated with an item being designed for manufacture is accessed by a semantic processing module. A semantic graph of each of the boundary representations of shapes is generated and a numerical processing module computes geometric attributes of each of the shapes. The semantic graph of a shape is updated based on any geometric attributes computed for the shape. The semantic graphs are then compared to a repository of semantic graphs of manufacturing features to identify instances of manufacturing features. Geometric attributes associated with each instance of a manufacturing feature are then computed. For each instance, the associated geometric attributes are compared against a repository of semantic manufacturing rules to determine whether the instance is in compliance with the rules. A user designing the item is alerted to the presence of any instances of manufacturing features that are not in compliance with the rules.

Abstract translation: 包括与被设计用于制造的物品相关联的形状的边界表示的数据集由语义处理模块访问。 生成每个形状的边界表示的语义图，并且数值处理模块计算每个形状的几何属性。 基于为形状计算的任何几何属性，更新形状的语义图。 然后将语义图与制造特征的语义图库进行比较，以识别制造特征的实例。 然后计算与制造特征的每个实例相关联的几何属性。 对于每个实例，将相关联的几何属性与语义制造规则的存储库进行比较，以确定实例是否符合规则。 设计该项目的用户会警告任何不符合规则的制造功能实例的存在。

公开(公告)号：US09244909B2

公开(公告)日：2016-01-26

申请号：US13710218

申请日：2012-12-10

Applicant: General Electric Company

Inventor： Luis Babaji Ng Tari ,  Abha Moitra

IPC: G06F12/06 ,  G06F17/27

CPC classification number: G06F17/2785 ,  G06F17/2705 ,  G06F17/274

Abstract: A system for extracting ontological information from a body of text is disclosed. The system parses one or more sentences from the body of text into parse tree format to generate a set of parsed sentences. The system further performs named-entity-recognition by identifying a subset of parsed sentences from the set of parsed sentences. A subset of noun phrases from the subset of parsed sentences are identified and the noun phrases are examined to classify the noun phrases as an entity or as a property. The system also identifies and outputs a conceptual relationship between the entity and the property based at least partially on grammatical relationship of the entity and the property.

Abstract translation: 公开了一种从文本体提取本体信息的系统。 系统将文本主体中的一个或多个句子解析为解析树格式，以生成一组解析的句子。 该系统通过从解析的语句集合中识别解析语句的子集来进一步执行命名实体识别。 识别来自解析语句子集的名词短语的子集，并且对名词短语进行检查，将名词短语分类为实体或属性。 该系统还至少部分地基于实体和财产的语法关系来识别并输出实体与财产之间的概念关系。

公开(公告)号：US10101752B2

公开(公告)日：2018-10-16

申请号：US15252554

申请日：2016-08-31

Applicant: General Electric Company

Inventor： Adam Rasheed ,  Abha Moitra ,  Aisha Yousuf ,  Jinfeng Zhang

IPC: E21B41/00 ,  E21B43/12 ,  E21B47/00 ,  G05D7/06 ,  G06N5/02

Abstract: A hydrocarbon extractor (HE) evaluator system includes a central controller and an HE evaluator model that includes a hierarchical equipment model of heterogeneous HE type, subtype, and property, a plurality of rules arrangeable as a hierarchical equipment rule set, and as a hierarchical well feature rule set, a rules engine, the hierarchical well feature rule set formatted for a multi-factor comparison by the rules engine between heterogeneous HE types from disparate sources applied to the hierarchical equipment model. The rules engine configured to apply rules using class structure and one or more categories to an extracted portion of the hierarchical equipment model to generate results displayable to a user for determination of an HE type suitable for a particular well. A method for evaluating HE types and a non-transitory computer-readable medium containing instructions for a processor to perform the method are also disclosed.