公开(公告)号：US10062222B2

公开(公告)日：2018-08-28

申请号：US14949614

申请日：2015-11-23

Applicant: GM Global Technology Operations LLC

Inventor： Dnyanesh G. Rajpathak ,  Soumen De

IPC: G06F17/27 ,  G07C5/08 ,  G06N99/00 ,  G06F17/30 ,  G07C5/00

CPC classification number: G06F17/2735 ,  G06F16/285 ,  G06F17/277 ,  G06N5/022 ,  G06N7/005 ,  G06N20/00 ,  G07C5/00 ,  G07C5/006 ,  G07C5/0808

Abstract: A system and method of analyzing content of multilingual vehicle diagnostic records includes: determining a word window within a vehicle diagnostic record; identifying a pair or a tuple comprising parts, symptoms, or actions; generating a plurality of pairs or tuples comprising parts, symptoms, or actions; determining a frequency value for each pair or tuple; and comparing the determined frequency value with a predetermined threshold.

公开(公告)号：US09342489B2

公开(公告)日：2016-05-17

申请号：US14243972

申请日：2014-04-03

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Ramesh Sethu ,  Prakash M. Peranandam ,  Dnyanesh Rajpathak ,  Soumen De

IPC: G06F17/22 ,  G06F17/27

CPC classification number: G06F17/2211 ,  G06F17/277 ,  G06F17/2775 ,  G06F17/2785

Abstract: A method of automatic identifying linking relationships of requirements in a plurality of requirement documents. Terms in the plurality of requirement documents are identified. A part-of-speech tag is assigned to each term. Each identified term is selected as a focal term. Co-occurring terms within a predetermined distance of the selected focal term are determined. A linking relationship probability is calculated for each co-occurring term associated with the selected focal term. The selected focal terms and associated co-occurring terms between the plurality of requirement documents are compared. A degree of linking relationship is identified between two requirements as a function of a comparison between selected focal terms and the associated co-occurring terms between the plurality of requirement documents. An analysis report identifying the degree of linking relationships between two respective requirements is output.

Abstract translation: 一种在多个要求文件中自动识别需求的链接关系的方法。 识别多个要求文件中的术语。 词性标签被分配给每个术语。 每个确定的术语被选为重点术语。 确定所选焦点项的预定距离内的共出现项。 针对与所选焦点项相关联的每个共同出现项计算链接关系概率。 比较多个要求文件之间的选定的焦点项和相关联的共同词。 在两个要求之间确定了一定程度的链接关系，作为所选择的焦点项与多个要求文档之间的相关联的发生项之间的比较的函数。 输出一个分析报告，确定两个相关需求之间的链接关系程度。

公开(公告)号：US20140258304A1

公开(公告)日：2014-09-11

申请号：US13792913

申请日：2013-03-11

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Gregory D. Sabanski ,  Martin Case ,  Soumen De ,  Dnyanesh Rajpathak

IPC: G06F17/30

CPC classification number: G06F16/904

Abstract: A warranty database stores service repair verbatims. An ontology database that specifies relationships between service terms includes linking relationships between vehicle terminology and cluster categories. The ontology database is reconfigurable for allowing a user to add, delete, and modify contents within the ontology database. A verbatim extraction tool extracts service repair verbatims from the warranty database as function of user selected parameters and a user selected ontology. The user selected ontology is a subset of the ontology database. The service verbatims are segregated into a plurality of cluster categories as a function of the selected parameters and the user selected ontology. A report generating device selectively generated reports based on segregating service verbatims into a plurality of cluster categories. Each respective cluster category includes associated service repair verbatims that are selected as a function of the linking relationship of terms within the service verbatim and the user selected ontology.

Abstract translation: 保修数据库将服务维修逐字记录。 指定服务术语之间的关系的本体数据库包括链接车辆术语和集群类别之间的关系。 本体数据库是可重构的，用于允许用户添加，删除和修改本体数据库内的内容。 逐字提取工具根据用户选择的参数和用户选择的本体的功能，从保修数据库中逐字提取服务修复。 用户选择的本体是本体数据库的一个子集。 根据所选择的参数和用户选择的本体，将服务逐字节分隔为多个集群类别。 报告生成装置基于将服务逐字分类为多个集群类别来选择性地生成报告。 每个相应的集群类别包括根据服务逐字逐句和用户选择的本体中的术语的链接关系来选择的相关联的服务修复逐字节。

公开(公告)号：US09317596B2

公开(公告)日：2016-04-19

申请号：US14551723

申请日：2014-11-24

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Joseph A. Donndelinger ,  John A. Cafeo ,  Soumen De ,  Dnyanesh Rajpathak ,  Prakash M. Peranandam ,  Kay L. Darden

IPC: G06F17/30

CPC classification number: G06F17/30734 ,  G06F17/30336 ,  G06F17/30604 ,  G06F2201/80 ,  G06Q10/06 ,  G06Q10/10

Abstract: A method of automatically developing an ontology for product function and failure mode documentation for an apparatus. The apparatus is identified. A function-flow model is generated for the identified apparatus for identifying a composite structure of the apparatus. Functions and failure modes associated with the identified apparatus are enumerated. Failure data is obtained from a plurality of heterogeneous data sources. A semantic similarity module is applied to the enumerated failures by comparing a plurality of documents between the data sources. The semantic similarity module bridges a variety of terms used in the heterogeneous data to describe a respective failure. Failures associated with the enumerated apparatus functions are extracted from the plurality of documents between heterogeneous data sources. A composite of related terminology is generated for each identified failure mode. A failure mode information document is generated utilizing the composite of related terminology for each identified failure mode.

Abstract translation: 自动开发用于设备的产品功能和故障模式文档的本体的方法。 识别设备。 生成用于识别装置的复合结构的识别装置的功能流模型。 列举了与识别的设备相关联的功能和故障模式。 从多个异构数据源获得故障数据。 通过比较数据源之间的多个文档，将语义相似性模块应用于枚举的故障。 语义相似性模块桥接异构数据中使用的各种术语来描述相应的故障。 在异构数据源之间从多个文档中提取与枚举装置功能相关联的故障。 针对每个识别的故障模式生成相关术语的复合物。 使用每个识别的故障模式的相关术语的复合来生成故障模式信息文档。

公开(公告)号：US10325021B2

公开(公告)日：2019-06-18

申请号：US15627380

申请日：2017-06-19

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Prakash Mohan Peranandam ,  Soumen De

IPC: G06F17/30 ,  G06F17/27

Abstract: A system and method for extracting a relevant phrase from text. The system and method may build a plurality of n-gram phrases using a seed from a seed list as a start, a middle, or an end of each n-gram phrase. The seed list may be directed to a specific vehicle system and each seed may indicate a symptom, part, or action to extract relevant phrases from vehicle information verbatims. The plurality of n-gram phrases may be filtered to obtain one or more relevant phrases. The filtering process may include calculating an external relevance factor, an internal relevance factor, or a context pattern relevance factor.

公开(公告)号：US20180365222A1

公开(公告)日：2018-12-20

申请号：US15627380

申请日：2017-06-19

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Prakash Mohan Peranandam ,  Soumen De

IPC: G06F17/27

CPC classification number: G06F17/2785 ,  G06F17/274 ,  G06F17/277 ,  G06F17/2795

Abstract: A system and method for extracting a relevant phrase from text. The system and method may build a plurality of n-gram phrases using a seed from a seed list as a start, a middle, or an end of each n-gram phrase. The seed list may be directed to a specific vehicle system and each seed may indicate a symptom, part, or action to extract relevant phrases from vehicle information verbatims. The plurality of n-gram phrases may be filtered to obtain one or more relevant phrases. The filtering process may include calculating an external relevance factor, an internal relevance factor, or a context pattern relevance factor.