公开(公告)号：US09208535B2

公开(公告)日：2015-12-08

申请号：US14089307

申请日：2013-11-25

Applicant: Xerox Corporation

Inventor： Changjun Wu ,  Tong Sun

IPC: G06T11/20 ,  G06T1/20 ,  G09G5/22

CPC classification number: G06T1/20 ,  G06T1/60 ,  G06T11/20 ,  G06T11/203 ,  G06T11/206 ,  G06T2210/32

Abstract: A method, non-transitory computer readable medium, and apparatus for large-scale web community detection using a graphical processing unit (GPU) are disclosed. For example, the method receives an input graph formatted into one or more first adjacency lists from a central processing unit (CPU), performs a first level shingling on the one or more first adjacency lists, sends the first level shingling to the CPU to generate an aggregate graph based upon the first level shingling, receives the aggregate graph formatted into one or more second adjacency lists from the CPU, performs a second level shingling on the one or more second adjacency lists and sends the second level shingling to the CPU to generate a dense sub-graph that identifies one or more web communities.

Abstract translation: 公开了一种使用图形处理单元（GPU）进行大规模网络社区检测的方法，非暂时计算机可读介质和装置。 例如，该方法从中央处理单元（CPU）接收格式化成一个或多个第一相邻列表的输入图，对该一个或多个第一邻接列表执行第一级着色，向CPU发送第一级着色，以产生 基于第一级着色的聚合图形从CPU接收格式化成一个或多个第二邻接列表的聚合图形，在一个或多个第二邻接列表上执行第二级别着色，并将第二级别着色发送到CPU以产生 识别一个或多个Web社区的密集子图。

公开(公告)号：US20140310053A1

公开(公告)日：2014-10-16

申请号：US13859951

申请日：2013-04-10

Applicant: XEROX CORPORATION

Inventor： Hua Liu ,  Changjun Wu ,  Frank Goetz ,  Arun Bakthavachalu ,  Selvakumar Periasamy

IPC: G06Q10/06

CPC classification number: G06Q10/0633

Abstract: A system and method for providing a real-time business process suggestion and recommendation utilizing a business process modeler. A dynamic input from a business analyst can be incorporated utilizing a real-time suggestion engine. A real-time search can be performed by organizing a number of business processes in a tree structure where each leaf node represents a business process and each branch node represents a set of components that are shared by the business processes in a sub tree. A semantic execution path search can be performed to provide a real-time match between the partial business process and a catalogue of existing business processes by determining a constituent component and a score based on a reachability rule. The edges and/or components can be added and/or deleted to effectively organize the existing business processes based on previous suggestion to speed up a future suggestion.

Abstract translation: 一种使用业务流程建模者提供实时业务流程建议和建议的系统和方法。 可以使用实时建议引擎来整合来自业务分析师的动态输入。 可以通过在树结构中组织多个业务流程来执行实时搜索，其中每个叶节点表示业务流程，并且每个分支节点表示由子树中的业务流程共享的一组组件。 可以执行语义执行路径搜索，以通过基于可达性规则确定构成组件和分数来提供部分业务流程和现有业务流程的目录之间的实时匹配。 可以添加和/或删除边缘和/或组件，以便根据先前的建议有效地组织现有的业务流程，以加速未来的建议。

公开(公告)号：US20140297662A1

公开(公告)日：2014-10-02

申请号：US13855477

申请日：2013-04-02

Applicant: XEROX CORPORATION

Inventor： Changjun Wu ,  Hua Liu

IPC: G06F17/30

CPC classification number: G06F17/30424

Abstract: The present invention generally relates to systems and methods for identifying a workflow, from a set of workflows, that best match a given query partial workflow. In addition to identifying the best match, the systems and methods can identify the portion of the workflow that best matches the query partial workflow.

Abstract translation: 本发明一般涉及用于从一组工作流中识别与给定查询部分工作流最匹配的工作流的系统和方法。 除了识别最佳匹配之外，系统和方法还可以识别最符合查询部分工作流程的工作流部分。

公开(公告)号：US09235616B2

公开(公告)日：2016-01-12

申请号：US13855477

申请日：2013-04-02

Applicant: XEROX CORPORATION

Inventor： Changjun Wu ,  Hua Liu

IPC: G06F17/30

CPC classification number: G06F17/30424

Abstract: The present invention generally relates to systems and methods for identifying a workflow, from a set of workflows, that best match a given query partial workflow. In addition to identifying the best match, the systems and methods can identify the portion of the workflow that best matches the query partial workflow.

Abstract translation: 本发明一般涉及用于从一组工作流中识别与给定查询部分工作流最匹配的工作流的系统和方法。 除了识别最佳匹配之外，系统和方法还可以识别最符合查询部分工作流程的工作流部分。

公开(公告)号：US20140129285A1

公开(公告)日：2014-05-08

申请号：US13670733

申请日：2012-11-07

Applicant: XEROX CORPORATION

Inventor： Changjun Wu ,  Hua Liu

IPC: G06Q10/06

CPC classification number: G06Q10/0633

Abstract: The present invention generally relates to systems and methods for comparing workflows. More particularly, the invention relates to thinning a number of workflow pairs to compare, prior to conducting a detailed comparison among pairs of workflows. The invention can be used to generate a workflow similarity graph based on a large set of workflows.

Abstract translation: 本发明一般涉及用于比较工作流的系统和方法。 更具体地，本发明涉及在进行工作流对之间的详细比较之前，稀疏多个工作流对以进行比较。 本发明可以用于基于大量工作流来生成工作流相似度图。

公开(公告)号：US20140304027A1

公开(公告)日：2014-10-09

申请号：US13857648

申请日：2013-04-05

Applicant: XEROX CORPORATION

Inventor： Changjun Wu ,  Hua Liu ,  Frank Goetz ,  Arun Bakthavachalu

IPC: G06Q10/06

CPC classification number: G06Q10/0633

Abstract: A system and method for generating and searching workflow cluster profiles by generating a workflow similarity graph based on multiple workflows, generating a set of workflow clusters based on the workflow similarity graph, generating workflow cluster profiles for the set of workflow clusters, receiving a querying workflow, and comparing the querying workflow to the workflow cluster profiles.

Abstract translation: 一种用于通过基于多个工作流生成工作流相似度图来生成和搜索工作流集群简档的系统和方法，基于所述工作流相似度图生成一组工作流集群，为所述一组工作流集群生成工作流集群简档，接收查询工作流 ，并将查询工作流与工作流集群配置文件进行比较。

公开(公告)号：US20150145866A1

公开(公告)日：2015-05-28

申请号：US14089307

申请日：2013-11-25

Applicant: Xerox Corporation

Inventor： Changjun Wu ,  Tong Sun

IPC: G06T1/20 ,  G06T11/20

CPC classification number: G06T1/20 ,  G06T1/60 ,  G06T11/20 ,  G06T11/203 ,  G06T11/206 ,  G06T2210/32

Abstract: A method, non-transitory computer readable medium, and apparatus for large-scale web community detection using a graphical processing unit (GPU) are disclosed. For example, the method receives an input graph formatted into one or more first adjacency lists from a central processing unit (CPU), performs a first level shingling on the one or more first adjacency lists, sends the first level shingling to the CPU to generate an aggregate graph based upon the first level shingling, receives the aggregate graph formatted into one or more second adjacency lists from the CPU, performs a second level shingling on the one or more second adjacency lists and sends the second level shingling to the CPU to generate a dense sub-graph that identifies one or more web communities.

Abstract translation: 公开了一种使用图形处理单元（GPU）进行大规模网络社区检测的方法，非暂时计算机可读介质和装置。 例如，该方法从中央处理单元（CPU）接收格式化成一个或多个第一相邻列表的输入图，对该一个或多个第一邻接列表执行第一级着色，向CPU发送第一级着色，以产生 基于第一级着色的聚合图形从CPU接收格式化成一个或多个第二邻接列表的聚合图形，在一个或多个第二邻接列表上执行第二级别着色，并将第二级别着色发送到CPU以产生 识别一个或多个Web社区的密集子图。