公开(公告)号：US20160162474A1

公开(公告)日：2016-06-09

申请号：US14564170

申请日：2014-12-09

Applicant: XEROX CORPORATION

Inventor： Arvind Agarwal ,  Saurabh Kataria ,  Tong Sun ,  Sumit Bhatia

IPC: G06F17/28 ,  G06F17/27

CPC classification number: G06F17/274 ,  G06F17/2765 ,  G06F17/2775 ,  G06F17/279 ,  G06F19/24 ,  G06N99/005 ,  G06Q30/00 ,  G06Q50/01 ,  G10L15/06

Abstract: The technical solution under the present disclosure automatically analyzes conversations between users by receiving a training dataset having a text sequence including sentences of a conversation between the users; extracting feature(s) from the training dataset based on features; providing equation(s) for a plurality of tasks, the equation(s) being a mathematical function for calculating value of a parameter for each of the tasks based on the extracted feature; determining value of the parameter for tasks by processing the equation(s); assigning label(s) to each of the sentences based on the determined value of the parameter, a first label being selected from a plurality of first labels, and a second label being selected from a number of second labels; and storing and maintaining with the database a pre-defined value of the parameter, first labels, conversations, second labels, a test dataset, equation(s), and pre-defined features.

Abstract translation: 本公开的技术方案通过接收具有包括用户之间的会话的句子的文本序列的训练数据集来自动分析用户之间的对话; 基于特征从训练数据集中提取特征; 提供多个任务的等式，所述方程式是用于基于所提取的特征来计算每个任务的参数的值的数学函数; 通过处理方程确定任务参数的值; 基于所确定的参数值，从多个第一标签中选择第一标签和从多个第二标签中选择的第二标签，将标签分配给每个句子; 并且使用数据库存储和维护参数的预定义值，第一标签，对话，第二标签，测试数据集，等式和预定义的特征。

公开(公告)号：US09213730B2

公开(公告)日：2015-12-15

申请号：US13965924

申请日：2013-08-13

Applicant: Xerox Corporation

Inventor： Sumit Bhatia ,  Saurabh Kataria ,  Wei Peng ,  Tong Sun

IPC: G06F17/30

CPC classification number: G06F17/30336 ,  G06F17/3053 ,  G06F17/30616 ,  G06F17/30663

Abstract: A method, non-transitory computer readable medium, and apparatus for extracting text from a social media document are disclosed. For example, the method indexes a plurality of social media documents into a plurality of snippets, receives a query including one or more keywords and a purpose, identifies one or more of the plurality of snippets that include the one or more keywords in an index, ranks the one or more of the plurality of snippets in accordance with the purpose and provides the one or more plurality of snippets that are ranked in accordance with the purpose.

Abstract translation: 公开了一种用于从社交媒体文档中提取文本的方法，非暂时计算机可读介质和装置。 例如，该方法将多个社交媒体文档索引到多个片段中，接收包括一个或多个关键字和目的的查询，识别包括索引中的一个或多个关键字的多个片段中的一个或多个片段， 根据目的对多个片段中的一个或多个片段进行排序，并提供根据目的排列的一个或多个片段。

公开(公告)号：US20150052120A1

公开(公告)日：2015-02-19

申请号：US13965924

申请日：2013-08-13

Applicant: Xerox Corporation

Inventor： SUMIT BHATIA ,  Saurabh Kataria ,  Wei Peng ,  Tong Sun

IPC: G06F17/30

CPC classification number: G06F17/30336 ,  G06F17/3053 ,  G06F17/30616 ,  G06F17/30663

Abstract: A method, non-transitory computer readable medium, and apparatus for extracting text from a social media document are disclosed. For example, the method indexes a plurality of social media documents into a plurality of snippets, receives a query including one or more keywords and a purpose, identifies one or more of the plurality of snippets that include the one or more keywords in an index, ranks the one or more of the plurality of snippets in accordance with the purpose and provides the one or more plurality of snippets that are ranked in accordance with the purpose.

Abstract translation: 公开了一种用于从社交媒体文档中提取文本的方法，非暂时计算机可读介质和装置。 例如，该方法将多个社交媒体文档索引到多个片段中，接收包括一个或多个关键字和目的的查询，识别包括索引中的一个或多个关键字的多个片段中的一个或多个片段， 根据目的对多个片段中的一个或多个片段进行排序，并提供根据目的排列的一个或多个片段。

公开(公告)号：US10853820B2

公开(公告)日：2020-12-01

申请号：US13836233

申请日：2013-03-15

Applicant: Xerox Corporation

Inventor： Lei Li ,  Wei Peng ,  Saurabh Kataria ,  Tong Sun

IPC: G06Q50/00 ,  G06Q30/00

Abstract: A method, non-transitory computer readable medium, and apparatus for recommending a topic-cohesive and interactive implicit community are disclosed. For example, the method receives a request for customer care, selects an implicit community identified from a plurality of individual users of a social media website based upon a relevance score related to a topic of the request for customer care and recommends the implicit community in response to the request for customer care.

公开(公告)号：US09785891B2

公开(公告)日：2017-10-10

申请号：US14564138

申请日：2014-12-09

Applicant: XEROX CORPORATION

Inventor： Arvind Agarwal ,  Saurabh Kataria

IPC: G06N99/00 ,  G06Q30/00

CPC classification number: G06N99/005 ,  G06Q30/016

Abstract: Embodiments of a computer-implemented method for automatically analyzing a conversational sequence between multiple users are disclosed. The method includes receiving signals corresponding to a training dataset including multiple conversational sequences; extracting a feature from the training dataset based on predefined feature categories; formulating multiple tasks for being learned from the training dataset based on the extracted feature, each task related to a predefined label; and providing a model for each formulated task, the model including a set of parameters common to the tasks. The set includes an explicit parameter, which is explicitly shared with each of the formulated tasks. The method further includes optimizing a value of the explicit parameter to create an optimized model; creating a trained model for the formulated tasks using the optimized value of the explicit parameter; and assigning predefined labels for the formulated tasks to a live dataset based on the corresponding trained model.

公开(公告)号：US09324038B2

公开(公告)日：2016-04-26

申请号：US14081203

申请日：2013-11-15

Applicant: Xerox Corporation

Inventor： Yasmine Charif ,  Julien Jean Lucien Bourdaillet ,  David Russell Vandervort ,  Michael P. Kehoe ,  Saurabh Kataria

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: A process discovery system that includes an offline system training module configured to cluster similar process log traces using Non-negative Matrix Factorization (NMF) with each cluster representing a process model, and learn a Conditional Random Field (CRF) model for each process model and an online system usage module configured to decode new incoming log traces and construct a process graph in which transitions are shown or hidden according to a tuning parameter.

Abstract translation: 一种过程发现系统，其包括离线系统训练模块，其被配置为使用非负矩阵因子分解（NMF）来聚类相似的过程日志跟踪，每个群表示过程模型，并且为每个过程模型学习条件随机场（CRF）模型， 在线系统使用模块被配置为解码新的传入日志跟踪并构造根据调谐参数显示或隐藏转移的过程图。

公开(公告)号：US20140279627A1

公开(公告)日：2014-09-18

申请号：US13803951

申请日：2013-03-14

Applicant: XEROX CORPORATION

Inventor： Dhanwant S. Kang ,  Hua Liu ,  Tong Sun ,  Saurabh Kataria

IPC: G06Q10/10

CPC classification number: G06Q10/105

Abstract: A method, system, and computer program product for determining skills of an employee is disclosed. The method includes determining a first likelihood of at least one keyword from a plurality of keywords being relevant to a topic. The plurality of keywords is extractable from one or more publications associated with the employee, the one or more publications being accessible from a plurality of sources. The method further includes determining a second likelihood of the employee being associated with the topic for at least one source from the plurality of sources. A first set of keywords from the plurality of keywords is assigned to the employee based on the first likelihood and the second likelihood. The first set of keywords is indicative of the skills of the employee.

Abstract translation: 公开了一种用于确定员工技能的方法，系统和计算机程序产品。 该方法包括从与主题相关的多个关键字中确定至少一个关键字的第一可能性。 所述多个关键字可从与雇员相关联的一个或多个出版物中提取，所述一个或多个出版物可从多个来源访问。 所述方法还包括确定所述员工与所述主题相关联的第二可能性，用于来自所述多个源的至少一个源。 基于第一可能性和第二似然性，将多个关键词的第一组关键字分配给雇员。 第一组关键字表示员工的技能。