公开(公告)号：US20150058362A1

公开(公告)日：2015-02-26

申请号：US13973271

申请日：2013-08-22

Applicant: XEROX CORPORATION

Inventor： Pallavi Manohar ,  Shourya Roy

IPC: G06F17/30

CPC classification number: G06F17/3071 ,  G06Q50/01 ,  G06Q50/20 ,  G09B7/02 ,  G09B19/00

Abstract: Methods and systems for facilitating evaluation of one or more electronic documents. One or more templates are extracted from the one or more electronic documents. At least one area in the one or more templates is identified. The at least one area includes a response provided by a user associated with the electronic document. One or more groups are generated based on similarity between the responses in the at least one area in the one or more templates. The one or more groups are distributed to one or more remote workers or a crowdsourcing platform for the evaluation.

Abstract translation: 促进评估一个或多个电子文件的方法和系统。 从一个或多个电子文档中提取一个或多个模板。 识别一个或多个模板中的至少一个区域。 所述至少一个区域包括由与电子文档相关联的用户提供的响应。 基于一个或多个模板中的至少一个区域中的响应之间的相似性来生成一个或多个组。 一个或多个组被分发给一个或多个远程工作者或用于评估的众包平台。

公开(公告)号：US10776693B2

公开(公告)日：2020-09-15

申请号：US15420119

申请日：2017-01-31

Applicant: XEROX CORPORATION

Inventor： Ganesh Jawahar ,  Himanshu Sharad Bhatt ,  Manjira Sinha ,  Shourya Roy

IPC: G06N3/08 ,  G06N3/04

Abstract: The disclosed embodiments illustrate a domain adaptation method for learning transferable feature representations from a source domain for a target domain. The method includes receiving input data comprising a plurality of labeled instances of the source domain and a plurality of unlabeled instances of the target domain. The method includes learning common representation shared between the source domain and the target domain, based on the plurality of labeled instances of the source domain. The method includes labeling one or more unlabeled instances in the plurality of unlabeled instances of the target domain, based on the common representation. The method includes determining a target specific representation corresponding to the target domain. The method includes training a target specific classifier based on the target specific representation and the common representation to perform text classification on remaining one or more unlabeled instances of the plurality of unlabeled instances of the target domain.

公开(公告)号：US10089382B2

公开(公告)日：2018-10-02

申请号：US14887096

申请日：2015-10-19

Applicant: Xerox Corporation

Inventor： Akhil Arora ,  Manoj Gupta ,  Shourya Roy

IPC: G06F17/30

Abstract: A method, non-transitory computer readable medium and apparatus for transforming a knowledge base into a machine readable format for an automated system are disclosed. For example, the method includes clustering two or more documents of a plurality of documents in the knowledge base that are similar based upon a domain specific shingling function, identifying a pattern from each document of the plurality of documents that are clustered, wherein the pattern comprises a sequence of steps, aggregating the pattern of the each document of the plurality of documents that are clustered into a trie data-structure that is machine readable, receiving a request and applying the trie data-structure to provide a solution to the request.

公开(公告)号：US09652445B2

公开(公告)日：2017-05-16

申请号：US13904319

申请日：2013-05-29

Applicant: Xerox Corporation

Inventor： Chithralekha Balamurugan ,  Shourya Roy ,  Sujit Gujar

IPC: G06F17/24

CPC classification number: G06F17/243

Abstract: The disclosed embodiments illustrate methods and systems for creating one or more tasks of digitizing an electronic document. The electronic document comprises one or more fields. The method comprising receiving inputs to define one or more characteristics associated with each of the one or more fields. The one or more fields are categorized in one or more groups based on the one or more characteristics. Additionally, a task is created for each of the one or more categorized fields based on the one or more characteristics associated with each of the one or more categorized fields, wherein the task comprises at least a user interface for facilitating at least one remote worker to input a response for the task.

公开(公告)号：US20170109426A1

公开(公告)日：2017-04-20

申请号：US14887096

申请日：2015-10-19

Applicant: Xerox Corporation

Inventor： Akhil Arora ,  Manoj Gupta ,  Shourya Roy

IPC: G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/30011 ,  G06F17/30327 ,  G06F17/3053

Abstract: A method, non-transitory computer readable medium and apparatus for transforming a knowledge base into a machine readable format for an automated system are disclosed. For example, the method includes clustering two or more documents of a plurality of documents in the knowledge base that are similar based upon a domain specific shingling function, identifying a pattern from each document of the plurality of documents that are clustered, wherein the pattern comprises a sequence of steps, aggregating the pattern of the each document of the plurality of documents that are clustered into a trie data-structure that is machine readable, receiving a request and applying the trie data-structure to provide a solution to the request.

公开(公告)号：US20160300034A1

公开(公告)日：2016-10-13

申请号：US14632117

申请日：2015-02-26

Applicant: XEROX CORPORATION

Inventor： Vijay Huddar ,  Vaibhav Rajan ,  Sakyajit Bhattacharya ,  Shourya Roy

IPC: G06F19/00

CPC classification number: G16H50/30 ,  G16H10/60

Abstract: According to embodiments illustrated herein, there is provided a system for predicting a health condition of a first patient. The system includes a document processor configured to extract one or more headings from one or more medical records of the first patient based on one or more predefined rules. The document processor is further configured to extract one or more words from one or more phrases written under each of the extracted one or more headings, wherein the one or more phrases correspond to documentation of the observation of the first patient by a medical attender. The system further includes one or more processors configured to predict the health condition of the first patient based on a count of the one or more words in historical medical records and the one or more medical records.

Abstract translation: 根据本文所示的实施例，提供了一种用于预测第一患者的健康状况的系统。 该系统包括被配置为基于一个或多个预定规则从第一患者的一个或多个医疗记录提取一个或多个标题的文档处理器。 文档处理器还被配置为从在所提取的一个或多个标题中的每一个标题下写入的一个或多个短语中提取一个或多个单词，其中所述一个或多个短语对应于由医疗人员观察第一患者的文档。 该系统还包括一个或多个处理器，其被配置为基于历史医疗记录中的一个或多个单词的计数和一个或多个医疗记录来预测第一患者的健康状况。

公开(公告)号：US09396255B2

公开(公告)日：2016-07-19

申请号：US13973271

申请日：2013-08-22

Applicant: Xerox Corporation

Inventor： Pallavi Manohar ,  Shourya Roy

IPC: G06F17/00 ,  G06F17/30 ,  G06Q50/00 ,  G09B19/00 ,  G09B7/02

CPC classification number: G06F17/3071 ,  G06Q50/01 ,  G06Q50/20 ,  G09B7/02 ,  G09B19/00

Abstract: Methods and systems for facilitating evaluation of one or more electronic documents. One or more templates are extracted from the one or more electronic documents. At least one area in the one or more templates is identified. The at least one area includes a response provided by a user associated with the electronic document. One or more groups are generated based on similarity between the responses in the at least one area in the one or more templates. The one or more groups are distributed to one or more remote workers or a crowdsourcing platform for the evaluation.

Abstract translation: 促进评估一个或多个电子文件的方法和系统。 从一个或多个电子文档中提取一个或多个模板。 识别一个或多个模板中的至少一个区域。 所述至少一个区域包括由与电子文档相关联的用户提供的响应。 基于一个或多个模板中的至少一个区域中的响应之间的相似性来生成一个或多个组。 一个或多个组被分发给一个或多个远程工作者或用于评估的众包平台。

公开(公告)号：US20150154529A1

公开(公告)日：2015-06-04

申请号：US14094820

申请日：2013-12-03

Applicant: Xerox Corporation

Inventor： Preethi Raj Raajaratnam ,  Shourya Roy

IPC: G06Q10/06 ,  G06Q10/10

CPC classification number: G06Q10/063114 ,  G06Q10/1097

Abstract: Methods and systems for creating a task are provided. A request from a worker is received to perform the task. A task is created in response to the request. The task comprises at least one new sub-task and at least one additional sub-task, wherein the at least one additional sub-task is selected from a set of unfinished sub-tasks associated with one or more previously attempted tasks. The task is communicated to the worker. The worker may receive a bonus remuneration for correctly attempting the at least one additional sub-task.

Abstract translation: 提供了创建任务的方法和系统。 接收到来自工作者的请求来执行该任务。 响应请求创建任务。 该任务包括至少一个新的子任务和至少一个附加子任务，其中从与一个或多个先前尝试的任务相关联的一组未完成的子任务中选择所述至少一个附加子任务。 工作通知工作人员。 工作人员可以收到正确尝试至少一个附加子任务的奖励报酬。

公开(公告)号：US20140359418A1

公开(公告)日：2014-12-04

申请号：US13904319

申请日：2013-05-29

Applicant: Xerox Corporation

Inventor： Chithralekha Balamurugan ,  Shourya Roy ,  Sujit Gujar

IPC: G06F17/24

CPC classification number: G06F17/243

Abstract: The disclosed embodiments illustrate methods and systems for creating one or more tasks of digitizing an electronic document. The electronic document comprises one or more fields. The method comprising receiving inputs to define one or more characteristics associated with each of the one or more fields. The one or more fields are categorized in one or more groups based on the one or more characteristics. Additionally, a task is created for each of the one or more categorized fields based on the one or more characteristics associated with each of the one or more categorized fields, wherein the task comprises at least a user interface for facilitating at least one remote worker to input a response for the task.

Abstract translation: 所公开的实施例示出了用于创建数字化电子文档的一个或多个任务的方法和系统。 电子文档包括一个或多个字段。 所述方法包括接收输入以定义与所述一个或多个场中的每一个相关联的一个或多个特征。 一个或多个字段基于一个或多个特征被分类在一个或多个组中。 另外，基于与一个或多个分类字段中的每一个相关联的一个或多个特征，为一个或多个分类字段中的每一个创建任务，其中该任务包括至少一个用户界面，用于促使至少一个远程工作者 输入任务的响应。

公开(公告)号：US20140358605A1

公开(公告)日：2014-12-04

申请号：US13909181

申请日：2013-06-04

Applicant: XEROX CORPORATION

Inventor： Chithralekha Balamurugan ,  Sujit Gujar ,  Shourya Roy

IPC: G06Q10/06

CPC classification number: G06Q10/06311

Abstract: The disclosed embodiments illustrate methods and systems for crowdsourcing a task. The method comprises presenting the task to one or more crowdworkers based on their reputation scores and a redundancy degree associated with the task. The task comprises one or more sub-tasks. A plurality of responses to the task are received from the one or more crowdworkers. Each response further comprises one or more sub-responses each of which in turn corresponds to a response for a sub-task of the one or more sub-tasks. A first set of sub-tasks is identified from the one or more sub-tasks based on a first set of similar sub-responses received for the first set of sub-tasks from the plurality of responses. A first set of crowdworkers from the one or more crowdworkers who provided the first set of similar sub-responses for the first set of sub-tasks are remunerated.

Abstract translation: 所公开的实施例示出了使任务众包的方法和系统。 该方法包括基于其信誉分数和与该任务相关联的冗余程度将任务呈现给一个或多个群众工作者。 该任务包括一个或多个子任务。 从一个或多个人群中接收到对该任务的多个响应。 每个响应还包括一个或多个子响应，每个子响应又分别对应于一个或多个子任务的子任务的响应。 基于从多个响应中为第一组子任务接收的第一组相似子响应，从一个或多个子任务中识别第一组子任务。 来自一个或多个群众工作者的第一组人群工作者为第一组子任务提供了第一组相似的子回应，是有报酬的。