公开(公告)号：US20180150743A1

公开(公告)日：2018-05-31

申请号：US15370305

申请日：2016-12-06

Applicant: Xerox Corporation

Inventor： Fenglong Ma ,  Radha Chitta ,  Jing Zhou ,  Palghat S. Ramesh ,  Tong Sun ,  Saurabh Singh Kataria

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/084 ,  G06N3/0445 ,  G06N3/063

Abstract: A long-term memory network method and system for text comprehension. A recurrent neural network can be provided, which includes an external memory module and a long-short term memory unit, wherein said recurrent neural network encodes raw text information into vector representations, forms memories, finds relevant sentences to answer questions, and generates multi-word answers to said questions utilizing the long short term memory unit.

公开(公告)号：US20160203218A1

公开(公告)日：2016-07-14

申请号：US14593593

申请日：2015-01-09

Applicant: Xerox Corporation

Inventor： David R. Vandervort ,  Saurabh Singh Kataria ,  Veerasundaravel Thirugnanasundaram

IPC: G06F17/30

CPC classification number: G06F16/951

Abstract: An apparatus, method and non-transitory computer readable medium for developing a query on a social media service are disclosed. For example, the apparatus includes a processor and a computer readable medium storing a plurality of instructions, which when executed by the processor, cause the processor to perform operations for developing the query on the social media service. The operations include receiving a keyword, providing an option to select a sentiment and an option to include a time frame, finding a plurality of related keywords based on the keyword, the sentiment that is selected and the time frame that is selected using one or more external databases, generating the query using the keyword and all of the plurality of related keywords and the time frame that is selected and applying the query to the social media service.

Abstract translation: 公开了一种用于在社交媒体服务上开发查询的装置，方法和非暂时计算机可读介质。 例如，该设备包括处理器和存储多个指令的计算机可读介质，当由处理器执行该指令时，该处理器和处理器使处理器执行用于在社交媒体服务上开发查询的操作。 这些操作包括接收关键字，提供选择情绪的选项和包括时间框架的选项，基于关键字找到多个相关关键字，所选择的情绪和使用一个或多个选择的时间框架 外部数据库，使用关键字和所有多个相关关键字生成查询，以及选择的时间框架并将该查询应用于社交媒体服务。

公开(公告)号：US10963789B2

公开(公告)日：2021-03-30

申请号：US15370305

申请日：2016-12-06

Applicant: Xerox Corporation

Inventor： Fenglong Ma ,  Radha Chitta ,  Jing Zhou ,  Palghat S. Ramesh ,  Tong Sun ,  Saurabh Singh Kataria

IPC: G06N5/02 ,  G06N5/04 ,  G06F17/27 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: A long-term memory network method and system for text comprehension. A recurrent neural network can be provided, which includes an external memory module and a long-short term memory unit, wherein said recurrent neural network encodes raw text information into vector representations, forms memories, finds relevant sentences to answer questions, and generates multi-word answers to said questions utilizing the long short term memory unit.

公开(公告)号：US10529030B2

公开(公告)日：2020-01-07

申请号：US14593530

申请日：2015-01-09

Applicant: Xerox Corporation

Inventor： Saurabh Singh Kataria ,  Arvind Agarwal

IPC: G06Q50/00 ,  G06Q30/00 ,  G06Q30/02 ,  G06Q10/06 ,  H04L12/58

Abstract: A system, method and non-transitory computer readable medium for labeling a plurality of messages from a customer-agent interaction on a social media service to identify an issue and a response are disclosed. For example, the system includes a conversation interface, a conversation database coupled to the conversation interface, a conversation analysis server coupled to the conversation database and a conversation knowledge repository coupled to the conversation analysis server. The conversation analysis server includes a preprocessing module, a dialogue act analysis module, an issue status analysis module and an issue/response identification module.

公开(公告)号：US20170262587A1

公开(公告)日：2017-09-14

申请号：US15065424

申请日：2016-03-09

Applicant: Xerox Corporation

Inventor： Arvind Agarwal ,  Stuti Awasthi ,  Saurabh Singh Kataria ,  Veerasundaravel Thirugnanasundaram

IPC: G06F19/00 ,  G06Q50/00

CPC classification number: G06F19/325 ,  G06Q50/01 ,  G16H10/60 ,  G16H50/20 ,  G16H50/30

Abstract: A method and non-transitory computer readable medium for generating patient profiles via a social media service are disclosed. For example, the method receives data from the social media service, extracts one or more attributes from the data from the social media service, classifies the one or more attributes to one or more of a plurality of predefined profile attributes, generates a patient profile based on the one or more attributes that are classified, determines a medical action to be executed based on the patient profile and transmits the medical action to be executed to a health administration server.

公开(公告)号：US20160203566A1

公开(公告)日：2016-07-14

申请号：US14593530

申请日：2015-01-09

Applicant: Xerox Corporation

Inventor： Saurabh Singh Kataria ,  Arvind Agarwal

IPC: G06Q50/00 ,  H04L12/58 ,  G06Q30/00 ,  G06Q30/02 ,  G06Q10/06

CPC classification number: G06Q50/01 ,  G06Q10/06398 ,  G06Q30/016 ,  G06Q30/0201 ,  H04L51/02 ,  H04L51/16 ,  H04L51/32

Abstract: A system, method and non-transitory computer readable medium for labeling a plurality of messages from a customer-agent interaction on a social media service to identify an issue and a response are disclosed. For example, the system includes a conversation interface, a conversation database coupled to the conversation interface, a conversation analysis server coupled to the conversation database and a conversation knowledge repository coupled to the conversation analysis server. The conversation analysis server includes a preprocessing module, a dialogue act analysis module, an issue status analysis module and an issue/response identification module.

Abstract translation: 公开了一种用于从社交媒体服务上的客户代理交互标记多个消息以识别问题和响应的系统，方法和非暂时计算机可读介质。 例如，系统包括对话界面，耦合到会话界面的对话数据库，耦合到对话数据库的对话分析服务器和耦合到对话分析服务器的会话知识库。 会话分析服务器包括预处理模块，对话动作分析模块，问题状态分析模块和问题/响应识别模块。