公开(公告)号：US20170046338A1

公开(公告)日：2017-02-16

申请号：US15211340

申请日：2016-07-15

Applicant: Thomson Reuters Global Resources

Inventor： Frank Schilder ,  Blake Howald ,  Ravi Kondadadi

IPC: G06F17/28 ,  G06F17/21 ,  G06F17/27

CPC classification number: G06F17/2881 ,  G06F17/218 ,  G06F17/2785

Abstract: A method includes receiving a corpus comprising a set of pre-segmented texts. The method further includes creating a plurality of modified pre-segmented texts for the set of pre-segmented texts by extracting a set of semantic terms for each pre-segmented text within the set of pre-segmented texts and applying at least one domain tag for each pre-segmented text within the set of pre-segmented texts. The method further includes clustering the plurality of modified pre-segmented texts into one or more conceptual units, wherein each of the one or more conceptual units is associated with one or more templates, wherein each of the one or more templates corresponds to one of the plurality of modified pre-segmented texts.

Abstract translation: 一种方法包括接收包含一组预分段文本的语料库。 所述方法还包括通过针对所述一组预分段文本中的每个预分割文本提取一组语义项来为所述一组预分段文本创建多个经修改的预分割文本，并将至少一个域标签应用于 预分段文本集中的每个预分割文本。 该方法还包括将多个经修改的预分割文本聚类成一个或多个概念单元，其中所述一个或多个概念单元中的每一个与一个或多个模板相关联，其中所述一个或多个模板中的每一个对应于 多个修改的预分段文本。

公开(公告)号：US20170046336A1

公开(公告)日：2017-02-16

申请号：US14821787

申请日：2015-08-10

Applicant: International Business Machines Corporation

Inventor： Samuel R. Connor ,  Jonathan W. Jackson ,  Joseph Kuczynski

IPC: G06F17/28

CPC classification number: G06F17/2809 ,  G06F17/274 ,  G06F17/2785 ,  G06F17/2881

Abstract: Disclosed aspects include initiating an electronic communication configured to be transmitted to a first intended recipient. Based on a set of profile data, a first cultural indicator may be identified for the first intended recipient. Using a natural language processing technique, a cultural element of the electronic communication may be detected. Based on both the first cultural indicator and the cultural element, a first cultural-version of the cultural element may be determined for the first intended recipient. Using the first cultural-version, a cultural translation object may be established in the electronic communication. In response to establishing the cultural translation object in the electronic communication, the electronic communication may be transmitted to the first intended recipient.

公开(公告)号：US20170039193A1

公开(公告)日：2017-02-09

申请号：US15195183

申请日：2016-06-28

Applicant: International Business Machines Corporation

Inventor： Joy Mustafi ,  Krishma Singla

IPC: G06F17/28 ,  G06K9/18 ,  G06F17/30

CPC classification number: G06F17/2881 ,  G06F17/30654 ,  G06K9/00476

Abstract: A computer-implemented method for language generation of a flow diagram, which receives a flow diagram. A plurality of geometric shapes within the flow diagram is identified. A plurality of text elements within the flow diagram is identified. The plurality of text elements and corresponding geometric shapes are associated. The association between the plurality of geometric shapes are identified. A diagram matrix based on the associations between the plurality of geometric shapes is generated. A linear language representation of the diagram matrix is generated.

Abstract translation: 用于语言生成流程图的计算机实现的方法，其接收流程图。 识别流程图内的多个几何形状。 识别流程图中的多个文本元素。 多个文本元素和对应的几何形状相关联。 识别多个几何形状之间的关联。 产生基于多个几何形状之间的关联的图表矩阵。 生成图矩阵的线性语言表示。

公开(公告)号：US20160357731A1

公开(公告)日：2016-12-08

申请号：US15114607

申请日：2014-07-29

Applicant: Somol Zorzin GmbH

Inventor： Luciano Zorzin

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/2785 ,  G06F17/273 ,  G06F17/2755 ,  G06F17/2881

Abstract: The invention relates to a method for automatically detecting meaning patterns in a text using a plurality of input words, in particular a text with at least one sentence, comprising a database system containing words of a language, a plurality of defined categories of meaning in order to describe the properties of the words, and meaning signals for all the words stored in the database, wherein a meaning signal is a clear numerical characterization of the meaning of the words using the categories of meaning.

Abstract translation: 本发明涉及一种用于使用多个输入单词，特别是具有至少一个句子的文本来自动检测文本中的含义模式的方法，包括包含语言的单词，多个定义的含义类别的数据库系统 描述单词的属性，并且意味着存储在数据库中的所有单词的信号，其中意义信号是使用意义类别的单词的含义的清楚的数字表征。

公开(公告)号：US20160352657A1

公开(公告)日：2016-12-01

申请号：US14726569

申请日：2015-05-31

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Michel GALLEY ,  Alessandro SORDONI ,  Christopher John BROCKETT ,  Jianfeng GAO, III ,  William Brennan DOLAN ,  Yangfeng JI ,  Michael AULI ,  Margaret Ann MITCHELL ,  Christopher Brian QUIRK

IPC: H04L12/58

CPC classification number: H04L51/02 ,  G06F17/2881 ,  H04L51/10 ,  H04L51/26

Abstract: Examples are generally directed towards automatic assessment of machine generated conversational responses. Context-message-response n-tuples are extracted from at least one source of conversational data to generate a set of multi-reference responses. A response in the set of multi-reference responses includes it context-message data pair and rating. The rating indicates a quality of the response relative to the context-message data pair. A response assessment engine generates a metric score for a machine-generated response based on an assessment metric and the set of multi-reference responses. The metric score indicates a quality of the machine-generated conversational response relative to a user-generated message and a context of the user-generated message. A response generation system of a computing device, such as a digital assistant, is optimized and adjusted based on the metric score to improve the accuracy, quality, and relevance of responses output to the user.

Abstract translation: 实例通常针对机器生成的会话响应的自动评估。 从至少一个会话数据源提取上下文消息响应n元组，以生成一组多参考响应。 多参考响应集中的响应包括上下文消息数据对和评级。 该等级表示相对于上下文消息数据对的响应的质量。 响应评估引擎基于评估度量和多参考响应集合生成机器生成的响应的度量得分。 度量得分表示相对于用户生成的消息和用户生成的消息的上下文的机器生成的会话响应的质量。 基于度量分数优化和调整诸如数字助理的计算设备的响应生成系统，以提高对用户输出的响应的准确性，质量和相关性。

公开(公告)号：US20160330597A1

公开(公告)日：2016-11-10

申请号：US14707895

申请日：2015-05-08

Applicant: BlackBerry Limited

Inventor： Nicholas KALKOUNIS ,  Shiladitya SIRCAR

IPC: H04W4/12 ,  H04W76/02 ,  H04L12/58 ,  G06F17/30 ,  G06F3/0484 ,  H04W4/02 ,  G06N7/00

CPC classification number: H04W4/12 ,  G06F3/04842 ,  G06F17/276 ,  G06F17/2785 ,  G06F17/2881 ,  G06F17/3043 ,  G06F17/3053 ,  G06N7/005 ,  H04L51/02 ,  H04L51/22 ,  H04W4/02 ,  H04W76/10

Abstract: A method of responding to a text-based communication on a portable electronic device includes receiving the text-based communication at the portable electronic device, performing textual analysis on the text-based communication to determine a set of possible responses, for each possible response of the set of possible responses, ranking the possible responses based at least on auxiliary information at the portable electronic device, and selecting a first possible response as a suggested response based on the ranking of the possible responses.

Abstract translation: 响应于便携式电子设备上的基于文本的通信的方法包括在便携式电子设备处接收基于文本的通信，对基于文本的通信执行文本分析以确定一组可能的响应，以针对每个可能的响应 所述一组可能的响应，至少基于所述便携式电子设备上的辅助信息对可能的响应进行排序，以及基于所述可能响应的排序来选择作为建议响应的第一可能响应。

公开(公告)号：US09483455B1

公开(公告)日：2016-11-01

申请号：US15046541

申请日：2016-02-18

Applicant: International Business Machines Corporation

Inventor： Paul R. Bastide ,  Matthew E. Broomhall ,  Donna K. Byron ,  Robert E. Loredo

IPC: G06F17/00 ,  G06F17/24 ,  G06F17/27 ,  G06F17/30

CPC classification number: G06F17/30011 ,  G06F17/2264 ,  G06F17/245 ,  G06F17/27 ,  G06F17/2881 ,  G06F17/3002 ,  G06F17/30038 ,  G06F17/30106 ,  G06F17/30339 ,  G06F17/30401 ,  G06F17/3053 ,  G06F17/30563 ,  G06F17/30616 ,  G06F17/30648 ,  G06F17/30654 ,  G06F17/30684 ,  G06F17/30719

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for generating a plan for document processing. A plurality of electronic documents are received from a data store. The plurality of electronic documents are analyzed. Textual data within the identified tabular data are identified, by performing a first natural language search of the analyzed plurality of electronic documents. Textual hints are generated, where the generated textual hints are mapped to a lookup set. References are identified, and a count of identified references are determined. A priority score is calculating based on the count of identified references. In response to receiving a priority score modifying value, a modified priority score is calculated. Ingestion plans are generated based on the modified priority score. Generated ingestion plans are communicated by the computer using the network.

Abstract translation: 本发明的实施例公开了一种用于生成文档处理计划的方法，计算机程序产品和系统。 从数据存储器接收多个电子文档。 分析多个电子文档。 通过对所分析的多个电子文档进行第一自然语言搜索来识别所识别的表格数据内的文本数据。 生成文本提示，其中生成的文本提示映射到查找集。 确定参考文献，并确定已识别参考文献的计数。 优先分数是根据识别的参考的计数进行计算。 响应于接收到优先级分数修改值，计算修改的优先级得分。 基于修改的优先级得分摄取计划。 生成的摄取计划由计算机通过网络进行传送。

公开(公告)号：US20160306775A1

公开(公告)日：2016-10-20

申请号：US15192568

申请日：2016-06-24

Applicant: SONY CORPORATION

Inventor： MASAAKI HOSHINO ,  KENICHIRO KOBAYASHI ,  SHOUICHI DOI ,  AKIHIRO WATANABE

IPC: G06F17/21 ,  G06F3/0484 ,  H04L29/08 ,  G06F17/27

CPC classification number: G06F16/9535 ,  G06F3/0482 ,  G06F3/0484 ,  G06F7/20 ,  G06F16/58 ,  G06F16/90348 ,  G06F17/212 ,  G06F17/271 ,  G06F17/2735 ,  G06F17/2755 ,  G06F17/2765 ,  G06F17/277 ,  G06F17/2881 ,  H04L67/18

Abstract: An information processing apparatus includes a selection unit selecting at least a part of a text included in contents, an acquisition unit acquiring a processing result of natural language processing for the part of the text selected by the selection unit, a specifying unit specifying a predetermined part of the text based on the processing result acquired by the acquisition unit, a detection unit detecting a keyword from the predetermined part of the text based on the processing result acquired by the acquisition unit, a tag generation unit automatically generating a tag in accordance with the keyword detected by the detection unit, and an association unit associating the tag generated by the tag generation unit with the predetermined part of the text.

公开(公告)号：US09454760B2

公开(公告)日：2016-09-27

申请号：US14103144

申请日：2013-12-11

Applicant: Avaya, Inc.

Inventor： Reinhard Klemm ,  George Erhart ,  Lee Becker ,  David Skiba

IPC: H04M1/64 ,  G06Q30/00 ,  G06F17/28

CPC classification number: G06Q30/01 ,  G06F17/2881

Abstract: Contact centers may incorporate automated agents to respond to inquiries. The inquiries may solicit a substantive response, for example, by providing a time when the inquiry asks for the departure time for a flight. Such responses omit the normal conversational subject matter used to embellish person-to-person conversations and appear are very machine-like. Herein, a source of user context, such as a social media website, customer database, or other data, is accessed. Certain aspects of the customer may then be identified and used to embellish the reply with additional and/or alternative content. As a result, the reply may be more conversational.

Abstract translation: 联络中心可以结合自动化代理来回应查询。 查询可以征求实质性答复，例如，提供询问要求航班起飞时间的时间。 这样的答复省略了用于修饰个人对人对话的正常对话主题，并且出现非常类似机器。 这里，访问诸如社交媒体网站，客户数据库或其他数据的用户上下文来源。 然后可以识别客户的某些方面并用于用附加和/或替代内容来修饰该回复。 因此，答复可能会更多的对话。

公开(公告)号：US09454730B2

公开(公告)日：2016-09-27

申请号：US14856654

申请日：2015-09-17

Applicant: Steven Dennis Flinn ,  Naomi Felina Moneypenny

Inventor： Steven Dennis Flinn ,  Naomi Felina Moneypenny

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06 ,  G06N5/04 ,  G06Q50/00 ,  G06F17/30 ,  G06F17/28

CPC classification number: G06N5/048 ,  G06F17/2881 ,  G06F17/30528 ,  G06F17/30867 ,  G06Q50/01 ,  H04L51/16

Abstract: A method and system of expertise discovery in social networks accesses behavioral information associated with users' use of a computer-implemented social network, whereby the computer-implemented social network enables its users to have subscribing relationships with other users. Expertise levels of users of the social network with respect to one or more topics are automatically inferred from the behavioral information. The behavioral information may comprise interactions by other users with respect to content published by a user. The expertise levels of users may be inferred in accordance with the expertise levels of other users who are subscribed to them. Recommendations of users based on their expertise levels may be delivered, as well as explanations for the recommendations. Expertise levels of multiple users and/or expertise levels of a user over time may be delivered for display.

Abstract translation: 社交网络中的专业知识发现的方法和系统访问与用户使用计算机实现的社交网络相关联的行为信息，由此计算机实现的社交网络使其用户能够与其他用户具有订阅关系。 根据行为信息自动推断关于一个或多个主题的社交网络的用户的专业级别。 行为信息可以包括其他用户相对于用户发布的内容的交互。 可以根据订阅其他用户的专业知识水平来推断用户的专业知识水平。 可以提供用户基于其专业知识水平的建议，以及对建议的解释。 可以提供用户随时间的多个用户和/或专业级别的专业水平以供显示。