公开(公告)号：US08738366B2

公开(公告)日：2014-05-27

申请号：US13923744

申请日：2013-06-21

Applicant: Rakuten, Inc.

Inventor： Yu Hirate

IPC: G06F17/27 ,  G06F17/28 ,  G06F17/21 ,  G10L15/04 ,  G10L21/00

CPC classification number: G06F17/30442 ,  G06F17/21 ,  G06F17/2795 ,  G06F17/3064 ,  G06F17/30737

Abstract: A search query of a search word entered by the user is received, the received search queries are stored in accordance with reception order, a preceding search query whose reception order is earlier than that of the received search query is extracted on the basis of a preset search query extracting condition, a preceding search word constructing the extracted preceding search query and a search word constructing the received search query are stored as a character string set, a character string set having the search word which is the same or similar to the preceding search word is extracted in accordance with a preset character string set extraction start condition (S51), a character set as a related word is specified from the extracted character string set on the basis of a preset registration condition (S53), and the specified character string set is registered as related words into a related-word database (S54).

Abstract translation: 接收用户输入的搜索词的搜索查询，根据接收顺序存储接收的搜索查询，根据预设的提取方式提取其接收顺序早于接收到的搜索查询的前一搜索查询 搜索查询提取条件，构成提取的先前搜索查询的前一搜索词和构成接收到的搜索查询的搜索词被存储为字符串集合，具有与前一搜索相同或相似的搜索词的字符串集 根据预设字符串设置提取开始条件（S51）提取字词，根据预设注册条件（S53）从提取的字符串中指定作为相关字的集合的字符，并且指定的字符串 集合作为相关词记录到相关字数据库中（S54）。

公开(公告)号：US20140143331A1

公开(公告)日：2014-05-22

申请号：US13683160

申请日：2012-11-21

Applicant: David Smith ,  Milind Sarambale ,  Souheil Ben Yacoub

Inventor： David Smith ,  Milind Sarambale ,  Souheil Ben Yacoub

IPC: H04L29/08

CPC classification number: H04L67/02 ,  G06F17/2795 ,  G06F17/2881 ,  H04L29/12641 ,  H04L61/3025

Abstract: Systems and methods are provided for providing domain name suggestions based on user preferences and terms extracted from one or more information sources. Terms may be continuously extracted from information sources and used to generate domain name suggestions. Generated domain name suggestions may then be delivered to customers. The systems and methods may utilize customer preferences in providing the domain name suggestions, such as preferences as to information sources or topics of interest. The systems and methods may be self-learning, taking historical domain name registration information into account to improve the domain name suggestions.

Abstract translation: 提供系统和方法，用于根据从一个或多个信息源提取的用户偏好和术语提供域名建议。 条款可以不断地从信息源中提取出来，用于生成域名建议。 然后可以将生成的域名建议传递给客户。 系统和方法可以利用客户偏好来提供域名建议，例如关于信息源或感兴趣的主题的偏好。 系统和方法可能是自学习的，考虑到历史域名注册信息来改进域名建议。

公开(公告)号：US08682898B2

公开(公告)日：2014-03-25

申请号：US12771543

申请日：2010-04-30

Applicant: Sachindra Joshi ,  Tanveer Faruquie ,  Hima Prasad Karanam ,  Marvin Mendelssohn ,  Mukesh Kumar Mohania ,  Angel Marie Smith ,  L Venkata Subramaniam ,  Girish Venkatachaliah

Inventor： Sachindra Joshi ,  Tanveer Faruquie ,  Hima Prasad Karanam ,  Marvin Mendelssohn ,  Mukesh Kumar Mohania ,  Angel Marie Smith ,  L Venkata Subramaniam ,  Girish Venkatachaliah

IPC: G06F7/00 ,  G06F17/00

CPC classification number: G06F17/2735 ,  G06F17/2795

Abstract: A clustering-based approach to data standardization is provided. Certain embodiments take as input a plurality of addresses, identify one or more features of the addresses, cluster the addresses based on the one or more features, utilize the cluster(s) to provide a data-based context useful in identifying one or more synonyms for elements contained in the address(es), and standardize the address(es) to an acceptable format, with one or more synonyms and/or other elements being added to or taken away from the input address(es) as part of the standardization process.

Abstract translation: 提供了基于聚类的数据标准化方法。 某些实施例将多个地址作为输入，识别地址的一个或多个特征，基于一个或多个特征聚集地址，利用群集提供用于识别一个或多个同义词的基于数据的上下文 对于包含在地址中的元素，并将地址标准化为可接受的格式，其中一个或多个同义词和/或其他元素作为标准化的一部分被添加到或从输入地址中取走 处理。

公开(公告)号：US20140081626A1

公开(公告)日：2014-03-20

申请号：US13683509

申请日：2012-11-21

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： Walter W. Chang ,  Gregg D. Wilensky ,  Lubomira A. Dontcheva

IPC: G06F17/28

CPC classification number: G06F17/28 ,  G06F17/2735 ,  G06F17/2785 ,  G06F17/2795

Abstract: Natural language vocabulary generation and usage techniques are described. In one or more implementations, one or more search results are mined for a domain to determine a frequency at which words occur in the one or more search results, respectively. A set of the words is selected based on the determined frequency. A sense is assigned to each of the selected set of the words that identifies a part-of-speech for a respective word. A vocabulary is then generated that includes the selected set of the words and a respective said sense, the vocabulary configured for use in natural language processing associated with the domain.

Abstract translation: 描述自然语言词汇生成和使用技术。 在一个或多个实现中，为一个域开采一个或多个搜索结果，以分别确定在一个或多个搜索结果中发生单词的频率。 基于确定的频率来选择一组单词。 将识别分配给识别相应词的词性的所选择的一组词中的每一个。 然后生成包括所选择的单词集合和相应的所述感觉的词汇，所述词汇被配置为在与域相关联的自然语言处理中使用。

公开(公告)号：US20140074456A1

公开(公告)日：2014-03-13

申请号：US13782239

申请日：2013-03-01

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Peter J. Johnson ,  Stephen J. Upton

IPC: G06F17/28

CPC classification number: G06F17/28 ,  G06F17/2785 ,  G06F17/2795 ,  G06Q10/06 ,  G06Q10/067

Abstract: Embodiments are directed to refining hierarchies in object-oriented models. A method includes providing a business object model in the form of an object-oriented model having one or more members with multiple distinct verbalizations and identifying distinct verbalizations of a given business object model member. The method also includes reviewing existing rules of the business object model to produce mappings of the distinct verbalizations and any attributes or operations used in conjunction with the distinct verbalizations of members of the business object model and analysing the mappings to identify patterns of use of the distinct verbalizations. The method further includes categorising a distinct verbalization as a superclass or subclass.

Abstract translation: 实施例旨在改进面向对象模型中的层次结构。 一种方法包括以面向对象模型的形式提供业务对象模型，该模型具有一个或多个具有多个不同语言表达的成员，并且识别给定业务对象模型成员的不同语言表达。 该方法还包括审查业务对象模型的现有规则，以产生不同语言表达的映射以及与业务对象模型的成员的不同口头语言结合使用的任何属性或操作，并分析映射以识别不同的 言语表达 该方法还包括将不同的语言分类归类为超类或子类。

公开(公告)号：US20140067368A1

公开(公告)日：2014-03-06

申请号：US13597277

申请日：2012-08-29

Applicant: Wen-tau Yih ,  Geoffrey G. Zweig ,  John C. Platt

Inventor： Wen-tau Yih ,  Geoffrey G. Zweig ,  John C. Platt

IPC: G06F17/27

CPC classification number: G06F17/2795 ,  G06F16/3338 ,  G06F17/2785

Abstract: A document-term matrix may be generated based on a corpus. A term representation matrix may be generated based on modifying a plurality of elements of the document-term matrix based on antonym information included in the corpus. Similarities may be determined based on a plurality of elements of the term representation matrix.

Abstract translation: 可以基于语料库生成文档术语矩阵。 可以基于基于语料库中包含的反义词信息修改文档项矩阵的多个元素来生成术语表示矩阵。 可以基于术语表示矩阵的多个元素来确定相似度。

公开(公告)号：US20140040302A1

公开(公告)日：2014-02-06

申请号：US13889567

申请日：2013-05-08

Applicant: Patrick Sander Walsh

Inventor： Patrick Sander Walsh

IPC: G06F17/30

CPC classification number: G06F16/90332 ,  G06F16/374 ,  G06F17/2795

Abstract: The present invention is a method and system for enhancing the output of standard thesaurus databases. The user requires little knowledge of the meaning of a word for which he is seeking related words. The system requires at least one starter word, and it returns all synonyms regardless of meaning from multiple databases. The synonyms are then arranged in a two dimensional array, and sorted according to frequency. The user then scans the list, starting from the top, and selects one or more entries from the sorted frequency array, and the re-runs. After several cycles of running and selecting new entries, the related words having the highest relevance to the searcher will rise to top of the frequency array. The end result is a group of related words having one or more meanings, and also having a relationship to a single concept being sought by the user.

Abstract translation: 本发明是用于增强标准词库数据库的输出的方法和系统。 用户几乎不需要知道他正在寻找相关词语的单词的含义。 该系统需要至少一个起始字，并且返回所有同义词，而不管多个数据库的含义。 然后将同义词排列成二维阵列，并根据频率进行排序。 然后，用户从顶部开始扫描列表，并从排序的频率数组中选择一个或多个条目，并重新运行。 在运行和选择新条目的几个周期之后，与搜索者具有最高相关性的相关词将升至频率阵列的顶部。 最终结果是一组具有一个或多个含义的相关词，并且与用户所寻求的单一概念具有关系。

公开(公告)号：US08635070B2

公开(公告)日：2014-01-21

申请号：US13071549

申请日：2011-03-25

Applicant: Kazuo Sumita

Inventor： Kazuo Sumita

IPC: G06F17/28 ,  G10L13/00 ,  G10L13/08

CPC classification number: G06F17/2795 ,  G06F17/2854 ,  G06F17/289 ,  G10L17/26

Abstract: According to one embodiment, a speech translation apparatus includes a receiving unit, a first recognition unit, a second recognition unit, a first generation unit, a translation unit, a second generation unit, a synthesis unit. The receiving unit is configured to receive a speech in a first language and convert to speech signal. The first recognition unit is configured to perform speech recognition and generate a transcription. The second recognition unit is configured to recognize which emotion type is included in the speech and generate emotion identification information including recognized emotion type(s). The first generation unit is configured to generate a filtered sentence. The translation unit is configured to generate a translation of the filtered sentence in the first language in a second language. The second generation unit is configured to generate an insertion sentence. The synthesis unit is configured to convert the filtered and the insertion sentences into speech signal.

Abstract translation: 根据一个实施例，语音翻译装置包括接收单元，第一识别单元，第二识别单元，第一生成单元，翻译单元，第二生成单元，合成单元。 接收单元被配置为以第一语言接收语音并转换成语音信号。 第一识别单元被配置为执行语音识别并产生转录。 第二识别单元被配置为识别哪个情感类型被包括在语音中并且生成包括识别的情绪类型的情感识别信息。 第一代单元被配置为生成过滤句子。 翻译单元被配置为以第二语言生成第一语言的过滤句子的翻译。 第二代单元被配置为生成插入语句。 所述合成单元被配置为将所述滤波和插入语句转换为语音信号。

公开(公告)号：US20140019116A1

公开(公告)日：2014-01-16

申请号：US14049168

申请日：2013-10-08

Applicant: ARTIFICIAL SOLUTIONS IBERIA SL

Inventor： Sonja Petrovic Lundberg ,  Eric Aili ,  Andreas Wieweg ,  Rebecca Jonsson ,  David Hjelm

IPC: G06F17/28

CPC classification number: G06F17/289 ,  G06F8/30 ,  G06F8/447 ,  G06F11/3476 ,  G06F11/3664 ,  G06F17/2785 ,  G06F17/2795 ,  G06F17/28 ,  G06F17/30893 ,  G06F17/30976 ,  G10L15/183

Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.

Abstract translation: 一种用于自然语言交互应用的监督自动代码生成和调优的系统，包括构建环境，包括开发者用户界面，自动编码工具，自动化测试工具和自动化优化工具以及分析框架软件模块。 文本样本被导入到构建环境中，并且执行自动聚类以将它们分配给多个输入组，每个输入组包括多个语义相关的输入。 语言识别规则由自动编码工具生成。 自动测试工具对语言识别规则进行自动测试，并产生调整语言识别规则的建议。 分析框架执行交互日志文件的分析，以识别候选自然语言交互应用程序中的问题。 对候选自然语言交互应用进行优化，并将优化的自然语言交互应用程序部署到生产中并存储在解决方案数据存储库中。

公开(公告)号：US08630846B2

公开(公告)日：2014-01-14

申请号：US13736903

申请日：2013-01-08

Applicant: Fluential, LLC

Inventor： Farzad Ehsani ,  Eva M. Knodt ,  Demitrios L. Master

IPC: G06F17/27 ,  G10L15/00

CPC classification number: G06F17/28 ,  G06F17/2775 ,  G06F17/2795 ,  G10L15/183 ,  G10L15/193 ,  G10L15/197 ,  G10L15/22

Abstract: The invention enables creation of grammar networks that can regulate, control, and define the content and scope of human-machine interaction in natural language voice user interfaces (NLVUI). The invention enables phrase-based modeling of generic structures of verbal interaction to be used for the purpose of automating part of the design of such grammar networks. Most particularly, the invention enables such grammar networks to be used in providing a voice-controlled user interface to human readable text data that is also machine-readable (such as a Web page, a word processing document, a PDF document, or a spreadsheet).

Abstract translation: 本发明能够创建可以调节，控制和定义自然语言语音用户界面（NLVUI）中人机交互的内容和范围的语法网络。 本发明使语言交互的通用结构的基于短语的建模能够用于自动化这种语法网络的一部分设计。 最具体地，本发明使得这种语法网络能够用于为也可机读的人可读文本数据（诸如网页，文字处理文档，PDF文档或电子表格）提供语音控制用户界面 ）。