利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

83 条记录 (耗时 0.035 秒)

    SYSTEM AND METHOD FOR VALIDATING NATURAL LANGUAGE CONTENT USING CROWDSOURCED VALIDATION JOBS
    72.
    发明申请
    SYSTEM AND METHOD FOR VALIDATING NATURAL LANGUAGE CONTENT USING CROWDSOURCED VALIDATION JOBS 有权
    用自动验证作业验证自然语言内容的系统和方法

    公开(公告)号：US20170069326A1

    公开(公告)日：2017-03-09

    申请号：US15219088

    申请日：2016-07-25

    申请人： VOICEBOX TECHNOLOGIES CORPORATION

    发明人： Spencer John ROTHWELL ,  Daniela BRAGA ,  Ahmad Khamis ELSHENAWY ,  Stephen Steele CARTER

    IPC分类号： G10L15/30 ,  G10L15/01 ,  G06F17/28 ,  G06F17/27

    CPC分类号： G10L15/30 ,  G06F17/2725 ,  G06F17/28 ,  G06Q30/02 ,  G06Q50/01 ,  G10L15/01

    摘要： Systems and methods of validating transcriptions of natural language content using crowdsourced validation jobs are provided herein. In various implementations, a transcription pair comprising natural language content and text corresponding to a transcription of the natural language content may be gathered. A first group of validation devices may be selected for reviewing the transcription pair. A first crowdsourced validation job may be created for the first group of validation devices. The first crowdsourced validation job may be provided to the first group of validation devices. A vote representing whether or not the text accurately represents the natural language content may be received from each of the first group of validation devices. A validation score may be assigned to the transcription pair based, at least in part, on the votes from each of the first group of validation devices.

    摘要翻译： 本文提供使用众包验证作业验证自然语言内容的转录的系统和方法。 在各种实现中，可以收集包括自然语言内容和对应于自然语言内容的转录的文本的转录对。 可以选择第一组验证装置来检查转录对。 可以为第一组验证设备创建第一个众包验证作业。 可以将第一群众化验证作业提供给第一组验证设备。 可以从第一组验证装置中的每一个接收表示文本是否准确地表示自然语言内容的投票。 至少部分地基于来自第一组验证装置的投票而将确认分数分配给转录对。

    INTEGRATION OF DOMAIN INFORMATION INTO STATE TRANSITIONS OF A FINITE STATE TRANSDUCER FOR NATURAL LANGUAGE PROCESSING
    74.
    发明申请
    INTEGRATION OF DOMAIN INFORMATION INTO STATE TRANSITIONS OF A FINITE STATE TRANSDUCER FOR NATURAL LANGUAGE PROCESSING 有权
    将域信息整合到用于自然语言处理的有限状态传输器的状态转换

    公开(公告)号：US20160188573A1

    公开(公告)日：2016-06-30

    申请号：US14855346

    申请日：2015-09-15

    申请人： VOICEBOX TECHNOLOGIES CORPORATION

    发明人： Min TANG

    IPC分类号： G06F17/28 ,  G10L15/18 ,  G06F17/27

    CPC分类号： G06F17/28 ,  G06F17/277 ,  G06F17/2775 ,  G06F17/2785 ,  G10L15/1815 ,  G10L2015/025

    摘要： The invention relates to a system and method for integrating domain information into state transitions of a Finite State Transducer (“FST”) for natural language processing. A system may integrate semantic parsing and information retrieval from an information domain to generate an FST parser that represents the information domain. The FST parser may include a plurality of FST paths, at least one of which may be used to generate a meaning representation from a natural language input. As such, the system may perform domain-based semantic parsing of a natural language input, generating more robust meaning representations using domain information. The system may be applied to a wide range of natural language applications that use natural language input from a user such as, for example, natural language interfaces to computing systems, communication with robots in natural language, personalized digital assistants, question-answer query systems, and/or other natural language processing applications.

    摘要翻译： 本发明涉及一种用于将域信息整合到用于自然语言处理的有限状态传感器（“FST”）的状态转换中的系统和方法。 系统可以将来自信息域的语义解析和信息检索整合以生成表示信息域的FST解析器。 FST解析器可以包括多个FST路径，其中的至少一个可以用于从自然语言输入生成意思表示。 因此，系统可以执行基于域的语义解析自然语言输入，使用域信息生成更加鲁棒的含义表示。 该系统可以应用于使用用户的自然语言输入的广泛的自然语言应用，例如对计算系统的自然语言接口，与自然语言的机器人的通信，个性化数字助理，问答回答查询系统 ，和/或其他自然语言处理应用程序。

    SYSTEM AND METHOD OF PROVIDING TASK-BASED SOLICITATION OF REQUEST RELATED USER INPUTS
    76.
    发明申请
    SYSTEM AND METHOD OF PROVIDING TASK-BASED SOLICITATION OF REQUEST RELATED USER INPUTS 审中-公开
    提供相关用户输入的基于任务的索引的系统和方法

    公开(公告)号：US20160078773A1

    公开(公告)日：2016-03-17

    申请号：US14855598

    申请日：2015-09-16

    申请人： VOICEBOX TECHNOLOGIES CORPORATION

    发明人： Daniel B. CARTER ,  Michael R. KENNEWICK

    IPC分类号： G09B7/02

    CPC分类号： G09B7/02

    摘要： In certain implementations, a training environment is provided. A task that is to be performed is provided. The task may relate to a user request that is invokeable in one or more other environments different than the training environment. One or more user inputs may be received for the training environment. A determination of whether performance of the task has been satisfied may be effectuated based on the one or more user inputs. A reward may be provided for a user in response to a determination that performance of the task has been satisfied. In some implementations, the determination of whether performance of the task has been satisfied may comprise a determination of whether the user request would have been invoked in the one or more other environments if the user inputs had been received for the one or more other environments.

    摘要翻译： 在某些实施方式中，提供了训练环境。 提供要执行的任务。 该任务可以涉及在与训练环境不同的一个或多个其他环境中可调用的用户请求。 可以为训练环境接收一个或多个用户输入。 可以基于一个或多个用户输入来实现是否已经满足任务性能的确定。 可以响应于已经满足任务的性能的确定，为用户提供奖励。 在一些实现中，确定是否已经满足任务的性能可以包括如果已经为一个或多个其他环境接收到用户输入，则确定用户请求是否将在一个或多个其他环境中被调用。

    VOICE COMMERCE
    77.
    发明申请
    VOICE COMMERCE 有权
    语音商务

    公开(公告)号：US20160078504A1

    公开(公告)日：2016-03-17

    申请号：US14855334

    申请日：2015-09-15

    申请人： VOICEBOX TECHNOLOGIES CORPORATION

    发明人： Michael R. KENNEWICK, SR.

    IPC分类号： G06Q30/06 ,  G10L15/18 ,  G10L15/22

    CPC分类号： G06Q30/0635 ,  G06Q30/0601 ,  G06Q30/0625 ,  G10L15/18 ,  G10L15/1815 ,  G10L15/22 ,  G10L2015/223

    摘要： In certain implementations, a system for facilitating voice commerce is provided. A user input comprising a natural language utterance related to a product or service to be purchased may be received. A first product or service that is to be purchased may be determined based on the utterance. First payment information that is to be used to purchase the first product or service may be obtained. First shipping information that is to be used to deliver the first product or service may be obtained. A purchase transaction for the first product or service may completed based on the first payment information and the first shipping information without further user input, after the receipt of utterance, that identifies a product or service type or a product or service, seller information, payment information, shipping information, or other information related to purchasing the first product or service.

    摘要翻译： 在某些实现中，提供了一种用于促进语音商务的系统。 可以接收包括与要购买的产品或服务相关的自然语言话语的用户输入。 要购买的第一种产品或服务可以基于说话来确定。 可以获得用于购买第一产品或服务的第一支付信息。 可以获得用于交付第一个产品或服务的第一个运送信息。 第一产品或服务的购买交易可以基于第一付款信息和第一送货信息而完成，而无需进一步的用户输入，在接收到话语之后，识别产品或服务类型，产品或服务，卖家信息，支付 信息，运送信息或与购买第一个产品或服务有关的其他信息。

    SYSTEM AND METHOD OF MARKETING OF USER REQUESTS
    78.
    发明申请
    SYSTEM AND METHOD OF MARKETING OF USER REQUESTS 审中-公开
    用户要求营销的系统与方法

    公开(公告)号：US20160078482A1

    公开(公告)日：2016-03-17

    申请号：US14855343

    申请日：2015-09-15

    申请人： VOICEBOX TECHNOLOGIES CORPORATION

    发明人： Michael R. KENNEWICK, SR.

    IPC分类号： G06Q30/02

    CPC分类号： G06Q30/0257 ,  G06Q10/1093 ,  G06Q30/0264 ,  G06Q30/0269

    摘要： In certain implementations, advertisers may be enabled to determine in real-time (as user requests are received from users) whether to include their advertisements (or other content) as part of responses to the user requests (e.g., queries, command, or other user requests). As an example, upon determining a user request based on a user input of a user, an advertisement opportunity associated with the user request may be provided to one or more advertisers. The advertisement opportunity may, for instance, comprise an opportunity to purchase an ad placement associated with the user request. Upon determining that an advertiser purchased the associated ad placement, the associated ad placement may be allocated for an advertisement associated with the advertiser so that a response to the user request will comprise an advertisement associated with the advertiser.

    摘要翻译： 在某些实施方式中，可以使得广告商能够实时地（由用户从用户接收的请求）确定是否将其广告（或其他内容）包括在用户请求的响应中（例如，查询，命令或其他 用户请求）。 作为示例，在基于用户的用户输入确定用户请求时，可以向一个或多个广告商提供与用户请求相关联的广告机会。 例如，广告机会可以包括购买与用户请求相关联的广告展示位置的机会。 在确定广告客户购买相关联的广告展示位置时，可以为与广告商相关联的广告分配相关联的广告展示位置，使得对用户请求的响应将包括与广告商相关联的广告。

    In-View and Out-of-View Request-Related Result Regions for Respective Result Categories
    79.
    发明申请
    In-View and Out-of-View Request-Related Result Regions for Respective Result Categories 有权
    相关结果类别的视图和视图中的请求相关结果区域

    公开(公告)号：US20160078106A1

    公开(公告)日：2016-03-17

    申请号：US14855331

    申请日：2015-09-15

    申请人： VOICEBOX TECHNOLOGIES CORPORATION

    发明人： Michael R. KENNEWICK, SR.

    IPC分类号： G06F17/30

    CPC分类号： G06F17/30867 ,  G06F3/04883 ,  G06F17/30401 ,  G06F17/30554 ,  G06F17/30598 ,  G06F17/30991

    摘要： The invention relates to systems and methods of providing in-view and out-of-view request-related result regions for respective result categories. The system may facilitate result presentation by providing, in response to a user request, at least one region that is designated to initially be in-view and at least one region that is designated to initially be out-of-view where: (i) the initial in-view region comprises one or more results related to the user request and a first category; and (ii) the initial out-of-view region comprises one or more results related to the user request and the second category. A result related to a category may comprise a result related to a specific topic, a result of a specific type, a result from a specific source, or other result. A user request may comprise a query, a command, or other user request.

    摘要翻译： 本发明涉及为相应的结果类别提供视听和视听请求的结果区域的系统和方法。 该系统可以通过响应于用户请求提供被指定为最初被视为的至少一个区域以及被指定为最初不在视图中的至少一个区域来促进结果呈现，其中：（i） 初始视图区域包括与用户请求相关的一个或多个结果和第一类别; 和（ii）初始视野外区域包括与用户请求和第二类别相关的一个或多个结果。 与类别相关的结果可以包括与特定主题相关的结果，特定类型的结果，来自特定源的结果或其他结果。 用户请求可以包括查询，命令或其他用户请求。

    System and method for delivering targeted advertisements and tracking advertisement interactions in voice recognition contexts
    80.
    发明授权
    System and method for delivering targeted advertisements and tracking advertisement interactions in voice recognition contexts 有权
    用于在语音识别上下文中提供有针对性的广告和跟踪广告交互的系统和方法

    公开(公告)号：US08886536B2

    公开(公告)日：2014-11-11

    申请号：US14016757

    申请日：2013-09-03

    申请人： VoiceBox Technologies Corporation

    发明人： Tom Freeman ,  Mike Kennwick

    IPC分类号： G10L15/18 ,  G06F17/27 ,  G10L21/00 ,  G06Q30/00 ,  G10L15/26 ,  G06Q30/02

    CPC分类号： G06Q30/0269 ,  G06F17/275 ,  G06Q30/0241 ,  G06Q30/0242 ,  G06Q30/0251 ,  G10L15/18 ,  G10L15/26 ,  G10L15/265

    摘要： The system and method described herein may use various natural language models to deliver targeted advertisements and track advertisement interactions in voice recognition contexts. In particular, in response to an input device receiving an utterance, a conversational language processor may select and deliver one or more advertisements targeted to a user that spoke the utterance based on cognitive models associated with the user, various users having similar characteristics to the user, an environment in which the user spoke the utterance, or other criteria. Further, subsequent interaction with the targeted advertisements may be tracked to build and refine the cognitive models and thereby enhance the information used to deliver targeted advertisements in response to subsequent utterances.

    摘要翻译： 本文描述的系统和方法可以使用各种自然语言模型来递送目标广告并在语音识别上下文中跟踪广告交互。 具体地，响应于输入设备接收到话语，会话语言处理器可以基于与用户相关联的认知模型来选择并递送针对用户讲话的用户的一个或多个广告，各种用户具有与用户相似的特征 ，用户说话的环境或其他标准。 此外，跟踪与目标广告的后续交互可以建立和完善认知模型，从而增强用于响应于随后话语而递送目标广告的信息。