公开(公告)号：US20100010805A1

公开(公告)日：2010-01-14

申请号：US12499544

申请日：2009-07-08

Applicant: Rajesh Balchandran ,  Linda M. Boyer

Inventor： Rajesh Balchandran ,  Linda M. Boyer

IPC: G06F17/27

CPC classification number: G06F17/2715 ,  G06F17/2785 ,  G10L15/26

Abstract: A method for processing language input can include the step of determining at least two possible meanings for a language input. For each possible meaning, a probability that the possible meaning is a correct interpretation of the language input can be determined. At least one relative data computation can be computed based at least in part upon the probabilities. At least one irregularity within the language input can be detected based upon the relative delta computation. The irregularity can include mumble, ambiguous input, and/or compound input. At least one programmatic action can be performed responsive to the detection of the irregularity.

Abstract translation: 用于处理语言输入的方法可以包括为语言输入确定至少两个可能的含义的步骤。 对于每个可能的含义，可以确定可能的含义是语言输入的正确解释的概率。 可以至少部分地基于概率来计算至少一个相对数据计算。 可以基于相对增量计算来检测语言输入内的至少一个不规则性。 不规则性可以包括嘟嘟声，模糊输入和/或复合输入。 响应于不规则性的检测可以执行至少一个编程动作。

公开(公告)号：US07562016B2

公开(公告)日：2009-07-14

申请号：US12035944

申请日：2008-02-22

Applicant: Rajesh Balchandran ,  Linda M. Boyer

Inventor： Rajesh Balchandran ,  Linda M. Boyer

IPC: G10L15/14 ,  G10L15/18

CPC classification number: G06F17/2715 ,  G06F17/2785 ,  G10L15/26

Abstract: A method for processing language input can include the step of determining at least two possible meanings for a language input. For each possible meaning, a probability that the possible meaning is a correct interpretation of the language input can be determined. At least one relative data computation can be computed based at least in part upon the probabilities. At least one irregularity within the language input can be detected based upon the relative delta computation. The irregularity can include mumble, ambiguous input, and/or compound input. At least one programmatic action can be performed responsive to the detection of the irregularity.

Abstract translation: 用于处理语言输入的方法可以包括为语言输入确定至少两个可能的含义的步骤。 对于每个可能的含义，可以确定可能的含义是语言输入的正确解释的概率。 可以至少部分地基于概率来计算至少一个相对数据计算。 可以基于相对增量计算来检测语言输入内的至少一个不规则性。 不规则性可以包括嘟嘟声，模糊输入和/或复合输入。 响应于不规则性的检测可以执行至少一个编程动作。

公开(公告)号：US07386440B2

公开(公告)日：2008-06-10

申请号：US10676524

申请日：2003-10-01

Applicant: Rajesh Balchandran ,  Linda M. Boyer

Inventor： Rajesh Balchandran ,  Linda M. Boyer

IPC: G06F17/27

CPC classification number: G10L15/1822 ,  G10L15/22

Abstract: In a natural language, mixed-initiative system, a method of processing user dialogue can include receiving a user input and determining whether the user input specifies an action to be performed or a token of an action. The user input can be selectively routed to an action interpreter or a token interpreter according to the determining step.

Abstract translation: 以自然语言，混合主动系统，处理用户对话的方法可以包括接收用户输入并确定用户输入是指定要执行的动作还是动作的标记。 可以根据确定步骤将用户输入选择性地路由到动作解释器或令牌解释器。

公开(公告)号：US20070168578A1

公开(公告)日：2007-07-19

申请号：US11260102

申请日：2005-10-27

Applicant: Rajesh Balchandran ,  Ilya Skuratovsky

Inventor： Rajesh Balchandran ,  Ilya Skuratovsky

IPC: G06F3/00

CPC classification number: G06F3/048 ,  G06F17/247 ,  G06F17/30905 ,  G06Q30/02

Abstract: A method for collecting data for statistical modeling purposes can include the step of selecting at least one user interface type from a plurality of previously defined user interface types. Parameters of the selected interface type can be defined for a particular data collection instance. Target participant data can be inputted. A data collection interface based upon the selected interface type and defined parameters can be deployed. Messages can be automatically conveyed to data providers selected in accordance with the target participant data. The data providers can be permitted to access the deployed data collection interface. Data provided by the data providers can be automatically stored and used for statistical modeling purposes related to the data collection instance.

Abstract translation: 用于收集用于统计建模目的的数据的方法可以包括从多个先前定义的用户界面类型中选择至少一个用户界面类型的步骤。 可以为特定数据收集实例定义所选接口类型的参数。 可以输入目标参与者数据。 可以部署基于所选接口类型和定义参数的数据收集接口。 消息可以自动传送到根据目标参与者数据选择的数据提供者。 可以允许数据提供者访问部署的数据收集界面。 数据提供者提供的数据可以自动存储并用于与数据收集实例相关的统计建模。

公开(公告)号：US20070156392A1

公开(公告)日：2007-07-05

申请号：US11324057

申请日：2005-12-30

Applicant: Rajesh Balchandran ,  Linda Boyer

Inventor： Rajesh Balchandran ,  Linda Boyer

IPC: G06F17/27

CPC classification number: G06F17/27

Abstract: The invention disclosed herein concerns a system (100) and method (600) for building a language model representation of an NLU application. The method 500 can include categorizing an NLU application domain (602), classifying a corpus in view of the categorization (604), and training at least one language model in view of the classification (606). The categorization produces a hierarchical tree of categories, sub-categories and end targets across one or more features for interpreting one or more natural language input requests. During development of an NLU application, a developer assigns sentences of the NLU application to categories, sub-categories or end targets across one or more features for associating each sentence with desire interpretations. A language model builder (140) iteratively builds multiple language models for this sentence data, and iteratively evaluating them against a test corpus, partitioning the data based on the categorization and rebuilding models, so as to produce an optimal configuration of language models to interpret and respond to language input requests for the NLU application.

Abstract translation: 本文公开的发明涉及用于构建NLU应用的语言模型表示的系统（100）和方法（600）。 方法500可以包括将NLU应用域（602）分类，鉴于分类（604）对语料库进行分类，并且考虑到分类（606）训练至少一种语言模型。 分类产生跨越一个或多个特征的类别，子类别和结束目标的分层树，用于解释一个或多个自然语言输入请求。 在开发NLU应用程序期间，开发人员将NLU应用程序的句子分配给一个或多个功能的类别，子类别或终端目标，以将每个句子与欲望解释相关联。 语言模型构建器（140）迭代地构建用于该句子数据的多个语言模型，并且针对测试语料库迭代地对它们进行评估，基于分类和重建模型分割数据，以便产生语言模型的最佳配置来解释和 响应NLU应用程序的语言输入请求。

公开(公告)号：US09104287B2

公开(公告)日：2015-08-11

申请号：US11260102

申请日：2005-10-27

Applicant: Rajesh Balchandran ,  Ilya Skuratovsky

Inventor： Rajesh Balchandran ,  Ilya Skuratovsky

IPC: G06F3/048 ,  G06F17/30 ,  G06Q30/02

CPC classification number: G06F3/048 ,  G06F17/247 ,  G06F17/30905 ,  G06Q30/02

Abstract: A method for collecting data for statistical modeling purposes can include the step of selecting at least one user interface type from a plurality of previously defined user interface types. Parameters of the selected interface type can be defined for a particular data collection instance. Target participant data can be inputted. A data collection interface based upon the selected interface type and defined parameters can be deployed. Messages can be automatically conveyed to data providers selected in accordance with the target participant data. The data providers can be permitted to access the deployed data collection interface. Data provided by the data providers can be automatically stored and used for statistical modeling purposes related to the data collection instance.

Abstract translation: 用于收集用于统计建模目的的数据的方法可以包括从多个先前定义的用户界面类型中选择至少一个用户界面类型的步骤。 可以为特定数据收集实例定义所选接口类型的参数。 可以输入目标参与者数据。 可以部署基于所选接口类型和定义参数的数据收集接口。 消息可以自动传送到根据目标参与者数据选择的数据提供者。 可以允许数据提供者访问部署的数据收集界面。 数据提供者提供的数据可以自动存储并用于与数据收集实例相关的统计建模。

公开(公告)号：US08521511B2

公开(公告)日：2013-08-27

申请号：US11764294

申请日：2007-06-18

Applicant: Rajesh Balchandran ,  Linda M. Boyer ,  Gregory Purdy

Inventor： Rajesh Balchandran ,  Linda M. Boyer ,  Gregory Purdy

IPC: G06F17/27

CPC classification number: G06F17/278 ,  G06F17/2715 ,  G06F17/2725 ,  G06F17/2785 ,  G06F17/28

Abstract: A method of extracting information from text within a natural language understanding system can include processing a text input through at least one statistical model for each of a plurality of features to be extracted from the text input. For each feature, at least one value can be determined, at least in part, using the statistical model associated with the feature. One value for each feature can be combined to create a complex information target. The complex information target can be output.

Abstract translation: 从自然语言理解系统中的文本提取信息的方法可以包括通过至少一个统计模型处理文本输入，以便从文本输入中提取多个要素中的每一个。 对于每个特征，至少可以使用与特征相关联的统计模型至少部分地确定至少一个值。 可以组合每个功能的一个值来创建复杂的信息目标。 可以输出复杂的信息目标。

公开(公告)号：US07974835B2

公开(公告)日：2011-07-05

申请号：US12112768

申请日：2008-04-30

Applicant: Rajesh Balchandran ,  Linda Boyer

Inventor： Rajesh Balchandran ,  Linda Boyer

IPC: G06F17/27

CPC classification number: G10L15/1822 ,  G10L15/22

Abstract: In a natural language, mixed-initiative system, a method of processing user dialogue can include receiving a user input and determining whether the user input specifies an action to be performed or a token of an action. The user input can be selectively routed to an action interpreter or a token interpreter according to the determining step.

Abstract translation: 以自然语言，混合主动系统，处理用户对话的方法可以包括接收用户输入并确定用户输入是指定要执行的动作还是动作的标记。 可以根据确定步骤将用户输入选择性地路由到动作解释器或令牌解释器。

公开(公告)号：US20080312905A1

公开(公告)日：2008-12-18

申请号：US11764285

申请日：2007-06-18

Applicant: Rajesh Balchandran ,  Linda M. Boyer ,  Gregory Purdy

Inventor： Rajesh Balchandran ,  Linda M. Boyer ,  Gregory Purdy

IPC: G06F17/27

CPC classification number: G06F17/277 ,  G06F17/278

Abstract: A method of processing text within a natural language understanding system can include applying a first tokenization technique to a sentence using a statistical tokenization model. A second tokenization technique using a named entity can be applied to the sentence when the first tokenization technique does not extract a needed token according to a class of the sentence. A token determined according to at least one of the tokenization techniques can be output.

Abstract translation: 一种在自然语言理解系统内处理文本的方法可以包括使用统计标记化模型对句子应用第一标记化技术。 当第一个标记化技术不能根据句子的类提取所需的标记时，使用命名实体的第二个标记化技术可以应用于该句子。 可以输出根据令牌化技术中的至少一个所确定的令牌。

公开(公告)号：US20080310718A1

公开(公告)日：2008-12-18

申请号：US11764294

申请日：2007-06-18

Applicant: Rajesh Balchandran ,  Linda M. Boyer ,  Gregory Purdy

Inventor： Rajesh Balchandran ,  Linda M. Boyer ,  Gregory Purdy

IPC: G06K9/50

CPC classification number: G06F17/278 ,  G06F17/2715 ,  G06F17/2725 ,  G06F17/2785 ,  G06F17/28

Abstract: A method of extracting information from text within a natural language understanding system can include processing a text input through at least one statistical model for each of a plurality of features to be extracted from the text input. For each feature, at least one value can be determined, at least in part, using the statistical model associated with the feature. One value for each feature can be combined to create a complex information target. The complex information target can be output.

Abstract translation: 从自然语言理解系统中的文本提取信息的方法可以包括通过至少一个统计模型处理文本输入，以便从文本输入中提取多个要素中的每一个。 对于每个特征，至少可以使用与特征相关联的统计模型至少部分地确定至少一个值。 可以组合每个功能的一个值来创建复杂的信息目标。 可以输出复杂的信息目标。