-
公开(公告)号:US07822699B2
公开(公告)日:2010-10-26
申请号:US11290076
申请日:2005-11-30
申请人: Sanjeev Katariya , Qi Steven Yao , Jun Liu , William D. Ramsey , Jianfeng Gao
发明人: Sanjeev Katariya , Qi Steven Yao , Jun Liu , William D. Ramsey , Jianfeng Gao
CPC分类号: G06F17/30663
摘要: Provided is an adaptive semantic reasoning engine that receives a natural language query, which may contain one or more contexts. The query can be broken down into tokens or a set of tokens. A task search can be performed on the token or token set(s) to classify a particular query and/or context and retrieve one or more tasks. The token or token set(s) can be mapped into slots to retrieve one or more task result. A slot filling goodness may be determined that can include scoring each task search result and/or ranking the results in a different order than the order in which the tasks were retrieved. The token or token set(s), retrieved tasks, slot filling goodness, natural language query, context, search result score and/or result ranking can be feedback to the reasoning engine for further processing and/or machine learning.
摘要翻译: 提供了一种自适应语义推理引擎,其接收可以包含一个或多个上下文的自然语言查询。 该查询可以分为令牌或一组令牌。 可以对令牌或令牌集执行任务搜索以对特定查询和/或上下文进行分类并检索一个或多个任务。 令牌或令牌集可被映射到插槽中以检索一个或多个任务结果。 可以确定插槽填充质量,其可以包括对每个任务搜索结果进行评分和/或以与检索任务的顺序不同的顺序对结果进行排序。 令牌或令牌集,检索任务,插槽填充良品,自然语言查询,上下文,搜索结果分数和/或结果排名可以反馈到推理引擎用于进一步处理和/或机器学习。
-
公开(公告)号:US20070203869A1
公开(公告)日:2007-08-30
申请号:US11363747
申请日:2006-02-28
申请人: William D. Ramsey , Sanjeev Katariya , Jun Liu , Jianfeng Gao , Qi Yao , Zhanliang Chen
发明人: William D. Ramsey , Sanjeev Katariya , Jun Liu , Jianfeng Gao , Qi Yao , Zhanliang Chen
IPC分类号: G06N7/02
CPC分类号: G06F17/279
摘要: An adaptive shared infrastructure that can be easily utilized to enable natural interaction between user(s) and machine system(s) is provided. Additionally, the novel innovation can provide interactive techniques that produce accurate intent-to-action mapping based upon a user input. Further, the innovation can provide novel mechanism by which assets (e.g., documents, actions) can be authored. The authoring mechanisms can enable the generation of learning models such that the system can infer a user intent based at least in part upon an analysis of a user input. In response thereto, the system can discover an asset, or group of assets based upon the inference. Moreover, the innovation can provide a natural language interface that learns and/or adapts based upon one or more user input(s), action(s), and/or state(s).
摘要翻译: 提供了可以容易地利用以实现用户和机器系统之间的自然交互的自适应共享基础设施。 此外,新颖的创新可以提供基于用户输入产生准确的意图 - 动作映射的交互技术。 此外,创新可以提供可以创作资产(例如,文档,动作)的新颖机制。 创作机制可以实现学习模型的产生,使得系统至少部分地基于对用户输入的分析来推断用户意图。 作为响应,系统可以基于推论发现资产或资产组。 此外,创新可以提供基于一个或多个用户输入,动作和/或状态来学习和/或适应的自然语言界面。
-
3.
公开(公告)号:US07933914B2
公开(公告)日:2011-04-26
申请号:US11294581
申请日:2005-12-05
CPC分类号: G06F17/30864
摘要: A task system and method are provided. The system provides an automated approach for task creation, maintenance and/or execution. The system includes a browser that receives search results and at least one task associated with a query from a search engine. The system further includes a browser helper object that binds to the browser at runtime. The browser helper object provides information associated with a user's action with respect to the search results and/or at least one task. The information can be employed as feedback to update model(s) (e.g., query classification model(s) and/or slot-filling model(s)) of a semantic reasoning component that retrieves task based, at least in part, upon user query(ies).
摘要翻译: 提供了一个任务系统和方法。 该系统为任务创建,维护和/或执行提供了一种自动化方法。 该系统包括接收搜索结果的浏览器和与搜索引擎的查询相关联的至少一个任务。 该系统还包括在运行时绑定到浏览器的浏览器助手对象。 浏览器辅助对象提供与用户对于搜索结果和/或至少一个任务相关联的操作的信息。 该信息可以用作反馈,以至少部分地基于用户来更新检索任务的语义推理组件的模型(例如,查询分类模型和/或插槽填充模型) 查询(ies)。
-
公开(公告)号:US07783588B2
公开(公告)日:2010-08-24
申请号:US11253866
申请日:2005-10-19
CPC分类号: G06N99/005 , G06F9/453
摘要: A context modeling architecture that includes a context representation portion, which adapted to represent context as features, is provided. The features are specifiable at runtime of an application including the context representation portion.
摘要翻译: 提供了一种包括上下文表示部分的上下文建模体系结构,其适用于将上下文表示为特征。 这些特征在包括上下文表示部分的应用的运行时是可指定的。
-
公开(公告)号:US07328199B2
公开(公告)日:2008-02-05
申请号:US11246847
申请日:2005-10-07
IPC分类号: G06N5/00
CPC分类号: G06F17/2785
摘要: The subject disclosure pertains to systems and methods for performing natural language processing in which tokens are mapped to task slots. The system includes a mapper component that generates a lattice representing possible interpretations of the tokens, a decoder component that creates a ranked list of paths traversing the lattice, a scorer component that generates scores used to rank paths and post-processing components that format the paths for use by other software. Each of these components may be independent, such that the component may be modified or replaced without affecting the remaining components. This allows a variety of different mathematical models and algorithms to be tested or deployed without requiring changes to the remainder of the system.
摘要翻译: 本发明涉及用于执行令牌被映射到任务时隙的自然语言处理的系统和方法。 该系统包括生成表示可能的令牌解释的格的映射器组件,创建遍历格子的路径的排序列表的解码器组件,产生用于对路径进行排序的得分器组件,以及后处理格式化路径的组件 供其他软件使用。 这些组件中的每一个可以是独立的,使得可以修改或替换组件而不影响剩余的组件。 这允许测试或部署各种不同的数学模型和算法,而不需要更改系统的其余部分。
-
公开(公告)号:US20070124263A1
公开(公告)日:2007-05-31
申请号:US11290076
申请日:2005-11-30
申请人: Sanjeev Katariya , Qi Yao , Jun Liu , William Ramsey , Jianfeng Gao
发明人: Sanjeev Katariya , Qi Yao , Jun Liu , William Ramsey , Jianfeng Gao
IPC分类号: G06F15/18
CPC分类号: G06F17/30663
摘要: Provided is an adaptive semantic reasoning engine that receives a natural language query, which may contain one or more contexts. The query can be broken down into tokens or a set of tokens. A task search can be performed on the token or token set(s) to classify a particular query and/or context and retrieve one or more tasks. The token or token set(s) can be mapped into slots to retrieve one or more task result. A slot filling goodness may be determined that can include scoring each task search result and/or ranking the results in a different order than the order in which the tasks were retrieved. The token or token set(s), retrieved tasks, slot filling goodness, natural language query, context, search result score and/or result ranking can be feedback to the reasoning engine for further processing and/or machine learning.
摘要翻译: 提供了一种自适应语义推理引擎,其接收可以包含一个或多个上下文的自然语言查询。 该查询可以分为令牌或一组令牌。 可以对令牌或令牌集执行任务搜索以对特定查询和/或上下文进行分类并检索一个或多个任务。 令牌或令牌集可被映射到插槽中以检索一个或多个任务结果。 可以确定插槽填充质量,其可以包括对每个任务搜索结果进行评分和/或以与检索任务的顺序不同的顺序对结果进行排序。 令牌或令牌集,检索任务,插槽填充良品,自然语言查询,上下文,搜索结果分数和/或结果排名可以反馈到推理引擎用于进一步处理和/或机器学习。
-
公开(公告)号:US20070094185A1
公开(公告)日:2007-04-26
申请号:US11246847
申请日:2005-10-07
申请人: William Ramsey , Jianfeng Gao , Sanjeev Katariya
发明人: William Ramsey , Jianfeng Gao , Sanjeev Katariya
IPC分类号: G06N5/00
CPC分类号: G06F17/2785
摘要: The subject disclosure pertains to systems and methods for performing natural language processing in which tokens are mapped to task slots. The system includes a mapper component that generates a lattice representing possible interpretations of the tokens, a decoder component that creates a ranked list of paths traversing the lattice, a scorer component that generates scores used to rank paths and post-processing components that format the paths for use by other software. Each of these components may be independent, such that the component may be modified or replaced without affecting the remaining components. This allows a variety of different mathematical models and algorithms to be tested or deployed without requiring changes to the remainder of the system.
摘要翻译: 本发明涉及用于执行令牌被映射到任务时隙的自然语言处理的系统和方法。 该系统包括生成表示可能的令牌解释的格的映射器组件,创建遍历格子的路径的排序列表的解码器组件,产生用于对路径进行排序的得分器组件,以及后处理格式化路径的组件 供其他软件使用。 这些组件中的每一个可以是独立的,使得可以修改或替换组件而不影响剩余组件。 这允许测试或部署各种不同的数学模型和算法,而不需要更改系统的其余部分。
-
公开(公告)号:US20070112546A1
公开(公告)日:2007-05-17
申请号:US11253866
申请日:2005-10-19
申请人: William Ramsey , Jianfeng Gao , Sanjeev Katariya
发明人: William Ramsey , Jianfeng Gao , Sanjeev Katariya
IPC分类号: G06F17/10
CPC分类号: G06N99/005 , G06F9/453
摘要: A context modeling architecture that includes a context representation portion, which adapted to represent context as features, is provided. The features are specifiable at runtime of an application including the context representation portion.
摘要翻译: 提供了一种包括上下文表示部分的上下文建模体系结构,其适用于将上下文表示为特征。 这些特征在包括上下文表示部分的应用的运行时是可指定的。
-
公开(公告)号:US07996783B2
公开(公告)日:2011-08-09
申请号:US11367292
申请日:2006-03-02
IPC分类号: G06F3/048
CPC分类号: G06F17/30893
摘要: A task framework and a semantic reasoning engine are combined to provide a scalable mechanism for dealing with extremely large numbers of widgets, allowing users to both find a widget and automatically fill-in whatever functionality is available on the widget. Calling applications are employed to obtain task information from each widget. The calling application also receives user queries that can be resolved by a widget. A task reasoning process based on an adaptive semantic reasoning engine utilizes the task information to select a widget best suited to respond to a user's query. The task reasoning process can also be employed to determine “best-guess” slot filling of the selected widget. The calling application can then invoke the selected widget and, if available, fill appropriate slots with information to facilitate user interaction with the selected widget. Instances can be client- and/or server-side based.
摘要翻译: 组合任务框架和语义推理引擎以提供可扩展的机制来处理极大数量的小部件,从而允许用户找到小部件,并自动填充小部件上可用的任何功能。 采用呼叫应用程序从每个小部件获取任务信息。 呼叫应用程序还接收可由窗口小部件解析的用户查询。 基于自适应语义推理引擎的任务推理过程利用任务信息来选择最适合于响应用户查询的小部件。 任务推理过程也可以用于确定所选小部件的“最佳猜测”插槽填充。 呼叫应用程序然后可以调用所选择的窗口小部件,并且如果可用,则填充具有信息的适当插槽以便于用户与所选择的窗口小部件交互。 实例可以是客户端和/或服务器端。
-
公开(公告)号:US07624099B2
公开(公告)日:2009-11-24
申请号:US11249623
申请日:2005-10-13
CPC分类号: G06F17/30666 , G06F17/278 , G06F17/30616 , Y10S707/99933 , Y10S707/99934
摘要: Word-breaking of a query from a client machine in a client-server environment includes determining whether to use a first word breaking module operable with a client machine in the client-server environment and/or a second word breaking module operable with a server in the client-server environment.
摘要翻译: 在客户机 - 服务器环境中从客户端机器断开查询包括确定是否使用可与客户机 - 服务器环境中的客户端机器一起操作的第一单词断开模块和/或可与服务器一起操作的第二单词断开模块 客户端 - 服务器环境。
-
-
-
-
-
-
-
-
-