公开(公告)号：US20060085414A1

公开(公告)日：2006-04-20

申请号：US10955190

申请日：2004-09-30

申请人： Joyce Chai ,  Pengyu Hong ,  Michelle Zhou

发明人： Joyce Chai ,  Pengyu Hong ,  Michelle Zhou

IPC分类号： G06F17/30

CPC分类号： G06F16/36

摘要： Reference resolution may be modeled as an optimization problem, where certain techniques disclosed herein can identify the most probable references by simultaneously satisfying a plurality of matching constraints, such as semantic, temporal, and contextual constraints. Two structures are generated. The first comprises information describing one or more referring expressions and describing relationships, if any, between the one or more referring expressions. The second comprises information describing one or more referents to which the one or more referring expressions might refer and describing relationships, if any, between the one or more referents. Matching is performed, by using the structures, to match a given one of the one or more referring expressions to at least a given referent. Matching simultaneously satisfies a plurality of matching constraints corresponding to the one or more referring expressions and the one or more referents, and also resolves one or more references by the given referring expression to the at least a given referent.

摘要翻译： 参考分辨率可以被建模为优化问题，其中本文公开的某些技术可以通过同时满足诸如语义，时间和上下文约束的多个匹配约束来识别最可能的参考。 生成两个结构。 第一个包括描述一个或多个引用表达并描述一个或多个引用表达之间的关系（如果有的话）的信息。 第二个包括描述一个或多个参考表达可以引用并描述一个或多个指称之间的关系（如果有的话）的一个或多个指称的信息。 通过使用结构来执行匹配，以将至少一个指定对象中的一个或多个引用表达式中的给定的一个匹配。 同时匹配满足与一个或多个参考表达式和一个或多个指称对应的多个匹配约束，并且还通过给定的参考表达式将一个或多个引用解析为至少给定的指示物。

公开(公告)号：US20100205238A1

公开(公告)日：2010-08-12

申请号：US12367132

申请日：2009-02-06

申请人： Nan Cao ,  David H. Gotz ,  Peter Kissa ,  Shi Xia Liu ,  Jie Lu ,  Wei Hong Qian ,  Zhen Wen ,  Michelle Zhou

发明人： Nan Cao ,  David H. Gotz ,  Peter Kissa ,  Shi Xia Liu ,  Jie Lu ,  Wei Hong Qian ,  Zhen Wen ,  Michelle Zhou

IPC分类号： G06F15/16 ,  G06F17/30

CPC分类号： G06Q10/10 ,  G06Q10/06

摘要： Methods and apparatus are provided for intelligent exploratory visualization and analysis. A semantics-based client-server application architecture is provided that enables interactive visualization and analysis applications over the web. From the client perspective, user activities are observed and the client determines if a sequence of user activities comprises one or more predefined semantics-based user actions. Semantics-based action descriptor are then sent to the server, optionally with any related parameters, and a response is then received from the server. From the server perspective, one or more semantics-based action descriptors are received from the client with an action type selected from a predefined set of types, wherein the semantics-based action descriptors are based on a sequence of activities of a user. The server processes the semantics-based action descriptors and sends a response to the client in response to the one or more semantics-based action descriptors.

摘要翻译： 提供了智能探索可视化和分析的方法和设备。 提供了一种基于语义的客户机 - 服务器应用程序体系结构，可通过Web进行交互式可视化和分析应用程序。 从客户端的角度来看，观察用户活动，并且客户端确定用户活动的序列是否包含一个或多个预定义的基于语义的用户动作。 然后将基于语义的动作描述符发送到服务器，可选地具有任何相关参数，然后从服务器接收响应。 从服务器的角度来看，从客户端接收从预定义的一组类型中选择的动作类型的一个或多个基于语义的动作描述符，其中基于语义的动作描述符基于用户的一系列活动。 服务器处理基于语义的动作描述符，并响应于一个或多个基于语义的动作描述符向客户端发送响应。

公开(公告)号：US20060155673A1

公开(公告)日：2006-07-13

申请号：US11031038

申请日：2005-01-07

申请人： Keith Houck ,  Shimei Pan ,  Siwei Shen ,  Michelle Zhou

发明人： Keith Houck ,  Shimei Pan ,  Siwei Shen ,  Michelle Zhou

IPC分类号： H04Q7/20 ,  H04B7/00

CPC分类号： G06F17/30401 ,  G06F17/30654

摘要： One embodiment of the present method and apparatus for robust input interpretation by conversation systems includes receiving a user request containing at least one un-interpretable term. The present invention conveys the conversation system's interpretation capabilities to the user, for example by suggesting at least one alternative request in context of the un-interpretable user request, where the alternative request is phrased in a manner that is substantially fully interpretable. A user may then select a suggested alternative request or formulate a new request in accordance with knowledge of the conversation system capabilities learned from the conveyed information. In another embodiment, a method may independently (e.g., without user prompting) adapt the un-interpretable user request in accordance with learned information regarding the meaning of any un-interpretable terms in the user request.

摘要翻译： 用于由对话系统进行鲁棒输入解释的本方法和装置的一个实施例包括接收包含至少一个不可解释术语的用户请求。 本发明将对话系统的解释能力传达给用户，例如通过在不可解释的用户请求的上下文中提出至少一个备选请求，其中替代请求以基本上完​​全可解释的方式来表达。 然后，用户可以根据从所传达的信息中学习的会话系统功能的知识，选择建议的备选请求或者制定新的请求。 在另一个实施例中，方法可以独立地（例如，没有用户提示）根据关于用户请求中的任何不可解释术语的含义的学习信息来适配不可解释的用户请求。

公开(公告)号：US20070016540A1

公开(公告)日：2007-01-18

申请号：US11171388

申请日：2005-07-01

申请人： Xiaohua Sun ,  Michelle Zhou

发明人： Xiaohua Sun ,  Michelle Zhou

IPC分类号： G06F15/18

CPC分类号： G06N5/045

摘要： Multimedia user interfaces provide an intelligent interaction paradigm that helps analysts to better formulate, validate and manage analyses hypotheses. Spatial-temporal metaphors are proposed to organize and present requested information, and all the information are gradually accumulated based on analysis flow. The analysis flow and the information flow are tightly coupled together, so that at any given point in the analysis process, the analysts are able to link a hypothesis to the relevant information shown in the information space. The analysts can also relate the information presented to a particular hypothesis and its state.

摘要翻译： 多媒体用户界面提供了一种智能交互范式，可帮助分析人员更好地制定，验证和管理分析假设。 提出了空间隐喻来组织和呈现所请求的信息，并且所有信息都基于分析流程逐渐积累。 分析流程和信息流程紧密耦合在一起，因此在分析过程的任何特定时刻，分析人员都能够将假设与信息空间中显示的相关信息相联系。 分析师还可以将呈现的信息与特定假设及其状态相关联。

公开(公告)号：US20060085387A1

公开(公告)日：2006-04-20

申请号：US10969581

申请日：2004-10-20

申请人： Vikram Aggarwal ,  Michelle Zhou

发明人： Vikram Aggarwal ,  Michelle Zhou

IPC分类号： G06F17/30

CPC分类号： G06F16/00 ,  Y10S707/946

摘要： Improved data content determination techniques are disclosed for use in accordance with information-seeking systems. For example, in one illustrative aspect of the invention, a technique for determining data content for a response to a query comprises obtaining a user query, and dynamically determining data content suitable for generating a response to the query, wherein data content determination is modeled as an optimization operation which attempts to balance context-based selection constraints. Further, the step of dynamically determining data content may further comprise modeling the context-based selection constraints as feature-based metrics. The feature-based metrics may be formulated using contextual information. Still further, the step of dynamically determining data content may further comprise performing the optimization operation such that one or more desirability metrics are maximized and one or more cost metrics are minimized, thus balancing the various constraints.

摘要翻译： 公开了根据信息寻求系统使用的改进的数据内容确定技术。 例如，在本发明的一个说明性方面，用于确定用于对查询的响应的数据内容的技术包括获得用户查询，以及动态地确定适于生成对查询的响应的数据内容，其中数据内容确定被建模为 尝试平衡基于上下文的选择约束的优化操作。 此外，动态确定数据内容的步骤还可以包括将基于上下文的选择约束建模为基于特征的度量。 基于特征的度量可以使用上下文信息来制定。 此外，动态确定数据内容的步骤还可以包括执行优化操作，使得一个或多个期望度量被最大化并且一个或多个成本度量被最小化，从而平衡各种约束。

公开(公告)号：US20050154750A1

公开(公告)日：2005-07-14

申请号：US10758546

申请日：2004-01-14

申请人： Michelle Zhou ,  Min Chen

发明人： Michelle Zhou ,  Min Chen

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30247 ,  Y10S707/913 ,  Y10S707/956 ,  Y10S707/99933 ,  Y10S707/99936

摘要： A technique is provided for generating automated graphics in response to a user request. A measure of similarity between the user request and one or more stored graphics examples is determined. At least one stored graphics example is obtained based on the similarity measure. Graphics are created from the at least one obtained graphics example and the user request.

摘要翻译： 提供了一种用于响应于用户请求产生自动图形的技术。 确定用户请求与一个或多个存储的图形示例之间的相似度的度量。 基于相似性度量获得至少一个存储的图形示例。 从至少一个获得的图形示例和用户请求创建图形。

公开(公告)号：US20070239670A1

公开(公告)日：2007-10-11

申请号：US11763132

申请日：2007-06-14

申请人： Vikram Aggarwal ,  Michelle Zhou

发明人： Vikram Aggarwal ,  Michelle Zhou

IPC分类号： G06F17/30

CPC分类号： G06F17/30 ,  Y10S707/946

摘要： Improved data content determination techniques are disclosed for use in accordance with information-seeking systems. For example, in one illustrative aspect of the invention, a technique for determining data content for a response to a query comprises obtaining a user query, and dynamically determining data content suitable for generating a response to the query, wherein data content determination is modeled as an optimization operation which attempts to balance context-based selection constraints. Further, the step of dynamically determining data content may further comprise modeling the context-based selection constraints as feature-based metrics. The feature-based metrics may be formulated using contextual information. Still further, the step of dynamically determining data content may further comprise performing the optimization operation such that one or more desirability metrics are maximized and one or more cost metrics are minimized, thus balancing the various constraints.

摘要翻译： 公开了根据信息寻求系统使用的改进的数据内容确定技术。 例如，在本发明的一个说明性方面，用于确定用于对查询的响应的数据内容的技术包括获得用户查询，以及动态地确定适于生成对查询的响应的数据内容，其中数据内容确定被建模为 尝试平衡基于上下文的选择约束的优化操作。 此外，动态确定数据内容的步骤还可以包括将基于上下文的选择约束建模为基于特征的度量。 基于特征的度量可以使用上下文信息来制定。 此外，动态确定数据内容的步骤还可以包括执行优化操作，使得一个或多个期望度量被最大化并且一个或多个成本度量被最小化，从而平衡各种约束。

公开(公告)号：US20070088735A1

公开(公告)日：2007-04-19

申请号：US11251686

申请日：2005-10-17

申请人： Vikram Aggarwal ,  Zhen Wen ,  Michelle Zhou

发明人： Vikram Aggarwal ,  Zhen Wen ,  Michelle Zhou

IPC分类号： G06F7/00

CPC分类号： G06F16/9038 ,  G06F16/248 ,  G06F16/3329 ,  G06T11/60

摘要： Improved visual context management techniques are disclosed. By way of example, a technique for updating an existing visual display to incorporate new information comprises obtaining new information requested by a subsequent user query, and dynamically deriving one or more visual transformations for updating at least a portion of the existing display to incorporate the new information, wherein the transformation derivation is modeled as an optimization operation which attempts to balance visual context management constraints and to achieve a desired presentation of intended information.

摘要翻译： 公开了改进的视觉上下文管理技术。 作为示例，用于更新现有视觉显示以合并新信息的技术包括获得由后续用户查询请求的新信息，以及动态地导出用于更新现有显示器的至少一部分的一个或多个视觉变换以包含新的 信息，其中变换导出被建模为尝试平衡视觉上下文管理约束并实现预期信息的期望呈现的优化操作。

公开(公告)号：US20060167835A1

公开(公告)日：2006-07-27

申请号：US11031951

申请日：2005-01-07

申请人： Vikram Aggarwal ,  Michelle Zhou ,  Zhen Wen

发明人： Vikram Aggarwal ,  Michelle Zhou ,  Zhen Wen

IPC分类号： G06F17/30 ,  G06F7/00

CPC分类号： G06F16/40 ,  G06F16/438

摘要： Improved media allocation techniques for use in accordance with information-seeking systems are provided. For example, in one aspect of the invention, a technique for allocating media to present data content for a response to a query comprises the following steps/operations. Data content suitable for generating a response to the query is determined. One or more media for presenting at least a portion of the response (e.g., at least a portion of the intended data content) are dynamically allocated. Media allocation is modeled as an optimization operation which attempts to balance context-based allocation constraints. The optimization operation may also attempt to achieve the desired presentation of intended data content.

摘要翻译： 提供了根据信息搜索系统使用的改进的媒体分配技术。 例如，在本发明的一个方面，一种用于分配媒体以呈现用于对查询的响应的数据内容的技术包括以下步骤/操作。 确定适于产生对查询的响应的数据内容。 用于呈现响应的至少一部分的一个或多个媒体（例如，预期数据内容的至少一部分）被动态分配。 媒体分配被建模为尝试平衡基于上下文的分配约束的优化操作。 优化操作也可以尝试实现期望的数据内容的呈现。