专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07941382B2 Method of classifying and active learning that ranks entries based on multiple scores, presents entries to human analysts, and detects and/or prevents malicious behavior 有权
标题翻译：基于多个分数对条目进行分类和主动学习的方法，向人类分析人员提供条目，并检测和/或防止恶意行为
公开(公告)号：US07941382B2
公开(公告)日：2011-05-10
申请号：US11871587
申请日：2007-10-12
申请人： Jack W. Stokes , John C. Platt , Michael Shilman , Joseph L. Kravis
发明人： Jack W. Stokes , John C. Platt , Michael Shilman , Joseph L. Kravis
IPC分类号： G06E1/00
CPC分类号： G06F15/16
摘要： A malicious behavior detection/prevention system, such as an intrusion detection system, is provided that uses active learning to classify entries into multiple classes. A single entry can correspond to either the occurrence of one or more events or the non-occurrence of one or more events. During a training phase, entries are automatically classified into one of multiple classes. After classifying the entry, a generated model for the determined class is utilized to determine how well an entry corresponds to the model. Ambiguous classifications along with entries that do not fit the model well for the determined class are selected for labeling by a human analyst. The selected entries are presented to a human analyst for labeling. These labels are used to further train the classifier and the models. During an evaluation phase, entries are automatically classified using the trained classifier and a policy associated with determined class is applied.
摘要翻译：提供了一种恶意行为检测/预防系统，例如入侵检测系统，其使用主动学习将条目分类到多个类中。单个条目可以对应于一个或多个事件的发生或一个或多个事件的不发生。在训练阶段，条目自动分为多个类别之一。在对条目进行分类之后，使用所确定的类的生成模型来确定条目对应于模型的良好程度。选择不确定的分类以及不符合确定类别的模型的条目，由人类分析师进行标签。选定的条目提交给人类分析人员进行标签。这些标签用于进一步训练分类器和型号。在评估阶段，使用训练有素的分类器对条目进行自动分类，并应用与确定类相关联的策略。

2. 发明申请

US20080195931A1 Parsing of ink annotations 审中-公开
标题翻译：解析墨迹注释
公开(公告)号：US20080195931A1
公开(公告)日：2008-08-14
申请号：US11589028
申请日：2006-10-27
申请人： Sashi Raghupathy , Paul A. Viola , Michael Shilman , Xin Wang
发明人： Sashi Raghupathy , Paul A. Viola , Michael Shilman , Xin Wang
IPC分类号： G06F17/00
CPC分类号： G06K9/00402
摘要： Annotation recognition and parsing is accomplished by first recognizing and grouping shapes such that relationships between the annotations and the underlying text and/or images can be determined. The recognition and grouping is followed by categorization of recognized annotations according to predefined types. The classification may be according to functionality, relation to content, and the like. In a third phase, the annotations are anchored to the underlying text or images they are found to be related to.
摘要翻译：注释识别和解析是通过首先识别和分组形状来实现的，使得可以确定注释和底层文本和/或图像之间的关系。识别和分组之后是根据预定义类型对所识别的注释进行分类。分类可以根据功能，与内容的关系等。在第三阶段，注释被锚定到被发现与之相关的底层文本或图像。

3. 发明申请

US20070282538A1 CONTINUOUS INFERENCE FOR SEQUENCE DATA 有权
标题翻译：序列数据的连续干扰
公开(公告)号：US20070282538A1
公开(公告)日：2007-12-06
申请号：US11421585
申请日：2006-06-01
申请人： Mukund Narasimhan , Paul Viola , Michael Shilman
发明人： Mukund Narasimhan , Paul Viola , Michael Shilman
IPC分类号： G06F19/00
CPC分类号： G06F19/22
摘要： Dynamic inference is leveraged to provide online sequence data labeling. This provides real-time alternatives to current methods of inference for sequence data. Instances estimate an amount of uncertainty in a prediction of labels of sequence data and then dynamically predict a label when an uncertainty in the prediction is deemed acceptable. The techniques utilized to determine when the label can be generated are tunable and can be personalized for a given user and/or a system. Employed decoding techniques can be dynamically adjusted to tradeoff system resources for accuracy. This allows for fine tuning of a system based on available system resources. Instances also allow for online inference because the inference does not require knowledge of a complete set of sequence data.
摘要翻译：利用动态推理来提供在线序列数据标签。这提供了对序列数据的推理的当前方法的实时替代。实例估计序列数据标签的预测中的不确定性量，然后当预测中的不确定性被认为是可接受的时候动态地预测标签。用于确定何时可以生成标签的技术是可调谐的，并且可以针对给定的用户和/或系统进行个性化。采用解码技术可以动态调整，以便对系统资源进行权衡以获得准确性。这允许基于可用的系统资源对系统进行微调。实例还允许在线推理，因为推理不需要知道一套完整的序列数据。

4. 发明申请

US20050177783A1 Systems and methods that utilize a dynamic digital zooming interface in connection with digital inking 有权
标题翻译：利用与数字墨迹相关的动态数字缩放界面的系统和方法
公开(公告)号：US20050177783A1
公开(公告)日：2005-08-11
申请号：US10775710
申请日：2004-02-10
申请人： Maneesh Agrawala , Michael Shilman
发明人： Maneesh Agrawala , Michael Shilman
IPC分类号： G06F17/21 , G06F3/048 , G06F17/00
CPC分类号： G06F3/04883 , G06F17/241 , G06F17/242 , G06F2203/04806
摘要： The present invention relates to systems and methods that facilitate annotating digital documents (e.g., digital inking) with devices such as Tablet PCs, PDAs, cell phones, and the like. The systems and methods provide for multi-scale navigation during document annotating via a space-scale framework that fluidly generates and moves a zoom region relative to a document and writing utensil. A user can employ this zoom region to annotate various portions of the document at a size comfortable to the user and suitably scaled to the device display. The space-scale framework enables dynamic navigation, wherein the zoom region location, size, and shape, for example, can automatically adjust as the user annotates. When the user finishes annotating the document, the annotations scale back with the zoom region to original page size. These novel features provide advantages over conventional techniques that do not contemplate multi-scale navigation during document annotating.
摘要翻译：本发明涉及利用诸如Tablet PC，PDA，手机等的装置来便于注释数字文档（例如，数字墨迹）的系统和方法。系统和方法通过空间尺度框架提供文档注释期间的多尺度导航，该框架流体地生成并相对于文档和书写工具移动缩放区域。用户可以使用该缩放区域以用户舒适的尺寸来标注文档的各个部分，并适当地缩放到设备显示。空间尺度框架能够实现动态导航，其中例如，缩放区域位置，大小和形状可以随着用户注释而自动调整。当用户完成对文档的注释时，注释随缩放区域缩小到原始页面大小。这些新颖特征提供了优于在文件注释期间不考虑多尺度导航的常规技术的优点。

5. 发明申请

US20050044106A1 Electronic ink processing 有权
标题翻译：电子油墨加工
公开(公告)号：US20050044106A1
公开(公告)日：2005-02-24
申请号：US10644900
申请日：2003-08-21
申请人： Richard Duncan , Bodin Dresevic , Jamie Wakeam , Herry Sutanto , Sashi Reghupathy , Timothy Kannapel , Zoltan Szilagyi , Jerome Turner , Todd Landstad , Thomas Wick , Alex Simmons , Peter Engrav , Kevin Paulson , Kentaro Urata , Steve Dodge , David Bargeron , Michael Shilman
发明人： Richard Duncan , Bodin Dresevic , Jamie Wakeam , Herry Sutanto , Sashi Reghupathy , Timothy Kannapel , Zoltan Szilagyi , Jerome Turner , Todd Landstad , Thomas Wick , Alex Simmons , Peter Engrav , Kevin Paulson , Kentaro Urata , Steve Dodge , David Bargeron , Michael Shilman
IPC分类号： G06F3/033 , G06F13/00 , G06F17/00 , G06F17/27 , G06K9/00 , G06K9/22
CPC分类号： G06K9/222 , G06F17/211 , G06F17/241 , G06F17/242 , G06K9/00402 , G06K9/00463 , G06K9/2081 , G06K2209/01 , Y10S707/99945 , Y10S707/99948
摘要： Systems, methods, and computer-readable media for making rich, flexible, and more natural electronic ink annotations in an electronic document include creating a first context node associated with a first portion of a base portion of an electronic document; creating a second context node associated with an annotation to the base portion; and linking the second context node with the first context node.
摘要翻译：用于在电子文档中制作丰富，灵活和更自然的电子墨水注释的系统，方法和计算机可读介质包括创建与电子文档的基本部分的第一部分相关联的第一上下文节点; 创建与所述基本部分的注释相关联的第二上下文节点; 以及将所述第二上下文节点与所述第一上下文节点相链接。

6. 发明授权

US07551187B2 Systems and methods that utilize a dynamic digital zooming interface in connection with digital inking 有权
标题翻译：利用与数字墨迹相关的动态数字缩放界面的系统和方法
公开(公告)号：US07551187B2
公开(公告)日：2009-06-23
申请号：US10775710
申请日：2004-02-10
申请人： Maneesh Agrawala , Michael Shilman
发明人： Maneesh Agrawala , Michael Shilman
IPC分类号： G09G5/00 , G06F17/00 , G06F17/20
CPC分类号： G06F3/04883 , G06F17/241 , G06F17/242 , G06F2203/04806
摘要： The present invention relates to systems and methods that facilitate annotating digital documents (e.g., digital inking) with devices such as Tablet PCs, PDAs, cell phones, and the like. The systems and methods provide for multi-scale navigation during document annotating via a space-scale framework that fluidly generates and moves a zoom region relative to a document and writing utensil. A user can employ this zoom region to annotate various portions of the document at a size comfortable to the user and suitably scaled to the device display. The space-scale framework enables dynamic navigation, wherein the zoom region location, size, and shape, for example, can automatically adjust as the user annotates. When the user finishes annotating the document, the annotations scale back with the zoom region to original page size. These novel features provide advantages over conventional techniques that do not contemplate multi-scale navigation during document annotating.
摘要翻译：本发明涉及利用诸如Tablet PC，PDA，手机等的装置来便于注释数字文档（例如，数字墨迹）的系统和方法。系统和方法通过空间尺度框架提供文档注释期间的多尺度导航，该框架流体地生成并相对于文档和书写工具移动缩放区域。用户可以使用该缩放区域以用户舒适的尺寸来标注文档的各个部分，并适当地缩放到设备显示。空间尺度框架能够实现动态导航，其中例如，缩放区域位置，大小和形状可以随着用户注释而自动调整。当用户完成对文档的注释时，注释随缩放区域缩小到原始页面大小。这些新颖特征提供了优于在文件注释期间不考虑多尺度导航的常规技术的优点。

7. 发明申请

US20090099988A1 ACTIVE LEARNING USING A DISCRIMINATIVE CLASSIFIER AND A GENERATIVE MODEL TO DETECT AND/OR PREVENT MALICIOUS BEHAVIOR 有权
标题翻译：主动学习使用分类分类器和生成模型来检测和/或防止恶意行为
公开(公告)号：US20090099988A1
公开(公告)日：2009-04-16
申请号：US11871587
申请日：2007-10-12
申请人： Jack W. Stokes , John C. Platt , Michael Shilman , Joseph L. Kravis
发明人： Jack W. Stokes , John C. Platt , Michael Shilman , Joseph L. Kravis
IPC分类号： G06F15/18
CPC分类号： G06F15/16
摘要： A malicious behavior detection/prevention system, such as an intrusion detection system, is provided that uses active learning to classify entries into multiple classes. A single entry can correspond to either the occurrence of one or more events or the non-occurrence of one or more events. During a training phase, entries are automatically classified into one of multiple classes. After classifying the entry, a generated model for the determined class is utilized to determine how well an entry corresponds to the model. Ambiguous classifications along with entries that do not fit the model well for the determined class are selected for labeling by a human analyst The selected entries are presented to a human analyst for labeling. These labels are used to further train the classifier and the models. During an evaluation phase, entries are automatically classified using the trained classifier and a policy associated with determined class is applied.
摘要翻译：提供了一种恶意行为检测/预防系统，例如入侵检测系统，其使用主动学习将条目分类到多个类中。单个条目可以对应于一个或多个事件的发生或一个或多个事件的不发生。在训练阶段，条目自动分为多个类别之一。在对条目进行分类之后，使用所确定的类的生成模型来确定条目对应于模型的良好程度。选择不确定的分类以及不符合确定类别的模型的条目，由人类分析人员进行标签。选定的条目将提交给人类分析人员进行标签。这些标签用于进一步训练分类器和型号。在评估阶段，使用训练有素的分类器对条目进行自动分类，并应用与确定类相关联的策略。

8. 发明申请

US20060280370A1 Application of grammatical parsing to visual recognition tasks 有权
公开(公告)号：US20060280370A1
公开(公告)日：2006-12-14
申请号：US11151708
申请日：2005-06-13
申请人： Paul Viola , Michael Shilman
发明人： Paul Viola , Michael Shilman
IPC分类号： G06K9/72
CPC分类号： G06K9/726 , G06F17/271 , G06K2209/01
摘要： Image recognition is utilized to facilitate in scoring parse trees for two-dimensional recognition tasks. Trees and subtrees are rendered as images and then utilized to determine parsing scores. Other instances of the subject invention can incorporate additional features such as stroke curvature and/or nearby white space as rendered images as well. Geometric constraints can also be employed to increase performance of a parsing process, substantially improving parsing speed, some even resolvable in polynomial time. Additional performance enhancements can be achieved in yet other instances of the subject invention by employing constellations of integral images and/or integral images of document features.

9. 发明申请

US20060271580A1 Grouping lines in freeform handwritten text 有权
标题翻译：分组线自由形式的手写文本
公开(公告)号：US20060271580A1
公开(公告)日：2006-11-30
申请号：US11141682
申请日：2005-05-30
申请人： Ming Ye , Herry Sutanto , Sashi Raghupathy , Chengyang Li , Michael Shilman
发明人： Ming Ye , Herry Sutanto , Sashi Raghupathy , Chengyang Li , Michael Shilman
IPC分类号： G06F7/00
CPC分类号： G06K9/00416
摘要： Techniques for efficiently and accurately organizing freeform handwriting into lines. A global cost function is employed to find the simplest partitioning of electronic ink strokes into line groups that also maximize the “goodness” of the resulting lines and the consistency of their configuration. The “goodness” of a line may be based upon its linear regression error and the horizontal and vertical compactness of the strokes making up the line. The line consistency configuration for a grouping of strokes is measured by the angle difference between neighboring groups. The global cost function also takes into account the complexity of the stroke partitioning, measured by the number of lines into which the strokes are grouped. An initial grouping of strokes is made, and the cost for this initial grouping is determined. Alternate groupings of the initial stroke grouping are then generated. The global cost of each of these alternate stroke groupings is then calculated, and the stroke grouping that produces the largest global cost decrease from the global cost of the original grouping is selected. The alternate grouping creation, cost determination and evaluation, and grouping selection process then is repeated until the global cost for new grouping alternates no longer decreases.
摘要翻译：高效，准确地组织自由形成笔迹的技术。采用全球成本函数来找到电子墨水笔划到线路组中最简单的划分，这也使得所得到的线条的“良好”和其配置的一致性最大化。线的“好”可以基于其线性回归误差和构成线的笔画的水平和垂直紧密度。一组笔画的线一致性配置是通过相邻组之间的角度差来测量的。全局成本函数还考虑到笔划分割的复杂程度，通过划分笔划的行数来衡量。进行笔划的初始分组，确定该初始分组的成本。然后生成初始笔划分组的替代分组。然后计算每个这些交替笔划组的全球成本，并且选择产生最大全局成本的笔划组，从原始分组的全局成本中减去。然后重复替代分组创建，成本确定和评估以及分组选择过程，直到新分组交替的全球成本不再降低。

10. 发明申请

US20060078202A1 Handwriting layout analysis of freeform digital ink input 有权
公开(公告)号：US20060078202A1
公开(公告)日：2006-04-13
申请号：US11281462
申请日：2005-11-18
申请人： Michael Shilman , Zile Wei , Yu Zou , Patrice Simard , Sashi Raghupathy , F. Jones , Charlton Lui , Jian Wang
发明人： Michael Shilman , Zile Wei , Yu Zou , Patrice Simard , Sashi Raghupathy , F. Jones , Charlton Lui , Jian Wang
IPC分类号： G06K9/18
CPC分类号： G06K9/00409 , G06K9/222
摘要： Electronic ink layout analysis systems and methods provide flexibility and efficiency in organizing, analyzing, and processing digital ink. These layout analysis systems and methods allow users substantial freedom in entering electronic ink into a pen-based computer system. Using these systems and methods, a user's input digital ink is not constrained by requirements that a user write in a specific screen orientation, that a user write in one specific orientation on all portions of a page, or that a user write using a specific minimum or maximum sized stroke. Rather, the systems and methods freely allow the user to write anywhere on a given page, in any orientation or size, while still enabling effective and efficient handwriting recognition and other processing of the input digital ink.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式