公开(公告)号：US06728690B1

公开(公告)日：2004-04-27

申请号：US09448408

申请日：1999-11-23

申请人： Christopher A. Meek ,  John C. Platt

发明人： Christopher A. Meek ,  John C. Platt

IPC分类号： G06N302

CPC分类号： G06K9/6281 ,  G06N3/0472 ,  G06N3/08

摘要： A training system for a classifier utilizes both a back-propagation system to iteratively modify parameters of functions which provide raw output indications of desired categories, wherein the parameters are modified based on a weighted decay, and a probability determining system with further parameters that are determined during iterative training. A margin error metric may be combined with weight decay, and a sigmoid is used to calibrate the raw outputs to probability percentages for each category. A method of training such a system involves gathering a training set of inputs and desired corresponding outputs. Classifier parameters are then initialized and an error margin is calculated with respect to the classifier parameters. A weight decay is then used to adjust the parameters. After a selected number of times through the training set, the parameters are deemed in final form, and an optimization routine is used to derive a set of probability transducer parameters for use in calculating the probable classification for each input.

摘要翻译： 用于分类器的训练系统利用反向传播系统来迭代地修改提供期望类别的原始输出指示的功能的参数，其中参数基于加权衰减进行修改，以及具有确定的其他参数的概率确定系统 在迭代训练期间。 边际误差度量可能与重量衰减相结合，S形用于将原始输出校准为每个类别的概率百分比。 训练这种系统的方法包括收集一组训练输入和期望的相应输出。 然后，分类器参数被初始化，并且相对于分类器参数计算误差容限。 然后使用重量衰减来调整参数。 在通过训练集合选定的次数之后，参数被认为是最终形式，并且使用优化例程来导出用于计算每个输入的可能分类的一组概率传感器参数。

公开(公告)号：US06380929B1

公开(公告)日：2002-04-30

申请号：US08717435

申请日：1996-09-20

申请人： John C. Platt

发明人： John C. Platt

IPC分类号： G09G500

CPC分类号： G06F3/0488

摘要： A method and system are provided for drawing or writing using an input device in computer systems. The system provides an absolute-coordinate drawing mode, in which the user may draw written strokes to which the computer system display is responsive, and a relative-coordinate repositioning mode, in which the user may figuratively “pick up the pen” and reposition the beginning of a following written stroke. The system enters the drawing mode in response to a user command, and remains in the drawing mode in response to continued written strokes. The system enters the cursor mode after a selected time period occurs with no written strokes, or in response to other user commands. In the drawing mode, a coordinate system for the touchpad is mapped to a coordinate system for a selected window on the display. The mapping is selected so that an initial position of a written stroke in the window corresponds to a final position selected during the cursor mode, so that the user is able to reposition the input device when it has (or is about to) “run off the edge” of an input tablet which is relatively smaller than the display. The system uses either a resistive touchpad input tablet, or a capacitive touchpad input tablet in conjunction with a passive stylus input device having a flexible conductive writing tip. The system alternatively provides a signature mode, in which the user is able to make a simple drawing, such as a handwritten signature.

摘要翻译： 提供了一种使用计算机系统中的输入设备进行绘图或书写的方法和系统。 该系统提供绝对坐标绘制模式，其中用户可以绘制计算机系统显示器所响应的写入笔画，以及相对坐标重新定位模式，其中用户可以形象地“拿起笔”并重新定位 开始以下笔画。 系统响应于用户命令进入绘图模式，并响应于继续写入笔画而保持在绘图模式。 在没有写入笔画或响应其他用户命令的选定时间段之后，系统进入光标模式。 在绘图模式中，用于触摸板的坐标系被映射到显示器上所选窗口的坐标系。 选择该映射，使得窗口中的写入笔画的初始位置对应于在光标模式期间选择的最终位置，使得用户能够在输入设备（或将要）运行时重新定位输入设备 输入图形输入板的边缘“，其比显示器小。 该系统使用电阻式触摸板输入平板电脑或电容式触摸板输入平板电脑与具有柔性导电写入尖端的被动触控笔输入装置。 系统交替地提供签名模式，其中用户能够进行简单的绘图，例如手写签名。

公开(公告)号：US6148104A

公开(公告)日：2000-11-14

申请号：US231911

申请日：1999-01-14

申请人： Chung-Ning Wang ,  John C. Platt ,  Nada P. Matic

发明人： Chung-Ning Wang ,  John C. Platt ,  Nada P. Matic

IPC分类号： G06K9/22 ,  G06K9/18

CPC分类号： G06K9/00436 ,  G06F3/018 ,  G06K9/00416 ,  G06K2209/011

摘要： A method for incremental recognition of ideographic handwriting comprises in order the steps of: (1) entering in a natural stroke order at least one stroke of an ideographic character from a computer entry tablet; (2) providing the at least one stroke to an incremental character recognizer, which produces a hypothesis list of at least one candidate character; (3) displaying a hypothesis list of candidate characters containing the at least one stroke; (4) selecting a correct character from among the candidate characters on the hypothesis list if it a correct character appears thereon; (5) entering in natural stroke order at least one additional stroke of the ideographic character from the computer entry tablet if no candidate character is a correct character; (6) providing the additional stroke(s) to the incremental character recognizer, which produces an updated hypothesis list; (7) displaying the updated hypothesis list of candidate characters containing every stroke; (8) selecting a correct character from among the candidate characters on the updated hypothesis list if it a correct character appears thereon; and (9) repeating steps (5) through (8) until a correct character is selected from the updated hypothesis list.

公开(公告)号：US09141704B2

公开(公告)日：2015-09-22

申请号：US11427291

申请日：2006-06-28

申请人： Christopher A. Meek ,  Eric J. Horvitz ,  Joshua T. Goodman ,  Gary W. Flake ,  Oliver Hurst-Hiller ,  Anoop Gupta ,  Ramez Naam ,  Kenneth A. Moss ,  William H. Gates, III ,  John C. Platt ,  Trenholme J. Griffin ,  Bradly A. Brunell

发明人： Christopher A. Meek ,  Eric J. Horvitz ,  Joshua T. Goodman ,  Gary W. Flake ,  Oliver Hurst-Hiller ,  Anoop Gupta ,  Ramez Naam ,  Kenneth A. Moss ,  William H. Gates, III ,  John C. Platt ,  Trenholme J. Griffin ,  Bradly A. Brunell

IPC分类号： G06F17/30 ,  G06Q50/00

CPC分类号： G06F17/30867 ,  G06Q50/01

摘要： Architecture that monitors interaction data (e.g., search queries, query results and click-through rates), and provides users with links to other users that fall into similar categories with respect to the foregoing monitored activities (e.g., providing links to individuals and groups that share common interests and/or profiles). A search engine can be interactively coupled with one or more social networks, and that maps individuals and/or groups within respective social networks to subsets of categories associated with searches. A database stores mapped information which can be continuously updated and reorganized as links within the system mapping become stronger or weaker. The architecture can comprise a social network system that includes a database for mapping search-related information to an entity of a social network, and a search component for processing a search query for search results and returning a link to an entity of a social network based on the search query.

摘要翻译： 监视交互数据（例如搜索查询，查询结果和点击率）的架构，并向用户提供与上述受监视活动相类似的类别的其他用户的链接（例如，提供与个人和组的链接 分享共同的兴趣和/或简介）。 搜索引擎可以与一个或多个社交网络交互地耦合，并且将各个社交网络内的个人和/或组映射到与搜索相关联的类别的子集。 数据库存储可以不断更新和重新组织的映射信息，因为系统映射中的链接变得更强或更弱。 该架构可以包括社交网络系统，其包括用于将搜索相关信息映射到社交网络的实体的数据库，以及用于处理搜索结果的搜索查询并返回到基于社交网络的实体的链接的搜索组件 在搜索查询上。

公开(公告)号：US08799190B2

公开(公告)日：2014-08-05

申请号：US13163010

申请日：2011-06-17

申请人： Jack W. Stokes ,  Nikos Karampatziakis ,  John C. Platt ,  Anil Francis Thomas ,  Adrian M. Marinescu

发明人： Jack W. Stokes ,  Nikos Karampatziakis ,  John C. Platt ,  Anil Francis Thomas ,  Adrian M. Marinescu

IPC分类号： G06F21/56 ,  G06K9/62

CPC分类号： G06K9/62 ,  G06F21/56 ,  G06F21/563 ,  G06K9/6224 ,  Y10S707/952

摘要： A reliable automated malware classification approach with substantially low false positive rates is provided. Graph-based local and/or global file relationships are used to improve malware classification along with a feature selection algorithm. File relationships such as containing, creating, copying, downloading, modifying, etc. are used to assign malware probabilities and simultaneously reduce the false positive and false negative rates on executable files.

摘要翻译： 提供了一种可靠的自动恶意软件分类方法，具有极低的假阳性率。 基于图形的本地和/或全局文件关系用于改进恶意软件分类以及特征选择算法。 使用诸如包含，创建，复制，下载，修改等的文件关系来分配恶意软件概率，并同时减少可执行文件上的假正负率。

公开(公告)号：US20140067368A1

公开(公告)日：2014-03-06

申请号：US13597277

申请日：2012-08-29

申请人： Wen-tau Yih ,  Geoffrey G. Zweig ,  John C. Platt

发明人： Wen-tau Yih ,  Geoffrey G. Zweig ,  John C. Platt

IPC分类号： G06F17/27

CPC分类号： G06F17/2795 ,  G06F16/3338 ,  G06F17/2785

摘要： A document-term matrix may be generated based on a corpus. A term representation matrix may be generated based on modifying a plurality of elements of the document-term matrix based on antonym information included in the corpus. Similarities may be determined based on a plurality of elements of the term representation matrix.

摘要翻译： 可以基于语料库生成文档术语矩阵。 可以基于基于语料库中包含的反义词信息修改文档项矩阵的多个元素来生成术语表示矩阵。 可以基于术语表示矩阵的多个元素来确定相似度。

公开(公告)号：US20130275436A1

公开(公告)日：2013-10-17

申请号：US13444717

申请日：2012-04-11

申请人： Surajit Chaudhuri ,  Lev Novik ,  John C. Platt

发明人： Surajit Chaudhuri ,  Lev Novik ,  John C. Platt

IPC分类号： G06F17/30

CPC分类号： G06F16/319 ,  G06F16/245

摘要： Various embodiments promote the discoverability of data that can be contained within a database. In one or more embodiments, data within a database is organized in a structure having a schema. The structure and data can be processed in a manner that renders one or more pseudo-documents each of which constitutes a sub-structure that can be indexed. Once produced and indexed, the pseudo-documents constitute a set of searchable objects each of which relationally points back to its associated structure within the database. Searches can now be performed against the pseudo-documents which, in turn, returns a set of search results. The set of search results can include multiple sub-sets of pseudo-documents, each sub-set of which is associated with a different structure.

摘要翻译： 各种实施例提高了可以包含在数据库内的数据的可发现性。 在一个或多个实施例中，数据库内的数据被组织在具有模式的结构中。 结构和数据可以以呈现一个或多个伪文档的方式进行处理，每个伪文档构成可被索引的子结构。 一旦生成和索引，伪文档构成一组可搜索的对象，每个可搜索对象在数据库中相互关联地指向其相关联的结构。 现在可以针对伪文档执行搜索，这些伪文档又返回一组搜索结果。 该组搜索结果可以包括多个伪文档子集，每个子​​集的每个子集与不同的结构相关联。

公开(公告)号：US20120323829A1

公开(公告)日：2012-12-20

申请号：US13163010

申请日：2011-06-17

申请人： Jack W. Stokes ,  Nikos Karampatziakis ,  John C. Platt ,  Anil Francis Thomas ,  Adrian M. Marinescu

发明人： Jack W. Stokes ,  Nikos Karampatziakis ,  John C. Platt ,  Anil Francis Thomas ,  Adrian M. Marinescu

IPC分类号： G06N5/04 ,  G06F15/18

CPC分类号： G06K9/62 ,  G06F21/56 ,  G06F21/563 ,  G06K9/6224 ,  Y10S707/952

摘要： A reliable automated malware classification approach with substantially low false positive rates is provided. Graph-based local and/or global file relationships are used to improve malware classification along with a feature selection algorithm. File relationships such as containing, creating, copying, downloading, modifying, etc. are used to assign malware probabilities and simultaneously reduce the false positive and false negative rates on executable files.

摘要翻译： 提供了一种可靠的自动恶意软件分类方法，具有极低的假阳性率。 基于图形的本地和/或全局文件关系用于改进恶意软件分类以及特征选择算法。 使用诸如包含，创建，复制，下载，修改等的文件关系来分配恶意软件概率，并同时减少可执行文件上的假正负率。

公开(公告)号：US20110314001A1

公开(公告)日：2011-12-22

申请号：US12818227

申请日：2010-06-18

申请人： Charles Edward Jacobs ,  John C. Platt ,  Johnson Tan Apacible

发明人： Charles Edward Jacobs ,  John C. Platt ,  Johnson Tan Apacible

IPC分类号： G06F17/30

CPC分类号： G06F16/951 ,  G06F16/3338 ,  G06F16/86

摘要： A method described herein includes an act of receiving a query from a user, wherein the query is configured to search over a plurality of documents belonging to a particular domain. The method also includes an act of providing data to the user for display on a display screen of a computing apparatus, wherein the data is provided based at least in part upon a statistical analysis undertaken with respect to structured data pertaining to the particular domain, wherein the structured data is based at least in part upon data included in the plurality of documents.

摘要翻译： 本文所述的方法包括从用户接收查询的动作，其中，所述查询被配置为搜索属于特定域的多个文档。 该方法还包括向用户提供数据以在计算设备的显示屏幕上显示的动作，其中至少部分地基于针对特定域的结构化数据进行的统计分析来提供数据，其中 结构化数据至少部分地基于包括在多个文档中的数据。

公开(公告)号：US20100192222A1

公开(公告)日：2010-07-29

申请号：US12358246

申请日：2009-01-23

申请人： Jack W. Stokes ,  John C. Platt ,  Jonathan M. Keller ,  Joseph L. Faulhaber ,  Anil Francis Thomas ,  Adrian M. Marinescu ,  Marius G. Gheorghescu ,  George Chicioreanu

发明人： Jack W. Stokes ,  John C. Platt ,  Jonathan M. Keller ,  Joseph L. Faulhaber ,  Anil Francis Thomas ,  Adrian M. Marinescu ,  Marius G. Gheorghescu ,  George Chicioreanu

IPC分类号： G06F21/00 ,  G06G7/62 ,  G06F17/30 ,  G06F9/455

CPC分类号： G06F21/563

摘要： A method of identifying a malware file using multiple classifiers is disclosed. The method includes receiving a file at a client computer. The file includes static metadata. A set of metadata classifier weights are applied to the static metadata to generate a first classifier output. A dynamic classifier is initiated to evaluate the file and to generate a second classifier output. The method includes automatically identifying the file as potential malware based on at least the first classifier output and the second classifier output.

摘要翻译： 公开了使用多个分类器识别恶意软件文件的方法。 该方法包括在客户端计算机上接收文件。 该文件包括静态元数据。 将一组元数据分类器权重应用于静态元数据以生成第一个分类器输出。 启动动态分类器来评估文件并生成第二个分类器输出。 该方法包括至少基于第一分类器输出和第二分类器输出将文件自动识别为潜在的恶意软件。