公开(公告)号：US20120278346A1

公开(公告)日：2012-11-01

申请号：US13095415

申请日：2011-04-27

申请人： Shi Han ,  Yingnong Dang ,  Song Ge ,  Dongmei Zhang

发明人： Shi Han ,  Yingnong Dang ,  Song Ge ,  Dongmei Zhang

IPC分类号： G06F17/30

CPC分类号： G06F17/30539 ,  G06F17/30306 ,  H04L67/10

摘要： A system for frequent pattern mining uses two layers of processing: a plurality of computing nodes, and a plurality of processors within each computing node. Within each computing node, the data set against which the frequent pattern mining is to be performed is stored in shared memory, accessible concurrently by each of the processors. The search space is partitioned among the computing nodes, and sub-partitioned among the processors of each computing node. If a processor completes its sub-partition, it requests another sub-partition. The partitioning and sub-partitioning may be performed dynamically, and adjusted in real time.

摘要翻译： 用于频繁模式挖掘的系统使用两层处理：多个计算节点和每个计算节点内的多个处理器。 在每个计算节点内，将要执行频繁模式挖掘的数据集存储在共享存储器中，由每个处理器并发访问。 搜索空间在计算节点之间划分，并在每个计算节点的处理器之间进行子分区。 如果处理器完成其子分区，则它请求另一个子分区。 可以动态执行分区和子分区，并实时调整。

公开(公告)号：US20120251006A1

公开(公告)日：2012-10-04

申请号：US13526236

申请日：2012-06-18

申请人： Yu Zou ,  Ming Chang ,  Shi Han ,  Dongmei Zhang ,  Jian Wang

发明人： Yu Zou ,  Ming Chang ,  Shi Han ,  Dongmei Zhang ,  Jian Wang

IPC分类号： G06K9/46

CPC分类号： G06K9/00416 ,  G06K2209/011

摘要： An exemplary method for online character recognition of characters includes acquiring time sequential, online ink data for a handwritten character, conditioning the ink data to produce conditioned ink data where the conditioned ink data includes information as to writing sequence of the handwritten character and extracting features from the conditioned ink data where the features include a tangent feature, a curvature feature, a local length feature, a connection point feature and an imaginary stroke feature. Such a method may determine neighborhoods for ink data and extract features for each neighborhood. An exemplary character recognition system may use various exemplary methods for training and character recognition.

摘要翻译： 用于字符的在线字符识别的示例性方法包括获取用于手写字符的时间顺序在线墨水数据，调节墨水数据以产生经调节的墨水数据，其中经调节的墨水数据包括关于写入手写字符的序列的信息并从 调节的油墨数据，其中特征包括切线特征，曲率特征，局部长度特征，连接点特征和假想笔画特征。 这种方法可以确定墨水数据的邻域并提取每个邻域的特征。 示例性字符识别系统可以使用用于训练和字符识别的各种示例性方法。

公开(公告)号：US08266078B2

公开(公告)日：2012-09-11

申请号：US12366655

申请日：2009-02-06

申请人： Yu Zou ,  Hao Wei ,  Gong Cheng ,  Dongmei Zhang ,  Jian Wang

发明人： Yu Zou ,  Hao Wei ,  Gong Cheng ,  Dongmei Zhang ,  Jian Wang

IPC分类号： G06F15/18 ,  G06K9/62 ,  G06K9/46

CPC分类号： G06K9/6253 ,  G10L15/063

摘要： A method for researching and developing a recognition model in a computing environment, including gathering one or more data samples from one or more users in the computing environment into a training data set used for creating the recognition model, receiving one or more training parameters defining a feature extraction algorithm configured to analyze one or more features of the training data set, a classifier algorithm configured to associate the features to a template set, a selection of a subset of the training data set, a type of the data samples, or combinations thereof, creating the recognition model based on the training parameters, and evaluating the recognition model.

摘要翻译： 一种用于在计算环境中研究和开发识别模型的方法，包括将来自所述计算环境中的一个或多个用户的一个或多个数据样本收集到用于创建所述识别模型的训练数据集中，接收定义一个或多个训练参数的训练参数 特征提取算法，其被配置为分析训练数据集的一个或多个特征，分类器算法，被配置为将特征与模板集合相关联，训练数据集的子集的选择，数据样本的类型或其组合 ，基于训练参数创建识别模型，并对识别模型进行评估。

公开(公告)号：US20120213372A1

公开(公告)日：2012-08-23

申请号：US13463444

申请日：2012-05-03

申请人： Dongmei Zhang ,  Xiaoyu Bi ,  Aiqin Zhang

发明人： Dongmei Zhang ,  Xiaoyu Bi ,  Aiqin Zhang

IPC分类号： H04L9/08 ,  H04B7/14

CPC分类号： H04W12/04 ,  H04L2463/061 ,  H04W84/047

摘要： A method and a device for obtaining a security key in a relay system are disclosed in the embodiment of the present invention. A node in the relay system obtains an initial key, according to the initial key, the node obtains a root key of an air interface protection key between the node and another node that is directly adjacent to the node, and according to the root key, the node obtains the air interface protection key between the node and said another node that is directly adjacent to the node. Therefore, according to the initial key, each lower-level node obtains a root key of an air interface protection key between each lower-level node, so that data of a UE on a Un interface link may be respectively protected, that is, each active UE has a set of security parameters on the Un interface link, and effective security protection is performed on data on each segment of an air interface.

摘要翻译： 在本发明的实施例中公开了一种在中继系统中获得安全密钥的方法和装置。 中继系统中的节点根据初始密钥获取初始密钥，节点获取节点与节点直接相邻的另一个节点之间的空中接口保护密钥的根密钥，根据根密钥， 该节点获得节点与直接相邻节点的另一个节点之间的空中接口保护密钥。 因此，根据初始密钥，每个下级节点获得每个下级节点之间的空中接口保护密钥的根密钥，从而可以分别保护Un接口链路上的UE的数据，即每个 主动UE在Un接口链路上具有一组安全参数，对空中接口的每个段上的数据执行有效的安全保护。

公开(公告)号：US20120143795A1

公开(公告)日：2012-06-07

申请号：US12960015

申请日：2010-12-03

申请人： Shi Han ,  Yingnong Dang ,  Shuo-Hsien (Stephen) Hsiao ,  Dongmei Zhang

发明人： Shi Han ,  Yingnong Dang ,  Shuo-Hsien (Stephen) Hsiao ,  Dongmei Zhang

IPC分类号： G06F11/07 ,  G06F15/18

CPC分类号： G06F11/079 ,  G06F11/3409 ,  G06F11/3447 ,  H04L41/0636 ,  H04L41/16

摘要： Techniques and systems for cross-trace scalable issue detection and clustering that scale-up trace analysis for issue detection and root-cause clustering using a machine learning based approach are described herein. These techniques enable a scalable performance analysis framework for computing devices addressing issue detection, which is designed as a multiple scale feature for learning based issue detection, and root cause clustering. In various embodiments the techniques employ a cross-trace similarity model, which is defined to hierarchically cluster problems detected in the learning based issue detection via butterflies of trigram stacks. The performance analysis framework is scalable to manage millions of traces, which include high problem complexity.

摘要翻译： 本文描述了用于交叉跟踪可扩展问题检测和聚类的技术和系统，其中使用基于机器学习的方法对用于问题检测和根本原因聚类进行放大跟踪分析。 这些技术使得可扩展的性能分析框架用于处理问题检测的计算设备，其被设计为用于基于学习的问题检测的多尺度特征以及根本原因聚类。 在各种实施例中，该技术采用交叉跟踪相似性模型，其被定义为通过三元组栈的蝴蝶在基于学习的问题检测中分层检测集群问题。 性能分析框架是可扩展的，以管理数百万条跟踪，其中包括高问题复杂性。

公开(公告)号：US07953279B2

公开(公告)日：2011-05-31

申请号：US11823644

申请日：2007-06-28

申请人： Xinjian Chen ,  Dongmei Zhang ,  Yu Zou ,  Ming Chang ,  Shi Han ,  Jian Wang

发明人： Xinjian Chen ,  Dongmei Zhang ,  Yu Zou ,  Ming Chang ,  Shi Han ,  Jian Wang

IPC分类号： G06K9/00 ,  G06F17/00

CPC分类号： G06K9/00973 ,  G06K9/6292 ,  G06K9/6296

摘要： Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.

摘要翻译： 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常，该组合提高了整体识别精度。 在一个方面，单独执行在线和离线识别以获得用于候选者（假设）的在线和离线角色级识别分数。 基于统计分析的组合算法，AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如，HMM识别器可以生成用于构建激进图形的在线激进分数，然后使用离线激进识别分数进行重新分类。 然后，搜索折叠图中的路径以提供组合识别结果，例如对应于具有最高分数的路径。

公开(公告)号：US20100163316A1

公开(公告)日：2010-07-01

申请号：US12345668

申请日：2008-12-30

申请人： Ming Chang ,  Shi Han ,  Dongmei Zhang ,  Yu Zou ,  Xinjian Chen

发明人： Ming Chang ,  Shi Han ,  Dongmei Zhang ,  Yu Zou ,  Xinjian Chen

IPC分类号： G08C21/00

CPC分类号： G06K9/00416 ,  G06K9/00429 ,  G16C20/70

摘要： Described is a multi-path handwriting recognition framework based upon stroke segmentation, symbol recognition, two-dimensional structure analysis and semantic structure analysis. Electronic pen input corresponding to handwritten input (e.g., a chemical expression) is recognized and output via a data structure, which may include multiple recognition candidates. A recognition framework performs stroke segmentation and symbol recognition on the input, and analyzes the structure of the input to output the data structure corresponding to recognition results. For chemical expressions, the structural analysis may perform a conditional sub-expression analysis for inorganic expressions, or organic bond detection, connection relationship analysis, organic atom determination and/or conditional sub-expression analysis for organic expressions. The structural analysis also performs subscript, superscript analysis and character determination. Further analysis may be performed, e.g., chemical valence analysis and/or semantic structure analysis.

摘要翻译： 描述了基于笔划分割，符号识别，二维结构分析和语义结构分析的多路径手写识别框架。 对应于手写输入（例如，化学表达）的电子笔输入通过可包括多个识别候选的数据结构被识别和输出。 识别框架对输入进行笔划分割和符号识别，并分析输入结构以输出与识别结果相对应的数据结构。 对于化学表达式，结构分析可以对有机表达进行无机表征或有机键检测，连接关系分析，有机原子测定和/或条件子表达分析的条件子表达分析。 结构分析还执行下标，上标分析和字符测定。 可以进行进一步分析，例如化学价态分析和/或语义结构分析。

公开(公告)号：US20090007271A1

公开(公告)日：2009-01-01

申请号：US11823546

申请日：2007-06-28

申请人： Song Huang ,  Yingnong Dang ,  Xiaohui Hou ,  Dongmei Zhang ,  Jian Wang

发明人： Song Huang ,  Yingnong Dang ,  Xiaohui Hou ,  Dongmei Zhang ,  Jian Wang

IPC分类号： G06F7/04

CPC分类号： G06F21/57 ,  G06F17/30864

摘要： A method for identifying a portion of aggregated software security data is described. The method includes accessing aggregated data associated with software vulnerabilities retrieved from a plurality of on-line sources. The method further includes searching a portion of the aggregated data for an exact match to a particular attribute of the data and searching the portion of the aggregated data for one or more partial matches associated with the particular attribute. The method also includes associating the portion of the data with the particular attribute based on the exact match of one or more of the partial matches.

摘要翻译： 描述了用于识别聚合的软件安全数据的一部分的方法。 该方法包括访问与从多个在线源检索的软件漏洞相关联的聚合数据。 所述方法还包括搜索所述聚合数据的一部分以与所述数据的特定属性精确匹配，并且搜索所述聚合数据的所述部分与所述特定属性相关联的一个或多个部分匹配。 该方法还包括基于一个或多个部分匹配的精确匹配将数据的该部分与特定属性相关联。

公开(公告)号：US20090003658A1

公开(公告)日：2009-01-01

申请号：US11821837

申请日：2007-06-26

申请人： Dongmei Zhang ,  Xiaohui Hou ,  Yingjun Qiu ,  Jian Wang

发明人： Dongmei Zhang ,  Xiaohui Hou ,  Yingjun Qiu ,  Jian Wang

IPC分类号： G06K9/00

CPC分类号： G06K9/00402 ,  G06F17/30253

摘要： Described is searching directly based on digital ink input to provide a result set of one or more items. Digital ink input (e.g., a handwritten character, sketched shape, gesture, drawing picture) is provided to a search engine and interpreted thereby, with a search result (or results) returned. Different kinds of digital ink can be used as search input without changing modes. The search engine includes a unified digital ink recognizer that recognizes digital ink as a character or another type of digital ink. When the recognition result is a character, the character may be used in a keyword search to find one or more corresponding non-character items, e.g., from a data store. When the recognition result is a non-character item, the non-character item is provided as the result, without keyword searching. The search result may appear as one or more item representations, such as in a user interface result panel.

摘要翻译： 描述的是基于数字墨水输入直接搜索以提供一个或多个项目的结果集。 将数字墨水输入（例如，手写字符，草图形状，手势，绘图图像）提供给搜索引擎，并由此返回搜索结果（或结果）。 不同类型的数字墨水可以用作搜索输入而不改变模式。 搜索引擎包括将数字墨水识别为字符或另一类型的数字墨水的统一数字墨水识别器。 当识别结果是字符时，可以在关键词搜索中使用该字符来查找例如来自数据存储的一个或多个相应的非字符项。 当识别结果是非字符项时，作为结果提供非字符项，而不进行关键字搜索。 搜索结果可以显示为一个或多个项目表示，例如在用户界面结果面板中。

公开(公告)号：US07460472B2

公开(公告)日：2008-12-02

申请号：US10683352

申请日：2003-10-14

申请人： Huihua Le ,  Haitao Wu ,  Yuehui Jin ,  Dongmei Zhang ,  Jian Ma

发明人： Huihua Le ,  Haitao Wu ,  Yuehui Jin ,  Dongmei Zhang ,  Jian Ma

IPC分类号： H04J1/16

CPC分类号： H04W80/06 ,  H04L1/0001 ,  H04L1/0002 ,  H04L1/1628 ,  H04L1/1867 ,  H04L1/187 ,  H04L1/20 ,  H04W28/0242

摘要： A method and system for transmitting information between a sending means and a receiving means using packets for information transmission. The receipt of transmitted packets is acknowledged and unacknowledged packets are retransmitted from the sending means. The amount of transmitted unacknowledged information or the number of consecutive unacknowledged packets is detected, and the reason for information or packet loss is determined based on the amount of transmitted unacknowledged information or the number of consecutive unacknowledged packets. This amount is compared with a path maximum transmission unit (PMTU) to determine the reason for loss. A single or small number of unacknowledged packets is determined to be a result of Bit Error Rate (BER), whereas a larger number of consecutive unacknowledged packets may be determined to be congestion. Congestion control parameters are kept unchanged when the reason for loss is caused by Bit Error Rate (BER), whereas control parameters are changed when the reason for loss is congestion.

摘要翻译： 一种用于在发送装置和接收装置之间使用用于信息传输的分组来发送信息的方法和系统。 发送的分组的接收被确认，并且从发送装置重传未确认的分组。 检测到发送的未确认信息的数量或连续的未确认分组的数量，并且基于发送的未确认信息的量或连续的未确认分组的数量来确定信息或分组丢失的原因。 将该量与路径最大传输单元（PMTU）进行比较，以确定丢失的原因。 一个或多个未确认的分组被确定为误码率（BER）的结果，而较大数量的连续未确认分组可被确定为拥塞。 当丢包原因是由误码率（BER）引起的，拥塞控制参数保持不变，而丢失原因拥塞时控制参数会发生变化。