专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明授权

US08266078B2 Platform for learning based recognition research 有权
标题翻译：基于学习的平台识别研究
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。

82. 发明申请

US20120213372A1 METHOD AND DEVICE FOR OBTAINING SECURITY KEY IN RELAY SYSTEM 有权
标题翻译：用于获取继电器系统中的安全钥匙的方法和装置
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。

83. 发明申请

US20120143795A1 CROSS-TRACE SCALABLE ISSUE DETECTION AND CLUSTERING 有权
标题翻译：跨轨迹可扩展问题检测和聚类
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。

84. 发明授权

US07953279B2 Combining online and offline recognizers in a handwriting recognition system 有权
标题翻译：将在线和离线识别器结合在手写识别系统中
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。

85. 发明申请

US20100163316A1 Handwriting Recognition System Using Multiple Path Recognition Framework 审中-公开
标题翻译：使用多路径识别框架的手写识别系统
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。

86. 发明授权

US07561739B2 Analyzing scripts and determining characters in expression recognition 有权
标题翻译：分析脚本并确定表达式识别中的字符
公开(公告)号：US07561739B2
公开(公告)日：2009-07-14
申请号：US11155748
申请日：2005-06-20
申请人： Mingqing Xu , Yu Zou , Lei Huang , Jian-Lai Zhou , Xianfang Wang , Xiaohui Hou , Dongmei Zhang , Zhouchen Lin , Jian Wang
发明人： Mingqing Xu , Yu Zou , Lei Huang , Jian-Lai Zhou , Xianfang Wang , Xiaohui Hou , Dongmei Zhang , Zhouchen Lin , Jian Wang
IPC分类号： G06K9/18
CPC分类号： G06K9/222
摘要： A mechanism for recognizing and inputting handwritten mathematical expressions into a computer by providing part of a multi-path framework is described. The part of the multi-path framework includes a subscript/superscript analysis and character determination component that is designed to identify subscript and superscript elements. A method for analyzing a handwritten mathematical expression includes receiving a symbols corresponding to handwritten mathematical expression input strokes, identifying subscript and/or superscript structures, and determining a character for each symbol of the set. A graph of vertexes and edges may be created based upon the set of symbols and the graph may be searched to determine optimized candidates.
摘要翻译：描述了通过提供一部分多路径框架来将手写数学表达式识别并输入计算机的机制。多路径框架的一部分包括下标/上标分析和字符确定组件，其被设计为识别下标和上标元素。一种用于分析手写数学表达式的方法包括接收对应于手写数学表达式输入笔画的符号，识别下标和/或上标结构，以及确定该组的每个符号的字符。可以基于符号集创建顶点和边缘的图形，并且可以搜索图形以确定优化的候选。

87. 发明申请

US20090007271A1 Identifying attributes of aggregated data 有权
标题翻译：识别聚合数据的属性
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。

88. 发明申请

US20090003658A1 Digital ink-based search 有权
标题翻译：数字墨水搜索
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。

89. 发明授权

US07460472B2 System and method for transmitting information in a communication network 有权
标题翻译：用于在通信网络中发送信息的系统和方法
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。

90. 发明申请

US20080219556A1 Radical-Based HMM Modeling for Handwritten East Asian Characters 有权
标题翻译：手写东亚人物基于激进的HMM建模
公开(公告)号：US20080219556A1
公开(公告)日：2008-09-11
申请号：US11682722
申请日：2007-03-06
申请人： Shi Han , Yu Zou , Ming Chang , Peng Liu , Yi-Jian Wu , Lei Ma , Frank Soong , Dongmei Zhang , Jian Wang
发明人： Shi Han , Yu Zou , Ming Chang , Peng Liu , Yi-Jian Wu , Lei Ma , Frank Soong , Dongmei Zhang , Jian Wang
IPC分类号： G06K9/18
CPC分类号： G06K9/00879
摘要： Exemplary methods, systems, and computer-readable media for developing, training and/or using models for online handwriting recognition of characters are described. An exemplary method for building a trainable radical-based HMM for use in character recognition includes defining radical nodes, where a radical node represents a structural element of an character, and defining connection nodes, where a connection node represents a spatial relationship between two or more radicals. Such a method may include determining a number of paths in the radical-based HMM using subsequence direction histogram vector (SDHV) clustering and determining a number of states in the radical-based HMM using curvature scale space-based (CSS) corner detection.
摘要翻译：描述用于开发，训练和/或使用用于字符的在线手写识别的模型的示例性方法，系统和计算机可读介质。用于构建用于字符识别的可训练基于激进的基于HMM的示例性方法包括定义基本节点，其中基本节点表示字符的结构元素，并且定义连接节点，其中连接节点表示两个或更多个之间的空间关系激进分子这种方法可以包括使用子序列方向直方图向量（SDHV）聚类确定基于激进的HMM中的路径数量，并使用基于曲率空间的（CSS）角检测确定基于激进的HMM中的状态数。

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