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

US06563952B1 Method and apparatus for classification of high dimensional data 失效
标题翻译：高维数据分类方法和装置
公开(公告)号：US06563952B1
公开(公告)日：2003-05-13
申请号：US09420252
申请日：1999-10-18
申请人： Anurag Srivastava , G. D. Ramkumar , Vineet Singh , Sanjay Ranka
发明人： Anurag Srivastava , G. D. Ramkumar , Vineet Singh , Sanjay Ranka
IPC分类号： G06K962
CPC分类号： G06K9/6276
摘要： The present invention is an apparatus and method for classifying high-dimensional sparse datasets. A raw data training set is flattened by converting it from categorical representation to a boolean representation. The flattened data is then used to build a class model on which new data not in the training set may be classified. In one embodiment, the class model takes the form of a decision tree, and large itemsets and cluster information are used as attributes for classification. In another embodiment, the class model is based on the nearest neighbors of the data to be classified. An advantage of the invention is that, by flattening the data, classification accuracy is increased by eliminating artificial ordering induced on the attributes. Another advantage is that the use of large itemsets and clustering increases classification accuracy.
摘要翻译：本发明是用于对高维稀疏数据集进行分类的装置和方法。原始数据训练集通过将其从分类表示转换为布尔表示而被平坦化。然后，使用平坦化的数据来构建一个类别模型，在该类模型中，不在训练集中的新数据可以被分类。在一个实施例中，类模型采用决策树的形式，并且使用大的项目集和集群信息作为分类的属性。在另一个实施例中，类模型基于要分类的数据的最近邻。本发明的优点在于，通过平坦化数据，通过消除对属性引起的人为排序来增加分类精度。另一个优点是使用大项集和聚类提高了分类精度。

2. 发明授权

US07269586B1 Patient rule induction method on large disk resident data sets and parallelization thereof 有权
标题翻译：大盘驻留数据集的病人规则感应方法及其并行化
公开(公告)号：US07269586B1
公开(公告)日：2007-09-11
申请号：US09470444
申请日：1999-12-22
申请人： Anurag Srivastava , Vineet Singh
发明人： Anurag Srivastava , Vineet Singh
IPC分类号： G06F17/30 , G06F7/00 , G06F17/60
CPC分类号： G06F17/30595 , G06F17/30592 , G06F19/00 , G06Q50/22 , G06Q50/24 , Y10S707/99935 , Y10S707/99936
摘要： The present invention relates to analysis of large, disk resident data sets using a Patient Rule Induction Method (PRIM) in a computer system wherein a relational data table is initially received. The relational data table includes continuous attributes, discrete attributes, a matter parameter and a cost attribute. The cost attribute represents cost output values based on continuous attribute values and discrete attribute values as inputs. A hyper-rectangle is then formed which encloses a multi-dimensional space defined by the continuous attribute values and the discrete attribute values. The continuous attribute values and the discrete attribute values are represented as points within the multi-dimensional space. A plurality of points along edges of the hyper-rectangle are then removed based on an average of the cost output value from the plurality of points until a count of the points enclosed within the hyper-rectangle equals the meta parameter. Discrete attribute values and continuous attribute values which were removed from the hyper-rectangle are next added along edges of the hyper-rectangle until a sum of the cost output value over the multi-dimensional space enclosed by the hyper-rectangle changes. In a further embodiment a parallel architecture computer system calculates the cost attribute average values over the plurality of points enclosed by the hyper-rectangle in parallel. The invention analyzes large disk resident data sets without having to load the data set into main memory and can be practiced on a parallel computer architecture or a symmetric multi-processor architecture to improve performance.
摘要翻译：本发明涉及在计算机系统中使用患者规则诱导方法（PRIM）分析大的盘驻留数据集，其中最初接收关系数据表。关系数据表包括连续属性，离散属性，事物参数和成本属性。成本属性表示基于连续属性值和离散属性值作为输入的成本输出值。然后形成超矩形，其包围由连续属性值和离散属性值定义的多维空间。连续属性值和离散属性值表示为多维空间内的点。然后根据多个点的成本输出值的平均值去除超矩形边沿的多个点，直到包含在超矩形内的点的计数等于元参数。从超矩形移除的离散属性值和连续属性值接下来沿着超矩形的边缘添加，直到由超矩形包围的多维空间的成本输出值的总和发生变化。在另一实施例中，并行架构计算机系统并行计算由超矩形包围的多个点上的成本属性平均值。本发明分析大盘驻留数据集，而不必将数据集加载到主存储器中，并且可以在并行计算机体系结构或对称多处理器架构上实践以提高性能。

3. 发明授权

US6055539A Method to reduce I/O for hierarchical data partitioning methods 失效
标题翻译：降低分层数据分区方法的I / O的方法
公开(公告)号：US6055539A
公开(公告)日：2000-04-25
申请号：US884080
申请日：1997-06-27
申请人： Vineet Singh , Anurag Srivastava
发明人： Vineet Singh , Anurag Srivastava
IPC分类号： G06F17/30
CPC分类号： G06F17/30961 , Y10S707/99943
摘要： A method and system for generating a decision-tree classifier from a training set of records, independent of the system memory size. The method includes the steps of: generating an attribute list for each attribute of the records, sorting the attribute lists for numeric attributes, and generating a decision tree by repeatedly partitioning the records using the attribute lists. For each node, split points are evaluated to determine the best split test for partitioning the records at the node. Preferably, a gini index and class histograms are used in determining the best splits. The gini index indicates how well a split point separates the records while the class histograms reflect the class distribution of the records at the node. Also, a hash table is built as the attribute list of the split attribute is divided among the child nodes, which is then used for splitting the remaining attribute lists of the node. The method reduces I/O read time by combining the read for partitioning the records at a node with the read required for determining the best split test for the child nodes. Further, it requires writes of the records only at one out of n levels of the decision tree where n.gtoreq.2. Finally, a novel data layout on disk minimizes disk seek time. The I/O optimizations work in a general environment for hierarchical data partitioning. They also work in a multi-processor environment. After the generation of the decision tree, any prior art pruning methods may be used for pruning the tree.
摘要翻译：一种用于从训练集记录中生成决策树分类器的方法和系统，与系统存储器大小无关。该方法包括以下步骤：为记录的每个属性生成属性列表，对数字属性的属性列表进行排序，以及通过使用属性列表重复分割记录来生成决策树。对于每个节点，分析点进行评估，以确定分区节点上的记录的最佳分割测试。优选地，使用基尼系数索引和类别直方图来确定最佳分割。 gini指数表示分割点将记录分离成多少，而类直方图反映了节点上记录的类分布。此外，由于分割属性的属性列表在子节点之间划分，因此构建了哈希表，然后用于分割节点的剩余属性列表。该方法通过将用于分割节点上的记录的读取与为确定子节点的最佳分割测试所需的读取相结合来减少I / O读取时间。此外，它需要在n> / = 2的决策树的n个级别中的一个层次上写入记录。最后，磁盘上的一个新颖的数据布局最大限度地减少了磁盘查找时间。 I / O优化适用于分层数据分区的通用环境。它们还可以在多处理器环境中工作。在生成决策树之后，可以使用任何现有技术的修剪方法来修剪树。

4. 发明授权

US08826408B2 Consolidating disparate cloud service data and behavior based on trust relationships between cloud services 有权
标题翻译：根据云服务之间的信任关系巩固不同的云服务数据和行为
公开(公告)号：US08826408B2
公开(公告)日：2014-09-02
申请号：US13483177
申请日：2012-05-30
申请人： Abhijit Deshmukh , Anurag Srivastava
发明人： Abhijit Deshmukh , Anurag Srivastava
IPC分类号： G06F21/41 , H04L29/06
CPC分类号： H04L63/0815
摘要： A method for consolidating cloud service data and behaviors can begin with the compilation of user/service membership data that associates requesting entities with subscribed cloud services by a trusted cloud service consolidator. A federated trust library housing inter-service trust information for the cloud services contained in the user/service membership data can be created. In response to a service request from a requesting entity, trusted secondary cloud services can be identified for the requesting entity. Identification of the trusted secondary cloud services can be based upon trust factors synthesized from data contained in the federated trust library. Data satisfying the service request and associated behaviors from each trusted secondary cloud service can then be consolidated into a unified data structure. A behavior can be an executable action supported by a trusted secondary cloud service. The unified data structure can be conveyed to the requesting entity in a service response.
摘要翻译：整合云服务数据和行为的方法可以从编辑用户/服务成员资格数据开始，该数据将请求实体与受信任的云服务合并器订阅的云服务相关联。可以创建包含用户/服务成员数据中包含的云服务的服务间信任信息的联合信任库。响应于来自请求实体的服务请求，可以为请求实体识别可信的辅助云服务。可信次级云服务的识别可以基于由联合信任库中包含的数据合成的信任因子。满足来自每个可信二级云服务的服务请求和相关联行为的数据可以被合并到统一的数据结构中。行为可以是受信任的辅助云服务支持的可执行操作。统一的数据结构可以在服务响应中传送给请求实体。

5. 发明申请

US20100217885A1 Access Node Based Targeted Information Insertion 有权
标题翻译：基于接入节点的目标信息插入
公开(公告)号：US20100217885A1
公开(公告)日：2010-08-26
申请号：US12389903
申请日：2009-02-20
申请人： Swarup Acharya , Anurag Srivastava
发明人： Swarup Acharya , Anurag Srivastava
IPC分类号： G06F15/16
CPC分类号： H04L12/2878 , H04L12/185 , H04L12/2881 , H04N21/23424 , H04N21/44016 , H04N21/6543 , H04N21/812 , H04N21/858
摘要： Advertisements or other types of targeted information are delivered to set-top boxes or other user interface devices of a signal distribution system. In one aspect of the invention, an access node sends a message to the user interface device directing the user interface device to switch from a content stream to a targeted information stream at a specified time. Responsive to the message, the access node receives a request from the user interface device to join a targeted multicast group associated with the targeted information stream. Without requiring receipt of a subsequent request from the user interface device to leave a content multicast group associated with a content stream, the access node causes the user interface device to be dropped from the content multicast group prior to the specified time. The access node then delivers the targeted information stream to the user interface device via the targeted multicast group.
摘要翻译：广告或其他类型的目标信息被传递到信号分配系统的机顶盒或其他用户接口设备。在本发明的一个方面，接入节点向用户接口设备发送消息，指示用户接口设备在指定时间从内容流切换到目标信息流。响应于该消息，接入节点接收来自用户接口设备的请求，以加入与目标信息流相关联的目标多播组。接收节点不需要从用户接口设备接收到离开与内容流相关联的内容多播组的后续请求，导致在指定时间之前从内容多播组中删除用户界面设备。接入节点然后经由目标多播组将目标信息流传送到用户接口设备。

6. 发明申请

US20100050227A1 Update Process for Interface Device Based Targeted Information Insertion 有权
标题翻译：基于接口设备的目标信息插入更新过程
公开(公告)号：US20100050227A1
公开(公告)日：2010-02-25
申请号：US12197505
申请日：2008-08-25
申请人： Swarup Acharya , Yee Him Cheung , Anurag Srivastava
发明人： Swarup Acharya , Yee Him Cheung , Anurag Srivastava
IPC分类号： H04N7/16 , H04L12/28
CPC分类号： H04L12/1868 , H04L65/4076 , H04N21/26291 , H04N21/2668 , H04N21/6405 , H04N21/6408 , H04N21/6581 , H04N21/812 , H04N21/8456
摘要： Advertisements or other types of targeted information are delivered to set-top boxes or other user interface devices of a signal distribution system. In one aspect of the invention, at least one multicast update comprising updated targeted information is sent to the user interface devices during a multicast update period. If a given one of the user interface devices is unable to obtain a complete set of the updated targeted information from the multicast update before timeout of the multicast update period, a unicast update comprising at least a portion of the updated targeted information is sent to the given user interface device during a unicast update period. The unicast update may be sent responsive to a request from the given user interface device for a designated portion of the updated targeted information.
摘要翻译：广告或其他类型的目标信息被传递到信号分配系统的机顶盒或其他用户接口设备。在本发明的一个方面，在组播更新周期期间，将包括更新的目标信息的至少一个组播更新发送到用户接口设备。如果给定的一个用户界面设备在多播更新周期的超时之前不能从组播更新中获得一整套更新的目标信息，则将包含更新的目标信息的至少一部分的单播更新发送到给定用户界面设备在单播更新周期。可以响应于来自给定用户界面设备的针对所更新的目标信息的指定部分的请求来发送单播更新。

7. 发明授权

US07426186B2 Data path provisioning in a reconfigurable data network 有权
标题翻译：可重配置数据网络中的数据路径配置
公开(公告)号：US07426186B2
公开(公告)日：2008-09-16
申请号：US10345612
申请日：2003-01-16
申请人： Swarup Acharya , Bhawna Gupta , Pankaj Risbood , Anurag Srivastava
发明人： Swarup Acharya , Bhawna Gupta , Pankaj Risbood , Anurag Srivastava
IPC分类号： G01R31/08
CPC分类号： H04L45/04 , H04L45/124
摘要： A method for data path provisioning in a reconfigurable data network is disclosed. A data path between a source IP router and a destination IP router is determined taking into account the IP-subnets of the network interfaces of the IP routers included in the path. In one embodiment, the requirement that two IP routers can send packets via their connected interface if and only if the two interfaces are on the same subnet (i.e., the subnet constraint) is completely honored during the data path determination. In another embodiment, the data path is determined while allowing some number of violations of the subnet constraint. A transform network graph is computed and is used to determine the data path taking into account the IP-subnets.
摘要翻译：公开了一种用于在可重配置数据网络中的数据路径供应的方法。源IP路由器和目的地IP路由器之间的数据路径被考虑到路径中包括的IP路由器的网络接口的IP子网被确定。在一个实施例中，当且仅当两个接口在同一子网（即，子网约束）上时，两个IP路由器可以经由其连接的接口发送分组的要求在数据路径确定期间被完全兑现。在另一个实施例中，确定数据路径，同时允许一些数量的违反子网约束。计算变换网络图，并用于确定考虑到IP子网的数据路径。

8. 发明授权

US07411900B2 Fast restoration for virtually-concatenated data traffic 有权
标题翻译：快速恢复虚拟连接的数据流量
公开(公告)号：US07411900B2
公开(公告)日：2008-08-12
申请号：US10446220
申请日：2003-05-28
申请人： Swarup Acharya , Bhawna Gupta , Pankaj Risbood , Anurag Srivastava
发明人： Swarup Acharya , Bhawna Gupta , Pankaj Risbood , Anurag Srivastava
IPC分类号： G01R31/08
CPC分类号： H04J3/1611 , H04J2203/006 , H04J2203/0094 , Y10S370/907
摘要： Techniques are disclosed for restoration of virtually-concatenated data traffic in a data transmission network. A virtually-concatenated group is formed comprising: (i) a plurality of primary members each associated with a corresponding data stream, and (ii) at least one backup member. Each of the plurality of primary members and the backup member of the virtually-concatenated group may be assigned a corresponding one of a plurality of data transmission routes between first and second nodes of the network. Responsive to a failure of a given one of the plurality of primary members, the backup member is utilized for restoring at least a portion of the data traffic of the given member. The invention also provides a modified link capacity adjustment scheme (LCAS) protocol which substantially reduces the time required to report changes in member status information from a sink node to a source node, thereby substantially reducing the amount of time required to perform a restoration operation.
摘要翻译：公开了用于在数据传输网络中恢复虚连接的数据业务的技术。形成了一个虚拟连接的组，包括：（i）多个主要成员，每个主要成员与相应的数据流相关联，和（ii）至少一个备份成员。可以为虚拟级联组的多个主要成员和备份成员中的每一个分配网络的第一和第二节点之间的多个数据传输路由中的相应一个。响应于多个主要成员中给定的一个成员的故障，备用成员被用于恢复给定成员的数据业务的至少一部分。本发明还提供了修改的链路容量调整方案（LCAS）协议，其大大减少了从汇聚节点向源节点报告成员状态信息的变化所需的时间，从而显着减少了执行恢复操作所需的时间量。

9. 发明申请

US20070300252A1 User Interface Methods and Apparatus for Roaming Access to Subscription Services 有权
标题翻译：漫游访问订阅服务的用户界面方法和设备
公开(公告)号：US20070300252A1
公开(公告)日：2007-12-27
申请号：US11425566
申请日：2006-06-21
申请人： Swarup Acharya , Yuh-Jye Chang , Anurag Srivastava
发明人： Swarup Acharya , Yuh-Jye Chang , Anurag Srivastava
IPC分类号： H04N7/173 , H04N7/16
CPC分类号： H04N7/165 , H04L67/14 , H04N21/25875 , H04N21/25891 , H04N21/4227 , H04N21/44204 , H04N21/4751 , H04N21/4753 , H04N21/4821 , H04N21/4882 , H04W4/50 , H04W8/02
摘要： A subscriber or other user is provided with access to a subscription service of a signal distribution system at a roaming location remote from a home location of the user. The subscription service comprises a plurality of selectable channels available to the user at the home location. In one aspect of the invention, a request for initiation of a roaming session is received, and responsive to initiation of the roaming session, at least one user interface is generated for presentation on a device at the remote location. The generated user interface is configured to provide access at the remote location to one or more of the channels available to the user at the home location, and represents an at least partial alteration of a normal user interface that would otherwise be presented on the device at the remote location in the absence of the roaming session.
摘要翻译：用户或其他用户被提供对远离用户的归属位置的漫游位置处的信号分发系统的订阅服务的访问。订阅服务包括在家庭位置可用于用户的多个可选择的频道。在本发明的一个方面，接收到发起漫游会话的请求，并且响应于漫游会话的启动，生成用于在远程位置的设备上呈现的至少一个用户界面。所生成的用户界面被配置为向远程位置提供在归属位置处对用户可用的一个或多个信道的访问，并且表示将以其他方式在设备上呈现的普通用户界面的至少部分更改在没有漫游会话的情况下的远程位置。

10. 发明申请

US20060259927A1 Method and apparatus for providing remote access to subscription television services 审中-公开
标题翻译：用于提供对订阅电视服务的远程访问的方法和装置
公开(公告)号：US20060259927A1
公开(公告)日：2006-11-16
申请号：US11130329
申请日：2005-05-16
申请人： Swarup Acharya , Anurag Srivastava
发明人： Swarup Acharya , Anurag Srivastava
IPC分类号： H04N7/173 , G06F3/00 , H04N5/445 , G06F13/00
CPC分类号： H04N21/4622 , H04N7/17318 , H04N21/2221 , H04N21/2543 , H04N21/25841 , H04N21/25875 , H04N21/472 , H04N21/6125
摘要： A subscriber or other user is provided with access to one or more of a plurality of subscription services of a signal distribution system at a location remote from a home location of the user. The subscription services may be subscription television services, such as cable, satellite or Internet protocol television (IPTV) services, subscription audio services delivered via digital satellite radio, or other types of subscription services. Authentication information relating to the user is received, for example, in head end equipment, and processed to determine one or more of the plurality of subscription services that are accessible to the user at the home location. One or more media streams are then delivered to the remote location based on the determination as to which of the plurality of subscription services are accessible to the user at the home location.
摘要翻译：用户或其他用户被提供对远离用户的本地位置的位置处的信号分配系统的多个订阅服务中的一个或多个的访问。订阅服务可以是诸如有线，卫星或互联网协议电视（IPTV）服务，经由数字卫星无线电提供的订阅音频服务或其他类型的订阅服务的订阅电视服务。例如在头端设备中接收与用户相关的认证信息，并被处理以确定用户在家庭位置可访问的多个订阅服务中的一个或多个。然后，基于对于用户在家庭位置可访问多个订阅服务中的哪一个的确定，将一个或多个媒体流传送到远程位置。

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