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

US5751571A Process and apparatus for determining optimum values for manipulated variables of a technical system 失效
标题翻译：用于确定技术系统的操纵变量的最佳值的过程和装置
公开(公告)号：US5751571A
公开(公告)日：1998-05-12
申请号：US578600
申请日：1996-01-04
申请人： Volker Tresp , Bernd Schurmann , Martin Schlang
发明人： Volker Tresp , Bernd Schurmann , Martin Schlang
IPC分类号： G05B13/02 , G05B13/04 , G06F15/18
CPC分类号： G05B13/042 , G05B13/027
摘要： Optimum values for manipulated variables s.sub.1, . . . ,s.sub.S of a technical system (.phi.) are determined for prescribed operational variables b.sub.1, . . . ,b.sub.B in order to optimize a prescribed target function z=g(y.sub.2. . . ,y.sub.N) of system properties y.sub.2, . . . , y.sub.N where y.sub.i =.phi..sub.i (s.sub.1, . . . ,s.sub.S,b.sub.1, . . . ,b.sub.B). Here, a set of functions f.sub.i (w.sub.1, . . . ,w.sub.W,x.sub.1, . . . ,x.sub.S=B) is used whose parameters w.sub.1, . . . ,w.sub.W are set in such a way that the functions f.sub.i model the system in such a way that the functions f.sub.i approximate the system functions .phi.i as functions of their variables x.sub.1, . . . ,x.sub.S+B in terms of an interval of prescribed magnitude; the manipulated variables s.sub.1, . . . ,s.sub.S are determined by optimizing the function g(f.sub.1 (w.sub.1, . . . ,w.sub.W,s.sub.1, . . . ,s.sub.S,b.sub.1, . . . ,b.sub.B), . . . , f.sub.N (w.sub.1, . . . ,w.sub.W,s.sub.1, . . . ,s.sub.S,b.sub.1, . . . ,b.sub.B)) at fixed values of w.sub.1, . . . ,w.sub.W and b.sub.1, . . . ,b.sub.B.
摘要翻译： PCT No.PCT / DE94 / 00762 Sec。 371日期1996年1月4日 102（e）日期1996年1月4日PCT提交1994年7月1日PCT公布。出版物WO95 / 02213 日期1995年1月19日操纵变量s1，...的最优值。。。，对于规定的操作变量b1，...确定技术系统（phi）的sS。。。，bB以便优化系统属性y2的规定目标函数z = g（y2，...，yN）。。。，yN，其中yi = phi i（s1，...，sS，b1，...，bB）。这里，使用一组函数fi（w1，...，wW，x1，...，xS = B），其参数w1，...。。。，wW被设置为使得函数fi以系统函数模拟系统，使得函数fi将系统函数phi i近似为它们的变量x1的函数。。。，xS + B以规定幅度的间隔; 操纵变量s1，。。。，sS通过优化函数g（f1（w1，...，wW，s1，...，sS，b1，...，bB），...，fN（w1，...，wW ，s1，...，sS，b1，...，bB））。。。，wW和b1，。。。，bB。

2. 发明授权

US5706401A Method for editing an input quantity for a neural network 失效
标题翻译：用于编辑神经网络的输入量的方法
公开(公告)号：US5706401A
公开(公告)日：1998-01-06
申请号：US699558
申请日：1996-08-19
申请人： Volker Tresp
发明人： Volker Tresp
IPC分类号： G06F15/18 , G06N3/02 , G06N3/04 , G06E1/00 , G06E3/00
CPC分类号： G06N3/04
摘要： In a method for supplementing missing data in a time series used as an input to a neural network or for improving noise-infested data supplied to a neural network, error distribution densities for the missing values are calculated on the basis of the known measured values from the time series and their known or predetermined error distribution density, and samples are taken from this error distribution density according to the Monte Carlo method. These each lead to an estimated or predicted value whose average is introduced for the value to be predicted. The method can be employed for the operation as well as for the training of the neural network, and is suitable for use in all known fields of utilization of neural networks.
摘要翻译：在用作补充神经网络的输入的时间序列中的缺失数据的补充方法中，或用于改善提供给神经网络的噪声感知数据的方法，基于已知的测量值来计算缺失值的误差分布密度时间序列及其已知或预定的误差分布密度，并根据蒙特卡罗方法从该误差分布密度中取样。这些都导致估计或预测值，其平均值被引入要预测的值。该方法可以用于神经网络的操作和训练，并且适用于所有已知的神经网络的利用领域。

3. 发明授权

US08566273B2 Method, system, and computer program for information retrieval in semantic networks 有权
标题翻译：语义网络中信息检索的方法，系统和计算机程序
公开(公告)号：US08566273B2
公开(公告)日：2013-10-22
申请号：US13008084
申请日：2011-01-18
申请人： Joshua Lamar Moore , Florian Steinke , Volker Tresp
发明人： Joshua Lamar Moore , Florian Steinke , Volker Tresp
IPC分类号： G06N5/02
CPC分类号： G06F17/30589 , G06F17/3053 , G06F17/30533
摘要： A method, system, and computer software for information retrieval in semantic networks, has the steps of: acquiring a graph of interest, assuming a novel metric regarding the acquired graph, specifying a query node of interest on the obtained graph, calculating a shortest-path distance from the query node of interest to a plurality of other nodes on the acquired graph, obtaining a ranked list of nodes based on the calculated shortest-path distance, and displaying for a user the retrieved information.
摘要翻译：一种用于语义网络中的信息检索的方法，系统和计算机软件具有以下步骤：获取感兴趣的图，假设关于所获取的图的新颖度量，在所获得的图上指定感兴趣的查询节点，从感兴趣的查询节点到所获取的图形上的多个其他节点的路径距离，基于计算的最短路径距离获得节点的排序列表，并且向用户显示所检索的信息。

4. 发明授权

US07949620B2 Method and device for detecting clusters amongst data arranged in orders for cluster creation and removal based on conditional probabilities between clusters 有权
标题翻译：基于群集创建和删除的顺序排列的数据之间的簇检测方法和设备，基于群集之间的条件概率
公开(公告)号：US07949620B2
公开(公告)日：2011-05-24
申请号：US11378640
申请日：2006-03-20
申请人： Clemens Otte , Rudolf Sollacher , Volker Tresp
发明人： Clemens Otte , Rudolf Sollacher , Volker Tresp
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00 , G06N3/02
CPC分类号： G06K9/6218 , G16H40/20 , G16H50/70
摘要： After initial clusters having only one component are formed, a conditional probability P(Ci|C′k) is determined for the cluster Ci being included in an order on condition that cluster C′k is included in the order. If P(Ci|C′k) is greater than a first threshold value S1, a new cluster Cn having all the components of clusters Ci, C′k is formed and the operations are repeated until no new clusters are formed.
摘要翻译：在形成仅具有一个分量的初始聚类之后，在簇C'被包括在该顺序的条件下，对于包含在簇C中的条件概率P（Ci | C'k）被确定。如果P（Ci | C'k）大于第一阈值S1，则形成具有簇Ci，C'k的所有分量的新簇Cn，并且重复该操作，直到形成新的簇。

5. 发明申请

US20090077079A1 METHOD FOR CLASSIFYING INTERACTING ENTITIES 审中-公开
标题翻译：分类实体的方法
公开(公告)号：US20090077079A1
公开(公告)日：2009-03-19
申请号：US12115244
申请日：2008-05-05
申请人： Achim RETTINGER , Volker Tresp
发明人： Achim RETTINGER , Volker Tresp
IPC分类号： G06F7/00
CPC分类号： G06Q30/08 , G06Q30/02
摘要： Interacting entities are classified into cluster classes, where an interaction is a relation between two entities based on a promised outcome by each entity and an effective outcome of the interaction. A model for infinite relational trust is used which has hidden variables associated with entity classes corresponding to the entities. A conditional probability distribution of the hidden variables is calculated depending on observable attributes assigned to the entities and the relations.
摘要翻译：交互实体被分类为集群类，其中交互是基于每个实体的承诺结果的两个实体之间的关系以及交互的有效结果。使用无限关系信任的模型，其具有与实体对应的实体类相关联的隐藏变量。根据分配给实体的可观察属性和关系，计算隐藏变量的条件概率分布。

6. 发明申请

US20060002513A1 Method and device for user-specific parameterization of an x-ray device 有权
标题翻译：用于X射线设备的用户特定参数化的方法和设备
公开(公告)号：US20060002513A1
公开(公告)日：2006-01-05
申请号：US11170661
申请日：2005-06-29
申请人： Philipp Bernhardt , Marcus Pfister , Rudolf Sollacher , Volker Tresp
发明人： Philipp Bernhardt , Marcus Pfister , Rudolf Sollacher , Volker Tresp
IPC分类号： H05G1/42
CPC分类号： A61B6/481 , A61B6/4035 , A61B6/504 , A61B6/542 , A61B6/544 , A61B6/583 , A61B6/588
摘要： A method and a suitable x-ray device (1) for carrying out the method are specified for effective and operationally simplified user-specific optimization of a parameter configuration (K) of an x-ray device (1), said configuration comprising at least one recording parameter (U,I,t,F). It is accordingly provided that a user (20) is shown a plurality of reference images (V, V1) for different reference parameter sets (PV) from a reference memory (21) in which are stored a large number of reference images (V, V0) each with an associated reference parameter set (PV), that for each reference image (V, V1) shown the user (20) submits an assessment (BM) of the image quality (V, V1), and that on the basis of the submitted assessments (BM) an optimized parameter configuration (K) is created from the reference parameter sets (PV) of the reference images (V, V1) shown.
摘要翻译：指定用于执行该方法的方法和合适的x射线装置（1），用于有效和操作地简化X射线装置（1）的参数配置（K）的用户特定优化，所述配置至少包括一个记录参数（U，I，t，F）。因此，用户（20）从参考存储器（21）中显示用于不同参考参数组（PV）的多个参考图像（V，V 1），其中存储了大量参考图像（V ，V 0），每个具有相关联的参考参数集（PV），对于所示的每个参考图像（V，V 1），用户（20）提交图像质量（V，V 1）的评估（BM），以及根据所提交的评估（BM），根据所示的参考图像（V，V 1）的参考参数组（PV）创建优化参数配置（K）。

7. 发明授权

US10055689B2 Calculating a relation indicator for a relation between entities 有权
公开(公告)号：US10055689B2
公开(公告)日：2018-08-21
申请号：US14680232
申请日：2015-04-07
申请人： Maximilian Nickel , Volker Tresp , Xueyan Jiang
发明人： Maximilian Nickel , Volker Tresp , Xueyan Jiang
IPC分类号： G06N7/00 , G06F17/18 , G06K9/00 , G06N99/00
CPC分类号： G06N7/00 , G06F17/18 , G06K9/00 , G06N20/00
摘要： A method is provided for calculating a relation indicator for a relation between entities based on an optimization procedure. The method combines the strong relational learning ability and the good scalability of the RESCAL model with the linear regression model, which may deal with observed patterns to model known relations. The method may be used to determine relations between objects, for instance entries in a database, such as a shopping platform, medical treatments, production processes, or in the context of the Internet of Things, in a fast and precise manner.

8. 发明申请

US20160300149A1 Calculating a Relation Indicator for a Relation Between Entities 审中-公开
标题翻译：计算实体之间关系的关系指标
公开(公告)号：US20160300149A1
公开(公告)日：2016-10-13
申请号：US14680232
申请日：2015-04-07
申请人： Maximilian Nickel , Volker Tresp , Xueyan Jiang
发明人： Maximilian Nickel , Volker Tresp , Xueyan Jiang
IPC分类号： G06N7/00 , G06F17/16
CPC分类号： G06N7/00 , G06F17/18 , G06K9/00 , G06N99/005
摘要： A method is provided for calculating a relation indicator for a relation between entities based on an optimization procedure. The method combines the strong relational learning ability and the good scalability of the RESCAL model with the linear regression model, which may deal with observed patterns to model known relations. The method may be used to determine relations between objects, for instance entries in a database, such as a shopping platform, medical treatments, production processes, or in the context of the Internet of Things, in a fast and precise manner.
摘要翻译：提供了一种基于优化过程来计算实体之间的关系的关系指标的方法。该方法将RESCAL模型的强关系学习能力和良好的可扩展性与线性回归模型相结合，可以处理观察到的模型以建立已知关系。该方法可以用于以快速和精确的方式确定对象之间的关系，例如数据库中的条目，例如购物平台，医疗处理，生产过程或物联网的上下文中。

9. 发明申请

US20120158639A1 METHOD, SYSTEM, AND COMPUTER PROGRAM FOR INFORMATION RETRIEVAL IN SEMANTIC NETWORKS 有权
标题翻译：方法，系统和计算机程序用于信息检索在语义网络
公开(公告)号：US20120158639A1
公开(公告)日：2012-06-21
申请号：US13008084
申请日：2011-01-18
申请人： Joshua Lamar Moore , Florian Steinke , Volker Tresp
发明人： Joshua Lamar Moore , Florian Steinke , Volker Tresp
IPC分类号： G06N5/02
CPC分类号： G06F17/30589 , G06F17/3053 , G06F17/30533
摘要： A method, system, and computer software for information retrieval in semantic networks, has the steps of: acquiring a graph of interest, assuming a novel metric regarding the acquired graph, specifying a query node of interest on the obtained graph, calculating a shortest-path distance from the query node of interest to a plurality of other nodes on the acquired graph, obtaining a ranked list of nodes based on the calculated shortest-path distance, and displaying for a user the retrieved information.
摘要翻译：一种用于语义网络中的信息检索的方法，系统和计算机软件具有以下步骤：获取感兴趣的图，假设关于所获取的图的新颖度量，在所获得的图上指定感兴趣的查询节点，从感兴趣的查询节点到所获取的图形上的多个其他节点的路径距离，基于计算的最短路径距离获得节点的排序列表，并且向用户显示所检索的信息。

10. 发明申请

US20090202061A1 METHOD FOR IDENTIFYING SPIT OR SPAM FOR VOIP 审中-公开
标题翻译：识别SPIT或SPAM的方法
公开(公告)号：US20090202061A1
公开(公告)日：2009-08-13
申请号：US12281935
申请日：2007-03-02
申请人： Joachim Charzinski , Christof Störmann , Volker Tresp , Stefan Hagen Weber , Kai Yu
发明人： Joachim Charzinski , Christof Störmann , Volker Tresp , Stefan Hagen Weber , Kai Yu
IPC分类号： H04M3/42
CPC分类号： H04M3/436 , H04L65/1079 , H04M7/006
摘要： The invention relates to a method for the computer-assisted identification of a class of VoIP calls of a first type (spam) in a communication network (internet). Said communication network has a plurality (N) of first subscribers (Tn1-1, . . . , Tn1-5) and a plurality (M) of second subscribers (Tn2-1, . . . , Tn2-7), the first and the second subscribers being allocated a definite characteristic (IP address, telephone number, e-mail address) wherein, at least some of the first subscribers (Tn1-1, . . . , Tn1-5) are allocated, respectively, with at least one list (white list, black list) which contains at least one definite characteristic of the second subscriber. During a call of one of the second subscribers to one of the first subscribers, a control screens to see whether the characteristic of the second subscriber is on the list of the first subscriber and in the event that the second subscriber is not on the list of the called first subscribers, the lists of the additional first subscriber are used to make a decision whether the call is classified as a call of the first type (spam or trusted caller).
摘要翻译：本发明涉及一种用于计算机辅助识别通信网络（互联网）中的第一类型（垃圾邮件）的VoIP呼叫的方法。所述通信网络具有多个（N）个第一用户（Tn1-1，...，Tn1-5）和多个（M）个第二用户（Tn2-1，...，Tn2-7），第一并且第二用户被分配有明确的特征（IP地址，电话号码，电子邮件地址），其中分别分配了第一用户（Tn1-1，...，Tn1-5）中的至少一些，具有至少包含第二用户的至少一个确定特征的列表（白名单，黑名单）。在第一用户之一的第二用户之一的呼叫期间，控制屏幕，以查看第二用户的特征是否在第一用户的列表上，以及在第二用户不在第被叫的第一用户，附加的第一用户的列表被用于决定呼叫是否被分类为第一类型的呼叫（垃圾邮件或受信任的呼叫者）。

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