-
1.
公开(公告)号:US6125105A
公开(公告)日:2000-09-26
申请号:US869900
申请日:1997-06-05
申请人: Timothy John Edwards , Jonathon Coward , Peter Hamer , Kevin John Twitchen , Phillip William Hobson
发明人: Timothy John Edwards , Jonathon Coward , Peter Hamer , Kevin John Twitchen , Phillip William Hobson
CPC分类号: H04L12/5602 , G06Q10/06 , H04L41/147 , H04L41/16 , H04L43/0876 , H04Q11/0478 , H04L2012/5621 , H04L2012/5626 , H04L2012/5632 , H04L2012/5686 , Y04S40/168
摘要: A method of predicting at least one future value of a time series of data using a neural network comprising the steps of:(I) inputting a plurality of values of the time series into the neural network;(ii) inputting information about a time into the neural network; and(iii) obtaining outputs from the neural network said outputs comprising predicted future value(s) of the time series.
摘要翻译: 一种使用神经网络预测数据的时间序列的至少一个未来值的方法,包括以下步骤:(I)将所述时间序列的多个值输入神经网络; (ii)将关于时间的信息输入神经网络; 以及(iii)从所述神经网络获得所述输出,包括所述时间序列的预测未来值。
-
公开(公告)号:US6049590A
公开(公告)日:2000-04-11
申请号:US913548
申请日:1998-03-23
CPC分类号: H04M3/242 , H04Q3/54516 , H04Q3/54583 , H04Q2213/1305 , H04Q2213/13057 , H04Q2213/13109 , H04Q2213/13376
摘要: Originating instructions are generated from a functional definition of a plurality of interacting modules. These modules have respective internal functional specifications and interfacing specifications. The originating instructions are converted into control instructions that are downloaded for execution by said telecommunications switching means. Instructions are tested using testing procedures before the control instructions are downloaded. The testing procedures are generated by processing the interfacing specifications.
摘要翻译: PCT No.PCT / GB96 / 00723 Sec。 371日期:1998年3月23日 102(e)1998年3月23日PCT 1996年3月27日PCT公布。 出版物WO96 / 31070 日期1996年10月3日由多个交互模块的功能定义生成支配指令。 这些模块具有各自的内部功能规格和接口规范。 发送指令被转换为被下载供所述电信交换装置执行的控制指令。 在下载控制指令之前,使用测试程序对指令进行测试。 测试程序是通过处理接口规范来生成的。
-
公开(公告)号:US6067535A
公开(公告)日:2000-05-23
申请号:US869884
申请日:1997-06-05
申请人: Phillip William Hobson , Peter Hamer , Kevin John Twitchen , Paul Colin Barson , Simon Field , Timothy John Edwards
发明人: Phillip William Hobson , Peter Hamer , Kevin John Twitchen , Paul Colin Barson , Simon Field , Timothy John Edwards
CPC分类号: H04W12/12 , G06N3/02 , G06Q20/403 , G06Q30/02 , G07F7/08
摘要: A method of managing the processing of information using a first neural network, the information relating to the transmission of messages in a telecommunications network, uses the steps of:(i) monitoring the performance of the first neural network in processing the information;(ii) creating a second neural network of the same topology as the first when a predetermined performance threshold is reached, and(iii) retraining the second neural network while continuing to process the information using the first neural network. If the neural networks are implemented using objects, such retraining can be facilitated by using a persistance mechanism to enable the objects to be stored and moved. Applications in fraud detection.
摘要翻译: 一种使用第一神经网络处理信息的方法,涉及电信网络中的消息传输的信息使用以下步骤:(i)在处理信息时监视第一神经网络的性能; (ii)当达到预定性能阈值时,创建与第一神经网络相同拓扑的第二神经网络,以及(iii)在继续使用第一神经网络处理信息的同时重新训练第二神经网络。 如果使用对象实现神经网络,则可以通过使用持续机制来使得能够存储和移动对象来促进这种再培训。 欺诈检测中的应用
-
公开(公告)号:US5966650A
公开(公告)日:1999-10-12
申请号:US894198
申请日:1997-03-13
CPC分类号: G06K9/62 , H04M15/47 , H04W12/12 , H04M2215/0148
摘要: An arrangement for the detection of fraudulent use of a telephone subscriber's instrument in a mobile telephone system includes an input preprocessor (110), a neural network engine (111) coupled to the preprocessor, and an output postprocessor (112) coupled to the neural network engine. The preprocessor determines for each subscriber a first long term calling profile, a second short term calling profile, and a subscriber profile pattern comprising the difference between the first and second profiles. Each calling profile and subscriber profile pattern comprises a set of values for a respective set of call attributes. The neural network engine comprises a self organizing map trained to effect pattern recognition of the subscriber profile patterns and a multilayer perceptron adapted to determine for each recognized pattern a value indicative of the probability of a fraud being associated with that pattern.
摘要翻译: PCT No.PCT / GB96 / 01663 Sec。 371日期1997年8月13日 102(e)日期1997年8月13日PCT提交1996年7月12日PCT公布。 公开号WO97 / 03533 日期1997年1月30日用于在移动电话系统中检测电话用户乐器的欺诈性使用的安排包括输入预处理器(110),耦合到预处理器的神经网络引擎(111)和输出后处理器(112) 耦合到神经网络引擎。 预处理器为每个用户确定第一长期呼叫简档,第二短期呼叫简档以及包括第一和第二简档之间的差异的用户简档模式。 每个呼叫简档和用户简档模式包括用于相应呼叫属性集合的一组值。 神经网络引擎包括被训练以实现用户简档模式的模式识别的自组织映射,以及适于为每个识别模式确定指示与该模式相关联的欺诈概率的值的多层感知器。
-
公开(公告)号:US5982769A
公开(公告)日:1999-11-09
申请号:US894582
申请日:1997-08-21
CPC分类号: H04Q3/54516 , H04Q3/54583 , H04Q2213/1305 , H04Q2213/13057 , H04Q2213/13109 , H04Q2213/13376
摘要: The operationality of instructions arranged to control a telecommunications switch is tested by referring to originating instructions. A module of instructions forming part of encoded sets of originating instructions is identified, and the module is processed to obtain definitions of its interactivity with other modules of the instruction set and the interactivity with signal transmissions external to the module. This facilitates the generation of upgraded or replacement originating instructions from which new executable instructions are obtainable after being embedded within the telecommunications switch.
摘要翻译: PCT No.PCT / GB96 / 00726 Sec。 371日期1997年8月21日 102(e)日期1997年8月21日PCT 1996年3月27日PCT公布。 公开号WO96 / 31071 日期1996年10月3日安排用于控制电信交换机的指令的操作性通过参考原始指令进行测试。 识别形成编码的始发指令集的一部分的指令的模块,并且处理模块以获得与指令集的其他模块的交互性的定义以及与模块外部的信号传输的交互性。 这有助于生成升级或替换的始发指令,从而可以在嵌入电信交换机之后从其获得新的可执行指令。
-
公开(公告)号:US6038555A
公开(公告)日:2000-03-14
申请号:US872332
申请日:1997-06-10
CPC分类号: H04W12/12 , G06N3/02 , G06Q20/403 , G06Q30/02 , G07F7/08
摘要: A generic anomaly detection engine is described which provides neural network technology to process information such as call detail records and detect anomalies in the information, such as mobile phone fraud. Information from call detail records is pre-processed to form signatures which represent the calling behavior of a subscriber. These signatures are formed in one of a plurality of predetermined formats. The generic anomaly detection engine is instantiated in order to create an anomaly detector which is suitable for a particular situation and during the instantiation process the topology of the neural network components is automatically adjusted to fit the required situation. The topology is adjusted to according to the format of the signatures.
摘要翻译: 描述了一种通用异常检测引擎,其提供神经网络技术来处理诸如呼叫详细记录的信息,并且检测诸如移动电话欺诈的信息中的异常。 来自呼叫详细记录的信息被预先处理以形成表示用户呼叫行为的签名。 这些签名以多种预定格式之一形成。 通用异常检测引擎被实例化,以创建适合于特定情况的异常检测器,并且在实例化过程期间,神经网络部件的拓扑被自动调整以适应所需的情况。 拓扑根据签名的格式进行调整。
-
-
-
-
-