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. 发明申请

US20140006330A1 DETECTING ANOMALIES IN REAL-TIME IN MULTIPLE TIME SERIES DATA WITH AUTOMATED THRESHOLDING 有权
公开(公告)号：US20140006330A1
公开(公告)日：2014-01-02
申请号：US13558727
申请日：2012-07-26
申请人： Alain E. Biem
发明人： Alain E. Biem
IPC分类号： G06N5/02
CPC分类号： G06F21/577 , G06F11/0709 , G06F11/0751 , G06F21/552
摘要： An approach is provided for detecting an anomaly in a processing environment. The approach includes using a processor to obtain a series of values collected within a processing interval of the processor in the processing environment. The processor normalizes this first series of values to obtain a first series of normalized values. A second series of normalized values is generated by applying a predictive filter to the first series of normalized values. A comparison score is generated from the normalized values by comparing the first series of normalized values and the second series of normalized values. The approach then determines whether the comparison score represents an anomaly relative to at least one other comparison score derived from values collected within the processing interval.

2. 发明授权

US08914317B2 Detecting anomalies in real-time in multiple time series data with automated thresholding 有权
公开(公告)号：US08914317B2
公开(公告)日：2014-12-16
申请号：US13535743
申请日：2012-06-28
申请人： Alain E. Biem
发明人： Alain E. Biem
IPC分类号： G06N5/00 , G06F11/00
CPC分类号： G06F21/577 , G06F11/0709 , G06F11/0751 , G06F21/552
摘要： An approach is provided for detecting an anomaly in a processing environment. The approach includes using a processor to obtain a series of values collected within a processing interval of the processor in the processing environment. The processor normalizes this first series of values to obtain a first series of normalized values. A second series of normalized values is generated by applying a predictive filter to the first series of normalized values. A comparison score is generated from the normalized values by comparing the first series of normalized values and the second series of normalized values. The approach then determines whether the comparison score represents an anomaly relative to at least one other comparison score derived from values collected within the processing interval.

3. 发明申请

US20090201817A1 METHOD OF OPTIMIZING A FLOW OF VALUE IN A NETWORK 审中-公开
标题翻译：在网络中优化流量的方法
公开(公告)号：US20090201817A1
公开(公告)日：2009-08-13
申请号：US12028408
申请日：2008-02-08
申请人： Rama K. Akkiraju , Alain E. Biem
发明人： Rama K. Akkiraju , Alain E. Biem
IPC分类号： G08C15/00
CPC分类号： G06Q90/00
摘要： A method of modeling flow between first and second economic entities (EEs), where the first and second EEs interact either directly or indirectly with other, including defining a network to which the first and second EEs belong, expressing economic interactions of each of the EEs in the network and for each economic interaction, determining first and second value transfers, which are respectively defined as a total of a set of transfers of value from one EE to another, and vice versa, and expressing a flow based on an absolute value of a difference between the first and the second value transfers, determining a value of a wallet of each of the EEs in the network based on external information, and calculating a maximum flow from the first EE to the second EE.
摘要翻译：对第一和第二经济实体（EE）之间的流动进行建模的方法，其中第一和第二EE直接或间接与其他EE交互，包括定义第一和第二EE所属的网络，表示每个EE的经济交互在网络和每个经济交互中，确定第一和第二价值转移，其分别被定义为从一个EE到另一个EE的一组价值转移的总和，反之亦然，并且基于绝对值第一和第二值之间的差异转移，基于外部信息确定网络中每个EE的钱包的值，以及计算从第一EE到第二EE的最大流量。

4. 发明授权

US09292576B2 Hypothesis-driven, real-time analysis of physiological data streams using textual representations 有权
标题翻译：假设驱动，使用文本表示的生理数据流的实时分析
公开(公告)号：US09292576B2
公开(公告)日：2016-03-22
申请号：US13570680
申请日：2012-08-09
申请人： Alain E. Biem , Timothy R. Dinger , Nagui Halim , Gang Luo , Daby M. Sow , Deepak S. Turaga
发明人： Alain E. Biem , Timothy R. Dinger , Nagui Halim , Gang Luo , Daby M. Sow , Deepak S. Turaga
IPC分类号： G06F17/30 , G06N5/02 , G06F19/00
CPC分类号： G06F19/324 , G06F17/30516 , G06F19/00 , G06N5/02 , G16H50/20
摘要： A method of analyzing physiological data streams. According to the method, physiological data is received into a computerized machine. The physiological data comprises numerical data and medical symptoms of a patient. Features are extracted from the physiological data based on development of the physiological data over a period of time. The features are converted into a textual representation using natural language generation. Input terms for an information retrieval system operating on the computerized machine are automatically generated based on the features. The input terms are input to the information retrieval system. A corpus of data is automatically searched to retrieve results to the input terms using the information retrieval system.
摘要翻译：分析生理数据流的方法。根据该方法，将生理数据接收到计算机化机器中。生理数据包括患者的数值数据和医学症状。基于一段时间内生理数据的发展，从生理数据中提取特征。使用自然语言生成将特征转换为文本表示。基于功能自动生成在计算机化机器上运行的信息检索系统的输入项。输入项输入到信息检索系统。使用信息检索系统自动搜索数据语料库以将结果检索到输入项。

5. 发明申请

US20140046889A1 HYPOTHESIS-DRIVEN, REAL-TIME ANALYSIS OF PHYSIOLOGICAL DATA STREAMS USING TEXTUAL REPRESENTATIONS 有权
标题翻译：使用文字表示的生理数据流的实时驱动实时分析
公开(公告)号：US20140046889A1
公开(公告)日：2014-02-13
申请号：US13570680
申请日：2012-08-09
申请人： Alain E. Biem , Timothy R. Dinger , Nagui Halim , Gang Luo , Daby M. Sow , Deepak S. Turaga
发明人： Alain E. Biem , Timothy R. Dinger , Nagui Halim , Gang Luo , Daby M. Sow , Deepak S. Turaga
IPC分类号： G06N5/02 , G06F17/30
CPC分类号： G06F19/324 , G06F17/30516 , G06F19/00 , G06N5/02 , G16H50/20
摘要： A method of analyzing physiological data streams. According to the method, physiological data is received into a computerized machine. The physiological data comprises numerical data and medical symptoms of a patient. Features are extracted from the physiological data based on development of the physiological data over a period of time. The features are converted into a textual representation using natural language generation. Input terms for an information retrieval system operating on the computerized machine are automatically generated based on the features. The input terms are input to the information retrieval system. A corpus of data is automatically searched to retrieve results to the input terms using the information retrieval system.
摘要翻译：分析生理数据流的方法。根据该方法，将生理数据接收到计算机化机器中。生理数据包括患者的数值数据和医学症状。基于一段时间内生理数据的发展，从生理数据中提取特征。使用自然语言生成将特征转换为文本表示。基于功能自动生成在计算机化机器上运行的信息检索系统的输入项。输入项输入到信息检索系统。使用信息检索系统自动搜索数据语料库以将结果检索到输入项。

6. 发明申请

US20140046890A1 HYPOTHESIS-DRIVEN, REAL-TIME ANALYSIS OF PHYSIOLOGICAL DATA STREAMS USING TEXTUAL REPRESENTATIONS 审中-公开
公开(公告)号：US20140046890A1
公开(公告)日：2014-02-13
申请号：US13571439
申请日：2012-08-10
申请人： ALAIN E. BIEM , TIMOTHY R. DINGER , NAGUI HALIM , GANG LUO , DABY M. SOW , DEEPAK S. TURAGA
发明人： ALAIN E. BIEM , TIMOTHY R. DINGER , NAGUI HALIM , GANG LUO , DABY M. SOW , DEEPAK S. TURAGA
IPC分类号： G06N5/02 , G06F17/30
CPC分类号： G06F19/324 , G06F16/24568 , G06N5/02 , G16H50/20
摘要： A method of analyzing physiological data streams. According to the method, physiological data is received into a computerized machine. The physiological data comprises numerical data and medical symptoms of a patient. Features are extracted from the physiological data based on development of the physiological data over a period of time. The features are converted into a textual representation using natural language generation. Input terms for an information retrieval system operating on the computerized machine are automatically generated based on the features. The input terms are input to the information retrieval system. A corpus of data is automatically searched to retrieve results to the input terms using the information retrieval system.

7. 发明授权

US08924333B2 Detecting anomalies in real-time in multiple time series data with automated thresholding 有权
标题翻译：通过自动化阈值检测多个时间序列数据中的实时异常
公开(公告)号：US08924333B2
公开(公告)日：2014-12-30
申请号：US13558727
申请日：2012-07-26
申请人： Alain E. Biem
发明人： Alain E. Biem
IPC分类号： G06N5/02 , G06F11/00
CPC分类号： G06F21/577 , G06F11/0709 , G06F11/0751 , G06F21/552
摘要： An approach is provided for detecting an anomaly in a processing environment. The approach includes using a processor to obtain a series of values collected within a processing interval of the processor in the processing environment. The processor normalizes this first series of values to obtain a first series of normalized values. A second series of normalized values is generated by applying a predictive filter to the first series of normalized values. A comparison score is generated from the normalized values by comparing the first series of normalized values and the second series of normalized values. The approach then determines whether the comparison score represents an anomaly relative to at least one other comparison score derived from values collected within the processing interval.
摘要翻译：提供了一种用于检测处理环境中的异常的方法。该方法包括使用处理器来获得在处理环境中在处理器的处理间隔内收集的一系列值。处理器将第一系列值归一化以获得第一系列的归一化值。通过将预测滤波器应用于第一系列归一化值来生成第二系列归一化值。通过比较第一系列归一化值和第二系列归一化值，从归一化值产生比较分数。该方法然后确定比较分数是否相对于从处理间隔内收集的值导出的至少一个其他比较分数来表示异常。

8. 发明申请

US20140006325A1 DETECTING ANOMALIES IN REAL-TIME IN MULTIPLE TIME SERIES DATA WITH AUTOMATED THRESHOLDING 有权
标题翻译：自动检测多个时间序列数据实时检测异常
公开(公告)号：US20140006325A1
公开(公告)日：2014-01-02
申请号：US13535743
申请日：2012-06-28
申请人： Alain E. Biem
发明人： Alain E. Biem
IPC分类号： G06N5/02
CPC分类号： G06F21/577 , G06F11/0709 , G06F11/0751 , G06F21/552
摘要： An approach is provided for detecting an anomaly in a processing environment. The approach includes using a processor to obtain a series of values collected within a processing interval of the processor in the processing environment. The processor normalizes this first series of values to obtain a first series of normalized values. A second series of normalized values is generated by applying a predictive filter to the first series of normalized values. A comparison score is generated from the normalized values by comparing the first series of normalized values and the second series of normalized values. The approach then determines whether the comparison score represents an anomaly relative to at least one other comparison score derived from values collected within the processing interval.
摘要翻译：提供了一种用于检测处理环境中的异常的方法。该方法包括使用处理器来获得在处理环境中在处理器的处理间隔内收集的一系列值。处理器将第一系列值归一化以获得第一系列的归一化值。通过将预测滤波器应用于第一系列归一化值来生成第二系列归一化值。通过比较第一系列归一化值和第二系列归一化值，从归一化值产生比较分数。该方法然后确定比较分数是否相对于从处理间隔内收集的值导出的至少一个其他比较分数来表示异常。

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