公开(公告)号：US08538908B2

公开(公告)日：2013-09-17

申请号：US13014019

申请日：2011-01-26

Applicant: Zhiguo Li ,  Rajinderjeet Singh Minhas

Inventor： Zhiguo Li ,  Rajinderjeet Singh Minhas

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G06N5/025

Abstract: A method for generating service rules corresponding to business data is disclosed. A plurality of business related data is gathered from various sources. The data is combined using a subjective logic technique. The data is then evaluated for temporal patterns. Finally a set of service rules corresponding to the combined business data are developed.

Abstract translation: 公开了一种用于生成与业务数据相对应的服务规则的方法。 从各种来源收集多个业务相关数据。 数据使用主观逻辑技术组合。 然后对时间模式进行数据的评估。 最后开发了与组合业务数据相对应的一组服务规则。

公开(公告)号：US08484144B2

公开(公告)日：2013-07-09

申请号：US12049911

申请日：2008-03-17

Applicant: Paul A. Rhodes

Inventor： Paul A. Rhodes

IPC: G06N3/00 ,  G06N7/04 ,  G06N7/06

CPC classification number: G06N3/10

Abstract: A simulated neural circuit includes a plurality of simulated neurons. The simulated neurons have input branches that are configured to connect to a plurality of inputs and activate in response to activity in the inputs to which they are connected. In addition, the simulated neurons are configured to activate in response to activity in their input branches. Initial connections are formed between various input branches and various inputs and a set of the inputs are activated. Thereafter, the stability of connections between input branches and inputs to which they are connected is moderated based on the activated set of inputs and a pattern of activity generated in the input branches and simulated neurons in response to the activated set of inputs.

Abstract translation: 模拟神经电路包括多个模拟神经元。 模拟神经元具有被配置为连接到多个输入并响应于它们所连接的输入中的活动而激活的输入分支。 此外，模拟的神经元被配置为响应于其输入分支中的活动来激活。 在各种输入分支和各种输入之间形成初始连接，并且一组输入被激活。 此后，基于激活的输入集合以及响应于激活的输入集合在输入分支和模拟神经元中产生的活动模式来调节输入分支与其连接的输入之间的连接的稳定性。

公开(公告)号：US08478709B2

公开(公告)日：2013-07-02

申请号：US12719198

申请日：2010-03-08

Applicant: Hsiu-Khuern Tang ,  Justin S. Dyer

Inventor： Hsiu-Khuern Tang ,  Justin S. Dyer

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G06F15/16 ,  G06N5/02

Abstract: System, including method, apparatus, and computer-readable media, for evaluating client status for a likelihood of churn. Client data may be received, with the client data representing events from a set of different event types performed by clients. Parameters of a statistical model that describes client behavior may be estimated using a computer and based on the client data. A churn type of event may be encoded in the statistical model as an absorbing state of a stochastic process, with a time of transition to the absorbing state modeled as being infinite. At least one of the parameters may correspond to the churn type of event. A likelihood of churn may be calculated for a plurality of the clients at one or more time points using the statistical model and its estimated parameters.

Abstract translation: 系统，包括方法，设备和计算机可读介质，用于评估客户端状态的可能性。 可以接收客户端数据，其中客户端数据表示由客户端执行的一组不同事件类型的事件。 可以使用计算机并基于客户端数据来估计描述客户端行为的统计模型的参数。 可以将统计模型中的流失类型作为随机过程的吸收状态进行编码，并将模拟为无穷大的吸收状态的过渡时间。 参数中的至少一个可以对应于事件的流失类型。 可以使用统计模型及其估计参数在一个或多个时间点为多个客户端计算流失的可能性。

公开(公告)号：US08417660B2

公开(公告)日：2013-04-09

申请号：US12501359

申请日：2009-07-10

Applicant: Bimal Vinod Patel ,  Cynthia Chiyemi Yamaga ,  Louis Leo Brunetti

Inventor： Bimal Vinod Patel ,  Cynthia Chiyemi Yamaga ,  Louis Leo Brunetti

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G06F19/3456 ,  G06F19/00 ,  G06F19/328 ,  G06Q50/22 ,  G06Q50/24 ,  G16H50/50

Abstract: Systems, methods and devices for modifying a patient adherence score which include, in one implementation, obtaining a patient profile in a patient population, the patient profile including multiple patient attributes and each patient attribute including a value; obtaining an adherence score for the patient profile for predicting patient adherence based on one or more of the multiple patient attributes wherein the adherence score indicates a likelihood of adherence of the patient to the prescribed treatment; and applying a modifier associated with an application to modify the adherence score obtained for the patient profile into a modified score for the application.

Abstract translation: 用于修改患者依从性评分的系统，方法和装置，其包括在一个实施方式中获得患者群体中的患者概况，所述患者概况包括多个患者属性和每个患者属性包括值; 基于所述多个患者属性中的一个或多个来获得用于预测患者依从性的患者概况的依从性分数，其中所述依从性分数表示患者遵守所述规定治疗的可能性; 以及应用与应用相关联的修饰符，以将所述患者简档获得的所述依从性得分修改为所述应用的修改得分。

公开(公告)号：US08374989B2

公开(公告)日：2013-02-12

申请号：US12579831

申请日：2009-10-15

Applicant: Jin Won Lee ,  Wang Yun Won ,  Kwang-Soon Lee

Inventor： Jin Won Lee ,  Wang Yun Won ,  Kwang-Soon Lee

IPC: G06N7/02 ,  G06N7/06

CPC classification number: A61B10/0012 ,  A61B2010/0019 ,  A61B2010/0029 ,  G06F19/00 ,  G16H10/20 ,  G16H50/50

Abstract: A system for customized prediction of a menstruation period or a fertility period is provided. The system includes a vital information measurer for measuring vital information about a user, a basic menstruation information generator for calculating the first day of menstruation or an ovulation day using the vital information received from the vital information measurer and outputting the first day of menstruation or the ovulation day as basic menstruation information, a menstruation cycle modeler having a menstruation cycle model representing a menstruation cycle as a function with a predetermined period, and a model parameter estimator for estimating and compensating a menstruation cycle parameter of the menstruation cycle model using the basic menstruation information received from the basic menstruation information generator.

Abstract translation: 提供了定期预测月经期或生育期的系统。 该系统包括用于测量关于用户的重要信息的重要信息测量器，用于使用从重要信息测量器接收的重要信息计算月经第一天或排卵日的基本月经信息发生器，并输出月经的第一天或 作为基本月经信息的排卵日，具有代表月经周期的月经周期模型作为功能的月经周期模型，具有预定时间段，以及用于使用基本月经估计和补偿月经周期模型的月经周期参数的模型参数估计器 从基本月经信息发生器收到的信息。

公开(公告)号：US08370287B2

公开(公告)日：2013-02-05

申请号：US13372468

申请日：2012-02-13

Applicant: David Snyder

Inventor： David Snyder

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G06F19/34 ,  G06N99/005

Abstract: Methods of classifying a subject's condition are described. The method includes: receiving measured signals from the subject; processing the measured signals using a computing device to identify a class associated with an identified condition of the subject; introducing an artificial class, the artificial class being associated with an unknown condition of the subject; classifying a feature vector from the subject into the identified class or the artificial class; and generating a signal in response to classifying the feature vector. The measured signals from the subject may include at least one signal extracted from brain activity of the subject.

Abstract translation: 描述对受试者状况进行分类的方法。 该方法包括：从主体接收测量信号; 使用计算设备处理所测量的信号以识别与所述对象的识别条件相关联的类别; 引入人工课程，人造课程与受试者的未知状况相关; 将特征向量从受试者分类到识别的类或人工类中; 以及响应于所述特征向量的分类而生成信号。 来自受检者的测量信号可以包括从受试者的大脑活动中提取的至少一个信号。

公开(公告)号：US08346709B2

公开(公告)日：2013-01-01

申请号：US12535375

申请日：2009-08-04

Applicant: Andrew E. Silverman ,  Abhinay Sharma ,  Scott S. Benson ,  Adrian Dumitru Corduneanu ,  Angshuman Guha ,  Tomas Lloret Llinares

Inventor： Andrew E. Silverman ,  Abhinay Sharma ,  Scott S. Benson ,  Adrian Dumitru Corduneanu ,  Angshuman Guha ,  Tomas Lloret Llinares

IPC: G06N7/06

CPC classification number: G06Q30/02

Abstract: Methods, systems, and apparatus, including computer program products, for determining a probability that a traffic conversion of a content item associated with a content source (e.g., website) will occur based on past traffic patterns for that content source. A traffic conversion defines, for example, minimum traffic interactions of one or more associated user sessions with a content source. The minimum traffic interactions can be based on, for example, the duration of the one or more user sessions on the content source, or a quantity of pages associated with the content source navigated in the one or more associated user sessions.

Abstract translation: 用于确定基于该内容源的过去流量模式来确定与内容源（例如，网站）相关联的内容项目的流量转换的概率的方法，系统和装置，包括计算机程序产品。 流量转换定义了例如一个或多个关联用户会话与内容源的最小流量交互。 最小流量交互可以基于例如内容源上的一个或多个用户会话的持续时间，或者与在一个或多个相关联的用户会话中导航的内容源相关联的页面的数量。

公开(公告)号：US08332346B1

公开(公告)日：2012-12-11

申请号：US13209018

申请日：2011-08-12

Applicant: Wai Yip To

Inventor： Wai Yip To

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G06K9/6226 ,  G06N99/005

Abstract: Systems and methods for extracting or analyzing time-series behavior are described. Some embodiments of computer-implemented methods include generating fuzzy rules from time series data. Certain embodiments also include resolving conflicts between fuzzy rules according to how the data is clustered. Some embodiments further include extracting a model of the time-series behavior via defuzzification and making that model accessible. Advantageously, to resolve conflicts between fuzzy rules, some embodiments define Gaussian functions for each conflicting data point, sum the Gaussian functions according to how the conflicting data points are clustered, and resolve the conflict based on the results of summing the Gaussian functions. Some embodiments use both crisp and non-trivially fuzzy regions and/or both crisp and non-trivially fuzzy membership functions.

Abstract translation: 描述了提取或分析时间序列行为的系统和方法。 计算机实现的方法的一些实施例包括从时间序列数据生成模糊规则。 某些实施例还包括根据数据如何聚类来解决模糊规则之间的冲突。 一些实施例还包括通过去模糊化提取时间序列行为的模型并使该模型可访问。 有利地，为了解决模糊规则之间的冲突，一些实施例为每个冲突数据点定义高斯函数，根据冲突数据点如何聚类来对高斯函数求和，并且基于对高斯函数求和的结果来解决冲突。 一些实施例使用清晰和非平凡的模糊区域和/或清晰和非平凡的模糊隶属函数。

公开(公告)号：US08326790B2

公开(公告)日：2012-12-04

申请号：US12488315

申请日：2009-06-19

Applicant: Karel Macek ,  Jana Trojanova ,  Jiri Rojicek

Inventor： Karel Macek ,  Jana Trojanova ,  Jiri Rojicek

IPC: G06F9/44 ,  G06N7/02 ,  G06N7/06

CPC classification number: G05B15/02 ,  G05B23/0278

Abstract: A system that transforms information into fuzzy observable states. These states may be matched against a mapping table which indicates which observable state admits or excludes particular faults. This information may be processed over time when in each time instant the admitted or excluded faults are used for updating the rate for each fault.

Abstract translation: 将信息转换为模糊可观察状态的系统。 这些状态可以与指示哪个可观察状态允许或排除特定故障的映射表相匹配。 该信息可以随时间被处理，当在每个时间瞬间，允许或排除的故障用于更新每个故障的速率。

公开(公告)号：US08296256B2

公开(公告)日：2012-10-23

申请号：US12579442

申请日：2009-10-15

Applicant: Eli Arbel ,  Oleg Rokhlenko ,  Karen Yorav

Inventor： Eli Arbel ,  Oleg Rokhlenko ,  Karen Yorav

IPC: G06N7/06 ,  G06F17/50

CPC classification number: G06F1/3203 ,  G06F1/3237 ,  G06F17/505 ,  G06F2217/62 ,  Y02D10/128

Abstract: Clock gating circuit is determined by transforming a clock gating opportunity function to a non-Boolean function and constraining inputs of the non-Boolean function. The non-Boolean function may be a ternary function. Constraining the inputs may be achieved by introducing control variables and a cardinality constraint associated with their values. The non-Boolean function may be utilized to approximate universal quantification of an input assigned with a non-Boolean value, such as “don't care” value. The non-Boolean function may be utilized to provide an ALL SAT solution of a Boolean function using a SAT solver.

Abstract translation: 时钟门控电路通过将时钟门控机会功能转换为非布尔函数并约束非布尔函数的输入来确定。 非布尔函数可以是三元函数。 可以通过引入控制变量和与其值相关联的基数约束来实现约束输入。 可以使用非布尔函数来近似分配有非布尔值的输入的通用量化，例如不关心价值。 可以使用非布尔函数来使用SAT求解器来提供布尔函数的ALL SAT解。