公开(公告)号：US20150088953A1

公开(公告)日：2015-03-26

申请号：US14493308

申请日：2014-09-22

Applicant: Infosys Limited

Inventor： Hari Manassery Koduvely ,  Sarbendu Guha ,  Arun Yadav ,  David C. Gladbin ,  Naveen Chandra Tewari ,  Utkarsh Gupta

IPC: G06F17/16 ,  G06F17/18

CPC classification number: G06F17/16 ,  G06K9/6249

Abstract: The present invention provides a method and system for distributed probabilistic matrix factorization. In accordance with a disclosed embodiment, the method may include partitioning a sparse matrix into a first set of blocks on a distributed computer cluster, whereby a dimension of each block is MB rows and NB columns. Further, the method shall include initializing a plurality of matrices including first mean matrix Ū, a first variance matrix Ũ, a first prior variance matrix ŨP, a second mean matrix V, a second variance matrix {tilde over (V)}, and a second prior variance matrix {tilde over (V)}P, by a set of values from a probability distribution function. The plurality of matrices can be partitioned into a set of blocks on the distributed computer cluster, whereby each block can be of a shorter dimension K, and the plurality of matrices can be updated iteratively until a cost function of the sparse matrix converges.

Abstract translation: 本发明提供了一种分布式概率矩阵分解的方法和系统。 根据所公开的实施例，该方法可以包括将稀疏矩阵划分为分布式计算机集群上的第一组块，由此每个块的维度是MB行和NB列。 此外，该方法应包括初始化多个矩阵，包括第一均方矩阵Ū，第一方差矩阵Ũ，第一先验方差矩阵ŨP，第二平均矩阵V，第二方差矩阵（V） 通过来自概率分布函数的一组值的第二先验方差矩阵{tilde over（V）} P。 多个矩阵可以被划分成分布式计算机集群上的一组块，由此每个块可以具有更短的维度K，并且可以迭代地更新多个矩阵，直到稀疏矩阵的成本函数收敛。

公开(公告)号：US09933353B2

公开(公告)日：2018-04-03

申请号：US14612651

申请日：2015-02-03

Applicant: Infosys Limited

Inventor： Gopichand Agnihotram ,  Hari Manassery Koduvely

IPC: G01B3/52 ,  G01N17/00 ,  G06Q10/00 ,  G06F11/30

CPC classification number: G01N17/00 ,  G06Q10/00

Abstract: The technique relates to a system and method for assessing corroded pipeline defect growth rate from partial defect growth rate information. The method involves obtaining a plurality of observed defect growth rates from the inspection data collected at different time intervals then determining at least one unobserved defect growth rate on the basis of distribution pattern of the plurality of observed defect growth rates thereafter simulating condition of at least one hyper parameter on the inspection data based on prior information of the at least one hyper parameter then simulating the plurality of observed defect growth rates and the at least one unobserved defect growth rate based on the simulated hyper parameters and finally obtaining defect growth rate point estimate from the simulated growth rate data. The method also involves determining a probability of failure of a defect from the defect growth rate point estimates.

公开(公告)号：US20150226660A1

公开(公告)日：2015-08-13

申请号：US14612651

申请日：2015-02-03

Applicant: Infosys Limited

Inventor： Gopichand Agnihotram ,  Hari Manassery Koduvely

IPC: G01N17/00 ,  G06N7/00 ,  G06N5/00

CPC classification number: G01N17/00 ,  G06Q10/00

Abstract: The technique relates to a system and method for assessing corroded pipeline defect growth rate from partial defect growth rate information. The method involves obtaining a plurality of observed defect growth rates from the inspection data collected at different time intervals then determining at least one unobserved defect growth rate on the basis of distribution pattern of the plurality of observed defect growth rates thereafter simulating condition of at least one hyper parameter on the inspection data based on prior information of the at least one hyper parameter then simulating the plurality of observed defect growth rates and the at least one unobserved defect growth rate based on the simulated hyper parameters and finally obtaining defect growth rate point estimate from the simulated growth rate data. The method also involves determining a probability of failure of a defect from the defect growth rate point estimates.

Abstract translation: 该技术涉及从部分缺陷生长率信息中评估腐蚀管道缺陷生长速率的系统和方法。 该方法包括从在不同时间间隔收集的检查数据获得多个观察到的缺陷生长速率，然后基于多个观察到的缺陷生长速率的分布模式确定至少一个未观察到的缺陷生长速率，然后模拟至少一个 基于所述至少一个超参数的先验信息，然后基于所述模拟的超参数来模拟所述多个观察到的缺陷生长速率和所述至少一个未观察到的缺陷生长速率，并且最终从所述至少一个超参数获得缺陷生长速率点估计 模拟增长率数据。 该方法还涉及从缺陷生长速率点估计中确定缺陷的故障概率。