Hewlett-packard Development Company, L.p.

Hewlett-packard Company

Nina Mishra

Henri Jacques Suermondt

Ram Swaminathan

Rajeev Motwani

Todd Mitchell Goin

James Richard Stinger

Douglas William Steele

Randall Bruce Campbell

Liadan O'Callaghan

Sudipto Guha

Thomas Elliott Fawcett

Umeshwar Dayal

Meichun Hsu

George H Forman

Arif Abdulhusein Merchant

Robert S Schreiber

Robert E Tarjan

Binyamin Pinkas

Mahesh Kallahalla

Qian Wang

Dana Ron

Gagan Aggarwal

A system and method is disclosed for determining a value of an element, having a k-th rank. The method discloses: calculating a total number of elements in a first and second dataset; prohibiting parties from accessing each other's dataset; ranking the elements within each dataset; computing a total number of elements in the datasets each having a value less than a test value; computing a total number of elements in the datasets each having a value greater than the test value; and setting the value of the element, having the k-th rank, equal to the test value, if the total number of elements having values less than the test value is &#x2266; the k-th rank minus one, and the total number of elements having values greater than the test value is &#x2266; the total number of elements minus the k-th rank. The system discloses means for practicing the method.

System and method for determining an element value in private datasets

A method for discovery of a cluster of objects in an arbitrary undirected graph. A subset of the objects is determined by performing a random walk starting from a first object of the objects and following a plurality of random edges of subsequent objects, the subset comprising the first object and the subsequent objects. An enlarged subset is determined by enlarging the subset to include other objects well-connected to the subset. It is determined whether the enlarged subset is a cluster.

Method for discovery of clusters of objects in an arbitrary undirected graph using a difference between a fraction of internal connections and maximum fraction of connections by an outside object

A method and system for finding a conjunctive cluster is disclosed. The method includes identifying a first group of points, identifying a second group of points, drawing a first sample from the first group of points of a first predetermined size and identifying subsets of the first sample. For each subset of the first sample of a second predetermined size the method includes identifying a subgroup of the second group of points that share an intersection with all of the points in the first sample of points, identifying a sub group of said first group of points that share an intersection with a specified number of the points in the subgroup of the second group of points and outputting a third group of points. It should be appreciated that the product of the magnitude of the subgroup of the second group and the magnitude of the subgroup of the first group is maximized.

Method and system for finding conjunctive clusters

A method for predicting parts for onsite repair which takes into account a repair history and the costs associated with mis-predictions. Parts for onsite repair of a product are predicted by determining an expected waste for one or more parts of the product. The parts having a lowest expected waste are selected and sent to the onsite repair. The expected waste indicates parts that are responsible for high support costs and highlights the mistakes being made and scores the mistakes by actual cost.

Predicting parts needed for an onsite repair using expected waste derived from repair history

The present invention is a system or method for assisting in the maintenance and servicing of computers. The system, for example, comprises a cluster database containing information relating to one or more computer clusters, the information relating to each cluster comprising one or more cluster descriptions and one or more representations of configuration information values that characterize typical computer members of the cluster, and also a tracker database containing configuration information values gathered from and relating to one or more computers. The system further comprises a computer and cluster comparison routine having access to the cluster and tracker databases that compares one or more of the representations of configuration information values relating to one or more of the clusters to one or more of the corresponding configuration information values gathered from at least one given computer and that then indicates how closely the given computer's configuration conforms with the configuration of typical computer members of the one or more clusters.

Method and system for comparing individual computers to cluster representations of their peers

A method of global data placement. The method includes assigning one or more workloads to one or more compute servers such that each workload flows to one compute server, assigning the data chunks that the workloads accesses to one or more storage servers, and determining how the workloads access the data.

Global data placement

A method and system for identifying clusters of similarly-configured computers. The method, for example, comprises gathering system and business configuration information values from a set of computers. Next, at least a portion of the system and business configuration information values gathered from the set of computers is analyzed along with the numbers of computers that are configured in various ways. Then, using the result of the analysis as a guide, logical expressions of configuration information values are selected for use as definitions of one or more clusters of similarly-configured computers, the selection process generally maximizing the number of computers included within each cluster and also generally maximizing the number of configuration information value specifications included within the definition of each cluster. Then, for one or more clusters so defined and selected, one or more statistics or limit values are generated from one or more configuration information values or both gathered from the subset of computers included in the one or more clusters.

Method and system for clustering computers into peer groups and comparing individual computers to their peers

A technique that uses a weighted divide and conquer approach for clustering a set S of n data points to find k final centers. The technique comprises 1) partitioning the set S into P disjoint pieces S, . . . , S; 2) for each piece S, determining a set Dof k intermediate centers; 3) assigning each data point in each piece Sto the nearest one of the k intermediate centers; 4) weighting each of the k intermediate centers in each set Dby the number of points in the corresponding piece Sassigned to that center; and 5) clustering the weighted intermediate centers together to find said k final centers, the clustering performed using a specific error metric and a clustering method A.

Computer implemented scalable, incremental and parallel clustering based on weighted divide and conquer

A technique that uses a weighted divide and conquer approach for clustering a set S of n data points to find k final centers. The technique comprises 1) partitioning the set S into P disjoint pieces S , . . . , S ; 2) for each piece S , determining a set D of k intermediate centers; 3) assigning each data point in each piece S to the nearest one of the k intermediate centers; 4) weighting each of the k intermediate centers in each set D by the number of points in the corresponding piece S assigned to that center; and 5) clustering the weighted intermediate centers together to find said k final centers, the clustering performed using a specific error metric and a clustering method A.

A divide and conquer method clusters a set of points to identify at least one centroid. A plurality of &ldquo;r&rdquo; subsets of points from the set of points are assigned into &ldquo;r&rdquo; partitions. The computer processes the subset of points to generate a plurality of partition centroids, Q, k for each of the r partitions, so as to optimize a clustering metric. The partition centroids are merged into a set of partition centroids, and are stored in main memory of the computer. Thereafter, the partition centroids are processed by accessing the memory to generate a plurality of centroids, c, one for each of the k clusters, so as to optimize a clustering metric. Data incremental and feature incremental divide and conquer techniques are disclosed. Furthermore, the divide and conquer technique has application for implementation in parallel processing computer systems.

Growing community of inventors

San Ramon, CA, United States of America

Nina Mishra