Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Micro Focus Lcc

Other

Entit Software LLC

Hewlett-packard Company

George H Forman

Henri Jacques Suermondt

Evan Randy Kirshenbaum

Kave Eshghi

Shyam Sundar Rajaram

Stephane Chiocchetti

Cullen Edwin Bash

Hila Nachlieli

Martin B Scholz

James Richard Stinger

Zhichen Xu

Mark David Lillibridge

Bin Zhang

Prakash D Reddy

Joseph J Martinka

Tom Fawcett

Patricia Collins

Robert A Luciano, Jr

Chandrakant D Patel

Ratnesh Kumar Sharma

Meichun Hsu

Suk Hwan Lim

Renato Keshet

Bradley Neal Suggs

Kei Yuasa

Eytan Adar

Yin Wang

Fereydoon Safai

Nina Mishra

Thomas M Tripp

Lada A Adamic

James R Hoover

Adrian Krug

Rong Pan

Timothy P J G Kindberg

Olga Shain

Aparna Seetharaman

Shyamsundar Rajaram

Glenn M Feldman

Art Bunce

Jerome Levine

Weston Lord

Xuemei Liu

An example method comprises performing for each class from a plurality of classes: constructing binary training set for the class, the binary training set including labeled cases for that class from the main training set other labeled cases from the main training set; training classifier for the class on the binary training set; computing a local calibration threshold using scores of the labeled cases in the binary training set; and adjusting all scores of the label cases in the binary training set with the local calibration threshold to meet a global decision threshold. The method also comprises determining, with the processor, a global hierarchical calibration threshold by using the adjusted scores for all classes to optimize a performance measurement of all trained classifiers. The method further comprises classifying, with the processor, a new case by using a previously trained classifier, a local calibration threshold, and the global hierarchical calibration threshold.

System and method for hierarchical classification

An example method is provided in according with one implementation of the present disclosure. The method comprises receiving a training dataset of cases, where each of a plurality of classes is associated with a set of labeled cases in the training dataset. The method also comprises defining a proper subset of classes in the training dataset, and training a first classifier model on the proper subset of classes in the training dataset. The method further comprises testing the first classifier model on at least one class in the training dataset that was excluded from the proper subset, and determining a performance measurement of the first classifier model.

Classifier

Example implementations relate to records based on bit-shifting. For example, a computing device may include at least one processor to receive a query, create a normalized query, and generate a mapping of the normalized query for each record in a set of records in a database using a state array, the mapping being based on bit-shifting of bits associated with similarities between each character in the normalized query and each character in a field of the respective record in the set of records, each successive level of the state array indicating a stronger match between the query and the respective record than an immediately prior level in the state array. The processor may calculate a score associated with each record based on the respective mapping and may provide a subset of the set of records in response to the query based on the score associated with each record.

Records based on bit-shifting

Example implementations relate to database records associated with a trie. For example, a computing device may include at least one processor to receive a query string and determine, based on the query string, a lookup string associated with a plurality of words in an order. The at least one processor may identify, based on the lookup string and a trie associated with the lookup string, a set of records from a database of records, each record in the set being associated with a score that is associated with a degree to which each record matches the query string, wherein the set is identified based on a penalty value calculated for each record based on a hypothesized collection of typing errors sufficient to transform a prefix of a string associated with each record into the lookup string. The at least one processor may provide a result based on the set.

Database records associated with a tire

An example method is provided in according with one implementation of the present disclosure. The method comprises generating a group of most frequent elements in a dataset, calculating features of each of the most frequent elements in the dataset, applying a trained model to the features of each of the most frequent elements, and generating a list of predicted relevant elements from the list of most frequent elements. The method further comprises determining at least one element-chain group for each predicted relevant element and a group score for the element-chain-group, ordering a plurality of element-chain groups for the dataset based on the group score for each of the element-chain groups, and identifying a predetermined number of element-chain groups to be outputted to a user.

Identifying groups

An example method is of image processing provided in according with one implementation of the present disclosure. The method includes receiving an image, placing a window across the image, and computing a set of all occurring grayscale values within the window. The method further includes computing a threshold value based on the set of all occurring grayscale values within the window and determining an output pixel value of at least one pixel from the window based on the threshold value.

Image processing

Examples herein involve generating a spiral visualization of items of a dataset. Dimensions of item indicators corresponding to items of a dataset are analyzed. Starting coordinates for a spiral path for a spiral visualization of the items are determined based on the dimensions of the item indicators and a display area of a display device. A spiral path may be calculated based on the starting coordinates and the dimensions of the item indicators. The spiral visualization may be generated by rendering the item indicators on the spiral path to present a first item indicator of the item indicators from a corresponding first item of the list at the starting coordinates and a last item indicator of the item indicators of a corresponding last item on the list on the spiral path toward the center of the spiral.

Spiral visualization generator

A technique for updating road maps is disclosed. A number of GPS traces can be matched with a number of roads in a map. Matched GPS traces may be processed by a matched segment module to produce proposed changes to the map. The map can be updated using a map updating module based on the proposed changes from the matched segment module. Unmatched GPS traces may be processed by an unmatched segment module to produce proposed changes to the map. The map can be updated using a map updating module based on the proposed changes from the unmatched segment module. The proposed changes to the map may include metadata defining new roads in the map, new intersections in the map, updates to turn restrictions in the map, updates to the allowable directional traffic flow on the roads within the map, updates to road closures in the map.

Updating road maps

A method and system of providing training information for training a categorizer includes receiving a query relating to at least one category and identifying at least one case within a data set that matches the query. The method and system receives one of a first indication that the identified at least one case belongs to the category, and a second indication that the identified at least one case does not belong to the category. Training information is modified based on receiving one of the first indication and second indication.

Providing training information for training a categorizer

The present disclosure provides a computer-implemented method of processing Web activity data. The method includes obtaining a collection of Web activity data generated by a plurality of users at a plurality of Webpages, wherein the Webpages are from a plurality of unaffiliated Websites. The method also includes extracting a plurality of search terms from the Web activity data and associating each of the plurality of search terms with a corresponding Webpage. The method also includes generating statistical data from the Web activity data based, at least in part, on the search terms, the statistical data corresponding to the online activity at one or more Webpages.

Method and system for processing web activity data

Provided are, among other things, systems, methods and techniques for document-based processing. In one implementation, a document is input; features are extracted from it; an index is queried using at least a subset of the extracted features and, in response, identifications for selected document classifiers are received from a larger pool of document classifiers; the document is processed using individual ones of the selected document classifiers, thereby generating corresponding classifier outputs; and then, based on such classifier outputs, (1) the document is categorized within a computer database and/or (2) feedback information is provided to a user.

Classifier indexing

Provided are, among other things, systems, methods and techniques for generating a set of representative components from a set of documents, by selecting at least one component for initial inclusion within a representative component set. An additional component is then identified based on (1) frequency of occurrence of the additional component across the set of documents and (2) strength of negative correlation with the representative component set across the set of documents. The representative component set is supplemented with the additional component, and the identification and supplementing steps are repeated multiple times until a specified end condition is satisfied. The representative component set is output and/or the documents are processed based on the representative component set.

Generation of representative document components

For each first entity of a subset of a number of first entities, an expected improvement of a predictive performance of a collaborative filtering model if additional ratings of the first entity in relation to a plurality of second entities were obtained is estimated. Particular first entities from the subset of the first entities of which to obtain the additional ratings in relation to the second entities are selected based at least on the expected improvements that have been determined. The additional ratings of the particular first entities in relation to the second entities are obtained.

Collaborative filtering model having improved predictive performance

A computing system including a component to perform a function and generates a noise. A microphone to receive an input including the noise. The computing system can monitor a component for an event that produces a noise.

Monitor an event that produces a noise received by a microphone

To detect duplicative hierarchically arranged sets of files in a storage system, a method includes generating, for hierarchically arranged plural sets of files, respective collections of values computed based on files in corresponding sets of files. For a further set of files that is an ancestor of at least one of the plural sets of files, a respective collection of values that is based on the collection of values computed for the at least one set is generated. Duplicative sets according to comparisons of the collections of values are identified.

Detecting duplicative hierarchical sets of files

Growing community of inventors

SE Port Orchard, WA, United States of America

George H Forman