International Business Machines Corporation

International Business Corporation

Raghu Kiran Ganti

Mudhakar Srivatsa

Dakshi Agrawal

Linsong Chu

Shreeranjani Srirangamsridharan

Pranita Sharad Dewan

Dinesh C Verma

Seraphin Bernard Calo

Douglas Morgan Freimuth

Ramya Raghavendra

Supriyo Chakraborty

Fan Ye

Joshua M Rosenkranz

Yeon-Sup Lim

Kisung Lee

Saritha Arunkumar

Nirmit V Desai

Raheleh B Dilmaghani

Omer Tripp

Kai Liu

Bong Jun Ko

James J Fan

Sheng Huang

Petros Zerfos

Shubhadip Ray

Jeffrey James Jonas

Norbert Herman

Xiao Yan Chen

Keith William Grueneberg

Stephen D Pipes

Jae-Wook Ahn

Shiqiang Wang

Carlos Henrique Andrade Costa

Shen Li

Jingjing Wang

Mathews Thomas

Catherine Helen Crawford

Swati Rallapalli

Bijan Davari

Thiago Bianchi

ChunHui Yang Higgins

Michele Merler

Utpal Mangla

Satishkumar Sadagopan

Shirley M Han

Mahmood Saajan Ashek

Tuan Minh Hoang Trong

Venkatesh Ashok Rao Rao

Mohammad Siddiqui

Dylan Zucker

Dean Steuer

Antara Palit

Mudhaker Srivatsa

Asif Sharif

Ramey Ghabros

Somesh Jha

Mojdeh Sayari Nejad

Isaiah Santala

Foad Khoshouei

Yusuf Mai

Adham Suliman

Naveen Mathew Nathan Sathiyanathan

Tiago Bertoni Scarton

A system, computer program product, and method are provided for distributed data workflow semantics. A pipeline, such as a machine learning (ML) pipeline, is represented in a data flow graph (DFG). The represented pipeline is subject to annotations, with the annotations including pipeline nodes and object references. The pre-processed pipeline is subject to execution or processing with the annotated object references capturing object lineage. Output from the executed pipeline is constructed and a corresponding control signal is formatted to dynamically and selectively control an operatively coupled physical hardware device or software.

Annotation of a machine learning pipeline with operational semantics to support distributed lineage tracking

A system, computer program product, and method are provided for distributed data workflow semantics. A pipeline, such as a machine learning pipeline, is represented in a data flow graph (DFG) with nodes and edges. The represented nodes are configured to be annotated with an operational semantic. On order of execution of the pipeline is discovered through the node annotation(s) represented in the annotated DFG, and execution of the pipeline is based on the discovered order. A control signal formatted based on the executed pipeline is configured to dynamically and selectively control an operatively coupled physical hardware device.

Annotation of a machine learning pipeline with operational semantics

Provided are a computer-implemented method, a computer program product, and a computer system for drone deployment for distributed asset maintenance and repair. Embodiments identify a fix for a problem at an asset and identify a drone to perform the fix. Embodiments generate an initial flight plan that describes a drone flight path for the drone, and embodiments generate an updated flight plan for the drone by updating the drone flight path using real-time air traffic data, real-time road traffic data, and real-time drone flight path conditions obtained from one or more edge devices. Embodiments generate an overall flight plan for the drone and one or more other drones using a predicted cost and a predicted period of time for the updated drone flight path. Embodiments send a drone flight path from the overall flight plan to the drone with instructions to fix the problem.

Drone deployment for distributed asset maintenance and repair

A system and method are provided for discovering k-nearest-neighbors to a given point within a certain distance d. The method includes constructing an index of geometries using geohashes of geometries as an indexing key to obtain an indexed set of geometries, and calculating a geohash representation of the given point with a resolution equal to a magnitude value of d. The method includes searching for a closest-prefix geometry from the indexed set using the geohash representation of the given point, and identifying geometries from the indexed set having a same prefix as the closest-prefix geometry. The method further includes calculating distances between the given point and the geometries identified from the indexed set having the same prefix as the closest-prefix geometry, and determining k geometries with respective shortest distances less than d from the geometries identified from the indexed set having the same prefix as the closest-prefix geometry.

Fast and accurate geomapping

Embodiments for providing rare topic detection using hierarchical topic modeling by a processor. A hierarchical topic model may be learned from one or more data sources. One or more dominant words in a selected cluster may be iteratively removed using the hierarchical topic model. The dominant words may relate to one or more primary topics of the cluster. The learned hierarchical topic model may be seeded with one or more words, n-grams, phrases, text snippets, or a combination thereof to evolve the hierarchical topic model and the removed dominant words are reinstated upon completion of the seeding.

Rare topic detection using hierarchical clustering

Aspects of the present disclosure relate to annotating or tagging customer data. In some embodiments, the annotating can include summarizing touchpoints into k-hot encoding feature vectors, mapping the feature vectors onto an embedding layer, predicting a hierarchical data sequence using the embedding layer and the feature vectors, extracting the feature vectors that are most influential in predicting the embedding layer, and outputting the touchpoints associated with the most influential feature vectors.

Annotating customer data

A computer implemented method performs data skipping in a hierarchically organized computing system. A group of processor units determines leaf node data sketches for data in leaf nodes in the hierarchically organized computing system. The leaf node data sketches summarize attributes of data in the leaf nodes. The group of processor units aggregates the leaf node data sketches at intermediate nodes in the hierarchically organized computing system to form aggregated data sketches at the intermediate nodes and retains data sketches received at the intermediate nodes from a group of child nodes to form retained data sketches. The retained data sketches are one of leaf node data sketches and the aggregated data sketches. The group of processor units searches the data using the retained data sketches and the data skipping within the hierarchically organized computing system in response to queries made to the intermediate nodes in the hierarchically organized computing system.

Hierarchical data skipping using data sketches

Systems, methods and/or computer program products for controlling and visualizing topic modeling results using a topic modeling interface. The interface allows user directed exploration, understanding and control of topic modeling algorithms, while offering both semantic summaries and/or structure attribute explanations about results. Explanations and differentiations between results are presented using metrics such as cohesiveness and visual displays depicting hierarchical organization. Through user-manipulation of features of the interface, iterative changes are implemented through user-feedback, adjusting parameters, broadening or narrowing topic results, and/or reorganizing topics by splitting or merging topics. As users trigger visual changes to results being displayed, users can compare and contrast output from the topic modeling algorithm. With each change to parameters, users view different explanations informing the user why the changes being displayed occurred, providing users deeper understanding of the topic modeling process, how to manipulate parameters to achieve accurate topic results and adjust granularity of information presented.

Transparent and controllable topic modeling

A cloud-enterprise resource management system enables sharing of computing resources belonging to different datacenters by one or more clients of a resource pooling and sharing service. Each datacenter of includes a first partition of computing resources and a second partition of computing resources. The first partition is designated as reserved for use by an enterprise operating the datacenter. The second partition is designated as available for use by one or more clients of the resource pooling and sharing service. A workload manager in each datacenter predicts workload and transfers (i) a first computing resource from the first partition to the second partition wherein when the predicted workload is below a first threshold and (ii) a second computing resource from the second partition to the first partition when the predicted workload is above a second threshold.

Shared enterprise cloud

Aspects of the invention include receiving, by a processor, airspace data associated with a predefined airspace, obtaining roadway data associated with the predefined airspace, determining a set of air travel channels within the predefined airspace based on the roadway data, defining a set of travel lanes within the set of air travel channels, wherein each travel lane in the set of travel lanes comprises an altitude range, receiving unmanned aircraft (UA) data associated with a set of UAs within the predefined airspace, wherein the UA data comprises one or more flight paths for each UA in the set of UAs, and assigning each UA in the set of UAs to a travel lane in the set of travel lanes based on the one or more flight paths.

Traffic management for unmanned aircraft

Aspects of the present disclosure relate to identifying friction points in customer data. In some embodiments, identifying friction points can include receiving a set of input sequence data and predicted class labels for the set of input sequence data; selecting input sequences, from the set of input sequence data, that have class labels matching a ground truth class label; reducing the selected sequences to anchor points; and grouping the reduced selected sequences into critical data set signatures using discriminatory subsequence mining.

Identifying friction points in customer data

Provided are a method, system, and computer program product for representing text, in which a text is received and analyzed by utilizing a pre-trained embedding model and a feature vector model, wherein selected words in the text have corresponding weights. Operations whose parameters include weights of a feature vector and an embedding are performed to generate a weighted embedding data structure. A summation is performed of all corresponding columns of a plurality of rows of the weighted embedding data structure to generate a data structure that represents the text. The data structure that represents the text is utilized to generate at least one of a classification metadata for the text and a summarization of the text.

Domain knowledge based feature extraction for enhanced text representation

Aspects of the invention include generating a combined raster image from point cloud data and reference data describing an original location of a power line. Selecting a set of candidate pixels from the combined raster image describing an updated location of a power line, wherein the selection is based at least in part on a location of pixels in the combined raster image that describe the original location. Detecting pixels from the set of candidate pixels that describe an updated location of a power line. Modifying the combined raster image to reflect the updated location of the power line.

Power line georectification

Growing community of inventors

Elmsford, NY, United States of America

Raghu Kiran Ganti