International Business Machines Corporation

Pranita Sharad Dewan

Mudhakar Srivatsa

Raghu Kiran Ganti

Joshua M Rosenkranz

Linsong Chu

Dinesh C Verma

Ramya Raghavendra

Dakshi Agrawal

Praveen Jayachandran

Nirmit V Desai

Catherine Helen Crawford

Chander Govindarajan

Joao Souto Maior

Priyanka Prakash Naik

Kavya Govindarajan

Aneesh Agrawal

In an approach to identifying occluded objects, a computer retrieves a first image that includes an object at least partially occluded by one or more occlusions. A computer removes the one or more occlusions from the first image to create a partial object in a second image. A computer runs a detection model with the second image to predict one or more identifications of a symbol represented by the partial object. A computer determines top predictions of the one or more identifications of the symbol by the detection model. A computer identifies at least one geometric property associated with the one or more identifications of the symbol included in the one or more top predictions. A computer applies the at least one geometric property to the partial object. A computer determines a probability of the one or more top predictions correctly identifying the symbol represented by the partial object.

Identifying occluded objects in engineering drawings

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

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

Embodiments herein describe computer-implemented methods, computer program products and systems for efficient spatial indexing. In an embodiment, the computer-implemented method may include one or more processors configured for obtaining from a database index data representing one or more assets, wherein each of the one or more assets comprise an asset identifier and a spatial attribute; generating a location hash for each of the one or more assets using the respective asset identifier and the respective spatial attribute; determining one or more sets of location hashes based on the asset identifier and the spatial attribute at one of one or more precision values; generating shadow index data comprising the one or more sets of location hashes at the one of one or more precision values; receiving a query corresponding to the index data; and returning a first set of results corresponding to the query in a first query response time.

Efficient spatial indexing

An ensemble of autoencoder models can be trained using different seeds. The trained ensemble of autoencoder models can be run on new time series data to generate a prediction associated with the new time series data. The new time series data can include multiple dimensions per time step. Reconstruction errors can be determined for the prediction. Dimensions having highest reconstruction errors can be selected among the multiple dimensions based on a threshold. The prediction can be segmented based on bursts of the reconstruction errors over time, where temporal segments can be obtained. At least one common pattern including a set of dimensions among the selected dimensions across the temporal segments can be obtained to represent a failure fingerprint.

Localizing faults in multi-variate time series data

Aspects of the invention include generating a vector representation of a root node of the error based on a hierarchical topology of a computing system; generating a respective vector representations of each subject matter expert of a plurality of subject matter experts based at least in part on the hierarchical topology; selecting a subject matter expert based at least in part on the vector representation of root cause of the error; and uploading a diagnostic software to the computing system.

Reinforcement learning approach to root cause analysis

Embodiments for implementing intelligent customer journey prediction and customer segmentation of a processor in a computing environment. A response outcome of a customer journey for a user may be predicted according to an assigned score based on one or more discriminatory sequence patterns identified between one or more groups of customers using one or more machine learning operations.

Customer journey prediction and customer segmentation

Methods and systems for detecting events. A satellite image is obtained and the satellite image is processed using a first convolutional neural network (CNN) to produce a satellite vector that identifies at least one fire. A mobile sensor is automatically directed to a mobile location based on the satellite vector.

Fire detection via remote sensing and mobile sensors

A distributed file system (DFS) is provided that is configured to store data in a General Parallel File system (GPFS) and interface with a client configured to interface with a HADOOP Distributed File System (HDFS). The DFS includes a first Node; and a plurality of second Nodes including the GPFS. The first Node is configured to convert an HDFS command from the client into a GPFS command, apply the GPFS command to the GPFS to access a GPFS file, format an HDFS data structure to include identifiers of a set of the second nodes storing the GPFS file, a filename of the GPFS file, and an offset into the GFPS file, and send the HDFS data structure to the client. Each of the second Nodes is configured to access the GPFS using a part of the HDFS data structure received from the client.

Enabling a Hadoop file system with POSIX compliance

Embodiments for implementing customized traversal routes by at least a portion of a processor in a computing environment. One or more traversal routes may be generated from a route network for a user to traverse according to one or more parameters and user preferences. One or more edge metrics may be assigned to the one or more traversal routes while periodically updating the one or more parameters, the user preferences, or a combination thereof associated with the one or more traversal routes.

Growing community of inventors

New York, NY, United States of America

Pranita Sharad Dewan