Patents by Inventor Suman Roy
Suman Roy has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11989240Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using an attention-based text encoder machine learning model that is trained using a multi-task training routine that is associated with two or more training tasks (e.g., a multi-task training routine that is associated with two or more sequential training tasks, a multi-training routine that is associated with two or more concurrent training tasks, and/or the like).Type: GrantFiled: June 22, 2022Date of Patent: May 21, 2024Assignee: Optum Services (Ireland) LimitedInventors: Suman Roy, Ayan Sengupta, Michael Bridges, Amit Kumar
-
Publication number: 20240160513Abstract: Systems, computer program products, and methods are described herein for real-time overload detection using image processing analysis. The present disclosure is configured to receive a first set of images associated with a device, wherein the one or more images are associated with a resiliency status of the device; deploy, using a machine learning (ML) subsystem, a trained ML model on the first set of images of the device; determine, using the trained ML model, a change in the resiliency status of the device based on the first set of images; and generate a notification indicating the change in the resiliency status of the device; and transmit control signals configured to cause a first user input device to display the notification.Type: ApplicationFiled: November 14, 2023Publication date: May 16, 2024Applicant: BANK OF AMERICA CORPORATIONInventors: Maharaj Mukherjee, Carl M. Benda, Elvis Nyamwange, Utkarsh Raj, Suman Roy Choudhury, Vidya Srikanth, Colin Murphy
-
Publication number: 20240160552Abstract: Systems, computer program products, and methods are described herein for performance monitoring using aggregated telemetry. The present disclosure is configured to receive, from the first performance monitoring engine, a first metadata associated with the first resiliency status; receive, from the second performance monitoring engine, a second metadata associated with the second resiliency status; determine, using a machine learning (ML) subsystem, an overall resiliency status of the device based on at least the first metadata, the second metadata, the first resiliency status, and the second resiliency status; determine one or more actions to be executed on the device, wherein the one or more actions are associated with the overall resiliency status; generate a notification indicating the overall resiliency status of the device and the one or more actions associated with the overall resiliency status; and transmit control signals configured to cause a user input device to display the notification.Type: ApplicationFiled: November 14, 2023Publication date: May 16, 2024Applicant: BANK OF AMERICA CORPORATIONInventors: Maharaj Mukherjee, Carl M. Benda, Elvis Nyamwange, Utkarsh Raj, Suman Roy Choudhury, Vidya Srikanth, Colin Murphy
-
Patent number: 11941357Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing text similarity determination. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform text similarity determination by using at least one of Word Mover's Similarity measures, Relaxed Word Mover's Similarity measures, and Related Relaxed Word Mover's Similarity measures.Type: GrantFiled: June 23, 2021Date of Patent: March 26, 2024Assignee: OPTUM TECHNOLOGY, INC.Inventors: Suman Roy, Amit Kumar, Sourabh Kumar Bhattacharjee, Shashi Kumar, William Scott Paka, Tanmoy Chakraborty
-
Publication number: 20240098055Abstract: Techniques are described with respect to a system, method, and computer product for generating relevance alerts. An associated method includes analyzing a multi-party discussion based on a generated profile associated with a user and assigning at least one relevance value associated with the user to the multi-party discussion based on the analysis and an amount of multi-party discussion participation associated with the user. The method further includes generating an alert for the user to participate in the multi-party discussion in response to determining the relevance value exceeding a relevance threshold associated with the multi-party discussion.Type: ApplicationFiled: September 20, 2022Publication date: March 21, 2024Inventors: James William Murdock, IV, Radha Mohan De, Jaymin Desai, Suman Patra, Sujoy Roy, Mary Diane Swift
-
Publication number: 20240062052Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for generating a representative embeddings for a plurality of temporal sequences by using a graph attention augmented temporal network based at least in part on dynamic co-occurrence graphs for preceding temporal sequences and initial embeddings, where the dynamic co-occurrence graphs are projections of a global guidance co-occurrence graph on features of the preceding temporal sequences, and the initial embeddings are generated by processing a latent representation of corresponding features that is generated by a sequential long short term memory model as well as a feature tree using a tree-based long short term memory model.Type: ApplicationFiled: August 18, 2022Publication date: February 22, 2024Inventors: Amit Kumar, Suman Roy, Ayan Sengupta, Paul J. Godden
-
Publication number: 20240045784Abstract: Aspects of the disclosure relate to outage prevention. A computing platform may train, using historical parameter information and historical outage information, an outage prediction model. The computing platform may receive, from at least one system, current parameter information, and may normalize the current parameter information. The computing platform may convert, using a CNN of the outage prediction model, the normalized current parameter information to a frequency domain. The computing platform may input, into at least one RNN of the outage prediction model, the frequency domain information, to produce a likelihood of outage score. The computing platform may compare the likelihood of outage score to a predetermined outage threshold. Based on identifying that the likelihood of outage score meets or exceeds the predetermined outage threshold, the computing platform may direct the at least one system to execute a performance modification to prevent a predicted outage.Type: ApplicationFiled: August 3, 2022Publication date: February 8, 2024Inventors: Maharaj Mukherjee, Vidya Srikanth, Utkarsh Raj, Carl M. Benda, Elvis Nyamwange, Suman Roy Choudhury
-
Publication number: 20230419034Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using an attention-based text encoder machine learning model that is trained using a multi-task training routine that is associated with two or more training tasks (e.g., a multi-task training routine that is associated with two or more sequential training tasks, a multi-training routine that is associated with two or more concurrent training tasks, and/or the like).Type: ApplicationFiled: June 22, 2022Publication date: December 28, 2023Inventors: Suman Roy, Ayan Sengupta, Michael Bridges, Amit Kumar
-
Publication number: 20230418880Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using an attention-based text encoder machine learning model that is trained using a multi-task training routine that is associated with two or more training tasks (e.g., a multi-task training routine that is associated with two or more sequential training tasks, a multi-training routine that is associated with two or more concurrent training tasks, and/or the like).Type: ApplicationFiled: June 22, 2022Publication date: December 28, 2023Inventors: Suman Roy, Ayan Sengupta, Michael Bridges, Amit Kumar
-
Publication number: 20230419035Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using an attention-based text encoder machine learning model that is trained using a multi-task training routine that is associated with two or more training tasks (e.g., a multi-task training routine that is associated with two or more sequential training tasks, a multi-training routine that is associated with two or more concurrent training tasks, and/or the like).Type: ApplicationFiled: June 22, 2022Publication date: December 28, 2023Inventors: Suman Roy, Ayan Sengupta, Michael Bridges, Amit Kumar
-
Patent number: 11842162Abstract: There is a need for more effective and efficient natural language processing (NLP) solutions. This need can be addressed by, for example, solutions for performing NLP-based document prioritization by utilizing joint sentiment-topic (JST) modeling.Type: GrantFiled: October 3, 2022Date of Patent: December 12, 2023Assignee: Optum Technology, Inc.Inventors: Ayan Sengupta, Suman Roy, Tanmoy Chakraborty, Gaurav Ranjan, William Scott Paka
-
Publication number: 20230351099Abstract: Various embodiments provide for summarization of an interaction, conversation, encounter, and/or the like in at least an abstractive manner. In one example embodiment, a method is provided. The method includes generating, using an encoder-decoder machine learning model, a party-agnostic representation data object for each utterance data object. The method further includes generating an attention graph data object to represent semantic and party-wise relationships between a plurality of utterance data objects. The method further includes modifying, using the attention graph data object, the party-agnostic representation data object for each utterance data object to form a party-wise representation data object for each utterance data object. The method further includes selecting a subset of party-wise representation data objects for each of a plurality of parties.Type: ApplicationFiled: May 2, 2022Publication date: November 2, 2023Inventors: Suman Roy, Vijay Varma Malladi, Ayan Sengupta
-
Publication number: 20230351109Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using a hybrid reason code prediction machine learning framework. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform natural language processing using a hybrid reason code prediction machine learning framework that comprises one or more of the following: (i) a hierarchical transformer machine learning model, (ii) an utterance prediction machine learning model, (iii) an attention distribution generation machine learning model, (iv) an utterance-code pair prediction machine learning model, and (v) a hybrid prediction machine learning model.Type: ApplicationFiled: April 28, 2022Publication date: November 2, 2023Inventors: Suman Roy, Thomas G. Sullivan, Vijay Varma Malladi, Matthew J. Stewart, Abraham G. Tesfay, Gaurav Ranjan
-
Publication number: 20230308526Abstract: Methods and systems for automatically determining correspondences between communication ports of a networked device and encoders and decoders connected to those communication ports. In some embodiments, the networked device and the encoders and decoders are connected to a video communications network provided by a switch. The networked device can query the video communications network for information related to the encoders and decoders to determine and save the port-to-device correspondences. In some embodiments, the networked device can extract device information from video signals received at its input ports to map the input ports to respectively connected decoders. In similar fashion, the networked device may transmit or embed port-specific information from its output ports to respectively connected encoders. Then, the networked device can query the video communications network for the port-specific information received at the encoders to map the output ports to respectively connected encoders.Type: ApplicationFiled: April 24, 2023Publication date: September 28, 2023Applicant: Stryker CorporationInventors: Brandon HUNTER, Eric HEREFORD, Suman ROY
-
Patent number: 11741143Abstract: As described herein, various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using a combination of a cross-token attention machine learning, a cross-utterance attention machine learning model, and an integer linear programming joint keyword-utterance optimization model to select an extractive keyword summarization of a multi-party communication transcript data object that comprises a selected utterance subset of U utterances (e.g., U sentences) of a document data object and a selected keyword subset of K candidate keywords of the document data object.Type: GrantFiled: July 28, 2022Date of Patent: August 29, 2023Assignee: Optum, Inc.Inventors: Vijay Varma Malladi, Suman Roy, Lia O. Solis Obineche, Irfan Bulu
-
Patent number: 11727935Abstract: There is a need for more effective and efficient predictive natural language summarization. This need can be addressed by, for example, solutions for performing predictive natural language summarization using a constrained optimization model. In one example, a method includes identifying one or more per-party utterance subsets in a multi-party call transcript; generating a plurality of eligible extractive summaries that comply with one or more optimization constraints; for each eligible extractive summary of the plurality of eligible extractive summaries, determining an overall summary utility measure; generating the optimal extractive summary based at least in part on each overall summary utility measure for an eligible extractive summary of the plurality of eligible extractive summaries; and performing one or more summary-based actions based at least in part on the optimal extractive summary.Type: GrantFiled: December 15, 2020Date of Patent: August 15, 2023Assignee: Optum Technology, Inc.Inventors: Vijay Varma Malladi, Suman Roy, Gaurav Ranjan, Gunjan Balde
-
Patent number: 11698934Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive structural analysis on document data objects that are associated with an ontology graph. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis operations on document data objects that are associated with an ontology graph using document embeddings that are generated by graph-embedding-based paragraph vector machine learning models.Type: GrantFiled: September 3, 2021Date of Patent: July 11, 2023Assignee: Optum, Inc.Inventors: Suman Roy, Amit Kumar, Ayan Sengupta, Riccardo Mattivi, Ahmed Selim, Shashi Kumar
-
Publication number: 20230129994Abstract: Aspects of the disclosure relate to transliteration of machine interpretable languages. A computing platform may train a machine learning model using source syntax trees and target dialect syntax trees, which may configure the model to output source dialect keys and their corresponding target dialect queries. The computing platform may execute the corresponding target dialect queries to identify whether they are valid. For a valid target dialect query, the computing platform may store the valid target dialect query and first source dialect keys corresponding to the valid target dialect query in a lookup table. For an invalid target dialect query resulting in error, the computing platform may: 1) identify a cause of the error; 2) generate a transliteration rule to correct the error; and 3) store, in the lookup table, the invalid target dialect query, second source dialect keys corresponding to the invalid target dialect query, and the transliteration rule.Type: ApplicationFiled: December 21, 2021Publication date: April 27, 2023Inventors: Maharaj Mukherjee, Carl M. Benda, Elvis Nyamwange, Suman Roy Choudhury, Utkarsh Raj
-
Publication number: 20230130267Abstract: Aspects of the disclosure relate to transliteration of machine interpretable languages. A computing platform may receive a query formatted in a first format for execution on a first database. The computing platform may translate the query to a second format for execution on a second database by: 1) extracting non-essential portions of the query from the query, and replacing the non-essential portions of the query with pointers to create a query key; 2) storing, along with their corresponding pointers, the non-essential portions of the query as query parameters; 3) executing a lookup function on a query library to identify a translated query corresponding to the query key and including the corresponding pointers; and 4) updating the translated query to include the query parameters based on the corresponding pointers to create an output query. The computing platform may execute the output query on the second database.Type: ApplicationFiled: December 21, 2021Publication date: April 27, 2023Inventors: Maharaj Mukherjee, Utkarsh Raj, Carl M. Benda, Elvis Nyamwange, Suman Roy Choudhury
-
Publication number: 20230129782Abstract: Aspects of the disclosure relate to transliteration of machine interpretable languages. A computing platform may configure a client application to use a custom driver when communicating with an enterprise database. The computing platform may receive a database query formatted in a first database format corresponding to a first database. The computing platform may translate, using a query translation library, the database query from the first database format into a second database format corresponding to a second database, which may cause the custom driver to execute a transliteration process using pre-verified query keys stored in the query translation library to convert the database query from the first database format into the second database format. The computing platform may execute the translated database query on the second database to obtain a query result, and may send the query result to the client application.Type: ApplicationFiled: December 21, 2021Publication date: April 27, 2023Inventors: Carl M. Benda, Maharaj Mukherjee, Utkarsh Raj, Elvis Nyamwange, Suman Roy Choudhury