Patents by Inventor Sahil KUMAR

Sahil KUMAR 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).

  • Publication number: 20250103620
    Abstract: Methods, systems, and computer programs are presented for searching the content of voice conversations. The conversations are translated into text and analysis of the conversation is performed to identify information in the conversation. The information identified includes turns taking data in the conversation and states identified within each state. A powerful user interface (UI) is provided to review the conversations and add annotations that tag the different turns. Additionally, parameter values are extracted from the text. A powerful search engine is provided with multiple search options, such as searching for text, searching by state within the conversation, searching by parameters extracted from the conversation, or a combination thereof.
    Type: Application
    Filed: December 11, 2024
    Publication date: March 27, 2025
    Inventors: Luke Percival DE OLIVEIRA, Umair Akeel, Alfredo Láinez Rodrigo, Nicolas Acosta Amador, Sahil Kumar, Liat Barda Dremer, Byeongung Ahn, Tyler Cole
  • Publication number: 20250045306
    Abstract: Methods, systems, and computer programs are presented for searching the content of voice conversations. The conversations are translated into text and analysis of the conversation is performed to identify information in the conversation. The information identified includes turns taking data in the conversation and states identified within each state. A powerful user interface (UI) is provided to review the conversations and add annotations that tag the different turns. Additionally, parameter values are extracted from the text. A powerful search engine is provided with multiple search options, such as searching for text, searching by state within the conversation, searching by parameters extracted from the conversation, or a combination thereof.
    Type: Application
    Filed: October 22, 2024
    Publication date: February 6, 2025
    Inventors: Luke Percival de Oliveira, Umair Akeel, Alfredo Láinez Rodrigo, Nicolas Acosta Amador, Sahil Kumar, Liat Barda Dremer, Byeongung Ahn, Tyler Cole
  • Publication number: 20250030797
    Abstract: Methods, systems, and computer programs are presented for searching and labeling the content of voice conversations. An Engagement Intelligence Platform (EIP) analyzes conversation transcripts to find states and information for each of the states (e.g., interest rate quoted and value of the interest rate). An annotator User Interface (IU) is provided for performing queries, such as, “Find calls were the agent asked the customer for their name and the customer did not answer;” “Find calls where the customer objected after the interest rate for the loan was quoted, “Find calls where the agent asked for consent for recording the call, but no customer confirmation was received.” The EIP analyzes the conversation and labels (e.g., “tags”) the text where the conversation associated with the label took place, such as, “An interest rate was provided.” The labels are customizable, so each client can define its own labels based on business needs.
    Type: Application
    Filed: October 3, 2024
    Publication date: January 23, 2025
    Inventors: Tyler Cole, Eduardo Pardo San Llorente, Sahil Kumar, Byeongung Ahn, Elaine Lee, Nicolas Acosta Amador, Pablo Pérez Diez
  • Patent number: 12166919
    Abstract: Methods, systems, and computer programs are presented for searching and labeling the content of voice conversations. An Engagement Intelligence Platform (EIP) analyzes conversation transcripts to find states and information for each of the states (e.g., interest rate quoted and value of the interest rate). An annotator User Interface (IU) is provided for performing queries, such as, “Find calls were the agent asked the customer for their name and the customer did not answer;” “Find calls where the customer objected after the interest rate for the loan was quoted, “Find calls where the agent asked for consent for recording the call, but no customer confirmation was received.” The EIP analyzes the conversation and labels (e.g., “tags”) the text where the conversation associated with the label took place, such as, “An interest rate was provided.” The labels are customizable, so each client can define its own labels based on business needs.
    Type: Grant
    Filed: August 11, 2023
    Date of Patent: December 10, 2024
    Assignee: Twilio Inc.
    Inventors: Tyler Cole, Eduardo Pardo San Llorente, Sahil Kumar, Byeongung Ahn, Elaine Lee, Nicolas Acosta Amador, Pablo Pérez Diez
  • Patent number: 12158902
    Abstract: Methods, systems, and computer programs are presented for searching the content of voice conversations. The conversations are translated into text and analysis of the conversation is performed to identify information in the conversation. The information identified includes turns taking data in the conversation and states identified within each state. A powerful user interface (UI) is provided to review the conversations and add annotations that tag the different turns. Additionally, parameter values are extracted from the text. A powerful search engine is provided with multiple search options, such as searching for text, searching by state within the conversation, searching by parameters extracted from the conversation, or a combination thereof.
    Type: Grant
    Filed: July 19, 2021
    Date of Patent: December 3, 2024
    Assignee: Twilio Inc.
    Inventors: Luke Percival de Oliveira, Umair Akeel, Alfredo Láinez Rodrigo, Nicolas Acosta Amador, Sahil Kumar, Liat Barda Dremer, Byeongung Ahn, Tyler Cole
  • Publication number: 20240397258
    Abstract: A system includes a plurality of acoustic sensor elements co-located with one another, each acoustic sensor element of the plurality of acoustic sensor elements being configured to generate a signal representative of sound incident upon the plurality of acoustic sensor elements, and a processor configured to determine data indicative of a location of a source of the sound based on the signals representative of the incident sound. The plurality of acoustic sensor elements include a directional acoustic sensor element configured to generate a signal representative of a directional component of the sound.
    Type: Application
    Filed: August 2, 2024
    Publication date: November 28, 2024
    Inventors: Frederic Francois Leon Lepoutre, Sahil Kumar Gupta
  • Patent number: 12075210
    Abstract: A system includes a plurality of acoustic sensor elements co-located with one another, each acoustic sensor element of the plurality of acoustic sensor elements being configured to generate a signal representative of sound incident upon the plurality of acoustic sensor elements, and a processor configured to determine data indicative of a location of a source of the sound based on the signals representative of the incident sound. The plurality of acoustic sensor elements include a directional acoustic sensor element configured to generate a signal representative of a directional component of the sound.
    Type: Grant
    Filed: October 5, 2020
    Date of Patent: August 27, 2024
    Assignee: Soundskrit Inc.
    Inventors: Frederic Francois Leon Lepoutre, Sahil Kumar Gupta, Lucas Henrique Teixeira Carneiro
  • Publication number: 20230388413
    Abstract: Methods, systems, and computer programs are presented for searching and labeling the content of voice conversations. An Engagement Intelligence Platform (EIP) analyzes conversation transcripts to find states and information for each of the states (e.g., interest rate quoted and value of the interest rate). An annotator User Interface (IU) is provided for performing queries, such as, “Find calls were the agent asked the customer for their name and the customer did not answer;” “Find calls where the customer objected after the interest rate for the loan was quoted, “Find calls where the agent asked for consent for recording the call, but no customer confirmation was received.” The EIP analyzes the conversation and labels (e.g., “tags”) the text where the conversation associated with the label took place, such as, “An interest rate was provided.” The labels are customizable, so each client can define its own labels based on business needs.
    Type: Application
    Filed: August 11, 2023
    Publication date: November 30, 2023
    Inventors: Tyler Cole, Eduardo Pardo San Llorente, Sahil Kumar, Byeongung Ahn, Elaine Lee, Nicolas Acosta Amador, Pablo Pérez Diez
  • Patent number: 11792566
    Abstract: Microphones, microphone systems, and methods for capturing and processing sound are described. The microphones and microphone systems may adaptively change the direction from which sound is captured. The microphones and microphone systems avoid the need to provide arrays of microphones, while providing adaptive beamforming without a time delay between each channel of information, and multi-directional sound capture. A dependency between the frequency response and system size is also avoided.
    Type: Grant
    Filed: January 4, 2019
    Date of Patent: October 17, 2023
    Assignees: Soundskrit Inc., The Research Foundation for The State University of New York
    Inventors: Sahil Kumar Gupta, Stephane Leahy, Iman Moazzen, Ronald Miles, Jian Zhou
  • Publication number: 20230306454
    Abstract: Disclosed herein are systems and methods for account management with real-time incentives. For example, a method includes receiving one or more account identifiers identifying a financial account associated with a user. The method further includes receiving a payment request including a payment amount, a credit account selection from the one or more account identifiers, and a payment account selection from the one or more account identifiers. Upon receiving the payment request, the method includes transmitting a first financial transfer request to an electronic system associated with a bank account, causing the bank account to receive a first payment from the selected payment account and transmitting a second financial transfer request to the electronic system, causing the electronic system to transfer a second payment to the selected credit account. The method includes generating the incentive based on the payment amount and providing a notification to the user.
    Type: Application
    Filed: October 31, 2022
    Publication date: September 28, 2023
    Inventor: Sahil Kumar
  • Patent number: 11765267
    Abstract: Methods, systems, and computer programs are presented for searching and labeling the content of voice conversations. An Engagement Intelligence Platform (EIP) analyzes conversation transcripts to find states and information for each of the states (e.g., interest rate quoted and value of the interest rate). An annotator User Interface (IU) is provided for performing queries, such as, “Find calls were the agent asked the customer for their name and the customer did not answer;” “Find calls where the customer objected after the interest rate for the loan was quoted, “Find calls where the agent asked for consent for recording the call, but no customer confirmation was received.” The EIP analyzes the conversation and labels (e.g., “tags”) the text where the conversation associated with the label took place, such as, “An interest rate was provided.” The labels are customizable, so each client can define its own labels based on business needs.
    Type: Grant
    Filed: September 7, 2021
    Date of Patent: September 19, 2023
    Assignee: Twilio Inc.
    Inventors: Tyler Cole, Eduardo Pardo San Llorente, Sahil Kumar, Byeongung Ahn, Elaine Lee, Nicolas Acosta Amador, Pablo Pérez Diez
  • Publication number: 20230218463
    Abstract: The present invention provides devices and methods to capture airborne agents, microbes, including viruses, and microbial antigens, toxins and allergens and prevent the spread of infection from direct contact with contaminated surfaces (contact contamination), from large droplets of infectious material that fall out of the air, or from small droplets that can be carried by the air stream throughout the environment (airborne contamination).
    Type: Application
    Filed: June 17, 2021
    Publication date: July 13, 2023
    Inventors: Vikram Kapila, Valentin SIDERSKIY, Armando GRANADO, Sahil KUMAR, Tom Sowers, Hassam Khan WAZIR, Miles Quinn KILCOURSE, Sai Prasanth KRISHNAMOOTHY, Ryan GONZALEZ
  • Publication number: 20220408180
    Abstract: A system includes a plurality of acoustic sensor elements co-located with one another, each acoustic sensor element of the plurality of acoustic sensor elements being configured to generate a signal representative of sound incident upon the plurality of acoustic sensor elements, and a processor configured to determine data indicative of a location of a source of the sound based on the signals representative of the incident sound. The plurality of acoustic sensor elements include a directional acoustic sensor element configured to generate a signal representative of a directional component of the sound.
    Type: Application
    Filed: October 5, 2020
    Publication date: December 22, 2022
    Inventors: Frederic Francois Leon LEPOUTRE, Sahil Kumar GUPTA, Lucas Henrique TEIXEIRA CARNEIRO
  • Patent number: 11455284
    Abstract: Described is an approach that provides an adaptive solution to missing data for machine learning systems. A gradient solution is provided that is attentive to imputation needs at each of several missingness levels. This multilevel approach treats data missingness at any of multiple severity levels while utilizing, as much as possible, the actual observed data.
    Type: Grant
    Filed: September 9, 2019
    Date of Patent: September 27, 2022
    Inventors: Michael Zoll, Yaser I. Suleiman, Subhransu Basu, Angelo Pruscino, Wolfgang Lohwasser, Wataru Miyoshi, Thomas Breidt, Thomas Herter, Klaus Thielen, Sahil Kumar
  • Publication number: 20220210268
    Abstract: Methods, systems, and computer programs are presented for searching and labeling the content of voice conversations. An Engagement Intelligence Platform (EIP) analyzes conversation transcripts to find states and information for each of the states (e.g., interest rate quoted and value of the interest rate). An annotator User Interface (IU) is provided for performing queries, such as, “Find calls were the agent asked the customer for their name and the customer did not answer;” “Find calls where the customer objected after the interest rate for the loan was quoted, “Find calls where the agent asked for consent for recording the call, but no customer confirmation was received.” The EIP analyzes the conversation and labels (e.g., “tags”) the text where the conversation associated with the label took place, such as, “An interest rate was provided.” The labels are customizable, so each client can define its own labels based on business needs.
    Type: Application
    Filed: September 7, 2021
    Publication date: June 30, 2022
    Inventors: Tyler Cole, Eduardo Pardo San Llorente, Sahil Kumar, Byeongung Ahn, Elaine Lee, Nicolas Acosta Amador, Pablo Pérez Diez
  • Publication number: 20220156296
    Abstract: Methods, systems, and computer programs are presented for searching the content of voice conversations. The conversations are translated into text and analysis of the conversation is performed to identify information in the conversation. The information identified includes turns taking data in the conversation and states identified within each state. A powerful user interface (UI) is provided to review the conversations and add annotations that tag the different turns. Additionally, parameter values are extracted from the text. A powerful search engine is provided with multiple search options, such as searching for text, searching by state within the conversation, searching by parameters extracted from the conversation, or a combination thereof.
    Type: Application
    Filed: July 19, 2021
    Publication date: May 19, 2022
    Inventors: Luke Percival de Oliveira, Umair Akeel, Alfredo Láinez Rodrigo, Nicolas Acosta Amador, Sahil Kumar, Liat Barda Dremer, Byeongung Ahn, Tyler Cole
  • Patent number: 11308049
    Abstract: Described is an improved approach to remove data outliers by filtering out data correlated to detrimental events within a system. One or more detrimental even conditions are defined to identify and handle abnormal transient states from collected data for a monitored system.
    Type: Grant
    Filed: September 18, 2017
    Date of Patent: April 19, 2022
    Assignee: Oracle International Corporation
    Inventors: Yaser I. Suleiman, Michael Zoll, Subhransu Basu, Angelo Pruscino, Wolfgang Lohwasser, Wataru Miyoshi, Thomas Breidt, Thomas Herter, Klaus Thielen, Sahil Kumar
  • Publication number: 20210139332
    Abstract: Disclosed herein are methods of synthesizing a hybrid nanomaterial comprising 3D out-of-plane single- to few-layer fuzzy graphene on a scaffold, such as a Si nanowire mesh through a plasma-enhanced chemical vapor deposition process. By varying graphene growth conditions (CH4 partial pressure and process time), the size, density, and electrical properties of the hybrid nanomaterial can be controlled. Porous nanowire-templated 3D graphene hybrid nanomaterials exhibit high electrical conductivity and also demonstrate exceptional electrochemical functionality.
    Type: Application
    Filed: April 17, 2018
    Publication date: May 13, 2021
    Applicant: CARNEGIE MELLON UNIVERSITY
    Inventors: Raghav Garg, Sahil Kumar Rastogi, Tzahi Cohen-Karni, Daniel J. San Roman, Rahul Panat
  • Patent number: 10997135
    Abstract: Described is an approach for performing context-aware prognoses in machine learning systems. The approach harnesses streams of detailed data collected from a monitored target to create a context, in parallel to ongoing model operations, for the model outcomes. The context is then probed to identify the particular elements associated with the model findings.
    Type: Grant
    Filed: September 18, 2017
    Date of Patent: May 4, 2021
    Assignee: Oracle International Corporation
    Inventors: Michael Zoll, Yaser I. Suleiman, Subhransu Basu, Angelo Pruscino, Wolfgang Lohwasser, Wataru Miyoshi, Thomas Breidt, Thomas Herter, Klaus Thielen, Sahil Kumar
  • Patent number: 10909095
    Abstract: Described is an improved approach to implement selection of training data for machine learning, by presenting a designated set of specific data indicators where these data indicators correspond to metrics that end users are familiar with and are easily understood by ordinary users and DBAs within their knowledge domain. Selection of these indicators would correlate automatically to selection of a corresponding set of other metrics/signals that are less understandable to an ordinary user. Additional analysis of the selected data can then be performed to identify and correct any statistical problems with the selected training data.
    Type: Grant
    Filed: September 18, 2017
    Date of Patent: February 2, 2021
    Assignee: Oracle International Corporation
    Inventors: Yaser I. Suleiman, Michael Zoll, Subhransu Basu, Angelo Pruscino, Wolfgang Lohwasser, Wataru Miyoshi, Thomas Breidt, Thomas Herter, Klaus Thielen, Sahil Kumar