Patents by Inventor Sudhanshu Sharma

Sudhanshu Sharma 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: 12340332
    Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support functionality for identifying, quantifying, and mitigating risks. A dataset that includes a plurality of data items associated with one or more entities is generated and a set of rules is executed against the dataset to determine a sentiment for each data item of the plurality of data items. The dataset may be evaluated against a machine learning model configured to produce a set of risk categorizations that associate each of the plurality of data items with a risk category. Scoring metrics are generated for each of the data items based at least in part on the evaluating. The scoring metrics may account for an impact of dependencies and capabilities of the one or more entities on risks corresponding to the risk categorizations.
    Type: Grant
    Filed: December 10, 2021
    Date of Patent: June 24, 2025
    Assignee: Accenture Global Solutions Limited
    Inventors: Rajarajan Tr, Auri Priyadharshini Munivelu, Venkata Rama Krishna P, Jhilam Dutta, Ravi Kanth Vinnakota, Sudhanshu Sharma, Yash Mishra
  • Publication number: 20250156750
    Abstract: Various embodiments of the present disclosure provide reinforcement learning for machine learning using dynamic confidence thresholds. In one example, an embodiment provides for generating a plurality of training datasets for a machine learning model by augmenting a labeled dataset for the machine learning model with a synthetic labeled dataset, generating a plurality of retrained model versions of the machine learning model based on the plurality of training datasets, generating a reward indicator for a retrained model version of the plurality of retrained versions of the machine learning model based on a comparison between a validation dataset for the machine learning model and a respective output dataset for the retrained model version, and modifying the defined confidence threshold based on the reward indicator for the retrained model version to generate a modified confidence threshold for the machine learning model.
    Type: Application
    Filed: November 14, 2023
    Publication date: May 15, 2025
    Inventors: Ayan Sengupta, Sudhanshu Sharma, Julie Zhu, Elizabeth Patterson Cohn
  • Publication number: 20250077957
    Abstract: Various embodiments of the present disclosure provide quality assurance for machine learning using distribution patterns related to training datasets. In one example, an embodiment provides for generating an augmented training dataset of a plurality of augmented training datasets for a machine learning model by randomly modifying a subset of binary labels of a training dataset for the machine learning model based on a probability value, generating a graphical distribution pattern for the training dataset based on a plurality of accuracy scores of the plurality of augmented training datasets, and generating a quality score for the training dataset based on a comparison between the graphical distribution pattern and a predefined graphical distribution pattern.
    Type: Application
    Filed: September 1, 2023
    Publication date: March 6, 2025
    Inventors: Sudhanshu Sharma, Ayan Sengupta
  • Publication number: 20240230879
    Abstract: A multi-static radar detection system for a vehicle includes one or more receivers for collecting multi-carrier modulation signals emitted by one or more transmitters that are positioned at base stations located in an environment surrounding the vehicle. The multi-carrier modulation signals include one or more types of reference signals. The multi-static radar detection system also includes one or more controllers in electronic communication with the one or more receivers. The one or more controllers execute instructions to collect, by the one or more receivers, a multi-carrier modulation signal emitted by the one or more transmitters. The one or more controllers determine a Doppler shift and a time delay of a respective object located within the environment surrounding the vehicle based on an interpolated time-frequency grid; and transform a value for the Doppler shift into a velocity value and a value for the time delay into a range value.
    Type: Application
    Filed: October 21, 2022
    Publication date: July 11, 2024
    Inventors: Kamran Ali, Fan Bai, Andreas Molisch, Nikhil Kowshika Nataraja, Sudhanshu Sharma
  • Publication number: 20240193471
    Abstract: Various embodiments of the present disclosure disclose machine-learning based evaluation techniques for detecting feature bias. An evaluation framework is provided that utilizes new evaluation data structures for comprehensibly evaluating feature bias in machine learning models. The evaluation framework includes receiving evaluation dataset for a machine learning model that includes one or more different feature classes of an evaluation feature. The evaluation framework includes generating, using an evaluation function, at least two performance metrics for the machine learning model and generating a unitless dissimilarity metric for the evaluation feature based at least in part on the first performance metric, the second performance metric, and an average between the first and second performance metrics. In this way, the unitless dissimilarity metric is based on a variability associated with the evaluation feature.
    Type: Application
    Filed: December 8, 2022
    Publication date: June 13, 2024
    Inventors: Arun Tiwari, Amardeep Sharma, Rahul Pathak, Sudhanshu Sharma, Urvi Sharma, Radhika Agarwal
  • Publication number: 20240193470
    Abstract: Various embodiments of the present disclosure disclose machine-learning based evaluation techniques for detecting feature bias. An evaluation framework is provided that utilizes new evaluation data structures for comprehensibly evaluating feature bias in machine learning models. The evaluation framework includes receiving evaluation dataset for a machine learning model that includes one or more different feature classes of an evaluation feature. The evaluation framework includes generating, using an evaluation function, at least two performance metrics for the machine learning model and generating a unitless dissimilarity metric for the evaluation feature based at least in part on the first performance metric, the second performance metric, and an average between the first and second performance metrics. In this way, the unitless dissimilarity metric is based on a variability associated with the evaluation feature.
    Type: Application
    Filed: December 8, 2022
    Publication date: June 13, 2024
    Inventors: Arun Tiwari, Amardeep Sharma, Rahul Pathak, Sudhanshu Sharma, Urvi Sharma, Radhika Agarwal
  • Publication number: 20240134032
    Abstract: A multi-static radar detection system for a vehicle includes one or more receivers for collecting multi-carrier modulation signals emitted by one or more transmitters that are positioned at base stations located in an environment surrounding the vehicle. The multi-carrier modulation signals include one or more types of reference signals. The multi-static radar detection system also includes one or more controllers in electronic communication with the one or more receivers. The one or more controllers execute instructions to collect, by the one or more receivers, a multi-carrier modulation signal emitted by the one or more transmitters. The one or more controllers determine a Doppler shift and a time delay of a respective object located within the environment surrounding the vehicle based on an interpolated time-frequency grid; and transform a value for the Doppler shift into a velocity value and a value for the time delay into a range value.
    Type: Application
    Filed: October 20, 2022
    Publication date: April 25, 2024
    Inventors: Kamran Ali, Fan Bai, Andreas Molisch, Nikhil Kowshika Nataraja, Sudhanshu Sharma
  • Publication number: 20230186213
    Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support functionality for identifying, quantifying, and mitigating risks. A dataset that includes a plurality of data items associated with one or more entities is generated and a set of rules is executed against the dataset to determine a sentiment for each data item of the plurality of data items. The dataset may be evaluated against a machine learning model configured to produce a set of risk categorizations that associate each of the plurality of data items with a risk category. Scoring metrics are generated for each of the data items based at least in part on the evaluating. The scoring metrics may account for an impact of dependencies and capabilities of the one or more entities on risks corresponding to the risk categorizations.
    Type: Application
    Filed: December 10, 2021
    Publication date: June 15, 2023
    Inventors: Rajarajan Tr, Auri Priyadharshin Munivelu, Venkata Rama Krishna P, Jhilam Dutta, Ravi Kanth Vinnakota, Sudhanshu Sharma, Yash Mishra
  • Patent number: 9553927
    Abstract: The disclosure relates generally to providing synchronized supplemental content. In one aspect, second user devices may be used to consume supplemental content associated with primary content presented on a first display. The supplemental content may be synchronized with the primary content. Such synchronization may be performed by detecting and reporting triggers within the primary content and transmitting synchronization signals to appropriate second user devices. Another aspect of the disclosure relates to determining which interfaces or applications will report the triggers, and fine-tuning how many interfaces or applications will report the triggers.
    Type: Grant
    Filed: March 13, 2013
    Date of Patent: January 24, 2017
    Assignee: Comcast Cable Communications, LLC
    Inventors: Sudhanshu Sharma, James D. Mora
  • Patent number: 9253531
    Abstract: Exemplary methods and systems for managing media content sessions are disclosed herein. As described in more detail below, a media content access device may detect a media content session associated with the media content access device, communicate with one or more other media content access devices by way of a local area network to detect one or more other media content sessions associated with the one or more other media content access devices, and present a graphical user interface configured to facilitate user management of the media content session and the one or more other media content sessions. Corresponding methods and systems are also disclosed.
    Type: Grant
    Filed: May 10, 2011
    Date of Patent: February 2, 2016
    Assignee: VERIZON PATENT AND LICENSING INC.
    Inventors: Donald H. Relyea, Brian F. Roberts, Heath Stallings, Lonnie Katai, Michael D'Argenio, Sudhanshu Sharma, Jayson Sellers
  • Patent number: 9003473
    Abstract: A method may include receiving an enhanced television (ETV) application in a video client over a first data path and executing the ETV application in the video client. In one embodiment, the ETV application may include an enhanced television binary interchange format (EBIF) resource. The method may also include extracting, from the EBIF resource, an identifier of an extension application and requesting the identified extension application. The method may include receiving the extension application, over a second data path different than the first data path and executing the extension application.
    Type: Grant
    Filed: November 9, 2009
    Date of Patent: April 7, 2015
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Sudhanshu Sharma, Karthic Chinnadurai, Vedhashree Sampath, Shrividhyaa Kannan
  • Patent number: 8923685
    Abstract: An exemplary method includes receiving a command input by a user to record media content, recording media content data representative of the media content in response to the command, automatically selecting at least one storage device from a local storage device and a network storage device for storage of the recorded media content data in accordance with at least one of a plurality of storage balancing factors, and storing the recorded media content data in the at least one selected storage device. Corresponding methods and systems are also disclosed.
    Type: Grant
    Filed: May 28, 2010
    Date of Patent: December 30, 2014
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Brian F. Roberts, Harpal S. Bassali, Sudhanshu Sharma, Donald H. Relyea, Raul I. Aldrey, Japan A. Mehta
  • Patent number: 8850475
    Abstract: A method includes detecting, from an Enhanced Television (ETV) Integrated Signaling Stream (EISS), an indication that an ETV application is available to be downloaded; downloading, in response to the indication, the ETV application from a video stream identified by the indication, where the ETV application does not conform to an ETV Binary Interchange Format (EBIF) standard; detecting, from the EISS, another indication that the ETV application is to be started; executing, in response to the other indication, the ETV application to generate an ETV page, where the ETV page includes information that is not permitted by the EBIF standard; and displaying the ETV page on a video display device to enables a user to interact with the ETV page.
    Type: Grant
    Filed: October 5, 2010
    Date of Patent: September 30, 2014
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Sudhanshu Sharma, Neena Pandey
  • Publication number: 20140280695
    Abstract: The disclosure relates generally to providing synchronized supplemental content. In one aspect, second user devices may be used to consume supplemental content associated with primary content presented on a first display. The supplemental content may be synchronized with the primary content. Such synchronization may be performed by detecting and reporting triggers within the primary content and transmitting synchronization signals to appropriate second user devices. Another aspect of the disclosure relates to determining which interfaces or applications will report the triggers, and fine-tuning how many interfaces or applications will report the triggers.
    Type: Application
    Filed: March 13, 2013
    Publication date: September 18, 2014
    Applicant: COMCAST CABLE COMMUNICATIONS, LLC
    Inventors: Sudhanshu SHARMA, James D. MORA
  • Patent number: 8839290
    Abstract: An exemplary method includes receiving a plurality of data chunks each representative of a distinct portion of a media content program, generating a personalized version of the media content program based on at least a subset of the data chunks and in accordance with one or more of a plurality of personalization factors associated with a user, and providing the personalized version of the media content program for presentation to the user. Corresponding methods and systems are also described.
    Type: Grant
    Filed: June 10, 2010
    Date of Patent: September 16, 2014
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Brian F. Roberts, Harpal S. Bassali, Sudhanshu Sharma, Donald H. Relyea, Raul I. Aldrey, Japan A. Mehta
  • Patent number: 8824645
    Abstract: An exemplary method includes a video messaging system 1) providing an asynchronous video messaging service, 2) maintaining communication thread data representative of a video communication thread that includes a plurality of video messages exchanged between users of the asynchronous video messaging service, 3) providing a user interface configured to facilitate user interaction with the video communication thread, 4) receiving, by way of the user interface, a user input command to process multiple video messages included in the video communication thread, and 5) stitching together the multiple video messages for use in processing the multiple video messages in response to the user input command. Corresponding systems and methods are also disclosed.
    Type: Grant
    Filed: September 30, 2011
    Date of Patent: September 2, 2014
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Brian F. Roberts, Anthony M. Lemus, Japan A. Mehta, Kishore Tallapaneni, Donald H. Relyea, Sudhanshu Sharma
  • Patent number: 8646021
    Abstract: An approach provides interactive application and advertisement within media streams. A program map table of a media stream is retrieved, wherein the program map table includes a plurality of private descriptor fields that permit user specified tag values. One of the descriptor fields is configured to indicate whether the media stream is associated with an interactive application or advertisement information.
    Type: Grant
    Filed: April 20, 2011
    Date of Patent: February 4, 2014
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Sudhanshu Sharma, Neena Pandey
  • Patent number: 8558716
    Abstract: A media client receives, from a remote control device, a signal to launch a selected interactive television application and sends, to the remote control device, a client program for reprogramming buttons on the remote control device. The media client sends, to the remote control device, a script, for button functions of the remote control device, which are based on the selected interactive television application. The remote control device executes the script on the client program to reprogram the buttons functions. The media client presents, on a display device, a button map that corresponds to the script, and receives, from the remote control device, a signal based on the scripting.
    Type: Grant
    Filed: June 10, 2010
    Date of Patent: October 15, 2013
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Brian F. Roberts, Sudhanshu Sharma, Carl Randall Mosty
  • Publication number: 20130083906
    Abstract: An exemplary method includes a video messaging system 1) providing an asynchronous video messaging service, 2) maintaining communication thread data representative of a video communication thread that includes a plurality of video messages exchanged between users of the asynchronous video messaging service, 3) providing a user interface configured to facilitate user interaction with the video communication thread, 4) receiving, by way of the user interface, a user input command to process multiple video messages included in the video communication thread, and 5) stitching together the multiple video messages for use in processing the multiple video messages in response to the user input command. Corresponding systems and methods are also disclosed.
    Type: Application
    Filed: September 30, 2011
    Publication date: April 4, 2013
    Applicant: VERIZON PATENT AND LICENSING INC.
    Inventors: Brian F. Roberts, Anthony M. Lemus, Japan A. Mehta, Kishore Tallapaneni, Donald H. Relyea, Sudhanshu Sharma
  • Publication number: 20120291060
    Abstract: Exemplary methods and systems for managing media content sessions are disclosed herein. As described in more detail below, a media content access device may detect a media content session associated with the media content access device, communicate with one or more other media content access devices by way of a local area network to detect one or more other media content sessions associated with the one or more other media content access devices, and present a graphical user interface configured to facilitate user management of the media content session and the one or more other media content sessions. Corresponding methods and systems are also disclosed.
    Type: Application
    Filed: May 10, 2011
    Publication date: November 15, 2012
    Applicant: VERIZON PATENT AND LICENSING, INC.
    Inventors: Donald H. Relyea, Brian F. Roberts, Heath Stallings, Lonnie Katai, Michael D'Argenio, Sudhanshu Sharma, Jayson Sellers