Patents by Inventor Sankalp Srivastava

Sankalp Srivastava 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: 20220417886
    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may establish, via a first subscriber service, at least one protocol data unit (PDU) session. The UE may receive a first internet protocol (IP) address associated with the first subscriber service. The UE may register the first subscriber service with an IP multimedia subsystem (IMS) network using the first IP address. The UE may register a second subscriber service with the IMS network using a second IP address, wherein the second subscriber service uses the at least one PDU session of the first subscriber service. Numerous other aspects are described.
    Type: Application
    Filed: June 21, 2022
    Publication date: December 29, 2022
    Inventors: Reza SHAHIDI, Bhupesh Manoharlal UMATT, Vikram SINGH, Suli ZHAO, Carlos Marcelo Dias PAZOS, Yong XIE, Sankalp SRIVASTAVA, Ramananda Arkalgud SHELVANANDA
  • Patent number: 11048979
    Abstract: Techniques for active learning-based data labeling are described. An active learning-based data labeling service enables a user to build and manage large, high accuracy datasets for use in various machine learning systems. Machine learning may be used to automate annotation and management of the datasets, increasing efficiency of labeling tasks and reducing the time required to perform labeling. Embodiments utilize active learning techniques to reduce the amount of a dataset that requires manual labeling. As subsets of the dataset are labeled, this label data is used to train a model which can then identify additional objects in the dataset without manual intervention. The process may continue iteratively until the model converges. This enables a dataset to be labeled without requiring each item in the dataset to be individually and manually labeled by human labelers.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: June 29, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Fedor Zhdanov, Siddharth Joshi, Sankalp Srivastava, Rahul Sharma, Pietro Perona, Sindhu Chejerla
  • Patent number: 10984164
    Abstract: An approach is described for a method, system, and product, the approaching includes identification of an integrated circuit design, identification of sync groups (nets having synchronous voltage levels), generation of a physical design having sync group constraints, and performance of design rule checking on a physical design based on at least transferred sync group information. This provides for performing design rule analysis at least using small minimum spacing requirements then would otherwise be required with prior techniques. In some embodiments, the approach includes a verification process that ensures that synchronous voltage behavior is appropriately associated with members of respective sync groups and cleans up old association data that is no longer relevant/correct.
    Type: Grant
    Filed: October 23, 2019
    Date of Patent: April 20, 2021
    Assignee: Cadence Design Systems, Inc.
    Inventors: Ankur Chaplot, Yashu Gupta, Nikhil Garg, Sachin Shrivastava, Michaela Guiney, Sankalp Srivastava