Patents by Inventor Deepak Mittal

Deepak Mittal 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: 12223712
    Abstract: Systems and methods for detecting and aligning land property boundaries on aerial imagery are provided. The system receives an aerial imagery having land properties. The system applies a feature encoder having a plurality of levels to the aerial imagery. A first level of the plurality of levels includes a convolution block and a discrete wavelet transform layer. The discrete wavelet transform layer decomposes an input feature tensor to the first level into a low-frequency band and a high-frequency band. The high-frequency band is cached and processed with side-convolutional blocks before the high-frequency band are passed to a feature decoder. The system applies the feature decoder to an output of the feature encoder based at least in part on one of inverse discrete wavelet transform layers. The system determines boundaries of the one or more land properties based at least in part on a boundary cross-entropy loss function.
    Type: Grant
    Filed: December 18, 2023
    Date of Patent: February 11, 2025
    Assignee: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravarasapu, Deepak Mittal
  • Publication number: 20240346403
    Abstract: A computer-implemented method for associating at least one actor with an operation using machine learning includes receiving actor data comprising at least one actor parameter corresponding to at least one operation parameter of the operation, determining a weightage score for each actor parameter using a trained machine-learning model, determining a suitability score for each actor based on the weightage scores, generating a preliminary group of suitable actors including each actor having a suitability score satisfying a predetermined threshold, and transmitting, to a portal viewable by at least one of the actors, a selection of at least one actor from the preliminary group of suitable actors to be associated with the operation. One or more of the operation parameters may be predictive of a predetermined distribution of operations across the plurality of actors.
    Type: Application
    Filed: April 14, 2023
    Publication date: October 17, 2024
    Inventors: Manik SINGLA, Ankit JAIN, Deepak MITTAL
  • Publication number: 20240135704
    Abstract: Systems and methods for detecting and aligning land property boundaries on aerial imagery are provided. The system receives an aerial imagery having land properties. The system applies a feature encoder having a plurality of levels to the aerial imagery. A first level of the plurality of levels includes a convolution block and a discrete wavelet transform layer. The discrete wavelet transform layer decomposes an input feature tensor to the first level into a low-frequency band and a high-frequency band. The high-frequency band is cached and processed with side-convolutional blocks before the high-frequency band are passed to a feature decoder. The system applies the feature decoder to an output of the feature encoder based at least in part on one of inverse discrete wavelet transform layers. The system determines boundaries of the one or more land properties based at least in part on a boundary cross-entropy loss function.
    Type: Application
    Filed: December 18, 2023
    Publication date: April 25, 2024
    Applicant: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravarasapu, Deepak Mittal
  • Publication number: 20240005533
    Abstract: Computer vision systems and methods for noisy contour alignment are provided. The system generates a loss function and trains a convolutional neural network with the loss function and a plurality of images of a dataset to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales. The system can align an attribute of an image of the dataset by the trained neural network.
    Type: Application
    Filed: March 21, 2023
    Publication date: January 4, 2024
    Applicant: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravasarapu, Abhishek Goel, Deepak Mittal, Maneesh Kumar Singh
  • Patent number: 11847824
    Abstract: Systems and methods for detecting and aligning land property boundaries on aerial imagery are provided. The system receives an aerial imagery having land properties. The system applies a feature encoder having a plurality of levels to the aerial imagery. A first level of the plurality of levels includes a convolution block and a discrete wavelet transform layer. The discrete wavelet transform layer decomposes an input feature tensor to the first level into a low-frequency band and a high-frequency band. The high-frequency band is cached and processed with side-convolutional blocks before the high-frequency band are passed to a feature decoder. The system applies the feature decoder to an output of the feature encoder based at least in part on one of inverse discrete wavelet transform layers. The system determines boundaries of the one or more land properties based at least in part on a boundary cross-entropy loss function.
    Type: Grant
    Filed: November 17, 2021
    Date of Patent: December 19, 2023
    Assignee: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravarasapu, Deepak Mittal
  • Patent number: 11610322
    Abstract: Computer vision systems and methods for noisy contour alignment are provided. The system generates a loss function and trains a convolutional neural network with the loss function and a plurality of images of a dataset to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales. The system can align an attribute of an image of the dataset by the trained neural network.
    Type: Grant
    Filed: November 25, 2020
    Date of Patent: March 21, 2023
    Assignee: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravasarapu, Abhishek Goel, Deepak Mittal, Maneesh Kumar Singh
  • Publication number: 20220156493
    Abstract: Systems and methods for detecting and aligning land property boundaries on aerial imagery are provided. The system receives an aerial imagery having land properties. The system applies a feature encoder having a plurality of levels to the aerial imagery. A first level of the plurality of levels includes a convolution block and a discrete wavelet transform layer. The discrete wavelet transform layer decomposes an input feature tensor to the first level into a low-frequency band and a high-frequency band. The high-frequency band is cached and processed with side-convolutional blocks before the high-frequency band are passed to a feature decoder. The system applies the feature decoder to an output of the feature encoder based at least in part on one of inverse discrete wavelet transform layers. The system determines boundaries of the one or more land properties based at least in part on a boundary cross-entropy loss function.
    Type: Application
    Filed: November 17, 2021
    Publication date: May 19, 2022
    Applicant: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravarasapu, Deepak Mittal
  • Publication number: 20210158549
    Abstract: Computer vision systems and methods for noisy contour alignment are provided. The system generates a loss function and trains a convolutional neural network with the loss function and a plurality of images of a dataset to learn to align contours with progressively increasing complex forward and backward transforms over increasing scales. The system can align an attribute of an image of the dataset by the trained neural network.
    Type: Application
    Filed: November 25, 2020
    Publication date: May 27, 2021
    Applicant: Insurance Services Office, Inc.
    Inventors: Venkata Subbarao Veeravasarapu, Abhishek Goel, Deepak Mittal, Maneesh Kumar Singh
  • Publication number: 20120215613
    Abstract: A method for managing offers for prepaid telephony accounts of a plurality of users is provided. The method includes obtaining information related to user profiles and usage patterns of a plurality of telecommunication services offered to the plurality of users through their respective prepaid telephony accounts. The method also includes customizing prepaid telephony offers for each of the plurality of users based upon the information related to the user profiles and the usage patterns and delivering the customized prepaid telephony offers to a mobile device of each of the plurality of users via unstructured supplementary services data (USSD) messages.
    Type: Application
    Filed: January 9, 2012
    Publication date: August 23, 2012
    Inventors: Rajiv Madhok, Deepak Mittal