Patents by Inventor Deepthi Uppalapati

Deepthi Uppalapati 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).

  • Unstructured text processing for geographical location determination system
    Patent number: 11822562
    Abstract: Aspects described herein include systems and methods for determining addresses for assets, prioritizing the addresses for inspection by users, and applying natural language processing techniques to unstructured text input by the users. According to some aspects, a message may be received that includes unstructured text that was input by a user. The unstructured text may be associated with an inspection, by the user, of an address for an asset. One or more natural language techniques may be applied to the unstructured text to, among other things, facilitate the determination and sending of a response message to the unstructured text in an automated fashion. The response message may, if the asset was not found, include another address as a suggestion for the user to inspect for the asset. This suggested address may be determined based on changes to address priority that were caused by processing of the unstructured text.
    Type: Grant
    Filed: March 31, 2022
    Date of Patent: November 21, 2023
    Assignee: Capital One Services, LLC
    Inventors: Lokesh S. Tulshan, Deepthi Uppalapati, Anirban Majumdar, Daniel Pereira, Manish R. Chhabra, Kukumina Pradhan, Kuldeep Kashinath Marganache, Raghavendra Chivukula
  • UNSTRUCTURED TEXT PROCESSING FOR GEOGRAPHICAL LOCATION DETERMINATION SYSTEM
    Publication number: 20230315743
    Abstract: Aspects described herein include systems and methods for determining addresses for assets, prioritizing the addresses for inspection by users, and applying natural language processing techniques to unstructured text input by the users. According to some aspects, a message may be received that includes unstructured text that was input by a user. The unstructured text may be associated with an inspection, by the user, of an address for an asset. One or more natural language techniques may be applied to the unstructured text to, among other things, facilitate the determination and sending of a response message to the unstructured text in an automated fashion. The response message may, if the asset was not found, include another address as a suggestion for the user to inspect for the asset. This suggested address may be determined based on changes to address priority that were caused by processing of the unstructured text.
    Type: Application
    Filed: March 31, 2022
    Publication date: October 5, 2023
    Inventors: Lokesh S. Tulshan, Deepthi Uppalapati, Anirban Majumdar, Daniel Pereira, Manish R. Chhabra, Kukumina Pradhan, Kuldeep Kashinath Marganache, Raghavendra Chivukula