Patents by Inventor Karthik KRISHNAMOORTHI

Karthik KRISHNAMOORTHI 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: 20240290327
    Abstract: A method includes obtaining an utterance from a user including a user query directed toward a digital assistant. The method includes generating, using a language model, a first prediction string based on the utterance and determining whether the first prediction string includes an application programming interface (API) call to invoke a program via an API. When the first prediction string includes the API call to invoke the program, the method includes calling, using the API call, the program via the API to retrieve a program result; receiving, via the API, the program result; updating a conversational context with the program result that includes the utterance; and generating, using the language model, a second prediction string based on the updated conversational context. When the first prediction string does not include the API call, the method includes providing an utterance response to the utterance based on the first prediction string.
    Type: Application
    Filed: May 8, 2024
    Publication date: August 29, 2024
    Applicant: Google LLC
    Inventors: William J. Byrne, Karthik Krishnamoorthi, Saravanan Ganesh
  • Patent number: 11990124
    Abstract: A method includes obtaining an utterance from a user including a user query directed toward a digital assistant. The method includes generating, using a language model, a first prediction string based on the utterance and determining whether the first prediction string includes an application programming interface (API) call to invoke a program via an API. When the first prediction string includes the API call to invoke the program, the method includes calling, using the API call, the program via the API to retrieve a program result; receiving, via the API, the program result; updating a conversational context with the program result that includes the utterance; and generating, using the language model, a second prediction string based on the updated conversational context. When the first prediction string does not include the API call, the method includes providing an utterance response to the utterance based on the first prediction string.
    Type: Grant
    Filed: December 22, 2021
    Date of Patent: May 21, 2024
    Assignee: Google LLC
    Inventors: William J. Byrne, Karthik Krishnamoorthi, Saravanan Ganesh
  • Publication number: 20230197070
    Abstract: A method includes obtaining an utterance from a user including a user query directed toward a digital assistant. The method includes generating, using a language model, a first prediction string based on the utterance and determining whether the first prediction string includes an application programming interface (API) call to invoke a program via an API. When the first prediction string includes the API call to invoke the program, the method includes calling, using the API call, the program via the API to retrieve a program result; receiving, via the API, the program result; updating a conversational context with the program result that includes the utterance; and generating, using the language model, a second prediction string based on the updated conversational context. When the first prediction string does not include the API call, the method includes providing an utterance response to the utterance based on the first prediction string.
    Type: Application
    Filed: December 22, 2021
    Publication date: June 22, 2023
    Applicant: Google LLC
    Inventors: William J. Byrne, Karthik Krishnamoorthi, Saravanan Ganesh
  • Patent number: 10670657
    Abstract: A system configured for monitoring the operation status of an electric machine; a mobile phone therefor and server-based system using the same. The system includes a portable unit, adapted for free movement around the electric machine; an airborne acoustics sensor, adapted for measuring acoustic data produced by the electric machine at a first position in a path of the free movement; a magnetic field sensor, adapted for measuring magnetic field data produced by the electric machine at a second position in the path of the free movement; and a processing unit, adapted for calculating the operation status of the electric machine based on the acoustic data from the airborne acoustics sensor and the magnetic field data from the magnetic field sensor; wherein: the airborne acoustics sensor and the magnetic field sensor are integrated with the portable unit.
    Type: Grant
    Filed: March 8, 2017
    Date of Patent: June 2, 2020
    Assignee: ABB Schweiz AG
    Inventors: Maciej Orman, Pawel Rzeszucinski, Karthik Krishnamoorthi
  • Patent number: 10353004
    Abstract: In aspects, the present invention discloses a method of detecting a rotor fault in an electric machine using a data analysis unit. The method comprises measuring magnetic field strength along a first axis and a second axis, determining operating slip frequency of the electric machine using the measured magnetic field strength along the first axis and the second axis, determining an amplitude of the determined operating slip frequency in a first frequency spectrum and an amplitude of operating slip frequency in a second frequency spectrum, and detecting the rotor fault by comparing the amplitude of the determined operating slip frequency in the first frequency spectrum and the amplitude of operating slip frequency in the second frequency spectrum against a predetermined threshold.
    Type: Grant
    Filed: March 24, 2015
    Date of Patent: July 16, 2019
    Assignee: ABB Schweiz AG
    Inventors: Prasad Mulay, Maciej Orman, Karthik Krishnamoorthi, Cajetan Pinto, Pawel Rzeszucinski
  • Publication number: 20190204390
    Abstract: In aspects, the present invention discloses a system for monitoring condition of a plurality of motors. The system includes a plurality of condition monitoring devices capable of measuring one or more parameters associated with the corresponding motors, a gateway device coupled to the one or more condition monitoring devices for configuring the one or more condition monitoring devices upon installation and for communicating measurement data from the one or more condition monitoring devices, a server configured to receive measurement data from the gateway device 140 and to detect a condition of at least one motor from the one or more motors, and at least one mobile device capable of configuring the one or more condition monitoring devices, and for displaying one or more alert messages associated with the detected condition of the at least one motor based on a message from the server.
    Type: Application
    Filed: August 23, 2017
    Publication date: July 4, 2019
    Inventors: Karthik KRISHNAMOORTHI, Cajetan PINTO, Maciej ORMAN, Anant URALA, Amandine HEQUING SUN, Pawel RZESZUCINSKI
  • Publication number: 20170082692
    Abstract: In aspects, the present invention discloses a method of detecting a rotor fault in an electric machine using a data analysis unit. The method comprises measuring magnetic field strength along a first axis and a second axis, determining operating slip frequency of the electric machine using the measured magnetic field strength along the first axis and the second axis, determining an amplitude of the determined operating slip frequency in a first frequency spectrum and an amplitude of operating slip frequency in a second frequency spectrum, and detecting the rotor fault by comparing the amplitude of the determined operating slip frequency in the first frequency spectrum and the amplitude of operating slip frequency in the second frequency spectrum against a predetermined threshold.
    Type: Application
    Filed: March 24, 2015
    Publication date: March 23, 2017
    Inventors: Prasad MULAY, Maciej ORMAN, Karthik KRISHNAMOORTHI, Cajetan PINTO, Pawel RZESZUCINSKI