Patents by Inventor Saravanan Ganesh

Saravanan Ganesh 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
  • Patent number: 11886368
    Abstract: A repeater circuit includes at least a first input, and output, and a repeater. The first input for receiving a single-ended data signal from an embedded universal serial bus (eUSB) host. The output provides a differential data signal in a differential universal serial bus (USB) format. The repeater is coupled between the first input and output for converting the single-ended data signal to a differential data signal, the repeater includes an adaptive delay element operable for both sides of the differential data signal to delay one, but not both, of a rising edge and a falling edge of the differential data signal in order to meet a crossover specification for the USB format.
    Type: Grant
    Filed: April 1, 2022
    Date of Patent: January 30, 2024
    Assignee: SEMICONDUCTOR COMPONENTS INDUSTRIES, LLC
    Inventors: Athar Ali Khan P, Saravanan Ganesh
  • Publication number: 20230315663
    Abstract: A repeater circuit includes at least a first input, and output, and a repeater. The first input for receiving a single-ended data signal from an embedded universal serial bus (eUSB) host. The output provides a differential data signal in a differential universal serial bus (USB) format. The repeater is coupled between the first input and output for converting the single-ended data signal to a differential data signal, the repeater includes an adaptive delay element operable for both sides of the differential data signal to delay one, but not both, of a rising edge and a falling edge of the differential data signal in order to meet a crossover specification for the USB format.
    Type: Application
    Filed: April 1, 2022
    Publication date: October 5, 2023
    Applicant: SEMICONDUCTOR COMPONENTS INDUSTRIES, LLC
    Inventors: Athar Ali KHAN P, 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