MUMBAI, India, July 25 -- Intellectual Property India has published a patent application (202528066315 A) filed by Google Llc, Mountain View, U.S.A., on July 11, for 'using large language model(s) in generating automated assistant response(s).'
Inventor(s) include Baeuml, Martin; Amarasiriwardena, Thushan; Pieraccini, Roberto; Sridar, Vikram; Adiwardana, Daniel De Freitas; Shazeer, Noam M; and Le, Quoc.
The application for the patent was published on July 25, under issue no. 30/2025.
According to the abstract released by the Intellectual Property India: "As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received."
The patent application was internationally filed on Nov. 30, 2021, under International application No.PCT/US2021/061214.
Disclaimer: Curated by HT Syndication.
