公开(公告)号：US12271742B2

公开(公告)日：2025-04-08

申请号：US18230561

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Cliff Kuang ,  Diana Avram ,  Mugurel-Ionut Andreica ,  Radu Voroneanu ,  Sneha Ashok ,  Deepak Goyal ,  Kyunghoon Lee ,  Alice Liang ,  Dana Ritter ,  Adam Coimbra ,  Anton Berezin ,  Andre Elisseeff

IPC: G06F9/451 ,  G06F3/0482 ,  G06F3/0484

Abstract: Implementations relate to determining a rendering type for an application that is executing automatically. Based on user interactions with an application that is associated with specified input from the user while the user is interacting with the application, a confidence metric is generated for each specified input and a rendering type is determined based on the confidence metrics. Subsequently, when the user requests that a sequence of actions be performed, the application will be displayed according to the rendering type.

公开(公告)号：US20250045071A1

公开(公告)日：2025-02-06

申请号：US18230561

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Cliff Kuang ,  Diana Avram ,  Mugurel-Ionut Andreica ,  Radu Voroneanu ,  Sneha Ashok ,  Deepak Goyal ,  Kyunghoon Lee ,  Alice Liang ,  Dana Ritter ,  Adam Coimbra ,  Anton Berezin ,  Andre Elisseeff

IPC: G06F9/451 ,  G06F3/0482 ,  G06F3/0484

Abstract: Implementations relate to determining a rendering type for an application that is executing automatically. Based on user interactions with an application that is associated with specified input from the user while the user is interacting with the application, a confidence metric is generated for each specified input and a rendering type is determined based on the confidence metrics. Subsequently, when the user requests that a sequence of actions be performed, the application will be displayed according to the rendering type.

公开(公告)号：US20250013438A1

公开(公告)日：2025-01-09

申请号：US18746997

申请日：2024-06-18

Applicant: Google LLC

Inventor： Michael Andrew Goodman ,  Deepak Goyal

IPC: G06F8/35 ,  G06F8/34 ,  G10L13/08 ,  G10L15/22

Abstract: A method include receiving a natural language prompt from a user comprising a command to generate a code script for an automated assistant to perform a routine. The routine includes multiple discrete actions specified by the natural language prompt. The method further includes processing, by a pre-trained large language model (LLM), the natural language prompt to generate the code script as an LLM output, and processing the code script to determine the code script is incomplete, thereby rendering the code script unsuitable for the automated assistant to fulfill performance of the routine. Based on determining the code script is incomplete, the method includes issuing a user prompt soliciting the user to provide additional information needed to complete the code script and receiving user input of the additional information needed to complete the code script. The method includes supplementing the code script with the additional information to render completed code script.