公开(公告)号：US20230214094A1

公开(公告)日：2023-07-06

申请号：US18067532

申请日：2022-12-16

Applicant: GOOGLE LLC

Inventor： Yana Yushkina ,  Nicholas Sexton ,  Samuel Birch ,  Filip Jerzy Gorski ,  Theresa Marie Sullivan ,  Ayman Almadhoun ,  Donn Locke Denman ,  Gang Wu ,  Krishnan R. Subramaniam ,  Bharath Santosh ,  SM Shabab Hossain ,  Sheng Wang ,  Damon Chizu Kawamoto ,  Tina Lin Zeng

IPC: G06F3/0483 ,  G06F3/0482 ,  G06F16/9538

CPC classification number: G06F3/0483 ,  G06F3/0482 ,  G06F16/9538

Abstract: A device may, in response to selection of a search area included in a webpage displayed within a display area of a browser: request a search for content of the search area, receive a searched query, a search result page for the searched query, and a related search request, and cause display of a first search request indicator and a second search request indicator within a search result area outside of the display area and within the browser. A device may receive a selection of the first search request indicator. A device may, in response to the selection of the first search request indicator, cause display of content for the first search request indicator within a navigation area of the search result area.

公开(公告)号：US20250139105A1

公开(公告)日：2025-05-01

申请号：US18496281

申请日：2023-10-27

Applicant: GOOGLE LLC

Inventor： Pranesh Srinivasan ,  Sameer Panwar ,  Krishna Rakeshkumar Shukla ,  Laichee Man ,  Bharath Santosh

IPC: G06F16/2457 ,  G06F16/248

Abstract: A method is disclosed for generating an extractive summary of a resource responsive to a query. Extractive resources can be used to rank responsive resources and/or to enhance a search result. An example method can involve determining relevance scores for sentences within the resources, generating extractive summaries from sentences with the highest relevance scores, and calculating a resource relevance scores for each resource based on the extractive summary. The resources are then ranked based on the relevance scores and a search result page generated. In some implementations, a machine learned model is used to generate the relevance score and/or the extractive summary.