公开(公告)号：US20240289407A1

公开(公告)日：2024-08-29

申请号：US18589371

申请日：2024-02-27

Applicant: GOOGLE LLC

Inventor： Mahsan Rofouei ,  Anand Shukla ,  Qing Wei ,  Chi Tang ,  Ryan Brown ,  Enrique Piqueras

IPC: G06F16/957 ,  G06F16/9532 ,  G06F16/9535 ,  G06F40/40

CPC classification number: G06F16/9577 ,  G06F16/9532 ,  G06F16/9535 ,  G06F40/40

Abstract: Implementations are described herein for augmenting a traditional search session with stateful chat—via what will be referred to as a “generative companion”—to facilitate more interactive searching. In various implementations, a query may be received, e.g., from a client device operated by a user. Contextual information associated with the user or the client device may be retrieved. Generative model (GM) output may be generated based on processing, using a generative model, data indicative of the query and the contextual information. Synthetic queries may be generated using the GM output, and search result documents (SRDs) may be selected. State data indicative of: the query, contextual information, one or more of the synthetic queries, and the set of search result documents, may be processed to identify a classification of the query. Based on the classification downstream GM(s) may be selected and used to generate one or more additional GM outputs.

公开(公告)号：US09996624B2

公开(公告)日：2018-06-12

申请号：US14751774

申请日：2015-06-26

Applicant: Google LLC

Inventor： Anand Shukla ,  Pavan K. Desikan ,  Isabelle L. Stanton ,  Salvatore J. Candido

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30345 ,  G06F17/30528 ,  G06F17/30554 ,  G06F17/30864

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing actions of determining that one or more in-depth article search results are to be provided in response to a query, obtaining a topicality score for each in-depth article of a plurality of in-depth articles, each topicality score indicating a degree of relevance of a respective in-depth article to the query, obtaining a document score for each in-depth article of the plurality of in-depth article, each document score being based on a respective topicality score and a respective in-depth article score, selecting one or more in-depth articles from the plurality of in-depth articles based on respective document scores, and providing the one or more in-depth article search results for display, each in-depth article search result representing an in-depth article of the one or more in-depth articles.