US 11,886,828 B1
Generative summaries for search results
Matthew K. Gray, Reading, MA (US); John Blitzer, Mountain View, CA (US); Corinn Herrick, Mountain View, CA (US); Srinivasan Venkatachary, Sunnyvale, CA (US); Jayant Madhavan, San Francisco, CA (US); Sam Oates, Cambridge, MA (US); Phiroze Parakh, San Jose, CA (US); Aditya Shah, Mountain View, CA (US); Mahsan Rofouei, Menlo Park, CA (US); and Ibrahim Badr, Zurich (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Aug. 22, 2023, as Appl. No. 18/236,760.
Application 18/236,760 is a continuation of application No. 18/123,861, filed on Mar. 20, 2023, granted, now 11,769,017.
Claims priority of provisional application 63/436,416, filed on Dec. 30, 2022.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/40 (2020.01); G06F 16/332 (2019.01)
CPC G06F 40/40 (2020.01) [G06F 16/3328 (2019.01)] 22 Claims
OG exemplary drawing
 
1. A system, comprising:
memory storing instructions;
one or more processors operable to execute the instruction to:
receive a query associated with a client device;
in response to receiving the query:
select a set of search result documents, wherein in selecting the set of search result documents one or more of the processors are to select, for inclusion in the set, a plurality of query-responsive search result documents based on the query-responsive search result documents being responsive to the query;
generate a prompt that includes:
corresponding content from each of the search result documents of the set of search result documents, and
additional content that is in addition to the corresponding content and that is in addition to the query;
generate large language model (LLM) output based on processing the prompt using an LLM;
generate a natural language (NL) based summary using the LLM output; and
cause the NL based summary to be rendered at the client device in response to the query.