公开(公告)号：US20250117381A1

公开(公告)日：2025-04-10

申请号：US18908392

申请日：2024-10-07

Applicant: GOOGLE LLC

Inventor： Asaf Revach ,  Hongrae Lee ,  Zhengzhong Liang

IPC: G06F16/2453 ,  G06F40/40

Abstract: Implementations leverage a generative model (e.g., a large language model (LLM)) to generate a plurality of candidate subqueries for multifaceted natural language (NL) based input, where each of the candidate subqueries is potentially directed to a facet or problem of the multifaceted NL based input. Those implementations further select, from the plurality of candidate subqueries and using one or more evaluation metrics, a subset of the candidate queries. Those implementations further, in response to selecting the subset of the candidate queries, obtain, for each of the candidate subqueries of the selected subset, at least one corresponding search result. Those implementations further generate a response to the NL based input based on the corresponding search results for the candidate subqueries of the subset, and cause the response to be rendered responsive to the NL based input.

公开(公告)号：US11249993B2

公开(公告)日：2022-02-15

申请号：US16881899

申请日：2020-05-22

Applicant: Google LLC

Inventor： Jayant Madhavan ,  Hongrae Lee ,  Warren H. Y. Shen ,  Sreeram Viswanath Balakrishnan

IPC: G06F16/00 ,  G06F16/2452 ,  G06F16/245 ,  G06F16/951 ,  G06F16/2457

Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.

公开(公告)号：US20200265191A1

公开(公告)日：2020-08-20

申请号：US16865747

申请日：2020-05-04

Applicant: Google LLC

Inventor： Quoc V. Le ,  Hongrae Lee ,  Wei Yu

IPC: G06F40/284 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.

公开(公告)号：US10698888B1

公开(公告)日：2020-06-30

申请号：US15881315

申请日：2018-01-26

Applicant: Google LLC

Inventor： Jayant Madhavan ,  Hongrae Lee ,  Warren H. Y. Shen ,  Sreeram Viswanath Balakrishnan

IPC: G06F16/00 ,  G06F16/2452 ,  G06F16/245 ,  G06F16/951 ,  G06F16/2457

Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.

公开(公告)号：US10679006B2

公开(公告)日：2020-06-09

申请号：US16508066

申请日：2019-07-10

Applicant: Google LLC

Inventor： Quoc V. Le ,  Hongrae Lee ,  Wei Yu

IPC: G06F40/284 ,  G06N3/08 ,  G06F40/289 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.

公开(公告)号：US20190340236A1

公开(公告)日：2019-11-07

申请号：US16508066

申请日：2019-07-10

Applicant: Google LLC

Inventor： Quoc V. Le ,  Hongrae Lee ,  Wei Yu

IPC: G06F17/27 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.

公开(公告)号：US20240119047A1

公开(公告)日：2024-04-11

申请号：US18487361

申请日：2023-10-16

Applicant: GOOGLE LLC

Inventor： Jayant Madhavan ,  Hongrae Lee ,  Sreeram Viswanath Balakrishnan ,  Warren H.Y. Shen

IPC: G06F16/2452 ,  G06F16/245 ,  G06F16/2457 ,  G06F16/951

CPC classification number: G06F16/24522 ,  G06F16/245 ,  G06F16/24578 ,  G06F16/951

Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.

公开(公告)号：US11789946B2

公开(公告)日：2023-10-17

申请号：US17650939

申请日：2022-02-14

Applicant: GOOGLE LLC

Inventor： Jayant Madhavan ,  Hongrae Lee ,  Sreeram Viswanath Balakrishnan ,  Warren H. Y. Shen

IPC: G06F16/00 ,  G06F16/2452 ,  G06F16/245 ,  G06F16/951 ,  G06F16/2457

CPC classification number: G06F16/24522 ,  G06F16/245 ,  G06F16/24578 ,  G06F16/951

Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.

公开(公告)号：US20220171779A1

公开(公告)日：2022-06-02

申请号：US17650939

申请日：2022-02-14

Applicant: GOOGLE LLC

Inventor： Jayant Madhavan ,  Hongrae Lee ,  Sreeram Viswanath Balakrishnan ,  Warren H.Y. Shen

IPC: G06F16/2452 ,  G06F16/245 ,  G06F16/951 ,  G06F16/2457

Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.

公开(公告)号：US11048875B2

公开(公告)日：2021-06-29

申请号：US16865747

申请日：2020-05-04

Applicant: Google LLC

Inventor： Quoc V. Le ,  Hongrae Lee ,  Wei Yu

IPC: G06F40/30 ,  G06F40/284 ,  G06N3/04 ,  G06N3/08 ,  G06F40/289

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.