公开(公告)号：US11886828B1

公开(公告)日：2024-01-30

申请号：US18236760

申请日：2023-08-22

Applicant: GOOGLE LLC

Inventor： Matthew K. Gray ,  John Blitzer ,  Corinn Herrick ,  Srinivasan Venkatachary ,  Jayant Madhavan ,  Sam Oates ,  Phiroze Parakh ,  Aditya Shah ,  Mahsan Rofouei ,  Ibrahim Badr

IPC: G06F40/40 ,  G06F16/332

CPC classification number: G06F40/40 ,  G06F16/3328

Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

公开(公告)号：US10353964B2

公开(公告)日：2019-07-16

申请号：US14644803

申请日：2015-03-11

Applicant: Google LLC

Inventor： Ashish Venugopal ,  Jakob D. Uszkoreit ,  John Blitzer ,  Edward Everett Anderson

IPC: G06F16/951 ,  G06F16/33

Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.

公开(公告)号：US09984684B1

公开(公告)日：2018-05-29

申请号：US13926844

申请日：2013-06-25

Applicant: Google LLC

Inventor： Jakob D. Uszkoreit ,  John Blitzer ,  Engin Cinar Sahin ,  Rahul Gupta ,  Dekang Lin ,  Fernando Pereira

IPC: G06F17/30 ,  G10L15/18 ,  G06F17/27

CPC classification number: G10L15/1822 ,  G06F17/271 ,  G06F17/30424 ,  G06F17/30654 ,  G06F17/30864 ,  G10L15/26

Abstract: A language processing system collects similar queries and respective responses and aggregated by responses. Incorrect responses are determined and filtered by the aggregation. The remaining responses are then used to query a high precision system for attributes of entities specified by the queries. The attribute type is determined from the responses of the high precision system, and corresponding parse rules are generated. The parse rules are then associated with an operation that yields a response that specifies an attribute of the attribute type.

公开(公告)号：US11769017B1

公开(公告)日：2023-09-26

申请号：US18123861

申请日：2023-03-20

Applicant: GOOGLE LLC

Inventor： Matthew K. Gray ,  John Blitzer ,  Corinn Herrick ,  Srinivasan Venkatachary ,  Jayant Madhavan ,  Sam Oates ,  Phiroze Parakh ,  Aditya Shah ,  Mahsan Rofouei ,  Ibrahim Badr

IPC: G06F40/40 ,  G06F16/332

CPC classification number: G06F40/40 ,  G06F16/3328

Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

公开(公告)号：US10521479B2

公开(公告)日：2019-12-31

申请号：US16416842

申请日：2019-05-20

Applicant: Google LLC

Inventor： Ashish Venugopal ,  Jakob D. Uszkoreit ,  John Blitzer ,  Edward Everett Anderson

IPC: G06F16/951 ,  G06F16/33

Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.

公开(公告)号：US20190130251A1

公开(公告)日：2019-05-02

申请号：US16176961

申请日：2018-10-31

Applicant: Google LLC

Inventor： Ni Lao ,  Chen Liang ,  Quoc V. Le ,  John Blitzer

IPC: G06N3/04 ,  G06F17/30 ,  G06F17/27 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output from a system input using a neural network system comprising an encoder neural network configured to, for each of a plurality of encoder time steps, receive an input sequence comprising a respective question token, and process the question token at the encoder time step to generate an encoded representation of the question token, and a decoder neural network configured to, for each of a plurality of decoder time steps, receive a decoder input, and process the decoder input and a preceding decoder hidden state to generate an updated decoder hidden state.

公开(公告)号：US20250005303A1

公开(公告)日：2025-01-02

申请号：US18829990

申请日：2024-09-10

Applicant: GOOGLE LLC

Inventor： Matthew K. Gray ,  John Blitzer ,  Corinn Herrick ,  Srinivasan Venkatachary ,  Jayant Madhavan ,  Sam Oates ,  Phiroze Parakh ,  Aditya Shah ,  Mahsan Rofouei ,  Ibrahim Badr

IPC: G06F40/40 ,  G06F16/332

Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

公开(公告)号：US12118325B2

公开(公告)日：2024-10-15

申请号：US18232144

申请日：2023-08-09

Applicant: GOOGLE LLC

Inventor： Matthew K. Gray ,  John Blitzer ,  Corinn Herrick ,  Srinivasan Venkatachary ,  Jayant Madhavan ,  Sam Oates ,  Phiroze Parakh ,  Aditya Shah ,  Mahsan Rofouei ,  Ibrahim Badr

IPC: G06F40/40 ,  G06F16/332

CPC classification number: G06F40/40 ,  G06F16/3328

Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

公开(公告)号：US20240220735A1

公开(公告)日：2024-07-04

申请号：US18232144

申请日：2023-08-09

Applicant: GOOGLE LLC

Inventor： Matthew K. Gray ,  John Blitzer ,  Corinn Herrick ,  Srinivasan Venkatachary ,  Jayant Madhavan ,  Sam Oates ,  Phiroze Parakh ,  Aditya Shah ,  Mahsan Rofouei ,  Ibrahim Badr

IPC: G06F40/40 ,  G06F16/332

CPC classification number: G06F40/40 ,  G06F16/3328

Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.

公开(公告)号：US20210026846A1

公开(公告)日：2021-01-28

申请号：US16949076

申请日：2020-10-13

Applicant: GOOGLE LLC

Inventor： Amarnag Subramanya ,  Fernando Pereira ,  Ni Lao ,  John Blitzer ,  Rahul Gupta

IPC: G06F16/245

Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.