公开(公告)号：US20230222285A1

公开(公告)日：2023-07-13

申请号：US17928984

申请日：2020-12-22

Applicant: Google LLC

Inventor： Mingyang Zhang ,  Cheng Li ,  Tao Chen ,  Spurthi Amba Hombaiah ,  Michael Bendersky ,  Marc Alexander Najork ,  Te-Lin Wu

IPC: G06F40/166 ,  G06F40/284 ,  G06V30/413 ,  G06F40/109

CPC classification number: G06F40/166 ,  G06F40/284 ,  G06V30/413 ,  G06F40/109

Abstract: Systems and methods for document processing that can process and understand the layout, text size, text style, and multimedia of a document can generate more accurate and informed document representations. The layout of a document paired with text size and style can indicate what portions of a document are possibly more important, and the understanding of that importance can help with understanding of the document. Systems and methods utilizing a hierarchical framework that processes the block-level and the document-level of a document can capitalize on these indicators to generate a better document representation.

公开(公告)号：US20230169128A1

公开(公告)日：2023-06-01

申请号：US17995248

申请日：2020-03-30

Applicant: GOOGLE LLC

Inventor： Michael Bendersky ,  Przemyslaw Gajda ,  Sergey Novikov ,  Marc Alexander Najork ,  Shuguang Han

IPC: G06F16/951 ,  G06Q30/0207

CPC classification number: G06F16/951 ,  G06Q30/0239

Abstract: Techniques of generating recrawl policies for commercial offer pages include generating a multiple strategy approach using a number of different strategies. In some implementations, each strategy is an arm of a K-armed adversarial bandits algorithm with reinforcement learning. Moreover, in some implementations, the multiple strategy approach also uses a machine learning algorithm to estimate parameters such as a click rate, impression rate, and likelihood of price change, i.e., change rate, which was assumed known in the conventional approaches.

公开(公告)号：US10970293B2

公开(公告)日：2021-04-06

申请号：US16550918

申请日：2019-08-26

Applicant: Google LLC

Inventor： Mike Bendersky ,  Marc Alexander Najork ,  Donald Metzler ,  Xuanhui Wang

IPC: G06F16/2457 ,  G06F16/248 ,  G06F16/25 ,  G06F16/335

Abstract: Methods and apparatus related to using document feature(s) of a document that is responsive to a query, and optionally query feature(s) of the query, to determine a presentation characteristic for presenting a search result that corresponds to the document. In some implementations, measures associated with the document feature(s) and/or query feature(s) may be used to determine the presentation characteristic. The measures may be based on past interactions, by corresponding users, with other documents that share one or more of the document features with the document, where a plurality of the other documents are different from the document (and optionally each different from one another). In some implementations, the document and/or the other documents include, or are restricted to, documents that are access restricted.

公开(公告)号：US12182509B2

公开(公告)日：2024-12-31

申请号：US17336093

申请日：2021-06-01

Applicant: Google LLC

Inventor： Karthik Raman ,  Liu Yang ,  Mike Bendersky ,  Jiecao Chen ,  Marc Alexander Najork

IPC: G06F40/284 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a tuple of respective input sequences to generate an output. In one aspect, one of the systems includes a neural network comprising a plurality of encoder neural networks and a head neural network, each encoder neural network configured to: receive a respective input sequence from the tuple; process the respective input sequence using one or more encoder network layers to generate an encoded representation comprising a sequence of tokens; and process each of some or all of the tokens in the sequence of tokens using a projection layer to generate a lower-dimensional representation, and the head neural network configured to: receive lower-dimensional representations of a respective proper subset of the sequence of tokens generated by the encoder neural network; and process the lower-dimensional representations to generate the output.

公开(公告)号：US12141214B2

公开(公告)日：2024-11-12

申请号：US17995248

申请日：2020-03-30

Applicant: GOOGLE LLC

Inventor： Michael Bendersky ,  Przemysław Gajda ,  Sergey Novikov ,  Marc Alexander Najork ,  Shuguang Han

IPC: G06F16/951 ,  G06F18/214 ,  G06Q30/0207 ,  G06Q30/0601

Abstract: Techniques of generating recrawl policies for commercial offer pages include generating a multiple strategy approach using a number of different strategies. In some implementations, each strategy is an arm of a K-armed adversarial bandits algorithm with reinforcement learning. Moreover, in some implementations, the multiple strategy approach also uses a machine learning algorithm to estimate parameters such as a click rate, impression rate, and likelihood of price change, i.e., change rate, which was assumed known in the conventional approaches.

公开(公告)号：US20220004918A1

公开(公告)日：2022-01-06

申请号：US16946779

申请日：2020-07-06

Applicant: Google LLC

Inventor： Spurthi Amba Hombaiah ,  Vladimir Ofitserov ,  Mike Bendersky ,  Marc Alexander Najork

IPC: G06N20/00 ,  G06N5/04 ,  G06F16/9038

Abstract: Implementations relate to training a model that can be used to process values for defined features, where the values are specific to a user account, to generate a predicted user measure that reflects both popularity and quality of the user account. The model is trained based on losses that are each generated as a function of both a corresponding generated popularity measure and a corresponding generated quality measure of a corresponding training instance. Accordingly, the model can be trained to generate, based on values for a given user account, a single measure that reflects both quality and popularity of the given user account. Implementations are additionally or alternatively directed to utilizing such predicted user measures to restrict provisioning of content items that are from user accounts having respective predicted user measures that fail to satisfy a threshold.

公开(公告)号：US20210049165A1

公开(公告)日：2021-02-18

申请号：US17086564

申请日：2020-11-02

Applicant: Google LLC

Inventor： Marc Alexander Najork ,  Sujith Ravi ,  Michael Bendersky ,  Peter Shao-sen Young ,  Timothy Youngjin Sohn ,  Mingyang Zhang ,  Thomas Nelson ,  Xuanhui Wang

IPC: G06F16/248 ,  G06F16/2455 ,  G06F16/951 ,  G06F16/38

Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, to facilitate identification of additional trigger-terms for a structured information card. In one aspect, the method includes actions of accessing data associated with a template for presenting structured information, wherein the accessed data references (i) a label term and (ii) a value. Other actions may include obtaining a candidate label term, identifying one or more entities that are associated with the label term, identifying one or more of the entities that are associated with the candidate label term, and for each particular entity of the one or more entities that are associated with the candidate label term, associating, with the candidate label term, (i) a label term that is associated with the particular entity, and (ii) the value associated with the label term.