公开(公告)号：US11694034B2

公开(公告)日：2023-07-04

申请号：US17078569

申请日：2020-10-23

Applicant: Google LLC

Inventor： Liu Yang ,  Marc Najork ,  Michael Bendersky ,  Mingyang Zhang ,  Cheng Li

IPC: G06F40/30 ,  G06N3/08 ,  G06F40/205 ,  G06N3/045

CPC classification number: G06F40/30 ,  G06F40/205 ,  G06N3/045 ,  G06N3/08

Abstract: Systems and methods of the present disclosure are directed to a method for predicting semantic similarity between documents. The method can include obtaining a first document and a second document. The method can include parsing the first document into a plurality of first textual blocks and the second document into a plurality of second textual blocks. The method can include processing each of the plurality of first textual blocks and the second textual blocks with a machine-learned semantic document encoding model to obtain a first document encoding and a second document encoding. The method can include determining a similarity metric descriptive of a semantic similarity between the first document and the second document based on the first document encoding and the second document encoding.

公开(公告)号：US20220129638A1

公开(公告)日：2022-04-28

申请号：US17078569

申请日：2020-10-23

Applicant: Google LLC

Inventor： Liu Yang ,  Marc Najork ,  Michael Bendersky ,  Mingyang Zhang ,  Cheng Li

IPC: G06F40/30 ,  G06F40/205 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods of the present disclosure are directed to a method for predicting semantic similarity between documents. The method can include obtaining a first document and a second document. The method can include parsing the first document into a plurality of first textual blocks and the second document into a plurality of second textual blocks. The method can include processing each of the plurality of first textual blocks and the second textual blocks with a machine-learned semantic document encoding model to obtain a first document encoding and a second document encoding. The method can include determining a similarity metric descriptive of a semantic similarity between the first document and the second document based on the first document encoding and the second document encoding.

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：US12210837B2

公开(公告)日：2025-01-28

申请号：US18321424

申请日：2023-05-22

Applicant: Google LLC

Inventor： Liu Yang ,  Marc Najork ,  Michael Bendersky ,  Mingyang Zhang ,  Cheng Li

IPC: G06F40/30 ,  G06F40/205 ,  G06N3/045 ,  G06N3/08

Abstract: Systems and methods of the present disclosure are directed to a method for predicting semantic similarity between documents. The method can include obtaining a first document and a second document. The method can include parsing the first document into a plurality of first textual blocks and the second document into a plurality of second textual blocks. The method can include processing each of the plurality of first textual blocks and the second textual blocks with a machine-learned semantic document encoding model to obtain a first document encoding and a second document encoding. The method can include determining a similarity metric descriptive of a semantic similarity between the first document and the second document based on the first document encoding and the second document encoding.

公开(公告)号：US20230297783A1

公开(公告)日：2023-09-21

申请号：US18321424

申请日：2023-05-22

Applicant: Google LLC

Inventor： Liu Yang ,  Marc Najork ,  Michael Bendersky ,  Mingyang Zhang ,  Cheng Li

IPC: G06F40/30 ,  G06N3/08 ,  G06F40/205 ,  G06N3/045

CPC classification number: G06F40/30 ,  G06N3/08 ,  G06F40/205 ,  G06N3/045

Abstract: Systems and methods of the present disclosure are directed to a method for predicting semantic similarity between documents. The method can include obtaining a first document and a second document. The method can include parsing the first document into a plurality of first textual blocks and the second document into a plurality of second textual blocks. The method can include processing each of the plurality of first textual blocks and the second textual blocks with a machine-learned semantic document encoding model to obtain a first document encoding and a second document encoding. The method can include determining a similarity metric descriptive of a semantic similarity between the first document and the second document based on the first document encoding and the second document encoding.

公开(公告)号：US20190235888A1

公开(公告)日：2019-08-01

申请号：US16381447

申请日：2019-04-11

Applicant: Google LLC

Inventor： Cheng Li ,  BO Wang ,  Okan Kolak ,  Peter Hodgson ,  Deniz Binay ,  Dhruv Amin ,  Pravir Gupta ,  Nitin Shetti ,  Javier Rey

IPC: G06F9/451 ,  G06F9/48

CPC classification number: G06F9/453 ,  G06F9/4843 ,  G10L15/22

Abstract: Techniques are described herein for leveraging information about a user to enable a personal assistant module to make various inferences about what actions that may be responsive to a user declaration. In various implementations, upon identifying a user declaration received at a computing device, a plurality of candidate responsive actions that can be initiated by the computing device in response to the user declaration may be identified. A single candidate responsive action may then be non-deterministically (e.g., randomly, stochastically) selected to be exclusively initiated on the computing device in response to the user declaration.