公开(公告)号：US11688191B2

公开(公告)日：2023-06-27

申请号：US17941971

申请日：2022-09-09

Applicant: GOOGLE LLC

Inventor： Ibrahim Badr ,  Nils Grimsmo ,  Gokhan H. Bakir ,  Kamil Anikiej ,  Aayush Kumar ,  Viacheslav Kuznetsov

IPC: G06V30/262 ,  G06F16/58 ,  G06F16/9032 ,  G06V20/62 ,  G06V10/70 ,  G06V30/10

CPC classification number: G06V30/262 ,  G06F16/5866 ,  G06F16/9032 ,  G06V10/768 ,  G06V20/63 ,  G06V30/10

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextually disambiguating queries are disclosed. In an aspect, a method includes receiving an image being presented on a display of a computing device and a transcription of an utterance spoken by a user of the computing device, identifying a particular sub-image that is included in the image, and based on performing image recognition on the particular sub-image, determining one or more first labels that indicate a context of the particular sub-image. The method also includes, based on performing text recognition on a portion of the image other than the particular sub-image, determining one or more second labels that indicate the context of the particular sub-image, based on the transcription, the first labels, and the second labels, generating a search query, and providing, for output, the search query.

公开(公告)号：US20200081609A1

公开(公告)日：2020-03-12

申请号：US16681689

申请日：2019-11-12

Applicant: Google LLC

Inventor： Aayush Kumar ,  Gokhan Bakir

IPC: G06F3/0484 ,  G06N5/04 ,  G06F3/0481 ,  G06F9/48

Abstract: Contextual paste target prediction is used to predict one or more target applications for a paste action, and do so based upon a context associated with the content that has previously been selected and copied. The results of the prediction may be used to present to a user one or more user controls to enable the user to activate one or more predicted application, and in some instances, additionally configure a state of a predicted application to use the selected and copied content once activated. As such, upon completing a copy action, a user may, in some instances, be provided with an ability to quickly switch to an application into which the user was intending to paste the content. This can provide a simpler user interface in a device such as phones and tablet computers with limited display size and limited input device facilities. It can result in a paste operation into a different application with fewer steps than is possible conventionally.

公开(公告)号：US11442983B2

公开(公告)日：2022-09-13

申请号：US16731786

申请日：2019-12-31

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Nils Grimsmo ,  Gokhan H. Bakir ,  Kamil Anikiej ,  Aayush Kumar ,  Viacheslav Kuznetsov

IPC: G06F16/58 ,  G06F16/9032 ,  G06V10/70 ,  G06V20/62 ,  G06V30/10

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextually disambiguating queries are disclosed. In an aspect, a method includes receiving an image being presented on a display of a computing device and a transcription of an utterance spoken by a user of the computing device, identifying a particular sub-image that is included in the image, and based on performing image recognition on the particular sub-image, determining one or more first labels that indicate a context of the particular sub-image. The method also includes, based on performing text recognition on a portion of the image other than the particular sub-image, determining one or more second labels that indicate the context of the particular sub-image, based on the transcription, the first labels, and the second labels, generating a search query, and providing, for output, the search query.

公开(公告)号：US20200250227A1

公开(公告)日：2020-08-06

申请号：US16731786

申请日：2019-12-31

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Nils Grimsmo ,  Gokhan H. Bakir ,  Kamil Anikiej ,  Aayush Kumar ,  Viacheslav Kuznetsov

IPC: G06F16/58 ,  G06K9/32 ,  G06F16/9032 ,  G06K9/72

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextually disambiguating queries are disclosed. In an aspect, a method includes receiving an image being presented on a display of a computing device and a transcription of an utterance spoken by a user of the computing device, identifying a particular sub-image that is included in the image, and based on performing image recognition on the particular sub-image, determining one or more first labels that indicate a context of the particular sub-image. The method also includes, based on performing text recognition on a portion of the image other than the particular sub-image, determining one or more second labels that indicate the context of the particular sub-image, based on the transcription, the first labels, and the second labels, generating a search query, and providing, for output, the search query.

公开(公告)号：US10341272B2

公开(公告)日：2019-07-02

申请号：US15587783

申请日：2017-05-05

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Aayush Kumar ,  Goekhan Hasan Bakir ,  Nils Grimsmo ,  Bianca Madalina Buisman

IPC: G06F15/16 ,  H04L12/58

Abstract: A computer-implemented method is described. The method includes a computing system receiving an item of digital content from a user device. The computing system generates one or more labels that indicate attributes of the item of digital content. The computing system also generates one or more conversational replies to the item of digital content based on the one or more labels that indicate attributes of the item of digital content. The method also includes the computing system selecting a conversational reply from among the one or more conversational replies and providing the conversational reply for output to the user device.

公开(公告)号：US11755662B1

公开(公告)日：2023-09-12

申请号：US16293645

申请日：2019-03-06

Applicant: Google LLC

Inventor： Alasdair John Mackintosh ,  Aayush Kumar

IPC: G06F16/951

CPC classification number: G06F16/951

Abstract: Methods and apparatus related to creating entries in a personal cache of a user and/or a personal index of a user. Entries may be created in a personal cache and/or a personal index of a user based on web-based documents visited by the user and one or more of the entries may include content specific to the user’s experience with a web-based document. The personal cache and/or personal index may enable a user to view all or aspects of previously visited web-based documents and/or search previously visited web-based documents. An entry of a user’s personal cache and/or personal index may optionally include information that may not be found in a public cache and/or public index.

公开(公告)号：US10778619B2

公开(公告)日：2020-09-15

申请号：US16411792

申请日：2019-05-14

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Aayush Kumar ,  Goekhan Hasan Bakir ,  Nils Grimsmo ,  Bianca Madalina Buisman

IPC: G06F15/16 ,  H04L12/58

Abstract: A computer-implemented method is described. The method includes a computing system receiving an item of digital content from a user device. The computing system generates one or more labels that indicate attributes of the item of digital content. The computing system also generates one or more conversational replies to the item of digital content based on the one or more labels that indicate attributes of the item of digital content. The method also includes the computing system selecting a conversational reply from among the one or more conversational replies and providing the conversational reply for output to the user device.

公开(公告)号：US10565256B2

公开(公告)日：2020-02-18

申请号：US15463018

申请日：2017-03-20

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Nils Grimsmo ,  Gokhan H. Bakir ,  Kamil Anikiej ,  Aayush Kumar ,  Viacheslav Kuznetsov

IPC: G06F16/58 ,  G06K9/72 ,  G06F16/9032 ,  G06K9/32

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for contextually disambiguating queries are disclosed. In an aspect, a method includes receiving an image being presented on a display of a computing device and a transcription of an utterance spoken by a user of the computing device, identifying a particular sub-image that is included in the image, and based on performing image recognition on the particular sub-image, determining one or more first labels that indicate a context of the particular sub-image. The method also includes, based on performing text recognition on a portion of the image other than the particular sub-image, determining one or more second labels that indicate the context of the particular sub-image, based on the transcription, the first labels, and the second labels, generating a search query, and providing, for output, the search query.

公开(公告)号：US20240195765A1

公开(公告)日：2024-06-13

申请号：US18582513

申请日：2024-02-20

Applicant: GOOGLE LLC

Inventor： Ibrahim Badr ,  Aayush Kumar ,  Goekhan Hasan Bakir ,  Nils Grimsmo ,  Bianca Madalina Buisman

IPC: H04L51/046 ,  H04L51/10

CPC classification number: H04L51/046 ,  H04L51/10

Abstract: A computer-implemented method is described. The method includes a computing system receiving an item of digital content from a user device. The computing system generates one or more labels that indicate attributes of the item of digital content. The computing system also generates one or more conversational replies to the item of digital content based on the one or more labels that indicate attributes of the item of digital content. The method also includes the computing system selecting a conversational reply from among the one or more conversational replies and providing the conversational reply for output to the user device.

公开(公告)号：US20220337539A1

公开(公告)日：2022-10-20

申请号：US17859460

申请日：2022-07-07

Applicant: GOOGLE LLC

Inventor： Ibrahim Badr ,  Aayush Kumar ,  Goekhan Hasan Bakir ,  Nils Grimsmo ,  Bianca Madalina Buisman

IPC: H04L51/046 ,  H04L51/10

Abstract: A computer-implemented method is described. The method includes a computing system receiving an item of digital content from a user device. The computing system generates one or more labels that indicate attributes of the item of digital content. The computing system also generates one or more conversational replies to the item of digital content based on the one or more labels that indicate attributes of the item of digital content. The method also includes the computing system selecting a conversational reply from among the one or more conversational replies and providing the conversational reply for output to the user device.