公开(公告)号：US20230377331A1

公开(公告)日：2023-11-23

申请号：US18364856

申请日：2023-08-03

Applicant: Google LLC

Inventor： Henry Scott-Green ,  Anjali Malik

IPC: G06V20/20 ,  G06F16/957 ,  G06F40/134 ,  G06T5/00

CPC classification number: G06V20/20 ,  G06F16/957 ,  G06F40/134 ,  G06T5/00

Abstract: A set of media items accessible to users of a platform is identified, each media item including a reference to one or more objects. In response to a request from a client device associated with a user of the platform for access to a media item, a determination is made of one or more objects referenced by the media item that satisfies one or more criteria based on consumption data associated with the set of media items. The consumption data includes information about a consumption of the set of media items by other users of the platform over a time period. A source indicator associated with the determined objects is obtained. A user interface of the client device is updated to include, with the media item, an annotation of the objects to indicate that the objects are associated with the source indicator.

公开(公告)号：US11669860B2

公开(公告)日：2023-06-06

申请号：US16710954

申请日：2019-12-11

Applicant: Google LLC

Inventor： Henry Scott-Green ,  Michael de Ridder ,  T. J. Gaffney ,  Brian Mulford ,  Amund Tveit ,  Antoine Delaite ,  Preethi Puducheri Sundar

IPC: G06Q30/02 ,  G06Q30/0241 ,  G06N20/00 ,  G10L15/30 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06Q30/0248 ,  G06N20/00 ,  G10L15/22 ,  G10L15/26 ,  G10L15/30

Abstract: Methods, systems, and media for automated compliance determination of content items are provided. In some embodiments, the method comprises: receiving, at a server from a user device associated with a user, a request to provide a branded content item on a media content platform; in response to receiving the request, generating a transcript of a speech portion of the branded content item; generating a plurality of candidate word sequences based on the transcript; selecting a candidate word sequence from the plurality of candidate word sequences based on a similarity that is determined by comparing each of the plurality of candidate word sequences with each of a plurality of target word sequences; in response to selecting the candidate word sequence, applying a model to the selected candidate word sequence to determine whether the selected candidate word sequence contains a first disclosure statement in accordance with one or more disclosure requirements and applying the model to a content description associated with the branded content item to determine whether the content description contains a second disclosure statement in accordance with the one or more disclosure requirements; and associating the branded content item with a compliance indicator that indicates the branded content item is compliant with the one or more disclosure requirements in response to the model indicating that the selected candidate word sequence contains the first disclosure statement and in response to the model indicating that the content description contains the second disclosure statement.

公开(公告)号：US12120396B2

公开(公告)日：2024-10-15

申请号：US16627981

申请日：2019-05-15

Applicant: GOOGLE LLC

Inventor： Henry Scott-Green

IPC: H04N21/475 ,  G06N20/00 ,  H04N21/239 ,  H04N21/258 ,  H04N21/466

CPC classification number: H04N21/4756 ,  G06N20/00 ,  H04N21/2393 ,  H04N21/25891 ,  H04N21/4667

Abstract: Methods and systems for providing requested media items with supplemental media items customized for requesting users are described herein. A processing device receives a request of a first user for a first media item of a second user. The processing device determines that the first media item of the second user corresponds to a plurality of second media items of the second user. A set of rules is identified on how to select a second media item, from the plurality of second media items, to be integrated with the first media item of the second user, the set of rules being provided by the second user and comprising one or more conditions pertaining to the first user. The second media item is selected from the plurality of second media items based on the identified set of rules. The processing devices transmits the first media item and the selected second media item to a first user device of the first user, where the selected second media item is to be integrated with the first media item for presentation to the first user.

公开(公告)号：US20230306463A1

公开(公告)日：2023-09-28

申请号：US18204730

申请日：2023-06-01

Applicant: Google LLC

Inventor： Henry Scott-Green ,  Michael de Ridder ,  T.J. Gaffney ,  Brian Mulford ,  Amund Tveit ,  Antoine Delaite ,  Preethi Puducheri Sundar

IPC: G06Q30/0241 ,  G06N20/00 ,  G10L15/30 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06Q30/0248 ,  G06N20/00 ,  G10L15/30 ,  G10L15/22 ,  G10L15/26

Abstract: Methods, systems, and media for automated compliance determination of content items are provided. In some embodiments, the method comprises: receiving, at a server from a user device associated with a user, a request to provide a branded content item on a media content platform; in response to receiving the request, generating a transcript of a speech portion of the branded content item; generating a plurality of candidate word sequences based on the transcript; selecting a candidate word sequence from the plurality of candidate word sequences based on a similarity that is determined by comparing each of the plurality of candidate word sequences with each of a plurality of target word sequences; in response to selecting the candidate word sequence, applying a model to the selected candidate word sequence to determine whether the selected candidate word sequence contains a first disclosure statement in accordance with one or more disclosure requirements and applying the model to a content description associated with the branded content item to determine whether the content description contains a second disclosure statement in accordance with the one or more disclosure requirements; and associating the branded content item with a compliance indicator that indicates the branded content item is compliant with the one or more disclosure requirements in response to the model indicating that the selected candidate word sequence contains the first disclosure statement and in response to the model indicating that the content description contains the second disclosure statement.

公开(公告)号：US20210182902A1

公开(公告)日：2021-06-17

申请号：US16710954

申请日：2019-12-11

Applicant: Google LLC

Inventor： Henry Scott-Green ,  Michael de Ridder ,  T.J. Gaffney ,  Brian Mulford ,  Amund Tveit ,  Antoine Delaite ,  Preethi Puducheri Sundar

IPC: G06Q30/02 ,  G06N20/00 ,  G10L15/22 ,  G10L15/26 ,  G10L15/30

Abstract: Methods, systems, and media for automated compliance determination of content items are provided. In some embodiments, the method comprises: receiving, at a server from a user device associated with a user, a request to provide a branded content item on a media content platform; in response to receiving the request, generating a transcript of a speech portion of the branded content item; generating a plurality of candidate word sequences based on the transcript; selecting a candidate word sequence from the plurality of candidate word sequences based on a similarity that is determined by comparing each of the plurality of candidate word sequences with each of a plurality of target word sequences; in response to selecting the candidate word sequence, applying a model to the selected candidate word sequence to determine whether the selected candidate word sequence contains a first disclosure statement in accordance with one or more disclosure requirements and applying the model to a content description associated with the branded content item to determine whether the content description contains a second disclosure statement in accordance with the one or more disclosure requirements; and associating the branded content item with a compliance indicator that indicates the branded content item is compliant with the one or more disclosure requirements in response to the model indicating that the selected candidate word sequence contains the first disclosure statement and in response to the model indicating that the content description contains the second disclosure statement.

公开(公告)号：US20250024105A1

公开(公告)日：2025-01-16

申请号：US18902690

申请日：2024-09-30

Applicant: Google LLC

Inventor： Henry Scott-Green

IPC: H04N21/475 ,  G06N20/00 ,  H04N21/239 ,  H04N21/258 ,  H04N21/466

Abstract: Methods and systems for providing requested media items with supplemental media items are described herein. A request of a first user for a first media item of a second user is received. The first media item is associated with a set of rules on how to select additional media items corresponding to the first media item. The set of rules is provided by the second user and includes conditions pertaining to users requesting access to the first media item. A determination is made of whether one or more conditions defined by the set of rules and pertaining to the first user are satisfied with respect to a second media item of the additional media items. Responsive to a determination that the one or more conditions are satisfied, the second media item is provided for presentation via a first user device associated with the first user.

公开(公告)号：US20240331060A1

公开(公告)日：2024-10-03

申请号：US18744002

申请日：2024-06-14

Applicant: Google LLC

Inventor： Henry Scott-Green ,  Silviu Bota ,  Christoph Renner

IPC: G06Q50/00 ,  G06F16/9536 ,  G06N20/00 ,  G06Q10/0631 ,  G06Q10/10 ,  G06Q30/018 ,  G06Q50/26

CPC classification number: G06Q50/01 ,  G06Q30/0185 ,  G06Q50/265 ,  G06F16/9536 ,  G06N20/00 ,  G06Q10/06311 ,  G06Q10/10

Abstract: Methods, systems, and media for identifying abusive content items are provided. In some embodiments, the method comprises: receiving, at a server from a user device associated with a user, a request to provide user-generated content on a media content platform; in response to receiving the request, determining whether the user-generated content is to be reviewed by one or more reviewing users based on one or more bypass criterion; in response to determining that the user-generated content is to be reviewed based on the one or more bypass criterion, adding a review request to a queue of a reviewing user, wherein the review request includes the user-generated content and information associated with a user account corresponding to the user; and determining whether a decision responsive to the review request indicates that the user-generated content is to be provided on the media content platform, wherein: in response to determining that the decision indicates that the user-generated content item violates at least one policy associated with the media content platform, (i) a first message is transmitted to the user of the user device that indicates the at least one violated policy and a penalty to be administered to the user account corresponding to the user and (ii) a corresponding action is taken that inhibits the user-generated content from being provided on the media content platform; and in response to determining that the decision indicates that the user-generated content item does not violate the at least one policy associated with the media content platform, a second message is transmitted to the user of the user device that indicates that the user-generated content is eligible for providing on the media content platform.

公开(公告)号：US12026790B2

公开(公告)日：2024-07-02

申请号：US16615679

申请日：2019-05-13

Applicant: Google LLC

Inventor： Henry Scott-Green ,  Silviu Bota ,  Christoph Renner

IPC: G06Q50/00 ,  G06Q30/018 ,  G06Q50/26 ,  G06F16/9536 ,  G06N20/00 ,  G06Q10/0631 ,  G06Q10/10

CPC classification number: G06Q50/01 ,  G06Q30/0185 ,  G06Q50/265 ,  G06F16/9536 ,  G06N20/00 ,  G06Q10/06311 ,  G06Q10/10

Abstract: Methods, systems, and media for identifying abusive content items are provided. In some embodiments, the method comprises: receiving, at a server from a user device associated with a user, a request to provide user-generated content on a media content platform; in response to receiving the request, determining whether the user-generated content is to be reviewed by one or more reviewing users based on one or more bypass criterion; in response to determining that the user-generated content is to be reviewed based on the one or more bypass criterion, adding a review request to a queue of a reviewing user, wherein the review request includes the user-generated content and information associated with a user account corresponding to the user; and determining whether a decision responsive to the review request indicates that the user-generated content is to be provided on the media content platform, wherein: in response to determining that the decision indicates that the user-generated content item violates at least one policy associated with the media content platform, (i) a first message is transmitted to the user of the user device that indicates the at least one violated policy and a penalty to be administered to the user account corresponding to the user and (ii) a corresponding action is taken that inhibits the user-generated content from being provided on the media content platform; and in response to determining that the decision indicates that the user-generated content item does not violate the at least one policy associated with the media content platform, a second message is transmitted to the user of the user device that indicates that the user-generated content is eligible for providing on the media content platform.

公开(公告)号：US11727681B2

公开(公告)日：2023-08-15

申请号：US16627991

申请日：2019-04-08

Applicant: GOOGLE LLC

Inventor： Henry Scott-Green ,  Anjali Malik

IPC: G06V20/20 ,  G06F16/957 ,  G06F40/134 ,  G06T5/00

CPC classification number: G06V20/20 ,  G06F16/957 ,  G06F40/134 ,  G06T5/00

Abstract: Technology is disclosed for annotating and source linking the objects displayed in an image. An example method including detecting, by a processing device, an object in an image; associating the object in the image with a source indicator; annotating, by the processing device, the image to indicate the object is associated with the source indicator; receiving a user selection of the object in the image; and identifying a source based on the source indicator and on contextual data associated with the user selection, wherein the source comprises information about the object.