公开(公告)号：US11586684B2

公开(公告)日：2023-02-21

申请号：US16566076

申请日：2019-09-10

Applicant: Google LLC

Inventor： Matthew Strecker Burriesci ,  David Kent German ,  Mathieu Gagne ,  Michael Kleber ,  Jonathan Frank Guarino ,  Guy Maor

IPC: G06F16/951

Abstract: When a client device loads a resource, a request for a first content item for a first content item slot is transmitted to a content item selection system. The content item selection system uses a predictive model to determine a predicted content item slot based on a document object model position of the first content item slot and a URL of the resource or a publisher identifier. Parameters for the predicted content item slot are used to select a subsequent content item for the predicted content item slot. The first content item and the subsequent content item are transmitted to the client device responsive to the request. The subsequent content item includes metadata indicative of the parameters of the predicted content item slot to be matched to a subsequent content item slot of the resource.

公开(公告)号：US20220391947A1

公开(公告)日：2022-12-08

申请号：US17892699

申请日：2022-08-22

Applicant: Google LLC

Inventor： Michael Kleber ,  Gang Wang ,  Daniel Ramage ,  Charles Harrison ,  Josh Karlin ,  Moti Yung

IPC: G06Q30/02 ,  G06F16/951 ,  H04L9/32 ,  H04L9/08

Abstract: The present disclosure provides systems and methods for content quasi-personalization or anonymized content retrieval via aggregated browsing history of a large plurality of devices, such as millions or billions of devices. A sparse matrix may be constructed from the aggregated browsing history, and dimensionally reduced, reducing entropy and providing anonymity for individual devices. Relevant content may be selected via quasi-personalized clusters representing similar browsing histories, without exposing individual device details to content providers.

公开(公告)号：US20220253557A1

公开(公告)日：2022-08-11

申请号：US17627033

申请日：2020-04-16

Applicant: Google LLC

Inventor： Michael Kleber ,  Zhenyu Liu ,  Josh Karlin ,  Deepak Ravichandran ,  Nitish John Korula ,  Yijian Bai ,  Jason Hsueh ,  Gang Wang

IPC: G06F21/62 ,  G06N20/00 ,  H04L67/53 ,  H04L67/50

Abstract: The present disclosure provides systems and methods for client-side anonymized content selections. The method includes collecting a plurality of identifications of content selection lists, each content selection list associated with the first device and at least one other device. The method includes selecting a first subset of the content selection lists, responsive to a total number of unique device associated with a plurality of content selection lists of the first subset exceeding a threshold. The method includes transmitting a request for an item of content, the request comprising identifications of the content selection lists of the selected first subset. The method includes receiving a first item of content selected by the content server based on the content selection lists of the selected first subset.

公开(公告)号：US20210042787A1

公开(公告)日：2021-02-11

申请号：US16698548

申请日：2019-11-27

Applicant: Google LLC

Inventor： Michael Kleber ,  Gang Wang ,  Daniel Ramage ,  Charlie Harrison ,  Josh Karlin ,  Moti Yung

IPC: G06Q30/02 ,  H04L9/32 ,  H04L9/08 ,  G06F16/951

Abstract: The present disclosure provides systems and methods for content quasi-personalization or anonymized content retrieval via aggregated browsing history of a large plurality of devices, such as millions or billions of devices. A sparse matrix may be constructed from the aggregated browsing history, and dimensionally reduced, reducing entropy and providing anonymity for individual devices. Relevant content may be selected via quasi-personalized clusters representing similar browsing histories, without exposing individual device details to content providers.

公开(公告)号：US20210034782A1

公开(公告)日：2021-02-04

申请号：US16524792

申请日：2019-07-29

Applicant: GOOGLE LLC

Inventor： Michael Kleber ,  Vic Liu ,  Josh Karlin ,  Gang Wang ,  Nitish Korula ,  Yijian Bai ,  Jason Hsueh ,  Deepak Ravichandran

IPC: G06F21/62 ,  H04L29/08 ,  G06N20/00

Abstract: The present disclosure provides systems and methods for client-side anonymized content selections. The method includes collecting a plurality of identifications of content selection lists, each content selection list associated with the first device and at least one other device. The method includes selecting a first subset of the content selection lists, responsive to a total number of unique device associated with a plurality of content selection lists of the first subset exceeding a threshold. The method includes transmitting a request for an item of content, the request comprising identifications of the content selection lists of the selected first subset. The method includes receiving a first item of content selected by the content server based on the content selection lists of the selected first subset.

公开(公告)号：US20200336561A1

公开(公告)日：2020-10-22

申请号：US16917164

申请日：2020-06-30

Applicant: Google LLC

Inventor： Shing Franky Sze ,  Michael Kleber ,  Mathieu Gagne ,  Leonidas Kontothanassis

IPC: H04L29/08 ,  G06Q30/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reducing redirects. In one aspect, a method includes receiving request data indicating that a user device has requested a content item. The request data specifies other data processing apparatus to which user interactions with the content item are to be reported. The content item includes a reference to a resource that is requested in response to user interaction with the content item. Response data is provided. The response data includes data that cause presentation of the content item. Interaction data is received specifying user interaction with the content item occurred. Redirect data is provided that cause the user device to be redirected to the resource. Reporting data is provided to the other data processing apparatus, specifying user interaction with the content item occurred. The reporting data is provided asynchronously relative to the redirect data.