公开(公告)号：US10936258B1

公开(公告)日：2021-03-02

申请号：US16737730

申请日：2020-01-08

Applicant: Amazon Technologies, Inc.

Inventor： Andrew J. Bradley ,  Andrew Craig Brind ,  Anthony Richard McBryan ,  Sebastiano Merlino ,  Sean Daniel Murphy ,  Alistair Francis Smith ,  David Neil Turner

IPC: G06F3/12 ,  G06Q10/06

Abstract: This disclosure describes systems, methods, and computer-readable media related to retargeting online advertisement campaign recommendations for advertisements with multiple items or services. Bids may be based on a combined advertisement creative comprising two or more items or services. Dynamically selecting multiple items at bid time using a retargeting model to determine a potential revenue generation amount associated with an event may increase the probability of a conversion event based on the creative that includes the selected items. In some embodiments, a machine-learned retargeting model may be used to select multiple items to be displayed in an advertisement. The retargeting model may be applied to items that were previously viewed by the consumer and may determine a value for each of the items using factors. A bid may be calculated for each of the selected items using the values determined by the retargeting model.

公开(公告)号：US11037181B1

公开(公告)日：2021-06-15

申请号：US15826168

申请日：2017-11-29

Applicant: Amazon Technologies, inc.

Inventor： Christopher Walton ,  Graham Ritchie ,  Paul Anthony Kotas ,  Sean Donahoe ,  Oliver Masting ,  David Neil Turner ,  Ramesh Ravipati ,  José Lucas Lemos Mendonça ,  Sebastian Koch

IPC: G06Q30/02

Abstract: Systems, methods, and computer-readable media are disclosed for dynamically determining relative product performance using quantitative values. In one embodiment, an example method may include determining, by one or more computer processors coupled to at least one memory, a first product of a product catalog, determining a first set of actual performance values for the first product during a first time period, generating a first expected performance model based at least in part on a first set of product attributes for the first product and the first set of actual performance values, determining a first expected performance value for the first product based at least in part on the first expected performance model and the first set of product attributes, determining a first average actual performance value for the first product over the first time period based at least in part on the first set of actual performance values, and determining a first relative performance value for the first product based at least in part on the first average actual performance value and the first expected performance value.

公开(公告)号：US11256453B1

公开(公告)日：2022-02-22

申请号：US17169612

申请日：2021-02-08

Applicant: Amazon Technologies, Inc.

Inventor： Andrew J. Bradley ,  Andrew Craig Brind ,  Anthony Richard McBryan ,  Sebastiano Merlino ,  Sean Daniel Murphy ,  Alistair Francis Smith ,  David Neil Turner

IPC: G06F3/12 ,  G06Q30/02 ,  G06Q10/06

Abstract: This disclosure describes systems, methods, and computer-readable media related to retargeting online advertisement campaign recommendations for advertisements with multiple items or services. Bids may be based on a combined advertisement creative comprising two or more items or services. Dynamically selecting multiple items at bid time using a retargeting model to determine a potential revenue generation amount associated with an event may increase the probability of a conversion event based on the creative that includes the selected items. In some embodiments, a machine-learned retargeting model may be used to select multiple items to be displayed in an advertisement. The retargeting model may be applied to items that were previously viewed by the consumer and may determine a value for each of the items using factors. A bid may be calculated for each of the selected items using the values determined by the retargeting model.

公开(公告)号：US10559001B1

公开(公告)日：2020-02-11

申请号：US14747451

申请日：2015-06-23

Applicant: Amazon Technologies, Inc.

Inventor： Andrew J. Bradley ,  Andrew Craig Brind ,  Anthony Richard McBryan ,  Sebastiano Merlino ,  Sean Daniel Murphy ,  Alistair Francis Smith ,  David Neil Turner

IPC: G06Q30/02

Abstract: This disclosure describes systems, methods, and computer-readable media related to retargeting online advertisement campaign recommendations for advertisements with multiple items or services. Bids may be based on a combined advertisement creative comprising two or more items or services. Dynamically selecting multiple items at bid time using a retargeting model to determine a potential revenue generation amount associated with an event may increase the probability of a conversion event based on the creative that includes the selected items. In some embodiments, a machine-learned retargeting model may be used to select multiple items to be displayed in an advertisement. The retargeting model may be applied to items that were previously viewed by the consumer and may determine a value for each of the items using factors. A bid may be calculated for each of the selected items using the values determined by the retargeting model.

公开(公告)号：US10157404B1

公开(公告)日：2018-12-18

申请号：US14669953

申请日：2015-03-26

Applicant: Amazon Technologies, Inc.

Inventor： Andrew J. Bradley ,  Sebastiano Merlino ,  David Neil Turner ,  Alistair Francis Smith

IPC: G06Q30/02

Abstract: This disclosure describes systems, methods, and computer-readable media related to online advertisement campaign recommendations. A server may obtain data from an events datastore indicative of missing time slices from a partition of events data. The server may obtain first events data for the missing time slices. The server may identify redundant events data in the first events data that is redundant to second events data stored in the events datastore. The server may delete the redundant events data from the first events data to generate a modified first events data. The server may transmit the modified first events data to the events datastore.

公开(公告)号：US09894423B1

公开(公告)日：2018-02-13

申请号：US14220965

申请日：2014-03-20

Applicant: Amazon Technologies, Inc.

Inventor： Simon Lloyd Spencer ,  Brian Fergus Burns ,  Reginald Jassal ,  Martin Christopher Hare Robertson ,  Alistair Francis Smith ,  David Neil Turner ,  Guy Adam Taylor

IPC: H04N21/81 ,  H04N21/234 ,  H04N21/431 ,  H04N21/258 ,  G06Q30/02 ,  H04N21/458

CPC classification number: H04N21/812 ,  G06Q30/0251 ,  G06Q30/0276 ,  H04N21/23424 ,  H04N21/258 ,  H04N21/25808 ,  H04N21/25866 ,  H04N21/4316 ,  H04N21/458

Abstract: Systems and methods are disclosed for providing composite content, such as video content, by compositing. A template content may be received and may have one or more color blocks. One or more drop-in content sets may each have one or more drop-in content that correspond to the one or more colors of the template content color blocks. The one or more color blocks of the template content may be replaced with its corresponding drop-in content from one of the one or more drop-in content sets to generate a composite content. Furthermore, the composite content may have demographic, geographic, and/or behavioral parameters associated with it to enable targeting the composite content, such as in the form of advertisements and/or product or service recommendations, to one or more users.