WATCH-TIME CLUSTERING FOR VIDEO SEARCHES

    公开(公告)号:US20210368233A1

    公开(公告)日:2021-11-25

    申请号:US17396361

    申请日:2021-08-06

    Applicant: Google LLC

    Abstract: This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

    Watch-time clustering for video searches

    公开(公告)号:US11570512B2

    公开(公告)日:2023-01-31

    申请号:US17396361

    申请日:2021-08-06

    Applicant: Google LLC

    Abstract: This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

    Watch-time accumulation for video searches

    公开(公告)号:US11109097B2

    公开(公告)日:2021-08-31

    申请号:US16009697

    申请日:2018-06-15

    Applicant: Google LLC

    Abstract: This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

    Watch-Time Accumulation for Video Searches
    4.
    发明申请

    公开(公告)号:US20190020920A1

    公开(公告)日:2019-01-17

    申请号:US16009697

    申请日:2018-06-15

    Applicant: Google LLC

    Abstract: This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

    Watch-time clustering for improving video searches, selection and provision

    公开(公告)号:US10003847B2

    公开(公告)日:2018-06-19

    申请号:US15136558

    申请日:2016-04-22

    Applicant: Google LLC

    Abstract: This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

    Detecting digital content visibility

    公开(公告)号:US10152554B2

    公开(公告)日:2018-12-11

    申请号:US15050810

    申请日:2016-02-23

    Applicant: Google LLC

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying a set of digital content that are responsive to a search query; detecting an electronic tag within the set of digital content; automatically converting the electronic tag to a frame element; generating and transmitting to an user device a composite page that: is hosted at a different domain than at least some digital content; includes different digital content from the set of digital content; and initially hides presentation of the frame element in the composite page; receiving a request for additional content generated by the frame element that identifies one of the various digital content sources; embedding observation code into the additional content; and determining that the additional content was visually perceptible on a display of the user device based on an electronic message received from the intersection observer code executing at the user device.

Patent Agency Ranking