-
公开(公告)号:US11868414B1
公开(公告)日:2024-01-09
申请号:US16353604
申请日:2019-03-14
Applicant: Snap Inc.
Inventor: Pierre Leveau , Antoine Sinton
IPC: G06F16/9535 , G06N20/00 , G06N3/08 , G06F3/0484
CPC classification number: G06F16/9535 , G06N20/00 , G06F3/0484 , G06N3/08
Abstract: Methods, systems, and devices for generating contact suggestions for a user of a social network. A first score is computed for each one of the plurality of users, the first score being computed using an edge-weighted ranking algorithm based on the user graph. A second score is computed, using a machine learning model, for each user of the plurality of users, the second score of each user being, at least partially, based on the first score of said user, with the second score of each user being representative of a probability of a first user sending a connection request to said user. A ranked contact suggestion list of one or more users of the plurality of users is generated, the one or more users being ranked based on their respective second score.
-
公开(公告)号:US20230385347A1
公开(公告)日:2023-11-30
申请号:US18450110
申请日:2023-08-15
Applicant: Snap Inc.
Inventor: Pierre Leveau , Antoine Sinton
IPC: G06F16/9535 , G06N20/00
CPC classification number: G06F16/9535 , G06N20/00 , G06F3/0484
Abstract: Methods, systems, and devices for generating contact suggestions for a user of a social network. A first score is computed for each one of the plurality of users, the first score being computed using an edge-weighted ranking algorithm based on the user graph. A second score is computed, using a machine learning model, for each user of the plurality of users, the second score of each user being, at least partially, based on the first score of said user, with the second score of each user being representative of a probability of a first user sending a connection request to said user. A ranked contact suggestion list of one or more users of the plurality of users is generated, the one or more users being ranked based on their respective second score.
-
公开(公告)号:US20230341285A1
公开(公告)日:2023-10-26
申请号:US18347287
申请日:2023-07-05
Applicant: Snap Inc.
Inventor: Eric Guillaume , Antoine Sinton
IPC: G01L27/00 , G01L7/02 , G06F16/909 , H04W4/029 , G01C5/06
CPC classification number: G01L27/002 , G01L7/028 , G06F16/909 , H04W4/029 , G01C5/06
Abstract: Methods, systems, and devices for calibrating a barometer of a client device. A server computer accesses historical data including location data, and atmospheric pressure data collected from a plurality of client devices over a period of time. An equation system defined by the historical data is solved. The equation system has a plurality of unknown parameters, the plurality of unknown parameters comprising a barometer bias of a first client device among the plurality of client devices. The first client device is calibrated using the barometer bias.
-
公开(公告)号:US10936066B1
公开(公告)日:2021-03-02
申请号:US16274891
申请日:2019-02-13
Applicant: Snap Inc.
Inventor: Xabier Jaureguiberry , Alexy Lean , Antoine Martin , Antoine Sinton
IPC: G06F3/01 , G06F16/904 , G06F16/906
Abstract: Methods, systems, and devices for predicting a state of a user (e.g., asleep or awake). In some embodiments, the location sharing system accesses historical activity data of the user and extracts historical sleep records from the historical activity data. The system clusters the historical sleep records into a plurality of clusters and extracts a sleep pattern from each one of the plurality of clusters. Then, when the location sharing system receives current activity data of the user, the system can predict whether the user is currently asleep based on the current activity of the user and at least one of the sleep patterns. Some embodiments additionally compute an estimated wake up time of the user. Some embodiments share the predicted physiological state of the user with the user's friends via the map GUI. Some embodiments additionally share the estimated wake up time of the user.
-
公开(公告)号:US10725542B1
公开(公告)日:2020-07-28
申请号:US16274891
申请日:2019-02-13
Applicant: Snap Inc.
Inventor: Xabier Jaureguiberry , Alexy Lean , Antoine Martin , Antoine Sinton
IPC: G06F3/01 , G06F16/904 , G06F16/906
Abstract: Methods, systems, and devices for predicting a state of a user (e.g., asleep or awake). In some embodiments, the location sharing system accesses historical activity data of the user and extracts historical sleep records from the historical activity data. The system clusters the historical sleep records into a plurality of clusters and extracts a sleep pattern from each one of the plurality of clusters. Then, when the location sharing system receives current activity data of the user, the system can predict whether the user is currently asleep based on the current activity of the user and at least one of the sleep patterns. Some embodiments additionally compute an estimated wake up time of the user. Some embodiments share the predicted physiological state of the user with the user's friends via the map GUI. Some embodiments additionally share the estimated wake up time of the user.
-
-
-
-