-
公开(公告)号：US11870563B2
公开(公告)日：2024-01-09
申请号：US18102680
申请日：2023-01-27
Applicant: Apple Inc.
Inventor： Yoav Feinmesser , Rafi Vitory , Ron Eyal , Eyal Waserman , Yunxing Ye
CPC classification number: H04L67/52 , G06N20/00 , H04L67/535 , H04W4/33 , H04W4/38
Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.
-
Patent Agency Ranking
公开(公告)号：US11601514B2
公开(公告)日：2023-03-07
申请号：US17496479
申请日：2021-10-07
Applicant: Apple Inc.
Inventor： Yoav Feinmesser , Rafi Vitory , Ron Eyal , Eyal Waserman , Yunxing Ye
Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point, but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.
-
公开(公告)号：US20240402211A1
公开(公告)日：2024-12-05
申请号：US18677583
申请日：2024-05-29
Applicant: Apple Inc.
Inventor： Jonathan R. Schoenberg , Yoav Feinmesser , Alexander Singh Alvarado , Evan G. Kriminger , Jonathan M. Beard , Hollie R. Figueroa , Eyal Waserman , Rafi Vitory , Ron Eyal , Yunxing Ye
Abstract: In some implementations, responsive to a trigger signal at an associated first time, a mobile device generating a first location value using a first ranging session with one or more other devices. The technique may include storing the first location value in a memory. The technique may include tracking, using a motion sensor of the mobile device, motion of the mobile device to determine a present location relative to the first location value. Further, the technique may include determining that a present location for the mobile device has changed by a predetermined threshold amount from the first location value since the associated first time. Responsive to the present location for the mobile device having changed by more than the predetermined threshold amount since the associated first time, the technique may include, generating a second location value using a second ranging session with the one or more other devices.
-
公开(公告)号：US20230397154A1
公开(公告)日：2023-12-07
申请号：US18096803
申请日：2023-01-13
Applicant: Apple Inc.
Inventor： Yagil Burowski , Robert W. Brumley , Charles W. Duyk , Ron Eyal , Yunxing Ye
IPC: H04W64/00 , G06F3/04817 , G06F3/0482
CPC classification number: H04W64/006 , G06F3/04817 , G06F3/0482
Abstract: In some implementations, the device may include conducting ranging with one or more playback devices to determine ranging information between the mobile device and each of the one or more playback devices, where the one or more playback devices are configured to play the streaming data when received from the mobile device, and where the ranging information provides at least one of a distance and an orientation between the mobile device and each of the one or more playback devices. In addition, the device may include detecting a selection of a media item. Also, the device may include identifying a particular playback device from the one or more playback devices for playing the selected media item based on the ranging information of the mobile device relative to each of the one or more playback devices.
-
公开(公告)号：US20220394101A1
公开(公告)日：2022-12-08
申请号：US17496479
申请日：2021-10-07
Applicant: Apple Inc.
Inventor： Yoav Feinmesser , Rafi Vitory , Ron Eyal , Eyal Waserman , Yunxing Ye
Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point, but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.
-
公开(公告)号：US20230179671A1
公开(公告)日：2023-06-08
申请号：US18102680
申请日：2023-01-27
Applicant: Apple Inc.
Inventor： Yoav Feinmesser , Rafi Vitory , Ron Eyal , Eyal Waserman , Yunxing Ye
CPC classification number: H04L67/52 , G06N20/00 , H04L67/535 , H04W4/33 , H04W4/38
Abstract: A semi-supervised machine learning model can provide for classifying an input data point as associated with a particular target location or a particular action. Each data point comprises one or more sensor values from one or more signals emitted by one or more signal sources located within a physical area. A tagged sample set and an untagged sample set are combined to train the machine learning model. Each tagged sample includes a respective data point and a label representing a respective location/action. Each untagged sample includes a data point but is unlabeled. Once trained, given a current data point, the machine learning model can classify the current data point as associated with a particular location/action, after which a target object (e.g., other device or application to be used) can be predicted.
-
-
-
-
-
Search Results
6
records
(took 0.015 seconds)
