中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

52 records (took 0.022 seconds)

    EDGE DEVICES UTILIZING PERSONALIZED MACHINE LEARNING AND METHODS OF OPERATING THE SAME
    12.
    发明申请
    EDGE DEVICES UTILIZING PERSONALIZED MACHINE LEARNING AND METHODS OF OPERATING THE SAME 审中-公开

    公开(公告)号：US20190050683A1

    公开(公告)日：2019-02-14

    申请号：US16146860

    申请日：2018-09-28

    Applicant: Intel Corporation

    Inventor： Maruti Gupta Hyde ,  Florence Pon ,  Naissa Conde ,  Xue Yang ,  Wei Yee Koay

    IPC: G06K9/62 ,  G06N3/08 ,  G06F15/18 ,  G06F21/62

    Abstract: Edge devices utilizing personalized machine learning and methods of operating the same are disclosed. An example edge device includes a model accessor to access a first machine learning model from a cloud service provider. A local data interface is to collect local user data. A model trainer is to train the first machine learning model to create a second machine learning model using the local user data. A local permissions data store is to store permissions indicating constraints on the local user data with respect to sharing outside of the edge device. A permissions enforcer is to apply permissions to the local user data to create a sub-set of the local user data to be shared outside of the edge device. A transmitter is to provide the sub-set of the local user data to a public data repository.

    Using a generic classifier to train a personalized classifier for wearable devices
    14.
    发明授权
    Using a generic classifier to train a personalized classifier for wearable devices 有权
    使用通用分类器来训练可穿戴设备的个性化分类器

    公开(公告)号：US09563855B2

    公开(公告)日：2017-02-07

    申请号：US14318555

    申请日：2014-06-27

    Applicant: Intel Corporation

    Inventor： Xue Yang ,  Lakshman Krishnamurthy ,  Lama Nachman

    IPC: G06N99/00 ,  G06N5/04

    CPC classification number: G06N99/005 ,  G06F1/163 ,  G06N3/0454 ,  G06N3/08

    Abstract: Systems and methods may provide for using one or more generic classifiers to generate self-training data based on a first plurality of events associated with a device, and training a personal classifier based on the self-training data. Additionally, the one or more generic classifiers and the personal classifier may be used to generate validation data based on a second plurality of events associated with the device. In one example, the personal classifier is substituted for the one or more generic classifiers if the validation data indicates that the personal classifier satisfies a confidence condition relative to the one or more generic classifiers.

    Abstract translation: 系统和方法可以提供使用一个或多个通用分类器基于与设备相关联的第一多个事件来生成自训练数据，以及基于自训练数据训练个人分类器。 另外，一个或多个通用分类器和个人分类器可以用于基于与设备相关联的第二多个事件来生成验证数据。 在一个示例中，如果验证数据指示个人分类器相对于一个或多个通用分类器满足置信条件，则个人分类器被替换为一个或多个通用分类器。

    Gesture Recognition Mechanism
    15.
    发明申请
    Gesture Recognition Mechanism 审中-公开
    手势识别机制

    公开(公告)号：US20160283783A1

    公开(公告)日：2016-09-29

    申请号：US14671227

    申请日：2015-03-27

    Applicant: Intel Corporation

    Inventor： Xue Yang ,  Sridhar G. Sharma ,  Prasanna Singamsetty ,  Lakshman Krishnamurthy ,  Ke Ding

    IPC: G06K9/00 ,  G06K9/62

    CPC classification number: G06K9/00335 ,  G06F3/01 ,  G06K9/00342 ,  G06K9/6202 ,  G06K9/6267 ,  G06N3/0454

    Abstract: A method is described including storing reference vector data corresponding to user gestures at a plurality of neurons at pattern matching hardware, receiving real time signals from the sensor array and performing gesture recognition using the pattern matching hardware to compare incoming vector data corresponding to the real time signals with the reference vector data.

    Abstract translation: 描述了一种方法，其包括在模式匹配硬件处在多个神经元处存储与用户手势相对应的参考矢量数据，从传感器阵列接收实时信号，并使用模式匹配硬件来执行手势识别，以对比实时的输入矢量数据 信号与参考矢量数据。

    WI-FI SCAN SCHEDULING AND POWER ADAPTATION FOR LOW-POWER INDOOR LOCATION
    16.
    发明申请
    WI-FI SCAN SCHEDULING AND POWER ADAPTATION FOR LOW-POWER INDOOR LOCATION 审中-公开
    WI-FI扫描调度和低功耗室内位置的电源适配

    公开(公告)号：US20160219408A1

    公开(公告)日：2016-07-28

    申请号：US15026636

    申请日：2013-12-20

    Applicant: INTEL CORPORATION

    Inventor： Lei Yang ,  Hongtao Xu ,  Xue Yang

    IPC: H04W4/02 ,  H04W52/02

    CPC classification number: H04W4/023 ,  G01S5/0221 ,  G01S5/0252 ,  G01S5/14 ,  H04W24/00 ,  H04W52/0241 ,  H04W52/0245 ,  H04W52/0248 ,  H04W84/12 ,  Y02B70/30 ,  Y02D70/00 ,  Y02D70/142

    Abstract: Embodiments of a mobile station and method for Wi-Fi scan scheduling and power adaption for low-power indoor location are generally described herein. In some embodiments, the mobile station may identify channels, beacon timing and rough signal strength levels of nearby access points (APs) from at least one of a previous full-channel scan or a Wi-Fi fingerprint database and may configure receiver sensitivity based on the rough signal strength levels for receipt of subsequent beacons. The mobile station may wake-up from a low-power state to receive beacons for the nearby access points on the identified channels at times based on the identified beacon timing. The received signal strength indicators (RSSIs) levels of the received beacons may be used for location determination.

    Abstract translation: 本文通常描述用于低功率室内位置的用于Wi-Fi扫描调度和功率适配的移动台和方法的实施例。 在一些实施例中，移动台可以从先前的全频道扫描或Wi-Fi指纹数据库中的至少一个识别邻近接入点（AP）的信道，信标定时和粗略信号强度水平，并且可以基于 接收后续信标的粗糙信号强度水平。 基于所识别的信标定时，移动台可以从低功率状态唤醒以接收所识别信道上的附近接入点的信标。 所接收信标的接收信号强度指示（RSSI）电平可用于位置确定。

    Systems and methods for revisit location detection
    17.
    发明授权
    Systems and methods for revisit location detection 有权
    重新检测位置检测的系统和方法

    公开(公告)号：US09288633B2

    公开(公告)日：2016-03-15

    申请号：US14126096

    申请日：2013-06-28

    Applicant: INTEL CORPORATION

    Inventor： Xue Yang ,  Lei Yang ,  Aveek Purohit

    IPC: H04W4/04 ,  H04W64/00 ,  H04W4/02

    CPC classification number: H04W4/04 ,  G01S5/02 ,  G01S5/0252 ,  H04W4/02 ,  H04W4/029 ,  H04W64/00 ,  H04W64/006

    Abstract: A method of detecting a revisit position includes receiving at a computing system a plurality of position data points, each of the plurality of position data points including a signal scan measurement. The method farther includes calculating a first signal distance between a first signal scan measurement corresponding to a first position data point of the plurality of position data points and a second signal scan measurement corresponding to a second position data point of the plurality of position data points. The method further includes determining that the first signal distance is less than a first threshold, that the first signal distance is a local minimum for the first position data point, and the first signal distance is a local minimum for the second position data point. The method further includes, based on the determining, identifying the first and second position data points as revisit points.

    Abstract translation: 检测重访位置的方法包括在计算系统处接收多个位置数据点，所述多个位置数据点中的每一个包括信号扫描测量。 该方法还包括计算与多个位置数据点中的第一位置数据点相对应的第一信号扫描测量值和对应于多个位置数据点的第二位置数据点的第二信号扫描测量值之间的第一信号距离。 该方法还包括确定第一信号距离小于第一阈值，第一信号距离是第一位置数据点的局部最小值，第一信号距离是第二位置数据点的局部最小值。 该方法还包括：基于确定，将第一和第二位置数据点识别为重访点。

    Apparatus and methods to track sport implements
    19.
    发明授权
    Apparatus and methods to track sport implements 有权

    公开(公告)号：US11090539B2

    公开(公告)日：2021-08-17

    申请号：US16594756

    申请日：2019-10-07

    Applicant: Intel Corporation

    Inventor： Songnan Yang ,  Zhen Yao ,  Xue Yang ,  Stephanie Moyerman

    IPC: A63B24/00 ,  A63B63/00 ,  A63B71/06 ,  A63B102/24

    Abstract: Examples are disclosed to track sport implements and/or objects of interest. An example apparatus includes a first coil to generate a first magnetic field having a first vertical component with a zero magnitude along a first line of interest and a second coil partially overlapped with the first coil, where the second coil is to generate a second magnetic field. The example apparatus also includes a sensor to measure a magnitude of the first magnetic field in the first line of interest and a processor to determine an object of interest has crossed the first line of interest based on the magnitude of the first magnetic field measured by the sensor.

    BLOCKCHAIN-BASED DIGITAL DATA EXCHANGE
    20.
    发明申请
    BLOCKCHAIN-BASED DIGITAL DATA EXCHANGE 审中-公开

    公开(公告)号：US20190050854A1

    公开(公告)日：2019-02-14

    申请号：US16147012

    申请日：2018-09-28

    Applicant: Intel Corporation

    Inventor： Xue Yang ,  Florence Pon ,  Naissa Conde ,  Wei Yee Koay ,  Maruti Gupta Hyde

    IPC: G06Q20/38 ,  G06F17/30 ,  H04L9/08

    Abstract: Example blockchain-based digital data exchanges including example data publisher endpoint devices and example data subscriber endpoint systems are disclosed herein. Example data publisher endpoint devices disclosed herein include a datamart publisher client to transmit a message to a data exchange to publish availability of data to be accessed from data storage associated with the data publisher endpoint device, and in response to a request from a data subscriber endpoint system, initiate a transaction to provide the data subscriber endpoint system with access to the data. Disclosed example data publisher endpoint devices also include a blockchain client to publish a record of the transaction to a blockchain network when the transaction is validated by the datamart publisher client, the record to be included in a blockchain implemented by the blockchain network.

Patent Agency Ranking