中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.025 seconds)

    DISTRIBUTED LABELING FOR SUPERVISED LEARNING
    1.
    发明申请
    DISTRIBUTED LABELING FOR SUPERVISED LEARNING 审中-公开

    公开(公告)号：WO2020068360A1

    公开(公告)日：2020-04-02

    申请号：PCT/US2019/048924

    申请日：2019-08-29

    Applicant: APPLE INC.

    Inventor： BHOWMICK, Abhishek ,  ROGERS, Ryan M. ,  VAISHAMPAYAN, Umesh S. ,  VYRROS, Andrew H.

    IPC: G06N3/04

    Abstract: Embodiments described herein provide a technique to crowdsource labeling of training data for a machine learning model while maintaining the privacy of the data provided by crowdsourcing participants. Client devices can be used to generate proposed labels for a unit of data to be used in a training dataset. One or more privacy mechanisms are used to protect user data when transmitting the data to a server. The server can aggregate the proposed labels and use the most frequently proposed labels for an element as the label for the element when generating training data for the machine learning model. The machine learning model is then trained using the crowdsourced labels to improve the accuracy of the model.

    METHOD AND DEVICES FOR MANAGING USER ACCOUNTS ACROSS MULTIPLE ELECTRONIC DEVICES
    2.
    发明申请
    METHOD AND DEVICES FOR MANAGING USER ACCOUNTS ACROSS MULTIPLE ELECTRONIC DEVICES 审中-公开
    用于管理多个电子设备的用户帐户的方法和设备

    公开(公告)号：WO2013184347A1

    公开(公告)日：2013-12-12

    申请号：PCT/US2013/042016

    申请日：2013-05-21

    Applicant: APPLE INC.

    Inventor： SANTAMARIA, Justin E. ,  WOOD, Justin M.N. ,  VYRROS, Andrew H.

    IPC: H04L29/06

    CPC classification number: G06F15/173 ,  H04L61/15 ,  H04L63/0823 ,  H04L63/102

    Abstract: The disclosed embodiments provide a system that manages access to a user account on electronic devices of a user. An identity service provides a device token for the electronic device and a set of handles associated with the user account to the electronic device (302). The identity service receives, from the electronic device, a handle registration containing selected handles from the set (304). The identity service transmits an identity certificate comprising an association between the selected handles and the electronic device to the electronic device (306). The identity certificate and the association are used to route data associated with the selected handles to and from the electronic device (308). Examples of handles are the user's e-mail addresses or telephone numbers whereby the electronic device is configured to receive communications for the user sent to selected ones of the user's communication addresses comprised in the user account.

    Abstract translation: 所公开的实施例提供了一种管理对用户的电子设备上的用户帐户的访问的系统。 身份服务为电子设备提供设备令牌以及与电子设备（302）的用户帐户相关联的一组句柄。 身份服务从电子设备接收包含来自该组的选择的句柄的句柄注册（304）。 身份服务将包括所选择的句柄和电子设备之间的关联的身份证件发送到电子设备（306）。 身份证书和关联用于将与所选择的句柄相关联的数据路由到和从电子设备（308）发送。 手柄的示例是用户的电子邮件地址或电话号码，由此电子设备被配置为接收发送给包括在用户帐户中的用户的通信地址中的选定的用户的用户的通信。

    PRIVATIZED MACHINE LEARNING USING GENERATIVE ADVERSARIAL NETWORKS
    3.
    发明公开
    PRIVATIZED MACHINE LEARNING USING GENERATIVE ADVERSARIAL NETWORKS 审中-公开

    公开(公告)号：EP3525388A3

    公开(公告)日：2019-11-27

    申请号：EP19153349.6

    申请日：2019-01-23

    Applicant: Apple Inc.

    Inventor： BHOWMICK, Abhishek ,  VYRROS, Andrew H. ,  ROGERS, Ryan M.

    IPC: H04L9/00 ,  G06N20/00

    Abstract: One embodiment provides for a mobile electronic device comprising a non-transitory machine-readable medium to store instructions, the instructions to cause the mobile electronic device to receive a set of labeled data from a server; receive a unit of data from the server, the unit of data of a same type of data as the set of labeled data; determine a proposed label for the unit of data via a machine learning model on the mobile electronic device, the machine learning model to determine the proposed label for the unit of data based on the set of labeled data from the server and a set of unlabeled data associated with the mobile electronic device; encode the proposed label via a privacy algorithm to generate a privatized encoding of the proposed label; and transmit the privatized encoding of the proposed label to the server.

    LEARNING NEW WORDS
    7.
    发明申请
    LEARNING NEW WORDS 审中-公开
    学习新词

    公开(公告)号：WO2017218292A1

    公开(公告)日：2017-12-21

    申请号：PCT/US2017/036576

    申请日：2017-06-08

    Applicant: APPLE INC.

    Inventor： THAKURTA, Abhradeep Guha ,  VYRROS, Andrew H. ,  VAISHAMPAYAN, Umesh S. ,  KAPOOR, Gaurav ,  FREUDIGER, Julien ,  SRIDHAR, Vivek Rangarajan ,  DAVIDSON, Doug

    IPC: G06F17/30

    Abstract: Systems and methods are disclosed for a server learning new words generated by user client devices in a crowdsourced manner while maintaining local differential privacy of client devices. A client device can determine that a word typed on the client device is a new word that is not contained in a dictionary or asset catalog on the client device. New words can be grouped in classifications such as entertainment, health, finance, etc. A differential privacy system on the client device can comprise a privacy budget for each classification of new words. If there is privacy budget available for the classification, then one or more new terms in a classification can be sent to new term learning server, and the privacy budget for the classification reduced. The privacy budget can be periodically replenished.

    Abstract translation: 公开了系统和方法，用于服务器以众包方式学习由用户客户端设备生成的新词，同时保持客户端设备的本地差分隐私。 客户端设备可以确定在客户端设备上键入的单词是不包含在客户端设备上的字典或资产目录中的新单词。 新词汇可以按照娱乐，健康，金融等分类进行分组。客户端设备上的差分隐私系统可以包含每个新词分类的隐私预算。 如果存在用于分类的隐私预算，则可以将分类中的一个或多个新术语发送到新术语学习服务器，并且降低分类的隐私预算。 隐私预算可以定期补充。

    METHOD AND DEVICES FOR MANAGING USER ACCOUNTS ACROSS MULTIPLE ELECTRONIC DEVICES
    8.
    发明公开
    METHOD AND DEVICES FOR MANAGING USER ACCOUNTS ACROSS MULTIPLE ELECTRONIC DEVICES 有权
    方法和系统，用于管理多个电子器件的用户帐户

    公开(公告)号：EP2859702A1

    公开(公告)日：2015-04-15

    申请号：EP13729530.9

    申请日：2013-05-21

    Applicant: Apple Inc.

    Inventor： SANTAMARIA, Justin E. ,  WOOD, Justin M.N. ,  VYRROS, Andrew H.

    IPC: H04L29/06

    CPC classification number: G06F15/173 ,  H04L61/15 ,  H04L63/0823 ,  H04L63/102

    Abstract: The disclosed embodiments provide a system that manages access to a user account on electronic devices of a user. An identity service provides a device token for the electronic device and a set of handles associated with the user account to the electronic device (302). The identity service receives, from the electronic device, a handle registration containing selected handles from the set (304). The identity service transmits an identity certificate comprising an association between the selected handles and the electronic device to the electronic device (306). The identity certificate and the association are used to route data associated with the selected handles to and from the electronic device (308). Examples of handles are the user's e-mail addresses or telephone numbers whereby the electronic device is configured to receive communications for the user sent to selected ones of the user's communication addresses comprised in the user account.

    Abstract translation: 盘游离缺失实施例提供一种系统确实管理从在电子设备访问的用户帐户。 该系统包括一个身份服务确实提供用于所述电子装置和一组与所述用户账户的电子设备相关联的句柄的设备令牌。 接着，身份服务接收来自电子装置，手柄登记含有一个或从所述组句柄句柄多种。 最后，身份服务发送身份证书，其包括所选择的手柄和所述电子设备到电子设备，worin身份证书和关联被用于与所选择的手柄和从电子设备相关联的路由数据之间的关联。

    PRIVATIZED MACHINE LEARNING USING GENERATIVE ADVERSARIAL NETWORKS
    9.
    发明公开
    PRIVATIZED MACHINE LEARNING USING GENERATIVE ADVERSARIAL NETWORKS 审中-公开

    公开(公告)号：EP3525388A2

    公开(公告)日：2019-08-14

    申请号：EP19153349.6

    申请日：2019-01-23

    Applicant: Apple Inc.

    Inventor： BHOWMICK, Abhishek ,  VYRROS, Andrew H. ,  ROGERS, Ryan M.

    IPC: H04L9/00 ,  G06N20/00

    Abstract: One embodiment provides for a mobile electronic device comprising a non-transitory machine-readable medium to store instructions, the instructions to cause the mobile electronic device to receive a set of labeled data from a server; receive a unit of data from the server, the unit of data of a same type of data as the set of labeled data; determine a proposed label for the unit of data via a machine learning model on the mobile electronic device, the machine learning model to determine the proposed label for the unit of data based on the set of labeled data from the server and a set of unlabeled data associated with the mobile electronic device; encode the proposed label via a privacy algorithm to generate a privatized encoding of the proposed label; and transmit the privatized encoding of the proposed label to the server.

Patent Agency Ranking