-
公开(公告)号：US09645998B1
公开(公告)日：2017-05-09
申请号：US15275357
申请日：2016-09-24
申请人： Apple Inc.
发明人： Abhradeep Guha Thakurta , Andrew H. Vyrros , Umesh S. Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , Doug Davidson
CPC分类号： G06F17/2765 , G06F17/16 , G06F17/2705 , G06F17/2735 , G06F17/277 , G06F17/30737 , G06N99/005
摘要： 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.
-
公开(公告)号：US09594741B1
公开(公告)日：2017-03-14
申请号：US15275356
申请日：2016-09-24
申请人： Apple Inc.
发明人： Abhradeep Guha Thakurta , Andrew H. Vyrros , Umesh S. Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , Doug Davidson
CPC分类号： G06F17/2765 , G06F17/16 , G06F17/2705 , G06F17/2735 , G06F17/277 , G06F17/30737 , G06N99/005
摘要： 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.
摘要翻译： 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异隐私。 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。 新词可以分类为娱乐，健康，财务等分类。客户端设备上的差异隐私系统可以包括每个新词分类的隐私预算。 如果有可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，并且减少分类的隐私预算。 隐私预算可以定期补充。
-
公开(公告)号：US20190097978A1
公开(公告)日：2019-03-28
申请号：US16159473
申请日：2018-10-12
申请人： Apple Inc.
发明人： Abhradeep Guha Thakurta , Andrew H. Vyrros , Umesh S. Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , Doug Davidson
摘要： 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.
-
公开(公告)号：US10701042B2
公开(公告)日：2020-06-30
申请号：US16159473
申请日：2018-10-12
申请人： Apple Inc.
发明人： Abhradeep Guha Thakurta , Andrew H. Vyrros , Umesh S. Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , Doug Davidson
IPC分类号： H04L29/06 , G06N20/00 , G06F16/36 , G06N3/12 , G06F40/205 , G06F40/242 , G06F40/279 , G06F40/284 , G06F17/16 , G06F16/35 , G06F7/58 , G06F9/30
摘要： 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.
-
公开(公告)号：US10133725B2
公开(公告)日：2018-11-20
申请号：US15477921
申请日：2017-04-03
申请人： Apple Inc.
发明人： Abhradeep Guha Thakurta , Andrew H. Vyrros , Umesh S. Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , Doug Davidson
摘要： 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.
-
公开(公告)号：US20180039619A1
公开(公告)日：2018-02-08
申请号：US15477921
申请日：2017-04-03
申请人： Apple Inc.
发明人： Abhradeep Guha Thakurta , Andrew H. Vyrros , Umesh S. Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , Doug Davidson
CPC分类号： G06F17/2765 , G06F17/16 , G06F17/2705 , G06F17/2735 , G06F17/277 , G06F17/30737 , G06N99/005
摘要： 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.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.018 秒)
