公开(公告)号：US09462456B2

公开(公告)日：2016-10-04

申请号：US14547654

申请日：2014-11-19

Applicant: QUALCOMM Incorporated

Inventor： Isaac David Guedalia ,  Adam Schwartz ,  Sarah Glickfield

IPC: G10L15/04 ,  G06F17/27 ,  G06F17/21 ,  H04W8/20 ,  G06F17/18 ,  G06Q30/02

CPC classification number: H04W8/205 ,  G06F17/18 ,  G06Q30/02

Abstract: The disclosure relates to creating a time-sensitive grammar. A device receives a plurality of data points, identifies a plurality of time gaps associated with the plurality of data points, each of the plurality of time gaps representing a dwell time or a frequency of occurrence of a data point of the plurality of data points, generates a generic time factor representing a multiple of the plurality of time gaps, and combines the generic time factor with the plurality of data points to create a time-sensitive sequence of data points. The generic time factor may be inserted into the time-sensitive sequence a number of times representing the dwell time or the frequency of occurrence of a corresponding data point of the plurality of data points.

Abstract translation: 本公开涉及创建时间敏感语法。 设备接收多个数据点，识别与多个数据点相关联的多个时间间隔，多个时间间隔中的每一个表示多个数据点的数据点的驻留时间或出现频率， 产生表示多个时间间隔的倍数的通用时间因子，并将通用时间因子与多个数据点组合以创建数据点的时间敏感序列。 一般时间因子可以插入到时间敏感序列中，代表多个数据点的相应数据点的停留时间或出现频率的次数。

公开(公告)号：US10110674B2

公开(公告)日：2018-10-23

申请号：US14789005

申请日：2015-07-01

Applicant: QUALCOMM Incorporated

Inventor： Sarah Glickfield ,  Isaac David Guedalia ,  Adam Schwartz

IPC: G06F17/30 ,  H04L29/08 ,  G06F13/38

Abstract: Methods and apparatuses are disclosed for synchronizing data inputs generated at a plurality of frequencies by a plurality of data sources. A device receives a first set of data points from a first data source of the plurality of data sources generated at a first frequency of the plurality of frequencies, receives a second set of data points from a second data source of the plurality of data sources generated at a second frequency of the plurality of frequencies, selects a time window corresponding to a period of time during which at least a subset of the first set of data points and at least a subset of the second set of data points were generated, and generates a vector representing a first reduced form of the subset of the first set of data points and a second reduced form of the subset of the second set of data points.

公开(公告)号：US09949078B2

公开(公告)日：2018-04-17

申请号：US14822403

申请日：2015-08-10

Applicant: QUALCOMM Incorporated

Inventor： Adam Schwartz ,  Isaac David Guedalia ,  Sarah Glickfield

IPC: H04W4/02 ,  H04W4/00 ,  H04W4/04 ,  H04W52/28

CPC classification number: H04W4/023 ,  H04W4/029 ,  H04W4/043 ,  H04W4/33 ,  H04W4/50 ,  H04W52/283

Abstract: Systems and methods are disclosed for determining a context-dependent virtual distance based on stigmergic interference. The method may include obtaining environmental status information relating to an environment in proximity to a client device, calculating, based on the obtained environmental status information, the context-dependent virtual distance between the client device and a user of the client device, and controlling a user signaling pattern of the client device based on the calculated context-dependent virtual distance.

公开(公告)号：US10037374B2

公开(公告)日：2018-07-31

申请号：US14610345

申请日：2015-01-30

Applicant: QUALCOMM Incorporated

Inventor： Adam Schwartz ,  Isaac David Guedalia

IPC: G06F17/30

CPC classification number: G06F16/285 ,  G06F16/24568 ,  G06F16/288

Abstract: The disclosure relates to various distance metrics that may quantify semantic and syntactic relationships between devices. More particularly, a first grammar associated with a first device and a second grammar associated with a second device may each comprise a symbol sequence that re-expresses one or more sequenced data items and one or more rules that represent a repeated pattern in the symbol sequence. Accordingly, one or more distance metrics that quantify a similarity between the first grammar and the second grammar may be calculated according to a comparison between the rules in the first grammar and the rules in the second grammar such that a relationship between the first device and the second device can be determined according to the one or more distance metrics.

公开(公告)号：US09536072B2

公开(公告)日：2017-01-03

申请号：US14682838

申请日：2015-04-09

Applicant: QUALCOMM Incorporated

Inventor： Isaac David Guedalia ,  Adam Schwartz

IPC: G06F21/31 ,  G06F21/88 ,  G06N99/00 ,  G06N5/04

CPC classification number: G06F21/316 ,  G06F21/88 ,  G06N5/046 ,  G06N5/047 ,  G06N99/005

Abstract: The disclosure relates to machine-learning behavioral analysis to detect device theft and unauthorized device usage. In particular, during a training phase, an electronic device may generate a local user profile that represents observed user-specific behaviors according to a centroid sequence, wherein the local user profile may be classified into a baseline profile model that represents aggregate behaviors associated with various users over time. Accordingly, during an authentication phase, the electronic device may generate a current user profile model comprising a centroid sequence re-expressing user-specific behaviors observed over an authentication interval, wherein the current user profile model may be compared to plural baseline profile models to identify the baseline profile model closest to the current user profile model. As such, an operator change may be detected where the baseline profile model closest to the current user profile model differs from the baseline profile model in which the electronic device has membership.

Abstract translation: 本公开涉及机器学习行为分析以检测设备被盗和未授权的设备使用。 特别地，在训练阶段期间，电子设备可以生成表示根据质心序列的观察到的用户特定行为的本地用户简档，其中本地用户简档可以被分类为基线简档模型，其表示与各种关联的聚合行为 用户随着时间的流逝。 因此，在认证阶段期间，电子设备可以生成包括重新表达在认证间隔上观察到的用户特定行为的质心序列的当前用户简档模型，其中当前用户简档模型可以与多个基线简档模型进行比较以识别 最接近当前用户配置文件模型的基线配置文件模型。 因此，可以检测最接近当前用户简档模型的基线简档模型与电子设备具有成员资格的基线简档模型不同的操作员改变。