专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2013049654A1 UTILIZING RELATIONSHIPS BETWEEN PLACES OF RELEVANCE 审中-公开
标题翻译：利用相关位置之间的关系
公开(公告)号：WO2013049654A1
公开(公告)日：2013-04-04
申请号：PCT/US2012/058035
申请日：2012-09-28
申请人： QUALCOMM INCORPORATED , KUHN, Lukas Daniel , LEE, Jin Won , NARAYANAN, Vidya
发明人： KUHN, Lukas Daniel , LEE, Jin Won , NARAYANAN, Vidya
IPC分类号： H04W4/04
CPC分类号： H04W4/043 , H04W4/029
摘要： Methods, systems, computer-readable media, and apparatuses for utilizing relationships between places of relevance are presented. In some embodiments, a mobile computing device may obtain information indicative of a micro-place of relevance visited by the mobile device at a first time. The information may be based on measurements taken by the mobile device at the first time. Further, the mobile device may derive an attribute of the visit to the micro-place of relevance based on the obtained information and a place model that associates micro-places of relevance with macro-places of relevance.
摘要翻译：介绍了利用相关位置之间关系的方法，系统，计算机可读介质和装置。在一些实施例中，移动计算设备可以在第一时间获得指示由移动设备访问的相关性微点的信息。该信息可以基于第一次由移动设备进行的测量。此外，移动设备可以基于所获得的信息和将相关性的微观位置与相关性的宏观位置相关联的地点模型来导出对相关微观地点的访问的属性。

2. 发明申请

WO2013049360A1 DISCOVERING AND AUTOMATICALLY SIZING A PLACE OF RELEVANCE 审中-公开
标题翻译：发现和自动设置相关位置
公开(公告)号：WO2013049360A1
公开(公告)日：2013-04-04
申请号：PCT/US2012/057579
申请日：2012-09-27
申请人： QUALCOMM INCORPORATED , NARAYANAN, Vidya , LUKOWICZ, Pawel , KUHN, Lukas, D. , LEE, Jin Won , NANDA, Sanjiv
发明人： NARAYANAN, Vidya , LUKOWICZ, Pawel , KUHN, Lukas, D. , LEE, Jin Won , NANDA, Sanjiv
IPC分类号： H04W4/02 , H04W64/00
CPC分类号： H04W4/021 , G06F17/30241 , G06F17/30598 , H04W4/023 , H04W4/043 , H04W4/21 , H04W64/00 , Y10S707/921
摘要： One or more mobile devices make measurements while moving along a path. Each measurement may comprise a specific group of identifiers of wireless transmitters, and strengths of corresponding wireless signals. A set of measurements are made in a sequence along a path, and the subsets of the measurements are identified for satisfying a test on a value of a measure of similarity of measurements included in the subset. A new place of relevance is identified, by comparing the just-described subsets of the measurements with similar subsets of additional measurements (e.g. by clustering). Alternatively, a known place of relevance (e.g. having a label) is identified, by comparing the just-described subsets of the measurements with pre-computed model of measurements. Also, the just-described subsets of the measurements may be compared with corresponding subsets of measurements of another path, e.g. to identify common portions therein.
摘要翻译：一个或多个移动设备在沿着路径移动时进行测量。每个测量可以包括无线发射机的特定组标识符和相应无线信号的强度。在沿着路径的序列中进行一组测量，并且识别测量的子集，以满足对包括在子集中的测量的相似度的测量值的测试。通过将刚刚描述的测量子集与附加测量的类似子集（例如通过聚类）进行比较来识别新的相关地点。或者，通过将刚刚描述的测量的子集与预先计算的测量模型进行比较来识别已知的相关位置（例如，具有标签）。此外，可以将刚刚描述的测量的子集与另一路径的测量的相应子集进行比较，例如。以识别其中的公共部分。

3. 发明申请

WO2022174207A1 PRUNING FOR EFFICIENT TRAINING OF MACHINE LEARNING MODELS 审中-公开
公开(公告)号：WO2022174207A1
公开(公告)日：2022-08-18
申请号：PCT/US2022/070241
申请日：2022-01-18
申请人： QUALCOMM INCORPORATED
发明人： BHALGAT, Yash Sanjay , LEE, Jin Won , LIN, Jamie Menjay , PORIKLI, Fatih Murat , PATEL, Chirag Sureshbhai
IPC分类号： G06N3/08
摘要： Certain aspects of the present disclosure provide techniques for improved machine learning using gradient pruning, comprising computing, using a first batch of training data, a first gradient tensor comprising a gradient for each parameter of a parameter tensor for a machine learning model; identifying a first subset of gradients in the first gradient tensor based on a first gradient criteria; and updating a first subset of parameters in the parameter tensor based on the first subset of gradients in the first gradient tensor.

4. 发明申请

WO2021072338A1 LEARNED THRESHOLD PRUNING FOR DEEP NEURAL NETWORKS 审中-公开
公开(公告)号：WO2021072338A1
公开(公告)日：2021-04-15
申请号：PCT/US2020/055167
申请日：2020-10-10
申请人： QUALCOMM INCORPORATED
发明人： AZARIAN YAZDI, Kambiz , BLANKEVOORT, Tijmen Pieter Frederik , LEE, Jin Won , BHALGAT, Yash Sanjay
IPC分类号： G06N3/08 , G06N3/04 , G06N3/063
摘要： A method for pruning weights of an artificial neural network based on a learned threshold includes determining a pruning threshold for pruning a first set of pre-trained weights of multiple pre-trained weights based on a function of a classification loss and a regularization loss. The first set of pre-trained weights is pruned in response to a first value of each pre-trained weight in the first set of pre-trained weights being greater than the pruning threshold. A second set of pre-trained weights of the multiple pre-trained weights is fine-tuned or adjusted in response to a second value of each pre-trained weight in the second set of pre-trained weights being greater than the pruning threshold.

5. 发明申请

WO2015164114A1 USING LINK METRICS AND MOTION STATE FOR EARLY WLAN - WWAN HANDOVER 审中-公开
标题翻译：使用LINK METRICS和MOTION STATE进行早期WLAN - WWAN切换
公开(公告)号：WO2015164114A1
公开(公告)日：2015-10-29
申请号：PCT/US2015/025559
申请日：2015-04-13
申请人： QUALCOMM INCORPORATED
发明人： HUA, Sha , LEE, Jin Won , MEYLAN, Arnaud
IPC分类号： H04W36/32 , H04W84/12 , H04W36/30
CPC分类号： H04W36/32 , H04W36/0083 , H04W84/12
摘要： Methods, systems, and devices are described for using information relating to a motion state of a mobile device to inform a handover decision of the mobile device. In one aspect, a method may include obtaining motion state information of the mobile device and, based on the motion state information, generating predictive information, for example relating to whether the mobile device is moving out of a network coverage area, such as a WLAN, to a WWAN or another WLAN. The mobile device may then participate in a handover based on the predictive information. In one aspect, the mobile device may participate in the handover prior to disconnection with a serving network and/or prior to a connection quality with the serving network falling below a connection quality threshold.
摘要翻译：描述了使用与移动设备的运动状态有关的信息来通知移动设备的切换决定的方法，系统和设备。在一个方面，一种方法可以包括获得移动设备的运动状态信息并且基于运动状态信息生成预测信息，例如与移动设备是否正在移出网络覆盖区域（例如WLAN）有关的预测信息，到WWAN或另一个WLAN。移动设备然后可以基于预测信息参与切换。在一个方面，移动设备可以在与服务网络断开之前和/或在与服务网络的连接质量低于连接质量阈值之前参与切换。

6. 发明申请

WO2014150977A1 SYSTEMS AND METHODS FOR SHARING CONTEXT INFORMATION IN A NEIGHBOR AWARE NETWORK 审中-公开
标题翻译：用于在邻里网络中共享上下文信息的系统和方法
公开(公告)号：WO2014150977A1
公开(公告)日：2014-09-25
申请号：PCT/US2014/024695
申请日：2014-03-12
申请人： QUALCOMM INCORPORATED
发明人： SADASIVAM, Shankar , SWAMINATHAN, Ashwin , LEE, Jin Won , ABRAHAM, Santosh Paul , CHERIAN, George , DING, Li
IPC分类号： G01S5/02 , G09F19/00 , G08B13/196 , H04W4/00
CPC分类号： H04W72/0406 , G01S5/0072 , G01S5/0289 , H04L67/28 , H04W4/023 , H04W4/027 , H04W4/06 , H04W4/38 , H04W4/70 , H04W4/80 , H04W8/005
摘要： Systems and methods share context information on a neighbor aware network. A method for communicating data in a wireless communications network is disclosed. The method includes receiving, by a device, a first message from a station, decoding the message to determine service information, the service information identifying a service provided by the station, generating a second message, wherein the second message is generated to indicate the service provided by the station and service information of the device, and transmitting, by the device, the second message to a remote station.
摘要翻译：系统和方法在邻居感知网络上共享上下文信息。公开了一种在无线通信网络中传送数据的方法。所述方法包括：从设备接收来自站的第一消息，解码所述消息以确定服务信息，所述服务信息标识由所述站提供的服务，生成第二消息，其中生成所述第二消息以指示所述服务由设备提供的设备和服务信息，并且由设备将第二消息发送到远程站。

7. 发明申请

WO2022170085A1 SEMI-STRUCTURED LEARNED THRESHOLD PRUNING FOR DEEP NEURAL NETWORKS 审中-公开
公开(公告)号：WO2022170085A1
公开(公告)日：2022-08-11
申请号：PCT/US2022/015298
申请日：2022-02-04
申请人： QUALCOMM INCORPORATED
发明人： AZARIAN YAZDI, Kambiz , BLANKEVOORT, Tijmen Pieter Frederik , LEE, Jin Won , BHALGAT, Yash Sanjay
IPC分类号： G06N3/04 , G06N3/08
摘要： A method for pruning weights of an artificial neural network based on a learned threshold includes designating a group of pre-trained weights of an artificial neural network to be evaluated for pruning. The method also includes determining a norm of the group of pre-trained weights, and performing a process based on the norm to determine whether to prune the entire group of pre-trained weights.

8. 发明申请

WO2017031140A1 METHODS AND APPARATUSES FOR DETECTING MOTION DISORDER SYMPTOMS BASED ON SENSOR DATA 审中-公开
标题翻译：用于检测基于传感器数据的运动障碍症状的方法和装置
公开(公告)号：WO2017031140A1
公开(公告)日：2017-02-23
申请号：PCT/US2016/047238
申请日：2016-08-17
申请人： QUALCOMM INCORPORATED
发明人： LEE, Jin Won , WU, Xinzhou , AGHERA, Parixit Laljibhai , ATTAR, Rashid Ahmed Akbar
IPC分类号： A61B5/00 , A61B5/11 , G06F19/00
CPC分类号： A61B5/4082 , A61B5/0022 , A61B5/1118 , A61B5/1123 , A61B5/6824 , A61B5/6829 , A61B5/6898 , A61B5/7264 , A61B5/7275 , A61B5/7278 , A61B5/742 , A61B2562/0204 , A61B2562/0219 , A61B2562/0223 , G06F19/00 , G16H40/63 , G16H50/20 , G16H50/30
摘要： Disclosed are techniques for determining a severity of motion disorder symptoms by receiving sensor data from one or more sensors, determining that the sensor data represents one or more activities of daily life (ADLs) of a user, assigning one or more probabilities to the one or more determined ADLs, each probability of the one or more probabilities indicating a confidence level that the sensor data represents a corresponding ADL, and providing the sensor data and the one or more probabilities to a motion disorder symptom scoring module that generates one or more scores for the one or more determined ADLs based on the sensor data, each score of the one or more scores indicating the severity of the motion disorder symptoms for a corresponding ADL, and combines the one or more scores and the one or more probabilities to generate an aggregated severity score for the motion disorder symptoms.
摘要翻译：公开了通过从一个或多个传感器接收传感器数据来确定运动障碍症状的严重性的技术，确定传感器数据表示用户的一个或多个日常生活活动（ADL），将一个或多个概率分配给一个或多个更确定的ADL，所述一个或多个概率的每个概率指示所述传感器数据表示对应的ADL的置信水平，以及将所述传感器数据和所述一个或多个概率提供给运动障碍症状评分模块，所述运动障碍症状评分模块为所述一个或多个确定的ADL基于所述传感器数据，所述一个或多个评分的每个评分指示相应ADL的运动障碍症状的严重性，并且组合所述一个或多个分数与所述一个或多个概率以生成聚合运动障碍症状严重程度评分。

9. 发明申请

WO2013169794A3 CALENDAR MATCHING OF INFERRED CONTEXTS AND LABEL PROPAGATION 审中-公开
公开(公告)号：WO2013169794A3
公开(公告)日：2013-11-14
申请号：PCT/US2013/039969
申请日：2013-05-07
申请人： QUALCOMM INCORPORATED
发明人： DING, Li , NARAYANAN, Vidya , LEE, Jin Won
IPC分类号： H04L29/08 , G06Q10/00
摘要： Methods, systems, computer-readable media, and apparatuses for calendar matching of inferred contexts are described. In one potential embodiment, a mobile device may use context information to generate a calendar of inferred contexts. Label information from raw calendar data may be used to update an inferred context within a calendar of inferred contexts. Additionally, the label may be propagated to future contexts and entries in an inferred context calendar.

10. 发明申请

WO2016099832A1 SCAN CHANNEL REDUCTION TO IMPROVE WI-FI SYSTEM POWER 审中-公开
标题翻译：扫描通道减少以改善无线电系统的功率
公开(公告)号：WO2016099832A1
公开(公告)日：2016-06-23
申请号：PCT/US2015/062544
申请日：2015-11-24
申请人： QUALCOMM INCORPORATED
发明人： LEE, Jin Won , TEAGUE, Edward Harrison
IPC分类号： H04W36/00
CPC分类号： H04W48/20 , H04B17/26 , H04B17/318 , H04W36/0083 , H04W48/16
摘要： A system and method are disclosed that may selectively switch a station's association from a first AP to a second AP based, at least in part, on whether an indication of first RSSI values for the first AP is greater than an indication of second RSSI values for the second AP by more than a difference value. For some embodiments, the difference value may be dynamically adjusted based, at least in part, on the first RSSI values, on a connection history of the station, and/or on a user selection.
摘要翻译：公开了一种系统和方法，其可以至少部分地基于第一AP的第一RSSI值的指示是否大于第二RSSI值的指示来选择性地将站的关联从第一AP切换到第二AP，第二个AP超过差值。对于一些实施例，差值可以至少部分地基于第一RSSI值，在站的连接历史上和/或用户选择上进行动态调整。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式