公开(公告)号：US12118797B2

公开(公告)日：2024-10-15

申请号：US17457339

申请日：2021-12-02

申请人： Aptiv Technologies AG

发明人： Marco Braun ,  Moritz Luszek ,  Jan Siegemund

IPC分类号： G06V20/56 ,  B60W40/10 ,  G06F18/2415 ,  G06N3/02

CPC分类号： G06V20/56 ,  B60W40/10 ,  G06F18/24155 ,  G06N3/02 ,  B60W2420/403 ,  B60W2420/408

摘要： A method is provided for semantic segmentation of an environment of a vehicle. Via a processing device, a grid of cells is defined dividing the environment of the vehicle. A radar point cloud is received from a plurality of radar sensors, and at least one feature of the radar point cloud is assigned to each grid cell. By using a neural network including deterministic weights, high-level features are extracted for each grid cell. Several classes are defined for the grid cells. For layers of a Bayesian neural network, various sets of weights are determined probabilistically. Via the Bayesian neural network, confidence values are determined for each class and for each grid cell based on the high-level features and based on the various sets of weights in order to determine a predicted class and an extent of uncertainty for the predicted class for each grid cell.

公开(公告)号：US12056625B2

公开(公告)日：2024-08-06

申请号：US16983221

申请日：2020-08-03

申请人： Dell Products L.P.

发明人： Parminder Singh Sethi ,  Suren Kumar

IPC分类号： G06N5/04 ,  G06F18/2415 ,  G06N7/01

CPC分类号： G06N7/01 ,  G06F18/24155 ,  G06N5/04 ,  G06F2213/0028

摘要： A method comprises collecting data from a computing environment comprising one or more storage devices, wherein the data comprises information identifying assignments of the one or more storage devices to one or more servers in the computing environment. In the method, the data is analyzed using one or more machine learning algorithms, wherein the analyzing comprises predicting whether a given configuration of the one or more storage devices in combination with the one or more servers is a specified configuration. The method also includes generating a storage configuration recommendation for a user based on the analysis, and transmitting the storage configuration recommendation to the user.

公开(公告)号：US11941999B2

公开(公告)日：2024-03-26

申请号：US16780574

申请日：2020-02-03

申请人： Instructure, Inc.

发明人： Jonathan Templin

IPC分类号： G09B7/02 ,  G06F18/2415 ,  G06N7/01 ,  G09B7/00 ,  G09B7/04

CPC分类号： G09B7/02 ,  G06F18/24155 ,  G06N7/01 ,  G09B7/00 ,  G09B7/04

摘要： Techniques, methods, systems, and devices for diagnostic assessment of a respondent are described. The techniques for diagnostic assessment may use a classification model to characterize multiple dimensions of the respondent. The classification model may characterize the respondent as having an attribute (e.g., unobserved variable) that is measured by one or more outcomes (e.g., observed variables). The outcomes may be based on responses received from the respondent to items on an assessment. The classification model may also characterize one or more item parameters associated with the items of the assessment.

公开(公告)号：US11940770B2

公开(公告)日：2024-03-26

申请号：US17372247

申请日：2021-07-09

申请人： Mapped Inc.

发明人： Shaun Cooley ,  Jose De Castro ,  Jason Koh

IPC分类号： G06F16/25 ,  G05B19/05 ,  G06F9/54 ,  G06F16/21 ,  G06F16/901 ,  G06F18/21 ,  G06F18/2415 ,  G06N20/00 ,  H04L41/12

CPC分类号： G05B19/054 ,  G05B19/05 ,  G06F9/54 ,  G06F16/212 ,  G06F16/254 ,  G06F16/9024 ,  G06F18/2178 ,  G06F18/24155 ,  G06N20/00 ,  H04L41/12 ,  G05B2219/1215 ,  G05B2219/13129 ,  G05B2219/15012 ,  G05B2219/163

摘要： Described are platforms, systems, and methods to automatically discover, extract, map, merge, and enrich data found in on-premises in automated industrial and commercial environments and cloud systems for purposes of providing developers access to normalized, merged, and enriched data through an API. The platforms, systems, and methods identify a plurality of data sources associated with an automation environment; retrieve data from at least one of the identified data sources; apply a first algorithm to map the retrieved data to a predetermined ontology; merge the mapped data into a data store comprising timeseries of the mapped data; apply a second algorithm to identify patterns in the merged data and enriching the data based on one or more identified patterns; and provide one or more APIs or one or more real-time streams to provide access to the enriched data.

公开(公告)号：US11919546B2

公开(公告)日：2024-03-05

申请号：US18176852

申请日：2023-03-01

申请人： FORD GLOBAL TECHNOLOGIES, LLC

发明人： Wulue Zhao ,  Kevin L. Wyffels ,  G. Peter K. Carr

IPC分类号： B60W60/00 ,  G06F17/16 ,  G06F18/2415 ,  G06T19/00 ,  G06V20/56 ,  G06V20/58

CPC分类号： B60W60/00272 ,  B60W60/001 ,  G06F17/16 ,  G06F18/24155 ,  G06T19/00 ,  G06V20/58 ,  G06V20/588 ,  B60W2420/52 ,  G06T2207/10028 ,  G06T2210/12

摘要： Systems and methods for operating a robotic system. The methods comprise: inferring, by a computing device, a first heading distribution for the object from a 3D point cloud; obtaining, by the computing device, a second heading distribution from a vector map; obtaining, by the computing device, a posterior distribution of a heading using the first and second heading distributions; defining, by the computing device, a cuboid on a 3D graph using the posterior distribution; and using the cuboid to facilitate driving-related operations of a robotic system.

公开(公告)号：US20240038514A1

公开(公告)日：2024-02-01

申请号：US18337183

申请日：2023-06-19

申请人： THERMO FINNIGAN LLC

发明人： Paul R. Gazis

IPC分类号： H01J49/00 ,  G01N30/86 ,  G06F18/2415

CPC分类号： H01J49/0036 ,  G01N30/8631 ,  G06F18/24155

摘要： Disclosed herein are charge state deconvolution systems, as well as related methods, computing devices, and computer-readable media. For example, in some embodiments, a charge state deconvolution apparatus includes first logic to identify peaks in a mass spectrum; second logic to deconvolve the masses of the identified peaks and identify clusters of deconvolved mases that have contiguous charge states; and third logic to calculate a Bayesian fitness measure and perform an iterative decremental procedure to perform charge state deconvolution.

公开(公告)号：US11882005B2

公开(公告)日：2024-01-23

申请号：US17652967

申请日：2022-03-01

申请人： Ribbon Communications Operating Company, Inc.

发明人： Charles W. Boyle ,  Surya Kumar Kovvali ,  Nizar K Purayil

IPC分类号： H04L41/16 ,  G06F16/907 ,  G06N3/08 ,  G06Q10/0639 ,  G06N5/04 ,  H04L41/5009 ,  H04L43/0817 ,  H04L43/0823 ,  H04W24/02 ,  H04W24/04 ,  H04W24/08 ,  H04W24/10 ,  H04L65/1073 ,  H04M3/51 ,  H04L41/0631 ,  H04L65/65 ,  H04L65/1104 ,  G06F18/23 ,  G06F18/214 ,  G06F18/2415

CPC分类号： H04L41/16 ,  G06F16/907 ,  G06F18/2148 ,  G06F18/23 ,  G06F18/24155 ,  G06N3/08 ,  G06N5/04 ,  G06Q10/06393 ,  H04L41/0631 ,  H04L41/5009 ,  H04L43/0817 ,  H04L43/0823 ,  H04L65/1073 ,  H04L65/1104 ,  H04L65/65 ,  H04M3/5175 ,  H04W24/02 ,  H04W24/04 ,  H04W24/08 ,  H04W24/10

摘要： A method includes: receiving protocol event data from a plurality of probes within the telecommunication system; determining a most probable cause of a call event from the protocol event data; applying the most probable cause to a trained machine learning algorithm that includes the most probable cause as its input and a telecommunication system score as its output; and in response to an output score from the trained machine learning algorithm, performing a corrective action for a plurality of network users that are expected to be affected by the most probable cause.

公开(公告)号：US20240004710A1

公开(公告)日：2024-01-04

申请号：US18469695

申请日：2023-09-19

申请人： HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

发明人： Lianjie Cao ,  Faraz Ahmed ,  Puneet Sharma

IPC分类号： G06F9/50 ,  G06F9/30 ,  G06N20/00 ,  G06F11/34 ,  G06F18/214 ,  G06F18/2415

CPC分类号： G06F9/5005 ,  G06F9/505 ,  G06F9/5011 ,  G06F18/24155 ,  G06N20/00 ,  G06F11/3409 ,  G06F18/214 ,  G06F9/3009

摘要： Systems and methods are provided for optimally allocating resources used to perform multiple tasks/jobs, e.g., machine learning training jobs. The possible resource configurations or candidates that can be used to perform such jobs are generated. A first batch of training jobs can be randomly selected and run using one of the possible resource configuration candidates. Subsequent batches of training jobs may be performed using other resource configuration candidates that have been selected using an optimization process, e.g., Bayesian optimization. Upon reaching a stopping criterion, the resource configuration resulting in a desired optimization metric, e.g., fastest job completion time can be selected and used to execute the remaining training jobs.

公开(公告)号：US11799728B2

公开(公告)日：2023-10-24

申请号：US17588447

申请日：2022-01-31

申请人： Splunk Inc.

发明人： George Apostolopoulos ,  Zhuxuan Jin

IPC分类号： H04L41/0893 ,  H04L41/14 ,  H04L9/40 ,  H04L41/082 ,  H04L43/02 ,  H04L43/04 ,  H04L41/22 ,  H04L67/303 ,  G06F18/2415

CPC分类号： H04L41/0893 ,  G06F18/24155 ,  H04L41/082 ,  H04L41/145 ,  H04L41/22 ,  H04L43/02 ,  H04L43/04 ,  H04L63/1425 ,  H04L67/303

摘要： One or more embodiments are directed multistage device clustering. A log including network traffic of multiple devices in a network is received. From the log, features of the devices are extracted and an aggregated feature matrix generated. A traffic behavior subset of the features in the aggregated feature matrix is selected, and a topic modeling algorithm applied thereto to obtain traffic behavior device groups. An application behavior subset of the features in the aggregated feature matrix is selected. On a per traffic behavior device group basis, the topic modeling algorithm is applied to the application behavior subset to obtain application behavior device subgroups. One or more devices are assigned to at least one of the plurality of application behavior device subgroups to obtain an assignment.

公开(公告)号：US11758350B2

公开(公告)日：2023-09-12

申请号：US17485212

申请日：2021-09-24

申请人： Apple Inc.

发明人： Aditya Sarathy ,  Xiaoyuan Tu ,  Suresh B. Malakar ,  Hui Lin

IPC分类号： H04S7/00 ,  G06F9/448 ,  G06F18/2415

CPC分类号： H04S7/304 ,  G06F9/4498 ,  G06F18/24155 ,  H04S2400/11

摘要： Embodiments are disclosed for user posture transition detection and classification using a linked biomechanical model. In an embodiment, a method comprises: obtaining motion data from a headset worn by a user; selecting features of a linked biomechanical model based on a current posture state; determining at least one probability that a posture transition occurred based on an output of a classifier, where the output of the classifier is based on the selected features and the motion data; determining a posture transition based on the at least one probability; and performing at least one action based on detection of the posture transition.