-
公开(公告)号:US20180268296A1
公开(公告)日:2018-09-20
申请号:US15984754
申请日:2018-05-21
发明人: Bo ZHENG , Zhibin LIU , Rijia LIU , Qian CHEN
CPC分类号: G06N3/082 , G06K9/6218 , G06K9/6256 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G06N5/003 , G06N7/005 , G06N20/10 , G06N20/20 , H04L41/12 , H04L41/145 , H04L41/16
摘要: A method and an apparatus to build a machine learning based network model are described. For example, processing circuitry of an information processing apparatus obtains a data processing procedure of a first network model and a reference dataset that is generated by the first network model in the data processing procedure. The data processing procedure includes a first data processing step. Further, the processing circuitry builds a first sub-network in a second network model of a neural network type. The second network model is the machine learning based network model to be built. The first sub-network performs the first data processing step. Then, the processing circuitry performs optimization training on the first sub-network by using the reference dataset.
-
公开(公告)号:US20180268258A1
公开(公告)日:2018-09-20
申请号:US15919435
申请日:2018-03-13
申请人: TUPL, Inc.
发明人: Pablo TAPIA , Xiang CHEN , Rafael GUERRERO
CPC分类号: G06K9/6257 , G06F8/34 , G06F9/453 , G06F15/76 , G06K9/6262 , G06N5/003 , G06N7/005 , G06N20/00 , G06N20/20 , G06Q10/06393
摘要: Techniques are described for using artificial intelligence (i.e., machine learning) to identify a system problem. Multiple machine learning stages, or models, are used to better categorize inputs and more quickly derive a reliable solution. Each subsequent model identifies a more specific category than a previous model, i.e., each successive model operates on a more granular level. The described techniques include staged machine learning models and user interface elements that are used to train a system and support an application development process. These techniques can be used to more easily create logic that is directed to solving a problem in a particular system.
-
公开(公告)号:US20180260793A1
公开(公告)日:2018-09-13
申请号:US15973343
申请日:2018-05-07
发明人: Kaigang Li , Ashwath Aithal , Siddhartha Dalal , Liangkai Zhang
CPC分类号: G06Q10/20 , G06N3/0454 , G06N3/08 , G06N3/084 , G06N5/003 , G06N7/005 , G06N20/20 , G06Q30/0283 , G06Q40/08 , G06T7/0004 , G06T7/001 , G06T7/33 , G06T19/20 , G06T2207/10024 , G06T2207/30136 , G06T2207/30252 , G06T2219/2008
摘要: A system and method are provided for automatically estimating a repair cost for a vehicle. A method includes: receiving, at a server computing device over an electronic network, one or more images of a damaged vehicle from a client computing device; performing image processing operations on each of the one or more images to detect external damage to a first set of parts of the vehicle; inferring internal damage to a second set of parts of the vehicle based on the detected external damage; and, calculating an estimated repair cost for the vehicle based on the detected external damage and inferred internal damage based on accessing a parts database that includes repair and labor costs for each part in the first and second sets of parts.
-
44.
公开(公告)号:US20180247256A1
公开(公告)日:2018-08-30
申请号:US15888131
申请日:2018-02-05
申请人: FANUC CORPORATION
发明人: Hiroshi TAKIGAWA
CPC分类号: G06Q10/087 , G06N3/006 , G06N5/045 , G06N7/005 , G06N20/00 , G06N20/20 , H01S3/0014 , H01S3/02 , H01S3/0407 , H01S3/10069 , H01S3/11 , H01S3/1305 , H01S3/1312 , H01S3/1317 , H01S3/23 , H01S3/2383
摘要: An inventory management system includes a plurality of apparatuses, an information management device connected to the apparatuses, and an information processor. The information processor calculates the sum of cumulative failure rates that is the sum value of the cumulative failure rates of all of designated components having the same specifications used in the apparatuses at a certain point in time, in consideration of an acceleration depending on a driving condition with respect to a standard cumulative failure rate of each type of the designated components having the same specifications used in the apparatuses under a standard driving condition, and calculates the appropriate inventory quantity of the designated components based on the calculated sum of the cumulative failure rates.
-
公开(公告)号:US20180247239A1
公开(公告)日:2018-08-30
申请号:US15696137
申请日:2017-09-05
发明人: Michael Horrell , Adam McElhinney
CPC分类号: G06Q10/0635 , G05B23/0213 , G06F17/5009 , G06N5/003 , G06N5/045 , G06N5/046 , G06N5/048 , G06N7/005 , G06N20/20 , G06Q10/067 , G06Q10/20
摘要: Disclosed herein are systems, devices, and methods related to the interaction between assets and remote analytics systems, which may involve an asset compressing time-series values captured for a given operating data variable by producing an approximated version of the time-series values that comprises a set of approximation function-base region pairs.
-
公开(公告)号:US20180247222A1
公开(公告)日:2018-08-30
申请号:US15444912
申请日:2017-02-28
申请人: Oath Inc.
摘要: Briefly, example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate and/or support one or more operations and/or techniques for changing a classification of a landing page, such as via, for example, identifying features of the landing page, such as to predict a binary classification of the landing page as to post-click user experience. One or more adjustments to features of the landing page may be determined, such as using a machine learning approach, by way of non-limiting example.
-
公开(公告)号:US10061322B1
公开(公告)日:2018-08-28
申请号:US15480624
申请日:2017-04-06
CPC分类号: G06N3/04 , G06K9/00825 , G06K9/6273 , G06N3/0445 , G06N3/0454 , G06N3/08 , G06N3/084 , G06N5/003 , G06N7/005 , G06N20/10 , G06N20/20 , G06T11/60 , G06T2210/22
摘要: Systems and method are provided for controlling a vehicle. In one embodiment, a vehicle lighting detection method includes receiving sensor data associated with operation of one or more vehicles, and extracting from the sensor data a plurality of images and a plurality of corresponding image labels, wherein the images each include at least a portion of an observed vehicle, and the image labels indicate the corresponding lighting state of the observed vehicle in each of the images. The method further includes training, with a processor, a machine learning model utilizing the plurality of images and the plurality of corresponding image labels.
-
48.
公开(公告)号:US20180189128A1
公开(公告)日:2018-07-05
申请号:US15397627
申请日:2017-01-03
发明人: Mu Qiao , Ramani R. Routray , Quan Zhang
CPC分类号: G06F11/0751 , G06F11/0727 , G06F11/1448 , G06F11/1458 , G06F17/10 , G06F17/18 , G06F2212/1032 , G06K9/0053 , G06K9/0055 , G06K9/6247 , G06K9/6284 , G06K9/6292 , G06N7/00 , G06N7/005 , G06N20/20
摘要: One embodiment provides a method comprising receiving metadata comprising univariate time series data for each variable of a multivariate time series. The method comprises, for each variable of the multivariate time series, applying a hybrid and hierarchical model selection process to select an anomaly detection model suitable for the variable based on corresponding univariate time series data for the variable and covariations and interactions between the variable and at least one other variable of the multivariate time series, and detecting an anomaly on the variable utilizing the anomaly detection model selected for the variable. Based on each anomaly detection model selected for each variable of the multivariate time series, the method further comprises performing ensemble learning to determine whether the multivariate time series is anomalous at a particular time point.
-
公开(公告)号:US10003924B2
公开(公告)日:2018-06-19
申请号:US15674148
申请日:2017-08-10
申请人: YANDEX EUROPE AG
CPC分类号: H04W4/025 , G01C21/206 , G01C21/32 , G01S5/0036 , G01S5/0252 , G01S5/0263 , G06F16/00 , G06F16/245 , G06N3/0445 , G06N5/022 , G06N7/005 , G06N20/00 , G06N20/20 , H04W64/00
摘要: A method for generating an entity-vector associated with a geographical location is disclosed. The entity-vector is generated based on data from sensors of user-wireless-devices and user profile associated with user-wireless-devices. The method comprises, for a given location: receiving from user-wireless-devices being temporally-associated with the location, first and second sensed parameters from first and second sensors, the sensed parameters having been captured during the user-wireless-device being temporally-associated with the location; for each user-wireless-devices, retrieving an associated user profile and analyzing sensed parameters and user profile to generate, respectively, a given-user first and second parameter vectors and a given-user profile vector; aggregating, each user-wireless devices' (i) given-user first parameter vector, (ii) given-user second parameter vector, and (iii) the given-user profile vector into a pool; applying at least two analysis models to the pool, each analysis model generating its respective pooled-data vector; based on pooled-data vectors, generating an entity-vector associated with the location.
-
公开(公告)号:US20180150765A1
公开(公告)日:2018-05-31
申请号:US15363617
申请日:2016-11-29
摘要: A method of identifying location data in a data set comprises generating a data sample from the data set, training a plurality of models with the data sample to identify the location data in the data set, and applying the data set to the trained models to determine the location data within the data set. The plurality of models includes one or more first models to identify primary attributes of the location data indicating a geographical area and one or more second models to identify secondary attributes of the location data used to determine corresponding primary attributes.
-
-
-
-
-
-
-
-
-