-
公开(公告)号：US20190236505A1
公开(公告)日：2019-08-01
申请号：US16241322
申请日：2019-01-07
申请人： Magna Services, LLC
发明人： John MUIRHEAD-GOULD
CPC分类号： G06Q10/06315 , G06F16/24 , G06F16/248 , G06F16/285 , G06F16/288 , G06F16/9024 , G06F17/2765 , G06F17/277 , G06F17/2795 , G06F17/289 , G06K9/6297 , G06Q10/063112 , G06Q10/103 , Y04S50/00 , Y04S50/16
摘要： Resources are required to satisfy various needs and wants of people, businesses, and machines. Resources come in the forms of time, talents, money, materials, energy, services, people, knowledge, communication, and other tangible and intangible assets. When both the capacities and the needs of multiple resources are stored in a way that allows for them to be connected together using computers, they can be efficiently and effectively matched. This matching creates shared value, which has potential academic, economic, societal and philanthropic benefits. Connected computer system(s) can query and match resources together in a way that is mutually beneficial. While a common lexicon is the simplest way to perform the matching, natural language processing, machine translation, or use of similar technologies may be optimal. Any method of collecting these inputs should be able to handle one or multiple capacities, and one or multiple needs.
-
2.发明申请公开(公告)号：US20180219948A1
公开(公告)日：2018-08-02
申请号：US15859495
申请日：2017-12-30
申请人： Episys Science, Inc.
IPC分类号： H04L29/08 , G07C5/02 , H04W76/11 , G05D1/10 , G06K9/62 , H04W72/04 , H04W40/24 , H04W24/10 , H04W4/02 , H04W4/021 , G07C5/08 , H04W76/25 , G06K9/00 , G05D1/00 , H04W84/00 , H04W84/18
CPC分类号： H04L67/12 , G05D1/00 , G05D1/104 , G06K9/00664 , G06K9/6284 , G06K9/6296 , G06K9/6297 , G07C5/02 , G07C5/08 , H04W4/021 , H04W4/023 , H04W24/10 , H04W40/248 , H04W72/0406 , H04W76/11 , H04W76/25 , H04W84/005 , H04W84/18
摘要： Techniques for autonomously establishing, maintaining, and repairing of a wireless communication network among multiple autonomous mobile nodes (AMN) are provided. The multiple AMNs are flown towards a first node. A tentacle is established with the first node and extended to cover a second node over a distance, thereby establishing a wireless communication network between the first node and the second node via the multiple AMNs. Any damage to the established wireless communication network or tentacle may be autonomously detected and repaired by using spare AMNs. Further, the communication network may be used to enable autonomous detection, tracking of the second node, as well as autonomous detection of a contamination area, based on data received from one or more sensors onboard the AMNs deployed in the air.
-
公开(公告)号：US10008206B2
公开(公告)日：2018-06-26
申请号：US13551313
申请日：2012-07-17
申请人： Fang Chen , Bo Yin , Kim MacDonald
发明人： Fang Chen , Bo Yin , Kim MacDonald
IPC分类号： G10L15/00 , G10L17/00 , G10L21/00 , H04L9/00 , H04M3/00 , H04N7/00 , H04Q7/00 , G10L17/04 , G06K9/00 , G06F21/32 , G06K9/62
CPC分类号： G10L17/04 , G06F21/32 , G06K9/00892 , G06K9/6297
摘要： Verifying a user, such as, but not limited to, a user who answered questions for an unproctered test for employment. A representation of a transition pattern is stored (200). Time series voice data is received from a user responding to a sequence of questions (72) having multiple levels of difficulty. The transition pattern in the voice data (200) is based on a plurality of comparisons (503) of subsets (500) of the voice data corresponding to responses to questions having one or more different levels of difficulty. A further transition pattern (200) is determined from voice data in the same way but based on a shorter sequence of questions (78). The user is verified based on a comparison (78) of this further transition pattern to a previously stored transition pattern.
-
公开(公告)号：US09990050B2
公开(公告)日：2018-06-05
申请号：US15334269
申请日：2016-10-25
CPC分类号： G06F3/017 , G06K9/00355 , G06K9/6277 , G06K9/6297
摘要： The subject disclosure is directed towards a technology by which dynamic hand gestures are recognized by processing depth data, including in real-time. In an offline stage, a classifier is trained from feature values extracted from frames of depth data that are associated with intended hand gestures. In an online stage, a feature extractor extracts feature values from sensed depth data that corresponds to an unknown hand gesture. These feature values are input to the classifier as a feature vector to receive a recognition result of the unknown hand gesture. The technology may be used in real time, and may be robust to variations in lighting, hand orientation, and the user's gesturing speed and style.
-
公开(公告)号：US20180120826A1
公开(公告)日：2018-05-03
申请号：US15565019
申请日：2016-03-28
发明人： Eun-Hee RHIM
CPC分类号： G05B23/0254 , G05B2219/1196 , G05B2219/25428 , G05B2219/31211 , G05B2219/34012 , G06F11/22 , G06K9/6267 , G06K9/6297 , H04L12/2803 , H04L41/0622 , H04L41/0636 , H04L41/064 , H04L41/065 , H04L41/085 , H04L41/0866
摘要： Various examples of the present invention provide a server for providing information of an electronic device, and the server can comprise: a communication unit for receiving, from at least one first electronic device, at least one piece of information of the first electronic device; and a control unit for determining, from the received information, a current state among a plurality of states preset for the first electronic device, and controlling the first electronic device such that state prediction information of the first electronic device is transmitted to a second electronic device if the determined current state satisfies a preset notification condition on a state diagram in which a relationship among the plurality of states is set. Additionally, other examples could be possible besides the various examples of the present invention.
-
公开(公告)号：US20180005105A1
公开(公告)日：2018-01-04
申请号：US15615080
申请日：2017-06-06
CPC分类号： G06N3/0427 , A61F2/72 , G06F3/015 , G06K9/6297 , G06N3/063 , G06T7/277
摘要： A method of continuous decoding of motion for a direct neural interface. The method of decoding estimates a motion variable from an observation variable obtained by a time-frequency transformation of the neural signals. The observation variable is modelled using a HMM model whose hidden states include at least an active state and an idle state. The motion variable is estimated using a Markov mixture of experts where each expert is associated with a state of the model. For a sequence of observation vectors, the probability that the model is in a given state is estimated, and from this a weighting coefficient is deduced for the prediction generated by the expert associated with this state. The motion variable is then estimated by combination of the estimates of the different experts with these weighting coefficients.
-
公开(公告)号：US20170277981A1
公开(公告)日：2017-09-28
申请号：US15618384
申请日：2017-06-09
发明人： S. Kevin Zhou , Dorin Comaniciu , Bogdan Georgescu , Yefeng Zheng , David Liu , Daguang Xu
CPC分类号： G06K9/66 , G06K9/4609 , G06K9/4628 , G06K9/6297 , G06T7/0014 , G06T7/11 , G06T7/143 , G06T7/174 , G06T2207/10072 , G06T2207/10136 , G06T2207/20016 , G06T2207/20081 , G06T2207/30004 , G06T2207/30056 , G06T2207/30096
摘要： A method and apparatus for automatically performing medical image analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image of a patient is received. An output image that provides a result of a target medical image analysis task on the input medical image is automatically generated using a trained deep image-to-image network (DI2IN). The trained DI2IN uses a conditional random field (CRF) energy function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary and pairwise terms of the CRF energy function. The DI2IN may be trained on an image with multiple resolutions. The input image may be split into multiple parts and a separate DI2IN may be trained for each part. Furthermore, the multi-scale and multi-part schemes can be combined to train a multi-scale multi-part DI2IN.
-
公开(公告)号：US20170249524A1
公开(公告)日：2017-08-31
申请号：US15052941
申请日：2016-02-25
申请人： Xerox Corporation
发明人： Orhan Bulan , Palghat Ramesh , Vladimir Kozitsky
CPC分类号： G06K9/325 , G06K9/00771 , G06K9/3208 , G06K9/6265 , G06K9/6297 , G06K2209/01 , G06K2209/15
摘要： A detection-based segmentation-free method and system for license plate recognition. An image of a vehicle is initially captured utilizing an image-capturing unit. A license plate region is located in the image of the vehicle. A set of characters can then be detected in the license plate region and a geometry correction performed based on a location of the set of characters detected in the license plate region. An operation for sweeping an OCR across the license plate region can be performed to infer characters with respect to the set of characters and locations of the characters utilizing a hidden Markov model and leveraging anchored digit/character locations.
-
公开(公告)号：US20170220120A1
公开(公告)日：2017-08-03
申请号：US15110398
申请日：2015-01-07
IPC分类号： G06F3/01 , H04N21/4223 , H04N21/472 , H04N21/442 , G11B27/00 , G06K9/00
CPC分类号： G06F3/017 , G06K9/00355 , G06K9/6297 , G11B27/005 , H04N5/4403 , H04N21/4223 , H04N21/44218 , H04N21/47217
摘要： The playback of media by a playback device is controlled by input gestures. Each user gesture can be first broken down into a base gesture which indicates a specific playback mode. The gesture is then broken down into a second part which contains a modifier command which determines the speed for the playback mode determined from the base command. Media content is then played using the specified playback mode at a speed determined by the modifier command.
-
公开(公告)号：US20170200067A1
公开(公告)日：2017-07-13
申请号：US15382414
申请日：2016-12-16
发明人： S. Kevin Zhou , Dorin Comaniciu , Bogdan Georgescu , Yefeng Zheng , David Liu , Daguang Xu
CPC分类号： G06K9/66 , G06K9/4609 , G06K9/4628 , G06K9/6297 , G06T7/0014 , G06T7/11 , G06T7/143 , G06T7/174 , G06T2207/10072 , G06T2207/10136 , G06T2207/20016 , G06T2207/20081 , G06T2207/30004 , G06T2207/30056 , G06T2207/30096
摘要： A method and apparatus for automatically performing medical image analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image of a patient is received. An output image that provides a result of a target medical image analysis task on the input medical image is automatically generated using a trained deep image-to-image network (DI2IN). The trained DI2IN uses a conditional random field (CRF) energy function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary and pairwise terms of the CRF energy function. The DI2IN may be trained on an image with multiple resolutions. The input image may be split into multiple parts and a separate DI2IN may be trained for each part. Furthermore, the multi-scale and multi-part schemes can be combined to train a multi-scale multi-part DI2IN.
-
-
-
-
-
-
-
-
-
搜索结果
405 条记录 (耗时 0.035 秒)
