公开(公告)号：US12131507B2

公开(公告)日：2024-10-29

申请号：US18191565

申请日：2023-03-28

申请人： Intel Corporation

发明人： Tomer Bar-On ,  Jacob Subag ,  Yaniv Fais ,  Jeremie Dreyfuss ,  Gal Novik ,  Gal Leibovich ,  Tomer Schwartz ,  Ehud Cohen ,  Lev Faivishevsky ,  Uzi Sarel ,  Amitai Armon ,  Yahav Shadmiy

IPC分类号： G06T9/00 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/048 ,  G06N3/084 ,  G06N3/088 ,  H04N19/42 ,  H04N19/436

CPC分类号： G06T9/002 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/048 ,  G06N3/084 ,  G06N3/088 ,  H04N19/42 ,  H04N19/436

摘要： In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

公开(公告)号：US12125277B1

公开(公告)日：2024-10-22

申请号：US17503180

申请日：2021-10-15

申请人： NVIDIA Corporation

发明人： Joonhwa Shin ,  Fangyu Li ,  Zheng Liu ,  Kaustubh Purandare

IPC分类号： G06V20/40 ,  G06F18/28 ,  G06N3/044 ,  G06N3/08 ,  G06T7/20 ,  G06T7/70 ,  G06V10/22 ,  G06V10/25 ,  G06V10/94

CPC分类号： G06V20/41 ,  G06F18/28 ,  G06N3/044 ,  G06N3/08 ,  G06T7/20 ,  G06T7/70 ,  G06V10/225 ,  G06V10/25 ,  G06V10/95 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30232 ,  G06T2207/30241 ,  G06T2207/30248 ,  G06V2201/07

摘要： Apparatuses, systems, and techniques for real-time persistent object tracking for intelligent video analytics systems. A state of a first object included in an environment may be tracked based on a first set of images depicting the environment. The first set of images may be generated during a first time period. It may be determined that the first object is not detected in the environment depicted in a second set of images. The second set of images may be generated during a second time period that is subsequent to the first time period. One or more predicted future states of the first object may be obtained in view of the state of the first object in the environment depicted in the first set of images. A second object may be detected in the environment depicted in a third set of images generated during a third time period that is subsequent to the second time period. A determination may be made as to whether a current state of the second object corresponds to at least one of the one or more predicted future states of the first object. In response to a determination that a current state of the second object corresponds to at least one of the predicted future states of the first object, an identifier associated with the second object is updated to correspond to an identifier associated with the first object.

公开(公告)号：US12124800B2

公开(公告)日：2024-10-22

申请号：US17857771

申请日：2022-07-05

申请人： Robert Bosch GmbH

发明人： Bingqing Wang ,  Ishan Dindorkar ,  Lars Franke ,  Zhe Feng

IPC分类号： G06F40/20 ,  G06F18/2137 ,  G06F18/22 ,  G06F40/14 ,  G06F40/279 ,  G06N3/044 ,  G06N3/045

CPC分类号： G06F40/279 ,  G06F18/21375 ,  G06F18/22 ,  G06F40/14 ,  G06N3/044 ,  G06N3/045

摘要： Disclosed are systems and methods for a computerized framework that provides a document structure parsing system for requirement engineering documents, where the logical structure of the text is not available, and is to be rebuilt based on the raw textual content. The framework approaches the build of the logical structure according to two phases. The first phase involves creating a list of list of text snippets from the raw text, where sequence labeling is adopted to re-segment and merge initially segmented text snippets. The second phase involves the framework executing computerized techniques including embedding adaptation approach, a hierarchy structure rebuilt algorithm, and a requirement text selection strategy to rebuild the hierarchy structure.

公开(公告)号：US20240346247A1

公开(公告)日：2024-10-17

申请号：US18301105

申请日：2023-04-14

申请人： VIAVI Solutions Inc.

发明人： Sayed TAHERI ,  Faris MUHAMMAD ,  Hamed AL-RAWESHIDY

IPC分类号： G06F40/284 ,  G06F40/205 ,  G06F40/242 ,  G06N3/044 ,  G06N3/08

CPC分类号： G06F40/284 ,  G06F40/205 ,  G06F40/242 ,  G06N3/044 ,  G06N3/08

摘要： In some implementations, a device may receive training data associated with a set of training command logs and a set of training log masks. The device may generate at least one artificial intelligence model for communications system testing. The device may receive a command log, the command log associated with a first log mask. The device may execute the at least one artificial intelligence model to identify a second log mask for a second set of tests. The device may output information associated with the second log mask for the second set of tests.

公开(公告)号：US20240345566A1

公开(公告)日：2024-10-17

申请号：US18626984

申请日：2024-04-04

申请人： R4N63R Capital LLC

发明人： Prasad Narasimha AKELLA ,  Ananya Honnedevasthana ASHOK ,  Zakaria Ibrahim ASSOUL ,  Krishnendu CHAUDHURY ,  Sameer GUPTA ,  Sujay Venkata Krishna NARUMANCHI ,  David Scott PRAGER ,  Devashish SHANKAR ,  Ananth UGGIRALA ,  Yash Raj CHHABRA

IPC分类号： G05B19/418 ,  B25J9/16 ,  G01M99/00 ,  G05B19/423 ,  G05B23/02 ,  G06F9/448 ,  G06F9/48 ,  G06F11/07 ,  G06F11/34 ,  G06F16/22 ,  G06F16/23 ,  G06F16/2455 ,  G06F16/901 ,  G06F16/9035 ,  G06F16/904 ,  G06F18/21 ,  G06F30/20 ,  G06F30/23 ,  G06F30/27 ,  G06F111/10 ,  G06F111/20 ,  G06N3/006 ,  G06N3/008 ,  G06N3/04 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06N7/01 ,  G06N20/00 ,  G06Q10/06 ,  G06Q10/0631 ,  G06Q10/0639 ,  G06Q10/083 ,  G06Q50/26 ,  G06T19/00 ,  G06V10/25 ,  G06V10/44 ,  G06V10/82 ,  G06V20/52 ,  G06V40/20 ,  G09B19/00 ,  G16H10/60

CPC分类号： G05B19/4183 ,  G05B19/41835 ,  G06F9/4498 ,  G06F9/4881 ,  G06F11/0721 ,  G06F11/079 ,  G06F11/3452 ,  G06F16/2228 ,  G06F16/2365 ,  G06F16/24568 ,  G06F16/9024 ,  G06F16/9035 ,  G06F16/904 ,  G06F30/20 ,  G06F30/23 ,  G06F30/27 ,  G06N3/008 ,  G06N3/04 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084 ,  G06N7/01 ,  G06N20/00 ,  G06Q10/06 ,  G06Q10/063112 ,  G06Q10/06316 ,  G06Q10/06393 ,  G06Q10/06395 ,  G06Q10/06398 ,  G06T19/006 ,  G06V10/25 ,  G06V10/454 ,  G06V10/82 ,  G06V20/52 ,  G06V40/20 ,  G09B19/00 ,  B25J9/1664 ,  B25J9/1697 ,  G01M99/005 ,  G05B19/41865 ,  G05B19/423 ,  G05B23/0224 ,  G05B2219/32056 ,  G05B2219/36442 ,  G06F18/217 ,  G06F2111/10 ,  G06F2111/20 ,  G06N3/006 ,  G06Q10/083 ,  G06Q50/26 ,  G16H10/60

摘要： The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for automatic creation of certificates for each instance of a subject product or service. The certificate can string together snippets of the sensor streams along with indicators of cycles, processes, action, sequences, objects, parameters and the like captured in the sensor streams.

公开(公告)号：US20240335725A1

公开(公告)日：2024-10-10

申请号：US18500299

申请日：2023-11-02

申请人： Ballogy, Inc.

发明人： Todd Young ,  Syed Saad Hussain

IPC分类号： A63B71/06 ,  G06N3/044 ,  G06N3/08 ,  G06T7/73 ,  G06T7/90

CPC分类号： A63B71/0605 ,  G06N3/044 ,  G06N3/08 ,  G06T7/74 ,  G06T7/90 ,  A63B71/0622 ,  A63B2071/0694 ,  A63B2220/806 ,  A63B2243/0037 ,  G06T2207/10024

摘要： Example methods, apparatuses, and/or articles of manufacture are disclosed herein that may be utilized, in whole or in part, to facilitate and/or support one or more operations and/or techniques for computer vision and artificial intelligence applications, such as implemented, in whole or in part, for performance evaluation and/or skills development.

公开(公告)号：US12112266B2

公开(公告)日：2024-10-08

申请号：US17264356

申请日：2018-09-07

申请人： IUCF-HYU (INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY)

发明人： Joong Moo Byun ,  Dae Ung Yoon ,  Ji Ho Park

IPC分类号： G06N3/04 ,  G06N3/044 ,  G06N3/08

CPC分类号： G06N3/08 ,  G06N3/044

摘要： Provided is a method of processing elastic wave data, the method including selecting some elastic wave traces as a first label from among a plurality of elastic wave traces received without at least some elastic wave traces missing from whole elastic wave data, training an interpolation model on a machine learning basis by using at least two or more of remaining elastic wave traces except for the first label and the first label, restoring the at least some elastic wave traces missing from the whole elastic wave data by using the trained interpolation model, training an extrapolation model on a machine learning basis by using an elastic wave trace selected as a second label from among a plurality of elastic wave traces included in whole restored elastic wave data and at least two or more of remaining elastic wave traces except for the second label, and generating an additional elastic wave trace, which have not been included in the whole elastic wave data, by using the trained extrapolation model.

公开(公告)号：US12111492B2

公开(公告)日：2024-10-08

申请号：US16589603

申请日：2019-10-01

申请人： Toyota Motor Engineering & Manufacturing North America, Inc.

发明人： Sean P. Rodrigues ,  Paul Donald Schmalenberg ,  Hideo Iizuka ,  Jae Seung Lee ,  Ercan Mehmet Dede

IPC分类号： G06N3/044 ,  G02B6/12 ,  G06F18/24 ,  G06N3/04 ,  G06N3/048 ,  G06N3/067 ,  G06V10/82

CPC分类号： G02B6/12004 ,  G06F18/24 ,  G06N3/04 ,  G06N3/067 ,  G06V10/82

摘要： Embodiments described herein relate to an adaptable photonic apparatus including an optical neural network. The photonic apparatus includes an optical input that provides an optical signal. The photonic apparatus also includes a chassis component and an optical neural network (ONN). The chassis component includes at least one modular mounting location for receiving a modular network component. The ONN is operably connected with the optical input and is configured to perform optical processing on the optical signal according to a deep learning algorithm. The ONN includes optical components arranged into layers to form the ONN. The modular network component is an additional optical processing component that is configured to function in cooperation with the ONN to adapt the deep learning algorithm.

公开(公告)号：US12110042B1

公开(公告)日：2024-10-08

申请号：US17501480

申请日：2021-10-14

申请人： Aurora Operations, Inc.

发明人： Anh Tuan Hoang ,  Harshayu Girase ,  Sai Bhargav Yalamanchi ,  Micol Marchetti-Bowick

IPC分类号： B60W60/00 ,  B60W40/04 ,  B60W50/00 ,  B60W50/06 ,  G06N3/044 ,  G06N3/045

CPC分类号： B60W60/00274 ,  B60W40/04 ,  B60W50/0097 ,  B60W50/06 ,  B60W60/0011 ,  G06N3/044 ,  G06N3/045 ,  B60W2554/4041 ,  B60W2554/4044

摘要： Example aspects of the present disclosure describe the generation of more realistic trajectories for a moving actor with a hybrid technique using an algorithmic trajectory shaper in a machine-learned trajectory prediction pipeline. In this manner, for example, systems and methods of the present disclosure leverage the predictive power of machine-learning approaches combined with a priori knowledge about physically realistic trajectories for a given actor as encoded in an algorithmic approach.

公开(公告)号：US20240330678A1

公开(公告)日：2024-10-03

申请号：US18192746

申请日：2023-03-30

申请人： Truist Bank

发明人： Seshadri Chintalapati ,  Joseph Matthew Law ,  Josephine Middleton-Saulny ,  Chris McClennen ,  Phani Kumar Ankani ,  Michael Anthony Springs

IPC分类号： G06N3/08 ,  G06F21/62 ,  G06N3/044 ,  G06N3/0464

CPC分类号： G06N3/08 ,  G06F21/6245 ,  G06N3/044 ,  G06N3/0464

摘要： A data privacy management system and method that utilize machine learning are provided. The method includes providing at least one processor, at least one memory device including readable instructions, and at least one user device in communication with the at least one processor via a network connection. The at least one processor, upon execution of the computer-readable instructions, is configured to generate a predictive model during training of a machine learning program using a training data set including a personal data set of one or more users. The predictive model is configured to predict at least one predicted data privacy measure of at least one of the users. At least one actual data privacy measure is then initiated based upon the at least one predicted data privacy measure to provide enhanced data privacy protection and control to the user.