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. 发明授权

US11443143B2 Unattended object detection using machine learning 有权
公开(公告)号：US11443143B2
公开(公告)日：2022-09-13
申请号：US16931098
申请日：2020-07-16
申请人： International Business Machines Corporation
发明人： Rong Yan , Shi Lei Zhang , Junsong Wang , Ke Wei Sun
IPC分类号： G06V10/22 , G06K9/62 , G06N3/08 , G06V10/44
摘要： Techniques for unattended object detection using machine learning are disclosed. A machine learning policy, for use in identifying unattended objects in a captured image depicting one or more objects, is generated. The generating includes determining a level of occlusion in the captured image relating to the objects, and determining the machine learning policy based on the determined level of occlusion. A machine learning model is selected, from among a plurality of pre-defined machine learning models, based on the generated machine learning policy. An unattended object is detected in the captured image using the selected machine learning model.

2. 发明申请

US20200184380A1 CREATING OPTIMIZED MACHINE-LEARNING MODELS 审中-公开
公开(公告)号：US20200184380A1
公开(公告)日：2020-06-11
申请号：US16216138
申请日：2018-12-11
申请人： International Business Machines Corporation
发明人： Gegi Thomas , Adelmo Cristiano Innocenza Malossi , Tejaswini Pedapati , Ganesh Venkataraman , Roxana Istrate , Martin Wistuba , Florian Michael Scheidegger , Chao Xue , Rong Yan , Horst Cornelius Samulowitz , Benjamin Herta , Debashish Saha , Hendrik Strobelt
IPC分类号： G06N20/20 , G06N3/08 , G06N3/04
摘要： A machine-learning model generation method, system, and computer program product deciding, via a first algorithm, a machine-learning algorithm that is best for customer data, invoking the machine-learning algorithm to train a neural network model with the customer data, analyzing the neural network model produced by the training for an accuracy, and improving the accuracy by iteratively repeating the training of the neural network model until a customer-defined constraint is met, as determined by the first algorithm.

3. 发明申请

US20200167639A1 AUTOMATIC MONITORING AND ADJUSTMENT OF MACHINE LEARNING MODEL TRAINING 审中-公开
公开(公告)号：US20200167639A1
公开(公告)日：2020-05-28
申请号：US16199823
申请日：2018-11-26
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Chao Xue , Rong Yan , Yonghua Lin , Yonggang Hu , Yu Song
IPC分类号： G06N3/08 , G06K9/62
摘要： Methods and systems for training a machine learning model include training a machine learning model using training data. A status of the machine learning model's training is determined based on an accuracy curve of the machine learning model over the course of the training. Parameters of the training are adjusted based on the status. Training of the machine learning model is completed using the adjusted parameters.

4. 发明授权

US09538391B2 Sharing frequencies in an OFDM-based wireless communication system 有权
标题翻译：在基于OFDM的无线通信系统中共享频率
公开(公告)号：US09538391B2
公开(公告)日：2017-01-03
申请号：US14969780
申请日：2015-12-15
申请人： International Business Machines Corporation
发明人： Yong Hua Lin , Jianbin Tang , Qing Wang , Jun Song Wang , Rong Yan , Hai Zhan , Chao Zhu , Zhen Bo Zhu
IPC分类号： H04W72/08 , H04W72/04 , H04W28/04 , H04W16/14 , H04W72/00 , H04L1/00 , H04W24/08 , H04W24/10 , H04L27/26
CPC分类号： H04W16/14 , H04L1/0026 , H04L27/2691 , H04W24/08 , H04W24/10 , H04W28/04 , H04W72/005 , H04W72/042 , H04W72/0453 , H04W72/082 , H04W74/085
摘要： An apparatus for sharing frequencies in an orthogonal frequency-division multiplexing OFDM-based wireless communication system, wherein the OFDM-based wireless communication system comprises a base station and a mobile device that work within a radio frequency band, the method comprising: detecting an interference signal in the radio frequency band; setting by the base station, based upon the interference signal, interference indication information in a control header of a downlink frame to be sent to the mobile device, the interference indication information indicating a frequency range that is occupied by the interference signal in the radio frequency band; and sending by the base station the downlink frame to the mobile device, such that the mobile device may, based upon the interference indication information, avoid the frequency range where the interference signal is located.
摘要翻译：一种用于在正交频分复用基于OFDM的无线通信系统中共享频率的装置，其中所述基于OFDM的无线通信系统包括在无线电频带内工作的基站和移动设备，所述方法包括：检测干扰无线电频段信号; 由基站根据干扰信号设置要发送给移动设备的下行链路帧的控制报头中的干扰指示信息，指示由射频中的干扰信号占用的频率范围的干扰指示信息带; 以及由所述基站向所述移动设备发送下行链路帧，使得所述移动设备可以基于所述干扰指示信息来避免所述干扰信号所在的频率范围。

5. 发明申请

US20130321182A1 COMPRESSING AND DECOMPRESSING SIGNAL DATA 有权
公开(公告)号：US20130321182A1
公开(公告)日：2013-12-05
申请号：US13925275
申请日：2013-06-24
申请人： International Business Machines Corporation
发明人： Xinhao Cheng , Mingqiang Li , Yonghua Lin , Qing Wang , Chao Xue , Rong Yan , Hai Zhan , Chao Zhu
IPC分类号： H03M7/30
CPC分类号： H03M7/30 , G06T9/005 , H04B1/665 , H04J3/1611 , H04N7/52 , H04N19/61
摘要： The present invention relates to data compression and decompression, and particularly relates to a method and an apparatus for compressing and decompressing signal data. In an embodiment of the present invention, there is disclosed a method for compressing signal data, comprising: obtaining signal data; determining block lengths of a plurality of data blocks into which the signal data are divided, and determining exponents of the data blocks; forming a mantissa sequence of the data block by using the exponent of the data block to compress signal data contained in the data block; and forming a compressed data block by using the block length, the exponent and the mantissa sequence of the data block. By constructing a variable-length data block adapted to dynamic characteristics of signal data, the method for compressing signal data of the present invention increases the compression ratio of signal data.

6. 发明授权

US11164047B2 Object detection optimization 有权
公开(公告)号：US11164047B2
公开(公告)日：2021-11-02
申请号：US16518014
申请日：2019-07-22
申请人： International Business Machines Corporation
发明人： Ke Wei Sun , Junsong Wang , Yan GY Gong , Rong Yan , Yonghua Lin , Jie Zhang
IPC分类号： G06K9/00 , G06K9/62 , G06F16/28
摘要： The present disclosure provides a computer-implemented method, computer system and computer program product for object detection. According to the computer-implemented method, a first object can be classified to be a first category based on detection data acquired in a detection area. Then, a confidence score for the first category can be calculated based on historical detection data of the detection area, wherein the confidence score presents possibility degree of at least one object of the first category existing in the detection area. Whether classification of the first object is abnormal can be determined based on the confidence score.

7. 发明申请

US20160110527A1 Method and Apparatus for Digital Rights Management 审中-公开
标题翻译：数字版权管理方法与装置
公开(公告)号：US20160110527A1
公开(公告)日：2016-04-21
申请号：US14983888
申请日：2015-12-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Ya Bin Dang , Bo Feng , Ling Shao , Rong Yan
IPC分类号： G06F21/10 , H04L29/06 , H04L29/08
CPC分类号： G06Q20/203 , G06F21/10 , G06F21/105 , G06F21/31 , G06F2221/2101 , G06F2221/2117 , G06F2221/2135 , G06F2221/2137 , H04L63/08 , H04L67/306 , H04L2463/101
摘要： A method and apparatus for digital rights management (DRM) with steps and means for receiving a registration request from one of a plurality of DRM agent devices requesting to register one of a plurality of user accounts and the one DRM agent device to one of a plurality of rights issuers, completing a registration process in the one rights issuer, including establishment of a relationship among the one user account, the one DRM agent device and the one rights issuer; and returning a registration completion response to the one DRM agent device. The invention provides support to the many-to-many relationships among DRM entities, such as DRM agent device, user account and rights issuer, so that the DRM system can be applied to more business modes.
摘要翻译：一种用于数字版权管理（DRM）的方法和装置，其具有步骤和装置，用于从多个DRM代理设备之一接收请求将多个用户帐户中的一个注册并将一个DRM代理设备注册到多个的权利发行人，完成一个发行人的注册过程，包括建立一个用户帐户，一个DRM代理设备和一个发行者之间的关系; 并向所述一个DRM代理设备返回注册完成响应。本发明提供对诸如DRM代理设备，用户帐户和权限发布者之类的DRM实体之间的多对多关系的支持，使得DRM系统可以应用于更多的业务模式。

8. 发明授权

US09220004B2 Radio unit, baseband processing unit and base station system 有权
公开(公告)号：US09220004B2
公开(公告)日：2015-12-22
申请号：US13927931
申请日：2013-06-26
申请人： International Business Machines Corporation
发明人： Xinhao Cheng , Mingqiang Li , Yonghua Lin , Qing Wang , Chao Xue , Rong Yan , Hai Zhan , Chao Zhu
IPC分类号： H04W8/00 , H04W72/04 , H04L12/26 , H04W28/06 , H04L29/06 , H04W24/02
CPC分类号： H04W28/06 , H04L69/04 , H04W4/185 , H04W8/00 , H04W24/02 , H04W72/042
摘要： A radio unit configured to connect to a baseband processing unit includes a transformation unit configured to obtain uplink time domain signal data and transform the uplink time domain signal data into uplink frequency domain signal data; and a compression unit configured to compress the uplink frequency domain signal data by using a compression algorithm.

9. 发明授权

US09215479B2 System and method for real-time new event detection on video streams 有权
标题翻译：用于视频流实时新事件检测的系统和方法
公开(公告)号：US09215479B2
公开(公告)日：2015-12-15
申请号：US13759638
申请日：2013-02-05
申请人： International Business Machines Corporation
发明人： Gang Luo , Rong Yan , Philip Shi-Lung Yu
IPC分类号： G06K9/66 , G06K9/62 , H04N21/234 , G06K9/00 , H04N21/44 , H04N21/454 , H04N21/4545
CPC分类号： H04N21/23418 , G06K9/00765 , H04N21/44008 , H04N21/4542 , H04N21/45452
摘要： Techniques are disclosed for detecting new events in a video stream that yield improved detection efficiency in real time. For example, a method determines whether a given event is a new event in a video stream. The video stream includes a plurality of events. A first step extracts a first set of features (e.g., text features) from the given event. The first set of features is computationally less expensive to process as compared to a second set of features (e.g., image features) associated with the given event. A second step computes one or more first dissimilarity values between the given event and one or more previous events in the video stream using only the first set of features when one or more first dissimilarity criteria exist. A third step determines whether the given event is a new event based on the one or more computed first dissimilarity values.
摘要翻译：公开了用于检测视频流中的新事件的技术，其实时地提高了检测效率。例如，一种方法确定给定事件是否是视频流中的新事件。视频流包括多个事件。第一步骤从给定事件中提取第一组特征（例如，文本特征）。与给定事件相关联的第二组特征（例如，图像特征）相比，第一组特征在计算上较便宜。第二步骤当存在一个或多个第一不相似性标准时，仅使用第一组特征，在给定事件与视频流中的一个或多个先前事件之间计算一个或多个第一不相似性值。第三步骤基于一个或多个计算的第一不相似性值确定给定事件是否是新的事件。

10. 发明授权

US08902090B2 Compressing and decompressing signal data 有权
标题翻译：压缩和解压缩信号数据
公开(公告)号：US08902090B2
公开(公告)日：2014-12-02
申请号：US13899839
申请日：2013-05-22
申请人： International Business Machines Corporation
发明人： Xinhao Cheng , Mingqiang Li , Yonghua Lin , Qing Wang , Chao Xue , Rong Yan , Hai Zhan , Chao Zhu
IPC分类号： H03M7/30 , H04B1/66 , H04N19/61 , H04J3/16 , G06T9/00
CPC分类号： H03M7/30 , G06T9/005 , H04B1/665 , H04J3/1611 , H04N7/52 , H04N19/61
摘要： The present invention relates to data compression and decompression, and particularly relates to a method and an apparatus for compressing and decompressing signal data. In an embodiment of the present invention, there is disclosed a method for compressing signal data, comprising: obtaining signal data; determining block lengths of a plurality of data blocks into which the signal data are divided, and determining exponents of the data blocks; forming a mantissa sequence of the data block by using the exponent of the data block to compress signal data contained in the data block; and forming a compressed data block by using the block length, the exponent and the mantissa sequence of the data block. By constructing a variable-length data block adapted to dynamic characteristics of signal data, the method for compressing signal data of the present invention increases the compression ratio of signal data.
摘要翻译：本发明涉及数据压缩和解压缩，特别涉及用于压缩和解压缩信号数据的方法和装置。在本发明的实施例中，公开了一种用于压缩信号数据的方法，包括：获得信号数据; 确定信号数据被划分成多个数据块的块长度，并确定数据块的指数; 通过使用数据块的指数来形成数据块的尾数序列来压缩包含在数据块中的信号数据; 以及通过使用数据块的块长度，指数和尾数序列来形成压缩数据块。通过构造适于信号数据的动态特性的可变长度数据块，本发明的压缩信号数据的方法增加了信号数据的压缩比。

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