专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US07536365B2 Hybrid architecture for acquisition, recognition, and fusion 有权
标题翻译：用于采集，识别和融合的混合架构
公开(公告)号：US07536365B2
公开(公告)日：2009-05-19
申请号：US11297679
申请日：2005-12-08
申请人： Omar Aboutalib
发明人： Omar Aboutalib
IPC分类号： G06N5/00
CPC分类号： G06K9/3241 , G06K9/6288
摘要： A method comprises the steps of: producing one or more signals representative of a feature of a target or area of interest, statistically processing the signals to produce one or more first hypotheses of the target or area of interest, comparing the first hypotheses to one or more templates in a template library to produce one or more second hypotheses, and comparing the second hypotheses to one or more models in a model library to produce a target decision. An apparatus that performs the method is also provided.
摘要翻译：一种方法包括以下步骤：产生表示目标或感兴趣区域的特征的一个或多个信号，统计处理信号以产生目标或感兴趣区域的一个或多个第一假设，将第一假设与一个或多个模板库中的更多模板以产生一个或多个第二假设，以及将第二假设与模型库中的一个或多个模型进行比较以产生目标决策。还提供了执行该方法的装置。

52. 发明申请

US20050278150A1 Method and apparatus for digital signal filtering 失效
标题翻译：数字信号滤波方法和装置
公开(公告)号：US20050278150A1
公开(公告)日：2005-12-15
申请号：US10854836
申请日：2004-05-27
申请人： Magdi Mohamed , Weimin Xiao
发明人： Magdi Mohamed , Weimin Xiao
IPC分类号： G06F15/00 , G06K9/36 , G06K9/62
CPC分类号： G06K9/36 , G06K9/6288 , H03H17/0261 , H03H2017/0072 , H03H2222/02
摘要： A Q-Filter is a reconfigurable technique that performs a continuum of linear and nonlinear filtering operations. It is modeled by unique mathematical structure, utilizing a function called the Q-Measure, defined using a set of adjustable kernel parameters to enable efficient hardware and software implementations of a variety of useful, new and conventional, filtering operations. The Q-Measure is is based on an extension of the well-known Sugeno λ-Measure.
摘要翻译： Q滤波器是一种可重构技术，可执行线性和非线性滤波操作的连续性。它由独特的数学结构建模，利用称为Q-Measure的功能，使用一组可调内核参数定义，以实现各种有用的，新的和常规的过滤操作的高效硬件和软件实现。 Q-Measure是基于着名的Sugeno lambda-Measure的扩展。

53. 发明授权

US06754560B2 Robot device, robot device action control method, external force detecting device and external force detecting method 失效
标题翻译：机器人装置，机器人装置动作控制方法，外力检测装置及外力检测方法
公开(公告)号：US06754560B2
公开(公告)日：2004-06-22
申请号：US09980132
申请日：2002-03-14
申请人： Masahiro Fujita , Tsuyoshi Takagi , Rika Hasegawa , Osamu Hanagata , Jun Yokono , Gabriel Costa , Hideki Shimomura
发明人： Masahiro Fujita , Tsuyoshi Takagi , Rika Hasegawa , Osamu Hanagata , Jun Yokono , Gabriel Costa , Hideki Shimomura
IPC分类号： G06F1900
CPC分类号： G06K9/6288 , B25J13/003 , B25J13/08 , G05B2219/35453 , G05B2219/40201 , G06N3/008 , G10L15/26
摘要： A robot is proposed which has a speech recognition unit to detect information supplied simultaneously with or just before or after detection of a touch by a touch sensor, an associative memory/recall memory to store action made correspondingly to the touch and input information (speech signal) detected by the speech recognition unit in association with each other, and an action generator to control the robot to make action recalled by the associative memory/recall memory based on a newly acquired input information (speech signal). The robot has also a sensor data processor to allow the robot to act correspondingly to the touch detection by the touch sensor. Thus, the robot can learn action in association with an input signal such as speech signal.
摘要翻译：提出了一种机器人，其具有语音识别单元，用于检测由触摸传感器检测到触摸之前或之后提供的信息;相关存储器/回忆存储器，用于存储对应于触摸和输入信息（语音信号），以及动作发生器，其基于新获取的输入信息（语音信号），控制所述机器人使由所述关联存储器/召回存储器进行动作调用。机器人还具有传感器数据处理器，以允许机器人相应地通过触摸传感器进行触摸检测。因此，机器人可以与诸如语音信号的输入信号相关联地学习动作。

54. 发明申请

US20020158599A1 Robot device, robot device action control method, external force detecting device and external force detecting method 失效
标题翻译：机器人装置，机器人装置动作控制方法，外力检测装置及外力检测方法
公开(公告)号：US20020158599A1
公开(公告)日：2002-10-31
申请号：US09980132
申请日：2002-03-14
发明人： Masahiro Fujita , Tsuyoshi Takagi , Rika Hasegawa , Osamu Hanagata , Jun Yokono , Gabriel Costa , Hideki Shimomura
IPC分类号： B25J009/16
CPC分类号： G06K9/6288 , B25J13/003 , B25J13/08 , G05B2219/35453 , G05B2219/40201 , G06N3/008 , G10L15/26
摘要： A robot (1) is proposed which includes a speech recognition unit (101) to detect information supplied simultaneously with or just before or after detection of a touch by a touch sensor, an associative memory/recall memory (104) to store action made correspondingly to the touch and input information (speech signal) detected by the speech recognition unit (101) in association with each other, and an action generator (105) to control the robot (1) to make action recalled by the associative memory/recall memory (104) based on a newly acquired input information (speech signal). The robot (1) includes also a sensor data processor (102) to allow the robot (1) to act correspondingly to the touch detection by the touch sensor. Thus, the robot (1) can learn action in association with an input signal such as speech signal.
摘要翻译：提出了一种机器人（1），其包括语音识别单元（101），用于检测在触摸传感器触摸检测之前或之后提供的信息;联想存储器/回忆存储器（104），用于存储相应地进行的动作涉及由语音识别单元（101）检测到的触摸和输入信息（语音信号），以及动作发生器（105），用于控制机器人（1）使关联存储器/回忆存储器（104）基于新获取的输入信息（语音信号）。机器人（1）还包括传感器数据处理器（102），以允许机器人（1）对应于触摸传感器的触摸检测而起作用。因此，机器人（1）可以与诸如语音信号的输入信号相关联地学习动作。

55. 发明授权

US6125339A Automatic learning of belief functions 失效
标题翻译：自动学习信仰功能
公开(公告)号：US6125339A
公开(公告)日：2000-09-26
申请号：US996776
申请日：1997-12-23
申请人： Kurt Reiser , Yang Chen , Todd L. Baker
发明人： Kurt Reiser , Yang Chen , Todd L. Baker
IPC分类号： G06F15/18 , G06F101/14
CPC分类号： G06N99/005 , G06K9/6288
摘要： A method providing automatic learning belief functions enabling the combination of different, and possibly contradictory information sources. The present invention provides the ability to determine erroneous information sources, inappropriate information combinations, and optimal information granularities, along with enhanced system performance.
摘要翻译：一种提供自动学习信念功能的方法，可以组合不同的，也可能是相互矛盾的信息源。本发明提供了确定错误信息源，不适当信息组合和最佳信息粒度以及增强的系统性能的能力。

56. 发明授权

US5832465A Method for building a self-learning evidential reasoning system 失效
标题翻译：建立自学证据推理体系的方法
公开(公告)号：US5832465A
公开(公告)日：1998-11-03
申请号：US834582
申请日：1997-04-07
申请人： Daniel Mohimm Tom
发明人： Daniel Mohimm Tom
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , G06K9/6288
摘要： The present invention discloses a method for building a self-learning evidential reasoning system from examples. In this invention a hierarchical model structure for the self-learning evidential reasoning system is defined. After the model structure has been defined examples are supplied by experts. The examples are entered directly into example spreadsheets and then used to train the model structure. The model structure is then trained to minimize error between model output and the desired output. The error is minimized by using a gradient descent optimization. The model structure is then put into production and then used to make a recommendation. The self-learning evidential reasoning system can be used in various fields, such as analyzing the risk of financial service applications.
摘要翻译：本发明公开了一种从示例中构建自学证据推理系统的方法。在本发明中，定义了用于自学证明推理系统的层次模型结构。在模型结构定义之后，专家提供了示例。这些示例直接输入到示例电子表格中，然后用于训练模型结构。然后训练模型结构以最小化模型输出与期望输出之间的误差。通过使用梯度下降优化将错误最小化。然后将模型结构投入生产，然后用于推荐。自学证据推理系统可以用于各种领域，如分析金融服务应用的风险。

57. 发明公开

US20230244942A1 TENSOR MODIFICATION BASED ON PROCESSING RESOURCES 审中-公开
公开(公告)号：US20230244942A1
公开(公告)日：2023-08-03
申请号：US17679985
申请日：2022-02-24
申请人： NVIDIA Corporation
发明人： Chong Yu , Zhihao Xie , Jia Liu , Niall Dunan Emmart , Jingyang Zhu , Yu-Jung Chen
IPC分类号： G06N3/08 , G06K9/62
CPC分类号： G06N3/082 , G06K9/6288
摘要： Apparatuses, systems, and techniques to modify tensors based on processor requirements. In at least one embodiment, input tensors and weight tensors are modified to meet processing resource requirements.

58. 发明公开

US20230182729A1 VEHICLE LOCALIZATION 审中-公开
公开(公告)号：US20230182729A1
公开(公告)日：2023-06-15
申请号：US17547465
申请日：2021-12-10
申请人： Ford Global Technologies, LLC
发明人： Krishna Bandi , Samer Ibrahim , Colette Knopp , Basavaraj Tonshal , Sathyanaraya Chary Palakonda
IPC分类号： B60W30/12 , H04W4/40 , G06K9/62
CPC分类号： B60W30/12 , H04W4/40 , G06K9/6288 , G06K9/6256 , B60W2554/4041
摘要： A plurality of localization data sources accessible on a vehicle network in a vehicle can be identified. A plurality of active vehicle applications that request localization data provided by one or more of the localization data sources can be identified. Based on the active vehicle applications, a plurality of the localization data sources to be combined to output a vehicle location can be selected.

59. 发明授权

US11656336B2 Advanced gaming and virtual reality control using radar 有权
公开(公告)号：US11656336B2
公开(公告)日：2023-05-23
申请号：US17119312
申请日：2020-12-11
申请人： Google LLC
发明人： Patrick M. Amihood , Ivan Poupyrev
IPC分类号： G01S13/04 , G06F3/01 , G01S7/41 , G01S13/56 , G01S13/86 , H04Q9/00 , G06K9/62 , G01S13/88 , G06F21/32 , G06F3/04815 , G01S7/40 , H04W4/80 , G06N20/00 , H04W16/28 , G01S13/90 , G06V20/64 , G06V40/20 , G06F16/245 , G06F21/62 , A63F13/21 , A63F13/24 , G01S13/66 , G08C17/02 , G06T7/73 , G01S13/931 , G06F1/16 , G06F3/0484 , G01S19/42 , G06F3/0346 , G06F3/16
CPC分类号： G06F3/017 , A63F13/21 , A63F13/24 , G01S7/4004 , G01S7/41 , G01S7/412 , G01S7/415 , G01S13/56 , G01S13/66 , G01S13/86 , G01S13/867 , G01S13/88 , G01S13/888 , G01S13/90 , G01S13/904 , G06F3/011 , G06F3/04815 , G06F16/245 , G06F21/32 , G06F21/6245 , G06K9/629 , G06K9/6254 , G06K9/6255 , G06K9/6262 , G06K9/6288 , G06N20/00 , G06V20/64 , G06V40/28 , H04Q9/00 , H04W4/80 , H04W16/28 , A63F2300/8082 , G01S13/865 , G01S13/931 , G01S19/42 , G01S2013/9322 , G06F1/163 , G06F3/0346 , G06F3/0484 , G06F3/165 , G06F2203/0384 , G06F2221/2105 , G06T7/75 , G08C17/02 , G08C2201/93 , H04Q2209/883
摘要： Techniques are described herein that enable advanced gaming and virtual reality control using radar. These techniques enable small motions and displacements to be tracked, even in the millimeter or submillimeter scale, for user control actions even when those actions are optically occluded or obscured.

60. 发明授权

US10878173B2 Object recognition and tagging based on fusion deep learning models 有权
公开(公告)号：US10878173B2
公开(公告)日：2020-12-29
申请号：US16204918
申请日：2018-11-29
申请人： Adobe Inc.
发明人： Vlad Morariu , Rajiv Jain , Nishant Sankaran
IPC分类号： G06F40/117 , G06N5/04 , G06K9/62 , G06K9/00
CPC分类号： G06F40/117 , G06K9/00469 , G06K9/6288 , G06N5/046
摘要： In some embodiments, a computing system computes tags for an electronic document. The computing system identifies sets of objects for the electronic document by applying a set of object-recognition rules to the electronic document, with each object-recognition rule generating a set of identified objects. The computing system generates feature maps that represent a set of identified objects. The computing system generates a heat map that identifies attributes of the electronic document including object candidates of the electronic document by applying a page-segmentation machine-learning model to the electronic document. The computing system computes a tag by applying a fusion deep learning module to the feature map and the heat map to correlate a document object identified by the feature map with an attribute of the electronic document identified by the heat map. The computing system generates the tagged electronic document by applying the tag to the electronic document.

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