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. 发明公开

US20230244810A1 SEGMENTATION OF DATA IN HYBRID CLOUD 审中-公开
公开(公告)号：US20230244810A1
公开(公告)日：2023-08-03
申请号：US17588772
申请日：2022-01-31
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Shailendra Moyal , Sarbajit K. Rakshit , Venkata Vara Prasad Karri
IPC分类号： G06F21/62 , G06K9/62 , G06N20/00
CPC分类号： G06F21/6245 , G06K9/626 , G06N20/00
摘要： A computer hardware system associated with a hybrid cloud including a private cloud and a public cloud has a hardware processor configured to perform the following executable operations. A plurality of data sets of unprocessed data is randomly sampled to generate a plurality of random samples respectively associated with each of the plurality of data sets. The plurality of random samples is pre-processed, using a machine learning engine, to identify hidden correlations contained therein. The hidden correlations are evaluated against a confidentiality model to characterize each of the plurality of segments as to confidentiality. The data sets are segmented by assigning the data sets to one of the private cloud or the public cloud based upon the evaluating. Data sets assigned to the private cloud based upon the segmenting are processed using the private cloud.

2. 发明授权

US10878284B2 Method and apparatus for training image model, and method and apparatus for category prediction 有权
公开(公告)号：US10878284B2
公开(公告)日：2020-12-29
申请号：US16299177
申请日：2019-03-12
申请人： FUJITSU LIMITED
发明人： Wei Shen , Rujie Liu
IPC分类号： G06K9/00 , G06K9/62 , G06T11/60 , G06N3/08
CPC分类号： G06K9/6256 , G06K9/626 , G06N3/08 , G06T11/60 , G06T2210/12 , G06T2210/22
摘要： The method for training an image model, in each round of training performed with respect to each sample image: inputs an image obtained by cropping the sample image by an object extraction component obtained through a previous round of training, as a scale-adjusted sample image, into the image model, wherein the object extraction component is used for extracting concerned objects in sample images at respective scales; inputs a feature of the scale-adjusted sample image into a local classifier in the image model respectively, performs category prediction with respect to feature points in the feature, so as to obtain a local prediction result, and updates the object extraction component based on the local prediction result; performs object level category prediction for the scale-adjusted sample image based on the feature and the updated object extraction component; and trains the image model based on a category prediction result of the scale-adjusted sample image.

3. 发明申请

US20180315300A1 BUILDING SECURITY SYSTEM WITH EVENT DATA ANALYSIS FOR GENERATING FALSE ALARM RULES FOR FALSE ALARM REDUCTION 审中-公开
公开(公告)号：US20180315300A1
公开(公告)日：2018-11-01
申请号：US15947725
申请日：2018-04-06
申请人： Johnson Controls Technology Company , Tyco Fire & Security GmbH
发明人： Gopi Subramanian , Christine Trainor
IPC分类号： G08B29/18 , G08B31/00 , G08B19/00 , G06K9/62
CPC分类号： G08B29/185 , G06F3/0481 , G06K9/00771 , G06K9/626 , G06K9/6278 , G06K9/6297 , G06K2009/00738 , G08B19/005 , G08B31/00
摘要： A system for generating a false alarm rule for preventing a false alarm that occurs at a building includes a processing circuit configured to receive, via a communications interface, building data including events for the building devices. The building events include a first non-alarm event, a second non-alarm event different than the first non-alarm event, and a false alarm event. The processing circuit is configured to generate an event sequence based on the events, where the event sequence includes the first non-alarm event and the second non-alarm event and indicates a relationship between the first non-alarm event and the second non-alarm event that is indicative of a situation at the building that causes the false alarm event to occur. The processing circuit is configured to generate the false alarm rule based on the event sequence. The false alarm rule includes a recommendation for preventing the false alarm event from occurring.

4. 发明申请

US20180157524A1 METHOD AND SYSTEM FOR APPLICATION VIRTUALIZATION THAT INCLUDES MACHINE LEARNING 审中-公开
公开(公告)号：US20180157524A1
公开(公告)日：2018-06-07
申请号：US15887426
申请日：2018-02-02
申请人： DATA ACCELERATOR LTD
发明人： Priya Saxena , Jason Efstathiou , Martin Bernard Kirkby , Matthew Philip Clothier
IPC分类号： G06F9/455 , G06F9/54 , G06K9/62 , G06F15/18 , H04L29/06
CPC分类号： G06F9/45558 , G06F8/61 , G06F9/542 , G06F2009/45579 , G06F2009/45587 , G06K9/626 , G06K9/627 , G06N5/025 , G06N20/00 , H04L63/0236 , H04L63/107 , H04L67/10 , H04L69/22
摘要： A method for executing a virtualized application on a computing system that includes a user-space and a kernel-space is disclosed. In an embodiment, the method involves executing an application in the user-space, executing a user-level virtualization layer in the user-space, the user-level virtualization layer including a set of rules, performing, via the user-level virtualization layer, user-level hooking of events that are generated by the executing application according to the set of rules to identify events of interest, storing events that are identified as events of interest in a database, applying a pattern recognition process to the events that are stored in the database, generating a rule for the set of rules in the user-level virtualization layer based on the pattern recognition process, and applying the generated rule through the user-level virtualization layer.

5. 发明申请

US20160358081A1 AUTOMATED VEHICULAR ACCIDENT DETECTION 有权
标题翻译：自动车辆事故检测
公开(公告)号：US20160358081A1
公开(公告)日：2016-12-08
申请号：US14732836
申请日：2015-06-08
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Karl J. Cama , Norbert Herman , Shubhadip Ray
IPC分类号： G06N5/04 , G06F17/30 , G01S19/13
CPC分类号： G06N5/04 , B60W40/00 , G01S19/14 , G06F17/30241 , G06K9/00791 , G06K9/00832 , G06K9/626 , G06N3/08 , G06Q40/08 , G06Q50/30 , G08G1/0112 , G08G1/0129 , G08G1/0141 , G08G1/04 , G08G1/048 , G08G1/052 , G08G1/093 , G08G1/09626
摘要： A vehicle accident detection method and system is provided. The method includes receiving location coordinates associated with a location of an occuring vehicular accident. Data associated with possible causes of the vehicular accident is received from sensors. Traffic related rules associated with a geographical location are retrieved and analyzed with respect to the data. Parameters associated with at least one vehicle involved in the vehicular accident and a possible cause are determined via execution of programming logic and transmitted to additional systems. The possible cause for the vehicular accident is determined from all possible causes based on matching current and historical accident circumstances. Additionally, weighting factors may be available and adjusted over time for accurate accident detection. A possible cause comprising a greatest weighting factor may be used to identify a most likely cause.
摘要翻译：提供车辆事故检测方法和系统。该方法包括接收与发生的车辆事故的位置相关联的位置坐标。与传感器接收到与车辆事故可能原因有关的数据。与地理位置相关联的交通相关规则相对于数据被检索和分析。与涉及车辆事故的至少一辆车辆相关联的参数和可能的原因通过执行编程逻辑来确定并传送到附加系统。车辆事故的可能原因是根据当前和历史事故情况的一切可能原因确定的。另外，可以随时间调整加权因子以进行准确的事故检测。可能使用包含最大加权因子的可能原因来识别最可能的原因。

6. 发明申请

US20140301635A1 END-TO-END VISUAL RECOGNITION SYSTEM AND METHODS 有权
标题翻译：端到端视觉识别系统和方法
公开(公告)号：US20140301635A1
公开(公告)日：2014-10-09
申请号：US14245159
申请日：2014-04-04
申请人： THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
发明人： Stefano Soatto , Taehee Lee
IPC分类号： G06K9/62
CPC分类号： G06K9/626 , G06K9/00671 , G06K9/00744 , G06K9/4671 , G06K9/6255 , G06T7/207 , G06T7/246
摘要： We describe an end-to-end visual recognition system, where “end-to-end” refers to the ability of the system of performing all aspects of the system, from the construction of “maps” of scenes, or “models” of objects from training data, to the determination of the class, identity, location and other inferred parameters from test data. Our visual recognition system is capable of operating on a mobile hand-held device, such as a mobile phone, tablet or other portable device equipped with sensing and computing power. Our system employs a video based feature descriptor, and we characterize its invariance and discriminative properties. Feature selection and tracking are performed in real-time, and used to train a template-based classifier during a capture phase prompted by the user. During normal operation, the system scores objects in the field of view based on their ranking.
摘要翻译：我们描述一种端到端的视觉识别系统，其中“端对端”是指系统执行系统的所有方面的能力，从构建场景的“地图”或“场景”的“模型” 从训练数据的对象，到测试数据的类，身份，位置等推测参数的确定。我们的视觉识别系统能够在配备有感测和计算能力的移动手持设备（例如移动电话，平板电脑或其他便携式设备）上操作。我们的系统采用基于视频的特征描述符，我们描述其不变性和辨别性质。功能选择和跟踪是实时执行的，用于在用户提示的捕获阶段训练基于模板的分类器。在正常操作期间，系统根据其排名对视场中的对象进行分数。

7. 发明授权

US08805093B2 Method of pre-analysis of a machine-readable form image 有权
标题翻译：机器可读形式图像的预分析方法
公开(公告)号：US08805093B2
公开(公告)日：2014-08-12
申请号：US12977016
申请日：2010-12-22
申请人： Konstantin Zuev , Irina Filimonova , Sergey Zlobin
发明人： Konstantin Zuev , Irina Filimonova , Sergey Zlobin
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/00469 , G06K9/00449 , G06K9/46 , G06K9/6202 , G06K9/626 , G06K2209/01
摘要： In one embodiment, the invention provides a method for a machine to perform machine-readable form pre-recognition analysis. The method comprises preliminarily assigning at least one graphic image in a form for identification of form type, preliminarily creating at least one model of the said graphic image for identification of the form type, parsing a form image into regions, determining an image form type for the form image, comprising: (a) detecting on the form image at least one of said graphic images for identification of the form type, (b) performing a primary identification of the form image type based on a comparison of the detected graphic image with the said model, and(c) performing a profound analysis using a supplementary data said-primary identification results in multiple possibilities for the form image type.
摘要翻译：在一个实施例中，本发明提供了一种用于机器执行机器可读形式预识别分析的方法。该方法包括以形式类型的形式预先分配至少一个图形图像，预先创建所述图形图像的至少一个模型以识别形式类型，将形式图像解析为区域，确定图像形式类型所述形式图像包括：（a）在形式图像上检测至少一个所述图形图像以识别形式类型，（b）基于检测到的图形图像与所述模型，以及（c）使用补充数据进行深刻分析，所述主要识别导致形式图像类型的多种可能性。

8. 发明授权

US08717437B2 End-to end visual recognition system and methods 有权
标题翻译：端到端视觉识别系统和方法
公开(公告)号：US08717437B2
公开(公告)日：2014-05-06
申请号：US13735703
申请日：2013-01-07
申请人： The Regents of the University of California
发明人： Stefano Soatto , Taehee Lee
IPC分类号： H04N9/47
CPC分类号： G06K9/626 , G06K9/00671 , G06K9/00744 , G06K9/4671 , G06K9/6255 , G06T7/207 , G06T7/246
摘要： We describe an end-to-end visual recognition system, where “end-to-end” refers to the ability of the system of performing all aspects of the system, from the construction of “maps” of scenes, or “models” of objects from training data, to the determination of the class, identity, location and other inferred parameters from test data. Our visual recognition system is capable of operating on a mobile hand-held device, such as a mobile phone, tablet or other portable device equipped with sensing and computing power. Our system employs a video based feature descriptor, and we characterize its invariance and discriminative properties. Feature selection and tracking are performed in real-time, and used to train a template-based classifier during a capture phase prompted by the user. During normal operation, the system scores objects in the field of view based on their ranking.
摘要翻译：我们描述一种端到端的视觉识别系统，其中“端对端”是指系统执行系统的所有方面的能力，从构建场景的“地图”或“场景”的“模型” 从训练数据的对象，到测试数据的类，身份，位置等推测参数的确定。我们的视觉识别系统能够在配备有感测和计算能力的移动手持设备（例如移动电话，平板电脑或其他便携式设备）上操作。我们的系统采用基于视频的特征描述符，我们描述其不变性和辨别性质。功能选择和跟踪是实时执行的，用于在用户提示的捕获阶段训练基于模板的分类器。在正常操作期间，系统根据其排名对视场中的对象进行分数。

9. 发明申请

US20130215264A1 END-TO-END VISUAL RECOGNITION SYSTEM AND METHODS 有权
标题翻译：端到端视觉识别系统和方法
公开(公告)号：US20130215264A1
公开(公告)日：2013-08-22
申请号：US13735703
申请日：2013-01-07
申请人： THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
发明人： Stefano Soatto , Taehee Lee
IPC分类号： G06K9/00
CPC分类号： G06K9/626 , G06K9/00671 , G06K9/00744 , G06K9/4671 , G06K9/6255 , G06T7/207 , G06T7/246
摘要： We describe an end-to-end visual recognition system, where “end-to-end” refers to the ability of the system of performing all aspects of the system, from the construction of “maps” of scenes, or “models” of objects from training data, to the determination of the class, identity, location and other inferred parameters from test data. Our visual recognition system is capable of operating on a mobile hand-held device, such as a mobile phone, tablet or other portable device equipped with sensing and computing power. Our system employs a video based feature descriptor, and we characterize its invariance and discriminative properties. Feature selection and tracking are performed in real-time, and used to train a template-based classifier during a capture phase prompted by the user. During normal operation, the system scores objects in the field of view based on their ranking.
摘要翻译：我们描述一种端到端的视觉识别系统，其中“端对端”是指系统执行系统的所有方面的能力，从构建场景的“地图”或“场景”的“模型” 从训练数据的对象，到测试数据的类，身份，位置等推测参数的确定。我们的视觉识别系统能够在配备有感测和计算能力的移动手持设备（例如移动电话，平板电脑或其他便携式设备）上操作。我们的系统采用基于视频的特征描述符，我们描述其不变性和辨别性质。功能选择和跟踪是实时执行的，用于在用户提示的捕获阶段训练基于模板的分类器。在正常操作期间，系统根据其排名对视场中的对象进行分数。

10. 发明申请

US20120218436A1 Sensor-Based Mobile Search, Related Methods and Systems 有权
标题翻译：基于传感器的移动搜索，相关方法和系统
公开(公告)号：US20120218436A1
公开(公告)日：2012-08-30
申请号：US13465620
申请日：2012-05-07
申请人： Geoffrey B. Rhoads , Tony F. Rodriguez , Gilbert B. Shaw , Bruce L. Davis , William Y. Conwell
发明人： Geoffrey B. Rhoads , Tony F. Rodriguez , Gilbert B. Shaw , Bruce L. Davis , William Y. Conwell
IPC分类号： H04N5/228
CPC分类号： G01B11/14 , G01C21/3629 , G06F3/011 , G06F3/016 , G06K9/00523 , G06K9/00993 , G06K9/626 , G06Q30/02 , H04M2250/12 , H04M2250/52 , H04N5/225 , H04W4/02
摘要： A smart phone senses audio, imagery, and/or other stimulus from a user's environment, and acts autonomously to fulfill inferred or anticipated user desires. In one aspect, the detailed technology concerns phone-based cognition of a scene viewed by the phone's camera. The image processing tasks applied to the scene can be selected from among various alternatives by reference to resource costs, resource constraints, other stimulus information (e.g., audio), task substitutability, etc. The phone can apply more or less resources to an image processing task depending on how successfully the task is proceeding, or based on the user's apparent interest in the task. In some arrangements, data may be referred to the cloud for analysis, or for gleaning. Cognition, and identification of appropriate device response(s), can be aided by collateral information, such as context. A great number of other features and arrangements are also detailed.
摘要翻译：智能手机感测来自用户环境的音频，图像和/或其他刺激，并自动地执行以推断或预期的用户期望。一方面，详细的技术涉及电话摄像机观看的场景的基于手机的认知。应用于场景的图像处理任务可以通过参考资源成本，资源约束，其他刺激信息（例如，音频），任务可替换性等从各种替代方案中选择。电话可以将更多或更少的资源应用于图像处理任务取决于任务正在进行的成功，或者基于用户对任务的明显兴趣。在一些安排中，数据可能被称为云进行分析，或用于清除。识别和识别适当的设备响应可以通过附带信息（如上下文）来辅助。还详细介绍了许多其他功能和安排。

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