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. 发明申请

US20210390427A1 ENHANCED COLLECTION OF TRAINING DATA FOR MACHINE LEARNING TO IMPROVE WORKSITE SAFETY AND OPERATIONS 有权
公开(公告)号：US20210390427A1
公开(公告)日：2021-12-16
申请号：US16902107
申请日：2020-06-15
申请人： The Boeing Company
发明人： Brian D. Laughlin , William D. Kelsey
IPC分类号： G06N5/04 , G06N20/00 , G06Q10/06 , G06Q50/20 , G06Q50/26 , G06Q10/10 , G09B19/00 , H04W4/02
摘要： Systems and methods for enhanced collection of training data for machine learning to improve worksite safety and operations. One embodiment is a system with an interface to instruct a user device of a user to capture first sensor data of an object performing one or more known actions. The system also includes a training controller to allocate points as an award to the user of the user device for correctly capturing the object performing the one or more known actions, and to generate an instruction for the user to capture second sensor data of the object performing one or more unknown actions if the user has exceeded a threshold of awarded points. The training controller trains a machine learning function based on the second sensor data of the object performing the one or more unknown actions as identified by the user having exceeded the threshold of awarded points.

2. 发明授权

US09645652B2 Ubiquitous natural user system for human-machine interaction 有权
公开(公告)号：US09645652B2
公开(公告)日：2017-05-09
申请号：US14079692
申请日：2013-11-14
申请人： The Boeing Company
发明人： William D. Kelsey , Brian D. Laughlin , Richard N. Blair
IPC分类号： G06F3/01
CPC分类号： G06F3/017
摘要： A system is provided that includes sensor(s) configured to provide sensed input including measurements of motion of a user during performance of a task, and in which the motion may include a gesture performed in one of a plurality of 3D zones in an environment of the user that are defined to accept respective, distinct gestures. A front-end system may receive and process the sensed input including the measurements to identify the gesture and from the gesture, identify operations of an electronic resource. The front-end system may identify the gesture based on the one of the plurality of 3D zones in which the gesture is performed. The front-end system may then form and communicate an input to cause the electronic resource to perform the operations and produce an output. And the front-end system may receive the output from the electronic resource, and communicate the output to a display device.

3. 发明申请

US20140309970A1 MANAGING A MODEL HAVING AN OBJECT CYCLE 审中-公开
标题翻译：管理具有对象周期的模型
公开(公告)号：US20140309970A1
公开(公告)日：2014-10-16
申请号：US13860676
申请日：2013-04-11
申请人： The Boeing Company
发明人： William D. Kelsey , David H. Jones
IPC分类号： G06F17/50
CPC分类号： G06F17/50 , G06Q10/063
摘要： A model-management system includes a cycles map generator, object registry generator and runtime code generator. The cycles map generator is configured to create a cycles map that, for a cycle in an information model having a plurality of objects, identifies a non-dominant association of a second or later object to a first object. The object registry generator is configured to create an object registry map. And the runtime code generator is configured to generate an instantiable information model and object registry based on the information model and maps. Generation of the instantiable information model includes generation of a plurality of instantiable objects including a second/later instantiable object that, for the non-dominant association, includes an object qualifier that identifies a referenced object for the first object to be instantiated through the object registry, instead of a contained first instantiable object to be instantiated from within the second/later instantiable object.
摘要翻译：模型管理系统包括循环映射生成器，对象注册表生成器和运行时代码生成器。周期图生成器被配置为创建周期图，对于具有多个对象的信息模型中的周期，识别第二或更后的对象与第一对象的非显性关联。对象注册表生成器被配置为创建对象注册表映射。并且运行时代码生成器被配置为基于信息模型和映射生成可实例化的信息模型和对象注册表。生成可实例化信息模型包括生成多个可实例化对象，包括第二/后续可实例化对象，对于非显性关联，包括对象限定符，该对象限定符标识通过对象注册表要实例化的第一对象的引用对象，而不是从第二/后续可实例化对象中实例化的包含的第一可实例化对象。

4. 发明授权

US11267587B2 Methods and systems for an ad hoc network sensor system 有权
公开(公告)号：US11267587B2
公开(公告)日：2022-03-08
申请号：US16435669
申请日：2019-06-10
申请人： The Boeing Company
发明人： John W. Glatfelter , Brian D. Laughlin , William D. Kelsey
IPC分类号： B64F5/60 , H04L29/08 , H04L67/12 , H04W4/02 , H04W4/38 , H04W4/48 , G07C5/08 , G07C5/02 , G01W1/00 , H04W4/42
摘要： An example real-time ad hoc network sensor system includes a plurality of sensors positioned at fixed locations on an aircraft, a plurality of mobile devices in an interior of the aircraft, and a computing device having one or more processors and a non-transitory computer readable medium having stored thereon instructions, that when executed by the one or more processors, cause the computing device to perform functions including receiving outputs from the plurality of sensors and from the sensors of the plurality of mobile devices during the flight of the aircraft, mapping the outputs to a computer model of the aircraft for association with locations in the interior of the aircraft, and based on the mapping, creating a vehicle data-signature-map of the interior of the aircraft for at least one parameter of the aircraft.

5. 发明申请

US20210390280A1 ENHANCED COLLECTION OF TRAINING DATA FOR MACHINE LEARNING TO IMPROVE WORKSITE SAFETY AND OPERATIONS 有权
公开(公告)号：US20210390280A1
公开(公告)日：2021-12-16
申请号：US16902089
申请日：2020-06-15
申请人： The Boeing Company
发明人： Brian D. Laughlin , William D. Kelsey
IPC分类号： G06K9/00 , G06K9/62 , G06N20/00 , G06F16/9035
摘要： Systems and methods for enhanced collection of training data for machine learning to improve worksite safety and operations. One embodiment is a system with an interface to receive first evaluations of a first scene from a group of trainees, the first scene belonging to safety curriculum content and depicting a worksite with a known hazard that is associated in memory with a hazard profile. The system includes a controller to determine a trusted subgroup of the trainees that correctly identified the known hazard in the first scene. The interface receives second evaluations of a second scene from the trusted subgroup of the trainees that depicts the worksite with an unknown hazard. The controller trains a machine learning function based on the second evaluations from the trusted subgroup of the trainees for automatic identification of hazard indications in the second scene depicting the worksite with the unknown hazard.

6. 发明申请

US20190020669A1 CYBER SECURITY SYSTEM WITH ADAPTIVE MACHINE LEARNING FEATURES 审中-公开
公开(公告)号：US20190020669A1
公开(公告)日：2019-01-17
申请号：US15647173
申请日：2017-07-11
申请人： The Boeing Company
发明人： John W. Glatfelter , William D. Kelsey , Brian D. Laughlin
IPC分类号： H04L29/06 , G06N99/00
摘要： Systems and methods for a cyber security system with adaptive machine learning features. One embodiment is a system that includes a server configured to manage a plurality of user devices over a network, and a user device that includes an interface and a processor. The interface is configured to communicate with the server over the network, and the processor implements a machine learning function configured to monitor user interactions with the user device over time to establish a use profile, to detect anomalous use of the user device based on a variance from the use profile, to determine whether the anomalous use is representative of a security threat, and to instruct the user device to perform one or more automatic actions to respond to the security threat.

7. 发明授权

US11361537B2 Enhanced collection of training data for machine learning to improve worksite safety and operations 有权
公开(公告)号：US11361537B2
公开(公告)日：2022-06-14
申请号：US16902089
申请日：2020-06-15
申请人： The Boeing Company
发明人： Brian D. Laughlin , William D. Kelsey
IPC分类号： G06K9/62 , G06V20/13 , G06F16/9035 , G06N20/00
摘要： Systems and methods for enhanced collection of training data for machine learning to improve worksite safety and operations. One embodiment is a system with an interface to receive first evaluations of a first scene from a group of trainees, the first scene belonging to safety curriculum content and depicting a worksite with a known hazard that is associated in memory with a hazard profile. The system includes a controller to determine a trusted subgroup of the trainees that correctly identified the known hazard in the first scene. The interface receives second evaluations of a second scene from the trusted subgroup of the trainees that depicts the worksite with an unknown hazard. The controller trains a machine learning function based on the second evaluations from the trusted subgroup of the trainees for automatic identification of hazard indications in the second scene depicting the worksite with the unknown hazard.

8. 发明授权

US11354948B2 Methods and systems for performing maintenance on an aircraft 有权
公开(公告)号：US11354948B2
公开(公告)日：2022-06-07
申请号：US16435673
申请日：2019-06-10
申请人： The Boeing Company
发明人： John W. Glatfelter , Brian D. Laughlin , William D. Kelsey
IPC分类号： G07C5/08 , H04W84/18 , G07C5/02 , B64D45/00 , G07C5/10
摘要： An example method of performing maintenance on an aircraft includes receiving a vehicle data-signature-map of an interior of an aircraft for at least one parameter of the aircraft, and the vehicle data-signature-map is based on sensor outputs received from sensors of mobile devices positioned at locations in the interior of the aircraft. The method also includes comparing the vehicle data-signature-map with a previous vehicle data-signature-map, based on differences of the vehicle data-signature-map as compared to the previous vehicle data-signature-map making a determination for maintenance, and generating and outputting a recommendation for inspection of an identified portion of the aircraft based on the distribution of the at least one parameter in the vehicle data-signature-map for the identified portion of the aircraft being substantially different than the distribution of the at least one parameter in the vehicle data-signature-map for other portions of the aircraft to assist with the maintenance of the aircraft.

9. 发明授权

US10419468B2 Cyber security system with adaptive machine learning features 有权
公开(公告)号：US10419468B2
公开(公告)日：2019-09-17
申请号：US15647173
申请日：2017-07-11
申请人： The Boeing Company
发明人： John W. Glatfelter , William D. Kelsey , Brian D. Laughlin
IPC分类号： H04L29/06 , G06N20/00 , G06F21/31 , G06F21/55 , H04W12/12 , H04W12/00
摘要： Systems and methods for a cyber security system with adaptive machine learning features. One embodiment is a system that includes a server configured to manage a plurality of user devices over a network, and a user device that includes an interface and a processor. The interface is configured to communicate with the server over the network, and the processor implements a machine learning function configured to monitor user interactions with the user device over time to establish a use profile, to detect anomalous use of the user device based on a variance from the use profile, to determine whether the anomalous use is representative of a security threat, and to instruct the user device to perform one or more automatic actions to respond to the security threat.

10. 发明授权

US11636359B2 Enhanced collection of training data for machine learning to improve worksite safety and operations 有权
公开(公告)号：US11636359B2
公开(公告)日：2023-04-25
申请号：US16902107
申请日：2020-06-15
申请人： The Boeing Company
发明人： Brian D. Laughlin , William D. Kelsey
IPC分类号： G06N5/00 , G06N20/00 , G06Q10/00 , G06Q50/00 , G09B19/00 , H04W4/00 , G08B21/00 , G06N5/04 , G06Q10/0635 , G06Q10/0631 , G06Q50/20 , G06Q10/0639 , G06Q10/105 , H04W4/02 , G06Q50/26 , G08B21/02
摘要： Systems and methods for enhanced collection of training data for machine learning to improve worksite safety and operations. One embodiment is a system with an interface to instruct a user device of a user to capture first sensor data of an object performing one or more known actions. The system also includes a training controller to allocate points as an award to the user of the user device for correctly capturing the object performing the one or more known actions, and to generate an instruction for the user to capture second sensor data of the object performing one or more unknown actions if the user has exceeded a threshold of awarded points. The training controller trains a machine learning function based on the second sensor data of the object performing the one or more unknown actions as identified by the user having exceeded the threshold of awarded points.

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