-
公开(公告)号：US11227197B2
公开(公告)日：2022-01-18
申请号：US16053249
申请日：2018-08-02
Applicant: International Business Machines Corporation
Inventor： Craig M. Trim , Aaron K. Baughman , Barry Michael Graham , Todd R. Whitman
Abstract: Identifying words to accurately describe, with a range of specificity, an image is provided. A vector space corresponding to the image is generated using a convolutional neural network to extract a hierarchy of features ranging from broad to specific from the image. Closest vocabulary ranging from broad to specific are identified for the image using Huffman coding on the vector space. Accurate words ranging from broad to specific are identified that describe the image based on vocabulary output of the Huffman coding on the vector space. The accurate words ranging from broad to specific describing the image are output.
-
公开(公告)号：US10896376B2
公开(公告)日：2021-01-19
申请号：US15846746
申请日：2017-12-19
Applicant: International Business Machines Corporation
Inventor： Aaron K. Baughman , Diwesh Pandey , John P. Perrino , Todd R. Whitman
Abstract: In one embodiment of the present invention, environment information corresponding to a user is received. A target environment is simulated in augmented reality based on the environment information. Physiological information corresponding to the user is received. A cognitive state of the user is determined based on the physiological information. In response to determining that the cognitive state of the user is not a target cognitive state, the target environment is modified in augmented reality to achieve the target cognitive state.
-
公开(公告)号：US10887292B2
公开(公告)日：2021-01-05
申请号：US15955946
申请日：2018-04-18
Applicant: International Business Machines Corporation
Inventor： David C. Bastian , Aaron K. Baughman , Nicholas A. McCrory , Todd R. Whitman
Abstract: Disclosed embodiments provide techniques for improvements in electronic communications. A mobile electronic device associated with a user measures crowd density proximate to the user. When the crowd density exceeds a threshold, a haptic signal, such as a vibration or pneumatic output, is discretely provided to the user. After issuing the haptic signal, the device listens for false data. False data is data entered by the user that is not part of the expected data sequence. The false data is used to obfuscate the true data. The randomness of the false data can be used to generate a keypair used for communication. The keypair is used for asymmetric encryption that provides an extra level of security for electronic communications from the mobile electronic device.
-
公开(公告)号：US20200082002A1
公开(公告)日：2020-03-12
申请号：US16129095
申请日：2018-09-12
Applicant: International Business Machines Corporation
Inventor： Todd R. Whitman , Aaron K. Baughman , John P. Perrino , Diwesh Pandey
Abstract: Determining contextual confidence of images for associative deep learning includes receiving an image including a representation of a subject. Text data related to the image is received. One or more physical properties of the image are determined. Context information of the image is determined using natural language processing. The image is classified based upon the contextual information and the one or more physical properties using a classification model to determine a classification. An emotional state of the image is determined based upon the physical properties. A confidence of the classification and emotional state is determined.
-
公开(公告)号：US10581625B1
公开(公告)日：2020-03-03
申请号：US16196580
申请日：2018-11-20
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Diwesh Pandey , Aaron K. Baughman , Todd R. Whitman , John P. Perrino
Abstract: A computer-implemented method includes: obtaining, by a computer device, monitoring data of a user participating in a video conference; determining, by the computer device, a level of understanding of the user based on the monitoring data; adjusting, by the computer device, an output of the video conference for the user based on the determined level of understanding being less than a threshold; and determining, by the computer device, a success of the adjusting and updating a learning model based on the determined success.
-
Patent Agency Ranking
公开(公告)号：US10409291B2
公开(公告)日：2019-09-10
申请号：US15469635
申请日：2017-03-27
Applicant: International Business Machines Corporation
Inventor： Aaron K. Baughman , David C. Bastian , Nicholas A. McCrory , Todd R. Whitman
Abstract: Embodiments of the present invention provide a method, system and computer program product for teaming in swarm intelligent robot sets. The method includes programming a multiplicity of robots in a multi-robot set with a particular locomotive model and assigning each of the robots to different individual tasks corresponding to different individual objectives of a problem based upon the particular locomotive model of the corresponding robots. The method additionally includes deploying the multi-robot set into a confined geographic area and surveilling each robot to ensure that each robot assigned to a corresponding task is achieving the assigned task. Finally, the method includes responding to one of the robots appearing to be unable to complete a corresponding assigned one of the tasks by selecting a different robot with a locomotive model considered compatible with the corresponding assigned one of the tasks to complete the corresponding assigned one of the tasks.
-
公开(公告)号：US20190250700A1
公开(公告)日：2019-08-15
申请号：US16395239
申请日：2019-04-26
Applicant: International Business Machines Corporation
Inventor： Aaron K. Baughman , Diwesh Pandey , John P. Perrino , Todd R. Whitman
IPC: G06F3/01 , H04W4/80 , G06T11/60 , G05B15/02 , G06F3/147 , H04W76/10 , G09B21/00 , G06F3/038 , G09G5/02 , G06F3/14 , H05B37/02
Abstract: A determination can be made as to whether a user of an augmented reality device is within a threshold distance from a configurable physical apparatus including at least one display configured to emit light. Responsive to determining that the user is within the threshold distance from the configurable physical apparatus, a communication link can be established between the augmented reality device and a controller of the configurable physical apparatus. The controller can be initiated to change the configurable physical apparatus from a first configuration to a second configuration. In the first configuration the at least one display can visually depict textures causing the physical apparatus to look like a first type of ceiling or a first type of floor. In the second configuration the at least one display can visually depict textures causing the physical apparatus to look like a second type of ceiling or a second type of floor.
-
公开(公告)号：US10249098B2
公开(公告)日：2019-04-02
申请号：US15836451
申请日：2017-12-08
Applicant: International Business Machines Corporation
Inventor： David C. Bastian , Aaron K. Baughman , Nicholas A. McCrory , Todd R. Whitman
Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining virtual image data representing a virtual object; and encoding the virtual image data with physical image data to provide a formatted image file, wherein the encoding includes for a plurality of spatial image elements providing one or more data field that specifies physical image information and one or more data field that specifies virtual image information based on the virtual image data so the formatted image file for each of the plurality of spatial image elements provides physical image information and virtual image information, and wherein the encoding includes providing indexing data that associates an identifier for the virtual object to spatial image elements for the virtual object.
-
公开(公告)号：US10242757B2
公开(公告)日：2019-03-26
申请号：US15910193
申请日：2018-03-02
Applicant: International Business Machines Corporation
Inventor： Aaron K. Baughman , Diwesh Pandey , John P. Perrino , Todd R. Whitman
Abstract: Socially aware guidance and differential access controls within a control zone are determined for users based on individual wellness goals and predicted wellness patterns. Users are socially grouped based on wellness goals and predicted responsiveness to achieving the wellness goals. Biometric data obtained from users from social situations and activities provide insight into individual wellness progress and achievement of individual wellness goals. Predicted wellness patterns further assist users with achieving wellness goals through socially aware guidance and differential access controls.
-
公开(公告)号：US10215581B2
公开(公告)日：2019-02-26
申请号：US15196942
申请日：2016-06-29
Applicant: International Business Machines Corporation
Inventor： Guillaume Hoareau , Johannes J. Liebenberg , John G. Musial , Todd R. Whitman
Abstract: An aspect of vehicle navigation assistance includes generating a route based on a starting point of a vehicle and a user-inputted destination location. The route specifies a set of directions defined by location points, actions, and distance values. An aspect also includes comparing the generated route to previously travelled routes stored in the memory, identifying, from the comparing, a segment of the generated route that is in common with a segment from at least one of the previously travelled routes, and determining a frequency count indicating a number of instances that the segment of the generated route appears in the previously travelled routes. A further aspect includes upon determining that the frequency count exceeds a specified threshold value, muting output of audio-based directions through a speaker of the vehicle during traversal of the vehicle through the segment of the generated route.
-
-
-
-
-
-
-
-
-
Search Results
90
records
(took 0.05 seconds)
