438 patents
Utility
Viewable Screen Based Call Leg Transition
MSFT
7 Mar 24
A method and system for causing a call leg transition based on determining that a screen of a device is not viewable to a user are disclosed, comprising receiving, using a default first telephony application, an incoming call event having a first call leg over a first connection to a telecommunication network addressed to the device, accepting the incoming call event using a second telephony application, creating a second connection having a second call leg to the telecommunication network corresponding to the incoming call event, associating a call event continuity identifier unique to the incoming call event with each of the first and second call legs so that the first and second call legs are connectable at a common port in the telecommunication network, determining if the screen of the device is viewable to the user, and causing a transition from the second call leg to the first call leg based on determining that the screen of the device is not viewable to the user.
Amer Aref HASSAN, Vandana THOMAS, Michael J. DAVIS, Abhilash Chandrasekharan NAIR
Filed: 14 Nov 23
Utility
Training Multi-object Tracking Models Using Simulation
MSFT
7 Mar 24
Training a multi-object tracking model includes: generating a plurality of training images based at least on scene generation information, each training image comprising a plurality of objects to be tracked; generating, for each training image, original simulated data based at least on the scene generation information, the original simulated data comprising tag data for a first object; locating, within the original simulated data, tag data for the first object, based on at least an anomaly alert (e.g., occlusion alert, proximity alert, motion alert) associated with the first object in the first training image; based at least on locating the tag data for the first object, modifying at least a portion of the tag data for the first object from the original simulated data, thereby generating preprocessed training data from the original simulated data; and training a multi-object tracking model with the preprocessed training data to produce a trained multi-object tracker.
Ishani CHAKRABORTY, Jonathan C. HANZELKA, Lu YUAN, Pedro Urbina ESCOS, Thomas M. SOEMO
Filed: 13 Nov 23
Utility
Server Network Resource Reallocation
MSFT
7 Mar 24
A system and method for determining and generating a visualization of processor utilization is described.
Robert Martin TOUGHER, Randy Lehner, Daniel Christopher Gidycz
Filed: 10 Nov 23
Utility
Using a Multi-Task-Trained Neural Network to Guide Interaction with a Query-Processing System via Useful Suggestions
MSFT
29 Feb 24
A computer-implemented technique is described herein for assisting a user in advancing a task objective.
Corby Louis ROSSET, Chenyan XIONG, Paul Nathan BENNETT, Saurabh Kumar TIWARY, Daniel Fernando CAMPOS, Xia SONG, Nicholas Eric CRASWELL
Filed: 7 Nov 23
Utility
Contextual Messaging In Video Conference
MSFT
29 Feb 24
Generally discussed herein are devices, systems, and methods for contextual messaging in a conference.
Ryen William White, Peter Bailey
Filed: 7 Nov 23
Utility
ndvekl6w2v6wcukedd9dfxz52n2we7 a3ohljdep29iq1c2w5w
MSFT
29 Feb 24
Methods, systems, apparatuses, and computer-readable storage mediums are described for rendering document changes.
Rhys Martin SCHMIDTKE, Nimesha MUTHYA, James ZHANG
Filed: 7 Nov 23
Utility
0ox0pyu31a56gmc8wsydw3uze22jo2rlioygrw p6gqv
MSFT
29 Feb 24
A wearable computing device, including a device body, an inertial measurement unit (IMU), and a processor.
Evan Gregory LEVINE
Filed: 6 Nov 23
Utility
qc0qze9 s60zjtgn66v01zrbw52ywl6eo9qoflbuw
MSFT
29 Feb 24
Disclosed in some examples are methods, systems, devices, and machine-readable mediums which utilize digital tracking tags attached to data to monitor and/or control the data as it moves between applications and/or computing devices.
William James BLISS
Filed: 6 Nov 23
Utility
wv049h246pbzb2rm4qruzp0o2qbiimse8toy0wxk ilhivpariwxtgx9w3
MSFT
29 Feb 24
A system for generating depth information from low-resolution images is configured to access a plurality of image frames capturing an environment, identify a first group of image frames from the plurality of image frames, and generate a first image comprising a first composite image of the environment using the first group of image frames as input.
Michael BLEYER, Christopher Douglas EDMONDS, Antonios MATAKOS, Raymond Kirk PRICE
Filed: 6 Nov 23
Utility
kaigw9rjrfo1wwk714wyyhke
MSFT
7 Mar 24
Innovations for signaling state of a decoded picture buffer (“DPB”) and reference picture lists (“RPLs”).
Gary J. Sullivan, Yongjun Wu
Filed: 3 Nov 23
Utility
vijpw66bwgj4c2fbrd6h
MSFT
22 Feb 24
Disclosed herein are exemplary embodiments of methods, apparatus, and systems for performing content-adaptive deblocking to improve the visual quality of video images compressed using block-based motion-predictive video coding.
Xiaoyan Sun, Zhiwei Xiong, Feng Wu
Filed: 3 Nov 23
Utility
pajiu9ltewe9n6fkwopo7d dcz22t32tcipzt9o4sh9p
MSFT
22 Feb 24
A code generation system uses a non-terminal expansion model and a non-terminal selector model to generate a code sketch to complete a partially-formed source code snippet.
MILTIADIS ALLAMANIS, DAYA GUO, NEELAKANTAN SUNDARESAN, ALEXEY SVYATKOVSKIY
Filed: 3 Nov 23
Utility
sy5mqwptk3zkqqwwoq 3rvimzekwhwtd
MSFT
22 Feb 24
A computing system obtains a first article about a first topic, where the first article references a plurality of entities including a person.
Aman SINGHAL, Deep Narayan DUBEY, Marcelo Medeiros DE BARROS
Filed: 2 Nov 23
Utility
g2bp9g95kbchxijtdbkm
MSFT
7 Mar 24
Techniques and tools for reducing latency in video encoding and decoding by constraining latency due to reordering of video frames, and by indicating the constraint on frame reordering latency with one or more syntax elements that accompany encoded data for the video frames.
Gary J. Sullivan
Filed: 2 Nov 23
Utility
3vb03ozodq67ysjr351xucducpnjqe765
MSFT
22 Feb 24
The present disclosure describes automated generation of early warning predictive insights derived from contextual analysis of user activity data of a distributed software platform.
Shay BEN-ELAZAR, Daniel SITTON, Yossef BEN DAVID, Amnon CATAV, Meitar RONEN, Ori BAR-ILAN
Filed: 2 Nov 23
Utility
u53p25j6v7b6zlqml8em78njq91yxz7alkczzsh
MSFT
22 Feb 24
Distinguishing pattern differences from non-pattern differences.
David Ellis PUGH, Mark Alistair WILSON-THOMAS, Vu Minh LE
Filed: 2 Nov 23
Utility
8k783985zcdrk2thj47ypzm36ohjgseb9r1ztgm05tzcvojec8relt
MSFT
29 Feb 24
Independent refresh rates may be enabled for multiple monitors.
Michael Paul Erich VON HIPPEL, Reiner FINK, Leonardo Esteban BLANCO
Filed: 2 Nov 23
Utility
h6v2l74qg4k1t6x1k4p19q31jtbmt3buc7q96r8xwbohichap76u94n9iv
MSFT
22 Feb 24
Embodiments are directed to techniques for enforcing entitlements used by data privacy pipelines.
Yisroel Gershon Taber, Tomer Turgeman, Ittay Levy Ophir, Lev Rozenbaum, Nerya Cohen
Filed: 1 Nov 23
Utility
dgd8xnuj51h7anr3tka4ucd9c5jxew7lfvsxozyh7480w47wm
MSFT
22 Feb 24
A new processing architecture is described that utilizes a data processing unit (DPU).
Pradeep Sindhu, Jean-Marc Frailong, Wael Noureddine, Felix A. Marti, Deepak Goel, Rajan Goyal, Bertrand Serlet
Filed: 1 Nov 23
Utility
zl5odtg 230a4zrjairmlxakv0xnbv4tqhy
MSFT
22 Feb 24
A “Content Optimizer” applies a machine-learned relevancy model to predict levels of interest for segments of arbitrary content.
Jacob M. HOFMAN
Filed: 31 Oct 23