MICROSOFT TECHNOLOGY LICENSING, LLC patent applications on March 6th, 2025
Patent Applications by MICROSOFT TECHNOLOGY LICENSING, LLC on March 6th, 2025
MICROSOFT TECHNOLOGY LICENSING, LLC: 42 patent applications
MICROSOFT TECHNOLOGY LICENSING, LLC has applied for patents in the areas of G06F40/40 (6), G06F40/30 (3), G06N3/0455 (3), G06F3/01 (2), G06F9/445 (2) G06F40/40 (3), H04L41/0631 (2), C12Q1/6834 (1), G06T13/40 (1), G06Q10/063 (1)
With keywords such as: data, user, based, input, application, processing, language, include, matrix, and container in patent application abstracts.
Patent Applications by MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor(s): Karin STRAUSS of Seattle WA (US) for microsoft technology licensing, llc, Bichlien Hoang NGUYEN of Seattle WA (US) for microsoft technology licensing, llc
IPC Code(s): C12Q1/6834, C07H21/04, C07H99/00, C07K1/04, C07K1/10, C07K14/00, C07K17/00, C07K17/02, C07K17/08, C07K19/00
CPC Code(s): C12Q1/6834
Abstract: selectively controllable cleavable linkers include electrochemically-cleavable linkers, photolabile linkers, thermolabile linkers, chemically-labile linkers, and enzymatically-cleavable linkers. selective cleavage of individual linkers may be controlled by changing local conditions. local conditions may be changed by activating electrodes in proximity to the linkers, exposing the linkers to light, heating the linkers, or applying chemicals. selective cleaving of enzymatically-cleavable linkers may be controlled by designing the sequences of different sets of the individual linkers to respond to different enzymes. cleavable linkers may be used to attach polymers to a solid substrate. selective cleavage of the linkers enables release of specific polymers from the solid substrate. cleavable linkers may also be used to attach protecting groups to the ends of growing polymers. the protecting groups may be selectively removed by cleavage of the linkers to enable growth of specific polymers.
Inventor(s): Dragomir Dimitrov YANKOV of Palo Alto CA (US) for microsoft technology licensing, llc, Chiqun ZHANG of Sunnyvale CA (US) for microsoft technology licensing, llc, Antonios KARATZOGLOU of San Francisco CA (US) for microsoft technology licensing, llc, Helen Alta CRAIG of Palo Alto CA (US) for microsoft technology licensing, llc
IPC Code(s): G01C21/34, G06F16/29, G06F40/284, G06F40/40
CPC Code(s): G01C21/3407
Abstract: a technique for interacting with map-related information integrates the use of a machine-trained language model. upon submission of a query, the technique uses the machine-trained language model to assess at least one intent associated with the query. the technique then invokes an intent-specific processing flow to provide an output result. each processing flow invokes the use of at least one processing engine to perform an engine-specific task, such as geocoding, route finding, or image retrieval. a processing flow can also call on the machine-trained language model one or more additional times. in some cases, the technique includes a feedback mechanism for soliciting additional information from a user.
Inventor(s): Gregory Michael LINK of Charlotte NC (US) for microsoft technology licensing, llc, Michaela PORUBANOVA of Seattle WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F3/01, G09G3/00
CPC Code(s): G06F3/013
Abstract: techniques for determining a user's ipd are described. a first stimulus is displayed on a first display, and a second stimulus is displayed on a second display. a stimulus separation distance is a distance that exists between the first and second stimuli. the stimulus separation distance is progressively increased by progressively moving, in opposing directions relative to one another, the first and second stimuli. while that distance is being progressively increased, at least one of the user's eyes is tracked. while the distance is being progressively increased, a change in a rate of eye movement for the user's eye is detected. when the change is detected, a value for the stimulus separation distance is recorded. the recorded value is set as a baseline for the user's ipd.
Inventor(s): Matthias BAER of Seattle WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F3/0481
CPC Code(s): G06F3/0481
Abstract: electronic devices described herein are configured to display updated content associated with a first application having a first user interface element disposed in a background area of a display that is obscured by a second user interface element associated with a second application. responsive to a command from the first application to notify the user of the updated content, the operating system displays at least a portion of a translucent version of the first user interface element with the updated content in the foreground display area, wherein the translucent version of the first user interface element obscures at least a portion of the second user interface element.
Inventor(s): Rajsekhar DAS of Sammamish WA (US) for microsoft technology licensing, llc, Neeraj Kumar SINGH of Seattle WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F3/06
CPC Code(s): G06F3/0659
Abstract: the techniques disclosed herein enable systems to efficiently interface with zoned namespace (zns) storage devices through a specialized management entity. to achieve this, the management entity receives write requests from a file system containing data intended for storage at the zns device. in response, the management entity selects a zone from the zns device to write the file data to. accordingly, the file data is written by appending the file data to the zone at a location indicated by a write pointer. when the write operation is completed, the offset of the file data within the zone is observed and recorded by the file system in file metadata. in contrast to typical systems which allocate locations at the storage device prior to writing, appending file data and then recording the location enables improved efficiency in file system operations. namely, that write operations can be issued to the zns device non-serially.
20250077237. GAI TO APP INTERFACE ENGINE_simplified_abstract_(microsoft technology licensing, llc)
Inventor(s): Santhosh Sachindran of Campbell CA (US) for microsoft technology licensing, llc, Barkha A. Bhojak of Smyrna GA (US) for microsoft technology licensing, llc, Nicholas Smith of Walnut Creek CA (US) for microsoft technology licensing, llc, Eric Bollman of Sherman Oaks CA (US) for microsoft technology licensing, llc, Jeffrey Wang of San Francisco CA (US) for microsoft technology licensing, llc, Tamara Llosa-Sandor of Pasadena CA (US) for microsoft technology licensing, llc, Carlos H. Lopez of Westfield NJ (US) for microsoft technology licensing, llc
IPC Code(s): G06F9/445, G06N3/0475
CPC Code(s): G06F9/445
Abstract: embodiments of the disclosed technologies include, responsive to a first use of a first application by a first user, configuring, in a first prompt, at least one instruction based on first application context data and first user context data. the first prompt is stored in a memory that is accessible to the first application and a second application. via the second application, first output of a generative artificial intelligence (gai) model is presented to the first user. based on the first output of the gai model, at least one second use of the first application by the first user, or at least one first use of a third application by the first user, is configured.
Inventor(s): German David OBANDO CHACON of Kirkland WA (US) for microsoft technology licensing, llc, Dayton Ross ELLWANGER of Kirkland WA (US) for microsoft technology licensing, llc, Varun GUPTA of Bellevue WA (US) for microsoft technology licensing, llc, Dhruv Chand MUTTARAJU of Seattle WA (US) for microsoft technology licensing, llc, Jordan Lee MATTHIESEN of Battle Ground WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F9/445, G06F40/284, G06F40/30
CPC Code(s): G06F9/44505
Abstract: some embodiments determine machine configuration intentions from a natural language description of a target machine configuration. intentions are refined to remove ambiguity, and mapped to pre-approved configuration functions and tasks. a machine configuration task list which invokes the pre-approved configuration functions and tasks is generated by a stabilized language model, and is executed to configure a target machine. the requested target machine is produced without requiring a user or admin to spend substantial effort and time customizing the machine and confirming its security and policy compliance.
Inventor(s): William Tigard BAKER of Redmond WA (US) for microsoft technology licensing, llc, Dallas Allen WARREN of Redmond WA (US) for microsoft technology licensing, llc, Aaron Edward DIETRICH of Kirkland WA (US) for microsoft technology licensing, llc, Piyush GUPTA of Sammamish WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F11/263
CPC Code(s): G06F11/263
Abstract: aspects of the disclosure include methods and systems for performing automated fault scenario generation for chaos engineering. aspects include obtaining a configuration of a service under test, obtaining a first plurality of fault scenarios, and applying each of the first plurality of fault scenarios to the service under test. aspects also include recording telemetry data regarding an operation of the service under test under each of the fault scenarios, selecting, based on the telemetry data, a first fault scenario from the fault scenarios, and generating a second plurality of fault scenarios. aspects further include applying each of the second plurality of fault scenarios to the service under test, recording telemetry data regarding the operation of the service under test under each of the second plurality of fault scenarios, and identifying a vulnerability of the service under test based on the recorded telemetry data.
Inventor(s): Peter GROENEWEGEN of Sammamish WA (US) for microsoft technology licensing, llc, Nikola Minkov MIHAYLOV of Redmond WA (US) for microsoft technology licensing, llc, Larissa Marie COX of Seattle WA (US) for microsoft technology licensing, llc, Nicholas Taylor MULLEN of Seattle WA (US) for microsoft technology licensing, llc, Mark Alistair WILSON-THOMAS of Mercer Island WA (US) for microsoft technology licensing, llc, Paul CHAPMAN of Seattle WA (US) for microsoft technology licensing, llc, Kshama Gajraj BAFNA of Woodinville WA (US) for microsoft technology licensing, llc, Abhishek KUMAR of Folsom CA (US) for microsoft technology licensing, llc, Jason CHLUS of Hoboken NJ (US) for microsoft technology licensing, llc, Holly MITCHELL of Bellevue WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F16/215, G06F16/2457, G06F16/951
CPC Code(s): G06F16/215
Abstract: searches based on an incoming ticket identify quality ticket enrichment data using a vector database. language model prompts target particular kinds of quality ticket data. the incoming quality ticket, or a search result ticket, or both, are enriched using enrichment data, such as a user intent identification, a workaround suggestion, a resolution description, a target audience description, a relevance description, an impact description, a description of missing resolution facilitation information, an association between the incoming quality ticket and the search result ticket, a user sentiment identification, a tag suggestion, or a feedback utility estimate. the enrichment reduces engineering and support burdens, and facilitates faster more effective resolution of the problem or the request that is stated or implied in the incoming quality ticket. duplicate tickets are merged or removed. tickets are prioritized. missing problem resolution information is identified and requested sooner.
Inventor(s): Kameswara Venkatesh EMANI of Madison WI (US) for microsoft technology licensing, llc, Avrilia FLORATOU of Sunnyvale CA (US) for microsoft technology licensing, llc, Carlo Aldo CURINO of Woodinville WA (US) for microsoft technology licensing, llc, Karthik Saligrama RAMACHANDRA of Bangalore (IN) for microsoft technology licensing, llc, Alekh JINDAL of Sammamish WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F16/2452, G06F16/2455
CPC Code(s): G06F16/24528
Abstract: systems, methods, and devices are described for performing scalable data processing operations. a queue that includes a translatable portion comprising indications of data processing operations translatable to data queries and a non-translatable portion comprising indications of non-translatable data processing operations is maintained. a determination that a first data processing operation of a first code block statement is translatable to a database query is made. an indication of the first data processing operation is included in the translatable portion of the queue. responsive to a determination that a second data processing operation of a second code block statement is undeferrable, the translatable portion of the queue is compiled into a database query. an execution of the database query to be executed by a database engine to generate a query result is caused. a result dataset corresponding to the query result is transmitted to an application configured to analyze the result dataset.
Inventor(s): Shaily Jignesh FOZDAR of Boston MA (US) for microsoft technology licensing, llc, David Joseph DONAHUE of Cambridge MA (US) for microsoft technology licensing, llc, Fang LIU of Shanghai (CN) for microsoft technology licensing, llc, Noelle Yanhui LI of New York NY (US) for microsoft technology licensing, llc, Abhishek NARAIN of Woodinville WA (US) for microsoft technology licensing, llc, Irene Rogan SHAFFER of Cambridge MA (US) for microsoft technology licensing, llc, Wee Hyong TOK of Redmond WA (US) for microsoft technology licensing, llc, Ehimwenma NOSAKHARE of Newton MA (US) for microsoft technology licensing, llc, Vivek GUPTA of Groton MA (US) for microsoft technology licensing, llc, Gust VERBRUGGEN of Keerbergen (BE) for microsoft technology licensing, llc, Vu Minh LE of Redmond WA (US) for microsoft technology licensing, llc, Jordan Joseph HENKEL of Madison WI (US) for microsoft technology licensing, llc, Avrilia FLORATOU of Sunnyvale CA (US) for microsoft technology licensing, llc, Joyce Yu CAHOON of Woodinville WA (US) for microsoft technology licensing, llc, Richard ANARFI of Boston MA (US) for microsoft technology licensing, llc, Jason Wang of Boston MA (US) for microsoft technology licensing, llc, Daniel MUĂOZ HUERTA of Cambridge MA (US) for microsoft technology licensing, llc, Yan Qiu of Shanghai (CN) for microsoft technology licensing, llc
IPC Code(s): G06F16/25, G06F16/242
CPC Code(s): G06F16/254
Abstract: a computer-implemented method for performing natural language-based data integration includes causing execution of a data integration application on a remote device via a network and causing surfacing of a gui corresponding to the data integration application on a display of the remote device. the method includes receiving, via the gui, a natural language input representing a data integration task, generating, via an llm, a set of ordered activities corresponding to the data integration task represented by the natural language input, and selecting, via the llm, one or more apis for performing each activity within the set of ordered activities. the method also includes generating a data pipeline based on the set of ordered activities and the api(s) for performing each activity, as well as back-translating the data pipeline to a desired data format for execution by the data integration application.
Inventor(s): Ming WU of Kirkland WA (US) for microsoft technology licensing, llc, Yue MA of Issaquah WA (US) for microsoft technology licensing, llc, Yong NI of Bothell WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F16/903, G06F16/9032, G06F16/9038
CPC Code(s): G06F16/90335
Abstract: examples of the present disclosure describe systems and methods for enterprise search that leverage periodically updated user context of an enterprise user for intent understanding and treat a search session as a dialog between the user and a digital assistant to allow multi-modal interaction. for example, a query input by the user may be received from a client application having search functionality and an integrated assistant. a current state of the user context may be leveraged to understand the query. based on the understanding, one or more responsive entities may be retrieved from an enterprise search index as results. based on the results, a response may be generated that includes the results and a prompt to cause the user to further refine the query and/or provide feedback. the response may be provided to the client application for output as part of a search session dialog between the user and assistant.
Inventor(s): Jack David TOBIN of Maynooth (IE) for microsoft technology licensing, llc, Andre Michael McQUAID of Dublin (IE) for microsoft technology licensing, llc
IPC Code(s): G06F16/951, G06F16/955
CPC Code(s): G06F16/951
Abstract: a data processing system for providing a service to extract information from a resource includes: a network interface for communicating over a computer network; a scraper tool to receive user instruction specifying a target resource and to extract content from the specified resource, wherein the user instruction further specifies a desired restructuring of the extracted content; and a prompt generator to structure the extracted content into a prompt for an artificial intelligence (ai) model, the prompt further directing the ai model to restructure the extracted content based on the user instruction. the prompt generator is to call the ai model with the generated prompt. the service is to receive restructured content from the ai model and provide the restructured content to a workstation submitting the user instruction, the restructured content presenting the content of the target resource in a form according to the user instruction.
Inventor(s): Soeren BALKO of Brookfield, QLD (AU) for microsoft technology licensing, llc, Brock Andrew KENZLER of Red Hill, Queensland (AU) for microsoft technology licensing, llc
IPC Code(s): G06F16/958, H04L67/51
CPC Code(s): G06F16/986
Abstract: a device establishes a communications channel between a first web application executing within a first browsing context that is not cross-origin isolated and a second web application executing within a second browsing context that is cross-origin isolated. this includes loading a proxy page within a third browsing context of the web browser, the loading being initiated by the first browsing context, and loading a worker instance using a script provided by the proxy page. content of the proxy page is served from an origin associated with the second web application. the device passes a first message through the communications channel from the first web application to the second web application. the first message requests the performance of a compute job by the second web application. the device also passes, from the second web application to the first web application, a second message that comprises a result of the compute job.
20250077623. ROOT CAUSE TAXONOMY GENERATOR_simplified_abstract_(microsoft technology licensing, llc)
Inventor(s): Zhongkai LIU of Redmond WA (US) for microsoft technology licensing, llc, Lavaleen Kumar JHA of Bothell WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F18/24
CPC Code(s): G06F18/24765
Abstract: systems, methods, apparatuses, and computer program products are disclosed for generating a root cause taxonomy from incident data. top-level classification(s) and incident data are received as inputs. the incident data is processed to generate processed incident data, which is then analyzed to determine patterns in the processed incident data. second-level classification are generated based on the determined patterns, and added to the root cause taxonomy. the root cause taxonomy may then be used to classify incidents in the incident data.
Inventor(s): Jonathan GAZIT of Tel Aviv (IL) for microsoft technology licensing, llc, Dotan PATRICH of Kfar Saba (IL) for microsoft technology licensing, llc, Idan GUTMAN of Givatayim (IL) for microsoft technology licensing, llc
IPC Code(s): G06F21/53
CPC Code(s): G06F21/53
Abstract: methods, systems, and computer storage media for providing container secure computing modes using a container mode management engine of a security management system. a container secure computing mode can include a secure state in which a container operates to prioritize security measures and practices. a container secure computing mode can be assigned to a container instance and enforced via a container security agent. in operation, a container instance is initialized, the container instance is associated with a container security agent having a secure compute mode transition control for the container instance. based on the secure compute mode transition control, the container instance is transitioned into a secure state. a container operation of the container instance is accessed. the execution of the container operation is restricted based on the secure state of the container instance. the secure state is associated with a secure state configuration that supports restricting the container operation.
Inventor(s): Shizhuo ZHANG of Champaign IL (US) for microsoft technology licensing, llc, Xuchao ZHANG of Sammamish WA (US) for microsoft technology licensing, llc, Chetan BANSAL of Seattle WA (US) for microsoft technology licensing, llc, Pedro Henrique Bragioni LAS-CASAS of Belo Horizonte (BR) for microsoft technology licensing, llc, Rodrigo Lopes Cancado FONSECA of Bothell WA (US) for microsoft technology licensing, llc, Saravanakumar RAJMOHAN of Redmond WA (US) for microsoft technology licensing, llc
IPC Code(s): G06F40/30, G06F16/38
CPC Code(s): G06F40/30
Abstract: a confidence estimation tool uses a calibrated confidence mapping model to estimate confidence for a model-generated candidate root cause. the tool uses a generative artificial intelligence (âaiâ) model to determine, based on a description of a current event, a candidate root cause of the current event. the tool determines a description-based confidence score using the description of the current event and descriptions of a set of relevant historical events in a target domain. the tool also determines a cause-based confidence score using the candidate root cause of the current event and root causes of the set of relevant historical events. finally, the tool determines a final confidence score using the description-based and cause-based confidence scores. even if the generative ai model is configured for general-domain applications, by referencing relevant historical events, the tool can accurately estimate confidence for a model-generated candidate root cause within the target domain.
Inventor(s): Elizabeth Rose JESTER of Edmonds WA (US) for microsoft technology licensing, llc, Daniel Steven LECLAIR of Kenmore WA (US) for microsoft technology licensing, llc, Poonam Ganesh HATTANGADY of Seattle WA (US) for microsoft technology licensing, llc, Telmen Gerel DZJIND of Redmond WA (US) for microsoft technology licensing, llc, Sivaprasad Radhakrishnan LAKSHMI of Dublin CA (US) for microsoft technology licensing, llc
IPC Code(s): G06F40/40, G06F40/174, G06F40/279, H04L51/02, H04L51/063, G06F3/0482, G06F3/0484
CPC Code(s): G06F40/40
Abstract: the technology relates to systems and methods for generating advanced feedback for a draft message. the operations may include receive text for a message being drafted in a messaging application; upon an analysis condition being satisfied, analyze the message by applying at least one of a message-analysis model or heuristic to generate a feedback score for the message; and based on the feedback score crossing a feedback threshold, trigger generation of advanced feedback for the message. the operations may also or alternatively include receive an initial sent message from a messaging application; analyze the message by applying at least one of a message-analysis model or heuristic to generate a feedback score for the message; based on the feedback score crossing a feedback threshold, transmit a feedback alert message for surfacing in the messaging application; and based on receiving an interaction, trigger generation of advanced feedback for the message.
Inventor(s): Xilun Chen of Sunnyvale CA (US) for microsoft technology licensing, llc, Tzu Ming Kuo of Jersey City NJ (US) for microsoft technology licensing, llc, Xiaoqiang Luo of Cos Cob CT (US) for microsoft technology licensing, llc, Ilya Dan Melamed of New York NY (US) for microsoft technology licensing, llc, Ji Yan of San Jose CA (US) for microsoft technology licensing, llc, Peide Zhong of San Jose CA (US) for microsoft technology licensing, llc
IPC Code(s): G06F40/40, G06N20/20
CPC Code(s): G06F40/40
Abstract: embodiments of the disclosed technologies are capable of a training pipeline to fine-tune a machine learning model given a limited set of domain-specific data. the embodiments describe using a first machine learning model to generate a pseudo label associated with a domain-specific training document. the pseudo label comprises a machine-generated text of a content type extracted from the domain-specific training document. the embodiments further describe fine-tuning a second machine learning model using the pseudo label, the domain-specific training document, a first low-rank weight matrix, and a second low-rank weight matrix. the fine-tuned second machine learning model generates text of the content type from a domain-specific document.
Inventor(s): Brian Scott KRABACH of Snohomish WA (US) for microsoft technology licensing, llc, Paul Robert PAYNE of Seattle WA (US) for microsoft technology licensing, llc, Samuel Edward SCHILLACE of Portola Valley CA (US) for microsoft technology licensing, llc
IPC Code(s): G06F40/40, G06F16/35
CPC Code(s): G06F40/40
Abstract: a computing system for monitoring language model compliance with a rubric of one or more output characteristics. the computing system includes processing circuitry configured to interface with a trained generative language model that receives input of a prompt including natural language text input and, in response, generates an output that includes natural language text output. the processing circuitry is further configured to monitor compliance of the generative language model with the rubric, by feeding the output of the generative language model to a rubric classifier configured to generate a predicted classification for an output characteristic in the rubric, and output the predicted classification.
Inventor(s): Jianzhe LIN of Bellevue WA (US) for microsoft technology licensing, llc, Maurice DIESENDRUCK of Bellevue WA (US) for microsoft technology licensing, llc, Manqing MAO of Kenmore WA (US) for microsoft technology licensing, llc, Yijian XIANG of Redmond WA (US) for microsoft technology licensing, llc, Julia T. CHEN of Bellevue WA (US) for microsoft technology licensing, llc, Paishun TING of Kirkland WA (US) for microsoft technology licensing, llc, Mingyang XU of Kenmore WA (US) for microsoft technology licensing, llc, Liang DU of Redmond WA (US) for microsoft technology licensing, llc, Robin ABRAHAM of Redmond WA (US) for microsoft technology licensing, llc
IPC Code(s): G06N3/0455, G06N3/0475
CPC Code(s): G06N3/0455
Abstract: the present disclosure relates to efficiently receiving and processing input tasks in a way that is scalable and which reduces both the quantity of tokens processed by a foundation model (e.g., an llm) as well as the number of api calls that are made in processing the input tasks. a system batches a set of inputs to provide as a single batch of input(s) into an llm. the system generates one or more permutations of the batched input(s) to determine outputs based on variable orders in which the input data is provided within the respective permutations of the batched inputs. the system further may eliminate one or more of the data inputs within the respective batches to facilitate smaller batched inputs without sacrificing accuracy in a set of outputs generated by the llm responsive to the batch permutations.
Inventor(s): Ashraf Ayman MICHAIL of Kirkland WA (US) for microsoft technology licensing, llc
IPC Code(s): G06N3/082, G06N3/0455
CPC Code(s): G06N3/082
Abstract: methods are described for improving processing and storage efficiencies in large language models (llms) while also improving numerical accuracy. the methods are referred as distribution encoding. the disclosed distribution encoding techniques exploit the non-uniform distribution of model weights to provide improved numerical accuracy and compression, and consequently can reduce the number of gpu's needed for inferencing. this in turn enables the reduction of resources and cost necessary to implement such models.
Inventor(s): Andreas Christian Mueller of Los Gatos CA (US) for microsoft technology licensing, llc, Carlo Aldo Curino of Woodinville WA (US) for microsoft technology licensing, llc, Raghunath Ramakrishnan of Bellevue WA (US) for microsoft technology licensing, llc
IPC Code(s): G06N3/084, G06N3/045
CPC Code(s): G06N3/084
Abstract: a method, computer program product, and computing system for processing training data and prediction data as a plurality of tokens using a classification-based machine learning model. a plurality of weighting features associated with the training data and the prediction data are defined by processing the output of the machine learning model with an attention layer. the plurality of weighting features are reshaped to generate weights for a trained neural network by processing the plurality of weighting features with an attention layer.
Inventor(s): Vadym KLIUCHNIKOV of Ontario (CA) for microsoft technology licensing, llc
IPC Code(s): G06N10/20, G06F17/16
CPC Code(s): G06N10/20
Abstract: aspects of the disclosure include decomposing a matrix for a clifford unitary into a product of first and second involution matrices, determining first symplectic matrix that transforms first involution matrix into a first matrix, a first clifford unitary matrix being described by first symplectic matrix, and determining second symplectic matrix that transforms second involution matrix into second matrix, a second clifford unitary matrix being described by second symplectic matrix. aspects include, responsive to first matrix being a diagonal matrix, setting a second number to size of first matrix and setting a second sequence to include the second number of generalized s gates, and responsive to second matrix being a diagonal matrix, setting a first number to size of second matrix and setting a first sequence to include the first number of generalized s gates. aspects include executing first sequence, second sequence, and a pauli unitary p on the quantum computer.
Inventor(s): Ashraf Ayman MICHAIL of Kirkland WA (US) for microsoft technology licensing, llc
IPC Code(s): G06N20/00, G06F7/499
CPC Code(s): G06N20/00
Abstract: methods are described for improving processing and storage efficiencies in large language models (llms) while also improving numerical accuracy. the methods are referred as distribution encoding. the disclosed distribution encoding techniques exploit the non-uniform distribution of model weights to provide improved numerical accuracy and compression, and consequently can reduce the number of gpu's needed for inferencing. this in turn enables the reduction of resources and cost necessary to implement such models.
Inventor(s): Junxuan LI of Bellevue WA (US) for microsoft technology licensing, llc, Arko Provo MUKHERJEE of Issaquah WA (US) for microsoft technology licensing, llc, Allison RUTHERFORD of Redmond WA (US) for microsoft technology licensing, llc, Sahil BHATNAGAR of Seattle WA (US) for microsoft technology licensing, llc, Ryan Patrick WICKMAN of Arlington TN (US) for microsoft technology licensing, llc
IPC Code(s): G06Q10/063, G06F40/40, G06N3/0455, G06Q10/04
CPC Code(s): G06Q10/063
Abstract: example solutions for using natural language (nl) for complex optimization problems in operations research (or) include: receiving a user input for an or problem; generating an nl prompt based on at least the user input, the nl prompt comprising an objective, a variable, input data, and a constraint; using a large language model (llm), generating a domain-specific language (dsl) passage based on at least the nl prompt, the dsl passage representing the or problem; transpiling the dsl passage into a programming language passage; solving the or problem, wherein solving the or problem comprises executing the programming language passage to generate a problem solution; and generating a report of the problem solution.
Inventor(s): Karlton David POWELL of Lake Stevens WA (US) for microsoft technology licensing, llc, Anatoly CHURIKOV of Bellevue WA (US) for microsoft technology licensing, llc
IPC Code(s): G06T5/00, G06T5/50
CPC Code(s): G06T5/80
Abstract: systems and methods for processing a stream of input images are provided. an example method includes receiving a stream of input images and a pointing angle associated with the stream of input images, wherein each input image in the stream of input images comprises a plurality of pixels; interpolating an effective analytical projection, for each input image of the stream of input images, from a grid of predetermined analytical projections, based on the respective pointing angle and plurality of pixels of each of the input images of the stream of input images, wherein the grid of predetermined analytical projections comprises a plurality of spaces that each correspond to respective predetermined pointing angles; generating a modified stream of input images, by mapping pixels of the input stream of images to projected pixels of the modified stream of images, using the effective analytical projection; and displaying the modified stream of images.
20250078319. Camera Calibration_simplified_abstract_(microsoft technology licensing, llc)
Inventor(s): Hongli DENG of Bellevue WA (US) for microsoft technology licensing, llc, Duong NGUYEN of Bellevue WA (US) for microsoft technology licensing, llc, Gabriel BLANCO SALDANA of Kirkland WA (US) for microsoft technology licensing, llc, Ryan S. MENEZES of Bellevue WA (US) for microsoft technology licensing, llc
IPC Code(s): G06T7/80, G06F3/01, G06T7/55
CPC Code(s): G06T7/80
Abstract: the description relates to cameras, and camera calibration for enhancing user experiences. one example can receive a first image of a user at a first location relative to a camera. the first image can include the user's upper body but does not include the user from head to toe. the example can receive a second image of the user at a second location relative to a camera. the second image can include the user's upper body but does not include the user from head to toe. the example can estimate a distance of the second location from the first location relative to the camera and calibrate a height and tilt angle of the camera from the first image, the second image, and the estimated distance and without a full body image of the user.
Inventor(s): Li CHEN of Redmond WA (US) for microsoft technology licensing, llc, Ji LI of San Jose CA (US) for microsoft technology licensing, llc
IPC Code(s): G06T11/20, G06F40/40, G06T5/00, G06T7/50
CPC Code(s): G06T11/203
Abstract: systems and methods for generating custom art fonts with consistent style include receiving user input that identifies a base font style for a custom font and includes descriptive text that defies one or more text effects to use for the custom font. depth maps are selected for characters to be included in the custom font. the depth maps are preprocessed to add noise to the depth maps. a generative model generates custom font images conditioned with the text prompt and the depth maps. the custom font images are then used to render text on a display screen of a computing device.
Inventor(s): Charan Kumbakonam MOHAN of Bengaluru (IN) for microsoft technology licensing, llc, Parag AGRAWAL of Bengaluru (IN) for microsoft technology licensing, llc, Sourabh MAITY of Hyderabad (IN) for microsoft technology licensing, llc
IPC Code(s): G06T11/60, G06F40/166, G06F40/289, G06F40/30
CPC Code(s): G06T11/60
Abstract: this disclosure presents an image generation system designed to generate a series of contextually-persistent visual images for a text document. for instance, the image generation system utilizes multiple computer-based models, entity identifiers, and visual entity embeddings to create multiple synthetic images for a given text document. these synthetic images share a consistent theme and style. additionally, the synthetic images include the same characters, places, and objects. indeed, the image generation system implements seamless and consistent visual representations of the entities throughout the text document.
Inventor(s): Mar GONZALEZ FRANCO of Seattle WA (US) for microsoft technology licensing, llc, Payod PANDA of Cambridge (GB) for microsoft technology licensing, llc, Andrew D. WILSON of Seattle WA (US) for microsoft technology licensing, llc, Kori M. INKPEN of Redmond WA (US) for microsoft technology licensing, llc, Eyal OFEK of Redmond WA (US) for microsoft technology licensing, llc, William Arthur Stewart BUXTON of Toronto (CA) for microsoft technology licensing, llc
IPC Code(s): G06T13/40, G06T15/20, G06V20/20, G06V20/40, H04L65/403
CPC Code(s): G06T13/40
Abstract: systems and methods for representing two-dimensional representations as three-dimensional avatars are provided herein. in some examples, one or more input video streams are received. a first subject, within the one or more input video streams, is identified. based on the one or more input video streams, a first view of the first subject is identified. based on the one or more input video streams, a second view of the first subject is identified. the first subject is segmented into a plurality of planar object. the plurality of planar objects are transformed with respect to each other. the plurality of planar objects are based on the first and second views of the first subject. the plurality of planar objects are output in an output video stream. the plurality of planar objects provide perspective of the first subject to one or more viewers.
Inventor(s): Wolfgang Martin PAULI of Seattle WA (US) for microsoft technology licensing, llc, Mario Emil INCHIOSA of San Francisco CA (US) for microsoft technology licensing, llc, Lingzhi ALLEN of Kirkland WA (US) for microsoft technology licensing, llc, Daniel James HAINES of Emmbrook (GB) for microsoft technology licensing, llc, Matthew Anthony William HYDE of Brighton (GB) for microsoft technology licensing, llc
IPC Code(s): G06V10/774, G06V10/26, G06V10/764, G06V10/776, G06V10/82, G06V20/64, G08B21/02
CPC Code(s): G06V10/7747
Abstract: embodiments described herein are directed to an adaptive ai model for 3d object detection using synthetic training data. for example, an ml model is trained to detect certain items of interest based on a training set that is synthetically generated in real time during the training process. the training set comprises a plurality of images depicting containers that are virtually packed with items of interest. each image of the training set is a composite of an image comprising a container that is packed with items of non-interest and an image comprising an item of interest scanned in isolation. a plurality of such images is generated during any given training iteration of the ml model. once trained, the ml model is configured to detect items of interest in actual containers and output a classification indicative of a likelihood that a container comprises an item of interest.
Inventor(s): Nicola Ferri of Reading (GB) for microsoft technology licensing, llc, Felix Weninger of Wellesley MA (US) for microsoft technology licensing, llc, Puming Zhan of Acton MA (US) for microsoft technology licensing, llc
IPC Code(s): G10L15/16, G10L15/14
CPC Code(s): G10L15/16
Abstract: a method, computer program product, and computing system for dynamically adjusting the number of emitted tokens per frame in speech processing systems operating with large stride values. the number of emitted tokens per frame can be dynamically adjusted in speech processing systems operating with large stride values by processing a signal frame according to a time-synchronous beam search technique at a frame rate based on a stride value; determining a hypothesis score for each hypothesis of a set of first information for the signal frame; determining a hypothesis score for each hypothesis of a set of second information for the signal frame; comparing a worst hypothesis score of the set of first information to a sum of a best hypothesis score of the set of second information and a threshold value; and ceasing processing of the signal frame when the worst hypothesis score of the set of first information is greater than the sum of the best hypothesis score of the set of second information and the threshold value.
Inventor(s): Dushyant Sharma of Mountain View CA (US) for microsoft technology licensing, llc, Patrick A. Naylor of Reading (GB) for microsoft technology licensing, llc, Sri Harsha Dumpala of Halifax (CA) for microsoft technology licensing, llc, Chandramouli Shama Sastry of Halifax (CA) for microsoft technology licensing, llc
IPC Code(s): G10L21/02
CPC Code(s): G10L21/02
Abstract: a method, computer program product, and computing system for disentangling background information from speaker information in a speech signal. background information is extracted from the speech signal to generate a background acoustics embedding and speaker information is extracted from the speech signal to generate a speaker acoustics embedding. a first loss factor is applied to the background acoustics embedding to decrease speaker information therein to generate a processed background acoustics embedding using machine learning and a second loss factor is applied to the speaker acoustics embedding to decrease background information therein to generate a processed speaker acoustics embedding using machine learning. at least one of the processed background acoustics embedding and the processed speaker acoustics embedding is output to a speech processing system.
Inventor(s): Judith AMORES FERNANDEZ of Somerville MA (US) for microsoft technology licensing, llc, Seyone CHITHRANANDA of Berkeley CA (US) for microsoft technology licensing, llc, Kevin Kaichuang YANG of Cambridge MA (US) for microsoft technology licensing, llc
IPC Code(s): G16B15/30
CPC Code(s): G16B15/30
Abstract: systems and methods for determining predicted olfactory perception are provided. in particular, a method comprises receiving an input indicating an odorant, generating an odorant vector representing the odorant, generating an olfactory receptor vector, and determining one or more predicted olfactory percepts associated with the odorant based on the odorant vector and the olfactory receptor vector.
Inventor(s): Denizcan BILLOR of Seattle WA (US) for microsoft technology licensing, llc, Jamie GAUDETTE of Kirkland WA (US) for microsoft technology licensing, llc
IPC Code(s): H04J14/02
CPC Code(s): H04J14/0212
Abstract: systems and methods are provided for implementing an ultra-scalable high-performance computing (âhpcâ) network using dense wavelength-division multiplexing (âdwdmâ). the hpc system includes an interconnection of gpu devices, multiplexer/demultiplexer (âmux/demuxâ) devices, amplifiers, wavelength selective switches (âwsssâ), and optical circuit switches (âocssâ). each ocs includes a plurality of micro-electromechanical systems (âmemsâ) mirrors and a plurality of input/output (âi/oâ) ports each communicatively coupled to one wss mux/demux device one wss. each wss mux/demux device is either communicatively coupled to one of the i/o ports of an ocs or one of a plurality of gpu mux/demux devices via an amplifier. each gpu mux/demux device is communicatively coupled to a number of gpu devices, each including another number gpus and one or more optoelectronic devices. selectively controlling the mems mirrors of the ocss and the wss mux/demux devices of the wsss allows connecting the gpus in a network topology for computing a series of computations.
Inventor(s): Di WENG of Beijing (CN) for microsoft technology licensing, llc, Shandan ZHOU of Kirkland WA (US) for microsoft technology licensing, llc, Jue ZHANG of Beijing (CN) for microsoft technology licensing, llc, Bo QIAO of Beijing (CN) for microsoft technology licensing, llc, Si QIN of Beijing (CN) for microsoft technology licensing, llc, Karthikeyan SUBRAMANIAN of Redmond WA (US) for microsoft technology licensing, llc, Thomas MOSCIBRODA of Bellevue WA (US) for microsoft technology licensing, llc
IPC Code(s): H04L41/0631, H04L41/0604, H04L41/22, H04L47/74
CPC Code(s): H04L41/0631
Abstract: interactive analytics are provided for resource allocation failure incidents, which may be tracked, diagnosed, summarized, and presented in near real-time for users and/or platform/service providers to understand the root cause(s) of failure incidents and actual and hypothetical, failed and successful, allocation scenarios. a capacity analyzer simulates an allocation process implemented by a resource allocation platform. the capacity analyzer may determine which resources were and/or were not eligible for allocation for a request, based on information about the resource allocation failure, resources in the region of interest, and constraints associated with the incident, and the resource allocation rules associated with the resource allocation platform. users may quickly learn whether a request constraint, a requesting entity constraint, a capacity constraint, and/or a resource platform constraint caused a resource allocation incident. the capacity analyzer may proactively monitor performance and generate alerts about failed and/or successful requests in which users may be interested.
Inventor(s): Myriam TITON of Jerusalem (IL) for microsoft technology licensing, llc, Rachel LEMBERG of Herzliya (IL) for microsoft technology licensing, llc, Michael ALBURQUERQUE of Tel Aviv-Yafo (IL) for microsoft technology licensing, llc, Yaniv LAVI of Tel Aviv-Yafo (IL) for microsoft technology licensing, llc, Eliya HABBA of Jerusalem (IL) for microsoft technology licensing, llc, Jeremy SAMAMA of Netanya (IL) for microsoft technology licensing, llc, Hagit GRUSHKA of Lehavim (IL) for microsoft technology licensing, llc
IPC Code(s): H04L41/0631, H04L43/08
CPC Code(s): H04L41/0631
Abstract: the disclosure relates to utilizing an anomaly mitigation proposal system to determine root causes, summarize anomalous metrics, and report mitigation actions for service incidents in cloud computing systems. based on receiving an incident report request, the anomaly mitigation proposal system utilizes a two-layer approach that implements large generative language models to generate incident reports that include clear and concise text narratives summarizing metric anomalies, root causes, and corresponding mitigation actions. for example, the anomaly mitigation proposal system initially utilizes an online generative language model to provide these incident reports and, when unavailable within a time threshold, a fallback model that references root cause datastores.
Inventor(s): Laura MITRACHE of Bellevue WA (US) for microsoft technology licensing, llc, Martin TOMKA of Prague (CZ) for microsoft technology licensing, llc, Juraj BLAŽEK of Prague (CZ) for microsoft technology licensing, llc, Stephen TOUB of Winchester MA (US) for microsoft technology licensing, llc, Andrey NOSKOV of Prague (CZ) for microsoft technology licensing, llc, Martin TAILLEFER of Redmond WA (US) for microsoft technology licensing, llc, Scott Allen THURLOW of Bellevue WA (US) for microsoft technology licensing, llc, Lukas BARTON of Prague (CZ) for microsoft technology licensing, llc
IPC Code(s): H04L41/0816, H04L41/0604, H04L41/16
CPC Code(s): H04L41/0816
Abstract: some embodiments automatically and proactively adjust network device configuration settings during network operation, based on correlations between device performance and device configuration. correlations are computed using statistics routines or computed by a machine learning module. some embodiments share adjusted configuration values via a cache, and some persist adjusted values through an application restart. in some embodiments, the cache is hierarchical and different kinds of reconfiguration data are shared at different levels. in some embodiments, the configuration value is shared only between application instances that have sufficiently similar contexts. some embodiments detect a correlation loss and fall back to a known good configuration setting or a default configuration setting. some embodiments optimize network internode communications by making dynamic adjustments which are not available from static configuration settings or from static configuration rules.
Inventor(s): Alexander Stephen TOMLIN of Kirkland WA (US) for microsoft technology licensing, llc, Joshua Daniel BAUGHER of Warrenton VA (US) for microsoft technology licensing, llc, Alexander Stephen THIELMAN of Seattle WA (US) for microsoft technology licensing, llc, Matthew Dean SIEVERS of Redmond WA (US) for microsoft technology licensing, llc, Larry Darnell WILCHER, II of Dacula GA (US) for microsoft technology licensing, llc
IPC Code(s): H04L9/40, G06F9/455
CPC Code(s): H04L63/068
Abstract: a virtual machine (vm) test instance is created in a virtual machine scale set. when the vm test instance is created, a unique set of credentials is also created corresponding to the vm test instance. the unique set of credentials is stored in a secret store that is separate from other cloud and organization credentials. when access to a vm test instance is requested by a user, the unique credentials are provided to the user to use the vm test instance for a limited time. when the user is finished using the vm test instance, or when the vm test instance expires, then the vm test instance is destroyed and the unique credentials are also destroyed.
Inventor(s): Jason Thomas FAULKNER of Seattle WA (US) for microsoft technology licensing, llc, Mansoor JAFRY of Seattle WA (US) for microsoft technology licensing, llc, Xonatia Ravelle LEE of Seattle WA (US) for microsoft technology licensing, llc, Chad Aron VOSS of Seattle WA (US) for microsoft technology licensing, llc, Albert ROBLES of Redmond WA (US) for microsoft technology licensing, llc, Timothy James BROOKINS of Fargo ND (US) for microsoft technology licensing, llc
IPC Code(s): H04L65/403, H04L12/18, H04N13/366
CPC Code(s): H04L65/403
Abstract: systems for transitioning a user interface arrangement from a display of a two-dimensional image of a user to a rendering of a three-dimensional representation of the user is provided. a system can start with a ui including a rendering of a user that is based on a 2d image file. the system can receive an input that is configured to cause the system to transition the display of the rendering of the 2d image of the select user to a rendering of the three-dimensional representation of the select user. to display the rendering of the 3d representation of the select user, the system uses permission data and a three-dimensional model defining a position and orientation to display the 3d representation of the user. the system allows users to switch between viewing modes to allow users to interact with content using the most effective type of hardware.
Inventor(s): Shantanu DESAI of Bangalore (IN) for microsoft technology licensing, llc, Kantha Rao DAMMALAPATI of Bangalore (IN) for microsoft technology licensing, llc
IPC Code(s): H04W12/80, H04L1/1607, H04L5/00
CPC Code(s): H04W12/80
Abstract: the present disclosure relates to a packet data units (pdu) reliability system that improves lawful interception (li) network functions in a cloud computing system for a telecommunications network. the pdu reliability system utilizes new components and elements within the network functions of the telecommunications network to improve the reliability and robustness of transmitted pdus. these components include pdu acknowledgment packets, sequence number lists, and pdu receipt timers. for instance, the pdu reliability system utilizes a mediation and delivery function (mdf) to generate pdu acknowledgment packets based on pdus received from a point of interception (poi) application to indicate which pdus have been successfully received during pdu receipt timers. based on the pdu acknowledgment packets, the pdu reliability system causes the poi application to perform one or more pdu actions to ensure the robust and reliable transmission of the pdus.
MICROSOFT TECHNOLOGY LICENSING, LLC patent applications on March 6th, 2025
- MICROSOFT TECHNOLOGY LICENSING, LLC
- C12Q1/6834
- C07H21/04
- C07H99/00
- C07K1/04
- C07K1/10
- C07K14/00
- C07K17/00
- C07K17/02
- C07K17/08
- C07K19/00
- CPC C12Q1/6834
- Microsoft technology licensing, llc
- G01C21/34
- G06F16/29
- G06F40/284
- G06F40/40
- CPC G01C21/3407
- G06F3/01
- G09G3/00
- CPC G06F3/013
- G06F3/0481
- CPC G06F3/0481
- G06F3/06
- CPC G06F3/0659
- G06F9/445
- G06N3/0475
- CPC G06F9/445
- G06F40/30
- CPC G06F9/44505
- G06F11/263
- CPC G06F11/263
- G06F16/215
- G06F16/2457
- G06F16/951
- CPC G06F16/215
- G06F16/2452
- G06F16/2455
- CPC G06F16/24528
- G06F16/25
- G06F16/242
- CPC G06F16/254
- G06F16/903
- G06F16/9032
- G06F16/9038
- CPC G06F16/90335
- G06F16/955
- CPC G06F16/951
- G06F16/958
- H04L67/51
- CPC G06F16/986
- G06F18/24
- CPC G06F18/24765
- G06F21/53
- CPC G06F21/53
- G06F16/38
- CPC G06F40/30
- G06F40/174
- G06F40/279
- H04L51/02
- H04L51/063
- G06F3/0482
- G06F3/0484
- CPC G06F40/40
- G06N20/20
- G06F16/35
- G06N3/0455
- CPC G06N3/0455
- G06N3/082
- CPC G06N3/082
- G06N3/084
- G06N3/045
- CPC G06N3/084
- G06N10/20
- G06F17/16
- CPC G06N10/20
- G06N20/00
- G06F7/499
- CPC G06N20/00
- G06Q10/063
- G06Q10/04
- CPC G06Q10/063
- G06T5/00
- G06T5/50
- CPC G06T5/80
- G06T7/80
- G06T7/55
- CPC G06T7/80
- G06T11/20
- G06T7/50
- CPC G06T11/203
- G06T11/60
- G06F40/166
- G06F40/289
- CPC G06T11/60
- G06T13/40
- G06T15/20
- G06V20/20
- G06V20/40
- H04L65/403
- CPC G06T13/40
- G06V10/774
- G06V10/26
- G06V10/764
- G06V10/776
- G06V10/82
- G06V20/64
- G08B21/02
- CPC G06V10/7747
- G10L15/16
- G10L15/14
- CPC G10L15/16
- G10L21/02
- CPC G10L21/02
- G16B15/30
- CPC G16B15/30
- H04J14/02
- CPC H04J14/0212
- H04L41/0631
- H04L41/0604
- H04L41/22
- H04L47/74
- CPC H04L41/0631
- H04L43/08
- H04L41/0816
- H04L41/16
- CPC H04L41/0816
- H04L9/40
- G06F9/455
- CPC H04L63/068
- H04L12/18
- H04N13/366
- CPC H04L65/403
- H04W12/80
- H04L1/1607
- H04L5/00
- CPC H04W12/80