Microsoft Technology Licensing, LLC patent applications on April 3rd, 2025
Patent Applications by Microsoft Technology Licensing, LLC on April 3rd, 2025
Microsoft Technology Licensing, LLC: 41 patent applications
Microsoft Technology Licensing, LLC has applied for patents in the areas of G06F40/40 (4), G06N3/0455 (3), H04L9/40 (3), G06F9/38 (3), H04L41/16 (2) G06N3/0455 (2), H04L63/0236 (2), G06F9/3806 (2), G06F40/18 (2), G06F40/40 (2)
With keywords such as: data, branch, target, device, prompt, memory, based, optical, input, and computing in patent application abstracts.
Patent Applications by Microsoft Technology Licensing, LLC
Inventor(s): Adwaita Anil DANI of Redmond WA US for microsoft technology licensing, llc, Manish Keshrichand SHAH of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): F04D29/66, F04D27/00, G06F1/20, G06T7/70
CPC Code(s): F04D29/661
Abstract: systems and methods are disclosed where a user's position with respect to an electronic device including a fan is detected. a noise of the fan perceived by a user based on the user's position with respect to the electronic device is detected. a determination whether increased thermal dissipation is required is made and whether the noise of the fan perceived by the user is below a noise threshold. the system may increase fan speed if both increased thermal dissipation is required and if the noise of the fan is below the noise threshold.
Inventor(s): Binbin GUAN of Issaquah WA US for microsoft technology licensing, llc, Jamie GAUDETTE of Kirkland WA US for microsoft technology licensing, llc, Yawei YIN of Redmond WA US for microsoft technology licensing, llc, Denizcan BILLOR of Seattle WA US for microsoft technology licensing, llc
IPC Code(s): G02B6/293, G02B6/27, G02B6/32, G02B17/00
CPC Code(s): G02B6/2938
Abstract: a high-power multiplexer/demultiplexer (“mux/demux”) and a three-dimensional (“3d”) printed phase mask are provided for hollow-core optical fiber applications. the high-power mux/demux includes hollow core optical fiber interfaces configured to couple with free-space optical fiber cables, a diffraction grating, a 3d printed phase mask, and a set of lenses. the diffraction grating is configured, based on different wavelengths, either to at least diffract each optical signal of a plurality of optical signals having different wavelengths into two or more optical signals or to at least diffract a single optical signal having multiple wavelengths into a plurality of optical signals. the phase mask includes reflective features configured to reflect optical signals at different optical path lengths to provide reflected optical signals with different phases. the set of lenses is configured to collimate optical signals onto or from the diffraction grating or to focus optical signals onto or from the phase mask.
Inventor(s): Binbin GUAN of Issaquah WA US for microsoft technology licensing, llc, Denizcan BILLOR of Seattle WA US for microsoft technology licensing, llc, Jamie Dorea GAUDETTE of Kirkland WA US for microsoft technology licensing, llc, Yawei YIN of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): G02B6/32, G01M11/00, G02B6/293, G02B27/09, G02B27/28
CPC Code(s): G02B6/32
Abstract: a device for transmitting data from a plurality of solid core optical fibers to a hollow core fiber comprises a multiplexer; a first 4f optical system that is operative to receive the light output from the multiplexer; an amplifier disposed downstream of the first 4f optical system and upstream of a second 4f optical system, where the second 4f optical system is operative to receive amplified light output from the amplifier and output the amplified light to the hollow core fiber in a form that is compatible with the hollow core fiber.
Inventor(s): Denizcan BILLOR of Seattle WA US for microsoft technology licensing, llc, Jamie Dorea GAUDETTE of Kirkland WA US for microsoft technology licensing, llc, Yawei YIN of Redmond WA US for microsoft technology licensing, llc, Binbin GUAN of Issaquah WA US for microsoft technology licensing, llc
IPC Code(s): G02B6/42, G02B6/02
CPC Code(s): G02B6/4296
Abstract: a system for transmitting a light signal between a first solid core optical fiber network and a hollow core fiber network includes a plurality of transponder-amplifiers, where each transponder-amplifier of the plurality of transponder-amplifiers comprises a transponder in optical communication with one of a power amplifier and a pre-amplifier. the plurality of transponder-amplifiers is in optical communication with the first solid core optical fiber network and is operative to receive a plurality of first light signals from the plurality of transponder amplifiers. a multiplexer located downstream of the plurality of transponder-amplifiers is operative to receive the plurality of first light signals. the multiplexer is operative to select between a plurality of first light signals and transmits at least one light signal of the plurality of first light signals to the hollow core fiber network.
Inventor(s): Julio Gago Alonso of Barcelona ES for microsoft technology licensing, llc, Santiago Galan of Molins de Rei ES for microsoft technology licensing, llc, Antonio Juan Hormigo of Barcelona ES for microsoft technology licensing, llc, Ivan Pizarro of Hospitalet de Llobregat ES for microsoft technology licensing, llc
IPC Code(s): G06F9/38, G06F9/30
CPC Code(s): G06F9/3806
Abstract: improved branch target buffer (btb) structures are provided. a device can include branch target buffers storing entries corresponding to branch instructions and corresponding targets of the branch instructions. the device can include a victim cache storing a branch target buffer entry that has been evicted from a branch target buffer of the branch target buffers. the device can include branch prediction circuitry configured to access the victim cache responsive to receiving respective miss indications from each branch target buffer of the branch target buffers.
Inventor(s): Julio GAGO ALONSO of Barcelona ES for microsoft technology licensing, llc, Santiago GALAN of Molins de Rei ES for microsoft technology licensing, llc, Antonio JUAN HORMIGO of Barcelona ES for microsoft technology licensing, llc, Ivan PIZARRO of Hospitalet de Llobregat ES for microsoft technology licensing, llc
IPC Code(s): G06F9/38
CPC Code(s): G06F9/3806
Abstract: a branch prediction system is configured to perform a method that includes identifying processor branch instructions and building branch target buffer (btb) branch prediction entries corresponding to the branch instructions. the btb branch prediction entries are stored in a hierarchy of btbs. target branch instruction are identified that have a target btb entry following execution of a first branch instruction having a first btb branch prediction entry. a target btb entry reference is added to the first btb branch prediction entry.
Inventor(s): Julio GAGO ALONSO of Barcelona ES for microsoft technology licensing, llc, Santiago GALAN of Molins de Rei ES for microsoft technology licensing, llc, Ivan PIZARRO of Hospital de Llobregat ES for microsoft technology licensing, llc
IPC Code(s): G06F9/38
CPC Code(s): G06F9/3844
Abstract: a branch prediction device includes a hierarchy of successively slower to access branch target buffers that store branch target buffer entries identifying branch instructions, branch prediction circuitry configured to predict future branch instructions, and a branch target buffer prefetch table coupled to receive candidate entries corresponding to predicted future branch instruction branch target buffer misses, each entry of the candidate entries corresponding to a precursor branch instruction, and to receive predicted precursor branch instructions that trigger promotion of an entry in a branch target buffer of the branch target buffers to a faster branch target buffer of the branch target buffers.
Inventor(s): Scott Gregory WASSON of Millbury MA US for microsoft technology licensing, llc, Bhaskar Rao AMBEKAR of Westford MA US for microsoft technology licensing, llc
IPC Code(s): G06F9/455
CPC Code(s): G06F9/45558
Abstract: the present disclosure relates to systems, methods, and computer-readable media for determining whether a pinning misconfiguration exists between one or more virtual cores (e.g., vcpus) and physical cores on a computing device. in particular, the present disclosure involves virtual cores of an application or cloud-based service (e.g., a virtual machine) that runs machine loops on bursts of data packets that are assigned to the virtual core(s) and determines whether a delay has occurred in processing the packets. based on this delay, the disclosure discusses determining whether a pinning misconfiguration exists as a result of the physical core being mistakenly over-allocated to multiple virtual cores by the hypervisor of the computing device.
Inventor(s): Aobo GUAN of Redmond WA US for microsoft technology licensing, llc, Tristan Anthony BROWN of Houston TX US for microsoft technology licensing, llc, Tapan ANSEL of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): G06F9/48, G06F9/50
CPC Code(s): G06F9/4893
Abstract: examples of the present disclosure describe systems and methods for heterogeneous scheduling for processors with multiple core types. in some examples, a scheduler assigns thread policies to respective threads. the scheduler then allocates the threads to heterogeneous cores in accordance with the thread policies assigned to the respective threads. the heterogeneous cores include one or more power efficient cores, one or more intermediate cores, and one or more performance-oriented cores, among other core types. in some examples, a core parking engine determines how many cores should be unparked for one or more power efficient cores, one or more intermediate cores, and one or more performance-oriented cores, among other core types.
Inventor(s): Ram Kumar Donthula of Bothell WA US for microsoft technology licensing, llc, Amber Bhargava of Issaquah WA US for microsoft technology licensing, llc, Anand Rengasamy of Bothell WA US for microsoft technology licensing, llc, Wilco Gerardus Bernardus Bauwer of Renton WA US for microsoft technology licensing, llc, Grzegorz Andrzej Zygmunt of Sammamish WA US for microsoft technology licensing, llc, Jagdish Singh of Kirkland WA US for microsoft technology licensing, llc
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5005
Abstract: example aspects include techniques for providing an auditable mechanism for internal services to transact on tenant entities. these techniques may include receiving, from an internal service, by an assistant service, a service request to perform a cloud computing action over tenant data of a tenant of a cloud computing environment. in addition, the techniques may include identifying, by the assistant service, an existing principal of the assistant service within the tenant and possession of an existing permission associated with performing the cloud computing action within the tenant of the cloud computing environment. further, the techniques may include performing the cloud computing action on behalf of the internal service based on identifying the existing principal and possession of the existing permission.
Inventor(s): Majid Anaraki Nemati of San Diego CA US for microsoft technology licensing, llc, Terry M. Grunzke of Boise ID US for microsoft technology licensing, llc, Brett K. Dodds of Boise ID US for microsoft technology licensing, llc
IPC Code(s): G06F11/10, G06F5/01
CPC Code(s): G06F11/1004
Abstract: a method, computer program product, and computing system for generating first encoded data by performing a first encoding of data included within each of a plurality of memory dies of a memory module using an exclusive-or (xor) encoding process. second encoded data is generated by performing a second encoding of the data included within each of the plurality of memory dies of the memory module and the first encoded data using a cyclic code encoding process. error correction is performed on the data included within each of the plurality of memory dies of the memory module using the first encoded data, the second encoded data, an xor decoding process, and a cyclic code error correction process.
Inventor(s): Ishwar AGARWAL of Redmond WA US for microsoft technology licensing, llc, George Zacharias CHRYSOS of Portland WA US for microsoft technology licensing, llc, Oscar ROSELL MARTINEZ of Barcelona ES for microsoft technology licensing, llc
IPC Code(s): G06F11/10, G06F3/06, G06F11/14, G06F12/0811
CPC Code(s): G06F11/1068
Abstract: techniques of memory tiering in computing devices are disclosed herein. one example technique includes retrieving, from a first tier in a first memory, data from a data portion and metadata from a metadata portion of the first tier upon receiving a request to read data corresponding to a system memory section. the method can then include analyzing the data location information to determine whether the first tier currently contains data corresponding to the system memory section in the received request. in response to determining that the first tier currently contains data corresponding to the system memory section in the received request, transmitting the retrieved data from the data portion of the first memory to the processor in response to the received request. otherwise, the method can include identifying a memory location in the first or far memory that contains data corresponding to the system memory section and retrieving the data from the identified memory location.
Inventor(s): Julio GAGO ALONSO of Barcelona ES for microsoft technology licensing, llc, Santiago Galan of Molins de Rei ES for microsoft technology licensing, llc, Antonio Juan Hormigo of Barcelona ES for microsoft technology licensing, llc, Ivan Pizarro of Hospitalet de Llobregat ES for microsoft technology licensing, llc
IPC Code(s): G06F12/0891, G06F12/0877
CPC Code(s): G06F12/0891
Abstract: branch target buffer structures are provided. a device can include a hierarchy of branch target buffers storing entries corresponding to branch instructions, the hierarchy of branch target buffers including respective branch target buffers that have progressively slower access times. the device can include a first program counter configured to generate a first program counter value associated with a next instruction of an executing application. the device can include a second program counter configured to predict a second program counter value that is associated with a subsequent instruction of the executing application that is after the next instruction. the device can include first branch prediction circuitry configured to populate a branch target buffer of the branch target buffers based on the second program counter value.
Inventor(s): Julia Jacinta BUSONO of Woodinville WA US for microsoft technology licensing, llc, Robert Glenn RUNDELL of Bellevue WA US for microsoft technology licensing, llc
IPC Code(s): G06F13/38
CPC Code(s): G06F13/385
Abstract: a method of providing data communication between a first device and a second device includes, establishing a first communication link with a downstream device connected to the second device using a first mode via a usb-type interface, wherein in the first mode the usb-type interface utilizes a first set of usb communication lanes; establishing a second communication link with the first device via the usb-c port using an alternate mode wherein the alt-mode utilizes the first set of usb communication lanes; and, in accordance with establishing the second communication link, changing a mode of the first communication link so that the first communication link does not communicate via the first set of usb communication lanes.
Inventor(s): Victor Chukwuma DIBIA of Santa Clara CA US for microsoft technology licensing, llc, Chenglong WANG of Bellevue WA US for microsoft technology licensing, llc, Bongshin LEE of Issaquah WA US for microsoft technology licensing, llc, Jeevana Priya INALA of Redmond WA US for microsoft technology licensing, llc, John THOMPSON of Atlanta GA US for microsoft technology licensing, llc
IPC Code(s): G06F16/215
CPC Code(s): G06F16/215
Abstract: the disclosed concepts relate to leveraging a language model to identify data health issues in a data set. one example method involves accessing a data set. the example method also involves, using an automated evaluation planning agent, inputting a prompt to generate a data evaluation plan for the data set to a generative language model, the prompt including context describing the data set. the example method also involves receiving the data evaluation plan generated by the generative language model and identifying one or more data health issues in the data set by performing the data evaluation plan using an automated evaluation plan execution agent.
Inventor(s): Manish R. Baldua of San Jose CA US for microsoft technology licensing, llc, Daniel K. Hewlett of Clarksville MD US for microsoft technology licensing, llc, Gregory E. Pounds of San Jose CA US for microsoft technology licensing, llc, Xie Lu of Sunnyvale CA US for microsoft technology licensing, llc, Jonathan Pohl of Concord MA US for microsoft technology licensing, llc, Peter Rigano of San Francisco CA US for microsoft technology licensing, llc
IPC Code(s): G06F16/2453, G06F16/242, G06F40/40
CPC Code(s): G06F16/24542
Abstract: embodiments of the disclosed technologies include receiving a first query including at least one first query term and configuring at least one prompt to cause a large language model to translate the at least one first query term into a set of functions that can be executed to obtain at least one second query term and generate and output a plan that is executable to create a modified version of the first query based on the at least one second query term. the plan is obtained by applying the large language model to the at least one prompt as configured. the plan is executed to determine the at least one second query term and create the modified version of the first query. the modified version of the first query is executed to provide, via the user interface, a response to the first query.
Inventor(s): Ion TODIREL of Bellevue WA US for microsoft technology licensing, llc, Bogdan Ionut MIHALCEA of Sammamish WA US for microsoft technology licensing, llc, Benjamin John MCMORRAN of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): G06F16/34, G06F3/0488, G06F8/33, G06F40/30
CPC Code(s): G06F16/345
Abstract: techniques are described herein that are capable of controlling and/or visualizing context of an artificial intelligence prompt. a user-generated artificial intelligence prompt is detected. in a first technique, a visual representation of contextual information, which includes context regarding the prompt, is generated. based at least on detection of a user-generated instruction, presentation of the visual representation is triggered. in a second technique, a determination is made that an initial scope of contextual information, which includes context regarding the prompt, includes previous contextual information, which includes context regarding a previous user-generated prompt in a prompt chain that includes the prompt. the initial scope of the contextual information is automatically changed to provide a changed scope that does not include at least a portion of the previous contextual information. an artificial intelligence model is caused to generate an answer to the prompt that is based on the changed scope.
Inventor(s): Justin James WAGLE of Pacifica CA US for microsoft technology licensing, llc, Rogerio BONATTI of Bellevue WA US for microsoft technology licensing, llc
IPC Code(s): G06F16/583, G06F40/30, G06V10/82
CPC Code(s): G06F16/5846
Abstract: large language models (llms) are able to provide robust results based on specified formatting and organization. traditionally, however, users must form detailed queries to obtain desired results in a desired format. accordingly, although llms are designed to receive natural language input, users often lack the skill, knowledge, or patience to utilize llms to their full potential. ambient information and user history associated with device screenshots are leveraged to provide proactive artificial-intelligence (ai) assistance and query resolution in an llm environment. in particular, screenshots associated with a computer display are continuously captured and analyzed to detect activity triggers for plugins, for example. in response to detecting an activity trigger, local context associated with one or more prior screenshots is collected. the collected context is then used to inform the plugin for performing the task, thereby reducing the burden placed on the user to input the required information.
Inventor(s): Ryen William White of Woodinville WA US for microsoft technology licensing, llc
IPC Code(s): G06F16/953
CPC Code(s): G06F16/953
Abstract: multi-modal search systems with improved search request routing are provided. a device can include a module that identifies, based on content of a search request, provider criterion that indicates factors to be considered in making a routing decision, a criterion processor that determines, based on the provider criterion, a routing decision indicating whether to route the search request to a search engine or a chat engine based, at least in part, respective compute costs of servicing the search request using the search engine and the chat engine, respectively, and respective accuracies of responses provided responsive to the search request using the search engine and the chat engine, respectively, and an output port coupled to receive the search request and to provide the search request to the search engine or the chat engine in accord with the routing decision.
Inventor(s): Sean Michael FROHMAN of Seattle WA US for microsoft technology licensing, llc, Scott FUDALLY of Redmond WA US for microsoft technology licensing, llc, Robert D. YOUNG of Kirkland WA US for microsoft technology licensing, llc, Henri A. AUTIO of Kirkland WA US for microsoft technology licensing, llc, Augustus TERTZAKIAN of Kirkland WA US for microsoft technology licensing, llc, David ABZARIAN of Kenmore WA US for microsoft technology licensing, llc, Hamza MUSTAFA of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): G06F21/35, H04W12/08, H04W12/33, H04W12/63
CPC Code(s): G06F21/35
Abstract: a computing device is disclosed that exchanges wireless communications with a wearable device and processes the communications to determine the position and direction of motion of the wearable device, and the authentication status of the wearable device. the device then grants access based on these determinations. the wearable device authenticates a user and communicates with the user computing device to enable determination of its position, motion direction, and authentication status. also disclosed are methods for user authentication and de-authentication based on user presence and absence.
Inventor(s): Ishwar AGARWAL of Redmond WA US for microsoft technology licensing, llc, Stefan SAROIU of Redmond WA US for microsoft technology licensing, llc, Alastair WOLMAN of Seattle WA US for microsoft technology licensing, llc, Daniel Sebastian BERGER of Seattle WA US for microsoft technology licensing, llc
IPC Code(s): G06F21/55, G11C8/20, G11C11/406
CPC Code(s): G06F21/554
Abstract: the present disclosure relates to systems and methods implemented on a memory controller for detecting and mitigating memory attacks (e.g., row hammer attacks). for example, a memory controller may track activations of row addresses within a memory hardware (e.g., a dram device) and determine whether a pattern of activations is indicative of a row hammer attack. this is determined using a counting mode for corresponding memory sub-banks. where a likely row hammer attack is detected, the memory controller may activate a sampling mode (rather than the counting mode) for a particular sub-bank to identify which of the row addresses should be refreshed on the memory hardware. the implementations described herein provide a low computational cost alternative to heavy-handed detection mechanisms that require access to significant computing resources to accurately detect and mitigate row hammer attacks.
Inventor(s): Cheng-Yi HUNG of Valencia PA US for microsoft technology licensing, llc, Vimalraj Vasudevan THEKKOOT of San Jose CA US for microsoft technology licensing, llc, Rochak CHADHA of Pittsburgh PA US for microsoft technology licensing, llc, Gregory J. ZAVERTNIK of Mountain House CA US for microsoft technology licensing, llc
IPC Code(s): G06F21/57
CPC Code(s): G06F21/575
Abstract: techniques are described herein in which boot firmware validated by secure flash memory validates read-only portions of firmware stored by the firmware or a downloaded image of the read-only portions. the secure flash memory validates a portion of the firmware, which includes the boot firmware and a reference hash of the read-only portions, by comparing a calculated hash of the portion and the reference hash of the portion. the boot firmware initiates a boot of the firmware and validates the read-only portions (or the downloaded image of the read-only portions) by comparing a calculated hash of the read-only portions (or a calculated hash of the downloaded image) and the reference hash of the read-only portions. the boot firmware completes the boot of the firmware based at least on the read-only portions (or the downloaded image) being validated.
Inventor(s): Chenguang Zhu of Redmond WA US for microsoft technology licensing, llc, Yang LIU of Redmond WA US for microsoft technology licensing, llc, Nanshan ZENG of Bellevue WA US for microsoft technology licensing, llc, Xuedong HUANG of Bellevue WA US for microsoft technology licensing, llc, Ming ZHONG of Champaign IL US for microsoft technology licensing, llc, Yuantao Wang of Redmond WA US for microsoft technology licensing, llc, Wei XIONG of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): G06F40/166
CPC Code(s): G06F40/166
Abstract: generally discussed herein are devices, systems, and methods for. a method can include receiving, from a user through a user interface, a segmentation granularity value indicating a number of events in the transcript to be included in a summary, extracting, by a ranker model and from the transcript, a number of hints equal to the number of events, generating, by a summarizer model that includes a re-trained language model, respective summaries, one for each event, of a portion of the transcript corresponding to the event, and providing the respective summaries as an overall summary of the transcript.
Inventor(s): Advait SARKAR of Cambridge GB for microsoft technology licensing, llc, Sruti SRINIVASA RAGAVAN of Cambridge GB for microsoft technology licensing, llc, John Herbert Martin WILLIAMS of Cambridge GB for microsoft technology licensing, llc, Ian Zachariah DROSOS of Cambridge GB for microsoft technology licensing, llc, Nicholas Charles WILSON of Cambridge GB for microsoft technology licensing, llc, Irena BEREZOVSKY of Herzliya IL for microsoft technology licensing, llc, Lev SOLODKIN of Herzliya IL for microsoft technology licensing, llc, Andrew Donald GORDON of Cambridge GB for microsoft technology licensing, llc
IPC Code(s): G06F40/18
CPC Code(s): G06F40/18
Abstract: disclosed are novel approaches to debugging a formula in a spreadsheet environment. an execution trace shows step-by-step how a formula is evaluated. instead of overwhelming users by displaying a step for every atomic evaluation, multiple evaluations are displayed in the same step. this makes the execution trace compact yet intuitive, enabling users to quickly and efficiently understand how the formula is evaluated. visualizing formula execution in this way also reduces the computing and energy costs of excess recalculations incurred by trial-and-error based debugging techniques.
20250111135. RANGE PREVIEW WITH ELISIONS_simplified_abstract_(microsoft technology licensing, llc)
Inventor(s): Advait SARKAR of Cambridge GB for microsoft technology licensing, llc, Sruti SRINIVASA RAGAVAN of Cambridge GB for microsoft technology licensing, llc, John Herbert Martin WILLIAMS of Cambridge GB for microsoft technology licensing, llc, Ian Zachariah DROSOS of Cambridge GB for microsoft technology licensing, llc, Nicholas Charles WILSON of Cambridge GB for microsoft technology licensing, llc, Irena BEREZOVSKY of Herzliya IL for microsoft technology licensing, llc, Lev SOLODKIN of Herzliya IL for microsoft technology licensing, llc, Andrew Donald GORDON of Cambridge GB for microsoft technology licensing, llc
IPC Code(s): G06F40/18
CPC Code(s): G06F40/18
Abstract: disclosed is a range preview system that displays data from a relevant range of cells. the range preview system intelligently elides and contextualizes data ranges for efficient visualization. the range preview system optimizes space utilization by selectively collapsing rows and columns. for example, rows and columns that are referenced by a formula may be selected for inclusion in the range preview. this conserves screen real estate while providing users with a concise overview of data ranges. the range preview system may also infer labels, providing context during formula interpretation by associating references with nearby headers or other descriptions.
Inventor(s): Reid Allen PRYZANT of Seattle WA US for microsoft technology licensing, llc, Jerry Zheng LI of Redmond WA US for microsoft technology licensing, llc, Dan ITER of Cedar Park TX US for microsoft technology licensing, llc, Yin Tat LEE of Seattle WA US for microsoft technology licensing, llc, Chenguang ZHU of Issaquah WA US for microsoft technology licensing, llc, Nanshan ZENG of Bellevue WA US for microsoft technology licensing, llc, Anup Shirgaonkar of New York NY US for microsoft technology licensing, llc
IPC Code(s): G06F40/20, G06F40/166
CPC Code(s): G06F40/20
Abstract: systems and methods are provided for implementing automatic prompt optimization using textual gradients. in various embodiments, a feedback prompt, input into a large language model (“llm”), is used to generate textual gradients that criticize a current prompt. the feedback prompt includes the current prompt and predictions that are incorrect compared with corresponding labels associated with minibatch data processed by the llm using the current prompt. the textual gradients and current prompt are used in an editing prompt to the llm to obtain a set of optimized prompts, which may be expanded using a paraphrasing prompt that is input into the llm to generate a set of paraphrased prompts. a selection algorithm is used to select one or more optimized prompts from the set of optimized prompts and/or the set of paraphrased prompts, and the process is repeated with the selected one or more optimized prompts replacing the current prompt.
Inventor(s): Xinyu HU of Redmond WA US for microsoft technology licensing, llc, Pengfei TANG of Redmond WA US for microsoft technology licensing, llc, Simiao ZUO of Redmond WA US for microsoft technology licensing, llc, Qiang LOU of Redmond WA US for microsoft technology licensing, llc, Jian JIAO of Redmond WA US for microsoft technology licensing, llc, Denis Xavier CHARLES of Redmond WA US for microsoft technology licensing, llc, Eren MANAVOGLU of Menlo Park CA US for microsoft technology licensing, llc
IPC Code(s): G06F40/35, G06F16/33, G06F40/40
CPC Code(s): G06F40/35
Abstract: a computing system is disclosed that includes a processor and memory. the memory stores instructions that, when executed by the processor, cause the processor to perform several acts. the acts comprise receiving conversational data indicative of an interaction between a client computing device and a generative model. the conversational data is provided as input into an intent classification module and the intent classification module produces an output indicative of a user intent based upon the conversational data. an anchor generation module generates anchor text indicative of portions of the conversational data correlated with the user intent. a content query based upon the anchor text is generated and content responsive to the content query is obtained and presented at the client computing device.
Inventor(s): Pramod Kumar SHARMA of Seattle WA US for microsoft technology licensing, llc, Arindam MITRA of Redmond WA US for microsoft technology licensing, llc
IPC Code(s): G06F40/40, G06F8/41
CPC Code(s): G06F40/40
Abstract: machine learning models are used to invoke a sequence of tools in response to a user request. a list of available tools is culled before a machine learning model selects from the remaining tools to generate a plan. the plan, which describes tool invocations in natural language, is then converted to code that can programmatically invoke the tools. in some configurations, the list of available tools is first culled by removing tools that do not appear in similarly described plans. the list may further be culled by removing tools that do not appear in plans generated by machine learning models. then, a machine learning model is prompted to generate a final plan from the culled list and the user request. in some configurations, the final plan is converted to code by prompting a machine learning model to extrapolate from the code of similar plans.
Inventor(s): Craig Thomas MCINTYRE of Kirkland WA US for microsoft technology licensing, llc, Bradley Scott STEVENSON of London GB for microsoft technology licensing, llc, Andrew Paul MCGOVERN of Kirkland WA US for microsoft technology licensing, llc, Adam Douglas TROY of Bothell WA US for microsoft technology licensing, llc, Anand Sharad UNAWANE of Hyderabad IN for microsoft technology licensing, llc, Pankaj Vitthal AHER of Hyderabad IN for microsoft technology licensing, llc
IPC Code(s): G06F40/40, G06F16/383
CPC Code(s): G06F40/40
Abstract: various embodiments of the technology described herein dynamically determine at least one target lm skill to use to generate an output for an initial prompt without the need for the target lm skill to be included in the original prompt. embodiments of the technology described herein perform this determination via an intermediate lm skill layer that implements an orchestration loop in a computationally efficient manner that reduces effects of hallucination by identifying one or more target lm skills based on each task identified in the initial prompt. embodiments of the intermediate lm skill layer are separate from the user device and the llm. for example, the intermediate lm skill layer is positioned between an llm abstraction layer and an application layer by which a user can interface with the intermediate lm skill layer.
Inventor(s): Ning WU of Beijing CN for microsoft technology licensing, llc, Yaobo LIANG of Beijing CN for microsoft technology licensing, llc, Baoquan FAN of Beijing CN for microsoft technology licensing, llc, Linjun SHOU of Haidian CN for microsoft technology licensing, llc, Ming GONG of Beijing CN for microsoft technology licensing, llc, Daxin JIANG of Beijing CN for microsoft technology licensing, llc, Nan DUAN of Beijing CN for microsoft technology licensing, llc
IPC Code(s): G06F40/58, G06F16/3332
CPC Code(s): G06F40/58
Abstract: the present disclosure proposes a method, apparatus and computer program product for sentence representation generation for cross-lingual retrieval. a target sentence may be obtained. an initial target sentence representation of the target sentence may be generated through an encoder, the encoder pretrained through a contrastive context prediction mechanism. a target sentence representation of the target sentence for cross-lingual retrieval may be generated based on the initial target sentence representation through cross-lingual calibration.
Inventor(s): MohammadReza GHAEINI of Seattle WA US for microsoft technology licensing, llc, Can LI of Redmond WA US for microsoft technology licensing, llc, Bin ZHANG of Kirkland WA US for microsoft technology licensing, llc
IPC Code(s): G06N3/0455, G06N3/0475
CPC Code(s): G06N3/0455
Abstract: the technology relates to systems and methods for dynamically generating prompts for a generative artificial intelligence (ai) model. an example method includes receiving input content for evaluation by a generative ai model; receiving an input-content embedding for the input content; receiving trait data and trait-data embeddings for the trait data; identifying similar trait data by comparing the input-content embedding with the trait-data embeddings, wherein the similar trait data is a subset of the trait data that is similar to the input content; generating a prompt including the input content and the identified similar trait data; providing the prompt to the generative ai model; and receiving, from the generative ai model in response to the prompt, an output payload including an evaluation of the input content.
Inventor(s): Mahan DAS of Sunnyvale CA US for microsoft technology licensing, llc, Jeremias Lion EICHELBAUM of Seattle WA US for microsoft technology licensing, llc, Melissa AILEM of Los Angeles CA US for microsoft technology licensing, llc, Ye XING of Wellesley MA US for microsoft technology licensing, llc
IPC Code(s): G06N3/0455, G06F21/55, G06N3/08
CPC Code(s): G06N3/0455
Abstract: a computer-implemented method is provided that generates shots for inclusion in a few-shot learning technique. the method includes generating an input, such as a prompt, for a generative model. the input includes a received example generative model input, and instructions which, when processed by the generative model, cause the generative model to generate example input instructions according to different tiers. the input is provided to the llm, and in response the generated example input instructions are received. the generated example input instructions are stored as shots in a data store, with the computer language input.
Inventor(s): Katja HOFMANN of Cambridge GB for microsoft technology licensing, llc, Anssi Samuli KANERVISTO of Cambridge GB for microsoft technology licensing, llc, Sam Michael DEVLIN of Cambridge GB for microsoft technology licensing, llc, Tabish RASHID of Cambridge GB for microsoft technology licensing, llc, Tarun GUPTA of Oxford GB for microsoft technology licensing, llc, Timothy PEARCE of Cambridge GB for microsoft technology licensing, llc, Ryen W. WHITE of Woodinville WA US for microsoft technology licensing, llc
IPC Code(s): G06N3/0475, G06N3/0455, G06N3/08
CPC Code(s): G06N3/0475
Abstract: the disclosed concepts relate to implementation of application and application engine functionality using machine learning. one example method involves obtaining a seed image representing a seeded application state and mapping the seed image to at least one seed image token using an image encoder. the example method also involves inputting the at least one seed image token as a prompt to a neural dreaming model that has been trained to predict training sequences obtained from one or more executions of one or more applications, the training sequences including images output by the one more applications during the one or more executions and inputs to the one or more applications during the one or more executions. the example method also involves generating subsequent image tokens with the neural dreaming model, and decoding the subsequent image tokens with an image decoder to obtain subsequent images.
Inventor(s): BENJAMIN STEENHOEK of DES MOINES IA US for microsoft technology licensing, llc., ALEXEY SVYATKOVSKIY of BELLEVUE WA US for microsoft technology licensing, llc., NEELAKANTAN SUNDARESAN of BELLEVUE WA US for microsoft technology licensing, llc., MICHELE TUFANO of BELLEVUE WA US for microsoft technology licensing, llc.
IPC Code(s): G06N3/092
CPC Code(s): G06N3/092
Abstract: a deep learning model is trained to learn to generate a better-quality unit test case for a focal method through reinforcement learning using a reward score that considers static code quality properties of a best coding standard. the static code quality properties include an assertion in the predicted unit test case, an invocation of the focal method in the predicted unit test case, and a descriptive name for the predicted unit test case. a reward model is trained to compute a reward score for a model-predicted unit test case based on the static code quality properties. the reward score is used in a proximal policy optimization method to produce a policy loss that updates the parameters of the deep learning model towards generating a better-quality unit test case.
Inventor(s): Bhuvan MALLADIHALLI SHASHIDHARA of Bothell WA US for microsoft technology licensing, llc, Chengcheng LI of Bellevue WA US for microsoft technology licensing, llc, Devin John KREUZER of New York City NY US for microsoft technology licensing, llc, Priyadarshini VENKATRAMANI of Redmond WA US for microsoft technology licensing, llc, Tanuja MACHINENI of Redmond WA US for microsoft technology licensing, llc, Joseph John PFEIFFER of Bothell WA US for microsoft technology licensing, llc, Qiangqiang ZHU of Beijing CN for microsoft technology licensing, llc
IPC Code(s): G06N20/20
CPC Code(s): G06N20/20
Abstract: the disclosure describes a subjective data application system that utilizes large generative models (lgms) to leverage unlabeled and poorly labeled subjective data. the subjective data application system utilizes multiple instances of lgms as label functions, which in turn creates a dependable training dataset from a collection of unlabeled subjective data. by using this reliable training data, the subjective data application system develops and trains lightweight, computationally efficient, generative models. these models are then employed to process subjective data with accuracy and speed in real-time or online applications.
Inventor(s): Myriam TITON of Jerusalem IL for microsoft technology licensing, llc, Jeremy SAMAMA of Herzliya IL for microsoft technology licensing, llc, Rachel LEMBERG of Herzliya IL for microsoft technology licensing, llc, Yaniv LAVI of Tel Aviv-Yafo IL for microsoft technology licensing, llc, Hagit GRUSHKA of Lehavim IL for microsoft technology licensing, llc, Michael Tony ALBURQUERQUE of Tel-Aviv IL for microsoft technology licensing, llc, Eliya HABBA of Petah Tikva IL for microsoft technology licensing, llc, Dor GRYNSHPAN of Ramat Gan IL for microsoft technology licensing, llc
IPC Code(s): H04L41/0631, G06F40/20, H04L41/16
CPC Code(s): H04L41/064
Abstract: disclosed herein is a system for determining scores that are usable to filter a larger set of metrics (e.g., thousands of metrics) down to a smaller set of relevant metrics (e.g., hundreds of metrics) that can be more efficiently queried and ingested for root-cause analysis of an incident. during a training stage, the system analyzes known incidents and converts the names of the metrics, as described via customer-defined words, into mathematical representations (e.g., word embedding featurization vectors). when a new metric with a new name is received for a new incident, the system implements an incident inference stage during which the new name is converted into a new mathematical representation. the system compares the new mathematical representation to the mathematical representations to identify a similar mathematical representation. the system retrieves the score for the metric associated with the similar mathematical representation and assigns the retrieved score to the new metric.
Inventor(s): Sathiya Kumaran MANI of Kirkland WA US for microsoft technology licensing, llc, Tsuwang HSIEH of Sammamish WA US for microsoft technology licensing, llc, Ranveer CHANDRA of Kirkland WA US for microsoft technology licensing, llc, Srikanth KANDULA of Redmond WA US for microsoft technology licensing, llc, Santiago Martin SEGARRA of Houston TX US for microsoft technology licensing, llc
IPC Code(s): H04L43/045, H04L41/16, H04L43/08, H04L43/55
CPC Code(s): H04L43/045
Abstract: securing and optimizing communications for a cloud service provider includes collecting connection summary information at network interface devices associated with host computing devices for a group of resources allocated to a customer of the cloud computing environment. the connection summary information includes local address information, remote address information, and data information, each connection established via the network interface devices. at least one communication graph is generated for the group of resources using the connection summary information. the graph includes nodes that represent communication resources of the group of resources and edges extending between nodes that characterize communication between the nodes. at least one analytics process is performed on data from the graph to identify at least one of a micro-segmentation strategy, a communication pattern, and a flow prediction for the group of resources.
Inventor(s): Thomas BASNIGHT of Raleigh NC US for microsoft technology licensing, llc, Gregory A. BRYANT of Raleigh NC US for microsoft technology licensing, llc, Viren Ramesh PATEL of Cary NC US for microsoft technology licensing, llc
IPC Code(s): H04L43/0811, H04L49/00, H04L49/109
CPC Code(s): H04L43/0811
Abstract: systems and methods are disclosed for detecting a deadlock in a cyclical dependency between a set of the plurality of nodes in a mesh network. in some aspects, each of the nodes having a stall detection circuit. the stall detection circuit of each of the nodes operates by providing a stall output that is asserted not only when linked input and output pipeline circuits are stalled but when a stall input from an upstream node indicates that the upstream node is stalled. the stall output is provided as a stall input to the downstream node. in this manner, the stall outputs of the stall detection circuits are stable and asserted when there is a deadlock in a cyclical dependency between a closed loop of nodes in the mesh network.
Inventor(s): Rohan GANDHI of Pune IN for microsoft technology licensing, llc
IPC Code(s): H04L47/125, H04L43/0864, H04L45/12, H04L45/745
CPC Code(s): H04L47/125
Abstract: the present disclosure relates to methods and systems for providing performance aware mux selection for traffic in layer-4 load balancing. the methods and systems assign a subset of vip ranges (vip shards) to a subset of muxes based on capacity of the muxes. the methods and systems allow sources (end-hosts) in the same datacenter (dc) to select the muxes for intra-dc traffic. the methods and systems allow the sources to use weights calculated by a controller for splitting the traffic across muxes based on an end-to-end latency of the muxes. the methods and systems allow the sources to know the muxes handling the traffic by using packet modification and allow the muxes to route the packets to reach specific muxes.
Inventor(s): Timothy James PIERREPONT of London GB for microsoft technology licensing, llc
IPC Code(s): H04L9/40, H04L65/65
CPC Code(s): H04L63/0236
Abstract: in a udp firewall, a flow of packets is received from a public communications network, the flow of packets being sent into a private communications network. the firewall forwards a threshold amount of the flow of packets into the private communications network and validates the flow of packets in response to receiving a packet from the private communications network. in response to the validation failing the firewall blocks the flow of packets. in response to the validation succeeding the firewall allows the flow of packets to continue to be forwarded into the private communications network.
Inventor(s): Safwan Mahmud KHAN of Woodinville WA US for microsoft technology licensing, llc, Michael HENDRICKX of Bellevue WA US for microsoft technology licensing, llc
IPC Code(s): H04L9/40
CPC Code(s): H04L63/0236
Abstract: methods, systems, apparatuses, and computer-readable storage mediums are described for enabling runtime supply chain security of web applications and the discovery of active malware attacks. for example, a server is configured to receive csp-based data from browsers executing on various clients. such data may be received via a browser extension or via a proxy between the web applications and the browsers. using the csp-based data, the server generates a database of supply chain inventory. the database specifies resources that are loaded for a particular web application, along with a location from where such resources are loaded. the database further specifies a chain of dependencies between such resources. the database is analyzed to determine whether any such resources have been compromised with malware or whether clients on which such resource have been loaded have been compromised with malware. responsive to determining such cases, actions(s) may be performed to mitigate the malware.
Inventor(s): Atharva Mulmuley of Hyderabad IN for microsoft technology licensing, llc, Krupesh Satishkumar Dhruva of Hyderabad IN for microsoft technology licensing, llc, Chandra Mouli Addaguduru of Bangalore IN for microsoft technology licensing, llc, Monis Masood Khan of Garner NC US for microsoft technology licensing, llc
IPC Code(s): H04L9/40, G06F9/54
CPC Code(s): H04L63/083
Abstract: a method, computer program product, and computing system for processing a request from a cloud-computing environment to access an on-premises kubernetes application programming interface (api) server. a user associated with the request is identified. a user-specific service account for accessing the on-premises kubernetes api server is generated. a protocol type associated with the request is determined. a user-specific reverse proxy for the user-specific service account is generated based upon, at least in part, the protocol type associated with the request. the request is forwarded to the on-premises kubernetes api server using the user-specific reverse proxy.
Microsoft Technology Licensing, LLC patent applications on April 3rd, 2025
- Microsoft Technology Licensing, LLC
- F04D29/66
- F04D27/00
- G06F1/20
- G06T7/70
- CPC F04D29/661
- Microsoft technology licensing, llc
- G02B6/293
- G02B6/27
- G02B6/32
- G02B17/00
- CPC G02B6/2938
- G01M11/00
- G02B27/09
- G02B27/28
- CPC G02B6/32
- G02B6/42
- G02B6/02
- CPC G02B6/4296
- G06F9/38
- G06F9/30
- CPC G06F9/3806
- CPC G06F9/3844
- G06F9/455
- CPC G06F9/45558
- G06F9/48
- G06F9/50
- CPC G06F9/4893
- CPC G06F9/5005
- G06F11/10
- G06F5/01
- CPC G06F11/1004
- G06F3/06
- G06F11/14
- G06F12/0811
- CPC G06F11/1068
- G06F12/0891
- G06F12/0877
- CPC G06F12/0891
- G06F13/38
- CPC G06F13/385
- G06F16/215
- CPC G06F16/215
- G06F16/2453
- G06F16/242
- G06F40/40
- CPC G06F16/24542
- G06F16/34
- G06F3/0488
- G06F8/33
- G06F40/30
- CPC G06F16/345
- G06F16/583
- G06V10/82
- CPC G06F16/5846
- G06F16/953
- CPC G06F16/953
- G06F21/35
- H04W12/08
- H04W12/33
- H04W12/63
- CPC G06F21/35
- G06F21/55
- G11C8/20
- G11C11/406
- CPC G06F21/554
- G06F21/57
- CPC G06F21/575
- G06F40/166
- CPC G06F40/166
- G06F40/18
- CPC G06F40/18
- G06F40/20
- CPC G06F40/20
- G06F40/35
- G06F16/33
- CPC G06F40/35
- G06F8/41
- CPC G06F40/40
- G06F16/383
- G06F40/58
- G06F16/3332
- CPC G06F40/58
- G06N3/0455
- G06N3/0475
- CPC G06N3/0455
- G06N3/08
- CPC G06N3/0475
- G06N3/092
- CPC G06N3/092
- Microsoft technology licensing, llc.
- G06N20/20
- CPC G06N20/20
- H04L41/0631
- H04L41/16
- CPC H04L41/064
- H04L43/045
- H04L43/08
- H04L43/55
- CPC H04L43/045
- H04L43/0811
- H04L49/00
- H04L49/109
- CPC H04L43/0811
- H04L47/125
- H04L43/0864
- H04L45/12
- H04L45/745
- CPC H04L47/125
- H04L9/40
- H04L65/65
- CPC H04L63/0236
- G06F9/54
- CPC H04L63/083
