DYNAMIC PROMPT CREATION FOR LARGE LANGUAGE MODELS
Granted: April 3, 2025
Application Number:
20250111202
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…
AUTOMATIC LANGUAGE MODEL (LM) INPUT OPTIMIZATION USING TEXTUAL GRADIENTS
Granted: April 3, 2025
Application Number:
20250111147
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…
PERSONALIZED AI ASSISTANCE USING AMBIENT CONTEXT
Granted: April 3, 2025
Application Number:
20250110985
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…
DATA HEALTH EVALUATION USING GENERATIVE LANGUAGE MODELS
Granted: April 3, 2025
Application Number:
20250110934
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…
HETEROGENEOUS SCHEDULING FOR PROCESSORS WITH MULTIPLE CORE TYPES
Granted: April 3, 2025
Application Number:
20250110778
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,…
HIGH-POWER MULTIPLEXER AND DEMULTIPLEXER FOR HOLLOW CORE FIBER DENSE WAVELENGTH-DIVISION MULTIPLEXING (DWDM) APPLICATIONS
Granted: April 3, 2025
Application Number:
20250110280
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…
DIGITAL IMAGE SUB-DIVISION AND ANALYSIS FOR NEIGHBORING SUB-IMAGE IDENTIFICATION
Granted: March 27, 2025
Application Number:
20250104244
Digital image processing methods performed by a computer are disclosed. In one example, a first digital image captured by a real camera is sub-divided into a first plurality of sub-images. A second digital image captured by a real camera is sub-divided into a second plurality of sub-images. A set of image features in a first sub-image of the first plurality of sub-images is identified. A subset of neighboring sub-images is identified from the second plurality of sub-images based at least…
ACCESS BRIDGE FOR ACCESS CONTROL METHODOLOGY MIGRATION
Granted: March 27, 2025
Application Number:
20250106259
Implementations of an access bridge to facilitate migration from a role-based access control management system to an attribute-based access control management system are provided. One aspect provides a computing system comprising processing circuitry coupled to memory that stores instructions, which, upon execution by the processing circuitry, cause the processing circuitry to: identify a role-based protected resource; identify a set of user accounts permitted to access the role-based…
CONFIGURATION VERIFICATION USING VARIABLE INPUTS AND HASH FUNCTIONS
Granted: March 27, 2025
Application Number:
20250106035
Systems and methods for configuration verification using variable inputs and hash functions are disclosed. A computing device may receive, via an operating system user interface, configuration data associated with a configuration setting of the computing device. In response to receiving the configuration data, the computing device may store the configuration data and obtain, based on a hash configuration, a set of inputs and a hash function. The computing device may hash, using the hash…
INTELLIGENT SYSTEM AND METHOD OF PROVIDING SPEECH ASSISTANCE DURING A COMMUNICATION SESSION
Granted: March 27, 2025
Application Number:
20250104689
A system and method and for providing speech assistance during a virtual meeting includes receiving a request over a communication network to provide speech assistance during a virtual meeting between a plurality of participants and analyzing speech data of the virtual meeting, via a speech impediment detection engine, to detect a speech impediment for one of the plurality of participants. Upon detecting the speech impediment, an avatar is automatically generated for the participant…
DISTORTION CORRECTION FOR DIGITAL IMAGE SUB-DIVISION
Granted: March 27, 2025
Application Number:
20250104203
Digital image processing methods performed by a computer are disclosed. In one example, a digital image captured by a real camera having intrinsic and extrinsic parameters is received. One or more distortion correction transformations are applied to the digital image to generate a distortion-corrected digital image. The distortion-corrected digital image is sub-divided into a plurality of distortion-corrected sub-images. For each distortion-corrected sub-image of the plurality of…
METHOD AND SYSTEM OF ANALYZING ENTERPRISE-TO-ENTERPRISE CONNECTIONS
Granted: March 27, 2025
Application Number:
20250103994
A system and method for analyzing connections between a first enterprise and a second enterprise includes retrieving connection data related to connections between the first enterprise and the second enterprise from a plurality of data sources and utilizing a connection graph generating engine to generate a connection graph for the connections between the first enterprise and the second enterprise, where the connection graph is generated based on the retrieved connection data. The…
PASSING COMPLEX DATA OBJECTS IN LARGE LANGUAGE MODEL PROCESSES
Granted: March 27, 2025
Application Number:
20250103858
Examples are disclosed that relate to passing complex data objects as context variables between iterative prompts to AI models. One example provides a method, comprising receiving an input, constructing a prompt based upon the input, and inputting the prompt into an orchestrator. The method further comprises, based on the prompt, forming a context variable to reference complex data. The method further comprises providing modified input to a first AI plugin at a first orchestration stage,…
Detecting Computer-Generated Hallucinations using Progressive Scope-of-Analysis Enlargement
Granted: March 27, 2025
Application Number:
20250103800
A technique determines whether a target item is adequately supported by a source item, and therefore likely free of hallucinations. The technique operates by progressively expanding a scope of source content to be considered when determining whether an individual target part of the target item has support in the source item. For instance, the technique initially determines whether any individual source part in the source item supports the target part. If this stage fails to identify…
HYBRID ACCESS CONTROL RESOURCE MANAGEMENT
Granted: March 27, 2025
Application Number:
20250103734
Hybrid access control management systems for managing role-based access control resources and attribute-based access control resources are provided. One aspect provides a computing system for implementing hybrid access control management, the computing system comprising: processing circuitry coupled to memory that stores instructions, which, upon execution by the processing circuitry, cause the processing circuitry to: receive a request from a user account to access an access-controlled…
WORKFLOW FOR DATABASE SYSTEM RECOVERY USING LOCAL AND BACKED UP RESOURCES
Granted: March 27, 2025
Application Number:
20250103615
A data processing system implements techniques for operating and recovering databases that includes a plurality of replicas. The plurality of replicas includes a primary replica, a secondary replica, and a delta replica. The primary replica handles read and write operations, the secondary replica is a backup of the primary replica capable of read-only operations. The delta replica comprising a copy of the transactional log information of the primary replica but not the data. The system…
CACHE-EFFICIENT TOP-K AGGREGATION OVER HIGH CARDINALITY LARGE DATASETS
Granted: March 27, 2025
Application Number:
20250103591
A data processing system implements a cache-conscious aggregation framework for cache-efficient top-k aggregation over high cardinality large datasets. The framework leverages skew in the distribution of data in the datasets to minimize data movements within the local caches of the cores of the multicore processors of the data processing system. The framework performs representative sampling on the dataset and utilizes these samples to identify candidate groups in the dataset for the…
CODE REVIEW COMMENT GENERATION VIA INSTRUCTION PROMPTING WITH INTENT
Granted: March 27, 2025
Application Number:
20250103325
A code review is automatically generated by a large language model given a prompt that includes code changes made to a source code program, an associated intent, and an extended context. The intent represents an issue with the code changes from a code reviewer's perspective and is predicted from a neural classifier given the code changes in a code diff format. The neural classifier is a neural encoder transformer model pre-trained on various code review datasets and fine-tuned on code…
ADJUSTING TOUCH INPUT FORCE THRESHOLD
Granted: March 27, 2025
Application Number:
20250103158
Computing devices, touchpads, and related methods for adjusting a force threshold for touch input on a touchpad are disclosed. In one example, a computing device comprises a force sensing touchpad, a processor, and a memory storing instructions executable by the processor to receive a first contact on the touchpad. An area of touch of the first contact is determined, and an adjusted force threshold for touch input is determined based at least on the area of the touch. A second contact is…
SYSTEMS AND METHODS FOR CENTRALIZED AND SCALABLEVAPOR MANAGEMENT SYSTEM IN IMMERSION COOLING
Granted: March 20, 2025
Application Number:
20250098115
A thermal management system includes a boiler tank and at least one heat-generating component positioned in the boiler tank. The boiler tank is in fluid communication with a vapor return line and a liquid return line. A condenser is in fluid communication with the vapor return line and the liquid return line. The condenser is positioned between vapor return line and the liquid return line in the fluid communication.
