Alerta

QUANTUM COMPUTING FOR ACCELERATING MACHINE LEARNING MODEL TRAINING

Absstract of: WO2026075653A2

A system and method to accelerate machine learning training comprises receiving, by a non-quantum computer, a set of data for training a machine learning model; dividing the set of data into a plurality of data batches, each data batch determined according to predetermined requirements of a quantum computer; calculating, by the non-quantum computer, a Jacobian matrix for each of the plurality of data batches, the Jacobian matrix and a loss vector being part of a linear matrix equation for updating weights in the model; arranging, by the non-quantum computer, input data of a polynomial function formatted for a quantum computer; solving, by the quantum computer, a vector of weight updates; and updating the weights in the model.

SYSTEM AND METHOD FOR COLD-START MACHINE LEARNING MODELS

Absstract of: EP4797167A1

Provided are computer-implemented methods and systems for generating a prediction using a cold-start model, including: providing at least one data set from at least one data source, the at least one data set comprising historical transactional data for a first plurality of individuals, and contextual data for a second plurality of individuals, the first plurality of individuals comprising a subset of the second plurality of individuals; determining at least one activity from the at least one data set, the at least one activity comprising at least one feature of the corresponding data set; generating a cold start prediction comprising at least one candidate identifier; generating at least one attribution value based on the at least one feature of the at least one activity; and generating an explainable prediction. Also provided are computer-implemented methods and systems for generating a cold-start model.

AUTOMATED CONTENT MODALITY TRANSFORMATION

Absstract of: CA3292429A1

Aspects of the present disclosure relate to automated content modality transformation. Embodiments include receiving content that corresponds to a particular modality. Embodiments further include providing the content as input to a generative machine learning model that has been trained to generate versions of provided content items that correspond to a target modality. Embodiments further include receiving, as an output from the generative machine learning model, a new version of the content that corresponds to the target modality. Embodiments further include providing the content and the new version of the content as input to a given machine learning model that is trained to generate a confidence score that indicates a likelihood that the new version is an accurate representation of the content in the target modality. Embodiments further include performing one or more actions involving the new version of the content based on the confidence score.

Synthesis of Air Quality Data from Diverse Sources Using Machine Learning

Absstract of: US20260276614A1

0000 Composite health impact scoring of air quality for multiple pollutants is described. In one or more implementations, input data is received indicating concentrations of multiple pollutants at a geographic location. A composite health impact score is generated based on the input data. As part of this, response factors are applied to the multiple pollutants, where the response factors quantify health impacts from exposure to respective pollutants of the multiple pollutants. Moreover, independence factors are applied to the multiple pollutants, where the independence factors adjust the health impacts attributable to the respective pollutants based on combined exposure to the multiple pollutants. The composite health impact score is communicated to a client device for output in a user interface.

ENTITY MATCHING BY LARGE LANGUAGE MODELS WITH RUN TIME ANNOTATION

Absstract of: US20260277882A1

A computing device may select, at run time, a number of pairs of records from a plurality of records. Each record, of the plurality of records, includes attributes. The computing device may obtain, for each of the selected number of pairs of records, key attributes at run time. The computing device may provide, at run time, a prompt to a machine learning model to obtain a prediction of whether records, of a particular pair of records that is not selected from the records, are matched. The prompt may be generated based on the key attributes of the selected number of pairs of records.

METHOD AND SYSTEM FOR DYNAMICALLY CUSTOMIZING FOOD FORMULATIONS

Absstract of: US20260278461A1

The present disclosure provides a system, a method and a non-transitory computer-readable storage medium for dynamically customizing one or more pre-existing food formulations. The method includes receiving one or more input parameters from a user device. The method includes extracting one or more pre-existing food formulations and a set of food processing conditions for the one or more pre-existing food formulations. The method includes generating, using the machine learning model, the nutrient degradation profile for each nutrient corresponding to one or more ingredients associated with the one or more pre-existing food formulations. The method includes determining a set of degradation coefficients for each nutrient corresponding to the one or more ingredients. The method includes predicting nutrient retention rates associated with the one or more pre-existing food formulations. The method includes customizing the one or more pre-existing food formulations.

COMPUTER-BASED SYSTEMS CONFIGURED TO ORCHESTRATE A TRANSFER OF A DATA OBJECT AND METHODS OF USE THEREOF

Absstract of: WO2026193487A1

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving a request for data communication from an external entity to a particular internal enterprise system; identifying the distinct internal system-specific data ontology associated with the particular internal enterprise system; utilizing a machine learning matrix to dynamically compare the request for the data communication to the distinct internal system-specific data ontology; generating a standardized data ontology; verifying the plurality of protocols associated with the standardized data ontology; generating a standardized application programming interface between the external entity and the particular internal enterprise system; and utilizing an adapter to orchestrate a transfer of a data object from the particular internal enterprise system to the external entity.

NOISY QUANTUM CHANNEL ERROR MITIGATION

Absstract of: US20260278451A1

0000 Systems and methods for implementing noisy quantum channel error mitigation are described. For example, a method can include providing to a machine learning model, input data indicative of an original quantum state of a quantum system that is modified by an amount of noise added by a non-unitary quantum communication channel. The machine learning model is trained to predict the original quantum state in order to perform error mitigation by simulating an inverse of the non-unitary quantum communication channel to reverse one or more errors caused by the non-unitary quantum communication channel. The method can further include obtaining, from the machine learning model, output data indicative of the original quantum state, and causing a quantum computing system to perform at least one quantum computing operation, involving at least one of error mitigation or quantum state preparation, based on the output data.

RESIDUAL INITIALIZATION FOR TRAINING NODE NETWORKS

Absstract of: US20260278384A1

0000 This disclosure describes systems, methods, and computer-readable media for initializing and training differentiable logic gate networks for machine-learning inference. In various embodiments, parameters of learnable logic gate operators are initialized using a residual initialization that biases the initial probability distribution of discrete gate choices toward a feedforward operation, such as a wire or an inverter, thereby preserving information flow and mitigating vanishing gradients in deep networks. During training, the gate parameters are updated so that gates can remain as feedforward connections or transition to other logic operations as needed. The residual initialization can be applied to convolutional logic gate-tree architectures and pooling operations, and trained networks can be discretized and synthesized into efficient logic circuits in hardware or software.

MACHINE LEARNING SYSTEMS TO CONDUCT INMATE ASSESSMENT INTERVIEWS

Absstract of: WO2026192915A1

Systems and methods for automatically conducting an assessment interview to predict risks an individual poses to self and others by executing an interview conducting machine-learning model using as input interviewee responses and interview guidance to generate interviewer questions and responses, the interview guidance including guidelines for assessing individuals for risks to themselves and others, and generating an interview transcript including the interviewer questions, the interviewee responses, and the interviewer responses, automatically generating assessment inputs based on the assessment interview by, generating, based on the interviewee responses, assessment inputs, and providing the assessment inputs as input to an analysis engine to generate an assessment of the individual, the assessment reflecting a prediction of risks the individual poses to self and others, automatically generating a report on the assessment by generating, based on the interview transcript and sensor data collected during the assessment interview, a confidence score for the assessment.

CONTENT GENERATION ASSISTANT

Absstract of: US20260277957A1

Aspects of the present disclosure involves systems and techniques for content generation system. The systems and techniques include receiving disclosure materials; generating, by a claim generator comprising a machine learning model trained on claim language, one or more claims based on the disclosure materials; receiving one or more changes to the one or more claims; and inputting the one or more changes to the claim generator as training data to further train the claim generator.

MACHINE LEARNING FRAMEWORK TO DETECT AND MONITOR COMPLIANCE MATTERS

Absstract of: WO2026193314A1

System apparatus, article of manufacture, method and/or computer program embodiments are provided for detecting and monitoring compliance matters. An example method may include obtaining a first set of image data corresponding to an environment from one or more image sensors; processing the first set of image data using a first machine learning algorithm to yield annotated image data that identifies at least one object within the environment; processing the annotated image data using a second machine learning algorithm to determine one or more attributes associated with the at least one object within the environment; and generating, based on the one or more attributes, an evidence package corresponding to the at least one object within the environment, the evidence package being configured to facilitate a determination of one or more action items associated with the at least one object.

Smart Micro Fulfillment Centers Powered by Machine Learning Based Clusters

Absstract of: US20260278532A1

A system and method are disclosed for determining inventory to stock at a supply chain site. The method includes determining a set of inventory clusters identifying inventory items that have been purchased together, ranking the set of inventory clusters based on a number of times each cluster of inventory items was purchased together, determining an amount of shelf space needed for each of the set of inventory clusters, ranking any inventory clusters that were purchased an equal number of times based on the amount of shelf space needed to generate a cluster ranking, and determining inventory to stock at the supply chain site based on the cluster ranking. The method further includes generating an inventory stocking plan based on the determined inventory to stock, and implementing the inventory stocking plan at the supply chain site based on the inventory stocking plan using one or more pieces of automated stocking machinery.

APPORTIONING DATA CENTER COMPUTE POWER

Absstract of: US20260278689A1

0000 The present invention provides a method and apparatus for a thinking system using an ASI distributed Application State Machine that connects to real, accurate, dedicated absolute data, providing privacy, security, and eliminating hallucinated AI. Specifically, one embodiment of the present invention discloses an ASI Command, Control, Communications and Computer Intelligence (C4I) system for independent, intelligent AI Prompting and ASI Browsing. The ASI Application State Machine comprises: ASI Application data structure network; ASI Enterprise Interface State Machine, said data structures interfacing with a back-end channel, a Finite State Machine embedded in each data structure; and Application Service Information Base providing a uniform interface for ASI Application data structure identities. Additional embodiments disclose ASI Browser displaying ASI Applications; ASI Agents; ASI Application Network Nodes; ASI Operating System; ASI Switch; ASI Database of real, accurate, dedicated absolute data, for Machine Learning to train AI Models, for performing real-time, bi-directional transactions, connecting to billing.

SELECTING MACHINE LEARNING MODELS FOR TASKS USING A REGRESSION MODEL

Absstract of: US20260278453A1

A computer-implemented method is provided. A processor set receives a benchmark dataset comprising a number of benchmark records for evaluating a number of machine learning models. The processor set creates a number of prompts for the number of machine learning models based on a subset of benchmark records from the number of benchmark records. The processor set retrieves a number of outputs for each machine learning model by inputting the number of prompts to each machine learning model from the number of machine learning models. The processor set determines a performance score for each machine learning model based on correctness for the number of outputs for each machine learning model using a regression model. The processor set selects a subset of machine learning models from the number of machine learning models to perform a task based on performance scores for the number of machine learning models.

MODEL UNLEARNING FOR MACHINE LEARNING MODELS BY DELINEATING UNDERLYING DATA

Absstract of: US20260278455A1

0000 A computer-implemented method is provided. A processor set identifies a dataset for model learning for a number of machine learning models. The processor set delineates a subset of data in the dataset. Data entries from the subset of data are relevant to context of subject matter to be removed from the model learning for the number of machine learning models. The processor set labels a portion of data from the subset of data. Data entries from the portion of data are associated with metric scores that indicate removal of the data will not prevent the number of machine learning models from performing tasks. The processor set modifies the portion of data from the dataset to form an updated dataset. The portion of data from the dataset is not used for the model learning for the number of machine learning models.

MACHINE LEARNING-BASED AUTOMATIC EVALUATION THRESHOLD CALIBRATION

Absstract of: US20260278475A1

A method and apparatus provide machine learning automatic evaluation threshold calibration. Human-generated labels are accessed. Each human-generated label represents a decision of acceptability of a respective output of a plurality of outputs of a first ML model. A plurality of automatic evaluation metric scores are accessed. Each automatic evaluation metric score represents a determination by a second ML model of a quality of a respective output of the plurality of outputs. An automatic evaluation metric score threshold is determined using a third ML model based on the human-generated labels and the plurality of automatic evaluation metric scores.

Systems and Methods for Dynamic Control of Machine Learning Parameters

Absstract of: US20260278469A1

Systems and methods for dynamic control of machine learning parameters, allowing for modification of weights for input values and vectors during processing. Implementations of these systems provide greater flexibility without requiring extensive retraining of a model, and may improve accuracy of classifications for diagnostic systems or other analyzers.

MACHINE LEARNING-ENABLED FEEDBACK

Absstract of: US20260278650A1

Methods disclosed herein include receiving a record of an interaction between an agent and a human participant in the interaction, analyzing the record to generate at least one characteristic of the interaction attributable to the human participant, wherein the characteristic comprises: a topic, a non-word symbol, metadata, a period of silence, a language characteristic, or an acoustic aspect, determining at least one category or score for at least a portion of the interaction based on the characteristic, generating a summary of the interaction using a machine learning model, and generating a customized communication based on the category or score, wherein the customized communication includes the summary and at least one prompt for the human participant.

Machine Learning Techniques For Generating Skill Hierarchies

Absstract of: US20260278493A1

0000 Techniques for using machine learning to generate skill hierarchies are disclosed. A system generates a graph that models a set of skills, including first and second nodes that represent first and second subsets of the skills. The system uses a model to determine that the first and second nodes are candidates to be connected by an edge in the graph, then uses a large language model to determine that the nodes are sufficiently similar to be connected by the edge. The system performs a minimum cut of a connected subgraph that includes the first and second nodes, to obtain first and second connected sub-subgraphs. The system uses generative artificial intelligence to determine (a) first and second node-level representatives for the first and second nodes and (b) a sub-subgraph-level representative skill. The system generates a skill hierarchy that includes the node-level and sub-subgraph-level representative skills.

APPARATUS, METHOD, AND SYSTEM FOR MACHINE LEARNING JOB CHECKPOINTING IN TRUSTLESS DISTRIBUTED TRAINING PLATFORMS

Absstract of: US20260278400A1

An approach is provided for Machine Learning (ML) job checkpointing in trustless distributed training platforms. The approach, for example, involves receiving an abort message from a resource owner system. The abort message relates to a ML training job that is running. The approach also involves receiving a checkpoint claim from the resource owner system based on the cancelling of the ML training job. The approach further involves receiving a proof of the checkpoint claim comprising at least one of: a proof of execution of the ML training job generated within a Trusted Execution Environment (TEE); or a creation of a future restore failure transaction on a Distributed Ledger Technology (DLT) network configured to execute under a dispute protocol concerning a validity of the checkpoint claim. The approach further involves causing, at least in part, a storage of training artifacts of the ML training job based on the proof.

SYSTEMS AND METHODS FOR CLUSTERING AND SEPARATING GRAPH NETWORKS

Absstract of: US20260278467A1

Systems and methods for decomposing an optimization problem to reduce solve time. Input data associated with the optimization problem is read and the problem is represented as a graph comprising nodes and edges. A machine learning technique clusters the nodes into a plurality of clusters, and an association between constraints and edges spanning the clusters is obtained. For each constraint, a distribution of predicted load among the clusters is determined based on demand information generated by a machine learning model trained on the input data. At least one constraint is then split across the plurality of clusters in accordance with the predicted load distribution.

GENERATING CREDIT CAPACITY ESTIMATES

Absstract of: US20260278675A1

One or more computer processors are used to generate an estimate of a credit capacity of a client. Financial data relating to the client is received. The financial data is input to one or more trained machine learning models. The one or more trained machine learning models are used to generate, based on the financial data, the estimate of the credit capacity.

EXPLAINING RELATIONAL FEATURES UTILIZING SURROGATE ARTIFICIAL INTELLIGENCE MODELS

Absstract of: US20260281140A1

0000 Approaches to explaining relational features utilizing surrogate artificial intelligence (AI) models are described. An input to a machine learning (ML) model is received. The ML model returns a verdict corresponding to a network security evaluation-based graph classification. A surrogate AI model is trained to minimize a loss function while causing a masked output to come as close as possible numerically to the graph classification generated without a mask involved in a mathematical equation of the ML model. The AI model utilizes multiple different kinds of masks. Rating reports are generated based on learned masks from the surrogate AI model to indicate nodes or edges in the ML model most heavily responsible for the verdict returned from the ML model.

SYNTHETIC DATA GENERATION FOR APPLICATION PROGRAMMING INTERFACE REQUEST PAYLOADS AND MOCK DEPENDENCY RESPONSES

Nº publicación: US20260277709A1 17/09/2026

Applicant:

CAPITAL ONE SERVICES LLC [US]
Capital One Services, LLC

Absstract of: US20260277709A1

Systems and methods for generating application programming interface (API) request payloads and mock dependency responses. In some aspects, the system receives an API request schema for an API and a target output field and corresponding value for the API. The system generates, using a machine learning optimization algorithm, a plurality of candidate solutions. The system generates an API request to the API with each candidate solution to obtain one or more corresponding output values for the target output field. The system determines a fitness score of each candidate solution. The system adjusts, using the machine learning optimization algorithm, based on corresponding fitness scores, the plurality of candidate solutions. The system iteratively repeats generating the API request, determining the fitness score of each candidate solution, and adjusting the plurality of candidate solutions until the machine learning optimization algorithm converges on a final candidate solution.