Alerta

EXPLAINING BLACK BOX NLP MODELS VIA ENSURING INTERMEDIATE HUMAN-UNDERSTANDABLE REPRESENTATIONS WITH PROTOTYPE-BASED LEARNING

Resumen de: WO2025099498A1

A computer-implemented, machine learning method for providing human-understandable intermediate representations using prototype-based learning includes receiving textual input and generating a rationale using the textual input, where the rationale includes an explanation for the textual input. A closest prototype is identified based on the rationale and a defined distance measure. A classification label and a set of rationales for the closest prototype is provided to a user. The method has applications including, but not limited to, use cases in medicine / healthcare (e.g., for disease classification), resource allocation and data security, data integrity, crime investigation, for example, to optimize predictions or support decision-making.

TRANSFORMER-BASED ASSISTANT FOR IDENTIFYING, ORGANIZING, AND RESPONDING TO CUSTOMER CONCERNS

Resumen de: WO2025102019A1

Transformer-based agent assistant systems as machine learning-based customer service tools that analyze past customer-agent conversations to build a knowledge base of problem-resolution steps are disclosed. The system may include a natural language processing (NLP) model and a transfomer-based model to extract and generate customer concerns and resolutions. One embodiment also includes a head-topic and subtopic detection module for identifying trends in customer concerns. Another embodiment uses a question-answering model and a zero-shot-NLI (natural language inference) classifier for entity extraction and detection. The system is designed to be flexible, incorporating new data over time, and can retrieve company documentation or FAQs for the agent based on cosine similarity.

STATE MACHINE DRIVEN AUTOMATED AGENT WITH NESTED AUDITING

Resumen de: US2025156703A1

A system providing a state-driven automated agent. The state machine can include multiple nested state machines to receive, process, and generate responses to a user inquiry received through a chat application. The state machine has a plurality of states, and navigates between states based on one or more machine learning (ML) models. In some instances, each state is associated with a machine learning model that can predict what state the state machine should transition to from its current state. The machine learning model(s) can be implemented using one or more large language models (LLM). The state-driven automated agent includes an auditing state that analyzes a predicted response to a user inquiry and identifies errors with the response. The errors may be identified and automatically self-corrected.

DEVICES, DATA STRUCTURE, AND COMPUTER-IMPLEMENTED METHODS FOR MACHINE LEARNING USING SEMANTIC TECHNOLOGIES

Resumen de: US2025156758A1

Devices, data structure, and computer-implemented methods for machine learning. A method for machine learning includes providing a data structure of a database, which data structure includes a set of nodes and a set of relations, and a set of tuples. Each respective tuple includes at least two nodes, and at least one relation. The method includes predicting a plurality of tuples depending on the data structure, wherein each respective tuple includes at least two nodes and at least one relation, predicting, whether the respective tuples of the plurality of tuples classifies as a member of the set of tuples, selecting a tuple from the plurality of tuples depending on the uncertainties predicted for the respective tuples, acquiring a label that indicates whether the selected tuple classifies as a member of the set of tuples, and adding the selected tuple to the set of tuples based on the label.

Systems and methods for intelligent machine learning-based malware detection

Resumen de: US2025156546A1

Systems and methods for training a machine learning model for malware detection include steps of collecting a training dataset comprising a plurality of malicious files and a plurality of benign files from one or more sources; extracting features from each file in the training dataset, wherein the features include at least one of n-gram features, entropy features, or domain features; labeling each file in the training dataset as malicious or benign based on a predefined criterion; and applying a supervised machine learning technique to learn patterns in the extracted features and generate a trained machine learning model configured to predict whether a file is malicious or benign based on an incremental packet-based analysis.

Query Processing with Machine Learning

Resumen de: US2025156430A1

The description relates to executing an inference query relative to a database management system, such as a relational database management system. In one example a trained machine learning model can be stored within the database management system. An inference query can be received that applies the trained machine learning model on data local to the database management system. Analysis can be performed on the inference query and the trained machine learning model to generate a unified intermediate representation of the inference query and the trained model. Cross optimization can be performed on the unified intermediate representation. Based upon the cross-optimization, a first portion of the unified intermediate representation to be executed by a database engine of the database management system can be determined, and, a second portion of the unified intermediate representation to be executed by a machine learning runtime can be determined.

ARTIFICIAL INTELLIGENCE IN AN AEROSOL DELIVERY DEVICE

Resumen de: US2025151806A1

An aerosol delivery device is provided that includes sensor(s) to produce measurements of properties during use of the device, and processing circuitry to record data for a plurality of uses of the device, for each use of which the data includes the measurements of the properties. The processing circuitry is configured to build a machine learning model to predict a target variable, using a machine learning algorithm, at least one feature selected from the properties, and a training set produced from the measurements of the properties. The processing circuitry is configured to then deploy the machine learning model to predict the target variable, and control at least one functional element of the device based on the target variable, the target variable being a user profile depending on at least one of the properties, and times and durations of respective user puffs on the device.

ENSEMBLE MACHINE LEARNING SYSTEMS AND METHODS

Resumen de: US2025157670A1

Techniques for responding to a healthcare inquiry from a user are disclosed. In one particular embodiment, the techniques may be realized as a method for responding to a healthcare inquiry from a user, according to a set of instructions stored on a memory of a computing device and executed by a processor of the computing device, the method comprising the steps of: classifying an intent of the user based on the healthcare inquiry; instantiating a conversational engine based on the intent; eliciting, by the conversational engine, information from the user; and presenting one or more medical recommendations to the user based at least in part on the information.

VIRTUAL WORLD ENVIRONMENTS FOR ENTERPRISE DECISION-MAKING

Resumen de: US2025157088A1

In an example embodiment, machine learning is utilized to create a virtual world where a user can view and interact with data in a graphical environment. This virtual world may be termed a “Story Verse” environment, which can create multiple different virtual world universes capable of segmenting the traditional complexities of Enterprise system data into an easily usable and holistic set. In a further example embodiment, the virtual world is presented in a way that data is represented as real world objects, such as amusement park rides, clouds, etc.

HIGH-FIDELITY PREDICTION WITH TRUST REGIONS

Resumen de: US2025156747A1

According to one embodiment, a method, computer system, and computer program product for making high-fidelity predictions with trust regions is provided. The embodiment may include identifying a data set. The embodiment may also include partitioning the data set into two or more clusters. The embodiment may further include creating two or more disjoint polytopic regions in a multi-dimensional space, wherein a cluster from the two or more disjoint polytopic regions corresponds to a trust region from the two or more polytopic regions. The embodiment may also include training a machine learning model based on the two or more disjoint polytopic regions. The embodiment may further include drawing a conclusion based on the trained machine learning model.

SYNTHETIC DATA GENERATION USING LARGE LANGUAGE MODELS

Resumen de: US2025156644A1

In various examples, synthetic question-answer (QA) pairs may be generated using question and answer generation models comprising corresponding language models (e.g., autoregressive LLMs). A repository of textual data representing a particular knowledge base may be used to source synthetic QA pairs by partitioning textual data from the repository into units of text (e.g., paragraphs) that represent context. For each unit of text, the question generation model may be prompted to generate a synthetic question from that unit of text, and the answer generation model may be prompted to generate a synthetic answer to the synthetic question. Textual entailment and/or human evaluations may be used to filter out low quality, incorrect, and/or non-productive QA pairs that may be a result of hallucinations. As such, the synthetic QA pairs may be used as, and/or may be used to generate, training data for one or more machine learning models.

Suggesting Actions Based on Machine Learning

Resumen de: US2025156203A1

This document describes techniques for suggesting actions based on machine learning. These techniques determine a task that a user desires to perform, and presents a user interface through which to perform the task. To determine this task, the techniques can analyze content displayed on the user device or analyze contexts of the user and user device. With this determined task, the techniques determine an action that may assist the user in performing the task. This action is further determined to be performable through analysis of functionalities of an application, which may or may not be executing or installed on the user device. With some subset of the application's functionalities determined, the techniques presents the subset of functionalities via the user interface. By so doing, the techniques enable a user to complete a task more easily, quickly, or using fewer computing resources.

Technologies for Predictive Management of Customer Account Balance Attrition

Resumen de: US2025156939A1

Technologies for predictive management of customer account balance attrition include a compute device. The compute device includes circuitry configured to obtain data indicative of one or more attributes of a customer of a financial institution. The circuitry may also be configured to generate, from the obtained data, a feature set for use by an ensemble of machine-learning models trained to predict customer behavior, provide the feature set to the ensemble of machine-learning models to produce a prediction of whether the customer of the financial institution will be lost to (e.g., at least a portion of the customer's money will be transferred to) a competitor financial institution, obtain the prediction from the ensemble of machine-learning models, and perform, in response to a determination that the that the customer is predicted to be lost, a remedial action to reduce a likelihood of losing the customer.

MACHINE LEARNING-BASED AUTOMATED ABNORMALITY DETECTION IN MEDICAL IMAGES AND PRESENTATION THEREOF

Resumen de: US2025156677A1

The presently disclosed technology relates to medical image processing. An example method includes receiving medical image data which represents an anatomical structure and processing the received image data through convolutional neural network (CNN) to generate predictions. The predictions can include abnormality location proposals and abnormality class probabilities associated with each abnormality location proposals.

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING SYSTEM, PROGRAM, AND ISING MODEL DEVELOPMENT ASSISTANCE METHOD

Resumen de: EP4553723A1

With respect to an information processing device that supports creation of an Ising model for causing an annealing-type optimization machine to solve an optimum solution search problem, the information processing device includes a transforming unit configured to binarize an explanatory variable included in a training data set created using a trained machine learning model; a training unit configured to train an Ising model by performing machine learning with a relationship between the binarized explanatory variable and a predicted value of the training data set; and an output unit configured to output the trained Ising model.

DEVICES, DATA STRUCTURE, AND COMPUTER-IMPLEMENTED METHODS FOR MACHINE LEARNING USING SEMANTIC TECHNOLOGIES

Resumen de: EP4553716A1

Devices, data structure, and computer-implemented methods for machine learning, wherein a first method for machine learning comprises providing (402) a data structure of a database, wherein the data structure comprises a set of nodes, in particular a set of entities, or a set of subjects and objects, wherein the data structure comprises a set of relations, in particular a set of edges, or a set of predicates, and wherein the data structure comprises a set of tuples, wherein a respective tuple of the set of tuples comprises at least two nodes of the set of nodes, and at least one relation of the set of relations, in particular two entities of the set of entities and an edge of the set of edges, or a subject, and an object of the set of subjects and object, and a predicate of the set of predicates, wherein the method comprises predicting (404) a plurality of tuples depending on the data structure, wherein a respective tuple of the plurality of tuples comprises at least two nodes of the set of nodes, and at least one relation of the set of relations, in particular two entities of the set of entities and an edge of the set of edges, or a subject, and an object of the set of subjects and objects, and a predicate of the set of predicates, wherein the method comprises predicting (406), for the plurality of tuples, an uncertainty about whether the respective tuple of the plurality of tuples classifies as a member of the set of tuples or not, selecting (408) a tuple from the plurality

SYSTEMS AND METHODS FOR DYNAMICALLY UPDATING MODELS USING MACHINE LEARNING

Resumen de: WO2025096085A1

A computing system for detecting patterns in data is provided. The computing system includes a model engine configured to receive an initial dataset, and segment the initial dataset into a plurality of subsets. The model engine is further configured to assign a weight to each subset based at least in part on an age of the subset, train a machine learning model on each subset separately in accordance with the assigned weighting for that subset. The model engine is further configured to receive a candidate dataset, analyze the candidate dataset using the trained machine learning model, and assign a score to the candidate dataset based on the analysis. The computing system further includes a rules engine configured to receive the candidate dataset and the corresponding score from the model engine, and generate and output, based at least in part on the score, a decision regarding the candidate dataset.

APPARATUS AND METHOD FOR DETERMINING A COMPOSITION OF A REPLACEMENT THERAPY TREATMENT

Resumen de: US2025149142A1

An apparatus and method for determining a composition of a replacement therapy treatment is presented, the apparatus at least a processor and a memory communicatively connected to the processor, the memory containing instructions configuring the at least a processor to receive a user input wherein the user input comprises at least an identifier and a constitutional history of the user, generate a first condition descriptor as a function of the user input, determine a composition of a replacement therapy treatment as a function of the first condition descriptor, wherein the determination comprises training a first machine-learning process using user training data, wherein the user training data correlates user inputs to compositions of the replacement therapy treatment and determining the composition as a function of the user input and the first machine learning process, and output the composition of the replacement therapy treatment as a function of the determination.

SYSTEMS AND METHODS FOR DYNAMICALLY UPDATING MODELS USING MACHINE LEARNING

Resumen de: US2025148470A1

A computing system for detecting patterns in data transmitted over a network is provided. The computing system includes a model engine configured to receive an initial dataset including historical data for a first time period, and segment the initial dataset into a plurality of subsets, each subset associated with a second time period smaller than the first time period. The model engine is further configured to train a machine learning model on each subset separately, receive a candidate dataset, analyze the candidate dataset using the trained machine learning model, and assign a score to the candidate dataset based on the analysis. The computing system further includes a rules engine configured to receive the candidate dataset and the corresponding score from the model engine, and generate and output, based at least in part on the score, a decision regarding the candidate dataset.

MACHINE LEARNING MODEL PUBLISHING SYSTEMS AND METHODS

Resumen de: US2025148373A1

A machine learning (ML) model publisher can, responsive to an indication that a ML model is ready for publication, generate a publication request form or page on a user device. The ML model publisher can be invoked from within a ML modeling application. Responsive to an instruction received through the publication request form or page, the ML model publisher can access a data structure in memory used in training the ML model and populate the publication request form or page with attributes required by the ML model to run. Responsive to activation of a single-click publication actuator, the ML model publisher can publish the ML model directly from the ML modeling application to a target computing system by providing, to the target computing system, a path to a repository location where the ML model is stored and information on the attributes required by the ML model to run.

FLEXIBLE MACHINE LEARNING MODEL COMPRESSION

Resumen de: US2025148357A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compresses a machine learning model having a plurality of parameters. In one aspect, one of the methods includes obtaining trained values of a set of parameters for at least a portion of a machine learning model; identifying one or more dense ranges for the trained values; determining a least number of bits required to represent each trained value within the one or more dense ranges; identifying a second format having a range that is smaller than a range of the first format; and generating a compressed version of the at least a portion of the machine learning model.

POWER FEATURE AIDED MACHINE LEARNING TO REDUCE NON-LINEAR DISTORTION

Resumen de: US2025148376A1

A computer-implemented method performed by a device configured with a power feature aided machine learning, ML, model is provided that models a behavior of a DPD to reduce non-linear distortion of an output signal of a non-linear device. The method includes extracting a plurality of power features from an input signal destined to be input to the DPD. The method further includes labelling the extracted plurality of power features to obtain at least one labelled average power level; inputting the at least one labelled average power level to the input of the ML model to obtain an output signal from the ML model having characteristics to reduce the non-linear distortion of the output signal of the non-linear device; and providing the output signal from the ML model as an input to the non-linear device.

SYSTEMS AND METHODS FOR LEARNING DATA PATTERNS PREDICTIVE OF AN OUTCOME

Resumen de: US2025148259A1

System and methods for learning data patterns predictive of an outcome are described. An example system may include a plurality of input sensors communicatively coupled to a controller; a data collection circuit structured to collect output data from the plurality of input sensors; and a machine learning data analysis circuit structured to receive the output data, learn received output data patterns indicative of an outcome, and learn a preferred input data collection band among a plurality of available input data collection bands. The machine learning data analysis circuit may be structured to learn received output data patterns by being seeded with a model based on industry-specific feedback. The outcome may be at least one of: a reaction rate, a production volume, or a required maintenance.

SYSTEMS AND METHODS FOR DYNAMICALLY UPDATING MODELS USING MACHINE LEARNING

Resumen de: US2025148482A1

A computing system for detecting patterns in data is provided. The computing system includes a model engine configured to receive an initial dataset, and segment the initial dataset into a plurality of subsets. The model engine is further configured to assign a weight to each subset based at least in part on an age of the subset, train a machine learning model on each subset separately in accordance with the assigned weighting for that subset. The model engine is further configured to receive a candidate dataset, analyze the candidate dataset using the trained machine learning model, and assign a score to the candidate dataset based on the analysis. The computing system further includes a rules engine configured to receive the candidate dataset and the corresponding score from the model engine, and generate and output, based at least in part on the score, a decision regarding the candidate dataset.

Method, System, and Computer Program Product for Machine Learning Using Decoupled Knowledge Graphs

Nº publicación: US2025148353A1 08/05/2025

Solicitante:

VISA INT SERVICE ASSOCIATION [US]
Visa International Service Association