Alerta

DATABASE SYSTEM WITH QUERY OPERATIONS REGARDING MACHINE LEARNING MODELS AND TRAINING THEREOF

Resumen de: US20260187066A1

Within a database system, a computing node obtains a query that includes a training query operation regarding training of a machine learning model, identifies training data, and provides the training query operation and the training data to other computing nodes. Processing core resources (PCRs) of the computing nodes receive the training query operation. The PCRs receive, in a distributed manner, the sets of the training data. The PCRs execute, in substantial parallel, the training query operation on at least a portion of the machine learning model based on respective sub-sets of the sets of the training data to produce a plurality of partial training results. The computing node compiles the plurality of partial training results to produce a training result and, when the training result is favorable, update the machine learning model based on the training result.

TECHNIQUES FOR DETECTING EMERGING PATTERNS IN DATA USED FOR MACHINE LEARNING MODEL-BASED DECISIONS

Resumen de: US20260187524A1

0000 Described are examples for detecting emerging patterns in data. A detection system for detecting patterns outside of supervised machine learning models is provided for determining similarity scores between transactions to detect the emerging patterns. Transactions in the pattern can be reviewed to determine whether to render decisions on the transactions or similar subsequently occurring transactions. A self-correcting detection system is also provided for using machine learning models to correct for emerging patterns in the transaction data.

SYSTEM AND METHOD FOR EXTRACTING HIDDEN CUES IN INTERACTIVE COMMUNICATIONS

Resumen de: US20260188340A1

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process interactive communications between at least two participants. Speech and text, within the interactive communications, are analyzed using machine learning classifiers to extract prosodic, semantic and key phrase cues located within the interactive communications to identify changes to emotion, sentiments and key phrases. A summary of the interactive communications between a first participant and a second participant is generated at least, in-part, based on the extracted prosodic, semantic and key phrase cues and the summary is highlighted based on any of the changes to emotion, the sentiments or the key phrases.

OPERATIONALIZING MACHINE LEARNING MODELS AN INFORMATION TECHNOLOGY AND SECURITY OPERATIONS APPLICATION

Resumen de: US20260187518A1

Techniques are described for providing a ML data analytics application including guided ML workflows that facilitate the end-to-end training and use of various types of ML models, where such guided workflows may also be referred to as ML “experiments.” For example, the ML data analytics application may enable users to create experiments related to prediction of numeric fields (for example, using linear regression techniques), predicting categorical fields (for example, using logistic regression), detecting numerical outliers (for example, using various distribution statistics), detecting categorical outliers (for example, using probabilistic statistics), forecasting time series data, and clustering numeric events (for example, using k-means, density-based spatial clustering of applications with noise (DBSCAN), spectral clustering, or other techniques), among other possible uses of various types of ML models to analyze data.

DECISION TREE OF MODELS: USING DECISION TREE MODEL, AND REPLACING THE LEAVES OF THE TREE WITH OTHER MACHINE LEARNING MODELS

Resumen de: US20260187484A1

Described are techniques of generating and training a neural network that include training multiple models and constructing multiple decision trees with said models. Each decision tree may include additional decision trees at various levels of that decision tree. Each decision tree has a different accuracy indicator due to the unique structuring of each decision tree, and by testing each tree through a testing dataset, the tree with the highest accuracy can be determined.

BOOSTING AND MATRIX FACTORIZATION

Resumen de: US20260187197A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for presenting a new machine learning model architecture. In some aspects, the methods include obtaining a training dataset with a plurality of training samples that includes feature variables and output variables. A first matrix is generated using the training dataset which is a sparse representation of the training dataset. Generating the first matrix can include generating a categorical representation of numeric features and an encoded representation of the categorical features. The methods further include generating a second, third and a fourth matrix. Each feature of the first matrix is then represented using a vector that includes a multiple adjustable parameters. The machine learning model can learn by adjusting values of the adjustable parameters using a combination of a loss function the fourth matrix, and the first matrix.

VIRTUALLY MONITORING GLUCOSE LEVELS IN A PATIENT USING MACHINE LEARNING AND DIGITAL TWIN TECHNOLOGY

Resumen de: US20260182869A1

0000 A patient health management platform implements a machine-learned metabolic model to generate a prediction of a patient's glucose level. The platform implements a short-term prediction model to generate a daily prediction of the patient's glucose level based on nutrition data reported by the patient and sensor data and lab test data collected for the patient. The platform implements a long-term prediction model generate a prediction of the patient's glucose level during an extended time period based on sensor data and lab test data collected for the patient. Using the short-term prediction model, the long-term prediction model, or both, the patient health management platform generates predictions of the patient's glucose level and updates a digital twin of the patient's metabolic profile.

USER SEARCH CATEGORY PREDICTOR

Resumen de: US20260187663A1

0000 Described herein are embodiments for improving search engine results of listings of For Sale Objects (FSOs). A search engine may be improved by implementing rules that resolve ambiguity between listings for different (FSOs) that match the same search inputs. An unsupervised machine learning module may evaluate candidate rules and identify improvements that may not be obvious to a human evaluator. An ecommerce site that combines the improved search engine with the unsupervised machine learning module may dynamically evaluate search results using different candidate rules and iteratively improve search results.

UNCERTAINTY LEARNING DEVICE, STORAGE MEDIUM STORING UNCERTAINTY LEARNING PROGRAM, AND UNCERTAINTY LEARNING SYSTEM

Resumen de: US20260187536A1

0000 Included are: a training data acquiring unit that acquires training data created on the basis of operation-related data obtained from a machine device; a noise imparting unit that creates noise-imparted training data in which noise is imparted to the training data acquired by the training data acquiring unit; an outlier detecting unit that calculates an outlier score from the training data acquired by the training data acquiring unit and the noise-imparted training data created by the noise imparting unit; and a model learning unit that calculates a weighted loss function based on the outlier score calculated by the outlier detecting unit, and trains a machine learning model on the basis of the training data and the noise-imparted training data.

SYSTEMS AND METHODS FOR COORDINATING EXECUTION OF AN ENSEMBLE OF MACHINE LEARNING MODELS

Resumen de: US20260187545A1

System for coordinating execution of an ensemble of machine learning models to determine anatomical structures to target during cancer treatment are described herein. In examples, the systems can coordinate execution of multiple machine learning models based on different types of three-dimensional images of a patient. These images can include positron emission tomography (PET) images, computed tomography (CT) images, and/or other similar images. The outputs of the models can be correlated with one another to quantify locations and volumes of tumor lesions within the patient. In some examples, a tumor stage can be determined based on the quantification of the tumor lesions. This information can then be used to determine one or more optimal treatment plans for the patient.

SYSTEMS AND METHODS OF GENERATING DATASETS FROM HETEROGENEOUS SOURCES FOR MACHINE LEARNING

Resumen de: US20260187495A1

0000 A computer system is provided that is programmed to select feature sets from a large number of features. Features for a set are selected based on metagradient information returned from a machine learning process that has been performed on an earlier selected feature set. The process can iterate until a selected feature set converges or otherwise meets or exceeds a given threshold.

TECHNIQUES FOR IMPROVING DECISIONS RENDERED BASED ON MACHINE LEARNING MODEL OUTPUT

Resumen de: EP4769235A1

Described are examples for rendering decisions based on machine learning (ML) model output. A set of segments for a historical set of data for a division of interest, and associated budgets for the decision of interest, can be obtained. For each segment in the set, a budget for incorrect decisions rendered based on output from the ML model can be computed. For each data entry in a current set of data, a current decision can be rendered based on a configured cutoff value and also a shadow decision based on the candidate cutoff value for a segment of the set of segments associated with the data entry. The candidate cutoff value can be promoted to replace the configured cutoff value, for rendering subsequent decisions for a subsequent set of data, based on comparing the shadow decisions for the current set of data based on the budget for incorrect decisions.

MACHINE LEARNING BASED SYSTEM AND METHOD FOR AUTOMATICALLY REDISTRIBUTING DATA

Resumen de: EP4769259A1

A machine learning based (ML-based) method and system for redistributing data, is disclosed. Initially, an input data associated actual bank cash is obtained from data sources. The input data is pre-processed to generate pre-processed data. A month level data associated with the actual bank cash is predicted for a pre-determined horizon based on at least one of: historical cash flow data and seasonality, using machine learning (ML) models on the pre-processed data. At least one of: the month level data to week of month (WOM) level data and the WOM level data to day level data, is redistributed based on a pro-rata configuration using hyperparameters. At least one of: the WOM level data and the day level data, redistributed from the month level data, is provided as an output, to the users on user interfaces associated with electronic devices associated with the users.

QUALITY PREDICTION MODEL GENERATION METHOD, METAL MATERIAL QUALITY PREDICTION METHOD, METAL MATERIAL MANUFACTURING METHOD, METAL MATERIAL MANUFACTURING CONDITION PRESENTATION METHOD, QUALITY PREDICTION MODEL GENERATION DEVICE, METAL MATERIAL QUALITY PREDICTION DEVICE, METAL MATERIAL MANUFACTURING CONDITION PRESENTATION DEVICE, AND METAL MATERIAL MANUFACTURING SYSTEM

Resumen de: EP4769249A1

A method of generating a quality prediction model includes an acquisition step (S1) of acquiring an explanatory variable selected from manufacturing conditions of each process and an objective variable that is a state of quality defects in the manufactured metal material, a storage step (S3) of storing the explanatory variable and the objective variable in association with each other as training data, calculation steps (S4 to S6) of dividing the training data into groups and testing whether a significant difference exists in the state of quality defects, a search step (S7) of searching for a most significant grouping, and a generation step (S8) of generating the quality prediction model by machine learning using a group according to the most significant grouping found.

APPARATUS AND METHOD FOR INSPECTING BATTERY

Resumen de: EP4768897A1

0001 A method for inspecting a battery, according to an embodiment of the present invention, relates to a method for inspecting the quality of a battery in a manufacturing process, the method comprising the steps of: acquiring an image capturing at least a portion of the exterior of the battery to preprocess the image; detecting one or more defect candidate regions in the preprocessed image by using one or more detection algorithms; extracting position information of the defect candidate regions and shape feature information of the defect candidate regions; and inputting, into a pre-trained machine learning model, information related to the detection algorithms, the position information of the defect candidate regions, and the shape feature information of the defect candidate regions, to determine whether corresponding defect candidate shapes are defective.

MACHINE-LEARNING-BASED SYSTEM AND METHOD FOR AUTOMATICALLY EXTRACTING FIELDS FROM DOCUMENTS

Resumen de: EP4769285A1

0001 A machine-learning based (ML-based) system and method for automatically extracting one or more data fields from one or more documents, are disclosed. The ML-based system includes a document obtaining subsystem to obtain documents, a document pre-processing subsystem to generate pre-processed data, a field identifying subsystem to identify data fields using a trained ML model, and a field extracting subsystem to extract financial information. The ML-based system also comprises an output subsystem to deliver the extracted data to end users via user interfaces. The ML model is trained using historical documents, labelled data fields, and features such as distance-based features, direction-based features, dimension-based features, positional features, and value-based features. The M-based system employs hyperparameter optimization, noise removal, and accuracy assessment mechanisms to enhance performance. This ML-based system provides a scalable, accurate, and automated solution for financial information extraction, ensuring efficiency, adaptability, and seamless integration with enterprise systems.

APPARATUS AND METHOD FOR DESIGNING MULTILAYER FILM

Resumen de: EP4768891A1

An apparatus and method for designing a multilayer film is disclosed. An apparatus for designing a multilayer film may perform: modeling a multilayer film to be designed as a single layer structure having a preset thickness, collecting physical property data with respect to a film corresponding to the single layer structure, reading a value pre-stored in a storage space accessible by an apparatus for designing a multilayer film, and obtaining a feature setting mode for designating different feature setting manners depending on the read value, performing feature setting based on a plurality of physical indicators selected from the physical property data, depending on the feature setting mode, selecting at least one among a plurality of supervised learning models capable of a regression analysis as a machine learning model, predicting the dart impact strength of the multilayer film by using the machine learning model learned by taking the feature as an independent variable, and a dart impact strength of the multilayer film as a target variable, and generating design data for the multilayer film, by combining predicted values for other properties and a predicted value of the dart impact strength, so as to satisfy the design requirements of the multilayer film.

METHOD FOR INTELLIGENT ANALYSIS OF IMPORT AND EXPORT HAZARDOUS CHEMICALS BASED ON MACHINE LEARNING

Resumen de: NL4001738A

0001 The present disclosure relates to the technical field of data processing, in particular to a method for intelligent analysis of import and export hazardous chemicals based on machine learning. The method constructs a hazardous chemical knowledge graph and performs path detection on the hazardous chemical knowledge graph to obtain at least one valid path and at least one invalid path; acquires, for any invalid path, a value index of the any invalid path according to a degree of information coverage between intermediate entities of the any invalid path, a similarity feature between adjacent intermediate entities of the any invalid path, and a degree of reliability of each connected segment in the any invalid path; utilizes a value index of each invalid path to screen at least one high-value path among all invalid paths.

METHOD FOR TRAINING A MACHINE LEARNING MODEL WHICH IS DESIGNED TO DETERMINE THE CHARGING TIME FOR BATTERIES OF ELECTRIC VEHICLES

Resumen de: WO2026131066A1

The invention relates to a method for training a machine learning model which is designed to determine the charging time for batteries (104a, 104b, 104c) of electric vehicles (100a, 100b, 100c), having the steps of: providing (200) first training data (202) relating to batteries of a first plurality of electric vehicles; carrying out a first training process (204) on a machine learning model (206) in order to obtain a pre-trained machine learning model (208); providing (224) data (226) which is characteristic of trained individual machine learning models, each of the trained individual machine learning models being obtained by carrying out a second training process (216) on the pre-trained machine learning model (208), respective second training data (214) having been obtained for each of a second plurality of electric vehicles; providing (228) histograms (230) of the respective second training data; adapting (232) the pre-trained machine learning model on the basis of the histograms and on the basis of the data which is characteristic of the trained individual machine learning models in order to obtain one or more trained final machine learning models (234); and providing (236) the one or more trained final machine learning models.

MACHINE LEARNING BASED MODEL FOR DETERMINING EFFECTIVE COMMUNICATION MECHANISM WITH USERS

Resumen de: US20260178941A1

A system uses a machine learning based model to select a channel for communicating with users. The system generates a feature vector based on a user profile of the user. The user profile data includes time series data describing past communications to users and past user actions. The system executes one or more machine learning based models, each machine learning based model configured to receive a feature vector describing a particular user and predict a likelihood of the particular user performing an expected user action responsive to a communication sent via the communication channel. The system selects a communication channel based on the results of the machine learning based models and sends a communication to the user via the selected communication channel.

GENERATING AND MODIFYING ONTOLOGIES FOR MACHINE LEARNING MODELS

Resumen de: US20260178990A1

A method performed by a machine learning system that involves obtaining a first ontology that includes one or more labels. Each label is associated with a sample that includes text. The ML system is configured to use a particular label to retrieve one or more samples associated with the particular label. The method further involves receiving an identification of a label of a first ontology associated with a first machine learning model to share with a second ontology associated with a second machine learning model and sharing the label and the information with the second ontology. The method further involves training the second machine learning model using the shared information associated with the label.

ADAPTIVE DATA COLLECTION OPTIMIZATION

Resumen de: US20260178679A1

Systems and methods to intelligently optimize data collection requests are disclosed. In one embodiment, systems are configured to identify and select a complete set of suitable parameters to execute the data collection requests. In another embodiment, systems are configured to identify and select a partial set of suitable parameters to execute the data collection requests. The present embodiments can implement machine learning algorithms to identify and select the suitable parameters according to the nature of the data collection requests and the targets. Moreover, the embodiments provide systems and methods to generate feedback data based upon the effectiveness of the data collection parameters. Furthermore, the embodiments provide systems and methods to score the set of suitable parameters based on the feedback data and the overall cost, which are then stored in an internal database.

MACHINE LEARNING MODEL AND NARRATIVE GENERATOR FOR PROHIBITED TRANSACTION DETECTION AND COMPLIANCE

Resumen de: US20260179097A1

There are provided systems and methods for a machine learning model and narrative generator for prohibited transaction detection and compliance. A service provider server, such as an electronic transaction processor, may generate a machine learning model using a supervised training technique, which may detect transactions that may be money laundering. The model may be iteratively trained by detecting flagged transactions and outputting those transactions to an agent for identification of false positives, which may be used to retrain the model. When outputting the flagged transactions, a narrative may be generated using an explainer graph and a machine learning prediction explainer that identifies the features of the transaction data that caused the transactions to be flagged. Further, once the model is trained additional transactions may be processed to determine whether the features of those transactions indicate prohibited behavior.

PLATFORM FOR FACILITATING AN AUTOMATED IT AUDIT

Resumen de: US20260179106A1

A platform for facilitating an automated IT audit. The platform may have a frontend allowing users to access the platform, a backend configured to perform processing, and a data collection system equipped to interface with connectors. The backend may include at least one server equipped to send, receive, store, and process data; a testing and analyzing system that may make use of algorithms, machine learning, and artificial intelligence in order to test and analyze the collected data against pre-configured best practice standards and policies, and a reporting system that may be configured to transmit the tested and analyzed data to the frontend. The backend system may be configured to opine on the data and generate specific recommendations about future developments of an auditee's IT infrastructure, allowing an audit to be completed automatically from start to finish by the use of the software, eliminating the need for human intervention.

SYSTEMS AND METHODS FOR SEIZURE PREDICTION AND DETECTION

Nº publicación: AU2026204165A1 25/06/2026

Solicitante:

CERIBELL INC
Ceribell, Inc.

Resumen de: AU2026204165A1

Abstract The present disclosure provides systems and methods for seizure detection. The method for seizure detection may include receiving a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject, preprocessing the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments, extracting a plurality of features from each temporal data segment for each channel, and applying a machine learning algorithm to the plurality of features to perform a seizure binary classification for each temporal data segment for each channel. A control policy may be employed to determine a seizure burden on the aggregated seizure binary classifications. When the seizure burden is equal to or exceeds a threshold, a notification may be generated. The notification may be usable by a healthcare practitioner to assess whether the subject may be at risk of having a seizure. Abstract wo 2021/055154 EEG Device Module Seizure Detection Module PCT/US2020/048258 ay a y w o EEG Device Module Seizure Detection Module