Alerta

MACHINE LEARNING NETWORKS, ARCHITECTURES AND TECHNIQUES FOR DETERMINING OR PREDICTING DEMAND METRICS IN ONE OR MORE CHANNELS

Resumen de: US2025315681A1

This disclosure relates to artificial intelligence (AI) and machine learning networks for predicting or determining demand metrics across multiple channels. An analytics platform can receive channel events from multiple channels corresponding to geographic areas, and channel features related to demand conditions in the channels can be extracted from the channel events. During a training phase, the channel features can be accumulated into one or more training datasets for training one or more demand prediction models. The one or more demand prediction models can be trained to predict or determine demand metrics for each of the channels. The demand metrics can indicate or predict demand conditions based on the current conditions in the channels and/or based on future, predicted conditions in the channels. Other embodiments are disclosed herein as well.

ANALYSIS OF STRUCTURED DATA IN CHAINS OF REPEATABLE ACTIONS WITHIN AN ARTIFICIAL INTELLIGENCE-BASED AGENT ENVIRONMENT

Resumen de: US2025315683A1

A framework for machine learning modeling of structured data that includes one or more artificial intelligence-based agents. These artificial intelligence-based agents are configured to create and execute chains of repeatable actions to perform user-driven and user-defined workflows with a given problem set and identified outcomes. Structured data that has been processed is fed by the artificial intelligence-based agents to language models to formulate actions operate as tools for analyzing a problem set that can be chained together to address a given workflow, in one or more prompts for constructing and delivering the identified outcomes. Chains of repeatable actions for saved and utilized for additional workflows having similar problem sets, and executed based on pre-identified triggers.

METHOD AND SYSTEM FOR ENABLING CONTINUOUS MACHINE LEARNING USING DOMAIN-SPECIFIC LEARNING PROCESSES

Resumen de: US2025315692A1

A method and system for continuous machine learning is disclosed. A set of domain-specific learning processes (LPs) from an external repository are obtained. Each LP of the domain-specific LPs is associated with at least one domain-specific knowledge graph representing learned parameters, patterns, and processing capabilities. Operational data from multiple sources is received and pattern representation is generated. One or more relevant LPs from the set of domain-specific LPs are identified by matching the pattern representation with at least one knowledge graph. The identified one or more LPs are executed to generate execution results and are validated through a contradiction resolution upon detecting the existence of contradictions between execution results and existing domain knowledge during the execution. The one or more LPs and their associated domain-specific knowledge graphs, trust relationships between LPs are updated based on validation outcomes and are submitted to the external repository.

Techniques For Using Machine Learning To Test Integrated Circuit Dies

Resumen de: US2025315583A1

A computing system includes a processor circuit configured to receive test data generated from testing integrated circuit dies in a test flow. The computing system includes a machine learning model that uses the test data generated from the test flow to predict bench results that are indicative of which ones of the integrated circuit dies fail to satisfy a manufacturing protocol when the integrated circuit dies are coupled to circuit boards.

System and Method for Federated Two-Stage Compression Within a Persistent Cognitive Machine

Resumen de: US2025317154A1

A system and method for federated two-stage compression with federated joint learning. The system and method proposed allow for fast and efficient lossless data compression of a large variety of data types. The system and method have a variety of real-world applications, including deep learning solutions for telemetry, tracking, and command subsystems for satellites. Satellites and their control centers are incredibly spaced apart which makes data compression an extremely important process to transmit large sets of information in a low-latency, high-efficiency environment. The proposed system and method utilize probability prediction driven arithmetic long short-term memory system for data compression.

PREDICTING ALBUMINURIA USING MACHINE LEARNING

Resumen de: US2025316377A1

An example embodiment may involve obtaining, by a computing system, an observation of demographic values of an individual, vital sign values of the individual, and blood test values of the individual: applying, by the computing system, a machine learning model to the observation, wherein the machine learning model was trained with a training data set, wherein the training data set contained observations of corresponding demographic values, vital sign values, blood test values, and either urine albumin-to-creatinine ratio (UACR) values or urine protein-to-creatinine ratio (UPR) values for a plurality of individuals, and wherein the machine learning model is configured to provide predictions of whether further observations are indicative of undiagnosed albuminuria or proteinuria; and providing, by the computing system, a prediction of whether the individual exhibits undiagnosed albuminuria or proteinuria based on the observation.

SYSTEM AND METHOD FOR GENERATING A PATH LOSS PROPAGATION MODEL THROUGH MACHINE LEARNING

Resumen de: US2025317224A1

The present disclosure provides a system and a method for generating a path loss propagation model through machine learning. The system generates a path loss propagation model for fifth generation (5G) networks for network planning. The path loss model predicts a reference signal received power/signal to noise interference ratio (RSRP/SINR) by leveraging a fourth generation (4G) user data.

System and Method for Performing Fault and Event Analysis in Electrical Substations

Resumen de: US2025315339A1

A system and method performing fault and event analysis in electrical substations comprises receiving a disturbance record triggered by an intelligent electronic device (IED) at an electrical substation, pre-processing the received disturbance record to extract at least one variable time series data of plurality of electrical parameters, generating a causality matrix based on the extracted at least one variable time series data by applying causal analysis, predicting, using a Machine learning (ML) module, a fault type at least based on the causality matrix, retrieving, from a knowledge database, a plurality of probable causes corresponding to the predicted fault type, determining at least one exact cause from the plurality of probable causes based on the causal pattern, and providing the fault type, the plurality of probable causes, and the at least one exact cause to a user.

MACHINE-LEARNING MODEL(S) FOR ESTIMATING RAN FUNCTIONALITY MACHINE LEARNING MODEL IMPACT ON PERFORMANCE MEASUREMENT COUNTERS

Resumen de: WO2025210109A1

This specification relates to the execution of machine-learning models on user devices. According to a first aspect of this specification, there is described apparatus comprising: means for receiving a network configuration derived from a plurality of machine-learning models, each machine-learning model directed towards a respective one or more radio access network functionalities; means for receiving a plurality of predicted performance measurement counters output from a plurality of machine-learning performance measurement models, each machine-learning prediction measurement model corresponding to one of the plurality of machine-learning models; and means for processing, using a common machine-learning performance measurement counter model, the network configuration and the plurality of predicted performance measurement counters to determine a model output comprising, for one or more performance measurement counters, a respective plurality of impact scores. Each impact score is indicative of a predicted impact of a corresponding machine-learning model in the plurality of machine-learning models on the respective performance measurement counter of said impact score for the network configuration.

SIMULATION-DATA BASED PREDICTIVE MODELS FOR GAS SEPARATION PLANTS

Resumen de: WO2025209965A1

The invention concerns a computer-implemented method for predicting performance parameter values of at least one individual gas separation stage, the method comprising: - receiving (162) a set of data points (21), each data point comprising operating parameter values indicative of a configuration or state of a separation stage of a gas separation plant (1800) and comprising performance parameter values obtained by simulating the operation of said separation stage given the operating parameter values of said data point; - using (164) the received set of data points as a training data set in a machine learning process for generating a trained predictive model (1704-1708, 2304); - receiving (166) input parameter values being indicative of one or more operation parameter values for the at least one separation stage; - using (168) the trained model for predicting performance parameter values of the at least one individual separation stage as a function of the input parameter values; and - outputting (170) the predicted performance parameter values for use in the design or control of the single separation stage or of the plant comprising the same.

Method, System, and Computer Program Product for Ensemble Learning With Rejection

Resumen de: US2025315740A1

Methods, systems, and computer program products are provided for ensemble learning. An example system includes at least one processor configured to: (i) generate a rejection region for each baseline model of a set of baseline models (ii) generate a global rejection region based on the rejection regions of each baseline model; (iii) train an ensemble machine learning model; (iv) update, based on a baseline model predictive performance metric for each baseline machine learning model, the set of baseline machine learning models; and (iv) repeat (i)-(iv) until there is a single baseline model in the set of baseline models or a predictive performance or global acceptance ratio of the ensemble model satisfies a threshold.

REPORTING OF INFERENCE ACCURACIES OF QUANTIZED MODELS FOR ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING PERFORMANCE MONITORING

Resumen de: WO2025208320A1

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit, to a network node, an indication of an inference accuracy level associated with a quantized artificial intelligence or machine learning (AI/ML) model for an AI/ML task, wherein the inference accuracy level is indicative of a relative accuracy of the quantized AI/ML model with respect to a floating-point AI/ML model for the AI/ML task. The UE may receive, from the network node, signaling associated with AI/ML performance monitoring based at least in part on the indication of the inference accuracy level. Numerous other aspects are described.

METHODS AND SYSTEMS FOR MITIGATING ERRORS IN A CAUSAL INFERENCE PROCESS

Resumen de: WO2025209635A1

Methods and server systems for mitigating errors in a causal inference process are described herein. The method performed by a server system includes accessing, for each of target and control entity, pre-treatment time series information and post-treatment time series information. Then, generating, by Machine Learning (ML) model, pre-treatment prediction time series information for target entity based on pre-treatment time series information of control entity. Then, computing a set of prediction error values by comparing pre-treatment prediction time series information and pre-treatment time series information of target entity. Then, generating, by ML model, post-treatment prediction time series information for target entity based on pre-treatment time series information of target entity and post-treatment time series information of control entity. Then, generating prediction range information based on post-treatment prediction time series information and set of prediction error values.

MACHINE LEARNING-BASED THERAPY DEVICE RESUPPLY PREDICTIONS

Resumen de: WO2025212863A1

Techniques for improved machine learning are provided. Forecasted acquisitions data indicating predicted future acquisitions of one or more respiratory therapy systems is determined. An active devices prediction is generated based on processing at least a subset of the forecasted acquisitions data using a first trained machine learning model trained based on historical acquisitions of one or more respiratory therapy systems. A resupply effectiveness prediction is generated using a second trained machine learning model trained based on historical consumption of one or more consumables for the one or more respiratory therapy systems. A consumables prediction is generated based on the active devices prediction and the resupply effectiveness prediction.

AN INTELLIGENT CENTRALIZED AGENT FOR AUTONOMOUSLY ORCHESTRATING MULTIPLE DATA TOOLS

Resumen de: WO2025212608A1

An intelligent centralized agent comprising: a dynamic planner; a context short-term memory specific to an interaction session; and at least one data tool that enables the intelligent centralized agent to interact with the application programming interface, the external long-term memory, the machine learning model, and the user interface; wherein the dynamic planner receives input from the application programming interface to make decisions regarding subsequent actions based on the interaction session from the context short term memory, the data tool, and the machine learning model. This unique system provides the intelligent centralized agent with vast access to externally stored data which enables users to resolve questions or queries quickly and reliably in milliseconds.

SYSTEMS AND METHODS FOR MACHINE LEARNING FEATURE GENERATION

Resumen de: WO2024119010A1

A method and apparatus for generating an ML model may include: generating an ML feature template comprising a first grouping of first ML feature variables and a second grouping of second ML feature variables; generating ML features by combining a respective one of each of the first ML feature variables with a respective one of each of the second ML feature variables; training a first ML model utilizing the ML features and first training data to generate an ML output; analyzing the ML output to determine a prediction accuracy of the ML features; based on the prediction accuracy of the ML features, selecting a subset of the ML features; training a second ML model based on the subset of the ML features and the first training data; and providing a network transaction to the second ML model to generate a classification of the network transaction.

PREDICTION DEVICE, PREDICTION METHOD, AND PREDICTION PROGRAM

Resumen de: EP4629144A1

A prediction device that accurately and efficiently predicts drug discovery of desired drugs as well as efficacy and side effects of drugs by integrating chemical substance information of compounds, information acquired at the time of administration to the cells, and biological or clinical information. The prediction device has an acquisition unit that acquires chemical substance information and pharmacological information of the drug; an estimation unit that estimates estimated information of the drug by performing machine learning using the chemical substance information and pharmacological information; and an output unit that predicts and output both efficacy and side effects of the drug on an organism by retraining a model of the machine learning on the basis of the estimated information.

CHANNEL RECOMMENDATIONS USING MACHINE LEARNING

Resumen de: CN120283235A

Techniques are discussed herein for generating user profile data, including one or more frequent channels, related users, and/or related topics within a communication platform. In some examples, a machine learning model may receive user interaction data (sent messages, read messages, channel publication, shared documents, frequent keywords used, etc.) associated with a communication platform, and output one or more frequent channels, related users, and/or related topics. The communication platform may then associate the one or more frequent channels, related users, and/or related topics with profile data for the users. In some examples, a communication platform may present different frequent channels, related users, and/or related topics associated with a profile page based on interaction actions associated with a user account viewing the profile page.

SYSTEM AND METHOD FOR PERFORMING FAULT AND EVENT ANALYSIS IN ELECTRICAL SUBSTATIONS

Nº publicación: EP4629009A1 08/10/2025

Solicitante:

ABB SCHWEIZ AG [CH]
ABB SCHWEIZ AG

Resumen de: EP4629009A1

The present disclosure describes a system and method performing fault and event analysis in electrical substations is disclosed. The method comprises the step of receiving a disturbance record triggered by an intelligent electronic device (IED) at an electrical substation, preprocessing the received disturbance record to extract at least one variable time series data of plurality of electrical parameters, generating a causality matrix based on the extracted at least one variable time series data by applying causal analysis, predicting, using a Machine learning (ML) module, a fault type at least based on the causality matrix, retrieving, from a knowledge database, a plurality of probable causes corresponding to the predicted fault type, determining at least one exact cause from the plurality of probable causes based on the causal pattern, and providing the fault type, the plurality of probable causes, and the at least one exact cause to a user.