Alerta

MACHINE LEARNING MODEL POSITIONING PERFORMANCE MONITORING AND REPORTING

Resumen de: EP4773657A2

0001 Disclosed are techniques for wireless communication. In an aspect, a network entity receives a provide location information message from a user equipment (UE), the provide location information message including one or more positioning estimates derived by the UE during one or more positioning inference occasions of a machine learning model, wherein the machine learning model is applied to one or more measurements of a wireless channel between the UE and a network node during each of the one or more positioning inference occasions, and transmits a performance report indicating a performance of the machine learning model at least in deriving the one or more positioning estimates during the one or more positioning inference occasions.

SPATIOTEMPORAL TRANSFER MACHINE LEARNING

Resumen de: WO2025046310A1

A computer-implemented, machine learning method for spatiotemporal transfer learning. Sectors of an area are aggregated using preprocessed data from one or more data sources. The sectors are clustered based on different representations obtained for each context feature associated with each of the sectors. One or more context features that have a higher impact on a target feature to be predicted than other context features are identified from a plurality of context features and aggregated to obtain a representation of the area. Using the representation of the area, a particular sector within each of the clustered sectors is selected based on similarity to a respective centroid of the cluster to generate a set of particular sectors. A model associated with a source sector of the set of particular sectors is trained. The method has applications including, but not limited to smart cities, public safety and energy optimization.

CONTROL VARIABLE OPTIMIZATION METHOD, BIORESOURCE PRODUCTION METHOD, AND BIORESOURCE PRODUCTION SYSTEM

Resumen de: EP4773049A1

0001 Provided are a control variable optimization method capable of determining improved culture conditions using a predictive model based on machine learning, and a bioresource production method and a bioresource production system using the same. 0002 A bioresource production system S according to another aspect of the present invention includes: a cultivation system B for performing bioresource production; and a control variable optimization system A for optimizing control variables obtained from the cultivation system. 0003 The control variable optimization system separates the control variables into initial variables and manipulated variables, creates predictive models adapted to the initial variables and the manipulated variables, respectively, and optimizes the control variables by combining the predictive models.

METHOD FOR ESTIMATING A REMAINING USEFUL LIFE OF A BATTERY, NON-TRANSITORY COMPUTER-READABLE MEDIUM, AND ELECTRONIC ESTIMATION DEVICE

Resumen de: WO2026137061A1

The method (200) comprises extracting (210) a set of selected features from at least one charge-discharge cycle (C) of a battery and estimating (230) the remaining useful life of the battery (1) by applying a machine learning model (140) to the set of selected features. The machine learning model (140) is trained during a preliminary phase (100), comprising: extracting (110) a set of primary features from the charge-discharge cycles (C) of reference batteries; processing (120) the set of primary features by applying an outlier detection process (25) and/or a data smoothing process to a primary feature (F) versus charge-discharge cycles (C) curve (F(C)A); selecting (130) the features from among the processed primary features using correlation between the set of primary features and the remaining useful lives of the reference batteries; and training the machine learning model (140) with a training set of the selected features extracted from multiple charge-discharge cycles (C) of the reference batteries.

Systems and Methods for Identifying Causes of Elevated Liver Enzymes in Dogs

Resumen de: US20260188493A1

A method for identifying a cause of elevated liver enzymes includes receiving new patient data, receiving a machine-learning based diagnostic model and a knowledge based diagnostic model, determining whether the machine-learning based diagnostic model indicates a cause of elevated liver enzymes for the new patient data, and in a case where the machine-learning based diagnostic model indicates the cause of elevated liver enzymes for the new patient data, assessing the cause of elevated liver enzymes using the knowledge based diagnostic model.

SYSTEMS AND METHODS WITH ENSEMBLE WORD EMBEDDING AND TABULAR FEATURE DATASET FOR IMPROVED CONDITION MODEL PERFORMANCE

Resumen de: US20260188447A1

Text data describing a patient's visit to a healthcare facility is extracted from a document and processed to remove stop words. Then, words associated with a medical condition can be determined and filtered to remove fully documented phrases that describe the medical condition. The filtered words are cleansed, ordered, and used to generate a final data set, which is used to train a first machine learning model to produce a numerical value that indicates a likelihood that the patient's visit to the healthcare facility is related to the medical condition. Features particular to the medical condition have feature attributes derived from historical data including medications, services, and observations pertaining to the medical condition. A data structure containing the numerical value, the features, and the feature attributes is input to a second machine learning model for generating a patient-specific score as evidence of the medical condition found during the patient's visit.

ELECTRONIC SUBMISSION OF DOCUMENTS TO ENTITIES BASED ON MACHINE LEARNING

Resumen de: US20260187158A1

0000 According to an embodiment of the present invention, a computer system comprises a processor set, one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media to cause the processor set to perform operations. The system analyzes a document to obtain parameters including an area of research in the document and metrics for quality of the document. A document influence score of the document is determined based on the parameters. An author influence score is determined based on a quantity of citations to an author of the document. An entity is selected for submission of the document based on the document influence score and the author influence score. The document is electronically submitted to the selected entity. Embodiments of the present invention further include a method and computer program product for electronically submitting a document in substantially the same manner described above.

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.

SYSTEM AND METHOD FOR CONVERSATION WITH AN AI COMPANION

Resumen de: US20260187116A1

A system and method for facilitating a collaborative conversation with an AI companion are provided. The system utilizes artificial intelligence and machine learning to monitor end user well-being, provide reminders for routine activities, provide real-time notifications to facilitators, and facilitate simulated social interactions with an AI companion. The system comprises a computing device, a server platform, and at an Application Programming Interface (API), configured to facilitate communication between the computing device and the server platform. The server platform houses a knowledge base and a learning language model. Information and conversational prompts are received from the end user via the computing device and relayed via the API to the server platform and processed by the learning language model with reference to the knowledge base, such that a response is formulated by the learning language module and transmitted from the server platform to the end user via the API and computing device.

INSIGHT-DRIVEN FRAMEWORK FOR ADAPTIVE OPTIMIZATION, EQUATION DISCOVERY, AND HYBRID COMPUTING ACROSS DOMAINS

Resumen de: US20260187180A1

0000 This invention presents a unified framework for addressing complex, multi-domain challenges through adaptive design optimization, equation discovery, and hypothesis generation. Central to the framework is the Mathematical Sphere Framework (MSF), which employs advanced machine learning and hybrid computing to interrelate equation families across fields such as CFD, FEM, CAD, and PLM. MSF enables cross-domain optimization with transparent, physics-based representations, fostering continuous insight generation and system evolution. A neural-assisted system refines equations from experimental and real-world data, advancing theoretical models and design exploration. Hybrid computing combines classical preprocessing with quantum optimization to enhance computational efficiency. A digital twin provides real-time simulation and predictive analysis, while lifecycle adaptability dynamically optimizes parameters across product stages. By improving efficiency, scalability, and interoperability, this invention transforms engineering workflows, supports innovation, and fosters cross-industry applications, including aerospace, energy, and manufacturing, driving progress in an ever-evolving landscape.

RISK ASSESSMENT IN A CHANGE REQUEST

Resumen de: US20260187546A1

Embodiments receive a change request for an environment from a first system, predict an impact of the change request of the second system using a first machine learning (ML) model and output an existing system prediction impact based on the predicted impact of the change request of the second system, predict the impact of the change request of at least one third system using a second ML model and output a dependent system prediction impact based on the predicted impact of the change request of the at least one third system, receive historical impact data associated with the change request from a knowledge base, generate an overall predictive score (OPS) based on the existing system prediction impact, the dependent system prediction impact, and the historical impact data, and send an approval decision output signal based on a third ML model which is trained on the OPS.

FACILITATING EFFICIENT GENERATION OF EVALUATOR LOGIC USING ARTIFICIAL INTELLIGENCE

Resumen de: US20260187521A1

In various examples, systems and methods are disclosed related to facilitating management of evaluator logic. In particular, evaluator logic is generated in association with a requirement in an effective and efficient manner. To efficiently generate evaluator logic, artificial intelligence (AI) technology may be used to perform various aspects of the evaluator logic generation. In particular, a logical formula that represents the requirement may be generated using a temporal logic. The logical formula may then be used to generate, via one or more machine learning models, an evaluator logic in an executable format. In accordance with efficiently generating evaluator logic, the evaluator logic may be implemented to evaluate a product, a system, or other technology.

ANOMALY IDENTIFICATION USING FUZZY-MATCH BASED ACCOUNT LINKING

Resumen de: US20260189582A1

0000 Example implementations relate to anomaly detection in a network environment. In an example, a similarity score for one or more attributes between a target user and a candidate user is calculated based on n-grams generated from the one or more attributes. Link data linking the target user to the first candidate user for the first attribute is generated if the similarity score between the target user and the first candidate user is greater than a first threshold. A machine learning model that identifies a likelihood whether the target user is linked to a terminated entity based on the one or more attributes is trained using the link data. The machine learning model applies respective weights to each of the one or more attributes. The respective weights associated with the one or more attributes is updated based on feedback data associated with changes in operating permissions within a predetermined time period.

MULTI-LAYER ARTIFICIAL INTELLIGENCE FOR LANGUAGE MODEL CONTEXT SELECTION

Resumen de: US20260187375A1

A processing system may sectionalize a text file into overlapping sections, generate, for each section, a question from a text of the section, where the question is associated with the section in a question-section pair, and apply each question to a machine learning language model to generate answers to the questions. For each question, the applying may include appending the text of the section as supplemental prompt content. The processing system may associate each question with an answer to generate a respective question-answer pair and may group the question-answer pairs into groups based upon a similarity metric. The processing system may then identify, for at least a first group, a text sequence that is within an intersection of the sections in the question-section pairs of the first group, where the text sequence is associated with the first group as a result of the identifying.

ENSEMBLE MACHINE LEARNING MODELS FOR PREDICTION AND UNCERTAINTY QUANTIFICATION OF NETWORK USAGE EXPERIENCE AND CONFERENCE APPLICATION EXPERIENCE

Resumen de: US20260187544A1

Data sets are analyzed with EDA for determining feasible data for training. Monitoring of stations can be passive by snooping data packets, and can be active by direct communication with an operating system. A conference application currently running on a specific station is detected from data packets associated with the specific station. A set of channel experiences and a set of conference application experiences are predicted using the experience prediction model. A sliding window can define a time period for predictions and weighting can define relativity between different inputs. The experience prediction module has been trained with validated channel statistics collected at network sensors dispersed at different locations on the enterprise network.

TRAINING A LANGUAGE MODEL FOR DOMAIN-SPECIFIC QUERIES

Resumen de: US20260187167A1

A large language model (LLM) is trained to provide domain specific answers. First, item information is extracted from a catalog of items. A machine-learning model is then prompted to generate a set of queries based in part on the item information associated with the items. Training examples are generated that are associated with the items using a first subset of queries from the set. Each training example is for a corresponding item, and includes a query (that is associated with the corresponding item and is from the first subset) and some item information that is an answer to the query and that is associated with the corresponding item. The LLM is trained using the training examples. Performance of the LLM is evaluated using a second subset of the set of queries that is separate from the first subset.

Artificial Intelligence System Having a Prediction Engine for Determining Predicted Metrics

Resumen de: US20260187525A1

Implementations include obtaining, from a database, a first set of data associated with an entity and generating, by a model generator, a machine learning model based on the first set of data. Implementations may include generating a predictive model by training the machine learning model using at least a portion of the first set of data. The predictive model may be used to determine, based on a second set of data, a predicted metric associated with a revenue cycle corresponding to the entity. Implementations may include outputting prediction data indicative of the predicted metric.

OPTIMIZING LEGACY PROTOCOLS FOR INTERNET OF THINGS DEVICES

Resumen de: US20260189633A1

A computer-implemented method for managing Internet of Things (IoT) protocols. A processor set continuously monitoring a number of IoT devices to collect a set of data from the number of IoT devices. The processor set trains a number of machine learning models using the set of data as training data. The processor set performs predictive analysis using the number of machine learning models to determine state of each protocol for the number of IoT devices based on real-time data from the set of data. The processor set identifies a number of legacy protocols from the protocols for the number of IoT devices based on the states of protocols for the number of IoT devices using the number of machine learning models. The processor set migrates the number of legacy protocols to a number of new protocols to optimize performance for the number of IoT devices.

COMMUNICATION NETWORK MANAGEMENT SYSTEM WITH FEDERATED LEARNING

Resumen de: US20260189599A1

0000 A processing system may obtain first data samples relating to a first network zone and second data samples relating to a second zone of the communication network, and train a first machine learning model for a first prediction task using the first data samples and a second machine learning model for a second prediction task using the second data samples, where the prediction tasks are of a same type. The processing system may next tune an aggregated machine learning model in accordance with first parameters of the first machine learning model and second parameters of the second machine learning model, where the tuning comprises generating third parameters for the aggregated machine learning model, apply an input data vector to the aggregated machine learning model to obtain an output, and perform a remedial action in the communication network in response to the output.

CROSS DIRECTIONAL HYPERPARAMETER TUNING

Resumen de: US20260187481A1

0000 Disclosed herein are system, method, and computer program product embodiments for using cross directional hyperparameter tuning. A system identifies a hyperparameter set to configure a first machine learning model, a first evaluation data set, and a machine learning evaluation process. The system determines a first tuned hyperparameter set for the first machine learning model by performing cross directional hyperparameter tuning, including iterating over the set of hyperparameters. At each iteration, the system selects a hyperparameter from the set, where the selected hyperparameter is a value within a range of values. The system iterates over the range of values, at each iteration, generates a score for the machine learning model via an evaluation process configured using the selected hyperparameter, set of hyperparameters, and the first evaluation data set. The system updates the selected hyperparameter. The system then saves the selected hyperparameter corresponding to a greatest score at the set of hyperparameters.

Alert-Based Artificial Intelligence System for Change Detection

Resumen de: US20260187728A1

0000 A solution for processing data and generating alerts is provided herein. The solution may include receiving data from a set of disparate data sources, performing a transformation operation on the data using a first set of machine learning models to generate structured data for storage in a database in accordance with a unified data schema, and performing an anomaly detection operation on the structured data using a second set of machine learning models to identify an anomaly associated with a transactional workflow. An alert event may be generated based on the anomaly. An alert profile associated with a user device may be determined, and alert data based on the alert event and the alert profile may be outputted. The alert data may be configured to cause a user interface of the user device to present a user interface element associated with the alert event.

PLATFORMS, SYSTEMS, AND METHODS FOR TRAINING MACHINE LEARNING MODELS WITH SPECIALIZED DATA

Resumen de: US20260188430A1

0000 According to one aspect, there is provided a computer-implemented method for training artificial intelligence models with specialized biologic data in an AI-guided analytic platform for development of a biologic synthesis process, comprising: collecting multimodal biologic data including at least one of a gene expression level, mRNA, metabolic reaction fluxes, or intracellular metabolite concentrations from biologic systems; processing the collected biologic data through data normalization and quality assurance steps to create model-ready data; and generating at least one output predicting an effect of genetic modification on a metabolite level or a reaction flux.

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.

PROGNOSTIC RISK ANALYSIS SYSTEM FOR HEAD AND NECK CANCER

Resumen de: US20260188505A1

0000 A prognostic risk analysis system for head and neck cancer includes a data collection module, a data processing module, a model training module, an analysis module, a risk stratification module and a clinical application module. The data collection module collects a training data of patients, each training data including a clinical data and an image data. The data processing module performs a preprocessing process on the training data to extract first feature values. The model training module trains a machine learning algorithm to build a prediction model by using the first feature values. The analysis module analyzes, based on the prediction model, a dataset of a patient to generate a prognostic risk data. The risk stratification module stratifies the prognostic risk data into a low-risk group, an intermediate-risk group or a high-risk group. The clinical application module applies the prognostic risk data and the risk groups to clinical practice.

ATTRIBUTION OF IN-STREAM WATER QUALITY VIA MONITORING REPORTING AND VERIFICATION SENSOR-GEOSPATIAL FUSION NETWORKS

Nº publicación: AU2025216427A1 02/07/2026

Solicitante:

VIRRIDY DIGITAL LLC
VIRRIDY DIGITAL LLC

Resumen de: AU2025216427A1

Attribution of in-stream water quality via monitoring reporting and verification sensor geospatial fusion networks may be provided by a system comprising a plurality of separate water fixtures, wherein each of the plurality of separate fixtures includes an optical sensor configured to measure a water quality metric of a water source and a data transmission system configured to transmit source data from each of the plurality of water fixtures, respectively, a remote data source configured to transmit remote data which includes survey data about one or more land use metrics, a contamination source detection system configured to receive the source data from the plurality of water fixtures and the remote data from the remote data source and employ a process-based land-surface model ensemble and a machine learning-based model to identify a land-based source of predicted contamination of a water source based upon the remote data and the source data.