Alerta

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Artificial Intelligence System for Operation Management

Resumen de: US20260186942A1

Implementations include obtaining a first dataset associated with a negative operation cycle event type; determining, via a first set of machine learning components, a set of causation identifiers corresponding to the negative operation cycle event; determining, via a machine learning classification component, a set of classifications comprising a classification of each causation identifier of the set of causation identifiers; training a second set of machine learning components to classify negative operation cycle events having the negative operation cycle event type according to the set of classifications; determining, based on a second dataset, an event classification associated with a negative operation cycle event; determining at least one rectification operation parameter associated with a rectification operation corresponding to the negative operation cycle event; and outputting assignment content configured to cause a user interface of a user device to present a user interface element associated with the rectification operation.

INCREASING DATA SOURCE FUNCTIONALITY THROUGH IMPLEMENTATION OF MACHINE LEARNING AND GENERATIVE ARTIFICIAL INTELLIGENCE

Resumen de: US20260187489A1

Increasing programming functionality of data sources through the use of Artificial Intelligence (AI), specifically Machine Learning (ML) models and Generative AI (GenAI). ML model(s) that have been trained to acquire a knowledge base from a data source are implemented and once acquired, further ML models are implemented that have been trained to identify, based on the knowledge base, opportunities for additional programming functionalities. Once the additional programming functionalities have been determined, the present invention implements GenAI to generate at least a portion of the technology stack associated with the data source. Generating a portion of the technology stack includes one or more rebuilding/revising the data source, generating a new data source, revising use application and/or data source management software and/or generating new use application and/or data source management software.

MACHINE LEARNING (ML) - ASSISTED PRESENTATION HOSTING PLATFORM

Resumen de: US20260187414A1

0000 Disclosed herein are systems and methods for providing a machine learning (ML)—assisted presentation hosting platform. An example method of preparing ML models of the presentation hosting platform comprises: receiving a first training dataset comprising: a plurality of different presentations having a plurality of different activities, one or more presentation scenarios for each presentation, and one or more devices and/or software that perform the plurality of activities; training a first ML model using the first training dataset to predict presentation scenarios for different types of presentations; receiving a second training dataset comprising a mapping between the one or more presentation scenarios and a plurality of devices and/or software with different configuration, resources, capabilities, and/or load; and training the second ML model using the second training dataset to predict a mapping of the activities of each presentation to devices and/or software of participants of the presentation.

MACHINE LEARNING AGENT WITH SEMANTIC ENTITLEMENT

Resumen de: US20260189557A1

0000 A computing system including one or more processing devices configured to receive a semantic entitlement that semantically specifies an access permission scope of a machine learning (ML) agent included in an ML system. The semantic entitlement has a natural language format. At least in part by processing the semantic entitlement at a generative language model included in the ML system, the one or more processing devices identify one or more resources that are included in the access permission scope indicated in the semantic entitlement. The one or more processing devices grant an ML agent of the plurality of ML agents access to the one or more identified resources. At the ML agent, the one or more processing devices compute an agent output based at least in part on the one or more identified resources. The one or more processing devices output the agent output to an additional computing process.

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.

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.

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.

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.