Alerta

OPTIMAL MULTICORE OPTIMIZATION FOR MACHINE LEARNING MODEL GENERATION

Absstract of: US2025371419A1

According to an embodiment, a method is proposed carried out by a computer system for tuning hyperparameters in a machine learning model, the computer system having a processing unit designed to execute a plurality of processes in parallel. The method comprising executing a plurality of independent hyperparameter search methods in different parallel processes of the processing unit, the results of the tests of the combinations of hyperparameters being stored in a memory in the computer system shared among the various processes, and wherein each process assesses whether a combination of hyperparameters searched for has already been tested by another process based on the results of tests stored in memory, and takes into account, in its own test history, the results of tests stored in the memory if the combination of hyperparameters searched for has already been tested.

SYSTEMS AND METHODS OF PROPERTY VALUATION

Absstract of: US2025371570A1

The disclosure features a method which includes inputting or receiving information on one or more features of a plurality of residential properties and prices of the residential properties including a marketed price, a listing price, and a closing price, providing the information to a Machine Learning Algorithm to determine the relationship between the one or more features and the prices of the residential properties to create a Machine Learned Model, inputting or receiving information on one or more features of a new residential property into the Machine Learned Model, and predicting a base price of the new residential property from the Machine Learned Model based on the one or more features of the new residential property. The disclosure also features one or more non-transitory, computer-readable storage media storing instructions capable of performing the method and a computer or computer system capable of performing the method.

PREDICTION OF EQUIPMENT-RELATED EVENTS USING MACHINE LEARNING

Absstract of: WO2025250329A1

Techniques are disclosed herein for machine-learning (ML)-assisted event prediction for industrial machines (106). A first set of embeddings (1986a) can be generated based on labeled first event data, which can be labeled with classifiers (1989b) determined based on signaling channel (110b) information for the first event data. A neural network (300) can be trained, using the classifiers (1989b), to generate (i) a similarity score for the first set of embeddings and the second set of embeddings and (ii) a classifier (1989b) recommendation for the second set of embeddings. The second set of embeddings can be generated based on data collected using condition monitoring sensors (104a) for a particular industrial machine. Accordingly, the system (200) can generate alerts, recommendations, and/or notifications based on the automatically classified data encoded in the second set of embeddings.

METHODS AND APPARATUS FOR MACHINE LEARNING BASED MALWARE DETECTION

Absstract of: US2025371152A1

Apparatus and methods describe herein, for example, a process that can include receiving a potentially malicious file, and dividing the potentially malicious file into a set of byte windows. The process can include calculating at least one attribute associated with each byte window from the set of byte windows for the potentially malicious file. In such an instance, the at least one attribute is not dependent on an order of bytes in the potentially malicious file. The process can further include identifying a probability that the potentially malicious file is malicious, based at least in part on the at least one attribute and a trained threat model.

METHODS AND SYSTEMS FOR IMPROVED AUTOMATED MACHINE LEARNING AND DATA ANALYSIS

Absstract of: US2025371427A1

The disclosed methods and systems automate the process of building machine learning models. A user interface receives a selection of a dataset for a machine learning experiment. An execution plan for the experiment is determined based on the selected dataset. The experiment is executed according to the execution plan to generate a plurality of machine learning models. The performance of the generated models is evaluated based on one or more performance metrics. A model is selected from the generated models based on the evaluation of the performance metrics. The selected model may be stored for future use.

Federated Machine Learning Management

Absstract of: US2025371429A1

Techniques are disclosed in which a computer system receives, from a plurality of user computing devices, a plurality of device-trained models and obfuscated sets of user data stored at the plurality of user computing devices, where the device-trained models are trained at respective ones of the plurality of user computing devices using respective sets of user data prior to obfuscation. In some embodiments, the server computer system determines similarity scores for the plurality of device-trained models, wherein the similarity scores are determined based on a performance of the device-trained models. In some embodiments, the server computer system identifies, based on the similarity scores, at least one of the plurality of device-trained models as a low-performance model. In some embodiments, the server computer system transmits, to the user computing device corresponding to the low-performance model, an updated model.

SYSTEMS AND METHODS FOR PROVIDING LOCATION-BASED TRAVEL OBJECTIVE NOTIFICATIONS

Absstract of: US2025369762A1

In some aspects, the techniques described herein relate to a method including: receiving, by a collaboration service, location data of a user, wherein the location data includes a timestamp; verifying, by the collaboration service and based on a digital itinerary associated with the user, a location of the user; processing data from a data profile associated with the user as input data to a machine learning model; receiving, by the collaboration service and as output of the machine learning model, a plurality of predicted travel objective classifications; determining, by the collaboration service, a plurality of travel objectives, wherein each of the plurality of travel objectives is associated with one of the plurality of predicted travel objective classifications; determining, by the collaboration service, a travel objective within a predefined proximity of the location of the user; and displaying the travel objective to the user via a planning interface.

TRAINING PREDICTIVE MODELS BASED ON REWARD SIGNALS AND HYPERPARAMETER SEARCHING

Absstract of: US2025371437A1

Aspects of the present disclosure provide techniques for training and using machine learning models to predict and present an optimal workflow to a user of a software application. An example method generally includes generating a training data set including a plurality of exemplars including features associated a user of a software application, a sequence of workflow steps presented to the user of the software application, and a reward metric. A plurality of hyperparameter sets for training a plurality of predictive models is generated. The plurality of predictive models are trained based on the plurality of hyperparameter sets. A hyperparameter set from the plurality of hyperparameter sets is selected based on performance metrics for each of the plurality of predictive models. A machine learning model is trained based on the selected hyperparameter set and the training data set, and the trained machine learning model is deployed.

ANALYSIS AND CORRECTION OF SUPPLY CHAIN DESIGN THROUGH MACHINE LEARNING

Absstract of: US2025371491A1

A dynamic supply chain planning system for analysis of historical lead time data that uses machine learning algorithms to forecast future lead times based on historical lead time data, weather data and financial data related to locations and dates within the supply chain.

METHOD FOR ADJUSTING HYPERPARAMETERS OF A MACHINE LEARNING MODEL

Absstract of: EP4657257A1

Selon un aspect, il est proposé un procédé mis en œuvre par un système informatique (SYS) d'hyperparamètres d'un modèle d'apprentissage automatique, le système informatique (SYS) comportant une unité de traitement (UT) configurée pour exécuter plusieurs processus en parallèle, le procédé comprenant une exécution de plusieurs méthodes de recherche indépendante d'hyperparamètres dans différents processus parallèles de l'unité de traitement (UT), les résultats des tests des combinaisons d'hyperparamètres étant stockés dans une mémoire du système informatique partagée entre les différents processus, et dans lequel chaque processus évalue si une combinaison d'hyperparamètres recherchée a déjà été testée par un autre processus à partir des résultats de tests stockés en mémoire, et prend en compte, dans son propre historique de tests, les résultats de tests stockés dans la mémoire si la combinaison d'hyperparamètres recherchée a déjà été testée.

AUTONOMOUS RECOMMENDATION SYSTEMS USING MACHINE LEARNING

Absstract of: CA3266564A1

An AI-driven recommendation system utilizes a machine learning model and a dynamically updated knowledge graph to generate personalized product recommendations. The system constructs a knowledge graph with nodes and edges representing relationships between users, prior product selections, and historical interactions. A supervised learning framework trains the machine learning model using labeled data from the knowledge graph to predict relevant products based on multidimensional constraints. A graphical user interface (GUI) presents dynamically adjusted interactive elements to capture user preferences. User responses are processed using natural language processing (NLP) to refine predictions and generate recommendations. The system continuously updates the knowledge graph with real-time user feedback and external data, retraining the machine learning model to enhance future recommendations. This adaptive approach enables personalized, context-aware recommendations that evolve based on user interactions and external influences.

SYSTEMS AND METHODS FOR EXPERIMENT ASPECT PREDICTION

Absstract of: WO2025245276A1

Disclosed herein are computer systems and computer-implemented methods for training a machine learning model to predict an aspect of an experiment. The method may comprise training a machine learning model to predict an aspect of an experiment. The method may comprise (i) grouping data retrieved from a plurality of sources into one or more groups based on a plurality of data types, (ii) identifying a plurality of entities of the data, (iii) generating modality data for a group of the one or more groups, (iv) generating a plurality of tokens from the modality data, (v) ordering the plurality of tokens based on the plurality of entities to form a token sequence based on one or more shared entities associated with the plurality of tokens, and (vi) training the machine learning model on the token sequence to predict the aspect of the experiment.

MACHINE LEARNING MODEL WITH GROUNDED CONTENT TOKEN INSERTION

Absstract of: WO2025244723A1

A computing system (10) is provided that receives a tokenized prompt (33) at a machine learning model (18), generates a model-generated content portion (40B) of an output sequence (38) of output tokens (40) in response to the tokenized prompt, identifies provenance metadata (29) for a grounded data source (44) in the model-generated content portion of the output sequence. Upon identification of the provenance metadata, the computing system at least temporarily ceases token-wise probabilistic generation of the output sequence with the machine learning model, retrieves grounded content (52) from the grounded data source using the provenance metadata, writes output tokens corresponding to the grounded content to a grounded content portion (40A1) of the output sequence, and transmits the output sequence to an additional computing process, for display, storage, or additional downstream processing, for example.

MACHINE LEARNING MODEL WITH CONSTRAINED OUTPUT TOKEN VOCABULARY

Absstract of: WO2025244724A1

A computing system (10) including one or more processing devices (12) configured to receive a prompt (20). At a machine learning model (30) that has an output token vocabulary (40) including candidate output tokens (42), the one or more processing devices are further configured to compute output token probabilities (34) over the output token vocabulary based at least in part on the prompt. At a decoder plugin (60), the one or more processing devices are further configured to compute a constrained output token vocabulary (64) as a proper subset of the output token vocabulary. The one or more processing devices are further configured to select output tokens (52) based at least in part on the computed output token probabilities. The output tokens are selected from among the candidate output tokens included in the constrained output token vocabulary. The one or more processing devices are further configured to transmit an output (50) including the output tokens to an additional computing process (54).

TARGETED ADVERTISEMENT RANKING USING MACHINE LEARNING

Absstract of: US2025363524A1

The present disclosure relates to ranking electronic advertisements using one or more machine learning algorithms for a targeted audience associated with an aircraft flight. For example, one or more embodiments described herein include a computer-implemented method comprising executing a learn-to-rank algorithm to train a machine learning model on a training dataset that includes electronic advertisements with associated scores characterizing a relevancy between the electronic advertisements and a defined query. The computer-implemented method can also comprise applying the trained machine learning model to rank a set of electronic advertisements based on a feature vector characterizing input data that includes flight details of an aircraft.

GENERATIVE HIERARCHICAL SEARCHING FOR COMPOUNDS

Absstract of: WO2025245236A1

A method performed by one or more computers. The method comprises receiving a natural language query specifying requirements for a compound; processing the natural language query using a language policy to generate a plurality of representations of candidate compounds that each satisfy at least a subset of the requirements specified in the natural language query. Each representation specifies at least a chemical formula of the corresponding candidate compound. The method further comprises, for each representation in a subset of the representations, using a generative machine learning model conditioned on the representation to generate one or more candidate chemical structures, each candidate chemical structure comprising a respective spatial location for each of the atoms of the corresponding candidate compound; and selecting a chemical structure and corresponding compound from the plurality of candidate chemical structures.

METHOD AND SYSTEM FOR IMPROVED SEGMENTATION OF LARGE DATASETS USING AI

Absstract of: US2025363511A1

In an embodiment, a method for segmenting a large dataset into distinct segments using artificial intelligence (AI) is disclosed. The method includes receiving aggregated datasets including user data and user IDs assigned thereto, processing the datasets to extract user data characteristics, and creating distinct segments according to a segmentation pipeline based on the extracted user data characteristics. The method further includes predicting segment membership using explainable AI and assigning users into given ones of the distinct segments according to an ensemble machine learning-based segmentation model and the extracted user data characteristics. The method further includes receiving additional user data, refining the segmentation model according to the additional user data, and updating a set of the distinct segments according to the refined segmentation model.

CREEP LIFE ASSESSMENT METHOD

Absstract of: WO2025243255A1

The present invention relates to a creep life assessment method having high precision and accuracy, especially for using in an inspection and assessment of the service life of material at high temperature including easy to apply with the conventional creep assessment. Moreover, said method intends to assess the actual creep life considering the creep life prediction from the model built from machine learning from the factor and operating condition data that affects the creep such as temperature, stress, including Larson-Miller parameter and Larson-Miller constant, which have been adjusted to consider the factor and operating condition, resulting in more precise and accurate creep life prediction. Said method also considers the creep life fraction assessment by considering the physical property of the material together with the accumulated creep condition simulation, so that the creep life fraction assessment of the material from model built from machine learning is more precise. Therefore, the actual creep life can be assessed.

GENERATION OF GRAPHICS FOR VEHICLE ITEMS

Absstract of: US2025363550A1

A computer-implemented method of generating a graphic for a vehicle item may include: causing a user device to display a user interface indicative of one or more vehicles; receiving, from the user device, vehicle selection information, the vehicle selection information indicative of a vehicle selected by a user; obtaining, from a database, user data corresponding to the user; generating, using a machine learning model, a first score corresponding to a first vehicle item based on the user data; determining whether the first score exceeds a first predetermined score threshold; generating, in response to a determination that the first score exceeds the first predetermined score threshold, a first graphic indicative of the first vehicle item; and causing the user device to display the first graphic via the user interface.

APPARATUS AND METHODS FOR PROACTIVE COMMUNICATION

Absstract of: US2025363400A1

Apparatus and methods for proactively and preemptively communicating with a user interacting with a software application are provided. The apparatus and methods may include an artificial intelligence/machine learning communication engine monitoring and tracking a user's interactions. The apparatus and methods may include the communication engine determining if the user requires further training, if the interaction is fraudulent, and pre-empting requests for information the user may commence. The apparatus and methods may include the communication engine creating and displaying training materials for the user to complete, revoking access if fraud is present, and proactively providing information before the user requests the information.

SYSTEMS AND METHODS FOR INTELLIGENTLY CONFIGURING AND DEPLOYING A MODEL ORCHESTRATOR MESH OF A MACHINE LEARNING-BASED DIALOGUE SYSTEM USING A GRAPHICAL USER INTERFACE

Absstract of: US2025363743A1

A system, method, and computer-program product includes instantiating a user interface (UI) that provides a user with a graphical environment for creating a model orchestration mesh controlling an operation of a plurality of disparate AI dialogue models, automatically installing, within the graphical environment of the UI, a root socket node, digitally assigning a first disparate AI dialogue model of the plurality of disparate AI dialogue models to the root socket node, automatically generating, within the graphical environment of the UI, a plurality of distinct mesh socket nodes, receiving, via the UI, an input from the user selecting a graphical UI control element displayed on the UI that, when selected, changes a state of the UI to an interactive gesture-based tracking state, constructing, within the graphical environment of the UI, a plurality of graphical socket transitions while the UI is in the interactive gesture-based tracking state.

ESTIMATING A CONCENTRATION OF A RESPIRATORY GAS IN THE BLOOD OF A PATIENT

Absstract of: US2025359785A1

A method for estimating a concentration of a respiratory gas in the blood of a patient comprises: receiving measurement data, which indicate a volume-dependent course of a concentration of the respiratory gas in a respiratory airflow exhaled by the patient depending on a respiratory air volume exhaled by the patient; generating input data from the measurement data, the input data comprising a matrix of values for various parameters with respect to the volume-dependent course; inputting the input data into a machine learning module which was trained to convert the input data into output data, which indicate a concentration of the respiratory gas in the blood of the patient; outputting the output data by way of the machine learning module.

METHODS FOR IMPROVED SURGICAL PLANNING USING MACHINE LEARNING AND DEVICES THEREOF

Absstract of: US2025359937A1

Methods, non-transitory computer readable media, and surgical computing devices are illustrated that improve surgical planning using machine learning. With this technology, a machine learning model is trained based on historical case log data sets associated with patients that have undergone a surgical procedure. The machine learning model is applied to current patient data for a current patient to generate a predictor equation. The current patient data comprises anatomy data for an anatomy of the current patient. The predictor equation is optimized to generate a size, position, and orientation of an implant, and resections required to achieve the position and orientation of the implant with respect to the anatomy of the current patient, as part of a surgical plan for the current patient. The machine learning model is updated based on the current patient data and current outcome

INTEGRATED AI-POWERED ADAPTIVE ROBOTIC SURGERY SYSTEM

Absstract of: US2025359955A1

A robotic surgical system includes a robotic manipulator configured to perform surgical procedures under direct surgeon control. A surgical camera system captures real-time intraoperative video. An external imaging interface receives multimodal imaging data, including preoperative and intraoperative data from at least one of magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, and fluoroscopy. An artificial intelligence (AI module has a trained neural network and a deep learning model trained on multi-institutional annotated surgical datasets, The AI module is configured to execute one or more of: fuse acquired video and imaging data into temporally and spatially coherent anatomical visualizations; generate continuously updating overlays aligned with the surgical field, with segmented anatomical features; projected tissue boundaries, proximity indicators for instruments, and predictive deformation trends; provide dynamic predictive trend visualization indicating zones of future anatomical complexity or risk; register and align preoperative imaging data with intraoperative imaging data in real time; adapt overlay presentation in response to tissue deformation without actuating the robotic manipulate or; and passively augment visual feedback without initiating any autonomous actuation of surgical instruments.

METHOD AND APPARATUS FOR MANAGING BEAM USING ARTIFICIAL INTELLIGENCE AND/OR MACHINE LEARNING

Nº publicación: US2025365588A1 27/11/2025

Applicant:

KT CORP [KR]
KT CORPORATION

Absstract of: US2025365588A1

Provided are a method and an apparatus for performing beam management in a wireless communication system. The method of a terminal may include triggering at least one beam failure recovery (BFR) for a cell that performs beam management using an artificial intelligence and/or machine learning model, deactivating the artificial intelligence and/or machine learning model based on the number of the at least one beam failure recovery triggered during a specific time duration, and transmitting deactivation information of the artificial intelligence and/or machine learning model to a base station. The method of the base station may include transmitting, to the terminal, configuration information related to the artificial intelligence and/or machine learning model, receiving, from the terminal, the deactivation information of the artificial intelligence and/or machine learning model, and, based on the received deactivation information, stopping beam generation related to the artificial intelligence and/or machine learning model.