Alerta

MULTISPECTRAL ANALYSIS USING A SMARTPHONE CAMERA FOR MEASURING CONCENTRATIONS OF LIGHT-EMITTING COMPOUNDS

Absstract of: US20260170715A1

In some embodiments, a computer-implemented method of measuring light-emitting compounds using a smartphone is provided. The smartphone determines a transformation matrix using one or more options specified via a configuration user interface. The smartphone transforms a low-color space image that depicts at least a subject into a multispectral data cube using the transformation matrix, and determines a measurement of a light-emitting compound associated with the subject using the multispectral data cube. In some embodiments, a computer-implemented method of measuring light-emitting compounds using a smartphone is provided. The smartphone transforms the low-color space image that depicts at least a subject into a multispectral data cube using a transformation matrix. The smartphone provides values from the multispectral data cube to an ensemble of two or more machine learning models, and determines a measurement of a light-emitting compound associated with the subject based on outputs of two or more machine learning models.

METHOD AND APPARATUS FOR TRANSMITTING AND RECEIVING SIGNAL IN WIRELESS COMMUNICATION SYSTEM

Absstract of: US20260172849A1

A method performed by a terminal in a wireless communication system according to at least one of the embodiments disclosed herein may include configuring at least one artificial intelligence/machine learning (AI/ML) model related to multiple transmissions and receptions (TRPs), monitoring the at least one AI/ML model, and performing, based on a performance of the monitored at least one AI/ML model, AI/ML model management to maintain or at least partially change the at least one AI/ML model, wherein the performance of the at least one AI/ML model may be determined based on a first multi-TRP data set related to training of the at least one AI/ML model and a second multi-TRP data set related to monitoring of the at least one AI/ML model.

MACHINE LEARNING MODEL EVALUATION METHOD, DATA PROCESSING METHOD, AND RELATED DEVICE

Absstract of: US20260170420A1

0000 A machine learning model evaluation method, a data processing method, and a related device are disclosed. The method can be applied to the autonomous driving field of artificial intelligence. The method includes: processing a plurality of pieces of segmented data in an evaluation sample using a machine learning model, to generate a plurality of prediction labels, and determining a parameter value of at least one evaluation indicator. The evaluation sample includes description data of a traffic scene within a first duration, the segmented data includes description data of the traffic scene within a first sub-duration of the first duration. The at least one evaluation indicator indicates stability and/or accuracy corresponding to the plurality of prediction labels, and the accuracy is obtained based on ground-truths corresponding to the plurality of pieces of segmented data.

MACHINE-LEARNING TECHNIQUES FOR PREDICTING UNOBSERVABLE OUTPUTS

Absstract of: WO2025034318A1

In some aspects, a computing system can generate and optimize a machine learning model to estimate an unobservable capacity of a target system or entity. The computing system can access training vectors which include training predictor variables, training performance indicators, and task quantities. A training performance indicator indicating performance outcome corresponding to the predictor variables and a task quantity associated with a task assigned to the target entity that leads to the training performance indicator. The machine learning model can be trained by performing adjustments of parameters of the machine learning model to minimize a loss function defined based on the training vectors. The trained machine learning model can be used to estimate the capacity of the target system or entity for handling tasks and be used in assigning tasks to the target entity according to the determined capacity.

METHOD AND DEVICE FOR SIGNAL TRANSMISSION AND RECEPTION IN WIRELESS COMMUNICATION SYSTEM

Absstract of: EP4761205A1

A method performed by a first apparatus in a wireless communication system according to at least one of the embodiments disclosed in the present specification may comprise the steps of: transmitting, to a second apparatus, a first signal including information about a first artificial intelligence/machine learning (AI/ML) model configured in the first apparatus; and receiving a second signal, including information about a second AI/ML model configured in the second apparatus, from the second apparatus in response to the first signal, wherein the first AI/ML model configured in the first apparatus and the second AI/ML model configured in the second apparatus are linked to each other, and the second signal includes at least one of information about a reference AI/ML model used in the second apparatus in order to evaluate the performance of the first AML model or information about conditions under which the second AI/ML model is applied.

SYSTEMS AND METHODS FOR IDENTIFYING COMMERCIAL DOMICILES

Absstract of: EP4760672A1

The present disclosure relates to systems and methods for identifying commercial domiciles. An example of one such method includes operating at least one processor to: receive telematics data originating from a plurality of telematics devices installed in a plurality of vehicles; identify, using the telematics data, a vehicle stop zone, each vehicle stop zone comprising a vehicle stop cluster; and identify the vehicle stop zone as a commercial domicile by applying to the vehicle stop cluster of the vehicle stop zone at least one machine learning model trained to classify vehicle stop zones based on one or more vehicle stop features thereof.

TECHNIQUES FOR PREDICTING IMMUNE-RELATED ADVERSE EVENTS

Absstract of: US20260162760A1

Described herein are techniques for predicting whether a subject will experience an immune-related adverse event (irAE) in response to administration of an immune checkpoint inhibitor (ICI) therapy. In some embodiments, the techniques include: determining a likelihood that the subject will experience the irAE in response to administration of the ICI therapy, the determining comprising: performing: (a) processing clinical data using a first machine learning (ML) model to output a first likelihood that the subject will experience the irAE, (b) processing RNA sequencing data using a second ML model to output a second likelihood that the subject will experience the irAE, and/or (c) processing immune receptor data using a third ML model to output a third likelihood that the subject will experience the irAE; and processing the first, second, and/or third likelihoods using a fourth ML model trained to predict the likelihood that the subject will experience the irAE.

MODEL GENERATION METHOD, MODEL GENERATION DEVICE, INFERENCE PROGRAM, AND INFERENCE DEVICE

Absstract of: US20260161978A1

The model generation device performs machine learning for an inference model that includes a preprocessing module and a graph inference module. The preprocessing module includes a feature extractor and a selection module. The feature extractor calculates a feature value of each element belonging to one of a plurality of sets included in the input graph. The selection module selects one or more edges extending from each element as a starting point based on the calculated feature value of each element, and generates graph information, indicating the calculated feature value of each element and an edge selection result for each set. The graph inference module is configured to be differentiable and infers a solution to a task for the input graph from the generated graph information for each set.

SYSTEM AND METHOD FOR PROVIDING DECENTRALIZED COMPUTING RESOURCES

Absstract of: US20260161472A1

0000 A computer based system and method for providing decentralized computing resources including translating a task of training of or inference with a machine learning model into a code in a programming language that is executable by a ready made runtime environment (RRE) that enables interface with an Internet; finding, among a plurality of computing devices, at least one computing devices that has available computing power; transferring a portion of the translated task to the at least one computing devices; and obtaining results of execution of the portions of the translated task from the at least one computing devices. The RRE may be configured to limit interaction between execution of the portions of the translated task and processes running on each of the at least one computing and/or to limit interaction between execution of the portions of the translated task and resources of each of the at least one computing devices.

SYSTEMS AND METHODS FOR ACTIVE CURRICULUM LEARNING

Absstract of: US20260161980A1

Computer systems and computer implemented methods for training a machine learning model are provided that includes: selecting seed data from an unlabeled dataset; labeling the seed data and storing the labeled seed data in a data store; training the machine learning model in an initial iteration using the labeled seed data, where the machine learning model is trained to select a next subset of the unlabeled dataset; selecting a next subset of the unlabeled dataset; computing difficulty scores for at least the next subset of the unlabeled dataset; labeling the next subset of the unlabeled data; and training the machine learning model in a second iteration using the labeled next subset of the unlabeled dataset. The machine learning model is generally trained to select the next subset of the unlabeled dataset for a subsequent training iteration by presenting the labeled next subset of the unlabeled dataset in an order sorted based on the difficulty scores.

SECURE AND PRIVATE PROXY FINE TUNING

Absstract of: US20260161967A1

The present disclosure involves systems, software, and computer implemented methods for secure and private proxy fine tuning. One example method includes receiving an inference input for a first machine learning model. The input is provided to the first model, a second machine learning model that has an output structure that is consistent with a corresponding portion of the first model and a smaller overall size than the first model, and a tuned second machine learning model that is a tuned version of the second machine learning model. Output data is identified for the first model, the second model, and tuned second model. An output difference is determined based on the output data for the second model and the tuned second model. The output difference is applied to the output data for the first model to generate adapted output data that is used to generate a normalized output.

IDENTIFYING SEPARATION-RELATED PROBLEMS IN PETS

Absstract of: US20260157349A1

0000 The present disclosure relates to systems, methods, and program applications for identifying separation-related problems in a pet. The methods, for example, can include identifying the presence or absence of multiple behavioral signs exhibited by a pet where each of the multiple behavioral signs are given a sign score based on binary annotations representing either the presence or the absence of each of the behavioral signs, and grouping subsets of the multiple behavioral signs into one of multiple principal component behavioral groupings using the binary annotations to generate principal component scores for each of the multiple principal component behavioral groupings. Methods can also include using one or more machine-learning algorithms under the control of at least one processor for accessing and correlating the principal component scores for each of the multiple principal component behavioral groupings with a population cluster associated with a type of separation-related problem.

SYSTEM AND METHODS FOR PREDICTING VIDEO GAMING ATTRIBUTES

Absstract of: WO2026122688A1

A server-based system and method are provided for predicting video-gaming attributes such as game performance and session duration across a distributed population of gaming systems. The system executes a global machine-learning model trained to predict gaming attributes of a video game when executed on a client gaming system. The global model is distributed as a local instantiation to multiple client gaming systems, where each local model ascertains hardware and software characteristics of the respective client, generates predictions of gaming performance and expected session duration, and updates local parameters based on telemetry data collected during gameplay. Gradients based on the updated local parameters are transmitted to the server, which aggregates the data to refine the global model. The refined model is redistributed to client systems to improve prediction accuracy across heterogeneous gaming environments while preserving user privacy and enabling continuous, adaptive learning.

SYSTEMS AND METHODS FOR AI-ASSISTED ECHOCARDIOGRAPHY

Absstract of: AU2024393489A1

A method for processing a sparsely populated data source, method for generating a training set for training a model to predict mitral regurgitation from echocardiograph data, and method of predicting heart failure from echocardiograph data including the steps of: retrieving echocardiograph measurement data from a plurality of patient records comprising echocardiography reports; analysing the echocardiograph data to determine unpopulated data fields; populating the unpopulated data fields with imputed echocardiograph data determined by a machine learning model; calculating a probability output from a trained model; analysing echocardiograph measurement data of individual patient records from the echocardiograph data to determine a prediction of the presence of a disease state in the patient on the basis of the calculated probability output; and associating the presence of the disease state to a prediction of heart failure in the patient.

METHOD FOR RAPIDLY EVALUATING FLOOD DRAINAGE EFFECT BASED ON MACHINE LEARNING AND ENSEMBLE PREDICTION

Absstract of: US20260161860A1

0000 A method for rapidly evaluating flood drainage effect based on machine learning and ensemble prediction is provided, including the following steps: S1, collecting and organizing feature data for predicting and evaluating the flood drainage effect; S2, constructing a flood hydrodynamic numerical model based on a physical mechanism; S3, constructing a data set, and pre-processing the data set; S4, determining a target hyperparameter combination of each of multiple machine learning regression models by using a Bayesian optimizer; S5, training multiple machine learning regression models based on multiple machine learning methods and hyperparameter optimization; S6, performing ensemble prediction on each machine learning regression model to construct a prediction and evaluation model of the flood drainage effect; and S7, using the prediction and evaluation model of the step S6 to rapidly evaluate and predict the flood drainage effect. The method improves a response speed of urban flood emergency management.

BINARY FILE MALWARE DETECTION WITH STRUCTURE AWARE MACHINE LEARNING

Absstract of: CN121569294A

Machine learning integrally receives input data from static analysis and dynamic analysis of the binary file to output a maliciousness/goodness determination of the binary file. The machine learning entirety includes structure-aware dynamic compressors ("compressors"). A compressor receives, as input, tree data structures generated based on application programming interface calls of binary files in various sandbox environments. A compressor performs various compression, tokenization, embedding, and shaping operations on the tree data structure to generate a compression tensor that holds a structure context from the tree data structure. Machine learning wholly uses compression tensors to generate malicious/good decisions for binary files.

MACHINE LEARNING TECHNIQUES FOR DISCOVERING KEYS IN RELATIONAL DATASETS

Absstract of: WO2025029579A1

Techniques for discovering primary, unique, and/or foreign keys for relational datasets are described. The techniques include profiling the relational datasets to obtain respective data profiles; identifying one or more primary key candidates for a first relational dataset using a first data profile of the first relational dataset and a first trained machine learning model; identifying one or more foreign key proposals for a second relational dataset using the one or more primary key candidates by performing a subset analysis of the second relational dataset with respect to the first relational dataset; identifying one or more foreign key candidates for the second relational dataset using the first data profile, a second data profile of the second relational dataset, and a second trained machine learning model different from the first trained machine learning model; and outputting the at primary key candidate(s) and the foreign key candidate(s).

METHODS FOR FEDERATED LEARNING

Absstract of: EP4756676A1

0001 A method, apparatus, and computer program are described comprising: receiving an input; and determining a classification of the input using a machine learning model, the machine learning model comprising a local part and a collaboratively learned part, the determining comprising: determining extracted features of the input using a feature extractor of the collaboratively learned part, the feature extractor being caused to extract features of the input; determining a set of similarity scores using a prototype layer of the local part of the model, the prototype layer being caused to determine similarities between extracted features of the input and a set of trained prototypes of the prototype layer; and determining a classification of the input using a prototypical classifier of the local part of the model, the prototypical classifier being caused determine the classification based on the similarity scores.

KNOWLEDGE-DRIVEN FEDERATED BIG DATA QUERY AND ANALYTICS PLATFORM

Absstract of: EP4756640A2

0001 A system for querying a federated data store includes a metadata knowledge graph describing the contents and relationships among one or more underlying data stores, an interactive user interface receiving requests from a data consumer, a predefined constrainable query ('nodegroup') store containing predefined constrainable queries that define data subsets of interest across one or more of the underlying data repositories, a knowledge-driven querying layer generating and executing queries against the federated data store and merging responsive results, a scalable analytic execution layer receiving the search results from the federated data store and applying machine learning/artificial intelligence techniques to analyze the results, and a user interface presenting visualizations of raw or analyzed results to the consumer. A method and a non-transitory computer-readable medium are also disclosed.

SYSTEMS AND METHODS FOR AUTOMATING EMAIL TO ORDER USING GENERATIVE ARTIFICIAL INTELLIGENCE (AI)

Absstract of: EP4756641A1

0001 Systems and methods provide for automating the conversion of email orders into structured order entries using generative AI, leveraging an integrated architecture comprising a Real-Time Data Mesh (RTDM), Advanced Analytic and Machine Learning (AAML) Module, and Single Pane of Glass (SPoG) User Interface. The system includes an Email Parser that extracts order information from emails, an Order Generation Engine that converts this information into structured entries, and an Integration Gateway that synchronizes the entries with external systems. The RTDM manages data flow and transformation, while the AAML provides predictive analytics and process automation. The SPoG UI performs real-time data visualization and user interaction. The system enhances order processing efficiency, accuracy, and scalability, enabling businesses to process email orders with minimal manual effort and greater precision.

MACHINE LEARNING BASED VIDEO ANALYSIS, DETECTION AND PREDICTION

Absstract of: US20260154962A1

A method comprises obtaining video data from one or more data sources, and processing the obtained video data in a machine learning system comprising an inference stage and an anticipation stage. The inference stage is configured to assign one or more labels to at least one of a group activity and an individual activity detected in the obtained video data. The anticipation stage is configured to predict one or more future actions relating to at least one of the group activity and the individual activity based at least in part on the one or more labels assigned in the inference stage. The method further comprises generating at least one control signal based at least in part on the predicted one or more future actions. The method is illustratively configured to implement role inference and action anticipation in team sports, although it is applicable to a wide variety of other contexts.

METHOD AND SYSTEM FOR DETERMINING BEHAVIORAL PATTERNS OF USER GROUPS BASED ON INTERACTIONS WITH OTHER USER GROUPS USING MACHINE LEARNING

Absstract of: US20260154579A1

0000 The disclosure describes a method of generating a target profile including the target's sequence of events (SOE) for a task. Such target profile sequence of events is derived from several source group's transactions, where any source group's transactions cannot be shared with other source groups but the derived target group's profile is the only information that is shared. Source-side information is periodically extracted for a plurality of sources that each interact with a plurality of targets. The information includes source stages, resources, and stage transition events for a task with a target. Source information is used to generate a set of normalized stages, and a set of normalized events for transitioning between the stages of the set of normalized stages. An artificial intelligence (AI) model is trained using the source information. The AI model can generate a target profile with target process information inferred using the trained model. The target process information can include the target's identifiers for each stage, an estimated duration of the stage, deliverables for the stage, and one or more stage transition events for the stage.

MULTI-FACETED SITE EVALUATOR INTEGRATING USER DEFINED EVALUATION ENGINES

Absstract of: US20260154488A1

A website building system (WBS) includes at least one hardware processor and a site evaluator running on the at least one hardware processor to evaluate at least one application area of a website according to at least one user category of the WBS. The site evaluator includes at least one evaluation engine to evaluate the at least one application area according to rules and at least one of: scripts and machine learning (ML) models, a site modifier to implement at least one of automatic and manual modifications to the website according to recommendations from the at least one evaluation engine and an evaluation engine handler to enable user creation and editing of the at least one evaluation engine.

PLATFORMS, SYSTEMS, AND METHODS FOR AUDIT AND VALIDATION IN ARTIFICIAL INTELLIGENCE MODELS

Absstract of: US20260154179A1

0000 A system may include one or more processors and memory storing instructions that, when executed by the one or more processors, cause a platform to: identify an appropriate analytic method based on an assessment of a data characteristic, implement a data preparation procedure specific to a particular application, apply a machine learning model to analyze data and generate a prediction, perform a model validation procedure to ensure analytical reliability, create an audit trail documenting an analytic procedure and result; and generate technical documentation and visualization of an analytic finding.

Machine Learning Aspect Based Sentiment Analysis

Nº publicación: US20260154506A1 04/06/2026

Applicant:

ORACLE INT CORP [US]
Oracle International Corporation

Absstract of: US20260154506A1

0000 Embodiments evaluate performance by receiving a plurality of training performance reviews. Embodiments extract from the training performance reviews, using a first machine learning model, a plurality of features comprising a training aspect, a training sentiment, and a corresponding training evidence. Embodiments use the extracted plurality of features to train a second machine learning model. Embodiments receive a first performance review and extract from the first performance review one or more first aspects, one or more corresponding first evidences, and one or more corresponding first sentiments. Embodiments, using the trained second machine learning model, predict first sentiment scores for each of the first aspects.