Alerta

FORECASTING USING DIFFERENTIAL-BASED MACHINE-LEARNING ARCHITECTURE

Resumen de: EP4560561A1

Conventional forecast models assume that the underlying data are stationary. In the case of non-stationary data, the conventional forecast model must be increased in complexity, or otherwise, must be frequently retrained. Embodiments are disclosed of a forecast model that accounts for non-stationary data, without increased complexity and without an increase in the frequency of retraining, by recasting the forecasting problem as a matter of tracking differentials in the data. In particular, variables (e.g., covariates) are input into differential determinations and/or intermediate machine-learning models to determine differences in past and forecasted values of a plurality of features. These differences are then input into a machine-learning model to predict a change in the value of the target, which is aggregated with a past value of the target to produce a forecasted value of the target.

SYSTEMS AND METHODS FOR PROCESSING IMAGES TO DETERMINE IMAGE-BASED COMPUTATIONAL BIOMARKERS FROM LIQUID SPECIMENS

Resumen de: US2025166397A1

A method of using machine learning to output task-specific predictions may include receiving a digitized cytology image of a cytology sample and applying a machine learning model to isolate cells of the digitized cytology image. The machine learning model may include identifying a plurality of sub-portions of the digitized cytology image, identifying, for each sub-portion of the plurality of sub-portions, either background or cell, and determining cell sub-images of the digitized cytology image. Each cell sub-image may comprise a cell of the digitized cytology image, based on the identifying either background or cell. The method may further comprise determining a plurality of features based on the cell sub-images, each of the cell sub-images being associated with at least one of the plurality of features, determining an aggregated feature based on the plurality of features, and training a machine learning model to predict a target task based on the aggregated feature.

SECURITY-RELATED EVENT ANOMALY DETECTION

Resumen de: US2025168179A1

The technology relates to machine responses to anomalies detected using machine learning based anomaly detection. In particular, to receiving evaluations of production events, prepared using activity models constructed on per-tenant and per-user basis using an online streaming machine learner that transforms an unsupervised learning problem into a supervised learning problem by fixing a target label and learning a regressor without a constant or intercept. Further, to responding to detected anomalies in near real-time streams of security-related events of tenants, the anomalies detected by transforming the events in categorized features and requiring a loss function analyzer to correlate, essentially through an origin, the categorized features with a target feature artificially labeled as a constant. An anomaly score received for a production event is determined based on calculated likelihood coefficients of categorized feature-value pairs and a prevalencist probability value of the production event comprising the coded features-value pairs.

Closed-Loop Intelligence

Resumen de: US2025165439A1

Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

DATA ANALYTICS SYSTEM AND METHOD FOR MACHINE LEARNING SOLUTIONS WITH ZERO CODING

Resumen de: WO2025104745A1

A novel system and method for the development of machine learning solutions without the need for any coding expertise The system includes a highly advanced interactive dashboard designed for data visualization. One of its key features is ensuring that user inputs remain error-free and only request relevant options based on the provided data. This approach revolutionizes the accessibility and usability of machine learning, making it more inclusive for a broader user base, regardless of their coding background. The interactive dashboard streamlines the 10 machine learning solution development process and significantly reduces the barriers to entry, making it a promising innovation in the field of data science and artificial intelligence.

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND RECORDING MEDIUM

Resumen de: WO2025104804A1

In this information processing device, a complementation means complements ontology data by using a graph machine learning model that has learned the relationship between information items included in the ontology data. A natural language processing model generation means generates a natural language processing model on the basis of the complemented ontology data. The information processing device can assist decision making of a user.

SYSTEMS AND METHODS FOR USING MACHINE LEARNING TECHNIQUES TO PREDICT ITEM GROUP COMPOSITION

Resumen de: WO2024144913A1

Systems and methods for predicting item group composition are disclosed. A system for predicting item group composition may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: receiving entity identification information and a timestamp associated with a transaction without receiving information distinguishing items associated with the transaction; determining, based on the entity identification information, a localized machine learning model trained to predict categories of items based on transaction information applying to all of the items associated with the transaction; and applying the localized machine learning model to a model input to generate predicted categories of items associated with the transaction, the model input including the received entity identification information and a timestamp but not including information distinguishing items associated with the transaction.

BUILDING SYSTEM WITH DIGITAL TWIN BASED AGENT PROCESSING

Resumen de: US2025164950A1

A system can include one or more memory devices that can store instructions thereon. The instructions can, when executed by one or more processors, cause the one or more processors to receive timeseries data associated with a building, detect that a new building device has been added to the building, determine that a representation of the new building device is absent from a digital twin of the building, and execute a machine learning model to add the representation of the new building device to the digital twin of the building.

SYSTEMS AND METHOD FOR CALCULATING LIABILITY OF A DRIVER OF A VEHICLE

Resumen de: US2025166083A1

Aspects of the present disclosure are related to systems, apparatus, and methods of generating or calculating liability and operational costs of a vehicle based on a driver's handling of the vehicle are described herein. Using a combination of vehicle sensors, video input, and on-board artificial intelligence and/or machine learning algorithms, the systems and methods of the present disclosure can identify risky events performed by the driver of a vehicle and generate, calculate, and evaluate driving scores for the driver of the vehicle and send the calculations to one or more entities.

SYSTEMS AND METHODS FOR PROCESSING IMAGES TO CLASSIFY THE PROCESSED IMAGES FOR DIGITAL PATHOLOGY

Resumen de: US2025165820A1

Systems and methods are disclosed for receiving a target image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning model to the target image to determine at least one characteristic of the target specimen and/or at least one characteristic of the target image, the machine learning model having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the at least one characteristic of the target specimen and/or the at least one characteristic of the target image.

Closed-Loop Intelligence

Resumen de: US2025165438A1

Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

INTERACTIVE REAL-TIME VIDEO SEARCH BASED ON KNOWLEDGE GRAPH

Resumen de: US2025165529A1

A method, computer system, and computer program product are provided for real-time video searching based on augmented knowledge graphs that are generated using machine learning models. Multimedia data is obtained comprising an image portion and an audio portion, and a user query with respect to the multimedia data is obtained. A knowledge graph of the multimedia data is generated using one or more machine learning models based on the image portion and the audio portion, wherein the knowledge graph includes a plurality of entities and relationships between entities. An augmented knowledge graph is generated, wherein the augmented knowledge graph augments the knowledge graph with additional entities and additional relationships between the additional entities using additional data that is obtained from a source external to the multimedia data. A response to the user query is provided based on the augmented knowledge graph.

GENERATING AN EMBEDDING SPACE FROM A TRAINING DATA SET FOR A MACHINE LEARNING ALGORITHM

Resumen de: US2025165865A1

A system for and a method of generating an embedding space from a training data set for a machine learning algorithm. The method includes receiving, through an input of a computer system, an input operating data point by one or more layers of a machine learning algorithm implemented on the computer system, generating an embedding space using a training data set, the embedding space including a plurality of inducing data points, each inducing data point corresponding to a cluster of training data points, comparing the input operating data point against the plurality of inducing data points, determining whether a sufficient set of supporting historical data points exists in the plurality of training data points within a fixed distance from the input operating data point, and generating an alert based on the determining to enable a user or an electronic controller to take appropriate action, and outputting the alert.

REAL TIME FEEDBACK FROM A MACHINE LEARNING SYSTEM

Resumen de: US2025165819A1

A technique for providing real time feedback from a machine learning system is provided that includes a method and system for interactively training machine learning models. In particular, by separating processing and analysis using static and dynamic models that are trained differently, the disclosed technique enables interactive training and prediction of machine learning models to increase the speed of generating new predictions based on real time feedback. In some cases, a dynamic model is applied to the output of a static model to generate an analysis, a correction of the analysis is received, and the correction is used to retrain the dynamic model. An updated analysis is generated based on reapplying the dynamic model to the output of the static model without having to retrain the static model.

GENERATING AN EMBEDDING SPACE FROM A TRAINING DATA SET FOR A MACHINE LEARNING ALGORITHM

Resumen de: EP4557165A1

A system for and a method of generating an embedding space from a training data set for a machine learning algorithm. The method includes receiving, through an input of a computer system, an input operating data point by one or more layers of a machine learning algorithm implemented on the computer system, generating an embedding space using a training data set, the embedding space including a plurality of inducing data points, each inducing data point corresponding to a cluster of training data points, comparing the input operating data point against the plurality of inducing data points, determining whether a sufficient set of supporting historical data points exists in the plurality of training data points within a fixed distance from the input operating data point, and generating an alert based on the determining to enable a user or an electronic controller to take appropriate action, and outputting the alert.

REUSE OF DATA FOR TRAINING MACHINE LEARNING MODELS

Resumen de: EP4557178A1

Example embodiments may relate to systems, methods and/or computer programs for reusing data for training machine learning models. In an example, an apparatus comprises means for receiving a request to collect new user data for training a machine learning model associated with an application. The apparatus may also comprise means for identifying existing stored data suitable for training the machine learning model based upon an ontology. The apparatus may also comprise means for providing access to the identified existing stored data in response to identifying that the data is suitable for training the machine learning model.

SYSTEM AND METHOD FOR AUTOMATED MAPPING OF DATA TYPES FOR USE WITH DATAFLOW ENVIRONMENTS

Resumen de: US2025156160A1

In accordance with various embodiments, described herein is a system (Data Artificial Intelligence system, Data AI system), for use with a data integration or other computing environment, that leverages machine learning (ML, DataFlow Machine Learning, DFML), for use in managing a flow of data (dataflow, DF), and building complex dataflow software applications (dataflow applications, pipelines). In accordance with an embodiment, the system can provide support for auto-mapping of complex data structures, datasets or entities, between one or more sources or targets of data, referred to herein in some embodiments as HUBs. The auto-mapping can be driven by a metadata, schema, and statistical profiling of a dataset; and used to map a source dataset or entity associated with an input HUB, to a target dataset or entity or vice versa, to produce an output data prepared in a format or organization (projection) for use with one or more output HUBs.

Automatically Recognizing and Surfacing Important Moments in Multi-Party Conversations

Resumen de: US2025157474A1

A system and a method are disclosed for identifying a subjectively interesting moment in a transcript. In an embodiment, a device receives a transcription of a conversation, and identifies a participant of the conversation. The device accesses a machine learning model corresponding to the participant, and applies, as input to the machine learning model, the transcription. The device receives as output from the machine learning model a portion of the transcription having relevance to the participant, and generates for display, to the participant, information pertaining to the portion.

REUSE OF DATA FOR TRAINING MACHINE LEARNING MODELS

Resumen de: US2025156763A1

Example embodiments may relate to systems, methods and/or computer programs for reusing data for training machine learning models. In an example, an apparatus comprises means for receiving a request to collect new user data for training a machine learning model associated with an application. The apparatus may also comprise means for identifying existing stored data suitable for training the machine learning model based upon an ontology. The apparatus may also comprise means for providing access to the identified existing stored data in response to identifying that the data is suitable for training the machine learning model.

MACHINE LEARNING-BASED AUTOMATED ABNORMALITY DETECTION IN MEDICAL IMAGES AND PRESENTATION THEREOF

Resumen de: US2025156676A1

The presently disclosed technology relates to medical image processing. An example method includes receiving medical image data which represents an anatomical structure and processing the received image data through convolutional neural network (CNN) to generate predictions. The predictions can include abnormality location proposals and abnormality class probabilities associated with each abnormality location proposals.

Automatically assigning hybrids or seeds to fields for planting

Resumen de: AU2025202916A1

A computer-implemented method comprising: using field assignment instructions in a server computer system, receiving, over a digital data communication network at the server computer system, grower datasets specifying agricultural fields of growers and inventories of hybrid products or seed products of the growers; using the field assignment instructions in the server computer system, obtaining over the digital data communication network at the server computer system, other input data comprising relative maturity values, historic yield values for the fields of the growers, and mean yield values for regions in which the fields of the growers are located; using the field assignment instructions in the server computer system, calculating pair datasets consisting of permutations of product assignments of two (2) products to two (2) fields from among the fields of the growers, and corresponding converse assignments of the same products and fields; inputting features of the pair dataset(s) to a trained machine learning model, to yield predicted probability of success (POS) values for each of the product assignments and its corresponding converse assignment; blending the predicted POS values for all fields with field classification data using an operations research model of other field data, to result in creating and storing score values for each of the product assignments and the corresponding converse assignments; using the field assignment instructions in the server computer syst

High Frequency QRS in Biometric Identification

Resumen de: AU2025202887A1

Abstract Disclosed is sampling HF-QRS signals from a number of subjects (or derived values or features), and using e.g. deep learning-convolutional neural networks to find features or values which are (i) sufficiently similar for the same subject over all samples, yet (ii) sufficiently different among different subjects to allow identification. Also disclosed is finding signatures which are sufficiently stable over a particular period such that these signatures are within a deviation threshold, and then monitoring all subjects to be identified at least as often as the period used to establish the deviation threshold.

FLEXIBLE MACHINE LEARNING MODEL COMPRESSION

Resumen de: WO2025101721A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compresses a machine learning model having a plurality of parameters. In one aspect, one of the methods includes obtaining trained values of a set of parameters for at least a portion of a machine learning model; identifying one or more dense ranges for the trained values; determining a least number of bits required to represent each trained value within the one or more dense ranges; identifying a second format having a range that is smaller than a range of the first format; and generating a compressed version of the at least a portion of the machine learning model.

BIOLOGICAL AGENT AEROSOL CLASSIFICATION/IDENTIFICATION USING MACHINE LEARNING ALGORITHMS

Resumen de: WO2025101490A1

In accordance with various embodiments, a system and a method for identifying a particle as a bioactive stimulant are provided. The system includes a processor configured to execute machine-readable instructions borne by a non-transitory computer-readable memory device to cause the processor to process one or more steps of the method disclosed herein. The system/method include the steps to: receive a dataset comprising scattered light signals and/or fluorescent light signals of the particle; analyze the dataset using one or more machine learning models, wherein the one or more machine learning models is trained using elastic scattering light intensity data and fluorescent light intensity data of a library of biological molecules; generate a probability score that the particle is bioactive based on the analysis of the dataset; determine, via classification of the probability score, that the particle is bioactive; and/or output a result indicating that the particle is the bioactive stimulant.

GENERATING INFORMED PRIORS FOR HYPERPARAMETER SELECTION

Nº publicación: WO2025101345A1 15/05/2025

Solicitante:

MICROSOFT TECH LICENSING LLC [US]
MICROSOFT TECHNOLOGY LICENSING, LLC

Resumen de: WO2025101345A1

A system iteratively evaluates the target machine learning model using evaluation hyperparameter values of the target machine learning model to measure performance of the target machine learning model for different combinations of the evaluation hyperparameter values. The system trains a surrogate machine learning model using the different combinations of the evaluation hyperparameter values as features and the performance of the target machine learning model based on a corresponding combination of the evaluation hyperparameter values as labels. The system generates a feature importance vector of the surrogate machine learning model based on the training of the surrogate machine learning model, generate informed priors based on the feature importance vector, and generates the target hyperparameter values of the target machine learning model based on the informed priors.