Alerta

SYSTEMS AND METHODS OF GENERATING DATASETS FROM HETEROGENEOUS SOURCES FOR MACHINE LEARNING

Resumen de: US2025086482A1

A computer system is provided that is programmed to select feature sets from a large number of features. Features for a set are selected based on metagradient information returned from a machine learning process that has been performed on an earlier selected feature set. The process can iterate until a selected feature set converges or otherwise meets or exceeds a given threshold.

COMPUTER-READABLE RECORDING MEDIUM STORING INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE

Resumen de: US2025086507A1

A non-transitory computer-readable recording medium storing an information processing program for causing a computer to execute processing includes: extracting partial data that corresponds to each of a plurality of patterns of which an index according to an appearance frequency in a plurality of training samples is equal to or more than a second threshold, that is a pattern of a combination of one or more feature amounts of which a contribution degree to estimation of a machine learning model is equal to or more than a first threshold; calculating a likelihood of an estimation result of a partial model for each pattern, in a case where the partial data extracted from the estimation target data is input to a corresponding partial model among the partial models trained for the respective patterns; and outputting the partial data selected based on the likelihood calculated for each partial model for each pattern.

MACHINE-LEARNED NATURAL LANGUAGE DOCUMENT PROCESSING SYSTEM

Resumen de: US2025086386A1

A computer system includes memory configured to store a document database and a machine learning model. The document database includes multiple historical documents each having at least one version labeled as compliant and at least one version labeled as non-compliant. The system includes a creator user interface, a compliance user interface, an automated distribution module, and a model building module configured to train the machine learning model to classify a document according to a compliance score indicating a likelihood of document compliance with one or more compliance criteria. The system also includes an orchestrator module configured to receive the compliance score for the submitted document from the machine learning model, determine whether the compliance score is greater than or equal to a compliance score threshold, and supply the submitted document to the compliance user interface for transmission to the compliance team device when the compliance score is above a threshold.

SYSTEMS, MEDIA, AND METHODS FOR AUTOMATED RESPONSE TO QUERIES MADE BY INTERACTIVE ELECTRONIC CHAT

Resumen de: US2025086730A1

Systems, media, and methods for automated response to social queries comprising: monitoring queries from users, each query submitted to a vendor via an interactive chat feature of an external electronic communication platform, monitoring human responses to the queries, monitoring subsequent communications conducted via the electronic communication platform until each query is resolved; applying a first machine learning algorithm to the monitored communications to identify a query susceptible to response automation; applying a second machine learning algorithm to the query susceptible to response automation to identify one or more responses likely to resolve the query; and either i) notifying a human to respond to the query susceptible to response automation with the one or more responses likely to resolve the query, or ii) instantiating an autonomous software agent configured to respond to the query susceptible to response automation with the one or more responses likely to resolve the query.

METHODS FOR HYDRAULIC FRACTURING

Resumen de: US2025084741A1

Hydraulic fracturing treatments are performed by injecting hydraulic fracturing materials into two or more perforation clusters. Treatment data concerning pressure, flow rate and properties of the hydraulic fracturing materials are recorded. These data are analyzed by one or more techniques for estimating cluster efficiency. The data may be entered into one or more computer models for hydraulic fracturing. The modeling results are compared to the treatment data. Or, the treatment data may be analyzed using one or more wellbore pressure-wave propagation models. These waves may be generated by pumps and other sources. The reflection times from hydraulic fractures provide additional information about their position. Or, the treatment data may be analyzed using one or more machine learning algorithms employing data from heterodyne distributed vibration sensing or other systems. The hydraulic fracturing treatment may be adjusted to improve perforation cluster efficiency. This procedure may be performed in real time.

METHODS AND SYSTEMS FOR GENERATING AN ALIMENTARY INSTRUCTION SET

Resumen de: US2025087349A1

A system for generating an alimentary instruction set, the system comprising a computing device; a diagnostic engine operating on the computing device, wherein the diagnostic engine is configured to assemble a first training set, the first training set comprising a plurality of diagnostic outputs describing a plurality of health conditions and a plurality of correlated alimentary instruction sets; parse the first training set into at least a vector; train, using the at least a vector a machine learning model; receive an input to the trained machine learning model containing a diagnostic output; and generate an output to the trained machine learning model containing an alimentary instruction set.

SYSTEMS AND METHODS FOR SELECTING RECOMMENDED CROSSES WITH INCREASED AN PROBABILITY OF MEETING PLANT-BASED PRODUCT SPECIFICATIONS

Resumen de: US2025087300A1

A computer-based method for selecting recommended crosses from a population of plants with an increased probability of meeting a plant-based product specification, comprising: (a) collecting plant data for the plant population including at least labelled parentage information including genetic and phenotype information; (b) training a machine learning model mapping phenotypes to genotype based on the collected data; (c) extracting a target list including one or more phenotypes needed to meet the product specification; (d) simulating pairwise combinations of one or more available parents using rapid recombination simulation; (e) applying the phenotype-to-genotype mapping to predict phenotypes for each simulated combination; (f) selecting the simulated combinations that meets phonetic criteria on target list; (g) simulating selfed combinations of each selected simulated combination using rapid recombination simulation; (h) repeating (e) through (g) until F3 generation is simulated; and (i) creating a predictive crossing list of simulated F3 progeny that meets the product specification.

A Machine Learning Pipeline for Highly-Sensitive Assessment of Rotator Cuff Function

Resumen de: US2025082229A1

Methods of generating a mobility assessment for a subject are provided. Aspects of the methods include: instructing the subject to perform an activity including an oscillatory motion; generating a visual recording of the subject performing the activity using a recording device; extracting time series data from the visual recording using a dynamic algorithm; generating one or more musculoskeletal movement biomarkers from the time series data; and producing the mobility assessment for the subject from the one or more musculoskeletal movement biomarkers. Also provided are systems for use in practicing methods of the invention.

CLASSIFYING DATA OBJECTS USING NEIGHBORHOOD REPRESENTATIONS

Resumen de: US2025086502A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes maintaining a dataset including reference data objects that each have one or more labels, one or more features, or both; receiving a request to add, to the dataset, a new data object that has one or more features but is missing one or more labels; selecting N neighbor data objects based on similarity scores of the neighbor data objects with respect to the new data object; generating a neighborhood feature vector for the new data object; processing the neighborhood feature vector using a machine learning model to predict the one or more labels for the new data object; and updating the dataset to include the new data object and to associate the one or more predicted labels with the new data object.

SYSTEMS AND METHODS FOR ANOMALY DETECTION USING EXPLAINABLE MACHINE LEARNING ALGORITHMS

Resumen de: US2025086638A1

The platforms, systems and methods provided herein may provide explanations for AI algorithm outputs to facilitate efficiency and trust for a user. More specifically, the platforms, systems and methods provided herein may provide anomaly detection using explainable machine learning algorithms. Provided here is a computer-implemented method for providing explanations for AI algorithm outputs, comprising: (a) receiving transaction log data; (b) identifying anomalous transactions based at least in part on the transaction log data; (c) generating an expectation surface for one or more anomalous transactions; and (d) generating explanations for the anomalous transactions based at least in part on the expectation surface.

UTILIZING INVARIANT USER BEHAVIOR DATA FOR TRAINING A MACHINE LEARNING MODEL

Resumen de: US2025088873A1

A device may receive mobile radio data identifying utilization of a mobile radio network that includes base stations and user devices in a geographical area. The device may process the mobile radio data, with a machine learning feature extraction model, to generate a behavioral representation, that is probabilistic in nature, of invariant aspects of spatiotemporal utilization of the mobile radio network. The device may generate one or more instances of the spatiotemporal utilization of the mobile radio network that reflects the probabilistic nature of a spatiotemporal predictable component of the behavioral representation. The device may utilize the one or more instances of the spatiotemporal utilization of the mobile radio network as a dataset for training or evaluating a system to manage performance of the mobile radio network.

System And Method For Machine Learning Model Determination And Malware Identification

Resumen de: US2025086513A1

A system and method for batched, supervised, in-situ machine learning classifier retraining for malware identification and model heterogeneity. The method produces a parent classifier model in one location and providing it to one or more in-situ retraining system or systems in a different location or locations, adjudicates the class determination of the parent classifier over the plurality of the samples evaluated by the in-situ retraining system or systems, determines a minimum number of adjudicated samples required to initiate the in-situ retraining process, creates a new training and test set using samples from one or more in-situ systems, blends a feature vector representation of the in-situ training and test sets with a feature vector representation of the parent training and test sets, conducts machine learning over the blended training set, evaluates the new and parent models using the blended test set and additional unlabeled samples, and elects whether to replace the parent classifier with the retrained version.

MULTIPLE-VALUED LABEL LEARNING FOR TARGET NOMINATION

Resumen de: US2025086505A1

A system for generating training data for a machine learning target prioritization model includes a processor and a memory having computer executable instructions stored thereon. The computer executable instructions are configured for execution by the processor to: cause the processor to receive rules linking a candidate targets to a goal, where the rules are incomplete, biased, and/or partially incorrect, cause the processor to generate voters, where each voter is associated with a corresponding rule and each voter contains the logic of each corresponding rule, cause the processor to assign, via each one of the voters, at least one of an association value or an abstention to each one of the candidate targets, and cause the processor to create a single training label for each one of the candidate targets having at least one association value by combining the association values assigned to each respective candidate target.

Domain-Based Machine-Learned Classifiers

Resumen de: US2025086500A1

A machine-learning classification system for a hosted data storage service classifies documents in storage domains of the hosted data storage service. A hosted data storage service can include isolated storage domains that are individually configured to provide domain access by an authorized entity for a domain and prohibit access to the domain by unauthorized entities. A machine-learned domain-specific classifier is associated with a storage domain and is configured to generate a classification label for documents of the entity associated with the respective storage domain. A training system is configured to generate a machine-learned domain-specific classifier using a subset of annotated documents from the selected storage domain.

COMPUTER-BASED SYSTEMS HAVING COMPUTER ENGINES AND DATA STRUCTURES CONFIGURED FOR MACHINE LEARNING DATA INSIGHT PREDICTION AND METHODS OF USE THEREOF

Resumen de: US2025086494A1

Disclosed herein are method, system, and computer product embodiments for generating a textual summary of a data set based on traversing a decision tree according to sequence and rank numbers related to a query. Subsets of the data set may receive a rank number indicating the relevancy of the subset of data to the query. In response to traversing the desicion tree, a textual summary representative of the data set and subsets of data may be generated and displayed. The textual summary may also include a course of action recommendation based on the culmination of the data set and relevant data subsets.

MACHINE LEARNING APPROACH FOR DESCRIPTIVE, PREDICTIVE, AND PRESCRIPTIVE FACILITY OPERATIONS

Resumen de: WO2023215538A1

A digital twin of a facility defines relationships between different components of the facility and a system of record for the facility. Information from different monitoring systems for the facility are related to events by the digital twin of the facility. Historical operation information for the facility is used to train a machine learning model. The trained machine learning model facilitates operations at the facility by providing descriptive information, predictive information, and/or prescriptive information on the operations at the facility.

INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE

Resumen de: EP4521307A1

An information processing program for causing a computer to execute processing includes: extracting partial data that corresponds to each of a plurality of patterns of which an index according to an appearance frequency in a plurality of training samples is equal to or more than a second threshold, that is a pattern of a combination of one or more feature amounts of which a contribution degree to estimation of a machine learning model is equal to or more than a first threshold, from among the plurality of training samples that includes the plurality of feature amounts, from estimation target data that includes a plurality of feature amounts, to be a target of estimation processing by using the machine learning model; calculating a likelihood of an estimation result of a partial model for each pattern, in a case where the partial data extracted from the estimation target data is input to a corresponding partial model among the partial models trained for the respective patterns; and outputting the partial data selected based on the likelihood calculated for each partial model for each pattern, as an estimation basis of the machine learning model for the estimation target data.

Explainable classifications with abstention using client agnostic machine learning models

Resumen de: GB2633494A

Embodiments relate to providing explainable classifications with abstention using client agnostic machine learning models. A technique includes inputting, by a processor, records to a machine learning model, the records being associated with an information technology (IT) domain. The technique includes classifying, by the processor, the records with labels using the machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of the IT domain.

ADAPTIVE DATA COLLECTION OPTIMIZATION

Resumen de: US2025077604A1

Systems and methods to intelligently optimize data collection requests are disclosed. In one embodiment, systems are configured to identify and select a complete set of suitable parameters to execute the data collection requests. In another embodiment, systems are configured to identify and select a partial set of suitable parameters to execute the data collection requests. The present embodiments can implement machine learning algorithms to identify and select the suitable parameters according to the nature of the data collection requests and the targets. Moreover, the embodiments provide systems and methods to generate feedback data based upon the effectiveness of the data collection parameters. Furthermore, the embodiments provide systems and methods to score the set of suitable parameters based on the feedback data and the overall cost, which are then stored in an internal database.

SHOPPING BASKET MONITORING USING COMPUTER VISION

Resumen de: US2025078632A1

A system for monitoring shopping carts uses cameras to generate images of the carts moving in a store. In some implementations, cameras may additionally or alternatively be mounted to the shopping carts and configured to image cart contents. The system may use the collected image data, and/or other types of sensor data (such as the store location at which an item was added to the basket), to classify items detected in the shopping carts. For example, a trained machine learning model may classify item in a cart as “non-merchandise,” “high theft risk merchandise,” “electronics merchandise,” etc. When a shopping cart approaches a store exit without any indication of an associated payment transaction, the system may use the associated item classification data, optionally in combination with other data such as cart path data, to determine whether to execute an anti-theft action, such as locking a cart wheel or activating a store alarm. The system may also compare the classifications of cart contents to payment transaction records (or summaries thereof) to, e.g., detect underpayment events.

METHOD FOR ESTIMATING TIME PERIOD UNTIL EMPTY FOR MATERIAL IN A TANK OF VEHICLE

Resumen de: US2025078586A1

During an initialization period of a machine learning model, an electronic data processor is configured to estimate an initial depletion estimate of time period until empty for a material in the tank or container of a machine based on summing initial weighted inputs to the machine learning model in accordance with an initial equation set being applicable to the initialization period that is defined by an initial sub-operation period. After the initialization period of the machine learning model, an electronic data processor is configured to estimate a revised depletion time, where the revised depletion time comprises a time duration until empty or near empty.

MACHINE-LEARNED MODEL FOR OPTMIZING SELECTION SEQUENCE FOR ITEMS IN A WAREHOUSE

Resumen de: US2025078025A1

An online shopping concierge system sorts a list of items to be picked in a warehouse by receiving data identifying a warehouse and items to be picked by a picker in the warehouse. The system retrieves a machine-learned model that predicts a next item of a picking sequence of items. The model was trained, using machine-learning, based on sets of data that each include a list of picked items, an identification of a warehouse from which the items were picked, and a sequence in which the items were picked. The system identifies an item to pick first and a plurality of remaining items. The system predicts, using the model, a next item to be picked based on the remaining items, the first item, and the warehouse. The system transmits data identifying the first item and the predicted next item to be picked to the picker in the warehouse.

Continuous Integration and Automated Testing of Machine Learning Models

Resumen de: US2025077986A1

A system and method are disclosed to generate, modify, and deploy machine learning models. Embodiments include a database comprising historical sales data and a server comprising a processor and memory. Embodiments receive historical sales data comprising aggregated sales data for one or more items sold in one or more stores over one or more past time periods. Embodiments train a first machine learning model to learn model parameters and generate sales predictions by identifying one or more causal factors that influence the sale of one or more items. Embodiments train a second machine learning model, based on the first machine learning model, to generate second predictions. Embodiments evaluate the predictions of the first and second machine learning models as compared to the historical sales data, and deploy the machine learning model that generated the predictions that are closer to the historical sales data to generate one or more subsequent predictions.

SYSTEM AND METHOD FOR DETERMINING ONE OR MORE PERFORMANCE INDICATOR VALUES FOR A PLURALITY OF PHYSICAL COMPONENTS IN A TECHNICAL INSTALLATION

Resumen de: WO2025045782A1

Disclosed is an engineering system (102) and a method (400) for determining one or more performance indicator values for a plurality of physical components (108A-108N) in a technical installation (106) to be visualized in a multi-layered manner. The method comprises receiving, by a processing unit (202), a request to determine one or more performance indicator values associated with one or more physical components in the technical installation (106), determining one or more physical components associated with the one or more performance indicators based on analysis of an engineering design and corresponding engineering project of the technical installation, determining a first knowledge graph from a second knowledge graph, and determining, the requested one or more performance indicator values using a trained machine learning model on the first knowledge graph.

CELL-FREE DNA SEQUENCE DATA ANALYSIS TECHNIQUES FOR ESTIMATING FETAL FRACTION AND PREDICTING PREECLAMPSIA

Nº publicación: AU2023329418A1 06/03/2025

Solicitante:

FRED HUTCHINSON CANCER CENTER
UNIV OF WASHINGTON
FRED HUTCHINSON CANCER CENTER,
UNIVERSITY OF WASHINGTON

Resumen de: AU2023329418A1

In some embodiments, a computer-implemented method of enhancing sequence read data from a cell-free DNA (cfDNA) sample from a subject for predicting a pregnancy-related condition is provided. A computing system determines a coverage profile based on sequence read data for a plurality of informative sites associated with specific tissue types, cell types, or cell states. The computing system generates a prediction of a presence of or an absence of the pregnancy-related condition by providing at least features from a set of features based on a predicted fetal fraction and a set of features based on the coverage profile as input to at least one machine learning model trained to predict a probability of future onset of the pregnancy-related condition based on the features. In some embodiments, a computer-implemented method of enhancing sequence read data for predicting fetal fraction is provided.