Alerta

SYSTEMS AND METHODS FOR MACHINE LEARNING CONTROL OF A SURGICAL DEVICE

Resumen de: US2025322952A1

A computer-implemented method for control of a surgical device includes accessing raw data captured by a sensor of the surgical device during a procedure, filtering the raw data with a filter, generating a difference data based on a difference between the raw data and the filtered data, generating zero-crossing data based on determining a point in time where an amplitude of the difference data last crossed from a non-zero amplitude value through a zero amplitude value to a non-zero amplitude value of the opposite sign, providing the zero-crossing data as an input to a machine learning classifier, and predicting a probability of an end stop point based on the machine learning classifier. The end stop point includes a point in time where a knife of the surgical device ceases to cut tissue.

MACHINE LEARNING OPTIMIZATION OF A PROCESS IN VIEW OF PREDICTED SUSTAINABILITY

Resumen de: US2025322210A1

A method of performing sustainability optimization includes processing a set of inputs using a trained machine learning model to generate a set of outputs, wherein the set of inputs correspond to configuration parameters of a process configured to be performed on a physical machine, and wherein the set of outputs includes a plurality of predicted waste metrics resulting from performance of the process on the physical machine. The method further includes optimizing the set of inputs and the set of outputs for meeting sustainability constraints in view of process constraints and outputting a recommendation for operating the process on the physical machine based on the optimized set of inputs and set of outputs, for avoiding a risk of failure to operate the process, while meeting the sustainability constraints and the process constraints.

AUGMENTING MACHINE LEARNING LANGUAGE MODELS USING SEARCH ENGINE RESULTS

Resumen de: US2025322236A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting machine learning language models using search engine results. One of the methods includes obtaining question data representing a question; generating, from the question data, a search engine query for a search engine; obtaining a plurality of documents identified by the search engine in response to processing the search engine query; generating, from the plurality of documents, a plurality of conditioning inputs each representing at least a portion of one or more of the obtained documents; for each of a plurality of the generated conditioning inputs, processing a network input generated from (i) the question data and (ii) the conditioning input using a neural network to generate a network output representing a candidate answer to the question; and generating, from the network outputs representing respective candidate answers, answer data representing a final answer to the question.

REAL-TIME CONTENT INTEGRATION BASED ON MACHINE LEARNED SELECTIONS

Resumen de: US2025322316A1

A candidate content item is identified for integration into a content collection. The candidate content item is associated with a first value. Using at least one machine learning model, a select value and a skip value are automatically generated for the candidate content item. The select value indicates a likelihood that the user will select the candidate content item, and the skip value indicates a likelihood that the user will bypass the candidate content item. A second value is generated for the candidate content item based on the first value, the select value, and the skip value. The candidate content item is automatically selected from a plurality of candidate content items based on the second value meeting at least one predetermined criterion. The selected candidate content item is then automatically integrated into the content collection, which is caused to be presented on a device of a user.

TECHNIQUES FOR GENERATING SYNTHETIC DATA

Resumen de: US2025322027A1

A system and method include generating synthetic data by generating a first set of hyperparameters for a first trained machine learning model and a second set of hyperparameters for a second trained machine learning model, generating a plurality of synthetic data vectors using the first and second trained machine learning models, computing an error function for the first and second set of hyperparameters using a third machine learning model, computing an objective function value, responsive to determining that the objective function value is not an optimal value, updating the first set of hyperparameters and the second set of hyperparameters or responsive to determining that the objective function value is an optimal value outputting the plurality of synthetic data vectors as a set of synthetic data.

TECHNIQUES FOR GENERATING SYNTHETIC DATA

Resumen de: US2025322026A1

A system and method include generating synthetic data by generating a first set of hyperparameters for a first trained machine learning model and a second set of hyperparameters for a second trained machine learning model, generating a plurality of synthetic data vectors using the first and second trained machine learning models, computing an error function for the first and second set of hyperparameters using a third machine learning model, computing an objective function value, responsive to determining that the objective function value is not an optimal value, updating the first set of hyperparameters and the second set of hyperparameters or responsive to determining that the objective function value is an optimal value outputting the plurality of synthetic data vectors as a set of synthetic data.

MITIGATING TEMPORAL GENERALIZATION FOR A MACHINE LEARNING MODEL

Resumen de: US2025322342A1

Mitigation of temporal generalization losses a target machine learning model is disclosed. Mitigation can be based on identifying, removing, modifying, transforming, etc., features, explanatory variables, models, etc., that can have an unstable relationship with a target outcome over time. Implementation of a more stable representation can be initiated. Temporal stability measures (TSMs) for one or more model feature(s) can be determined based on one or more variable performance metrics (VPMs). A group of one or more VPMs can be selected based on features of a model in either a development or production environment. Model feature modification can be recommended based on a TSM, which can prune a feature, transform a feature, add a feature, etc. Temporal stability information can be presented, e.g., via a dashboard-type user interface. Models can be updated based on mutations of a model comprising a feature modification(s), including competitive champion/challenger model updating.

Automated Data Hierarchy Extraction And Prediction Using A Machine Learning Model

Resumen de: US2025322312A1

Techniques are disclosed for revising training data used for training a machine learning model to exclude categories that are associated with an insufficient number of data items in the training data set. The system then merges any data items associated with a removed category into a parent category in a hierarchy of classifications. The revised training data set, which includes the recategorized data items and lacks the removed categories, is then used to train a machine learning model in a way that avoids recognizing the removed categories.

MACHINE LEARNING OPTIMIZATION OF A PROCESS IN VIEW OF PREDICTED SUSTAINABILITY

Resumen de: EP4632619A1

A method of performing sustainability optimization includes processing a set of inputs using a trained machine learning model to generate a set of outputs, wherein the set of inputs correspond to configuration parameters of a process configured to be performed on a physical machine, and wherein the set of outputs includes a plurality of predicted waste metrics resulting from performance of the process on the physical machine. The method further includes optimizing the set of inputs and the set of outputs for meeting sustainability constraints in view of prospcess constraints and outputting a recommendation for operating the process on the physical machine based on the optimized set of inputs and set of outputs, for avoiding a risk of failure to operate the process, while meeting the sustainability constraints and the process constraints.

INFORMATION PROCESSING METHOD, PROGRAM, AND INFORMATION PROCESSING DEVICE

Resumen de: EP4632637A1

Provided is an information processing method, etc. that assists a user in interpreting behavior of a generated machine learning model. In the information processing method, a computer executes processing of recording a plurality of sets of an explanatory data vector xn input to an existing machine learning model (21) and an objective data vector yn output from the machine learning model (21) in association with each other, calculating an interpretation matrix A† which is a vector product of an explanatory matrix X in which a plurality of sets of the explanatory data vector xn is arranged and a generalized inverse matrix of an objective matrix Y in which the objective data vector yn is arranged in an order corresponding to the explanatory data vector X, and outputting a chart (41, 42, and 43) related to the interpretation matrix A†.

Machine-learning model(s) for estimating ran functionality machine learning model impact on performance measurement counters

Resumen de: GB2640229A

An apparatus 100 comprising: means for receiving a network configuration 106 derived from a plurality of machine-learning, ML models, each ML model directed towards a respective one or more radio access network, RAN functionalities; means for receiving a plurality of predicted performance, PM measurement counters output 108 from a plurality of ML performance measurement models, each ML prediction measurement model corresponding to one of the plurality of ML models; and means for processing, using a common ML performance measurement counter model 102, the network configuration and the plurality of predicted performance measurement counters to determine a model output comprising, for one or more performance measurement counters, a respective plurality of impact scores 112, wherein each impact score is indicative of a predicted impact of a corresponding ML model in the plurality of ML models on the respective performance measurement counter of said impact score for the network configuration. The apparatus may further comprise means for executing the plurality of ML models on respective measurement data to generate a plurality of respective RAN functionality predictions; and means for generating, from the plurality of respective RAN functionality predictions, the network configuration.

METHOD FOR TRAINING DEEP LEARNING MODEL FOR GENERATIVE RETRIEVAL AND APPARATUS FOR PERFORMING QUERY INFERENCE USING PRE-TRAINED DEEP LEARNING MODEL

Resumen de: US2025307630A1

In accordance with an embodiment of the present invention, there is provided a method for training a deep learning model for generative retrieval, the method comprising: performing a first training step of the deep learning model to generate vocabulary identifiers for each of at least two documents by receiving the at least two documents as input; and performing a second training step of the deep learning model to determine weights for the vocabulary identifiers by receiving a query, a relevant document associated with the query, and an irrelevant document not associated with the query as input.

CANCER CLASSIFIER MODELS, MACHINE LEARNING SYSTEMS AND METHODS OF USE

Resumen de: US2025316339A1

Disclosed herein are classifier models, computer implemented systems, machine learning systems and methods thereof for classifying asymptomatic patients into a risk category for having or developing cancer and/or classifying a patient with an increased risk of having or developing cancer into an organ system-based malignancy class membership and/or into a specific cancer class membership.

SYSTEMS AND METHODS FOR AUGMENTING FEATURE SELECTION USING FEATURE INTERACTIONS FROM A PRELIMINARY FEATURE SET

Resumen de: US2025315722A1

Systems and methods for augmenting feature selection for a first machine learning model using feature interactions from a preliminary feature set used for a second model. In some aspects, the system receives a first candidate set of features to train a machine learning model. The system also receives a precursor feature set used to train a precursor machine learning model in preparation for the machine learning model. Using the first candidate set of features and the precursor feature set, the system trains an algorithm to produce an interaction matrix, wherein the interaction matrix indicates an explanative power of each feature when combined with other features. Based on the interaction matrix, the system generates a subset of features from the first candidate set of features and the precursor feature set using a selection program. The system thus trains the machine learning model to use the subset of features as input.

AI-POWERED ADAPTIVE PERFORMANCE

Resumen de: US2025315723A1

Methods and systems for federated caching with intelligent content delivery network (CDN) optimization are disclosed. A caching system collects data relating to one or more user's interactions with an application. Machine learning (M/L) models analyze and train on the usage data to predict user behavior patterns, application performance trends and potential data roadblocks. The predicted outputs may be used to generate an adaptive performance policy configured to enable proactive caching decisions and system performance optimizations.

Topic Identification Based on Virtual Space Machine Learning Models

Resumen de: US2025315628A1

Techniques for displaying workflow responses based on determining topics associated with user requests are discussed herein. In some examples, a user may post a request (e.g., question) to a virtual space (e.g., a channel, thread, board, etc.) of a communication platform. The communication platform may input the request into a machine learning model trained to identify topics associated with the request and confidence levels associated with topics. In such examples, the communication platform may associate a topic with the user request based on the confidence level of the topic. In some examples, the communication platform may determine that the topic is associated with a graphical identifier (e.g., emoji). The communication platform may cause the graphical identifier to be displayed to the virtual space within which the user request was posted. In response to displaying the graphical identifier, the communication platform may display a workflow response to the virtual space.

MACHINE-LEARNING-BASED IDENTIFICATION OF USER INTERESTS

Resumen de: US2025315627A1

A method for providing user-specific content recommendations to a user may comprise selecting a user interest from a plurality of predefined user interests, extracting user activity data associated with the selected user interest, constructing a context data structure associated with the selected user interest based on a predefined knowledge graph data structure associated with the plurality of predefined user interests, generating one or more new user interests by providing the constructed context data structure and the user activity data to a trained machine learning model, generating a user-specific content recommendation based on the one or more new user interests, and providing the user-specific content recommendation to the user.

TECHNIQUES FOR PROVIDING SYNCHRONOUS AND ASYNCHRONOUS DATA PROCESSING

Resumen de: US2025315437A1

Techniques discussed herein include dynamically providing synchronous and/or asynchronous data processing by a machine-learning model service. The machine-learning model service (“the service”) executes a stream manager application, a web interface, and a machine-learning model via a common container. The stream manager application can obtain input data (e.g., from an input data stream, a partition of an input data stream, etc.) and provide the data to the machine-learning model through the web interface using a local communication channel (e.g., a loopback interface that bypasses local network interface hardware of the computing device on which the model executes). Prediction results from the model may be provided as output data (e.g., to an output data stream, to a partition of an output data stream, etc.).

EVALUATING EXPLAINABLE ARTIFICIAL INTELLIGENCE MODELS AND AN ARCHITECTURE FOR AN ENSEMBLE EXPLAINABLE MODEL SELECTION

Resumen de: US2025315448A1

A system includes one or more processors to store a first explanatory model (e.g., a SHAP model or a LIME model) and a second explanatory model; execute the machine learning model (e.g., a neural network) using a first set of data to generate a first classification data point; generate a first plurality of explanatory evaluation metrics for the first explanatory model by applying the first explanatory model to the first classification data point; and responsive to the first plurality of explanatory evaluation metrics satisfying an explanatory model selection policy, apply the first explanatory model and the second explanatory model to a second classification data point output by the machine learning model based on a second set of transaction data.

PROCESSING SYSTEM HAVING A MACHINE LEARNING ENGINE FOR PROVIDING A SURFACE DIMENSION OUTPUT

Resumen de: US2025315868A1

Systems and apparatuses for generating surface dimension outputs are provided. The system may collect an image from a mobile device. The system may analyze the image to determine whether they comprise one or more standardized reference objects. Based on analysis of the image and the one or more standardized reference objects, the system may determine a surface dimension output. The system may determine one or more settlement outputs and one or more repair outputs for the driver based on the surface dimension output.

MACHINE LEARNING POWERED ANOMALY DETECTION FOR MAINTENANCE WORK ORDERS

Resumen de: US2025315798A1

An industrial work order analysis system applies statistical and machine learning analytics to both open and closed work orders to identify problems and abnormalities that could impact manufacturing and maintenance operations. The analysis system applies algorithms to learn normal maintenance behaviors or characteristics for different types of maintenance tasks and to flag abnormal maintenance behaviors that deviate significantly from normal maintenance procedures. Based on this analysis, embodiments of the work order analysis system can identify unnecessarily costly maintenance procedures or practices, as well as predict asset failures and offer enterprise-specific recommendations intended to reduce machine downtime and optimize the maintenance process.

ML MODEL PIPELINE FOR QUBO-BASED ANNEALING WORKLOADS

Resumen de: US2025315705A1

One example method includes using a first machine learning (ML) model L to select a set of Lagrangian weights λi for each constraint i defined in a given Hamiltonian function, using λi for every constraint i to compile the Hamiltonian function to a matrix, using a second ML model, trained with λi and hardware telemetry, to make a best hardware Ω selection, selecting a set of hyperparameters Ψi for a given QUBO, λi, and Ω, and solving the given QUBO using the best hardware Ω and the set of hyperparameters Ψi.

SYSTEMS AND METHODS FOR EMOTIONALLY ADAPTIVE FINANCIAL CHATBOT

Resumen de: US2025315824A1

Various examples are directed to systems and methods for emotionally adaptive financial chatbots. A method includes receiving authentication information from a user of the computer system, authenticating the user for a transaction based on the received authentication information, and detecting an abnormal aspect of the transaction based on parameters of the transaction. Upon detecting the abnormal aspect, the method includes determining, using machine learning, an emotional state of the user. The method further includes adapting an interaction style with the user based on the determined emotional state of the user, receiving an input from the user after adapting the interaction style, and implementing additional security requirements for the transaction based on the detected abnormal aspect, the input from the user, and the determined emotional state.

METHOD AND SYSTEM FOR IMPROVING MACHINE LEARNING OPERATION BY REDUCING MACHINE LEARNING BIAS

Resumen de: US2025315738A1

A network operation system and method accesses a training dataset for a network operation predictive model including historical network operation records and historical decision records, generates an inferred protected class dataset by executing a protected class demographic model, executes an algorithmic bias model using as input the historical decision records and the inferred protected class dataset to generate one or more fairness metrics, executes, based on the fairness metrics, a bias adjustment model using as input the historical decision records and the inferred protected class dataset to generate an adjusted training dataset, trains the network operation predictive model using as input the adjusted training dataset, receives an electronic request for a network operation, executes the network operation predictive model using as input at least one attribute of the electronic request for the network operation, and executes the network operation based on a prediction of the network operation predictive model.

PROACTIVE DEFENSE OF UNTRUSTWORTHY MACHINE LEARNING SYSTEM

Nº publicación: US2025315674A1 09/10/2025

Solicitante:

VISA INT SERVICE ASSOCIATION [US]
Visa International Service Association

Resumen de: US2025315674A1

Methods and systems for inducing model shift in a malicious computer's machine learning model is disclosed. A data processor can determine that a malicious computer uses a machine learning model with a boundary function to determine outcomes. The data processor can then generate transition data intended to shift the boundary function and then provide the transition data to the malicious computer. The data processor can repeat generating and providing the transition data, thereby causing the boundary function to shift over time.