Alerta

MACHINE LEARNING ASSISTANCE FOR INDUSTRIAL AUTOMATION PROGRAMMING AND DATA ENVIRONMENTS

Resumen de: US20260003335A1

Various embodiments of the present technology generally relate to solutions for improving industrial automation programming and data science capabilities with machine learning. More specifically, embodiments of the present technology include systems and methods for implementing machine learning engines within industrial programming and data science environments to improve performance, increase productivity, and add functionality. In an embodiment, a system comprises a user interface component configured to display a programming environment for editing control logic, wherein operational data from the industrial automation environment is accessible from within the programming environment through a data pipeline. A machine learning-based data science engine is configured to process the operational data from the industrial automation environment to generate processed data and identify a portion of the processed data relevant to a component of the control logic. The user interface component is further configured to surface the portion of the processed data in the programming environment.

SYSTEMS, APPARATUSES, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR GPS SPOOFING DETECTION

Resumen de: US20260003080A1

Systems, apparatuses, methods, and computer program products are provided herein. For example, a method may include access aviation specification data. In some embodiments, the method may include training a generative machine learning model using aviation specification data. In some embodiments, the method may include generating synthetic aviation data using the generative machine learning model. In some embodiments, the method may include training one or more global positioning system (GPS) spoofing detection machine learning models using the synthetic aviation data and historical aviation operations data. In some embodiments, the method may include deploying a first GPS spoofing detection machine learning model of the one or more GPS spoofing detection machine learning models to an edge-based device.

ADAPTABLE, SCALABLE, AND AUTONOMOUS PROTECTION VERIFICATION AND DECISION SUPPORT

Resumen de: US20260006080A1

A method includes obtaining information associated with assets and/or personnel to be protected and executing a set of weighting functions and a set of algorithms for protecting the assets and/or personnel. The weighting functions and algorithms are arranged in multiple levels of a hierarchy. Each level of the hierarchy includes one or more of the weighting functions and one or more of the algorithms. The one or more weighting functions and the one or more algorithms in at least one level of the hierarchy are applied across a timeline. The method also includes applying an artificial intelligence/machine learning (AI/ML) algorithm across the timeline to update results due to one or more changes during one or more operations involving the assets and/or personnel.

SYSTEMS AND METHODS FOR GENERATING A CONTEXTUALLY AND CONVERSATIONALLY CORRECT RESPONSE TO A QUERY

Resumen de: US20260003860A1

The present disclosure relates to systems and methods for generating contextually, grammatically, and conversationally correct answers to input questions. Embodiments provide for linguistic and syntactic structure analysis of a submitted question in order to determine whether the submitted question may be answered by at least one headnote. The question is then further analyzed to determine more details about the intent and context of the question. A federated search process, based on the linguistic and syntactic structure analysis, and the additional analysis of the question is used to identify candidate question-answer pairs from a corpus of previously created headnotes. Machine learning models are used to analyze the candidate question-answer pairs, additional rules are applied to rank the candidate answers, and dynamic thresholds are applied to identify the best potential answers to provide to a user as a response to the submitted question.

NOTEBOOK FOR NAVIGATING CODE USING MACHINE LEARNING AND FLOW ANALYSIS

Resumen de: US20260003580A1

A code notebook and backend cloud service are configured to intelligently analyze program source code that a developer wants analyzed. A user drafts a code query to be answered about the source code that may specify specific variables, code structure elements, and/or program flows to be scrutinized. A cloud-computing environment builds a code database of the source code and analyzes its text, code structures, and program flows using. The code database is embedded with indications of semantic equivalences for text in the source code, identifications of different code structural elements, and program flows. In the cloud-computing environment, a query service takes the code query of the developer and queries the database with the machine-learned embeddings, generating query results that are shared with the developer and shown in a representation of the source code.

RECORDING MEDIUM, TRAINING METHOD OF MACHINE LEARNING MODEL, AND TRAINING APPARATUS OF MACHINE LEARNING MODEL

Resumen de: US20260004189A1

A non-transitory computer-readable recording medium stores therein a training program of a machine learning model that outputs a proposal for obtaining a desired result, the training program of a machine learning model causes a computer to execute a process including acquiring training data including a plurality of attributes, acquiring constraint condition data of the attributes, calculating first information regarding prediction accuracy of the machine learning model based on the training data, calculating second information regarding feasibility of the proposal based on the training data and the constraint condition data, calculating an evaluation index based on the first information and the second information, and training the machine learning model based on the evaluation index.

SYSTEMS AND METHODS FOR USING ARTIFICIAL INTELLIGENCE FOR FRAUD DETECTION USING AN ENUMERATION DETECTION SYSTEM

Resumen de: US20260006037A1

A method for discontinuing interaction processing using an enumeration detection system may include receiving data associated with a plurality of interaction instances. The plurality of interaction instances may be associated with an entity. The method may further include extracting one or more interaction features from the data. The method may further include providing the one or more interaction features to a determinative machine-learning model. The determinative machine-learning model may be trained to identify enumeration patterns and output an enumeration score based on the identified enumeration patterns. The method may further include determining that the enumeration score exceeds a predetermined threshold. The method may further include discontinuing interaction processing for the entity based on the enumeration score exceeding the predetermined threshold.

SYSTEMS, APPARATUSES, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR GPS SPOOFING DETECTION

Resumen de: EP4671828A1

Systems, apparatuses, methods, and computer program products are provided herein. For example, a method may include access aviation specification data. In some embodiments, the method may include training a generative machine learning model using aviation specification data (504). In some embodiments, the method may include generating synthetic aviation data using the generative machine learning model (506). In some embodiments, the method may include training one or more global positioning system (GPS) spoofing detection machine learning models using the synthetic aviation data and historical aviation operations data (508). In some embodiments, the method may include deploying a first GPS spoofing detection machine learning model of the one or more GPS spoofing detection machine learning models to an edge-based device (510).

TRAINING PROGRAM OF MACHINE LEARNING MODEL, TRAINING METHOD OF MACHINE LEARNING MODEL, AND TRAINING APPARATUS OF MACHINE LEARNING MODEL

Resumen de: EP4672093A1

A training program of a machine learning model outputs a proposal for obtaining a desired result, the training program of a machine learning model causes a computer to execute a process including: acquiring training data including a plurality of attributes; acquiring constraint condition data of the attributes; calculating first information regarding prediction accuracy of the machine learning model based on the training data; calculating second information regarding feasibility of the proposal based on the training data and the constraint condition data; calculating an evaluation index based on the first information and the second information; and training the machine learning model based on the evaluation index.

MACHINE LEARNING MODELS FOR HIERARCHICAL MOLECULAR PROPERTY PREDICTION

Resumen de: EP4672250A2

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting properties of molecules based on the structure and composition of the molecules. In one aspect, a method comprises receiving molecule data characterizing a molecule and processing a model input based on the molecule data characterizing the molecule using a property prediction machine learning model comprising an ordered sequence of processing layers to generate, for each of a set of molecule properties, a respective value for the molecule property wherein: each processing layer is associated with a respective proper subset of the set of molecule properties; and each processing layer after the first in the sequence generates predicted molecule property values based on: (i) the model input to the property prediction machine learning model, and (ii) predicted molecule property values generated by one or more preceding processing layers in the sequence of processing layers.

METHOD OF DECISION-SUPPORT FOR A VEHICLE OR RELATED VEHICLE SIMULATION AND ASSOCIATED SYSTEM

Resumen de: EP4672085A1

Method of decision-support for a vehicle or related vehicle simulation, the method being executed by a system comprising a server (20), a client device (10) and a database (30), the method comprising the following phases:a. acquisition phase (100) in which the server (20) receives an input data from a device onboard of the vehicle,b. selection phase (200) in which the server (20) obtain a plurality of machine learning results R1, ..., Rn and computes at least one selection score, then at least one selection score being used to select a preferred machine-learning model MLp,c. transmission phase (300) in which the server (20) sends the result Rp as a recommendation to the client device (10),d. supply phase (400) in which the client device (10) provides the recommendation to a user (60),e. return phase (500) in which the client device returns decision data to a database (30).

DISEASE PREDICTION DEVICE, LEARNING MODEL GENERATION DEVICE, DISEASE PREDICTION METHOD, LEARNING MODEL GENERATION METHOD, AND COMPUTER-READABLE RECORDING MEDIUM

Resumen de: EP4672040A1

A learning model generation apparatus 10 comprises: a graph generation unit 11 which generates, from a data group including biometric information of persons and information indicating the presence or absence of occurrence of diseases in the persons, a graph composed of nodes representing data points and edges representing relationships between the nodes; a graph supplementation unit 12 which supplements the generated graph for a deficiency therein; and a model generation unit 13 which generates, from the supplemented graph, a data group in which the deficiency is supplemented, performs machine learning using the generated data group as training data, and generates a prediction model for predicting the occurrence of diseases in a person.

DEEP LEARNING ENABLED PREDICTION OF DRUG-INDUCED LIVER INJURY

Resumen de: WO2024178006A1

A method may include determining, based at least on a knowledge graph, a plurality of biological interaction profiles associated with a plurality of drugs. The knowledge graph being representative of a plurality of interactions between a variety of drugs, proteins, and a hierarchy of biological functions. Each biological interaction profile may be representative of the effects of a corresponding drug being propagated through protein-protein interactions and biological functions. A liver injury prediction model may be trained, based on a training dataset including the biological interaction profiles, a probability of drug induced liver injury. The liver injury prediction model to may be applied to determine, based on the biological interaction profile of a drug, the probability of liver injury associated with the drug. In some cases, the liver injury prediction model may further determine the probability of liver injury based on the molecular fingerprint and/or the molecular properties of the drug.

WEIGHT AVERAGED REWARDED POLICY TRAINING FOR MACHINE LEARNING MODELS

Resumen de: WO2025265056A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for fine-tuning a target machine learning model to perform a target machine learning task. In one aspect, a method comprises: obtaining initial parameters for a target machine learning model; at each interpolation iteration of a sequence of interpolation iterations: training a plurality of auxiliary machine learning models to perform the target machine learning task using training data for the target machine learning task, interpolating the trained parameters for the plurality of auxiliary machine learning models for the interpolation iteration, and updating the current parameters for the target machine learning model using the interpolated parameters for the interpolation iteration; and, after the final interpolation iteration, determining a trained set of parameters for the target machine learning model based on the current parameters for the target machine learning model.

FIRST NODE, SECOND NODE, COMPUTER SYSTEM AND METHODS PERFORMED THEREBY, FOR HANDLING HYPERPARAMETERS CORRESPONDING TO A PLURALITY OF SETS OF DATA

Resumen de: WO2025261578A1

A first node (111) obtains (302) two or more first sets of data out of a plurality of sets collected by third nodes (113). Each third node has collected a set. A plurality of clusters have been determined. Each of the two or more first sets of data corresponds to a respective set of data in a center of a respective cluster. The plurality of clusters have been determined based on a similarity of respective statistical features of the sets of data. A number of the two or more first sets of data is smaller than a second number of the plurality of sets. The first node (111) determines (303) and tunes a respective hyperparameter for each obtained two or more first sets of data to train a respective machine learning model with a corresponding set of data of the plurality of sets of data and outputs (305) an indication indicating the hyperparameters.

COMPUTER-BASED SYSTEMS CONFIGURED FOR ENTITY RESOLUTION AND INDEXING OF ENTITY ACTIVITY

Resumen de: US2025390770A1

In order to facilitate the entity resolution and entity activity tracking and indexing, systems and methods include receiving first source records from a first database and second source records from a record database. A candidate set of second source records is determined by a heuristic search in the set of second source records. A candidate pair feature vector associated with each candidate pair of first and second source records is generated. An entity matching machine learning model predicts matching first source records for each candidate second source record based on the respective candidate pair feature vector. An aggregate quantity associated with the matching first source records is aggregated from a quantity associated with each first source record, and a quantity index for each candidate second source record is determined based the aggregate quantities. Each quantity index is displayed to a user.

ANALYSIS AND CORRECTION OF SUPPLY CHAIN DESIGN THROUGH MACHINE LEARNING

Resumen de: US2025390817A1

A method and system for a machine learning cluster analysis of historical lead time data, which is augmented by one or more features. The data can also be divided into groups, based on time-density of the data, with clustering performed on each group. Furthermore, clustering can also be projected onto two dimensions. In addition, the historical lead time data is separated into a plurality of tolerance zones based on tolerance criteria. The clusters are separated in accordance with a tolerance zone of each group; and further separated according to one or more lead time identifiers to provide one or more separated clusters.

SPECIFIC FILE DETECTION BAKED INTO MACHINE LEARNING PIPELINES

Resumen de: US2025390576A1

A set of features including a first feature and a second feature is received at a server. A subset of the set of features is determined for use in generating a model usable by a device to locally make a malware classification decision. The device has reduced computing resources as compared to computing resources of the server. The subset of the set of features is used to generate the model. The generated model includes the first feature and does not include the second feature. A determination is made, at a time subsequent to the generation of the model, that an updated model should be deployed to the device. An updated model is generated.

SYSTEM AND METHOD FOR UTILIZING GROUPED PARTIAL DEPENDENCE PLOTS AND GAME-THEORETIC CONCEPTS AND THEIR EXTENSIONS IN THE GENERATION OF ADVERSE ACTION REASON CODES

Resumen de: US2025390794A1

A framework for interpreting machine learning models is proposed that utilizes interpretability methods to determine the contribution of groups of input variables to the output of the model. Input variables are grouped based on dependencies with other input variables. The groups are identified by processing a training data set with a clustering algorithm. Once the groups of input variables are defined, scores related to each group of input variables for a given instance of the input vector processed by the model are calculated according to one or more algorithms. The algorithms can utilize group Partial Dependence Plot (PDP) values, Shapley Additive Explanations (SHAP) values, and Banzhaf values, and their extensions among others, and a score for each group can be calculated for a given instance of an input vector per group. These scores can then be sorted, ranked, and then combined into one hybrid ranking.

SELECTING A NEURAL NETWORK ARCHITECTURE FOR A SUPERVISED MACHINE LEARNING PROBLEM

Resumen de: US2025390745A1

Systems and methods, for selecting a neural network for a machine learning (ML) problem, are disclosed. A method includes accessing an input matrix, and accessing an ML problem space associated with an ML problem and multiple untrained candidate neural networks for solving the ML problem. The method includes computing, for each untrained candidate neural network, at least one expressivity measure capturing an expressivity of the candidate neural network with respect to the ML problem. The method includes computing, for each untrained candidate neural network, at least one trainability measure capturing a trainability of the candidate neural network with respect to the ML problem. The method includes selecting, based on the at least one expressivity measure and the at least one trainability measure, at least one candidate neural network for solving the ML problem. The method includes providing an output representing the selected at least one candidate neural network.

MACHINE LEARNING MODELS FOR HIERARCHICAL MOLECULAR PROPERTY PREDICTION

Nº publicación: US2025391516A1 25/12/2025

Solicitante:

ISOMORPHIC LABS LTD [GB]
Isomorphic Labs Limited

Resumen de: US2025391516A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting properties of molecules based on the structure and composition of the molecules. In one aspect, a method comprises receiving molecule data characterizing a molecule and processing a model input based on the molecule data characterizing the molecule using a property prediction machine learning model comprising an ordered sequence of processing layers to generate, for each of a set of molecule properties, a respective value for the molecule property wherein: each processing layer is associated with a respective proper subset of the set of molecule properties; and each processing layer after the first in the sequence generates predicted molecule property values based on: (i) the model input to the property prediction machine learning model, and (ii) predicted molecule property values generated by one or more preceding processing layers in the sequence of processing layers.