Machine learning

IMAGE CLASSIFICATION USING MACHINE LEARNING INCLUDING WEAKLY-LABELED DATA

Absstract of: US20260087618A1

A system may receive a plurality of digital histology images, wherein each of the plurality of digital histology images is labeled with a respective image-level classification. A system may extract a plurality of tiles from each of the plurality of digital histology images. A system may create a first dataset comprising the plurality of tiles and respective image-level classifications. A system may train a first machine learning model using the first dataset. A system may create a second dataset by sampling the first dataset based on respective classifications and respective uncertainty measures for each of the plurality of tiles output by the trained first machine learning model. A system may train a second machine learning model using the second dataset, wherein the trained second machine learning model is configured to classify one or more tiles of a digital histology image.

METHOD FOR SINGLE CELL ANTIMICROBIAL SUSCEPTIBILITY TESTING IN A SUB-DOUBLING TIME

Absstract of: US20260085340A1

Methods and systems for antibacterial susceptibility testing of a bacterium are provided. The method includes exposing a bacterium to an antimicrobial agent. A series of images of the bacterium is captured over time after exposure The series of images are captured during an imaging period. For each image of the series of images, the method includes extracting a value of each feature in a set of morphological features of the bacterium. The set of morphological features includes one or more of area, aspect ratio, length, circularity, perimeter, angularity, curvature, ferret, pole, roundness, sinuosity, width, trajectory, morphology, orientation, solidity, and z-score. A rate of change is calculated for each feature of the set of morphological features during the imaging period. An inhibition status of the bacterium is determined using a machine-learning classifier applied to input data.

DATA PRIVACY PROTECTION AND REMOVAL FOR ARTIFICIAL INTELLIGENCE MODEL TRAINING AND DEPLOYMENT

Absstract of: US20260087104A1

There are provided systems and methods for data privacy protection and removal for artificial intelligence model training and deployment. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include use of machine learning (ML) models including large language models (LLMs). To comply with data privacy protections and copyright enforcement, a system may provide unlearning of content from ML models. The system may receive a request to unlearn a content and, after verifying the request is valid, identify the content used for during training of or inferencing by an ML model. The system may then map the content to concepts and correlate those concepts with ML model outputs using projections in a vector space. Based on the mapped concepts and outputs, neuron activation of the ML model may be analyzed to identify a negation vector and perform selective parameter dampening.

DEEP NEURAL NETWORKS (DNN) INFERENCE USING PRACTICAL EARLY EXIT NETWORKS

Absstract of: US20260086912A1

The present disclosure relates to methods and systems for providing inferences using machine learning systems. The methods and systems receive a load forecast for processing requests by a machine learning model and split the machine learning model into a plurality machine learning model portions based on the load forecast. The methods and systems determine a batch size for the requests for the machine learning model portions. The methods and systems use one or more available resources to execute the plurality of machine learning model portions to process the requests and generate inferences for the requests.

MACHINE LEARNING TECHNIQUES FOR GENERATING CONTROLLER LOGIC

Absstract of: US20260086524A1

Embodiments of the present disclosure relate to generating controller logic. Indication of a controller logic generation request associated with an asset identifier may be received. A prompt template set associated with a controller logic generation workflow may be identified based on the asset identifier. The prompt template of the prompt template set may comprise one or more instruction sets. The prompt template set may be input into a large language model comprising one or more transformer neural networks and configured to generate a controller logic configuration file for the asset identifier based on the prompt template set and intent classification associated with each prompt template. The controller logic configuration file may be received from the large language model. Performance of one or more prediction-based actions may be initiated based on the controller logic configuration file.

MODEL-BASED TASK PROCESSING

Absstract of: US20260087382A1

Embodiments of the disclosure provide a solution for model-based task processing. A method includes: obtaining a base parameter set of a pre-trained base machine learning model, and a first parameter set and a second parameter set of a trained low-rank machine learning model for a first task; applying a Hadamard operator on the base parameter set and the first parameter set, to obtain an intermediate parameter set; aggregating the second parameter set and the intermediate parameter set, to obtain an update parameter set; fine-tuning the base parameter set with the update parameter metric, to obtain a fine-tuned parameter set for a target machine learning model corresponding to the first task; and applying the target machine learning model to perform a model inference for the first task with the fine-tuned parameter set.

AUTOMATED MACHINE LEARNING FAULT MODELING WITH GROUPING

Absstract of: US20260086257A1

Methods, computing systems, and computer-readable media for a machine learning method of modeling fault-related properties of a geological region are presented. The techniques include: obtaining seismic geological data for a geological region; obtaining from a user identifications of a plurality of faults in the geological region; automatically generating values for descriptors of respective faults of the plurality of faults; automatically partitioning faults of the plurality of faults into a plurality of groups according to the values for the descriptors; obtaining a mapping of respective groups of the plurality of groups to modeling parameter values; applying the mapping to a fault in the geological region outside of the plurality of faults to obtain a modeling parameter value for the fault outside of the plurality of faults; and modeling a fault-related property of the geological region based on the modeling parameter value for the fault outside of the plurality of faults.

SYSTEMS AND METHODS FOR COLLISION DETECTION

Absstract of: US20260087858A1

A method for detecting vehicle collisions using multi-stage data analysis is described. Telematics data from a vehicle-installed computing device is received and processed through a heuristic filter to identify potential collisions. A feature vector is generated from the filtered data and input into a trained predictive model, which classifies the vector as representing a collision or not. The method then retrieves associated dashcam footage and uses it, along with the predictive model's output, to confirm the occurrence of a collision. Upon confirmation, a notification is transmitted to a remote computing device. This approach combines telematics data analysis, machine learning prediction, and video verification to achieve accurate collision detection and notification.

SYSTEM AND METHOD FOR TEACHING MACHINE LEARNING MODELS TO RECOGNIZE CONCEPTS IN MULTIMEDIA DOCUMENTS THROUGH NATURAL LANGUAGE INTERACTION AND MIXED-INITIATIVE LEARNING

Absstract of: AU2024274930A1

A method and system for training machine learning models using natural language interactions as well as techniques utilizing machine learning models trained using natural language interactions. A method includes applying a language model to text of a set of natural language interactions in order to output a set of domain-specific language (DSL) data, wherein the set of natural language interactions is between a user and at least one other entity, wherein the set of natural language interactions indicates at least one user-defined concept; querying a knowledge base based on the set of DSL data in order to obtain at least one DSL query result; integrating the at least one DSL query result with a structured representation of the natural language interactions in order to create at least one contextualized DSL query result; and training the language model using the at least one contextualized DSL query result.

METHOD FOR GENERATING DENTAL MODELS BASED ON AN OBJECTIVE FUNCTION

Absstract of: EP4715752A2

Disclosed is a computer-implemented method of generating a dental model based on an objective function output, comprising creating an objective function comprising at least one quality estimation function which trains at least one machine learning method that generates quality estimation output, and an objective function output is the output of the objective function providing a model as an input data to the objective function and generating model-related objective function output; and modifying the model based on the model-related objective function output to transform the model to a generated model, wherein the generated model is the dental model.

MODELING CLOUD INEFFICIENCIES USING DOMAIN-SPECIFIC TEMPLATES

Absstract of: US20260079768A1

Systems and methods are provided for identifying cloud inefficiencies. The method includes obtaining telemetric log data for services, distinct from the server, executing on cloud computing systems. The method also includes determining disaggregation data for the services based on the telemetric log data by applying disaggregation algorithms. The method also includes forming feature vectors based on the telemetric log data. The method also includes identifying software of service types and cloud wastage templates by inputting the feature vectors to trained classifiers, wherein the cloud wastage templates follow conventions of a domain specific language (DSL) that describe the cloud computing systems. Each classifier is a machine-learning model trained to identify cloud wastages for predetermined states of the cloud computing systems. The method also includes determining cloud states of computing resources used by the services based on the disaggregation data. The method also includes cataloging cloud inefficiencies using the cloud wastage templates.

MACHINE-LEARNING PREDICTION OR SUGGESTION BASED ON OBJECT IDENTIFICATION

Absstract of: US20260080314A1

Disclosed herein are system, computer-program product (non-transitory computer-readable medium), and method embodiments for machine-learning prediction or suggestion based on object identification. A system including at least one processor may be configured to cross-reference an identifier of a selected object with a list of known unique identifiers. The selected object may be selected via received selection. The at least one processor may further retrieve a set of values associated with the identifier of the selected object, upon determining that the list of known unique identifiers includes the identifier of the selected object, and perform machine-learning to derive a predicted-value set based at least in part on the set of values associated with the identifier of the selected object and a category applicable to the selected object. The at least one processor may determine that the predicted-value set satisfies a predetermined confidence condition, and output at least part of the predicted-value set.

DOMAIN-AWARE NEUROSYMBOLIC AGENTS FOR IMPROVING PROBLEM-SOLVING ACCURACY AND CONSISTENCY

Absstract of: US20260080313A1

A system receives domain specific questions from users and answers them. The system stores domain specific information comprising domain specific facts and domain specific programs. The system receives an input request to perform a domain specific task for the particular domain. The system provides the input request to a machine learning model trained to predict a score indicating whether the input request should be processed by a symbolic processor or by a neural network. If the score predicted by the machine learning model indicates that the input request should be processed by the symbolic processor, the system determines whether a stored domain specific program can solve the input request. If none of the stored domain specific programs can solve the input request, the system generates a new program for solving the input request using a machine learning based language model and the set of domain specific facts.

MACHINE LEARNING MODEL FOR PROCESSING A COMMUNICATION RECORD AND IDENTIFYING AN ACTION

Absstract of: US20260080457A1

In an embodiment, a computer-implemented method includes parsing a communication record, determining one or more intents of the communication record using a trained machine learning model, linking the communication record to one or more record IDs, identifying one or more fields within the communication record, presenting the communication record in a standardized form, including identification of intent, the standardized form resulting from the identified one or more fields, and determining a corresponding intent related action on the determined one or more intents.

SYSTEM AND METHOD FOR GENERATION AND USE OF DATA MODELS FOR DETERMINATION OF INFERRED SKILLS

Absstract of: WO2026059589A1

Embodiments described herein are generally directed to computer-based data analytics and the processing of enterprise data, including the generation and use of data models for determining inferred characteristics associated with candidates. In accordance with an embodiment, the system utilizes data-processing pipelines and machine learning models to process structured, semi-structured, and/or unstructured sets of data, received from various sources; generate a multi-dimensional ontology and a taxonomy associated with the characteristics of open positions or potential candidates; identify, based on the data models, one or more additional or inferred characteristics associated with the candidates; and present the output by way of an analytics dashboard, scorecard, or other data visualization.

Training a neural database for entity matching

Absstract of: AU2025201913A1

Certain aspects of the disclosure provide a method of training a neural database for entity matching. In examples, a method may include: extracting, from an electronic data repository, entity data related to a first entity that provides a good or a service; transforming the entity data into structured entity data configured to be processed by a machine learning model; processing the structured entity data with the machine learning model to generate metadata associated with the structured entity data; augmenting the structured entity data with the metadata associated with the structured entity data; and training the neural database based on the augmented structured entity data to predict one or more second entities that supply materials for the first entity and associated with the good or the service. Certain aspects of the disclosure provide a method of training a neural database for entity matching. In examples, a method may include: extracting, from an electronic data repository, entity data related to a first entity that provides a good or a service; transforming the entity data into structured entity data configured to be processed by a machine learning model; processing the structured entity data with the machine learning model to generate metadata associated with the structured entity data; augmenting the structured entity data with the metadata associated with the structured entity data; and training the neural database based on the augmented structured entity data to

CONSTRAINED NON-LINEAR HYBRID MODELS FOR PREDICTION FROM MULTIPLE DATA SOURCES

Absstract of: AU2024319668A1

In some aspects, a machine learning (ML) model can be trained for risk assessment. The ML model can be trained to determine a risk indicator for a target entity from predictor variables associated with the target entity. The predictor variables are obtained from multiple sources with varying availability, and the training of the ML model is accomplished based on a multi-dimensional representation of common information from the set of data sources. Once generated, the risk indicator can be transmitted to a remote computing device in a responsive message for use in controlling access of the target entity to a computing environment.

SYSTEMS AND METHODS FOR IDENTIFYING COMPLEMENTARY OBJECTS HAVING SIMILAR STYLES

Absstract of: US20260080282A1

Described are systems and methods for determining complementary and/or matching objects based on an input query object. The described systems and methods can generate an embedding representative of the provided object, which can be transformed to generate a style embedding by a trained system, such as a machine learning system. The style embedding can then be used to identify one or more complementary objects from a corpus of classified objects. Aspects of the present disclosure also relate to creation of the training dataset, as well as training the machine learning system.

AUTOMATED MACHINE LEARNING MODEL EXPLANATION GENERATION

Absstract of: US20260080283A1

A processing system including at least one processor may obtain description information of a first machine learning model, obtain a set of interpretation criteria for the first machine learning model, and generate, via a second machine learning model, an explanation text providing an interpretation of the first machine learning model in accordance with the set of interpretation criteria and the description information of the first machine learning model.

TRAFFIC PATTERN-BASED PREDICTION OF CLOUD USAGE COSTS

Absstract of: US20260081894A1

Traffic log data generated by cloud firewalls executing in a cloud environment during a time period that indicate classes and corresponding amounts of network traffic detected across sessions as well as usage cost data recorded for the cloud firewalls during the time period are obtained. The traffic log data are preprocessed to generate training data comprising feature vectors indicating the aggregate amount of network traffic detected for each traffic class during a corresponding time interval within the time period and are labeled with the associated usage cost. A machine learning model is trained on the labeled traffic log data to learn the impact each traffic class has on the accumulated usage costs. The trained model generates predicted usage costs based on distributions of detected network traffic across traffic classes that are analyzed to correlate traffic patterns with usage costs to determine the optimal size(s) of cloud firewalls to deploy.

AIRCRAFT HARDWARE COMPONENT ROTABILITY CLASSIFICATION USING MACHINE LEARNING

Absstract of: US20260079985A1

An application extracts a plurality of features of a hardware component of an aircraft. The application inputs a first subset of features of the plurality of features into a first machine learning model, and receives as output a first determination of whether the hardware component is rotable. The application inputs a second subset of features of the plurality of features into a second machine learning model, and receives as output a second determination of whether the hardware component is rotable. The applications determines, based on the first determination and the second determination, a final determination of whether the hardware component is rotable, and adds a data structure for the hardware component with the final determination in a searchable database. The application receives a query from a user that is associated with the hardware component, runs a search, outputs whether the hardware component is rotable.

SYSTEMS AND METHODS FOR MACHINE LEARNING-BASED CLASSIFICATION OF SIGNAL DATA SIGNATURES FEATURING USING A MULTI-MODAL ORACLE

Absstract of: US20260080009A1

The disclosed systems and methods provide a novel technical solution via mechanisms for identifying which models are truly high-performing and the set of models that would provide the most accurate single prediction for a signal data signature (SDS). The disclosed systems and methods provides a computerized framework that can document the depictions of individual model performance. Moreover, the disclosed framework can identify all high performing models according to positive results, negative results, as well as generalized results. The framework can additionally operate to combine high performing models into a single predictive oracle to render a final prediction based on input from many models.

METHODS AND SYSTEMS FOR PREDICTING AN ENERGY CONSUMPTION OF A VESSEL

Absstract of: WO2026057401A1

Methods and server systems for predicting energy consumption of a vessel are described herein. The method performed by a server system includes accessing a set of stable vessel operating parameters from a plurality of vessel operating parameters of a vessel, recorded at predefined intervals for the vessel. Herein, the set of stable vessel operating parameters satisfies stability criteria. The method further includes determining a subset of stable vessel operating parameters from the set of stable vessel operating parameters. Herein, each stable vessel operating parameter in the subset of stable vessel operating parameters satisfies a performance threshold. The method further includes generating a set of features based on the subset of stable vessel operating parameters. The method further includes predicting, by a Machine Learning (ML) model, an energy consumption for the vessel based on applying the set of features on the ML model.

SYSTEM AND METHOD FOR GENERATION AND USE OF DATA MODELS FOR DETERMINATION OF INFERRED SKILLS

Absstract of: US20260080325A1

Embodiments described herein are generally directed to computer-based data analytics and the processing of enterprise data, including the generation and use of data models for determining inferred characteristics associated with candidates. In accordance with an embodiment, the system utilizes data-processing pipelines and machine learning models to process structured, semi-structured, and/or unstructured sets of data, received from various sources; generate a multi-dimensional ontology and a taxonomy associated with the characteristics of open positions or potential candidates; identify, based on the data models, one or more additional or inferred characteristics associated with the candidates; and present the output by way of an analytics dashboard, scorecard, or other data visualization.

SYSTEM AND METHOD FOR GENERATION PREDICTION, FAULT DETECTION AND PERFORMANCE ENHANCEMENT OF PHOTOVOLTAIC GENERATING STATION

Nº publicación: WO2026058273A1 19/03/2026

Applicant:

ADANI GREEN ENERGY LTD AGEL [IN]
ADANI GREEN ENERGY LIMITED (AGEL)

Absstract of: WO2026058273A1

The present invention relates to a system and method for predicting photovoltaic (PV) power generation, detecting faults, and enhancing the performance of PV generating stations The system comprises a data collection module (14) that acquires actual data on environmental conditions and PV system performance and transmits sensor data to a cloud platform for analysis, the data analysis module (15) processes data to predict PV power generation, optimize system performance, and identify potential issues, and user interface (16) display system performance, provide accurate understandings, and enable remote monitoring. The system and method utilize advanced machine learning techniques to improve the accuracy of PV power generation predictions, detect faults, and optimize system performance, resulting in increased energy production and reduced operational costs.