Alerta

Network Packet Capture Analysis Using Machine Learning Model

Resumen de: US20260197254A1

0000 Embodiments relate to analyzing network packets in a telecommunication networks using machine learning models. The network packets are correlated and then labeled to indicate successes or failures in a subtask of communication flow. Features are extracted based on the labels and correlated network packets. The extracted features are applied to a machine learning model to predict or infer success or failure of the entire communication flow. The result from the machine learning model may again be applied to subsequent machine learning models to predict root cause of a failure or to predict or infer the type of success. In this way, more accurate diagnosis of network issues in the telecommunication networks may be made in a more expedient manner.

DATA DIGITIZATION VIA CUSTOM INTEGRATED MACHINE LEARNING ENSEMBLES

Resumen de: US20260195338A1

0000 Data digitization via custom integrated machine learning ensembles is provided. For example, a system integrates multiple trained machine learning ensembles to identify, extract, and map data. The system receives a data set from sources. The system identifies ensembles can include machine learning models that can determine an outcome. The system filters a subset of data from the data set. The system identifies a layout for the data set based on a vendor type, data type, and the data set. The system executes a block detection module to identify blocks of the layout. The system executes a header detection module. The system executes a policy detection module to identify the headers as policies. The system transforms, based on the headers, the layout, the blocks, and the policies, the data set into a second file type, and presents the transformed data set for integration into a capital management system.

A SYSTEM FOR PROCESSING, ANALYZING, AND CLASSIFYING GRAPH DATA IN MACHINE LEARNING AND DATA SCIENCE

Resumen de: WO2026147368A1

The invention relates to a system for processing, analyzing, and classifying graph data in the fields of machine learning and data science, and an operation method of said system.

GENERATING DATA BRIEFS USING GENERATIVE MACHINE LEARNING MODELS

Resumen de: US20260195356A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using a generative machine learning model to generate a data brief that characterizes the contents of a data store. In one aspect, a method comprises determining a user category of a user; generating a data brief that characterizes content from one or more data stores using a generative machine learning model by determining a prompt for the generative machine learning model based on the user category of the user, processing (i) the prompt and (ii) at least a subset of data stored in the data stores using the generative machine learning model to generate a model output in response the prompt, and including the generated model output in the data brief; and providing, to the user and by way of the user interface, a representation of the data brief generated using the generative machine learning model.

MACHINE-LEARNING SYSTEM FOR CONTRACT INTELLIGENCE AUTOMATION USING CONTRACT DIGITIZATION INTO MACHINE PARSEABLE OBJECTS AND METHOD THEREOF

Resumen de: WO2026145883A1

Proposed is a novel machine learning system (1) for contract intelligence automation, and corresponding method for training the machine learning system for automated text analysis and for applying it. A plurality of contracts (2) with a plurality of clauses (22) is received by the system (1), wherein wordings of equivalent clauses (22) vary across contracts (2); contract text (21) is read into a data processing system (15); clause text chunks (121) are identified, that are equivalent across contracts (2), and assigned a contract term category (122). Considering a respective semantic context (131) of each of the contracts (2), a semantic meaning (132) of each of the clause text chunks (121) is determined and encoded in a clause embedding space (141) and stored in vector database (14); data automation tasks can be performed using entries of the vector database (14), particularly automatic consistency monitoring (197) and outlier detection across contracts (2) and a monitoring of clause (22) nuances across contracts (2) e.g. via a graphical representation (16).

DIFFERENTIALLY PRIVATE FEDERATED EXTREME GRADIENT BOOSTING

Resumen de: US20260195639A1

Training a differential privacy-aware (DP-aware) machine learning model includes transmitting epsilon hyperparameters to federated learning (FL) nodes. A differential privacy-aware (DP-aware) machine learning model is generated based on noise-infused surrogate histograms received from the FL nodes, each noise-infused surrogate histogram based on an epsilon hyperparameter and representing a node-specific dataset. The DP-aware machine learning model is transmitted to the FL nodes. A DP-aware aggregate histogram is generated by merging DP-aware gradients and DP-aware Hessians determined by the FL nodes based on each FL node generating predictions by applying the DP-aware machine learning model to a node-specific dataset therein. A decision tree of the DP-aware machine learning model is expanded by dividing data in one or more decision tree nodes. The machine learning model is iteratively trained by successively merging further DP-aware gradients and DP-aware Hessians generated by FL nodes based on updated versions of the DP-aware machine learning model.

Federated Learning applications for secure and private Machine Learning in Oil and Gas Industry

Resumen de: US20260195608A1

0000 Techniques for training a global model for use at a host of oilfield application sites based on raw data obtained from the application sites without direct exposure of the data to the global model. The techniques include developing and distributing a global model with a predetermined set of parameter weights. The model is then locally employed at each application site by a local computer which maintains the integrity of the acquired data during performance of the oilfield application. The data is used to update the parameter weights based on real-time circumstances. Thus, the parameter weights may be transmitted to the centralized computer for updating of the global model. Further, the updated global model may continue to direct other applications and the process continued in a beneficial feedback loop manner.

DEEP LEARNING-BASED PATH PLANNING METHOD CONSIDERING HULL STABILITY OF UNMANNED SURFACE VEHICLE IN RESPONSE TO MARITIME ENVIRONMENT AND DEVICE THEREFOR

Resumen de: KR20260108793A

본 발명의 다양한 실시예에 따르면, 무인수상정의 선체 안정성을 고려한 딥러닝 기반 경로계획 장치는 상기 무인수상정의 내부에 위치한 센서 또는 외부로부터 상기 무인수상정의 상태 정보 또는 해상 환경 정보를 입력받고, 무인수상정의 상태 정보 또는 해상 환경 정보를 입력받아 무인수상정 롤(Roll) 정보를 출력하도록 미리 학습된 무인수상정 전복 위험도 예측 모델에 상기 입력받은 무인수상정의 상태 정보 또는 해상 환경 정보를 입력하고, 상기 무인수상정 전복 위험도 예측 모델로부터 출력된 상기 무인수상정 롤 정보를 미리 정의된 휴리스틱(heuristic) 함수에 적용하고, 상기 휴리스틱 함수 값을 기반으로 상기 무인수상정의 이동 경로를 결정할 수 있다.

System, Method, and Computer Program Product for Early Detection of a Merchant Data Breach Through Machine-Learning Analysis

Resumen de: US20260195760A1

Provided are systems, methods, and computer program products for early detection of a merchant data breach through machine-learning analysis. An example system includes a processor configured to receive transaction authorization request data. The processor is also configured to generate a metric based on security-testing transaction activity. The processor is further configured to generate features for training one or more models. The processor is further configured to generate a first dataset based on the features and associated with a plurality of merchants, and a second dataset based on the features and associated with a previously breached merchant. The processor is further configured to train an ensembled model to associate merchants with a likelihood of data breach. The processor is further configured to determine a breached merchant, automatically freeze a transaction, retrain the ensembled model, and determine another breached merchant based on the updated models.

METHOD FOR SCHEDULING PEER DEMANDS IN A CONSENSUS PROCESS FOR A BLOCKCHAIN

Resumen de: WO2026146097A1

The collected information is distributed (306) between input data and output data with a view to training (308) a machine learning model in order to obtain predictions identifying which peers are most likely to transmit missing blocks and at what time. The machine learning model thus trained enables each peer to determine a scheduling of demands made by said peer on the other peers in the consensus process for the elaboration of the blockchain, according to the predictions obtained. The consensus process is therefore more efficient.

Forward-Forward Training for Machine Learning

Resumen de: US20260195643A1

0000 Example implementations provide a computer-implemented method for training a machine-learned model, the method comprising: processing, using a layer of the machine-learned model, positive input data in a first forward pass; updating one or more weights of the layer to adjust, in a first direction, a goodness metric of the layer for the first forward pass; processing, using the layer, negative input data in a second forward pass; and updating the one or more weights to adjust, in a second direction, the goodness metric of the layer for the second forward pass.

METHOD AND SYSTEM FOR PREDICTING ABDOMINAL AORTIC ANEURYSM (AAA) GROWTH

Resumen de: US20260196354A1

0000 There are provided methods, systems and non-transitory storage mediums for predicting growth of an abdominal aortic aneurysm (AAA) of a patient having been diagnosed with AAA. Segmented regions of interest (ROI) comprising the aorta and adjacent structures are received by segmenting a set of images. A wall shear stress parameter and intraluminal thickness parameter is determined. A 3D parametric mesh comprising a plurality of concentric 3D mesh layers is generated, where each concentric 3D mesh layer includes a same predetermined number of nodes. The generation includes encoding the segmented ROIs, the wall shear stress parameter and the intraluminal thickness parameter as features at respective node locations in the 3D parametric mesh. A trained growth prediction machine learning model predicts, based at least on a subset of features of the 3D parametric mesh, if the given patient will show AAA growth. The training of the growth prediction model is also disclosed.

A SELF-ADAPTIVE FAULT CORRELATION SYSTEM BASED ON CAUSALITY MATRICES AND MACHINE LEARNING

Resumen de: US20260195611A1

The present invention describes a self-adaptive system capable of extracting correlations between multiple faults from net-work topologies, with the innovative component being the data preprocessing phase generating causality matrices to provide as an input to ML models. The proposed fault correlation system is responsible for, without any configuration, identifying the hierarchical relationships be-tween the multiple alarms, allowing for a better understanding of the causality and impact of each malfunction, hence assisting the implementation of RCA rules. This allows, not only for a huge dimensionality reduction of alarms needed to be processed by a TO's, but also significantly increases the knowledge about the topology, thus reducing downtime and increasing the quality of service of the network and services.

PARAMETER TUNING METHOD AND APPARATUS, AND DEVICE

Resumen de: US20260195119A1

0000 This application provides example parameter tuning methods. In one example method, a high-dimensional parameter space is divided based on one or more groups of software configuration parameters that are configured for software and corresponding software performance parameters, to form M high-dimensional parameter subspaces, where the M high-dimensional parameter subspaces satisfy: a similarity between data in any one of the high-dimensional parameter subspaces is greater than a similarity threshold, and a difference between amounts of data included in any two of the high-dimensional parameter subspaces is not greater than an amount threshold. M machine learning models are invoked to learn the M high-dimensional parameter subspaces. A target high-dimensional parameter subspace is selected from the M high-dimensional parameter subspaces, and a to-be-configured software configuration parameter is determined by using a machine learning model corresponding to the target high-dimensional parameter subspace.

CONTROL VARIABLE OPTIMIZATION METHOD, BIORESOURCE PRODUCTION METHOD, AND BIORESOURCE PRODUCTION SYSTEM

Resumen de: EP4773049A1

0001 Provided are a control variable optimization method capable of determining improved culture conditions using a predictive model based on machine learning, and a bioresource production method and a bioresource production system using the same. 0002 A bioresource production system S according to another aspect of the present invention includes: a cultivation system B for performing bioresource production; and a control variable optimization system A for optimizing control variables obtained from the cultivation system. 0003 The control variable optimization system separates the control variables into initial variables and manipulated variables, creates predictive models adapted to the initial variables and the manipulated variables, respectively, and optimizes the control variables by combining the predictive models.

MACHINE LEARNING MODEL POSITIONING PERFORMANCE MONITORING AND REPORTING

Resumen de: EP4773657A2

0001 Disclosed are techniques for wireless communication. In an aspect, a network entity receives a provide location information message from a user equipment (UE), the provide location information message including one or more positioning estimates derived by the UE during one or more positioning inference occasions of a machine learning model, wherein the machine learning model is applied to one or more measurements of a wireless channel between the UE and a network node during each of the one or more positioning inference occasions, and transmits a performance report indicating a performance of the machine learning model at least in deriving the one or more positioning estimates during the one or more positioning inference occasions.

SPATIOTEMPORAL TRANSFER MACHINE LEARNING

Resumen de: WO2025046310A1

A computer-implemented, machine learning method for spatiotemporal transfer learning. Sectors of an area are aggregated using preprocessed data from one or more data sources. The sectors are clustered based on different representations obtained for each context feature associated with each of the sectors. One or more context features that have a higher impact on a target feature to be predicted than other context features are identified from a plurality of context features and aggregated to obtain a representation of the area. Using the representation of the area, a particular sector within each of the clustered sectors is selected based on similarity to a respective centroid of the cluster to generate a set of particular sectors. A model associated with a source sector of the set of particular sectors is trained. The method has applications including, but not limited to smart cities, public safety and energy optimization.

OPTIMIZING LEGACY PROTOCOLS FOR INTERNET OF THINGS DEVICES

Resumen de: US20260189633A1

A computer-implemented method for managing Internet of Things (IoT) protocols. A processor set continuously monitoring a number of IoT devices to collect a set of data from the number of IoT devices. The processor set trains a number of machine learning models using the set of data as training data. The processor set performs predictive analysis using the number of machine learning models to determine state of each protocol for the number of IoT devices based on real-time data from the set of data. The processor set identifies a number of legacy protocols from the protocols for the number of IoT devices based on the states of protocols for the number of IoT devices using the number of machine learning models. The processor set migrates the number of legacy protocols to a number of new protocols to optimize performance for the number of IoT devices.

SYSTEM AND METHOD FOR EXTRACTING HIDDEN CUES IN INTERACTIVE COMMUNICATIONS

Resumen de: US20260188340A1

Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process interactive communications between at least two participants. Speech and text, within the interactive communications, are analyzed using machine learning classifiers to extract prosodic, semantic and key phrase cues located within the interactive communications to identify changes to emotion, sentiments and key phrases. A summary of the interactive communications between a first participant and a second participant is generated at least, in-part, based on the extracted prosodic, semantic and key phrase cues and the summary is highlighted based on any of the changes to emotion, the sentiments or the key phrases.

Artificial Intelligence System Having a Prediction Engine for Determining Predicted Metrics

Resumen de: US20260187525A1

Implementations include obtaining, from a database, a first set of data associated with an entity and generating, by a model generator, a machine learning model based on the first set of data. Implementations may include generating a predictive model by training the machine learning model using at least a portion of the first set of data. The predictive model may be used to determine, based on a second set of data, a predicted metric associated with a revenue cycle corresponding to the entity. Implementations may include outputting prediction data indicative of the predicted metric.

Systems and Methods for Identifying Causes of Elevated Liver Enzymes in Dogs

Resumen de: US20260188493A1

A method for identifying a cause of elevated liver enzymes includes receiving new patient data, receiving a machine-learning based diagnostic model and a knowledge based diagnostic model, determining whether the machine-learning based diagnostic model indicates a cause of elevated liver enzymes for the new patient data, and in a case where the machine-learning based diagnostic model indicates the cause of elevated liver enzymes for the new patient data, assessing the cause of elevated liver enzymes using the knowledge based diagnostic model.

METHOD FOR ESTIMATING A REMAINING USEFUL LIFE OF A BATTERY, NON-TRANSITORY COMPUTER-READABLE MEDIUM, AND ELECTRONIC ESTIMATION DEVICE

Resumen de: WO2026137061A1

The method (200) comprises extracting (210) a set of selected features from at least one charge-discharge cycle (C) of a battery and estimating (230) the remaining useful life of the battery (1) by applying a machine learning model (140) to the set of selected features. The machine learning model (140) is trained during a preliminary phase (100), comprising: extracting (110) a set of primary features from the charge-discharge cycles (C) of reference batteries; processing (120) the set of primary features by applying an outlier detection process (25) and/or a data smoothing process to a primary feature (F) versus charge-discharge cycles (C) curve (F(C)A); selecting (130) the features from among the processed primary features using correlation between the set of primary features and the remaining useful lives of the reference batteries; and training the machine learning model (140) with a training set of the selected features extracted from multiple charge-discharge cycles (C) of the reference batteries.

TRAINING A LANGUAGE MODEL FOR DOMAIN-SPECIFIC QUERIES

Resumen de: US20260187167A1

A large language model (LLM) is trained to provide domain specific answers. First, item information is extracted from a catalog of items. A machine-learning model is then prompted to generate a set of queries based in part on the item information associated with the items. Training examples are generated that are associated with the items using a first subset of queries from the set. Each training example is for a corresponding item, and includes a query (that is associated with the corresponding item and is from the first subset) and some item information that is an answer to the query and that is associated with the corresponding item. The LLM is trained using the training examples. Performance of the LLM is evaluated using a second subset of the set of queries that is separate from the first subset.

SYSTEMS AND METHODS WITH ENSEMBLE WORD EMBEDDING AND TABULAR FEATURE DATASET FOR IMPROVED CONDITION MODEL PERFORMANCE

Resumen de: US20260188447A1

Text data describing a patient's visit to a healthcare facility is extracted from a document and processed to remove stop words. Then, words associated with a medical condition can be determined and filtered to remove fully documented phrases that describe the medical condition. The filtered words are cleansed, ordered, and used to generate a final data set, which is used to train a first machine learning model to produce a numerical value that indicates a likelihood that the patient's visit to the healthcare facility is related to the medical condition. Features particular to the medical condition have feature attributes derived from historical data including medications, services, and observations pertaining to the medical condition. A data structure containing the numerical value, the features, and the feature attributes is input to a second machine learning model for generating a patient-specific score as evidence of the medical condition found during the patient's visit.

ELECTRONIC SUBMISSION OF DOCUMENTS TO ENTITIES BASED ON MACHINE LEARNING

Nº publicación: US20260187158A1 02/07/2026

Solicitante:

IBM [US]
International Business Machines Corporation

Resumen de: US20260187158A1

0000 According to an embodiment of the present invention, a computer system comprises a processor set, one or more computer-readable storage media, and program instructions stored on the one or more computer-readable storage media to cause the processor set to perform operations. The system analyzes a document to obtain parameters including an area of research in the document and metrics for quality of the document. A document influence score of the document is determined based on the parameters. An author influence score is determined based on a quantity of citations to an author of the document. An entity is selected for submission of the document based on the document influence score and the author influence score. The document is electronically submitted to the selected entity. Embodiments of the present invention further include a method and computer program product for electronically submitting a document in substantially the same manner described above.