Alerta

CLASSIFYING A SOURCE OF A LOGIN ATTEMPT TO A USER ACCOUNT USING MACHINE LEARNING

Resumen de: US20260270271A1

0000 A source of a login attempt to a user account can be classified using machine learning. For example, a computing system can input user activity observations associated with one or more login attempts to one or more user accounts into a trained machine learning model. One or more distinguishing factors for the one or more login attempts can be received from the trained machine learning model. The computing system can determine a source of a current login attempt by applying a clustering algorithm to current values of the one or more distinguishing factors. The current values may be derived from current user activity observations associated with the current login attempt. The computing system can determine an authentication level for the current login attempt to the user account based on the source of the current login attempt.

ESTIMATION MODEL GENERATION METHOD/GENERATION DEVICE FOR ESTIMATING REACTIVE CONDITION, REACTIVE CONDITION PROVIDING METHOD/PROVIDING DEVICE, AND PROGRAM

Resumen de: US20260269023A1

In the present invention, under a condition that acquired information on a plurality of chemical substances as reaction objects and a product is similar to information on a plurality of chemical substances and a product set to a reactive condition, a plurality of the acquired reactive conditions when a plurality of chemical substances as reaction objects are reacted are set from reaction items set to the reactive condition. Furthermore, using an estimation model in which machine learning has been executed with chemical structure information and physical property information of a plurality of chemical substances reacted in the past, reactive conditions in the reactions, chemical structure information and physical property information of produced products, and yields when the reactions are performed under the reactive conditions as training data, the yield is estimated for each of the plurality of reactive conditions, and the reactive condition under which the yield among the estimated yields meets a predetermined condition is displayed (output).

SYSTEMS AND METHODS FOR ANALYZING ARTIFICIAL INTELLIGENCE (AI) MODELS USING EFFECTIVE STATE-SIZE

Resumen de: US20260268213A1

A method for configuring a machine-learning sequence model based on memory utilization of the model, comprising receiving data representing one or more characteristics for the model from the group including: 1) an architecture, 2) an initialization stage, 3) a featurizer, 4) a training process, and 5) a configuration following the training stage of the model, computing a measure of effective state size of the model based on the received data, wherein the measure of effective state size characterizes memory utilization of the model, based on the computed measure of the effective state size, selecting a modification to the model from the group including a modification to: 1) the initialization stage, 2) the featurizer, 3) a loss function of the training stage, 3) a model order, 4) a hybridization, and 5) an architecture, applying the selected modification to the model, and training the model based on the applied modification.

RECONFIGURABLE LOGIC GATE ARRAY, IMAGE SENSOR ASSEMBLY, AND METHOD OF OPERATING

Resumen de: WO2026185211A1

An image sensor assembly includes an image sensor and a logic gate array. The image sensor generates digital image data. The logic gate array includes a plurality of interconnected, reconfigurable logic blocks. Each logic block is arranged to output a binary output signal having a value dependent on at least one input signal of the logic block and on a Boolean function implementable by the logic block. The logic gate array is configurable to generate and output machine learning data based on the digital image data.

FINGERPRINTING AND MACHINE LEARNING FOR PRODUCTION PREDICTIONS

Resumen de: US20260268419A1

A method of hydrocarbon production by obtaining a plurality of samples from a plurality of wells over a period of time, obtaining timelapse production characteristics from each sample, as well as time-lapse fingerprint data. These two datasets are used to train a machine learning model to obtain a predictive model that can be used to optimize and implement a production plan from one or more of the original wells or new wells in the same reservoir.

METHOD FOR TRAINING LARGE LANGUAGE MODEL, METHOD FOR PROCESSING MULTI-MODAL FILE, RELATED APPARATUS AND COMPUTER PROGRAM PRODUCT

Resumen de: WO2026184188A1

Provided in the present disclosure are a method for training a large language model, a method for processing a multi-modal file, an apparatus, an electronic device, a computer-readable storage medium and a computer program product, relating to the technical fields of data processing and artificial intelligence such as intelligent interaction and deep learning. A specific embodiment of the method for training a large language model comprises: reading a sample question and a sample answer for a sample multi-modal file; by means of using the sample multi-modal file, the sample question, the sample answer, and an answer-oriented chain-of-thought prompt as inputs of an initial large language model, using the initial large language model to generate logical reasoning information; and by means of using the sample multi-modal file and the sample question as inputs, and using at least an update result of positive example logical reasoning information as a desired output, updating parameters of the initial large language model. In the embodiment, the "answer" is used as a reference, such that the large language model can be trained in the dimension of the logical reasoning information, thereby improving the training effect on the large language model.

WEARABLE CARDIOVERTER DEFIBRILLATOR CARE SYSTEM WITH HEALTH AND EMOTIONAL COMPANION ACCESSORY

Resumen de: US20260263821A1

0000 A Wearable Cardioverter Defibrillator system supported with a customizable, goal-oriented, companion device. Functionality can be tailored to the goal for a user type. For a patient, the companion device can improve compliance with wear or prescription. Goals can include emotional support, or a specific health, including activity, support. The goal-oriented companion device can receive and process information using machine learning techniques, and interface with a user and other systems and devices.

SYSTEMS AND METHODS FOR ENHANCED USER SPECIFIC PREDICTIONS USING MACHINE LEARNING TECHNIQUES

Resumen de: US20260268166A1

Data sets can be processed using machine learning or artificial intelligence models to generate outputs predictive of a degree to which performing a protocol can positively modify an expected result associated with a condition. Generating the output may include accessing a user data set, inputting the user data set into a trained machine learning model to generate an output, and selecting an incomplete subset of a set of genes based on the output.

METHOD AND SYSTEM FOR AN END-TO-END ARTIFICIAL INTELLIGENCE WORKFLOW

Resumen de: US20260268230A1

0000 In general, certain embodiments of the present disclosure provide methods and systems for enabling a reproducible processing of machine learning models and scalable deployment on a distributed network. The method comprises building a machine learning model; training the machine learning model to produce a plurality of versions of the machine learning model; tracking the plurality of versions of the machine learning model to produce a change facilitator tool; sharing the change facilitator tool to one or more devices such that each device can reproduce the plurality of versions of the machine learning model; and generating a deployable version of the machine learning model through repeated training.

Automated routine platform

Resumen de: US20260267688A1

0000 Embodiments include systems and methods for automated routine generation and execution. In some embodiments, the method includes receiving a request to automate a target workflow; retrieving at least one document relevant to the target workflow from a knowledge base; generating a plurality of candidate routines based on the at least one document using a first machine learning model; generating an aggregate routine based on the plurality of candidate routines, the aggregate routine comprising instructions for automatically implementing the target workflow; mapping at least one step of the aggregate routine to at least one function configured to provide external functionality to a second machine learning model; and executing the aggregate routine using the second machine learning model, the step of executing the aggregate routine including calling the at least one function

ARTIFICIAL INTELLIGENCE DRIVEN SYSTEMS OF SYSTEMS FOR CONVERGED TECHNOLOGY STACKS

Resumen de: AU2025212532A1

An artificial intelligence driven system of systems may include a layered architecture for providing transaction support to various types of enterprises. A governance layer implements automated governance and policy enforcement through specialized governance modules utilizing generative AI technology. An enterprise layer supports enterprise functions by integrating management and control platforms with digital infrastructure. An offering layer creates and manages system offerings via content generation, personalization, and smart product modules. A transactions layer enables automated transaction orchestration through API integration, execution, and fulfillment modules. An operations layer manages AI systems through generation, training, verification and orchestration modules. A network layer provides adaptive networking capabilities through routing, protocol selection and communication modules. A data layer processes fused data from multiple sources using machine learning and AI systems. A resource layer manages computing, storage, and other resources through specialized resource modules.

COMPUTER-READABLE RECORDING MEDIUM HAVING STORED THEREIN INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE

Resumen de: US20260269012A1

A non-transitory computer-readable recording medium having stored therein an information processing program causes a computer to execute a process including: determining a weight of an input feature in a regression model, the regression model predicting an amino-acid sequence of a virus after mutation using an amino-acid sequence of the virus as the input feature, the determining being based on a first feature related to a three-dimensional (3D) structure of a protein of the virus and a second feature related to a contribution to prediction of a machine learning model, the contribution being obtained based on the first feature.

REDUCING RESOURCE UTILIZATION IN MACHINE LEARNING MODEL PROCESSING

Resumen de: US20260268164A1

0000 Reducing resource utilization in machine learning model processing, including: receiving a first query for machine learning model processing; receiving a response to the first query, wherein the response comprises an output from a particular machine learning model that processed the first query; determining, via natural language processing performed via a computer, that the first query includes a time-relative expression; storing a cache entry comprising the response to the first query and a time-to-live; receiving, at a time within the time-to-live, a second query for machine learning model processing; semantically analyzing the second query to determine that the second query has a similarity to the first query that exceeds a threshold value; retrieving the response from the cache entry; and transmitting the retrieved response to be an answer to the second query.

Dynamic Runtime Scoring and Selection of Machine Learning Models

Resumen de: US20260267773A1

0000 A method includes obtaining input data using a client device, and determining a plurality of attribute values, where the attribute values are associated with processing the input data using a client-side machine learning model and a server-side machine learning model. The method also includes determining, for each respective machine learning model of the client-side machine learning model and the server-side machine learning model, a corresponding capability value based on the plurality of attribute values. The corresponding capability value may represent a capability of the respective machine learning model for processing the input data under conditions represented by the plurality of attribute values. The method further includes selecting, from the client-side machine learning model and the server-side machine learning model and based on the corresponding capability values thereof, a preferred machine learning model for processing the input data, and providing the input data to the preferred machine learning model.

BIOLOGICAL AGENT AEROSOL CLASSIFICATION/IDENTIFICATION USING MACHINE LEARNING ALGORITHMS

Resumen de: US20260269022A1

In accordance with various embodiments, a system and a method for identifying a particle as a bioactive stimulant are provided. The system includes a processor configured to execute machine-readable instructions borne by a non-transitory computer-readable memory device to cause the processor to process one or more steps of the method disclosed herein. The system/method include the steps to: receive a dataset comprising scattered light signals and/or fluorescent light signals of the particle; analyze the dataset using one or more machine learning models, wherein the one or more machine learning models is trained using elastic scattering light intensity data and fluorescent light intensity data of a library of biological molecules; generate a probability score that the particle is bioactive based on the analysis of the dataset; determine, via classification of the probability score, that the particle is bioactive; and/or output a result indicating that the particle is the bioactive stimulant.

MATHEMATICAL MODEL OBTAINING METHOD AND RELATED DEVICE, AND OPERATIONS OPTIMIZATION METHOD

Resumen de: US20260268185A1

0000 A mathematical model obtaining method and device, and an operations optimization method are provided. In the method, an artificial intelligence technology may be used to obtain a mathematical model corresponding to an operations optimization problem. The method includes: outputting at least one problem, and obtaining an answer to each problem, where the answer to each problem is for obtaining first description information, the first description information is description information for describing the operations optimization problem, and a first problem is a problem for obtaining the description information of the operations optimization problem; and obtaining first information based on the first description information, and inputting the first information into a machine learning model, to obtain a mathematical model, where the mathematical model is for solving the operations optimization problem, and the mathematical model includes an objective function and a constraint.

Distributed System for Identifying the Appropriate Heart Valve Implant Using an Ensemble Machine-Learning Algorithm, Synthetic Data, and Edge Computing

Resumen de: US20260269081A1

0000 A system and method for and method for selecting an implantable heart valve for patients using is disclosed. The system includes analyzing population-level environmental exposure data to categorize geographic locations by cardiovascular risk. A synthetic clinical dataset is generated using a generative adversarial network along with predefined machine-learning parameters. The user device calculates an exposomic feature value by weighting pollutant concentrations based on residence durations. The user device is then trained using a machine-learning model, selected from random forest models, gradient-boosted decision tree models, support vector machines, artificial neural networks, and elastic net regression. After training, the model is executed on the user device using an edge computing approach with patient-specific data and exposomic feature values to generate heart valve intervention options that minimize the difference between the predicted remaining lifespan of the patient and the valve's operational lifespan while reducing the risk of failure or complications.

SYSTEM AND METHOD FOR DIAGNOSING AND MONITORING HEMATOPOIETIC NEOPLASMS USING DEEP LEARNING

Resumen de: WO2026187696A1

A system includes one or more processors. The one or more processors can acquire images of peripheral blood smears; can detect and isolate, for each of the one or more images using a first machine learning (ML) model, one or more target cell locations; can determine, for each of the one or more target cell locations using the first ML model, a confidence level associated with the target cell location; can generate, for each of the one or more target cell locations using a second ML model, a cell type classification based at least on the target cell location and the confidence level associated with the target cell location to obtain a plurality of cell type classifications; can generate a diagnosis based on the one or more cell type classifications; and can output the diagnosis.

MACHINE LEARNING SYSTEMS TO CONDUCT INMATE ASSESSMENT INTERVIEWS

Resumen de: US20260268891A1

Systems and methods for automatically conducting an assessment interview to predict risks an individual poses to self and others by executing an interview conducting machine-learning model using as input interviewee responses and interview guidance to generate interviewer questions and responses, the interview guidance including guidelines for assessing individuals for risks to themselves and others, and generating an interview transcript including the interviewer questions, the interviewee responses, and the interviewer responses, automatically generating assessment inputs based on the assessment interview by, generating, based on the interviewee responses, assessment inputs, and providing the assessment inputs as input to an analysis engine to generate an assessment of the individual, the assessment reflecting a prediction of risks the individual poses to self and others, automatically generating a report on the assessment by generating, based on the interview transcript and sensor data collected during the assessment interview, a confidence score for the assessment.

SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR PROVIDING ACCESS TO A MACHINE-LEARNING MODEL

Resumen de: WO2026187721A1

Provided are systems, methods, and computer program products for providing access to a machine-learning model. A system includes at least one processor configured to display a graphical user interface in a word processing application, the graphical user interface comprising at least a subset of prompts, receive a selection of a prompt from the subset of prompts from a user, execute the prompt, resulting in a model output, modify a textual document being displayed in the word processing application based on the model output, modify the prompt based on input from the user, resulting in a modified prompt, execute the modified prompt, resulting in a second model output, and store the modified prompt in the data storage device.

RETROACTIVE PREDICTION FRAMEWORK FOR SEQUENTIAL MESSAGE FILTERING AND RESOURCE OPTIMIZATION

Resumen de: US20260268147A1

0000 Various embodiments of the present disclosure provide retroactive prediction frameworks for sequentially filtering messages to optimize network efficiency and processing resource utilization in a complex prediction domain. The techniques may leverage a pre-filtering rule set to identify a set of candidate data objects from an object data store. The set of candidate data objects may be augmented with a plurality of composite recovery scores generated by a machine learning prioritization model and then filtered and ranked to create a prioritized ranking data structure. The prioritized ranking data structure may be leveraged to selectively provide verification requests to a remote verification platform.

MONITORING CHAIN-OF-THOUGHT IN REASONING MODELS TO MITIGATE REWARD HACKING

Resumen de: US20260268214A1

0000 Systems and techniques are described herein for monitoring machine learning models for misbehavior. For example, an apparatus comprising one or more processors and configured to: provide, to a first machine learning model, an inner monologue from a second machine learning model associated with a user task, wherein the user task comprises natural language text; and obtain, from the first machine learning model, information indicative of misbehavior within the inner monologue. In some aspects, misbehavior is blocked during inference (e.g., runtime) and reward hacking behavior is penalized during training. Non-limiting examples of misbehavior include reward hacking, misgeneralization, sycophancy, or deception.

AGENTIC ARTIFICIAL INTELLIGENCE-BASED INPUT AUGMENTATION

Resumen de: US20260267868A1

In some examples, input is provided to a first input augmentation sub-agent of a multi-agent system and input augmentation data is received from the first input augmentation sub-agent. The input augmentation data includes an aggregation of query results generated by an execution of a query on a dataset. The query is formulated by a generative machine learning model (GMLM) in response to a code generation instruction. The code generation instruction is formulated by the first input augmentation sub-agent in response to the input. The aggregation of query results is formulated by the GMLM in response to the execution of the query. A learning including a machine learning-based representation of the input and the input augmentation data is generated. The learning is used to determine a non-explicit user preference. The non-explicit user preference is used to control execution of a task according to the non-explicit user preference.

METHODS AND SYSTEMS OF PROGNOSTIC MODELS THAT CAN PERFORM STOCHASTIC TIME-SERIES FORECASTING

Resumen de: WO2026188052A1

A method to predict covariates related to progression of a disease includes receiving, for a study participant, baseline sample data corresponding to a baseline set of prognostic covariates, and predicting, via a first machine learning model based on the baseline sample data, first predicted sample data for each of a first set of prognostic covariates for a first time period for the study participant. At least one covariate of the first set of prognostic covariates is non-overlapping with any prognostic covariate of the baseline set of prognostic covariates. The method further includes predicting, via a second machine learning model based on the baseline sample data, second predicted sample data for each of a second set of prognostic covariates for a second time period. At least one covariate of the second set of prognostic covariates is non-overlapping with any covariate of the first set of prognostic covariates.

INFORMATION PROCESSING APPARATUS

Nº publicación: US20260268181A1 10/09/2026

Solicitante:

NEC CORP [JP]
NEC Corporation

Resumen de: US20260268181A1

An information processing apparatus according to the present disclosure includes an acquisition unit that acquires a set of models that predict objective variables at certain different periods ahead from an explanatory variable and a selection unit that selects a group of the models, based on a change in each predicted value using each of the models from a predetermined explanatory variable, in the group of the models respectively related to the certain periods ahead. This enables smooth forecasts generated by machine learning to support reliable decision making.