Ministerio de Industria, Turismo y Comercio LogoMinisterior
 

Alerta

Resultados 122 results.
LastUpdate Updated on 22/11/2026 [07:07:00]
pdfxls
Solicitudes publicadas en los últimos 30 días / Applications published in the last 30 days
previousPage Results 75 to 100 of 122 nextPage  

SYSTEMS AND METHODS FOR MACHINE LEARNING MODEL DEVELOPMENT

Publication No.:  US20260340479A1 29/10/2026
Applicant: 
CAPITAL ONE SERVICES LLC [US]
Capital One Services, LLC
US_20260340479_A1

Absstract of: US20260340479A1

0000 Methods and systems for machine learning (ML) development are disclosed. A method includes determining, by a data exploration module, at least one quality metric of a data set using at least one statistical test and/or visualization. A data processing module processes the data set based on the at least one quality metric for use by a ML model. A feature selection module determines at least one critical feature from the processed data set for building the ML model. A model selection module selects the ML model from a plurality of ML models based on the processed data set and the at least one critical feature. A model monitoring module monitors the ML model, where the monitoring includes determining whether an output of the ML model exceeds a defined threshold.

GENERATING NODE-SPECIFIC MACHINE LEARNING MODELS BY SELECTIVE CLUSTERING OF COLLECTED DATASETS

Publication No.:  US20260340080A1 29/10/2026
Applicant: 
DELL PRODUCTS LP [US]
Dell Products L.P.
US_20260340080_A1

Absstract of: US20260340080A1

0000 The technologies described herein are generally directed to generating node-specific machine learning models by selective clustering of collected datasets. For instance, a method can, based on a first metric value of a metric of network activity data of a first distributed node of network nodes of a network, and a second metric value of the metric of the network activity data of a second distributed node, identifying a clustering criterion applicable to cluster respective network activity data of the network nodes. The method may further include, based on the clustering criterion, clustering the respective network activity data, with the clustering criterion being selected from candidate clustering criteria based on at least one selection criterion. The method may further include, communicating to a machine learning training node, a training dataset applicable to train a machine learning model, with the training dataset being generated based on the clustered network activity data.

METHOD AND SYSTEM FOR AUTOMATICALLY INTEGRATING AN EXTERNAL MACHINE LEARNING MODEL INTO A TARGET COMPUTING ENVIRONMENT

Publication No.:  US20260340496A1 29/10/2026
Applicant: 
LTI MINDTREE LTD [IN]
LTI Mindtree Ltd
US_20260340496_A1

Absstract of: US20260340496A1

0000 A method and system for automatically integrating an external machine learning (ML) model into a target computing environment is disclosed. The system verifies the integrity of the external ML model based on model documentation using a dual-layer security verification including cryptographic validation and documentation compliance analysis. Feature requirements are extracted from the model documentation using NLP and features required by the external ML model are mapped to available data in the target computing environment using a multi-tiered mapping strategy. The system identifies missing features through comparison of model requirements and available data and generates executable code to create the identified missing features. The external ML model is then executed using the mapped and created features, and outputs from the external ML model are processed using a multi-layer approach.

MACHINE LEARNING MODEL DYNAMIC QUERY CLASSIFICATION AND CUSTOMIZED RESPONSE GENERATION

Publication No.:  US20260339960A1 29/10/2026
Applicant: 
INTUIT INC [US]
INTUIT INC.
US_20260339960_A1

Absstract of: US20260339960A1

0000 Techniques for dynamic query classification and customized response generation using machine learning models. Embodiments include determining a user intent based on an input query and one or more attributes associated with the input query. Embodiments include classifying the user intent according to one or more categories, retrieving, based on the user intent and the classifying, one or more software tools, and generating a prompt based on the classifying and the retrieving. Embodiments include providing, to a model, the prompt and an indication of the one or more software tools. Embodiments include selecting, based on an output from the model in response to the prompt and the indication, a particular software tool and executing the particular software tool. Embodiments include providing an output based on the executing, receiving feedback with respect to the output via a user interface, and performing an action based on the feedback.

DETERMINING OPTIMAL HYPERPARAMETER VALUES TO CONFIGURE A MACHINE LEARNING MODEL

Publication No.:  US20260340481A1 29/10/2026
Applicant: 
IBM [US]
INTERNATIONAL BUSINESS MACHINES CORPORATION
US_20260340481_A1

Absstract of: US20260340481A1

0000 Provided are a computer implemented method, system and computer program product for determining optimal hyperparameter values to configure a machine learning model. Model instances comprise the model configured with different sets of hyperparameter values for hyperparameters. The hyperparameter values define a structure of the model instances that control how the model instances operating during training. The model instances are trained with the different sets of hyperparameter values. The model instances run after training with a data set to determine prediction errors for the trained model instances. The model instances are ranked according to the prediction errors for the model instances in a prediction matrix. Hyperparameter values are selected based on the prediction errors in the prediction matrix for the model instances. The selected hyperparameter values are used to configure the model for training.

ANOMALY DETECTION USING AN ENSEMBLE OF PROCESSOR-BASED MACHINE LEARNING MODELS

Publication No.:  US20260340516A1 29/10/2026
Applicant: 
DELL PRODUCTS LP [US]
Dell Products L.P.
US_20260340516_A1

Absstract of: US20260340516A1

Techniques are provided for anomaly detection using an ensemble of processor-based machine learning (ML) models. One method comprises obtaining feature values related to a given event; obtaining multiple ML models, wherein the ML models (i) are associated with corresponding predictive scores determined prior to an occurrence of the given event and (ii) have respective distinct ML model structures; applying the feature values to the ML models to obtain corresponding probability values; determining one or more weighted values for a set of behavior classes using the probability values and the predictive scores; and initiating processing steps based on at least one of the one or more weighted values. A predicted behavior class may be determined for the given event by comparing the one or more weighted values to at least one reliability threshold.

SYSTEM AND METHOD FOR AUTOMATED ICE HOCKEY STICK AND SKATE FITTING USING EMBEDDED SENSORS AND MACHINE LEARNING ALGORITHMS

Publication No.:  WO2026226993A1 29/10/2026
Applicant: 
TENSORHAUS LLC [US]
TENSORHAUS LLC
WO_2026226993_A1

Absstract of: WO2026226993A1

A method for generating a player-specific stick includes receiving, from a plurality of sensors, a plurality of data streams associated with motion of a user, the plurality of sensors including at least two inertial measurement units (IMUs), the at least two IMUs coupled to at least one of the user or equipment associated with the user. The method includes synchronizing the plurality of data streams across the plurality of sensors to define synchronized data. The method includes extracting, from the synchronized data, user-specific features. The method includes training, based on the user-specific features, a machine-learning model to define a user-specific machine learning model. The method includes generating, using the user-specific machine learning model, at least one stick parameter, the at least one stick parameter associated with fabricating a stick and validating, based on one or more validation criterion, the at least one stick parameter to define a validated fabrication model.

INTEGRITY DETERMINATION VIA ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING FOR POSITIONING PROCEDURES

Publication No.:  WO2026226369A1 29/10/2026
Applicant: 
QUALCOMM INCORPORATED [US]
QUALCOMM INCORPORATED
WO_2026226369_A1

Absstract of: WO2026226369A1

Integrity determination via artificial intelligence or machine learning (AI/ML) for positioning procedures. A wireless device obtains (1705), from a network entity, an integrity parameter related to a positioning procedure, and obtains (1710) positioning information related to the positioning procedure. The wireless device outputs (1715), to the network entity, one or more integrity indicators, where the one or more integrity indicators may be determined via an AI/ML model based on the positioning information and the integrity parameter that are input to the AI/ML model. A network entity obtains positioning information related to a positioning procedure, and determines one or more integrity indicators associated with the positioning procedure via an AI/ML model based on the positioning information and an integrity parameter that are input to the AI/ML model.

MACHINE LEARNING MODEL PERFORMANCE MONITORING AND ADJUSTMENT USING DYNAMIC MODEL-BASED PERFORMANCE CRITERIA

Publication No.:  US20260340492A1 29/10/2026
Applicant: 
FMR LLC [US]
FMR LLC
US_20260340492_A1

Absstract of: US20260340492A1

0000 Methods and apparatuses for machine learning (ML) model performance monitoring and adjustment using dynamic model-based performance criteria include executing an ML model in monitoring runs over a first time period, generating a first subset of the performance data comprising data for each monitoring run that is outside of a static performance threshold range and a second subset of the performance data comprising data for the remaining monitoring runs, calculating a dynamic threshold based upon the second subset of data, setting a performance alert value when a difference between the performance metric and a baseline value exceeds the dynamic threshold, generating a performance anomaly alert based upon a number of monitoring runs in the first subset of data and a number of monitoring runs in the second subset of data that have an alert value set, and adjusting hyperparameters, the static performance threshold range, or a baseline job execution schedule.

SYSTEMS AND METHODS FOR EFFICIENT DATA SAMPLING FOR MACHINE-LEARNING APPLICATIONS

Publication No.:  US20260340426A1 29/10/2026
Applicant: 
JPMORGAN CHASE BANK NA [US]
JPMORGAN CHASE BANK, N.A.
US_20260340426_A1

Absstract of: US20260340426A1

0000 Systems and methods for efficient data sampling for machine learning applications are disclosed. According to an embodiment, a method may include: receiving, by a computer program, a data matrix; obtaining, by the computer program, a probability weight for each row in the data matrix; constructing, by the computer program, a sampling tree structure comprising a plurality of leaf nodes and a plurality of non-leaf nodes, wherein each leaf node of the sampling tree structure is associated with one of the probability weights, and each non-leaf node is associated with the weights of its leaf nodes; clustering, by the computer program, sampled data points using a clustering algorithm; and outputting, by the computer program, centers calculated by the clustering algorithm.

SYSTEM AND METHOD FOR DYNAMICALLY DEPLOYING EVALUATION METRICS TO ANALYZE MACHINE LEARNING MODELS IN ADVANCED CORE NETWORKS

Publication No.:  US20260340480A1 29/10/2026
Applicant: 
AT & T IP I LP [US]
AT&T Intellectual Property I, L.P.
US_20260340480_A1

Absstract of: US20260340480A1

0000 Aspects of the subject disclosure may include, for example, a device having: a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of: analyzing a subscription request to identify a type of a machine learning (ML) model; retrieving, from an evaluation metric repository stored in the memory, a plurality of preconfigured evaluation metrics associated with different types of ML models; selecting an evaluation metric from the plurality of preconfigured evaluation metrics; applying the evaluation metric selected to an output of the ML model to generate a performance score; comparing the performance score to a predetermined accuracy threshold; and initiating a corrective operation responsive to the performance score not meeting the predetermined accuracy threshold. Other embodiments are disclosed.

TRI-MATRIX LOW-RANK ADAPTATION OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING MODELS

Publication No.:  US20260340482A1 29/10/2026
Applicant: 
OKTA INC [US]
OKTA, INC.
US_20260340482_A1

Absstract of: US20260340482A1

A system may utilize a fine-tuning operation to fine-tune a pre-trained artificial intelligence or machine learning (AI/ML) model. The system may generate a set of matrices that are indicative of a decomposition of a set of parameter weights associated with a task-specific parameters for the fine-tuning operation. The set of matrices may include one or more first matrices with one or more initialized values and a second matrix with one or more uninitialized values. The system may then train the second matrix to adjust the one or more uninitialized values. Moreover, the one or more initialized values of the second matrix may be associated with a subset of the task-specific parameters. Further, based on training the second matrix and a function, the system may obtain a fine-tuned model that includes a fine-tuned set of parameters associated with a fine-tuned set of parameter weights via the fine-tuning operation.

HYBRID PREDICTIVE AND GENERATIVE ARTIFICIAL INTELLIGENCE DECISION LOGIC WITH DYNAMIC CONTEXT ENRICHMENT AND REFINEMENT FOR ORCHESTRATING AN AUTONOMOUS WORKFLOW

Publication No.:  WO2026226301A1 29/10/2026
Applicant: 
WESTLAKE CORP [US]
WESTLAKE CORPORATION
WO_2026226301_A1

Absstract of: WO2026226301A1

Embodiments of the present disclosure generally relate to methods for autonomous orchestration of a data labeling workflow. Embodiments include generating an embedding of an input string related to input data. Embodiments include selecting a set of candidate labels from a plurality of labels based on the embedding. Embodiments include selecting a refined set of candidate labels based on using a cross-encoder model to generate a respective joint embedding of the input string and each respective label in the set of candidate labels. Embodiments include providing natural language descriptions of the refined set of candidate labels and the input string to a language processing machine learning model. Embodiments include assigning a label to the input data based on the language processing machine learning model outputting the label in response to the natural language descriptions of the refined set of candidate labels and the input string.

SYSTEMS AND METHODS FOR GENERATING LATENT BIOLOGICAL REPRESENTATIONS AND HEALTH-RELATED PREDICTIONS FROM SEMANTICALLY MEANINGFUL INPUT GROUPS

Publication No.:  WO2026226586A1 29/10/2026
Applicant: 
ALDEN SCIENT INC [US]
ALDEN SCIENTIFIC, INC.
WO_2026226586_A1

Absstract of: WO2026226586A1

Systems and methods obtain health-related data for a subject, the health-related data being organized into a plurality of semantically meaningful input groups. Each input group is processed through a respective group-specific transformation pipeline relative to a common internal semantic basis to generate a corresponding group representation comprising a group- specific deviation. A respective adaptive weighting factor scales each group-specific deviation in a common slot-based semantic space, and the group-specific deviations are fused with the common internal semantic basis to generate an integrated representation aligned along common conceptual axes. The integrated representation is input into a machine-learning model to generate a latent biological representation of a biological state of the subject. The latent biological representation is used to generate at least one reconstruction output, including a denoised reconstruction, and at least one health-related prediction.

AGENTIC APPROACH TO MULTILINGUAL TEXT-TO-SQL CONVERSION WITH INTENT DETECTION AND SELF-CORRECTION

Publication No.:  US20260339941A1 29/10/2026
Applicant: 
PALO ALTO NETWORKS INC [US]
Palo Alto Networks, Inc.
US_20260220129_A1

Absstract of: US20260339941A1

Techniques are disclosed for processing natural-language requests associated with data stored in a data lake. A system or computer-implemented method receives, from a user, a natural-language request associated with data stored in the data lake and generates, using one or more machine-learning models, a structured query language (SQL) code snippet configured to retrieve data from the data lake. The SQL code snippet is executed on the data lake to generate results. The system or method determines whether a visualization of the results is appropriate and, in response to determining that the visualization is appropriate, generates a graph-generation prompt and generates a visualization using another machine-learning model. The visualization is output with the results.

LARGE LANGUAGE MODEL UPDATE METHOD, ELECTRONIC DEVICE, AND STORAGE MEDIUM

Publication No.:  US20260340384A1 29/10/2026
Applicant: 
BEIJING BAIDU NETCOM SCI & TECH CO LTD [CN]
BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
CN_122452737_PA

Absstract of: US20260340384A1

A method of large language model update, an electronic device, and a storage medium are disclosed, which relates to the field of artificial intelligence technology, and in particular to the technical fields of large models, intelligent recommendation, deep learning, etc. The method of large language model update includes: performing autonomous data generation using an initial LLM to obtain synthetic data corresponding to multiple capabilities of the initial LLM; constructing preference samples based on the synthetic data corresponding to the multiple capabilities; training the initial LLM using the preference samples to obtain a target LLM.

AI SUPERINTELLIGENCE APPLICATION STATE MACHINE

Publication No.:  US20260340733A1 29/10/2026
Applicant: 
ARUNACHALAM LAKSHMI [US]
Arunachalam Lakshmi
US_20260340733_A1

Absstract of: US20260340733A1

0000 The present invention provides a method and apparatus for a thinking system using an ASI distributed Application State Machine that connects to real, accurate, dedicated absolute data, providing privacy, security, and eliminating hallucinated AI. Specifically, one embodiment of the present invention discloses an ASI Command, Control, Communications and Computer Intelligence (C4I) system for independent, intelligent AI Prompting and ASI Browsing. The ASI Application State Machine comprises: ASI Application data structure network; ASI Enterprise Interface State Machine, said data structures interfacing with a back-end channel, a Finite State Machine embedded in each data structure; and Application Service Information Base providing a uniform interface for ASI Application data structure identities. Additional embodiments disclose ASI Browser displaying ASI Applications; ASI Agents; ASI Application Network Nodes; ASI Operating System; ASI Switch; ASI Database of real, accurate, dedicated absolute data, for Machine Learning to train AI Models, for performing real-time, bi-directional transactions, connecting to billing.

GENERATIVE HIERARCHICAL SEARCHING FOR COMPOUNDS

Publication No.:  US20260339968A1 29/10/2026
Applicant: 
GDM HOLDING LLC [US]
GDM Holding LLC
WO_2025245236_PA

Absstract of: US20260339968A1

A method performed by one or more computers. The method comprises receiving a natural language query specifying requirements for a compound; processing the natural language query using a language policy to generate a plurality of representations of candidate compounds that each satisfy at least a subset of the requirements specified in the natural language query. Each representation specifies at least a chemical formula of the corresponding candidate compound. The method further comprises, for each representation in a subset of the representations, using a generative machine learning model conditioned on the representation to generate one or more candidate chemical structures, each candidate chemical structure comprising a respective spatial location for each of the atoms of the corresponding candidate compound; and selecting a chemical structure and corresponding compound from the plurality of candidate chemical structures.

METHOD OF AUTOMATED SPATIAL PATTERNING OF DEFECT CENTERS IN A SUBSTRATE

Publication No.:  AU2025253711A1 29/10/2026
Applicant: 
DEUTSCHES ZENTRUM FUER LUFT UND RAUMFAHRT E V
DEUTSCHES ZENTRUM F\u00DCR LUFT- UND RAUMFAHRT E. V.
AU_2025253711_PA

Absstract of: AU2025253711A1

Method of automated spatial patterning of defect centers (6) in a substrate, particularly a diamond crystal lattice (50), comprising the following steps: - providing a defect center (6) distribution to a machine-learning model, the machine- learning model being particularly trained to determine an output for displacement of at least one defect center (6) based on the provided defect center (6) distribution, the machine learning model providing an output for displacement of individual defect centers (6), - particularly providing a substrate, particularly diamond, comprising defect centers (6) in a bulk structure of the substrate, particularly a bulk diamond crystal lattice (50), - detecting the position of at least one defect center (6) in the bulk structure of the substrate, particularly the bulk diamond crystal lattice (50), and - displacing (61) the at least one defect center (6) in the bulk structure of the substrate, particularly the bulk diamond crystal lattice (50), particularly site-specific.

METHOD FOR DISPLACING DEFECT CENTERS IN A SUBSTRATE FOR QUANTUM APPLICATIONS IN A DEFINED DIRECTION

Publication No.:  AU2025256006A1 29/10/2026
Applicant: 
DEUTSCHES ZENTRUM FUER LUFT UND RAUMFAHRT E V
DEUTSCHES ZENTRUM F\u00DCR LUFT- UND RAUMFAHRT E. V.
AU_2025256006_PA

Absstract of: AU2025256006A1

Method of automated spatial patterning of defect centers (6) in a substrate, particularly a diamond crystal lattice (50), comprising the following steps: - providing a defect center (6) distribution to a machine-learning model, the machine-learning model being particularly trained to determine an output for displacement of at least one defect center (6) based on the provided defect center (6) distribution, the machine learning model providing an output for displacement of individual defect centers (6), - particularly providing a substrate, particularly diamond, comprising defect centers (6) in a bulk structure of the substrate, particularly a bulk diamond crystal lattice (50), - detecting the position of at least one defect center (6) in the bulk structure of the substrate, particularly the bulk diamond crystal lattice (50), and - displacing (61) the at least one defect center (6) in the bulk structure of the substrate, particularly the bulk diamond crystal lattice (50), particularly site-specific, in a defined direction.

MACHINE LEARNING BASED QUESTION AND ANSWER (Q&A) ASSISTANT

Publication No.:  AU2024439837A1 29/10/2026
Applicant: 
NOTION LABS INC
NOTION LABS, INC.
AU_2024439837_A1

Absstract of: AU2024439837A1

A multimodal content management system having a block-based data structure can include an artificial intelligence (AI)-based embeddings generator and indexer. After receiving an item update instruction that includes an object (e.g., a block content, a block property, or a block schema) identifier and an update payload, the system can transform the update payload—for example, by generating a chunk to capture at least a portion of the update payload. The chunk can correspond to a particular content modality included in the update payload. The system can generate and retrievably store a vector comprising a set of embeddings corresponding to the chunk, where the embeddings represent a vectorized portion of block content, block property, or block schema.

METHOD AND SYSTEM FOR DETERMINING A LONG-TERM BRAIN STATE CHANGE OF A PATIENT

Publication No.:  AU2024433476A1 29/10/2026
Applicant: 
EPIMINDER LTD
EPIMINDER LIMITED
AU_2024433476_A1

Absstract of: AU2024433476A1

Systems and methods for determining a long-term brain state change (LTBSC) of a patient. The systems and methods may obtain long-term electroencephalogram (LTEEG) data comprising at least one LTEEG signal associated with a brain of the patient and gathered via an implant device of the patient. A first model trained using first model training data may receive the LTEEG data to generate LTBSC data indicating at least one LTBSC of the patient. In response to generating the LTBSC data, the systems and methods may one or more of: (i) retrain one or more machine learning models using the LTBSC data; (ii) provide the LTBSC data as an input to the one or more machine learning models; or (iii) generate a medical insight of the patient based upon the LTBSC data, and providing, by the one or more processors, the medical insight to a user device.

INDICATING MODEL PARAMETERS FOR CONTINUAL LEARNING OF COMMUNICATIONS NETWORK MODELS

Publication No.:  WO2026224600A1 29/10/2026
Applicant: 
LENOVO UNITED STATES INC [US]
LENOVO (UNITED STATES) INC.
WO_2026224600_A1

Absstract of: WO2026224600A1

Various aspects of the present disclosure relate to adapting (or updating) an artificial intelligence/machine learning (AI/ML) model (e.g., a deep neural network) to unknown/new target domains while minimizing any loss of knowledge of previous domains within which the model was deployed or adapted. For example, an adaptation procedure may determine or identify knowledge intensive (e.g., important) parameters of the model and adapt the model to a new domain while minimizing changes to values of the knowledge intensive parameters. The procedure may determine a metric for each parameter of the model (e.g., a knowledge coefficient or importance metric) and minimize changes to values of any parameters having relatively high importance metrics during adaptation/updating of the model.

METHOD FOR DETERMINING POLICY FOR SON AND ELECTRONIC DEVICE USING SAME

Publication No.:  US20260340408A1 29/10/2026
Applicant: 
SAMSUNG ELECTRONICS CO LTD [KR]
SAMSUNG ELECTRONICS CO., LTD.
WO_2025121565_PA

Absstract of: US20260340408A1

0000 A method for determining a policy for a Self-Organizing Network (SON), includes: receiving performance management (PM) data of a communication network; generating feature data indicating the PM data by using a deep learning-based encoder; determining an outlier score of the feature data by using a deep learning-based outlier detection model; and selecting, based on the outlier score, one of an artificial intelligence-based policy or a non-artificial intelligence-based policy for performing the SON in the communication network.

METHODS AND SYSTEMS OF FACILITATING A HEALTH ASSESSMENT

Nº publicación: US20260341513A1 29/10/2026

Applicant:

NEOPTIO HEALTH INCORPORATED [CA]
Neoptio Health Incorporated

WO_2025120557_PA

Absstract of: US20260341513A1

The present disclosure provides a method of facilitating a health assessment. Further, the method may include receiving a medical inquiry. Further, the medical inquiry may be generated by a user. Further, the method may include analyzing the medical inquiry. Further, the method may include generating an assessment query based on the analyzing. Further, the generation of the assessment query may be based on one or more of a template and a first machine learning model. Further, the template includes a standardized assessment query. Further, the method may include transmitting the assessment query. Further, the method may include receiving a response from the healthcare communication infrastructure. Further, the response corresponds. Further, the method may include analyzing the response. Further, the method may include determining a diagnosis data based on the analyzing. Further, the method may include transmitting the diagnosis data.

traducir