Alerta

AUTOMATIC DISCOVERY OF MACHINE LEARNING MODEL FEATURES

Resumen de: US20260236798A1

0000 A method performed by a processing system including at least one processor includes monitoring interactions of a human user with a platform for building machine learning models, where the human user is using the platform to build a new machine learning model, detecting, within the interactions, an event that triggers a suggestion feature, performing a search of a data source for existing data from existing machine learning models which can be reused to build the new machine learning model, using information about the event, presenting a suggestion to the human user to reuse a portion of the existing data discovered in the search in the new machine learning model, receiving a user feedback in response to the suggestion, and generating an updated suggestion in response to the user feedback.

SPATIOTEMPORAL TRANSFER MACHINE LEARNING

Resumen de: US20260236836A1

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.

GENERATING SOCIAL MEDIA CONTENT FOR A USER ASSOCIATED WITH AN ENTERPRISE

Resumen de: US20260236730A1

0000 Systems and methods disclosed herein relate to fine-tuning machine learning (ML) chatbots for an enterprise. The systems and methods may use ML chatbots and/or generative ML to generate social media content for a user associated with an enterprise. The systems and methods may fine-tune a base ML model, and use the fine-tuned ML model for the ML chatbot. A user profile may indicate user attributes, and a fine-tuned ML model may be loaded for the ML chatbot based upon an identified user profile.

LEVELS OF GRANULARITY FOR IDENTIFIERS RELATED TO ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING

Resumen de: US20260239267A1

Methods, systems, and devices for wireless communications are described. A wireless device may obtain, from a network entity, information related to at least one level of granularity of a set of multiple levels of granularity that correspond to one or more identifiers associated with one or more network settings. The one or more network settings may relate to communication of reference signaling for an artificial intelligence or machine learning (AI/ML)-based positioning or sensing procedure or measurement of reference signaling for an AI/ML-based positioning or sensing procedure. The wireless device may obtain, from the network entity, at least one identifier of the one or more identifiers that corresponds to the at least one level of granularity. Moreover, the wireless device may perform an operation to control the AI/ML-based positioning or sensing procedure based on the at least one identifier in accordance with the at least one level of granularity.

DATA MODIFICATION OPERATORS FOR REDUCING BIAS IN MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE MODELS

Resumen de: US20260236854A1

0000 A system generates data modification operators that reduce bias or distortions in artificial intelligence (AI) models. The system uses a first artificial intelligence (AI) model to generate outputs based on a set of corresponding inputs to the first AI model. First measurement values of one or more model output metrics in the outputs generated by the first AI model are received. Based on the first measurement values, the system generates a set of data modification operators that specifies one or more operations for modifying inputs to a second AI model. Inputs to the second AI model can be modified using the set of data modification operators to generate a modified set of corresponding inputs. The second AI model can then be applied to the modified set of corresponding inputs to the second AI model.

DYNAMIC CHANNEL STATE INFORMATION COMPRESSION BASED ON INPUT CHANNEL STATE INFORMATION SPECTRAL ENTROPY

Resumen de: WO2026169272A1

Systems and methods for dynamic channel state information (CSI) compression based on input CSI spectral entropy are discussed herein. For example, a user equipment receives, from a base station, a first CSI compression configuration and a reference signal. The UE generates first CSI feedback based on the reference signal received from the base station and generates a PSE value. Then, the UE determines, using the CSI compression configuration, based on the PSE value, a first compression profile for the first CSI feedback. The UE applies the first CSI feedback and the first compression profile at a first encoder of a first artificial intelligence (AI)/machine learning (ML) model to generate compressed CSI feedback, wherein the first encoder generates the first compressed CSI feedback according to the first compression profile for the first CSI feedback and sends the compressed CSI feedback and data corresponding to the compression profile to the base station.

MODEL USAGE EVALUATION METHOD, MODEL USAGE EVALUATION SYSTEM, AND MODEL USAGE EVALUATION PROGRAM

Resumen de: US20260237190A1

A model usage evaluation method for evaluating use of an inference model that is generated by machine learning training and inputs information based on an image includes: a target image feature amount acquisition step of acquiring a feature amount of a target image used as an input to the inference model; a training image feature amount acquisition step of acquiring a feature amount of a training image used for training for generating the inference model; and an evaluation step of comparing the feature amount of the target image acquired in the target image feature amount acquisition step with the feature amount of the training image acquired in the training image feature amount acquisition step to evaluate the use of the inference model for the target image.

SYSTEMS AND METHODS FOR MINING FREQUENTLY ASKED QUESTION (FAQ) FROM CONVERSATION DATA

Resumen de: US20260236793A1

0000 Systems and methods for mining question-and-answer pairs from conversation data to update knowledge bases are provided. In particular, a computing system may obtain conversation data, extract a question-and-answer pair from the conversation data with meta data using a machine learning model, the question-and-answer pair including a question and an answer corresponding to the question, determine whether a knowledge base includes existing content similar to the question-and-answer pair, provide the question-and-answer pair on a graphical user interface with an indication of a presence of any existing content in the knowledge base that is similar to the question-and-answer pair, receive an input to integrate the question-and-answer pair with the knowledge base, and update the knowledge base to integrate the question-and-answer pair in accordance with the input.

DEEP-LEARNING BASED PERSONA SPECIFIC INSIGHT GENERATOR

Resumen de: US20260236860A1

0000 A method for generating persona specific insights. The method may include receiving sensor data associated with a device; extracting features from the received sensor data; processing the features using a machine learning model to generate machine learning metrics; ingesting the machine learning metrics and the features to generate insights data associated with the device; generating personas data using the insights data and the features, and mapping the insights to the personas data; generating custom insights using the insights data, the personas data, and the features, wherein the custom insights are text-based summaries; and disseminating each of the custom insights to respective persona of the personas data to place service orders associated with the device.

IMAGE AND VIDEO CODING METHOD WITH PREDICTION USING SUCCESSIVE TRAINING OF A MACHINE-LEARNING MODEL

Resumen de: US20260237100A1

Methods of processing at least one of image or video data, and a decoder are provided. The method includes successively decoding a plurality of fragments of an image or video. The decoding includes, for one or more fragment in the plurality of fragments: decoding a respective encoded residual fragment to obtain a decoded residual fragment; generating, using a machine-learning model, a predicted fragment from a respective reference fragment, where the respective reference fragment is selected from one or more reference fragments stored in a set of reference fragments; generating, based on the predicted fragment and the decoded residual fragment, a reconstructed fragment; storing the reconstructed fragment in the set of reference fragments; and updating parameters of the machine-learning model based on the respective reference fragment and the reconstructed fragment.

THREAT DETECTION PLATFORMS FOR DETECTING, CHARACTERIZING, AND REMEDIATING EMAIL-BASED THREATS IN REAL TIME

Resumen de: US20260238659A1

0000 Conventional email filtering services are not suitable for recognizing sophisticated malicious emails, and therefore may allow sophisticated malicious emails to reach inboxes by mistake. Introduced here are threat detection platforms designed to take an integrative approach to detecting security threats. For example, after receiving input indicative of an approval from an individual to access past email received by employees of an enterprise, a threat detection platform can download past emails to build a machine learning (ML) model that understands the norms of communication with internal contacts (e.g., other employees) and/or external contacts (e.g., vendors). By applying the ML model to incoming email, the threat detection platform can identify security threats in real time in a targeted manner.

Model-based featurization and classification

Resumen de: AU2026206191A1

MARKED-UP COPY MARKED-UP COPY MARKED-UP In various embodiments, an analytics system uses models to determine features and classification of disease states. A disease state can indicate presence or absence of cancer, a cancer type, or a cancer tissue of origin. The models can include a binary classifier and a tissue of origin classifier. The analytics system can process sequence reads from test biological samples to generate data for training the classifiers. The analytics system can also use combinations of machine learning techniques to train the models, which can include a multilayer perceptron. In some embodiments, the analytics system uses methylation information to train the models to determine predictions regarding disease state. ul u l

MACHINE LEARNING FEATURE RECOMMENDATION

Resumen de: US20260228609A1

A specification of a desired target field for machine learning prediction and one or more tables storing machine learning training data are received. Within the one or more tables, eligible machine learning features for building a machine learning model to perform a prediction for the target field are identified. The eligible machine learning features are evaluated using a pipeline of different evaluations to successively filter out one or more of the eligible machine learning features to identify a set of recommended machine learning features among the eligible machine learning features. The set of recommended machine learning features is provided for use in building the machine learning model.

Systems and Methods for the Prediction of Post-Operative Cognitive Decline Using Blood-Based Inflammatory Biomarkers

Resumen de: US20260229316A1

Embodiments herein describe systems and methods to generate a risk score for an individual to develop postoperative neurocognitive disorder (POND). Various embodiments obtain multi-omics data from an individual, such as genomics, transcriptomics, and proteomics. In certain embodiments, a machine learning algorithm is used to generate the risk score based on the multi-omics data. In further embodiments, clinical data is further used in the determination of the risk score.

METHOD AND SYSTEM FOR GENERATION OF AT LEAST ONE OUTPUT ANALYTICS FOR A PROMOTION

Resumen de: US20260228773A1

0000 There is provided a method and system for generating an output analytic for a promotion. The method includes training and instantiating a machine learning model comprising at least a Random Forest model, with a selection training set, the selection training set comprising the historical data and the one or more input parameters; selecting, by the processor, using the machine learning model a configuration and a layout for the one or more products on the promotional materials; outputting, by the processor, the promotional materials based on the selection of the configuration and layout.

SYSTEMS AND METHODS FOR IDENTIFYING BREATHING COMFORT

Resumen de: US20260224834A1

A method for classifying a user of a respiratory pressure therapy (RPT) device is disclosed, the method comprising: identifying that the user has commenced a therapy session with the RPT device; receiving first input data associated with the user and the therapy session; training a machine learning model based on a plurality of pre-classified users and the first input data to determine an association between a user and a plurality of classifications; classifying the user into a classification of the plurality of classifications; and in response to classifying the user into the classification, causing a user device and/or the RPT device to execute an action. The first input data may include selections from the user in response to a survey prompt.

Deterministic Inference for Machine Learning Models with Variable Behavior

Resumen de: US20260228561A1

0000 Provided are systems and methods that enable deterministic inference for machine learning models with variable behavior. In particular, the present disclosure relates to a system in which a machine-learned model has a variable processing portion that is configured to variably apply one or more of a plurality of different processing operations when processing an input. According to an aspect of the present disclosure, one or more seed values can be used to deterministically control which of the plurality of different processing operations are applied by the machine-learned model when processing a given set of input data.

ETHICAL AND SAFE ARTIFICIAL GENERAL INTELLIGENCE (AGI)

Resumen de: US20260228491A1

0000 The existential question for Artificial General Intelligence (AGI) is whether the values of AGI will align with human values. Solving “the Alignment Problem” is critical. Get it right, and we unlock trillions of dollars of productivity and huge benefits for humanity. Get it wrong and humanity goes extinct. This invention shows how to design ethical and safe AGI that solves the Alignment Problem. The invention includes scalable ethics and safety features as well as several learning, training, tuning, and customization methods that go beyond the standard techniques of machine learning such as Transformers and Deep Learning techniques. The AGI is implemented using either external problem solvers connected on a network or internal AI agents collaborating within a single computerized system. Detailed implementation examples—revealing technological and economic synergy with Meta, Amazon, Google, DeepMind, YouTube, TikTok, Microsoft, OpenAI, Twitter/X, Tesla, Nvidia, Tencent, Apple, and Anthropic—are described.

Machine Learning-Based Synthetic Monitoring

Resumen de: US20260228642A1

Methods, systems, and apparatuses are described herein for using machine learning processes to improve synthetic monitoring of, e.g., websites. Training data may comprise sitemap information for a plurality of different websites and monitoring information that indicates whether, for each of a plurality of different portions of those websites, one or more synthetic monitoring scripts are executed. A machine learning model may be trained using that training data to output whether one or more portions of an input website should be monitored using synthetic monitoring. A sitemap of a first website may be determined and provided as input to the trained first machine learning model. Based on output from the trained first machine learning model, a synthetic monitoring script may be determined and executed to monitor at least a first portion of the first website.

PREDICTIVE MACHINE LEARNING MODELS FOR PARCELS OF REAL PROPERTY

Resumen de: US20260228572A1

0000 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and applying a machine learning model. One of the methods includes the actions of obtaining a collection of data associated with a specified parcel of real property, wherein the collection of data includes one or more parameters of interest; using a machine learning model to generate a prediction from the input collection of data for each of the one or more parameters of interest, wherein the prediction for each parameter of interest comprises a likelihood value that the parameter satisfies a particular condition, and wherein the machine learning model is trained using a training set comprising a collection of data associated with a labeled set of data, the labels indicating the existence of particular parameters on the parcels; and based on the prediction, classifying each of the one or more parameters of interest.

MONITORING A PERFORMANCE OF A MACHINE LEARNING MODEL

Resumen de: US20260230849A1

Various aspects of the present disclosure relate to monitoring a performance of a machine learning model. An apparatus, such as a UE or an NE, generates a set of probability values based on inputting unlabeled data in a machine learning model. In some examples, each probability value of the set of probability values indicates a probability that a respective label value is a label of at least a portion of the unlabeled data. Further, the apparatus generates a performance metric for the machine learning model based on the set of probability values and communicates in accordance with the performance metric.

Model Explainability Based on an Ensemble Approach

Resumen de: US20260228577A1

0000 Methods are provided for generation of natural-language explanations for machine learning model outputs that exhibit reduced hallucinations and higher accuracy while incurring lower computational costs and enhancing privacy. These methods include determining, for the textual and categorical features of an input, respective importance values regarding the degree to which the overall model output was influenced by the input features. These values, along with the input features themselves and the overall model output, are then applied to a natural language model to generate an explanation of the overall model output with respect to the input features. The importance values can be used to prune input features that were least important to the overall model output, further reducing hallucinations, increasing accuracy, and reducing overall computational cost by allowing models with smaller input widths or otherwise less computationally expensive natural language models to be used.

SYSTEMS AND ASSOCIATED METHODS FOR FEATURE RECOGNITION

Resumen de: US20260228377A1

0000 A system for feature recognition of design geometry according to an implementation of the present disclosure may include one or more processors coupled to memory. The one or more processors may be collectively operable to execute a mapping environment. The mapping environment may be operable to access at least one component design including a plurality of geometric features. The mapping environment may be operable to determine values for geometric attributes associated with the respective geometric features of the component design. The mapping environment may be operable to assign, using a machine learning classifier model, predefined names to the respective geometric features based on the values of the geometric attributes. The mapping environment may be operable to assign values for one or more parameters to the respective geometric features according to the assigned predefined names. A method for feature recognition of design geometry is also disclosed.

DATA HANDLING OF HOMOMORPHIC ENCRYPTED DATA USED FOR MACHINE LEARNING MODEL TRAINING IN O-RAN

Resumen de: WO2026165011A1

Embodiments of the disclosure describe a method for data handling of homomorphic encrypted data used for machine learning model training in an Open Radio Access Network (O-RAN). The method includes generating, at a data source entity, data with a Homomorphic Encryption (HE) and plain text labeling. The method further includes transmitting, by the data source entity, the generated data to a model training entity. The generated data with the HE and plain text labeling is used at the model training entity to train a Machine Learning (ML) model. The trained ML model is transferred from the model training entity to a model inference entity. The method further includes transmitting, by the data source entity, the HE data to the model inference entity, to perform one or more interference operations using the HE data and the transferred trained ML model, to obtain a plaintext output at the model inference entity.

SYSTEMS AND METHODS FOR CONTROLLING AUTONOMOUS ROBOTS USING MACHINE LEARNING BASED PLANNING

Nº publicación: WO2026162001A1 06/08/2026

Solicitante:

DALHOUSIE UNIV [CA]
DALHOUSIE UNIVERSITY

Resumen de: WO2026162001A1

Systems and methods for controlling autonomous robots using machine learning based planning are proposed that utilize an improved computational model that is configured to infers a small distribution over possible programmatic cognitive maps conditioned on human prior knowledge of the world, and uses this distribution to generate resource-efficient plans, using a trained Large Language Model as an embedding of human priors. Fragment based computation approaches to allow for computational reuse are also proposed. By using large language model, the system can generate programmatic map representation and fragment-based planning.