Alerta

COMPUTER-BASED SYSTEMS HAVING COMPUTER ENGINES AND DATA STRUCTURES CONFIGURED FOR MACHINE LEARNING DATA INSIGHT PREDICTION AND METHODS OF USE THEREOF

Resumen de: US20260340456A1

Disclosed herein are method, system, and computer product embodiments for generating a textual summary of a data set based on traversing a decision tree according to sequence and rank numbers related to a query. Subsets of the data set may receive a rank number indicating the relevancy of the subset of data to the query. In response to traversing the decision tree, a textual summary representative of the data set and subsets of data may be generated and displayed. The textual summary may also include a course of action recommendation based on the culmination of the data set and relevant data subsets.

INTEGRITY DETERMINATION VIA ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING FOR POSITIONING PROCEDURES

Resumen de: 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.

DYNAMIC ARTIFICIAL INTELLIGENCE-DRIVEN DATA MANAGEMENT USING TAXONOMIZED KNOWLEDGE GRAPHS

Resumen de: US20260340432A1

A taxonomical data structure is generated based on multi-modal unstructured enterprise data and unstructured external data using a machine learning component. A taxonomized knowledge graph is constructed based on the taxonomical data structure using the machine learning component. New data is obtained from at least one of an external data source or an internal data source. An action associated with the new data is inferred using the machine learning component and based on the taxonomized knowledge graph and the new data. An indication of the action is output.

INTEGRITY INFORMATION FOR POSITIONING OR SENSING PROCEDURES

Resumen de: WO2026226350A1

Some examples of the techniques described herein may provide signaling or procedures for handling positioning integrity failures or outages for positioning or sensing systems with artificial intelligence or machine learning (AI/ML) or non-AIML positioning procedures. For instance, approaches for managing procedures when a positioning outage occurs (e.g., when a protection level exceeds an alert limit) are provided. In some approaches, a wireless device may utilize a timer from an instance when a protection level exceeds an alert limit. The wireless device may perform one or more operations while the timer is running or after the timer expires. For example, the wireless device may stop processing the positioning resources for the given positioning method, may stop reporting measurements or location estimates, may change the reporting format, may request additional training data, may start a monitoring session, may change the AI/ML model used, or may default to a non-AI/ML-based positioning method.

MACHINE LEARNING NETWORKS, ARCHITECTURES AND TECHNIQUES FOR DETERMINING OR PREDICTING DEMAND METRICS IN ONE OR MORE CHANNELS

Resumen de: US20260340394A1

This disclosure relates to artificial intelligence (AI) and machine learning networks for predicting or determining demand metrics across multiple channels. An analytics platform can receive channel events from multiple channels corresponding to geographic areas, and channel features related to demand conditions in the channels can be extracted from the channel events. During a training phase, the channel features can be accumulated into one or more training datasets for training one or more demand prediction models. The one or more demand prediction models can be trained to predict or determine demand metrics for each of the channels. The demand metrics can indicate or predict demand conditions based on the current conditions in the channels and/or based on future, predicted conditions in the channels. Other embodiments are disclosed herein as well.

AUTOMATICALLY ROUTING INCIDENT TICKETS

Resumen de: US20260339765A1

Methods, apparatuses, and products for automatically routing incident tickets, including: receiving an incident ticket describing an event in a computing system; calculating a plurality of routing signals for the incident ticket, wherein calculating the plurality of routing signals comprises: calculating, based on a plurality of user-defined rule sets applied to the incident ticket, one or more rule-based signals of the plurality of routing signals; calculating, based on one or more machine learning models sets applied to the incident ticket, one or more model-based signals of the plurality of routing signals; and performing a routing decision for the incident ticket based on the plurality of routing signals.

TRAINING MACHINE LEARNING MODELS TO PREDICT CHARACTERISTICS OF ADVERSE EVENTS USING INTERMITTENT DATA

Resumen de: US20260340517A1

Methods, systems, and apparatus for providing a ML model for inference, the ML model having been trained using a first set of training data to provide predictions associated with an adverse event, after training of the ML model, receiving data from one or more data sources, the data representative of characteristics relevant to predictions associated with the adverse event, providing a second set of training data, determining, by a trigger module, a trigger decision based on a set of signals at least partially determined from the second set of training data, the trigger decision indicating whether the ML model is to be one of updated and retrained based on the second set of training data, and selectively executing one of updating and retraining of the ML model using at least a portion of the second set of training data in response to the trigger decision.

MACHINE LEARNING FOR ADAPTIVE BITRATE SELECTION

Resumen de: US20260343039A1

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.

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

Resumen de: 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.

METHOD AND SYSTEM FOR AUTOMATING CLINICAL DATA STANDARDS

Resumen de: US20260341427A1

A method and a clinical data standards (CDS) automated system are provided for automating clinical data standards and generating study data tabulation model (SDTM) artifacts required for a regulatory submission process using a machine learning model and a natural language processing (NLP) engine with minimal user intervention. The CDS automated system extracts metadata from multiple raw datasets automatically using NLP and feeds the extracted metadata into the machine learning model; predicts automatic case report form (CRF) annotations on the extracted metadata and records new learnings onto the CDS automated system; maps one or more raw datasets against a target SDTM variable; generates an SDTM statistical analysis system (SAS) code, an SDTM specification, and one or more SDTM datasets; generates a define package; validates the generated define package and the SDTM artifacts generated throughout the entire cycle; and generates validation reports in real time.

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

Resumen de: 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

Resumen de: 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.

VIRTUAL INTELLIGENCE AND OPTIMIZATION THROUGH MULTI-SOURCE, REAL-TIME, AND CONTEXT-AWARE REAL-WORLD DATA

Resumen de: US20260340518A1

A system for managing and optimizing real world entities with machine learning algorithms are described including a server computer system configured to store and process input data, the server computer system comprising a memory and a processor; and wherein the memory of the server computer system stores a persistent virtual world system comprising virtual replicas of the real world entities, and wherein the server computer system is configured to generate explicit data sets representing functioning and behavior of the real world entities; train the machine learning algorithms with the explicit data sets to generate trained machine learning data sets; and apply the trained machine learning data sets in an artificial intelligence application to manage operation of the real world entities and generate real behavior data of the real world entities during the operation of the real world entities. Corresponding methods are also described.

GENERATIVE HIERARCHICAL SEARCHING FOR COMPOUNDS

Resumen de: 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

Resumen de: 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

Resumen de: 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

Resumen de: 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

Resumen de: 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

Resumen de: 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.

CELL-FREE DNA SEQUENCE DATA ANALYSIS TECHNIQUES FOR ESTIMATING FETAL FRACTION AND PREDICTING PREECLAMPSIA

Resumen de: US20260341408A1

In some embodiments, a computer-implemented method of enhancing sequence read data from a cell-free DNA (cfDNA) sample from a subject for predicting a pregnancy-related condition is provided. A computing system determines a coverage profile based on sequence read data for a plurality of informative sites associated with specific tissue types, cell types, or cell states. The computing system generates a prediction of a presence of or an absence of the pregnancy-related condition by providing at least features from a set of features based on a predicted fetal fraction and a set of features based on the coverage profile as input to at least one machine learning model trained to predict a probability of future onset of the pregnancy-related condition based on the features. In some embodiments, a computer-implemented method of enhancing sequence read data for predicting fetal fraction is provided.

TECHNOLOGY FOR INEXPENSIVE AND QUANTIFIED ASSESSMENT OF INFANT SUCKLING BEHAVIOR

Resumen de: US20260334811A1

Provided herein is a method for evaluating infant suckling behavior, comprising: collecting suckling data from an infant using a vacuum measurement device, transmitting the collected suckling data to a processor, processing the collected suckling data by the processor using a pre-trained Machine Learning (ML) algorithm to identify one or more abnormalities in the infant's suckling behavior, wherein the ML algorithm has been trained on a set of training data comprising a plurality of dimensions associated with the training data, and wherein the identified one or more abnormalities are corresponding to one or more of the plurality of dimensions.

UNCERTAINTY PREDICTION MODELS

Nº publicación: US20260340512A1 29/10/2026

Solicitante:

INDIGO AG INC [US]
Indigo Ag, Inc.

Resumen de: US20260340512A1

A method of determining an uncertainty of a machine learning model. The method includes initializing a plurality of models, each with a unique set of model parameters, reading a training dataset, selecting a unique subset of the training dataset for each of the plurality of models, training each of the plurality of models according to its unique set of model parameters and unique subset of the training data, reading a validation dataset, applying each of the plurality of models to the validation dataset to obtain a plurality of output distributions, determining an uncertainty from the plurality of output distributions.