Alerta

MACHINE LEARNING-BASED TEXT RECOGNITION SYSTEM WITH FINE-TUNING MODEL

Resumen de: EP4818981A2

A non-transitory processor-readable medium stores instructions to be executed by a processor. The instructions cause the processor to receive a first trained machine learning model that generates a transcription based on a document. The instructions cause the processor to execute the first trained machine learning model and a second trained machine learning model to generate a refined transcription based on the transcription. The instructions cause the processor to execute a quality assurance program to generate a transcription score based on the document and the transcription. The instructions cause the processor to execute the quality assurance program to generate a refined transcription score based on the refined transcription and at least one of the document or the transcription. The at least one refined transcription score indicates an automation performance better than an automation performance for the at least one transcription score.

ANALYZING VIEWER BEHAVIOR IN REAL TIME

Resumen de: EP4819625A2

Systems, methods and articles of manufacture for are provided for analyzing user behavior in real time by ingesting telemetry data related to a streaming media application; feeding the telemetry data to a machine learning model (MLM) that produces a User Experience (UX) command based on the telemetry data and prior telemetry data received from the content streaming application; selecting content items to provide to the client device based on the telemetry data; determining, based on the telemetry data, whether the client device has sufficient free resources to receive the UX command and the content items in a current time window while providing a predefined level of service; when client device has sufficient free resources to receive the UX command and the content items, encapsulating the UX command with the content items in a content stream; and transmitting the content stream to the client device.

FAULT PREDICTION METHOD AND APPARATUS, AND RELATED DEVICE

Resumen de: EP4818906A1

0001 A fault prediction method and apparatus, and a related device are provided, relating to the field of computer technologies. Multiple pieces of error data are obtained, where each piece of error data indicates that a CE occurs in a storage medium. The multiple pieces of error data are classified. Fault prediction is performed, by using a first machine learning model, on first-type error data obtained through classification, and fault prediction is performed, by using a second machine learning model, on second-type error data obtained through classification, to obtain corresponding prediction results indicating whether a UCE occurs in the storage medium. A precision of the first machine learning model in predicting a UCE is greater than a first threshold, and a recall of predicting of the second machine learning model in predicting a UCE is greater than a second threshold. In this way, fault prediction is performed on different types of error data by using the machine learning model with a high prediction precision and the machine learning model with a high recall, so that both a precision and a recall of fault prediction can be considered, thereby effectively improving an overall prediction effect for the multiple pieces of error data.

AEROSOL DELIVERY DEVICE COMPRISING ARTIFICIAL INTELLIGENCE

Resumen de: MX2026010422A

An aerosol delivery device is provided that includes sensor(s) to produce measurements of properties during use of the device, and processing circuitry to record data for a plurality of uses of the device, for each use of which the data includes the measurements of the properties. The processing circuitry is configured to build a machine learning model to predict a target variable, using a machine learning algorithm, at least one feature selected from the properties, and a training set produced from the measurements of the properties. The processing circuitry is configured to then deploy the machine learning model to predict the target variable, and control at least one functional element of the device based thereon. The device may also include a digital camera to capture an image of a face of an attempted user to enable facial recognition to alter a locked state of the device.

HYBRID ARTIFICIAL INTELLIGENCE CLASSIFIER

Resumen de: MX2026010538A

System, methods, apparatuses, and computer program products are disclosed for generating and using a hybrid artificial intelligence classifier for classifying input into one or more nodes of a taxonomy. Training data is received for at least a first portion of the taxonomy and used to train a supervised machine learning (ML) model to classify input into the first portion of the taxonomy having training data. A large language model (LLM) taxonomy is determined for at least a second portion of the taxonomy. The hybrid AI classifier classifies input based on a first classification obtained by providing the input to the supervised ML, and a second classification obtained by providing at least the input and the LLM taxonomy to a pre-trained LLM.

APPARATUS AND METHOD FOR INSPECTING BATTERY

Resumen de: MX2026010476A

A method for inspecting a battery, according to an embodiment of the present invention, relates to a method for inspecting the quality of a battery in a manufacturing process, the method comprising the steps of: acquiring an image capturing at least a portion of the exterior of the battery to preprocess the image; detecting one or more defect candidate regions in the preprocessed image by using one or more detection algorithms; extracting position information of the defect candidate regions and shape feature information of the defect candidate regions; and inputting, into a pre-trained machine learning model, information related to the detection algorithms, the position information of the defect candidate regions, and the shape feature information of the defect candidate regions, to determine whether corresponding defect candidate shapes are defective.

SYSTEMS, APPARATUS AND METHODS FOR TREATMENT OF RETINAL AND MACULAR DISEASES USING ARTIFICIAL INTELLIGENCE

Resumen de: US20260294235A1

An optical coherence tomography (OCT) device includes artificial intelligence for recommending a treatment plan for a patient with a retinal or macular disease such as age-related macular degeneration (AMD). The OCT device includes a sensor configured to quantify an initial level of macular edema or retinal exudation. The OCT device receives treatment information for a series of anti-vascular endothelial growth factor (anti-VEGF) injections to the patient. The OCT device performs OCT on the patient subsequent to each anti-VEGF injection to determine subsequent levels of edema or retinal exudation. The OCT device collects a set of training data including: the initial and subsequent levels of edema or exudation, patient information, and treatment information. The OCT device applies the training data to a machine-learning model trained on training data for a plurality of patients to determine a treatment plan for the retinal or macular disease of the patient.

MACHINE LEARNING (ML)-BASED METHOD FOR DETERMINING A CONTROL CHANNEL ELEMENT (CCE) AGGREGATION LEVEL FOR A USER EQUIPMENT (UE) IN A PHYSICAL DOWNLINK CONTROL CHANNEL (PDCCH)

Resumen de: US20260303475A1

The disclosure relates to a ML-based method for determining a CCE aggregation level for a UE in a PDCCH. The method comprises obtaining RBS traces. The method comprises training, using first data obtained from the traces, a machine learning model to predict a probability of discontinuous transmission (DTX) “isDTX probability”. The method comprises inputting second data obtained from the traces into the machine learning model, obtaining the isDTX probability and expanding the second data with the isDTX probability. The method comprises, for each of a plurality of probability thresholds (PTs) and for each of a plurality of strategies, selecting a data having an isDTX probability greater or equal to the PT and best satisfying the strategy and using the data to train a classifier. The method comprises selecting one classifier and using the classifier for determining the CCE aggregation level for the UE in the PDCCH.

MID-CYCLE PREDICTIONS USING MACHINE LEARNING

Resumen de: US20260300780A1

0000 Implementations are disclosed for training and/or applying a single machine learning model to generate mid-cycle inferences based on variable length time series inputs. In some implementations, a time series of satellite imagery samples that depict an agricultural area over all or part of a crop cycle may be obtained. During training, ground truth agricultural classifications may be obtained for geographic units of the agricultural area represented by individual pixels of the satellite imagery samples. During training, sample(s) of the time series may be masked to generate a partially masked satellite imagery samples, which in tum may be used to generate input embedding(s). The input embedding(s) may be applied across a machine learning model to generate output(s) representing in-season agricultural prediction(s). During training, the in-season agricultural prediction(s) may be compared with the ground truth agricultural classifications to train the machine learning model.

MACHINE LEARNING MODEL PARAMETER TRANSFER

Resumen de: US20260300068A1

Various aspects of the present disclosure relate to a node for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and operable to cause the node to: obtain a machine learning (ML) model comprising of a set of model parameters; for each model parameter in the set of model parameters, determine a sensitivity of the model parameter, and provide error protection to the model parameter based on the sensitivity of the model parameter, the sensitivity of the model parameter indicating a degree of toleration for a value of the model parameter to vary without performance of the ML model degrading beyond a tolerance threshold value; and transmit the error protected model parameters to a further node.

SYSTEMS AND METHODS FOR AUTOMATED, "SELF-DRIVING" LABORATORY ANALYSIS OF BIOLOGICAL AND CHEMICAL SPECIMENS

Resumen de: WO2026207543A1

A self-driving laboratory system and associated methods for autonomous scientific experimentation are disclosed. The system integrates automated laboratory instrumentation, multi-modal sensors, and artificial intelligence models to design, execute, and iteratively optimize biological or chemical experiments. A computing platform receives research objectives, generates experimental protocols, and controls laboratory instruments to perform experimental procedures. Experimental data are collected from imaging systems, analytical instruments, and environmental sensors and are integrated using machine learning and sensor fusion techniques to estimate experimental state. Optimization algorithms, including probabilistic and multi-objective models, analyze the data to generate modified experimental protocols that improve experimental outcomes. The system may dynamically adjust environmental parameters and measurement strategies during experimentation and may share learning across distributed laboratory sites. Digital twin models may simulate laboratory workflows to guide experimental planning. The disclosed platform enables efficient exploration of complex experimental parameter spaces while improving reproducibility, resource utilization, and discovery in automated laboratory environments.

UTILIZING MACHINE LEARNING TO EVALUATE CHAT BOT INTERACTIONS

Resumen de: US20260303554A1

The disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that utilize machine learning to evaluate an electronic communication interaction between an artificial intelligence communication bot and a user. For example, the disclosed systems can utilize a configurable machine learning model that enables easy addition, deletion, or editing of evaluation prompts that guide the machine learning model in evaluating the electronic communication interaction from the AI communications bot. In particular, the disclosed systems can utilize the evaluation prompts with an electronic communication transcript from the AI communications bot to generate communication analysis objects that represent statistics and/or data on the behavior and/or operation of the AI communications bot. In addition, the disclosed systems can utilize the evaluation prompts with an electronic communication transcript from the AI communications bot to trigger digital actions determined from the electronic communication interaction.

MACHINE LEARNING MODEL AUTOMATED BUG IDENTIFICATION

Resumen de: US20260300137A1

0000 Aspects of the present disclosure relate to automated bug identification using machine learning models. Embodiments include instructing a machine learning model, via a prompt, to generate an output according to instructions in the prompt. Embodiments include providing the machine learning model, via the prompt, one or more transcripts, wherein each transcript is associated with a set of user communication data. Embodiments include instructing the machine learning model, via the prompt, to parse the one or more transcripts and create a classification for each given transcript of the one or more transcripts based on one or more attributes of the given transcript. Embodiments include instructing the machine learning model, via the prompt, to provide the classification for each given transcript as the output in a structured object format. Embodiments include receiving the output from the machine learning model in response to the prompt and performing an action based on the output.

MACHINE LEARNING MODEL INFERENCE SIMULATION

Resumen de: US20260300818A1

0000 Example embodiments are directed to a system that facilitates machine learning model inference simulation. A model inference simulation request is received. A model specification is identified based on the model inference simulation request. A job workflow is generated based on the model specification and the model inference simulation request. A model inference simulation result is generated using a machine learning model associated with the model specification. The model inference simulation result is then caused to be displayed on a user interface.

DISTRIBUTED GENERATION OF INFERENCES USING HOSTED MACHINE LEARNING MODELS

Resumen de: US20260300781A1

0000 Systems, methods, and computer program products for distributed generation of inferences using hosted machine learning models are disclosed. A method may comprise fetching, from a remote server, a first checklist comprising one or more pre-processing steps and a second checklist comprising one or more post-processing steps; performing the one or more pre-processing steps at a client on an input dataset to generate a pre-processed input dataset; transmitting, from the client to the remote server, the pre-processed input dataset to be processed by the machine learning model; receiving, at the client from the remote server, an output dataset; performing the one or more post-processing steps at the client on the output dataset to generate a post-processed output dataset; and presenting the post-processed output dataset via a client computing platform at the client..

DYNAMIC CONTEXT ADJUSTMENT DURING A MACHINE LEARNING MODEL INFERENCE PROCESS

Resumen de: US20260300816A1

Systems and methods are provided to dynamically adjust contextual data of a machine learning model during an inference process of the machine learning model. A system can identify one or more tokens generated by the machine learning model. The machine learning model may, during an inference process, generate the one or more tokens based on first contextual data. The system can determine that the one or more tokens satisfy one or more first parameters. The system can obtain second contextual data associated with the one or more tokens based on determining that the one or more tokens satisfy the one or more first parameters and can provide the second contextual data to the machine learning model. The machine learning model may generate an output based on the second contextual data and at least a portion of the first contextual data.

ANOMALY DETECTION FOR MACHINE LEARNING MODELS USING EMBEDDINGS OF THE MACHINE LEARNING MODELS

Resumen de: US20260300817A1

Systems and methods are provided to detect anomalous data obtained from and/or to be routed to a machine learning model. A system can identify a first embedding generated by a machine learning model. The system can obtain a first set of data associated with the machine learning model and can compare the first embedding generated by the machine learning model with the first set of data. Based on comparing the first embedding generated by the machine learning model with the first set of data, the system can determine a manner of processing a second set of data (e.g., an input to and/or an output of the machine learning model). The system can process the second set of data according to the manner of processing the second set of data.

GENERATIVE MACHINE LEARNING MODEL TRAINING USING DYNAMIC PROMPT ROUTING

Resumen de: US20260300011A1

0000 Aspects of the present disclosure relate to machine learning based automated content generation systems. Certain embodiments relate to a specific training data generation and supervised learning process for training a content generation model. In some embodiments, training data for a content generation machine learning model may be generated by routing training prompts to generative models that are optimized for a particular prompt type. The optimized models, which may each be optimized for a different type of prompt, may be used to generate ground truth outputs for each of the training prompts. The ground truth outputs and the training prompts may then be used as training data for training the content generation machine learning model. Thus, the training of each of the optimized models may be transferred to the content generation machine learning model.

DISTRIBUTED UPDATING OF MACHINE LEARNING MODELS

Resumen de: US20260300810A1

0000 An apparatus comprises at least one processing device configured to maintain, by a first entity, a first machine learning model associated with a label distribution of classifications for features characterizing operation of information technology assets running in an information technology infrastructure. The at least one processing device is also configured to generate residual labels characterizing portions of the label distribution not captured by the first machine learning model, to provide the residual labels to additional entities, and to receive from the additional entities partial predictions characterizing predicted classifications for the residual labels based on subsets of the features characterizing the operation of the information technology assets locally available at the additional entities. The at least one processing device is further configured to update one or more parameters of the first machine learning model based at least in part on an aggregation of the partial predictions received from the additional entities.

AUTOMATED FAIRNESS EVALUATION AND AUDITING OF MACHINE LEARNING MODELS

Resumen de: US20260300827A1

0000 An example computer-implemented method of improving fairness of a conformal predictor associated with a machine learning model includes receiving a calibration set including a plurality of subgroups; receiving a fairness criterion; receiving a set of thresholds for generating prediction sets by the conformal predictor; iteratively determining whether a threshold from the set of thresholds balances coverage for each subgroup in the plurality of subgroups based on the fairness criterion; and outputting an optimal threshold from the set of thresholds;

PREDICTING DETERIORATION OF ENTITIES USING MACHINE LEARNING

Resumen de: US20260300762A1

An aspect of the present disclosure provides for prediction of deterioration of entities. In an embodiment, one or more images of an entity are received, environmental conditions in the vicinity of the entity are determined, and deterioration of the entity is predicted, based at least in part, on the one or more images of the entity and the environmental conditions, using one or more machine learning models. The one or more images of the entity indicate a first state of the entity, the deterioration includes change in the state of the entity from the first state to a second state, and the prediction includes estimation of the time required for the state of the entity to change from the first state to the second state. The one or more machine learning models include a multimodal regression model, whose outputs include the estimated time and a level of deterioration.

MACHINE LEARNING FOR RESUPPLY ATTRITION PREDICTIONS

Resumen de: WO2026207217A1

Techniques for improved machine learning are provided. Resupply history for a plurality of users of respiratory therapy is accessed. It is determined that a first user of the plurality of users is approaching resupply attrition based on the resupply history. In response to determining that the first user is approaching resupply attrition, therapy data, for the first user, associated with the respiratory therapy is collected, and an attrition prediction for the first user is generated based on processing the therapy data using a machine learning model. An intervention is facilitated for the first user based on the attrition prediction.

INTELLIGENT FILTERING OF FLAGGED ELECTRONIC COMMUNICATIONS USING MACHINE LEARNING

Resumen de: US20260303557A1

Systems, methods, and computer-readable media are disclosed for systems and methods for intelligent filtering of flagged electronic communications using machine learning. Example methods include determining a first flagged electronic communication using a first machine learning model, where the first flagged electronic communication is flagged due to presence of a phrase, determining, using a second machine learning model, a first false positive score of the first electronic communication, and determining that the first false positive score is less than or equal to a first threshold. The method may include generating a manual review notification for the first flagged electronic communication, determining a manual review output signal associated with the first flagged electronic communication, and causing the second machine learning model to be retrained based at least in part on the manual review output signal.

COMPUTING SYSTEM AND METHOD FOR CREATING A MACHINE LEARNING MODEL HAVING IMPROVED FAIRNESS

Resumen de: US20260300443A1

A computing platform installed with executable software for producing a fairer version of a machine learning (ML) model that is configured to output a predicted value for a numerical variable, where the computing platform is programmed to (i) initialize a subpopulation-dependent fairer version of the ML model, (ii) train a subpopulation-independent projection of the subpopulation-dependent fairer ML model, (iii) evaluate multiple candidate instances of a subpopulation-independent fairer version of the ML model comprising a linear combination of (a) an unadjusted predicted value for the numerical variable that is output by the ML model and (b) a fairness-adjusted predicted value for the numerical variable that is output by the subpopulation-independent projection, and (iv) based on evaluating the multiple candidate instances of the subpopulation-independent fairer ML model, select a given candidate instance of the subpopulation-independent fairer ML model that is thereafter deployed.

COORDINATING INTERACTIONS WITH HETEROGENOUS MACHINE LEARNING AGENTS

Nº publicación: US20260300001A1 01/10/2026

Solicitante:

MICROSOFT TECH LICENSING LLC [US]
Microsoft Technology Licensing, LLC

Resumen de: US20260300001A1

0000 This document relates to facilitating interactions between a user and multiple agents, such as agents that provide different generative machine learning capabilities. In certain disclosed implementations, user input is received and two or more agents are selected to perform a particular task for the user. Then, interactions with the agents are coordinated on behalf of the user based on agent definitions of the selected agents. A result of the particular task is received and provided to the user. For instance, the user input can be received via a chat interface that allows the user to conduct a single chat session that involves the particular task being performed by multiple agents, thus giving the user the appearance of interacting with a single agent.