Alerta

METHOD FOR CONSTRUCTING MACHINE LEARNING MODEL FOR RECOMMENDING AIRWAY OPENING POSTURE ANGLE

Absstract of: US20260311061A1

0000 Disclosed is a method for constructing a machine learning model for recommending an airway opening posture angle. The method includes collecting independent variable data affecting a glottis exposure effect when opening a patient airway, conducting an airway opening experiment, taking a posture angle corresponding to an optimal glottis exposure image as an optimal posture angle, performing single-factor analysis on the independent variables, and screening out statistically significant independent variable data as candidate prediction variables. The method further includes preselecting machine learning models, training and verifying the models, evaluating using AUC values, and selecting a model with a highest AUC value as a prediction model for recommending the optimal airway opening posture angle. The obtained prediction model accurately recommends the optimal airway opening posture angle to expose a glottis of the patient for medical personnel, reducing or avoiding a risk of glottis exposure difficulty in bronchoscopy diagnosis and treatment.

TECHNIQUES TO EMBED A DATA OBJECT INTO A MULTIDIMENSIONAL FRAME

Absstract of: US20260310752A1

0000 Various embodiments are generally directed to techniques for embedding a data object into a multidimensional frame, such as for training an autoencoder to generate latent space representations of the data object based on the multidimensional frame, for instance. Additionally, in one or more embodiments latent space representations of data objects may be classified, such as with a machine learning algorithm. Some embodiments are particularly directed to embedding a data object comprising a plurality of object entries into a three-dimensional (3D) frame.

IDENTIFYING OPTIMAL WEIGHTS TO IMPROVE PREDICTION ACCURACY IN MACHINE LEARNING TECHNIQUES

Absstract of: US20260311066A1

0000 A computer-implemented method, system and computer program product for improving prediction accuracy in machine learning techniques. A teacher model is constructed, where the teacher model generates a weight for each data case. The current student model is then trained using training data and the weights generated by the teacher model. After training the current student model, the current student model generates state features, which are used by the teacher model to generate new weights. A candidate student model is then trained using training data and these new weights. A reward is generated by comparing the current student model with the candidate student model using training and testing data, which is used to update the teacher model if a stopping rule has not been satisfied. Upon a stopping rule being satisfied, the weights generated by the teacher model are deemed to be the “optimal” weights which are returned to the user.

ROBOT FLEET MANAGEMENT AND ADDITIVE MANUFACTURING FOR VALUE CHAIN NETWORKS

Absstract of: AU2026234064A1

Abstract A robot fleet management platform, includes a set of datastores that store a governance library that defines a set of governance standards that include at least one set of security standards, legal standards, ethical standards, regulatory standards, quality standards, or engineering standards that are applied to decisions made by one or more respective intelligence services; and includes: a set of one or more processors that execute a set of computer-readable instructions, wherein the set of one or more processors collectively execute: a governance-enabling intelligence layer that receives and responds to intelligence requests received from respective intelligence service clients, wherein the intelligence layer includes: a set of artificial intelligence services that includes at least one of a machine learning service, a rules-based intelligence service, a digital twin service, a robot process automation service, or a machine vision service; and an intelligence layer controller that coordinates performance of respective intelligence services on behalf of the respective intelligence service clients and performance of a set of analyses corresponding to the respective intelligence services based in part on the set of governance standards, wherein the intelligence layer returns decisions determined collectively by the artificial intelligence service in response to the intelligence requests, such that the decisions are determined based on a set of intelligence service dat

MACHINE LEARNING GENERATION FOR REAL-TIME LOCATION

Absstract of: US20260311056A1

A system and method for determining location information of a portable device relative to an object is provided. In one embodiment, aspects of the system to determine location with respect to the portable device may be transferred to another system for training that system to determine location with respect to the portable device or another type of portable device.

SYSTEM AND METHOD FOR INTELLIGENT GENERATION OF PRIVILEGE LOGS

Absstract of: US20260310899A1

Systems, methods, and computer readable media for intelligent generation of privilege logs are provided. These techniques may include applying an unsupervised machine learning model to a corpus of documents to identify a plurality of topics associated with the corpus of documents, associating a plurality of categories with respective subsets of the plurality of topics, executing a first classifier training model to train a first classifier for a category, and a second classifier training model to train a second classifier for the category, determining a performance metric for the first classifier for the category and a performance metric for the second classifier for the category, selecting one of the first classifier or the second classifier for the category based on the performance metrics, applying the selected classifier to documents in the corpus of documents, and generating a privilege log based upon the classifiers applied to documents in the corpus of documents.

METHODS AND SYSTEMS FOR DETERMINING CORRECTNESS OF MACHINE LEARNING MODEL OUTPUT

Absstract of: US20260310999A1

0000 The present disclosure provides methods and systems for generating a confidence label for a prediction produced by a predictive model. The method comprises: (a) generating training datasets for training a confidence model, the training datasets are generated using data collected from a cross validation process for evaluating the predictive model; (b) training the confidence model using the training datasets to learn a relationship between a score assigned by the predictive model to a prediction and a correctness measure of the prediction; and (d) feeding an input to the trained confidence model to output a confidence label. The input comprises a target precision or a target recall for a new prediction produced by the predictive model and a score assigned to the new prediction, and the confidence label indicates whether the new prediction is high confidence or low confidence.

Computer Implemented Method for Predicting a Level of Quality of a Vacuum into a Vacuum Chamber of a Coating Machine, and Corresponding Device

Absstract of: US20260308751A1

The invention relates to a computer implemented method for predicting a level of quality of a vacuum into a vacuum chamber (2) of a coating machine (1) suitable for coating optic elements (8). According to the invention, this method comprises steps of: —acquiring at least one technical feature of the coating machine during coating processes of optic elements, and —predicting said level of quality from the at least one measured technical feature by means of a processing unit that registers a machine learning model, said at least one technical feature being an input of said machine learning model and said level of quality being an output of said machine learning model.

REMOTE VALIDATION OF AUTOMATED TELLER MACHINES (ATMs) USING MACHINE LEARNING

Absstract of: US20260311570A1

0000 Aspects of the disclosure relate to a remote validation platform for ATMs. The platform may train a reconfiguration model to output sets of configuration instructions. The platform may receive a first information stream from a first ATM. The platform may receive one or more additional information streams from sources associated with the first ATM. The platform may generate, using the reconfiguration model, a first set of configuration instructions based on the first information stream and the one or more additional information streams. The platform may cause reconfiguration of the first ATM based on the first set of configuration instructions. The platform may refine the reconfiguration model based on the first set of configuration instructions.

MACHINE LEARNING TECHNIQUES FOR DISCOVERING KEYS IN RELATIONAL DATASETS

Absstract of: US20260310634A1

0000 Techniques for discovering primary, unique, and/or foreign keys for relational datasets are described. The techniques include profiling the relational datasets to obtain respective data profiles; identifying one or more primary key candidates for a first relational dataset using a first data profile of the first relational dataset and a first trained machine learning model; identifying one or more foreign key proposals for a second relational dataset using the one or more primary key candidates by performing a subset analysis of the second relational dataset with respect to the first relational dataset; identifying one or more foreign key candidates for the second relational dataset using the first data profile, a second data profile of the second relational dataset, and a second trained machine learning model different from the first trained machine learning model; and outputting the at primary key candidate(s) and the foreign key candidate(s).

ON-DEVICE MACHINE LEARNING PLATFORM

Absstract of: US20260311067A1

0000 The present disclosure provides systems and methods for on-device machine learning. In particular, the present disclosure is directed to an on-device machine learning platform and associated techniques that enable on-device prediction, training, example collection, and/or other machine learning tasks or functionality. The on-device machine learning platform can include a context provider that securely injects context features into collected training examples and/or client-provided input data used to generate predictions/inferences. Thus, the on-device machine learning platform can enable centralized training example collection, model training, and usage of machine-learned models as a service to applications or other clients.

PROCESS AND SYSTEM FOR GENERATION OF COKE DRUM OUTAGE PROJECTIONS

Absstract of: US20260310246A1

0000 An apparatus includes at least one processing device configured to obtain sensor data from sensors associated with one or more coke drums in a refinery. The at least one processing device is also configured to generate an outage projection for an end of a feed cycle of at least one of the coke drums by processing, utilizing a machine learning model, information derived from the sensor data characterizing (i) an amount of feedstock which has been fed to the at least one coke drum during the feed cycle, (ii) a time at which a level indicator for the at least one coke drum first exceeds a designated threshold value, and (iii) a density of the feedstock fed to the at least one coke drum during the feed cycle. The at least one processing device is further configured to provide, at a user interface, the generated outage projection.

PARALLEL PROCESSING FOR MODEL EXECUTION

Absstract of: US20260311057A1

The subject technology provides for distributed training and inferencing of a machine learning model across multiple processing resources. During a forward pass, each processing resource generates a portion of an update for its corresponding portion of a feature set. While performing this computation, each resource can approximate, compress, and transmit its portion of the features to other resources, and can receive an approximated and compressed portion generated elsewhere. Each resource then decompresses the received representation and updates its local feature portion without waiting for full-precision data from other nodes. By allowing approximation, compression, communication, and computation to occur in parallel, the system may reduce communication overhead that typically causes idle compute periods. This structure may improve sustained utilization and responsiveness when models operate across multiple distributed compute nodes.

FAULT PREDICTION METHOD AND APPARATUS, AND RELATED DEVICE

Absstract of: 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.

ANALYZING VIEWER BEHAVIOR IN REAL TIME

Absstract of: 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.

INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE

Absstract of: EP4819147A1

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

MACHINE-LEARNING-BASED PREDICTION AND DYNAMIC CORE ALLOCATION ARCHITECTURE

Absstract of: EP4818902A1

0001 Techniques and apparatuses are described for implementing a machine-learning (ML) based prediction and dynamic core allocation architecture. In example aspects, a plurality of parameters related to one or more operating conditions (e.g., temperature of a core) of one or more processors are generated. The plurality of parameters are used as an input for an ML-based model, which outputs a prediction of future parameters. The prediction is used as input for one or more process modules. The one or more process modules parse the prediction to provide a decision output, which is used to modify one or more facets of the one or more processors (a frequency, a voltage, core assignments for tasks, etc.). In this way, a system-on-chip can dynamically manage multiple operations concems for the one or more processors, such as balancing performance and temperature concerns to realize a tailored user experience.

COMPUTER-IMPLEMENTED METHOD AND SYSTEM FOR STRUCTURING AND VALUATING DATA ASSOCIATED WITH NON-FUNGIBLE ASSETS

Absstract of: EP4818985A1

Disclosed is a computer-implemented method for an automated valuation of non-fungible asset is performed by computing node(s) (202), communicably coupled to user device(s) (208) and data repository(s) (204), wherein the computing nodes, the data repository and the user device are connected via a computing network, comprises: receiving input data comprises at least one parameter that is a unique identifier of the non-fungible asset; capturing published data, wherein the published data comprises a second set of parameters; preprocessing the captured data for normalization of the published data to generate an output data that is structured; executing a pre-trained valuation model (212) to identify a proxy for parameters that are missing from the captured data; and applying a predictive machine learning model by executing a predictive valuation model (214) to generate valuation result for the non-fungible asset with a pre-set accuracy and display the valuation result at a screen.

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

Absstract of: 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.

Machine learning prediction of ion trap filling functions

Absstract of: GB2705175A

A method for facilitating machine learning prediction of ion trap filling functions is disclosed. The method comprises causing a mass analyser to perform a scan using an injection or accumulation time. The injection time is correlated to a requested or desired ion population size by an ion trap filling function, which may be non-linear. The coefficients of the ion trap filling function are predicted by a machine learning model based on current operational parameters of the mass analyser, e.g. the scan range or width of the mass analyser, pass range or width of an ion trap of the mass analyser, or the number of ion guide injections. The injection time may be scaled using a pre-scan ion flux estimate or an ion species distribution. The machine learning model may be trained in a supervised fashion and updated via backpropagation based on an error between the actual ion population size and the requested ion population size. The machine learning model may be a random forest regressor or a deep learning neural network. A system and a computer program are also claimed. Figure 15

COMPUTER-BASED SYSTEMS AND METHODS FOR MACHINE LEARNING BASED EXCEPTION PREDICTIONS

Absstract of: US20260300783A1

0000 A failure prediction method including a predicting flow and a model training flow, the predicting flow including receiving a natural language input from a client computer, translating the input into a task by a LLM, selecting a ML model dedicated to the task, receiving first data, converting the first data to second data of a predetermined format, immediately applying, the ML model on the second data for predicting an output and providing a corresponding explanation, storing the second data and the output into historical data in a storage layer, translating the output and the explanation into a prediction in the natural language by the LLM, and transmitting the prediction to the client computer and iterating the predicting flow for a predetermined number of time; and the model training flow including retrieving the historical data from the storage layer, and training the ML model on the historical data.

PERSONALIZED RECOMMENDATION SYSTEMS TO REMEDIATE INEFFICIENCIES IN USER BEHAVIOR

Absstract of: US20260301015A1

0000 A method for generating predictive and event-based action recommendations includes receiving, from at least one data source, input data representative of a user; generating, using a first machine learning model, a user behavior pattern for the user based on the input data representative of the user; classifying the user behavior pattern based on one or more personas representative of user characteristics; identifying, based on at least the input data and the one or more personas, an inefficiency in the user behavior pattern impacting a goal of the user; and generating, using a second machine learning model, a personalized recommendation for the user to remediate the inefficiency.

MID-CYCLE PREDICTIONS USING MACHINE LEARNING

Absstract of: 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.

METHOD AND SYSTEM FOR PREPROCESSING OPTIMIZATION OF STREAMING VIDEO DATA USING MACHINE LEARNING

Absstract of: US20260301385A1

0000 A method of improving a main output of a main AI model includes processing first video data using a machine learning model includes continuously analyzing incoming video data via a first processing pipeline and concurrently via a second processing pipeline. The first processing pipeline can include preprocessing incoming video data according to first preprocessing parameters that format the incoming video data to create the first video data and processing the first video data by the main AI model to determine the main output that is indicative of a first inference dependent upon the first video data. The second processing pipeline can include identifying first test preprocessing parameters that are predictive to produce a first test output that satisfies a baseline criterion and preprocessing the incoming video data according to the first test preprocessing parameters that format the incoming video data to create first test video data.

MACHINE LEARNING MODEL, MODEL TRAINING METHOD, DATA COLLECTION SYSTEM, AND ON-VEHICLE DEVICE

Nº publicación: WO2026204891A1 01/10/2026

Applicant:

DENSO CORP [JP]
\u682A\u5F0F\u4F1A\u793E\u30C7\u30F3\u30BD\u30FC

Absstract of: WO2026204891A1

A machine learning model (50) causes a computer to function as a first input unit (S10, S120), an inference result generation unit (S20, S130), a first output unit (S30, S140), a second input unit (S120), a weak point identification unit (S150 to S200), a collection condition generation unit (S220), and a second output unit (S230). The first input unit receives input of first input data. The inference result generation unit performs inference on the basis of the first input data and generates an inference result. The first output unit outputs the inference result. The second input unit receives input of second input data including a plurality of pieces of first input data and a plurality of pieces of ground truth data. The weak point identification unit identifies a weak point in the inference. The collection condition generation unit generates a collection condition corresponding to the weak point. The second output unit outputs collection condition data indicating the collection condition.