Alerta

LIGHTWEIGHT IMAGE RECOGNITION METHOD AND SYSTEM FOR CHARACTER-WHEEL CAMERA‑BASED WATER METER

Resumen de: WO2026214606A1

Disclosed in the present application are a lightweight image recognition method and system for a character-wheel camera‑based water meter. The embodiments of the present application implement the collection of a water-meter image, digit recognition and data transmission on the basis of an ESP32 development board, which is connected to a server. In the embodiments of the present application, a neural network is used to perform water‑meter digit recognition, and model parameters are optimized by means of forward propagation and backward propagation algorithms. In the present invention, a development board directly uses a character‑wheel recognition network to perform digit recognition on the current water‑meter image, so as to obtain a water‑meter reading result. It is unnecessary to upload the water‑meter image to a server for reading recognition, thereby helping improve the recognition efficiency of water‑meter readings. Moreover, simply by means of installing the development board on a character-wheel water meter, automatic reading can be implemented, thereby significantly improving the intelligence level of the conventional character-wheel water meter. The system in the embodiments of the present application has the characteristics of a lightweight design and a high efficiency, and is suitable for application scenarios of the automatic reading of smart water meters.

ARTIFICIAL INTELLIGENCE-BASED IDENTIFICATION METHOD FOR WIRELESS COMPOSITE JAMMING SIGNAL

Resumen de: US20260322523A1

An artificial intelligence-based identification method for a wireless composite jamming signal forms a novel neural network structure ACSNet through the integration of an asymmetric convolutional block (ACB), aiming to address composite jamming signal identification in wireless communication systems. The model of the artificial intelligence-based identification method enhances the detection capability of neural networks for subtle signal feature variations based on artificial intelligence, thereby improving the identification accuracy for intricate jamming patterns. The artificial intelligence-based identification method can effectively address the challenge of jamming signal identification under a low jamming-to-noise ratio (JNR). Additionally, ACSNet demonstrates significant resilience to variations in power ratios (PRs) of composite jamming signals, highlighting its adaptability to real-world environments with imbalanced jamming signal power distributions.

FACE FORGERY DETECTION METHOD AND SYSTEM BASED ON GRAPH CONVOLUTIONAL NEURAL NETWORK

Resumen de: WO2026213897A1

Disclosed in the present invention are a face forgery detection method and system based on a graph convolutional neural network. The method comprises: acquiring a facial video to be subjected to forgery detection; and inputting said facial video into a trained detection model, so as to obtain a determination result indicating whether face forgery is present in said video. The detection model comprises: an encoder, which is used for generating features of each image frame on the basis of said facial video; a spatiotemporal-graph construction module, which is used for constructing, on the basis of the features of each image frame, a spatiotemporal graph in which spatial graphs and temporal graphs are integrated; a spatiotemporal-graph convolution module, which is used for performing feature learning on the basis of the spatiotemporal graph, so as to obtain class features; and a classifier, which is used for predicting, on the basis of the class features, a forgery detection result for the facial video. In the present invention, a spatiotemporal graph in which spatial graphs and temporal graphs are integrated is constructed while satisfying the spatiotemporal consistency requirements of a facial video, thereby implementing efficient, accurate and highly-generalizable face forgery detection.

INTERACTIVE MLOps SYSTEM

Resumen de: US20260320470A1

An operating method of an interactive MLOps system according to an embodiment includes receiving an input message comprising a request related to a target artificial neural network model from a user, determining a process list to be provided by the interactive MLOps system, by inputting the request included in the input message into an internal artificial neural network model, transmitting a response message comprising the process list, receiving, from the user, a selection message comprising one or more selections from the process list, and building or updating a pipeline based on the request included in the input message and the selections included in the selection message.

APPARATUS, METHOD AND READABLE STORAGE MEDIUM FOR MODEL TRAINING

Resumen de: US20260320385A1

0000 A model training apparatus is configured to obtain a plurality of intermediate models determined by performing iteration training on a neural network model, each intermediate model including values of model parameters such as model weights and statistics of the neural network model. The model training apparatus may perform weighted summation on the values of each model parameter in different intermediate models to obtain the value of the corresponding model parameter in an aggregated model. The model training apparatus may adopt the aggregated model as the training results of the neural network model while the iteration is completed, which is beneficial to improving the generalization performance of the trained neural network model.

SYSTEMS AND METHODS OF SCALABLE CONVEX RECURRENT NEURAL NETWORK TRAINING FOR INTERPRETING BRAIN DYNAMICS

Resumen de: US20260320365A1

0000 Computer-implemented methods and systems for training a neural network to interpret neural dynamics, the method comprising obtaining functional connectivity between brain regions and artificial neurons simulated by the neural network, capturing neural activities between biological neurons, processing the captured neural activities to obtain training data for the neural network, and constructing the neural network using the training data to reproduce neural dynamics between the artificial neurons.

COMPUTER SYSTEM AND METHOD FOR MARITIME SURVEILLANCE AND SATELLITE-BASED EARTH OBSERVATION OF OBJECTS USING NADIR-NADIR IMAGE MATCHING

Resumen de: US20260321018A1

Computer systems and methods for maritime surveillance and identification of unknown vessels are provided. The system includes at least one data storage device storing: a database of known optical nadir satellite images each containing a known candidate vessel having a known unique vessel identifier; and an unknown optical nadir satellite image containing an unknown vessel. The system also includes at least one processor configured to execute a nadir-nadir image matcher configured to: compare, via a neural network, the unknown nadir image to a plurality of known nadir images in the database, the comparing including determining a similarity score indicating a similarity level between the unknown nadir image and a respective known nadir image; output, via the neural network, a ranked list of the known nadir images based on the determined similarity scores; and assign a known unique vessel identifier to the unknown nadir image based on the ranked list.

Multi-task real-time inference scheduling system machine tool and method thereof

Resumen de: US20260319474A1

The present invention relates to a multi-task real-time inference scheduling system and real-time inference scheduling method of a machine tool, wherein a central control unit is connected to each of one or more individual control units through a network, receives a use context of each machine tool through each individual control unit, generates a multi-task learning model through a neural network, infers multiple tasks required to be performed by the individual control unit of each machine tool through machine learning by using real-time use contexts collected during operation of the machine tool by a use scenario, and schedules the multiple tasks of the machine tool through machine learning.

SYSTEM AND METHOD FOR MICROMECHANICS SIMULATION

Resumen de: US20260320267A1

A micromechanics simulation framework has the steps of collecting one or more images of at least one composite material, providing, to a first neural network, an input including the one or more images, segmenting one or more microstructures in the one or more images, quantifying one or more physical descriptors of one or more segmented microstructures, passing an output including the one or more segmented microstructures and one or more quantified physical descriptors to one of: a statistical-based module using descriptor-driven stochastic construction routines with periodic boundary conditions, or a second deep generative neural network, and generating one or more stochastic representative volume element (SRVE) ensembles based on the one or more segmented microstructures and one or more quantified physical descriptors. A micromechanics simulation system is also disclosed for computing the homogenized elastic properties and the time-dependent response of composites in high-temperature environments.

FOCUSED HYPERPARAMETER TUNING USING ATTRIBUTION

Resumen de: US20260320412A1

0000 According to some embodiments, a method includes determining test predictions by performing an inference process using a checkpointed learning model and test vectors. The checkpointed learning model includes hyperparameters and weights. The method further includes determining an attribution map by performing one or more attribution processes using the test predictions and the test vectors. The method further includes determining a score for each particular hyperparameter by analyzing the attribution map using an association classifier. The method further includes determining, based on the analysis by the association classifier, whether each particular hyperparameter should be frozen or tuned again. The method further includes updating the hyperparameters and weights of the neural network when it is determined that at least one particular hyperparameter should be tuned again.

PANOPTIC SCENE COMPLETION

Resumen de: US20260321031A1

Panoptic scene completion may be achieved using a neural network comprising a sparse generative encoder-decoder network that performs scene-level occupancy prediction in a fixed-size voxel grid. To segment individual object instances, an instance decoder may segment individual object instances from the scene-level occupancy predictions to predict instance masks in the (occupied) voxel space in a class-agnostic fashion. For each predicted instance (e.g., transformer query), the instance decoder may regress a semantic embedding or token representing the semantic features (e.g., a CLIP token) for a corresponding object instance, enabling zero-shot prompting at test and/or inference time. As such, the neural network may produce semantic features that may be used for open-vocabulary querying directly from 3D measurements, and a representation of the resulting labeled masks may be provided to one or more downstream components such as a control policy of an ego-machine to make decisions on navigation, grasping, and/or manipulation actions.

TIME-SERIES DATA PROCESSING

Resumen de: US20260320155A1

A time-series data processing method includes: constructing a time-series curve diagram based on first time-series data and second time-series data; performing feature extraction on the time-series curve diagram to obtain a spatial relationship feature, performing association relationship recognition on the time-series curve diagram by using a neural network model to obtain a text, and performing feature extraction on the text to obtain an association relationship feature; merging the spatial relationship feature with the association relationship feature to obtain a merged feature, and performing feature retrieval in a time-series knowledge base based on the merged feature to obtain a candidate feature; and determining a similarity between the merged feature and the candidate feature, and determining a predicted label for the first time-series data based on the similarity and a time-series change label for the candidate feature.

DEVICE WAKE-UP METHOD, SYSTEM, AND CHIP

Resumen de: US20260320806A1

0000 This application provides a device wake-up method, a system, and a chip. The method may include: processing a captured first image, determining a motion region image in the first image, and determining, by using a level-1 neural network, whether a target object exists in the motion region image; and when it is determined that the target object exists in the motion region image, performing reconfirmation, by using a level-2 neural network cascaded with the level-1 neural network, on a result output by the level-1 neural network. It can be learned that the target object is determined by using the level-1 neural network and the level-2 neural network, so that a false alarm frequency can be reduced, and system power consumption can be reduced.

APPLICATION PROGRAMMING INTERFACE TO INDICATE FRAME INTERPOLATION SUPPORT

Resumen de: US20260320741A1

Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to indicate support to use one or more neural networks to perform frame interpolation.

Ventricular tachycardia exit site identification method and apparatus

Resumen de: AU2026201422A1

Abstract To non-invasively identify a ventricular tachycardia exit site in a heart of a particular patient (107) using electrocardiogram signals and medical imagery for the particular patient, a control circuit (101) can be configured to access (205) a neural network (104) that has been trained (202) using a plurality of synthetic data examples (203) and to input information regarding the electrocardiogram signals and the aforementioned medical imagery for the particular patient to the neural network. The control circuit can then output from the neural network information that identifies a predicted ventricular tachycardia exit site in the heart of the particular patient. Abstract eb b s t r a c t e b BY A CONTROL CIRCUIT GENERATE SYNTHETIC DATA EXAMPLES 201 SYNTHETIC TRAIN A DATA NEURAL DATA ACCESS A NEURAL NETWORK THAT HAS BEEN TRAINED INPUT INFORMATION REGARDING ELECTROCARDIOGRAM SIGNALS AND MEDICAL IMAGERY FOR A PARTICULAR 206 PATIENT TO THE NEURAL NETWORK OUTPUT FROM THE NEURAL NETWORK INFORMATION THAT IDENTIFIES A PREDICTED VENTRICULAR TACHYCARDIA 207EXIT SITE IN THE HEART OF THE PARTICULAR PATIENT eb e b -

NEURAL NETWORK-BASED NOISE SYNTHESIS

Resumen de: US20260320983A1

Apparatuses, systems, and techniques are presented to introduce noise or variation into images. In at least one embodiment, one or more neural networks are used to determine noise to be added to one or more images of one or more objects based, at least in part, upon one or more features of the one or more objects.

Prediction of bone based on point cloud

Resumen de: AU2026238109A1

A method for surgical planning includes obtaining, by a computing system, a first point cloud representing a first portion of a bone or a first cloud representing at least a portion of a bone, applying, by the computing system, a point cloud neural network to generate a second point cloud based on the first point cloud, the second point cloud comprising at least one of points representing at least a second portion of the bone or points representing an axis along the bone, and generating, by the computing system, surgical planning information based on the second point cloud. ep e p

INDEPENDENT POSITIONING OF AUXILIARY INFORMATION IN NEURAL NETWORK BASED PICTURE PROCESSING

Resumen de: US20260320995A1

Methods and apparatuses are provided for processing of picture data or picture feature data using a neural network with two or more layers. The present disclosure may be applied in the field of artificial intelligence (AI)-based video or picture compression technologies, and in particular, to the field of neural network-based video compression technologies. According to one or more embodiments, two kinds of data are combined during the processing by the neural network. The two kinds of data are obtained from different stages of processing by the network. Some of the advantages may include greater scalability and a more flexible design of the neural network architecture which may further lead to better encoding/decoding performance.

ATTRIBUTE-BASED ENCRYPTION FOR SELECTIVE DOCUMENT CONTENT PROTECTION

Resumen de: EP4823042A2

0001 The present disclosure provides a method for securing document content. A document security manager receives a digital document containing original text and image content. The original text content is processed to identify text portions by parsing annotations, analyzing proximate text, extracting content within the determined scope, and determining encryption attributes. The original image content is processed to identify image portions by detecting user-defined selections or employing a neural network to identify sensitive objects. Encrypt content requests are generated including the identified text and image portions with associated attributes and metadata. The requests are transmitted to a cryptographic engine, which returns encrypted content. A partially encrypted document is built by replacing original content with masking symbols, applying visual obfuscation, embedding encrypted content as metadata, and updating document properties to indicate encrypted content.

Neural networks for indicating priority of connection requests

Resumen de: GB2705387A

Apparatuses, systems, and techniques are described to predict priority of a connection request (e.g., a next connection request). For example, processing circuitry uses one or more neural networks to indicate priority of one or more next connection requests within one or more radio access network (RAN) networks. A base station of a UE device can use, perform, or otherwise execute the one or more neural networks to generate a prediction of what a next connection request will be. Fig. 1

METHOD FOR GENERATING INTERNAL STRUCTURE OF ORGANISM ON BASIS OF DEEP LEARNING

Resumen de: EP4822642A1

The present application relates to the field of life sciences and medical imaging device technologies, and more particularly, to a deep learning-based method for generating an internal structure of an organism. The method includes the following steps: S1, constructing and training an internal organ generation model of a imaging target; S2, obtaining a three-dimensional body surface contour image of the imaging target; S3, inputting the obtained three-dimensional body surface contour image of the imaging target into the internal organ generation model to obtain a three-dimensional internal organ distribution image; and S4, performing merging on the three-dimensional internal organ distribution image and the three-dimensional body surface contour image, and displaying a result obtained based on the merging. With a deep neural network-based internal organ generation model of the imaging target, the three-dimensional internal organ distribution image of the imaging target can be obtained quickly and accurately simply through obtaining the three-dimensional body surface contour image of the imaging target and inputting the three-dimensional body surface contour image into the internal organ generation model, which simplifies operation steps, realizes automatic imaging, improves an imaging efficiency, and has high applicability.

PERFORMING SEMANTIC SEGMENTATION OF 3D DATA USING DEEP LEARNING

Resumen de: US20260311336A1

0000 A computer-implemented method of training a deep artificial neural network includes receiving a three-dimensional point cloud and training the deep artificial neural network by subdividing the three-dimensional point cloud, and updating weights of the deep artificial neural network. A computing system includes a processor; and a memory having stored thereon computer-executable instructions that, when executed by the processor, cause the computing system to receive a three-dimensional point cloud and train the deep artificial neural network by subdividing the three-dimensional point cloud, and updating weights of the deep artificial neural network. In yet another aspect, a non-transitory computer-readable medium includes computer-executable instructions that when executed, cause a computer to receive a three-dimensional point cloud and train the deep artificial neural network by subdividing the three-dimensional point cloud, and updating weights of the deep artificial neural network.

SYSTEMS AND METHODS FOR ROPE EVALUATION

Resumen de: US20260309639A1

0000 In an embodiment of the disclosed principles, a method of analyzing a rope to estimate its residual break strength (RBS) is provided. The method entails training a multi-layered neural network to recognize rope damage and estimate an RBS for a rope under study by collecting high-resolution visual data of a plurality of sample ropes, extracting visual features of damaged areas of each rope, resolving each visual feature into a damage type and clustering damage type exemplars, breaking each sample rope to determine an actual RBS for each rope and classifying the visual data via determined RBS, specific to product type/damage mode. Job and product data are entered for the rope under study, the rope is paid out, and high-resolution visual data is captured while spooling back the rope. The correlated data is provided to the multi-layered neural network to generate an estimate of RBS for the rope under study.

ASSEMBLY LINE VARIANT PATH PLANNING SYSTEM AND METHOD BASED ON GRAPH-BASED DEEP REINFORCEMENT LEARNING

Resumen de: US20260311074A1

An assembly line variant path planning system based on graph-based deep reinforcement learning includes an input layer, a knowledge and mechanism layer, a core processing module, an output layer, and an application and feedback layer. An assembly line variant process is modelled as a graph structure and a reward function that precisely matches a change propagation preference objective is designed. By using the input change propagation preference mathematical model as a training basis, a neural network model constructed based on graph-based deep reinforcement learning is repeatedly trained until a model output result is stabilized and converged, thereby intelligently identifying an optimal preliminary variant path. A key dimensional linkage skeleton for subsequent instantiated reconstruction is provided by this optimal path, ultimately enabling rapid virtual-physical mapping modeling of the entire assembly process and significantly reducing time for physical assembly line reverse modeling.

OPTICAL INFORMATION READING DEVICE

Nº publicación: US20260310918A1 08/10/2026

Solicitante:

KEYENCE CORP [JP]
Keyence Corporation

Resumen de: US20260310918A1

To suppress an increase in processing time due to a load of inference processing while improving reading accuracy by the inference processing of machine learning. An optical information reading device includes a processor including: an inference processing part that inputs a code image to a neural network and executes inference processing of generating an ideal image corresponding to the code image; and a decoding processing part that executes first decoding processing of decoding the code image and second decoding processing of decoding the ideal image generated by the inference processing part. The processor executes the inference processing and the first decoding processing in parallel, and executes the second decoding processing after completion of the inference processing.