Alerta

METHOD AND APPARATUS FOR DETERMINING BRAIN-INSPIRED APPLICATION TEST SUITE, ELECTRONIC DEVICE, AND STORAGE MEDIUM

Resumen de: US20260330245A1

0000 The present application discloses a method and an apparatus for determining a brain-inspired application test suite, an electronic device, and a storage medium. The method includes: performing feature analysis on each brain-inspired application included in an initial application test suite to obtain a data representation feature corresponding to each brain-inspired application; computing a computational overhead generated when each brain-inspired application is executed based on a spiking neural network paradigm; determining a data computation feature corresponding to each brain-inspired application according to the computational overhead; performing clustering processing on the brain-inspired applications in the initial application suite based on the data representation feature and the data computation feature, so that applications having similar features are merged into a same group, obtaining several groups whose main features are pairwise orthogonal; and constructing a representative spiking neural network according to a feature vector corresponding to each group.

METHOD AND APPARATUS FOR MODEL INFERENCE USING CRYPTOGRAPHIC NEURAL NETWORK

Resumen de: US20260330179A1

0000 Embodiments of this specification provide a method and an apparatus for model inference using a cryptographic neural network. The cryptographic neural network includes a plurality of linear layers. The method includes: receiving ciphertext data and key data of a user, where the key data is partial data of an evaluation key of a target format, and the evaluation key of the target format includes a plurality of extended ciphertexts; and inputting the ciphertext data into the cryptographic neural network for cryptographic processing, where the cryptographic processing includes: performing, at any target linear layer in the plurality of linear layers, a ciphertext rotation operation by using a first data part corresponding to a first ciphertext level t in the evaluation key, where the first data part includes only partial data of a single extended ciphertext.

METHOD FOR MONITORING POSTURE OF HYDRAULIC SUPPORTS ON FULLY MECHANIZED COAL MINING FACE AND ELECTRONIC DEVICE

Resumen de: AU2025230958A1

The present invention provides a fully mechanized coal mining face hydraulic support orientation monitoring method and system. The method comprises: once a hydraulic support completes a support moving action, obtaining a monitoring video frame image used for monitoring a fully mechanized coal mining face; on the basis of the monitoring video frame image, extracting a target image, wherein the target image is a local image in the monitoring video frame image comprising a hydraulic support base image and a push rod image; and inputting the target image to a convolutional neural network model obtained by pre-training to obtain a monitoring result, output by the convolutional neural network model, of whether a support loss anomaly has occurred in the hydraulic support in the monitoring video frame image, the convolutional neural network model being used for performing feature extraction on the target image and outputting the monitoring result corresponding to the feature on the basis of the extracted feature. Whether a support loss anomaly has occurred in the hydraulic support can be automatically and accurately recognized, and the problem of system hydraulic support orientation automatic adjustment is solved, thereby reducing the labor cost, and improving the system intelligence level.

FOLDING CUMULATIVE SUMMATION OPERATIONS USING MATRIX MULTIPLICATIONS

Resumen de: US20260329963A1

A processor-implemented method for reformulating cumulative summation operation in an artificial neural network includes receiving a set of program code. A target operation in the set of program code is identified. The target operation includes a cumulative summation operation. The target operation in the set of program code is reformulated using a first matrix multiplication operation to produce a reformulated target operation. An updated set of program code including the reformulated target operation is output.

METHOD AND DEVICE FOR AUTOMATICALLY CALCULATING WINDOW SET INFORMATION USING ARTIFICIAL NEURAL NETWORK

Resumen de: US20260330820A1

A device for automatically calculating window set information using artificial neural networks according to an embodiment comprises a pre-trained artificial neural network module calculating window set information having a first input information comprising image information as input information, and a window set information extracting window set characteristics from the image information as output information and a feature extractor for extracting a 1-1 feature map and a 1-2 feature map having different scale values for the image information, in the artificial neural network module calculating window set information, wherein the artificial neural network module calculating window set information is generating a 3-1 feature map and a 3-2 feature map by applying convolution to the 1-1 feature map and the 1-2 feature map, respectively, and then determining one of the 3-1 feature map and the 3-2 feature map as a final feature map based on a preset criteria, and then calculating the window set information based on the selected final feature map.

REAL-TIME ARTIFICIAL VENTILATION ADEQUACY EVALUATION FEEDBACK SYSTEM BASED ON IMAGE DATA, AND CONTROL METHOD THEREFOR

Resumen de: WO2026221322A1

A real-time artificial ventilation adequacy evaluation feedback system based on image data, according to one embodiment of the present invention, comprises: a photographing module, which photographs a patient and an practitioner so as to generate image data for artificial ventilation; an artificial intelligence module using a pre-learned artificial neural network to recognize movements performed by the practitioner and a response of the patient from the image data and evaluate the adequacy of the artificial ventilation; and an output module for providing real-time feedback about the artificial ventilation on the basis of the adequacy evaluation results.

Cross-Modal Contrastive Learning for Text-to-Image Generation based on Machine Learning Models

Resumen de: US20260330705A1

0000 A computer-implemented method includes receiving, by a computing device, a particular textual description of a scene. The method also includes applying a neural network for text-to-image generation to generate an output image rendition of the scene, the neural network having been trained to cause two image renditions associated with a same textual description to attract each other and two image renditions associated with different textual descriptions to repel each other based on mutual information between a plurality of corresponding pairs, wherein the plurality of corresponding pairs comprise an image-to-image pair and a text-to-image pair. The method further includes predicting the output image rendition of the scene.

SYSTEM AND METHOD FOR MITIGATING HALLUCINATIONS IN TRANSFORMER MODELS

Resumen de: US20260330202A1

0000 A system and method of mitigating hallucinations may include receiving an input data signal, comprising a sequence of input data segments, and processing the input data segments through an encoder of a transformer-based model, to generate a respective sequence of encoding vectors. The encoding vectors may be processed through a decoder of the transformer-based model, to generate a set of candidate sequences, each representing a first transformation of the input data signal. A deep Neural Network may be applied on the encoding vectors, to obtain a reference sequence, representing a second transformation of the input data signal. Each of the candidate sequences may be aligned with the reference sequence. For each candidate sequence of the set of candidate sequences, a respective probability score may be computed to indicate a quality of its respective alignment. A candidate sequence may be identified as an hallucination, based on its respective probability score.

VIDEO COMPRESSION USING NEURAL NETWORKS

Resumen de: US20260332790A1

Apparatuses, systems, and techniques to perform compression of video data using neural networks to facilitate video streaming, such as video conferencing. In at least one embodiment, a sender transmits to a receiver a key frame from video data and one or more keypoints identified by a neural network from said video data, and a receiver reconstructs video data using said key frame and one or more received keypoints.

IMAGE-BASED SEARCH METHOD

Resumen de: US20260330875A1

An image-based search method receives a search input from a user that describes one or more attributes associated with at least one object. The search input is interpreted by applying system attentions and applying a trained neural network that is trained on a training set of syntactical elements and images. A vector is generated based on the interpretation. Images, which may comprise segments of videos, are interpreted by applying system attentions and the trained neural network. The interpretation is applied to generate vectors that correspond to patterns of pixels in the images. The vector associated with the search input is compared to the vectors corresponding to the images and images are selected based on the results of the vector comparisons. Representations of the selected images are provided to the user.

SYSTEM FOR IN-SITU MONITORING AND CONTROL USING SENSOR FUSION AND MACHINE LEARNING

Resumen de: WO2026218095A1

The described technology pertains to a system for monitoring and controlling industrial or manufacturing processes, including additive manufacturing processes such as laser powder bed fusion. A sensor subsystem captures process data from at least one sensor, and, in some embodiments, contextual process data is also used. A defect monitoring subsystem comprises a sensor fusion module that fuses the captured data into a unified representation using a neural-network-based data pipeline with variational autoencoder models, and a decision-making module that generates a defect classification output and a defect probability score, and employs a defect detection dictionary to generate a defect detection indication. A process control subsystem may dynamically adjust one or more process parameters based on outputs of the defect monitoring subsystem, and a sensor simulation subsystem may validate proposed control parameter changes by generating synthetic sensor signals.

DEVICE AND METHOD FOR UPSCALING A FEATURE MAP OF AN IMAGE

Resumen de: EP4826677A1

0001 Computer-implemented method for upsampling a feature map (F) of an image (x), the method comprising: • Obtaining the image (x) and the feature map (F); • Augmenting the image (x) with respective representations (c) of coordinates of pixels of the image, thereby creating an augmented image (au); • Providing the augmented image (au) as input to a neural network (61), wherein the neural network (61) comprises at least one cross-attention layer (CA) that uses the augmented image (au) or a representation (r) thereof as query input and the feature map (F) as key input; • Providing an output (o) of the neural network (60) as upsampled feature map, wherein the output (o) of the neural network (60) is based on an output of the cross-attention layer (CA).

System and method for angiographic dose reduction using machine learning with a concordance metric

Resumen de: GB2645395A

Methods, systems, and computer readable media are provided for reduced-dose angiography using machine learning (e.g., deep learning) with a concordance metric indicating a degree of similarity between an estimated segmentation of angiographic images generated by a machine learning model and segmented benchmark angiographic images provided as inputs to the machine learning model. Briefly, techniques described herein may use a neural network trained to conserve/preserve angiographic image quality while reducing the angiographic dose of potentially harmful chemical contrast and/or x-ray radiation by employing a concordance metric.

NEURAL NETWORK AUDIT ENGINE

Resumen de: WO2025128327A1

A method for auditing neural network performance may include receiving a first set of input data for the neural network and training the neural network. The method may further include updating an audit model of the neural network based on the training of the neural network and inputting, to the neural network the first set of input data. A first set of output data associated with the first set of input data may be received from the neural network, and an indication of one or more characteristics of the neural network that impacted the first set of output data may be generated based on the updated audit model of the neural network, the first set of input data, and the first set of output data.

COMPILER FOR NEURAL ACCELERATOR

Resumen de: US20260319769A1

A compiler of a computing device is described that identifies a sequence of neural network models frequently invoked by an application of the computing device, compiles the models in that sequence, and loads a static random access memory (SRAM) of a hardware accelerator with the compiled models only when the same compiled models-from another, but same, sequence that was previously invoked-are not already present in the SRAM. This prevents unnecessary reloading of compiled models into the SRAM, thereby increasing runtime speed and conserving computational energy.

SECURITY OPERATIONS OF PARKED VEHICLES

Resumen de: US20260322951A1

0000 Systems, methods and apparatus of vehicle security operations during parking. For example, a vehicle includes: a proximity sensor configured to detect presence of an object approaching the vehicle when the vehicle is in a parking state; at least one camera configured to monitor surroundings of the vehicle when the vehicle is in the parking state; and an artificial neural network configured to extract identification information of the object from images generated by the camera and determine a security classification of the presence of the object. The identification information is stored in the vehicle and/or transmitted to a server or a mobile device, in response to the security classification being in a predefined category.

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.

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.

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

Nº publicación: US20260319474A1 15/10/2026

Solicitante:

DN SOLUTIONS CO LTD [KR]
DN SOLUTIONS CO., LTD.

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.