Alerta

OBJECT SIMULATION USING REAL-WORLD ENVIRONMENTS

Resumen de: US20260203466A1

Systems and methods disclosed relate to generating training data. In one embodiment, the disclosure relates to systems and methods for generating training data to train a neural network to detect and classify objects. A simulator obtains 3D models of objects, and simulates 3D environments comprising the objects using physics-based simulations. The simulations may include applying real-world physical conditions, such as gravity, friction, and the like on the objects. The system may generate images of the simulations, and use the images to train a neural network to detect and classify the objects from images.

METHODS AND SYSTEMS FOR GENERATING RECOMMENDATIONS FOR COUNTERFACTUAL EXPLANATIONS OF COMPUTER ALERTS THAT ARE AUTOMATICALLY DETECTED BY A MACHINE LEARNING ALGORITHM

Resumen de: US20260203580A1

Methods and systems are described herein for generating recommendations for counterfactual explanations to computer alerts that are automatically detected by a machine learning algorithm. The methods and systems use an artificial neural network architecture that trains a hybrid classifier and autoencoder. For example, one model (or artificial neural network), which is a classifier, is trained to make predictions. A second model (or artificial neural network), which is an autoencoder, is trained to reconstruct its inputs. As the second model is trained to reconstruct its inputs means, the second model is implicitly trained to determine what in-sample data looks like. By combining these networks and train them jointly, the system generates predictions (e.g., counterfactual explanations) that are in-sample.

SYSTEMS AND METHODS FOR PRIVATE AUTHENTICATION WITH HELPER NETWORKS

Resumen de: US20260203014A1

0000 Helper neural network can play a role in augmenting authentication services that are based on neural network architectures. For example, helper networks are configured to operate as a gateway on identification information used to identify users, enroll users, and/or construct authentication models (e.g., embedding and/or prediction networks). Assuming, that both good and bad identification information samples are taken as part of identification information capture, the helper networks operate to filter out bad identification information prior to training, which prevents, for example, identification information that is valid but poorly captured from impacting identification, training, and/or prediction using various neural networks. Additionally, helper networks can also identify and prevent presentation attacks or submission of spoofed identification information as part of processing and/or validation.

SOLVING MULTIPLE TASKS SIMULTANEOUSLY USING CAPSULE NEURAL NETWORKS

Resumen de: US20260203576A1

0000 The invention provides a system and method for training artificial neural networks for solving multiple tasks simultaneously, wherein the artificial neural network comprises at least one capsule layer. The invention also provides a system and a method for solving multiple tasks simultaneously, wherein the artificial neural network comprises at least one capsule layer. The invention further provides additional connected aspects.

SYSTEMS AND METHODS FOR PRIVATE AUTHENTICATION WITH HELPER NETWORKS

Resumen de: US20260203013A1

0000 A set of measurable encrypted feature vectors can be derived from any biometric data and/or physical or logical user behavioral data, and then using an associated deep neural network (“DNN”) on the output (i.e., biometric feature vector and/or behavioral feature vectors, etc.) an authentication system can determine matches or execute searches on encrypted data. Behavioral or biometric encrypted feature vectors can be stored and/or used in conjunction with respective classifications, or in subsequent comparisons without fear of compromising the original data. In various embodiments, the original behavioral and/or biometric data is discarded responsive to generating the encrypted vectors. In other embodiment, helper networks can be used to filter identification inputs to improve the accuracy of the models that use encrypted inputs for classification.

METHOD AND DEVICE FOR DETERMINING LANE OF TRAVELING VEHICLE BY USING ARTIFICIAL NEURAL NETWORK, AND NAVIGATION DEVICE INCLUDING SAME

Resumen de: US20260204081A1

0000 An embodiment provides a lane determination apparatus for a driven vehicle using an artificial neural network comprising an image information collection module configured to acquire driving image information of a vehicle from at least one camera module installed in the vehicle, a pre-trained lane prediction artificial neural network module, with the driving image information as input information and with lane prediction information of the vehicle and confidence information for the lane prediction information as output information, an output information distribution calculation module configured to calculate a data distribution map of the output information to thereby generate a first data distribution map, a reference information distribution calculation module configured to collect reference information for actual traveling lane prediction information of the vehicle, to calculate a data distribution map of the reference information, and to thereby generate a second data distribution map and a confidence calibration module configured to update parameters of the artificial neural network module so as to reduce a difference between the first data distribution map and the second data distribution map based on the second data distribution map.

VIDEO PREDICTION USING ONE OR MORE NEURAL NETWORKS

Resumen de: US20260205558A1

0000 Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having one or more additional video frames.

METHOD AND APPARATUS FOR MICRO-NANO PARTICLE MORPHOLOGY DETECTION AND SLURRY-FORMING PERFORMANCE PREDICTION, AND DEVICE

Resumen de: WO2026149240A1

The present invention relates to the technical fields of energy materials and fluid engineering. Provided in the present invention are a method and apparatus for micro-nano particle morphology detection and slurry-forming performance prediction, and a device. The method comprises: preprocessing a slurry fuel sample, and collecting microscopic morphology images and particle size distribution data of particles in the slurry fuel sample, in order to form a raw dataset; on the basis of a region-based convolutional neural network algorithm, performing segmentation and feature extraction on the microscopic morphology images in the raw dataset, in order to identify particle morphology parameters in the microscopic morphology images; establishing a dynamic database including the particle morphology parameters and the particle size distribution data; on the basis of data in the dynamic database, using a grey correlation method to quantify the degree of correlation between the particle morphology parameters and corresponding slurry-forming performance metrics, and performing linear fitting; and constructing a slurry-forming performance prediction model, in order to obtain predicted slurry-forming performance values. The present invention can be directly applied to quality control and process optimization in slurry fuel production, thereby helping improve the production efficiency and the product quality consistency.

FREQUENCY AND AMPLITUDE REDUCTION REGULATION AND CONTROL METHOD AND SYSTEM FOR MULTI-SOURCE DYNAMIC DISTURBANCES IN DEEP TUNNELS

Resumen de: US20260202568A1

0000 Provided are a frequency and amplitude reduction regulation and control method and system for multi-source dynamic disturbances in deep tunnels. The method includes: acquiring first information and a wave-absorbing material dataset; determining mounting positions of sensors according to the first information, and acquiring second information, wherein the second information includes disturbance wave data collected by the sensors; constructing a first feature diagram according to the second information; determining third information according to the first feature diagram, wherein the third information includes types of disturbance waves; dividing the wave-absorbing material dataset according to the third information to obtain at least one divided wave-absorbing material dataset; and based on the divided wave-absorbing material dataset, training a neural network to obtain at least one trained neural network model, wherein the trained neural network model is configured to output wave-absorbing material mixture ratios corresponding to different types of disturbance waves.

METHOD AND APPARATUS FOR MODEL INFERENCE USING CRYPTOGRAPHIC NEURAL NETWORK

Resumen de: EP4776560A1

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.

ANOMALY DETECTION METHOD AND APPRATUS USING NEURAL NETWORK

Resumen de: KR20260109702A

0001a 뉴럴 네트워크를 이용하여 이상치를 탐지하는 전자 장치가 개시된다. 일 실시예에 따른 전자 장치는 메모리, 송수신기, 및 프로세서를 포함하고, 상기 프로세서는, 입력 이미지에 기초하여 산출된 심층 특징(feature) 및 상기 심층 특징의 평균에 기초하여 상기 입력 이미지에 대응하는 이상치를 탐지하도록 미리 학습된 뉴럴 네트워크 모델에 기초하여, 상기 입력 이미지의 이상치를 탐지할 수 있다.

An intelligent and precise analysis and guidance system and method for ideological and political education of college students

Resumen de: NL4001803A

The present invention relates to the technical field of educational informatization, and particularly relates to a precise analysis and guidance system and method for ideological and political education of college students. The system comprises a data acquisition layer, a data fusion layer, an intelligent analysis layer, and an application service layer connected in sequence. The system acquires full-dimensional data covering student family background, growth experience, on-campus teaching, student activities, and daily life. After cleaning, standardization, and knowledge graph construction, a student holographic profile is formed. Algorithms such as causal inference, graph neural networks, and long short-term memory networks are adopted to extract multi-dimensional ideological and political features, thereby realizing dynamic assessment, risk warning, and trend prediction of students’ ideological states. Finally, personalized ideological guidance schemes and visualized decision support are generated. The present invention can significantly improve the scientificity, timeliness, and precision of ideological and political work in colleges and universities.

ANOMALY DETECTION METHOD AND APPRATUS USING NEURAL NETWORK

Resumen de: KR20260109747A

0001a 뉴럴 네트워크를 이용하여 이상치를 탐지하는 전자 장치가 개시된다. 일 실시예에 따른 전자 장치는 메모리, 송수신기, 및 프로세서를 포함하고, 상기 프로세서는, 입력 이미지에 기초하여 산출된 심층 특징(feature) 및 상기 심층 특징의 평균에 기초하여 상기 입력 이미지에 대응하는 이상치를 탐지하도록 미리 학습된 뉴럴 네트워크 모델에 기초하여, 상기 입력 이미지의 이상치를 탐지할 수 있다.

Method and System for generating tissue staining image using neural network model

Resumen de: KR20260109227A

본 발명은 염색된 조직 이미지만으로 학습된 신경망 모델을 이용하여 염색되지 않은 조직 이미지로부터 염색된 조직 이미지를 생성하는 방법에 관한 것이다. 본 발명의 일 실시예에 따른 조직 염색 이미지 생성 방법은 염색된 조직이 제1 및 제2 파장의 광이 조사되는 각 환경에서 촬영된 제1 및 제2 이미지를 수집하는 단계, 상기 제1 및 제2 이미지로 구성된 훈련 데이터셋을 이용하여 신경망 모델을 학습시키는 단계, 타겟 조직이 상기 제1 파장의 광이 조사되는 환경에서 촬영된 무표지자 조직 이미지를 상기 학습된 신경망 모델에 입력하여 염색 조직 이미지를 생성하는 단계를 포함하되, 상기 제1 파장은 상기 조직의 염색에 사용된 염료의 흡수 스펙트럼 밖의 파장이며 상기 제2 파장은 상기 흡수 스펙트럼과 겹치는 파장인 것을 특징으로 한다.

METHOD AND DEVICE FOR SYNTHESIZING ADVERTISING TEXT INTO AN ORIGINAL VIDEO BASED ON VISUAL ATTENTION AND BACKGROUND COMPLEXITY OF THE ORIGINAL VIDEO USING A NEURAL NETWORK

Resumen de: KR102780102B1

The present invention relates to a server-based method which receives a sample image request for a photographed original image and advertisement information from a user terminal, determines an advertisement sentence position and a typography attribute for each frame by using an image analysis model and a sentence position determination model, generates a sample image obtained by synthesizing an advertisement sentence for each scene with the original image by typography, and provides the sample image to the user terminal. The server of the present invention improves production efficiency and image quality by optimizing the location of advertisement phrases through image analysis and automatic typography application.

APPARATUS AND METHOD FOR DETERMINING STATE OF PULMONARY CONGESTION BY USING ARTIFICIAL INTELLIGENCE ANALYSIS

Resumen de: US20260196241A1

Disclosed are an apparatus and a method for determining the state of pulmonary congestion by using artificial intelligence analysis. The apparatus for determining the state of pulmonary congestion by using artificial intelligence analysis, according to an embodiment, may comprise: a data reception unit that receives speech data from a user; a data preprocessing unit that extracts, from the received speech data, partial speech data corresponding to a portion of the speech data by using windowing processing, and converts the extracted partial speech data into a spectrogram; and a pulmonary congestion state determination unit that outputs, by using the spectrogram and a neural network-based pulmonary congestion state determination model, determination data including pulmonary congestion state information about the user.

METHOD, APPARATUS, AND MEDIUM FOR VISUAL DATA PROCESSING

Resumen de: US20260197449A1

Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: applying, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, a first filter in the NN-based model on an output of a synthesis transform in the NN-based model, at least one parameter of the first filter being configured based on one or more of the following: a first format for coding the visual data, the first format indicating a relationship between a size of a first component of the coded visual data and a size of a second component of the coded visual data, or a second format of output visual data from the conversion; and performing the conversion based on the applying

NEURAL NETWORK STRUCTURE SEARCH METHOD AND SYSTEM

Resumen de: WO2026145296A1

The present invention belongs to the technical field of collaboration between artificial intelligence and computer systems. Disclosed are a neural network structure search method and a system. The method comprises: deploying in a memory a network architecture template comprising a reconfigurable convolutional layer, wherein the convolutional layer consists of a plurality of FlexCell units, each FlexCell comprises a standard convolution operator and two depthwise separable convolution operators, and the degree of contribution of each operator is regulated by means of a trainable weight coefficient; using a graphics processing unit to perform three-dimensional hardware-aware encoding on the convolutional layer, so as to generate a structure definition matrix; and a central processing unit and the graphics processing unit collaboratively executing an improved genetic algorithm to perform parallel evaluation, crossover and mutation on candidate network structures in an encoding-based search space, so as to search out optimal network structure parameters. The present invention can automatically generate a network structure with few parameters and high precision, greatly improves search efficiency by means of heterogeneous computing collaboration, and is suitable for tasks such as image classification.

INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD

Resumen de: US20260197476A1

0000 Information processing with improved inferencing for machine learning is disclosed. In one example, a neural network is analyzed before inferencing is performed and generates control information for controlling compression and decoding of a feature amount processed by the neural network. Inferencing is performed using input data and the neural network and a processing result obtained by processing the feature amount is output as a computing result. The feature amount is compressed on the basis of the control information and recorded as a compressed feature amount. A decoder decodes the compressed feature amount temporarily recorded in the memory on the basis of the control information and outputs the decoded feature amount to the computing unit.

AUTOMATED MACROGRAPHIC SECTION ANALYSIS OF JOINTS

Resumen de: US20260195883A1

0000 A method for analyzing a cross-section of a joint includes: capturing, using a camera, an image of the cross-section of the joint; analyzing, using one or more neural networks, the image of the cross-section of the joint to classify two or more body segments that comprise the joint; isolating, using the one or more neural networks, the body segments of the joint; reassembling the body segments to form an assembled image of the joint; identifying key points in the assembled image of the joint; and measuring, using the key points, a value for a characteristic of the joint. A system for automated sectional analysis of a joint is also provided.

Method for Training a Neural Network for Determining Features of Objects for Object Tracking

Resumen de: US20260195584A1

0000 A method is for training a neural network for determining features of objects for object tracking. The method includes generating a training dataset with a plurality of training data elements. Each training data element has a first set of sensor data relating to a first state of an environment with a set of a plurality of objects and a second set of sensor data relating to a second state of the environment. In the second state, the positions of the objects have at least partially changed compared to the first state. The method also includes determining features of the objects by feeding the first set of sensor data to the neural network and determining features of the objects by feeding the second set of sensor data to the neural network. A loss is determined depending on the generated features, and the neural network is trained to reduce the loss.

DATA PROCESSING METHOD AND APPARATUS THEREFOR

Resumen de: US20260195400A1

0000 A data processing method is provided. The method is applied to image processing and includes: obtaining first data collected by an image sensor; and obtaining spectral information based on the first data by using a neural network model, where the neural network model includes an attention module, and the attention module is configured to determine an attention matrix based on input data, and perform an attention operation based on the attention matrix, where the attention matrix is obtained by performing a first fusion operation on correlation information between different channels of the input data and correlation information of the channels. In this application, a degree of correlation between the different channels and a degree of correlation of the channels may be fused, so that the attention matrix can model both correlation and particularity between the different channels, thereby improving accuracy of spectral signal reconstruction.

GENERATION OF MAGNETIC RESONANCE FINGERPRINTING PULSE SEQUENCES

Resumen de: US20260194611A1

Disclosed herein is a medical system (100, 300). The execution of machine executable instructions (120) causes a computational system (104) to repeatedly: generate (200) the random input vector; receive (202) a generated MRF pulse sequence (128) in response to inputting the random input vector into a GAN generator neural network (122); and append (204) the generated MRF pulse sequence to an MRF pulse sequence database (130). Execution of the machine executable instructions causes the computational system to: input (208) each generated MRF pulse sequence in the MRF pulse sequence database into a trained scoring algorithm (124) to assign the one or more score values to each generated MRF pulse sequence; and receive (210) a selected MRF pulse sequence (136) from the MRF pulse sequence database by applying a predetermined criterion (134) to the one or more score values of each generated MRF pulse sequence in the MRF pulse sequence database.

SPOKEN LANGUAGE UNDERSTANDING USING MACHINE LEARNING

Resumen de: US20260196210A1

0000 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating embeddings of spoken utterances. One of the methods includes obtaining audio data representing a spoken utterance; processing the audio data using an encoder neural network to generate an embedding of the spoken utterance; and processing the embedding of the spoken utterance using a prediction neural network to generate a prediction about the spoken utterance, the processing comprising: maintaining respective embeddings for a plurality of preceding spoken utterances; determining one or more embeddings of respective preceding spoken utterances that are relevant to generating the prediction about the spoken utterance; and processing (i) the embedding of the spoken utterance and (ii) the respective embeddings of the one or more determined preceding spoken utterances to generate the prediction about the spoken utterance.

IMAGE PROCESSING METHOD, SYSTEM AND APPARATUS, ELECTRONIC DEVICE, AND READABLE STORAGE MEDIUM

Nº publicación: US20260195854A1 09/07/2026

Solicitante:

VIVO MOBILE COMMUNICATION CO LTD [CN]
VIVO MOBILE COMMUNICATION CO., LTD.

Resumen de: US20260195854A1

0000 An image processing method, an image processing system, an image processing apparatus, an electronic device, and a non-transitory computer-readable storage medium are provided. The image processing method includes: calculating first data based on at least one padding pixel in an input image, a coefficient in one convolution kernel and in one-to-one correspondence with the at least one padding pixel, or an output bias corresponding to the one convolution kernel. The input image is an input image of a deconvolution layer in a neural network model. The image processing method further includes calculating second data based on at least one non-padding pixel in the input image or a coefficient in the one convolution kernel and in one-to-one correspondence with the at least one non-padding pixel. The image processing method also includes calculating a pixel value of one output pixel based on the first data and the second data.