Alerta

NEURAL NETWORKS FOR CHANGING CHARACTERISTICS OF VOCALS

Absstract of: EP4715678A2

A messaging system for audio character type swapping. Methods of audio character type swapping include receiving input audio data having a first characteristic and transforming the input audio data to an input image where the input image represents the frequencies and intensities of the audio. The methods further include processing the input image using a convolutional neural network (CNN) to generate an output image and transforming the output image to output audio data, the output audio data having a second characteristic. The input audio and output audio may include vocals. The first characteristics may indicate a male voice and the second characteristics may indicate a female voice. The CNN is trained together with another CNN that changes input audio having the second characteristic to audio having the first characteristic. The CNNs are trained using discriminator CNNs that determine whether audio has a first characteristic or a second characteristic.

INFORMATION GENERATION METHOD AND RELATED APPARATUS

Absstract of: EP4715669A1

0001 Embodiments of this application disclose an information generation method and a related apparatus. The method includes: A second device receives a first message and a third message, and sends a second message to a first device. The first message indicates all or a part of a first generator, the third message indicates all or a part of a third generator, an input supported by the first generator includes first information of a first type, an input supported by the third generator includes fourth information of the first type, and the first generator and the third generator are configured to train a neural network corresponding to a second generator; and the second message indicates all or a part of the second generator, and an input supported by the second generator includes the first information and the fourth information. According to embodiments of this application, information collected in a real scenario may be used to train a generation model, to implement communication-assisted detection and detection-assisted communication, so that a communication network develops towards a more intelligent and adaptive direction.

UNSUPERVISED PRE-TRAINING OF NEURAL NETWORKS USING GENERATIVE MODELS

Absstract of: US20260080214A1

0000 In various examples, systems and methods are disclosed relating to generating a response from image and/or video input for image/video-based artificial intelligence (AI) systems and applications. Systems and methods are disclosed for a first model (e.g., a teacher model) distilling its knowledge to a second model (a student model). The second model receives a downstream image in a downstream task and generates at least one feature. The first model generates first features corresponding to an image which can be a real image or a synthetic image. The second model generates second features using the image as an input to the second model. Loss with respect to first features is determined. The second model is updated using the loss.

PRETRAINING FRAMEWORK FOR NEURAL NETWORKS

Absstract of: US20260080533A1

0000 Apparatuses, systems, and techniques to indicate an extent, to which text corresponds to one or more images. In at least one embodiment, an extent to which text corresponds to one or more images is indicated using one or more neural networks and used to train the one or more neural networks.

CONTROL METHOD AND CONTROL APPARATUS OF BROADCAST MONITORING SYSTEM, COMPUTER DEVICE AND COMPUTER STORAGE MEDIUM

Absstract of: US20260080561A1

The present disclosure provides a control method of a broadcast monitoring system, a control apparatus of a broadcast monitoring system, a computer device, and a computer storage medium, and belongs to the field of image recognition and terminal broadcast monitoring. The control method of a broadcast monitoring system includes: obtaining a detected image; performing gaze recognition on the detected image through a pre-trained target neural network model, to obtain a recognition result of the detected image; and sending the recognition result to a terminal, so that the terminal determines a display state based on at least the recognition result.

DATA PROCESSING METHOD AND APPARATUS

Absstract of: US20260080675A1

0000 A data processing method is applied to image processing. The method includes: obtaining a first image and a second image, where the first image and the second image include text; obtaining an image feature of the first image and an image feature of the second image through a first neural network; obtaining, through a second neural network, a text feature of text included in the first image and a text feature of text included in the second image; performing fusion on a first feature representation and a third feature representation to obtain a first target feature representation; performing fusion on a second feature representation and a fourth feature representation to obtain a second target feature representation; determining a loss based on a relationship between the first target feature representation and the second target feature representation; and updating the first neural network based on the loss.

GEOMETRICALLY ACCURATE IMPLICIT SCENE REPRESENTATION

Absstract of: US20260080619A1

0000 The present disclosure relates to the geometrically accurate reconstruction of a scene based on an implicit representation provided by a neural network. A method of reconstructing an environment of at least one camera device can include capturing by the at least one camera device a plurality of images of an environment of the at least one camera device. The method can also include obtaining an implicit representation of the environment based on the plurality of images by means of a neural network and reconstructing the environment based on the implicit representation, including reconstructing at least one object of the environment having a flat surface. The implicit representation is obtained based on an objective function of the neural network comprising a regularization term obtained based on Singular Value Decomposition.

METHOD AND SYSTEM FOR ANALYZING PATHOLOGICAL IMAGES BASED ON MAGNIFICATION-ALIGNED TRANSFORMER (MAT)

Absstract of: US20260080696A1

A method for analyzing pathological images based on a magnification-aligned transformer (MAT) is provided, in which a pathological image dataset is identified and segmented to obtain pathological image patches; the pathological image patches is screened to obtain a patch set; an MAT classification network model including a self-supervised magnification alignment module and a global-local Transformer classification module is constructed; the MAT classification network model is trained for self-supervised magnification alignment using the patch set in the self-supervised magnification alignment module; the MAT classification network model is further trained using a convolutional neural network (CNN)-transformer; and a pathological image classification prediction result is obtained using the trained MAT classification network model. A system for implementing such method is also provided.

GENERATIVE NEURAL NETWORK SYSTEMS FOR GENERATING INSTRUCTION SEQUENCES TO CONTROL AN AGENT PERFORMING A TASK

Absstract of: US20260080207A1

A generative adversarial neural network system to provide a sequence of actions for performing a task. The system comprises a reinforcement learning neural network subsystem coupled to a simulator and a discriminator neural network. The reinforcement learning neural network subsystem includes a policy recurrent neural network to, at each of a sequence of time steps, select one or more actions to be performed according to an action selection policy, each action comprising one or more control commands for a simulator. The simulator is configured to implement the control commands for the time steps to generate a simulator output. The discriminator neural network is configured to discriminate between the simulator output and training data, to provide a reward signal for the reinforcement learning. The simulator may be non-differentiable simulator, for example a computer program to produce an image or audio waveform or a program to control a robot or vehicle.

METHOD, SYSTEM, AND COMPUTER-READABLE RECORDING MEDIUM FOR DETERMINATION OF ARTHRITIS GRADE USING PLURALITY OF ARTIFICIAL NEURAL MODELS

Absstract of: WO2026059148A1

The present invention relates to a method, a system, and a computer-readable recording medium for determination of an arthritis grade using a plurality of artificial neural models, wherein a first model corresponding to a CNN-based artificial neural network model and a third model corresponding to a transformer-based artificial neural network model are trained through training data corresponding to X-ray images labeled in a first manner of labeling with a low arthritis grade, a second model corresponding to a CNN-based artificial neural network model and a fourth model corresponding to a transformer-based artificial neural network model are trained through training data corresponding to X-ray images labeled in a second manner of labeling with a high arthritis grade, and the arthritis grade for an X-ray image is determined using the first model, the second model, the third model, and the fourth model to diagnose the arthritis grade while implementing a process in which medical staff performs overall/local determination and optimistic/pessimistic determination of the X-ray image at an actual medical site.

MULTI-HARDWARE ENERGY-CONSUMPTION-ORIENTED CHANNEL PRUNING METHOD AND RELATED PRODUCT

Absstract of: US20260080249A1

0000 A multi-hardware energy-consumption-oriented channel pruning method and a related product. The method includes: ranking importance of a filter in a to-be-pruned convolutional neural network (CNN) model by using a feature distribution discrepancy (FDD) evaluation model based on a feature distribution of an original network model, and deleting a filter with a lowest importance ranking to generate a candidate first pruning model; determining an energy consumption of the candidate first pruning model by using an energy consumption estimation model based on actual measured data; performing trade-off processing on importance of a filter in the candidate first pruning model and the energy consumption of the candidate first pruning model by using a multi-objective evolutionary solving model, and obtaining a pruning scheme corresponding to each hardware device; and pruning the to-be-pruned CNN model by using the pruning scheme, and obtaining a second pruning model corresponding to each hardware device.

Weld seam assessment

Absstract of: AU2025223879A1

Abstract 5 Computer-implemented method and system for assessing a non-destructive ultrasonic test on a plastic pipe weld, including the following steps: • receiving an ultrasound scan file by way of a server, 10 • a computing unit analyzing the ultrasound scan file based on predefined criteria, wherein the computing unit comprises a neural network, • the computing unit assessing the ultrasound scan file based on the predefined criteria. Figure 1 5 Abstract Computer-implemented method and system for assessing a non-destructive ultrasonic test on a plastic pipe weld, including the following steps: 10 receiving an ultrasound scan file by way of a server, a computing unit analyzing the ultrasound scan file based on predefined criteria, wherein the computing unit comprises a neural network, the computing unit assessing the ultrasound scan file based on the predefined criteria. Figure 1 ug b s t r a c t u g 100% CR USSD 100% VISUAL ? Fig. 1 ug u g % % ?

DOMAIN-AWARE NEUROSYMBOLIC AGENTS FOR IMPROVING PROBLEM-SOLVING ACCURACY AND CONSISTENCY

Absstract of: US20260080313A1

A system receives domain specific questions from users and answers them. The system stores domain specific information comprising domain specific facts and domain specific programs. The system receives an input request to perform a domain specific task for the particular domain. The system provides the input request to a machine learning model trained to predict a score indicating whether the input request should be processed by a symbolic processor or by a neural network. If the score predicted by the machine learning model indicates that the input request should be processed by the symbolic processor, the system determines whether a stored domain specific program can solve the input request. If none of the stored domain specific programs can solve the input request, the system generates a new program for solving the input request using a machine learning based language model and the set of domain specific facts.

SYSTEM AND METHOD FOR A COGNITIVIE ARCHITECTURE UTILIZED IN MANUFACTURING

Absstract of: US20260079456A1

A computer-implemented method includes receiving, at a neural network, input data indicating one or more tasks associated with production, wherein the neural network is integrated with cognitive architecture that includes an imaginal memory buffer, utilizing the input data indicating one or more tasks with one or more production rule sets associated with an expert decision, obtain goal data indicating the expert decision utilizing imaginal memory buffer, selecting, from the imaginal memory buffer, one or more sectors associated with goal data indicating the novice decision, goal data indicating the intermediate decision, and goal data indicating the expert decision to obtain data indicating decision-making results, and in response to meeting a convergence threshold utilizing the data indicating decision-making results, outputting a simulation associated with a recommendation indicating information associated with at least the input data indicating one or more tasks associated with production.

SYSTEMS AND METHODS FOR VIDEO-LANGUAGE NEURAL NETWORKS

Absstract of: US20260080681A1

0000 Embodiments described herein provide a vision-language neural network framework that outputs a text response to a user text query relating to the media content of the video input. Specifically, the vision-language neural network may comprise (1) a vision encoder (ViT) transforming each frame input from the video input into a set of tokens, (2) a frame-level tokenizer to reduce the number of tokens, (3) a temporal encoder to build video-level token representations, and (4) an autoregressive LLM generating a text output based on such video tokens and text prompt tokens.

IMAGE INSPECTION APPARATUS AND IMAGE INSPECTION METHOD

Absstract of: US20260080529A1

An image inspection apparatus includes a learned neural network storage storing a neural network that previously learns weighting factors between input, intermediate and output layers, and an inferer determining failure/no-failure of a workpiece and classify the workpiece to classes based on an image of the workpiece. The inferer performs first and second inferences. In the first inference, the inferer determines failure/no-failure of the workpiece based on failure/no-failure feature quantities that are obtained by providing the workpiece image to the neural network and a failure/no-failure determination boundary. In the second inference, the inferer define a classification boundary to be used to classify an inspection workpiece to the classes in a feature quantity space of the neural network based on classification feature quantities that represent the different-type classification workpiece images, and classifies a workpiece to the classes based on classification feature quantities of an image of the workpiece and the classification boundary.

IMAGE PROCESSING DEVICE AND METHOD USING ARTIFICIAL NEURAL NETWORK MODEL

Absstract of: US20260080569A1

0000 As one aspect disclosed herein, an image processing method may be proposed. The method is executed in an electronic device comprising one or more processors and one or more memories for storing instructions to be executed by the one or more processors, and may comprise the steps of: acquiring a plurality of mixed images of a sample including a plurality of biological molecules; and generating unmixed images of at least one of the plurality of biological molecules from the plurality of mixed images by using an unmixing matrix. The value of at least one element included in the unmixing matrix may be determined on the basis of artificial neural network model training.

MULTI-TASK REAL-TIME INFERENCE SCHEDULING SYSTEM MACHINE TOOL AND METHOD THEREOF

Nº publicación: EP4711869A1 18/03/2026

Applicant:

DN SOLUTIONS CO LTD [KR]
DN Solutions Co., Ltd

Absstract of: EP4711869A1

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.