公开(公告)号：EP4513385A1

公开(公告)日：2025-02-26

申请号：EP24188708.2

申请日：2024-07-15

Applicant: BEIJING YOUZHUJU NETWORK TECHNOLOGY CO. LTD.

Inventor： Ren, Weiluo ,  Fu, Weizhong ,  Chen, Ji

IPC: G06N3/08 ,  G06N5/01 ,  G06N10/40 ,  G06N10/60

Abstract: The present disclosure relates to a method and apparatus for determining a relative energy between systems, an electronic device, a computer-readable storage medium, and a computer program product. The method (300) includes: for a chemical system, performing a plurality of iteration rounds using a neural network variational Monte Carlo method (310); acquiring a linear relationship between energy errors and energy variances, which are obtained in the plurality of iteration rounds (320); determining a first energy error at a position where the energy variance is zero based on the linear relationship (330); and determining the relative energy between the chemical system and a further system based on the first energy error (340). It can be seen that, since there is no need to wait for complete convergence of training in the solution, the required time is less, and the efficiency is higher.

公开(公告)号：EP4512345A1

公开(公告)日：2025-02-26

申请号：EP23792037.6

申请日：2023-03-21

Applicant: Ontact Health Co., Ltd.

Inventor： JUNG, Sung Hee ,  SHIM, Hack Joon ,  JEONG, Da Wun ,  CHOI, Annes

IPC: A61B8/08 ,  G06T7/11 ,  G06T7/00 ,  G06N3/08

Abstract: The present invention provides a method for providing information on an M-mode ultrasound image implemented by a processor and device using same, the method comprising the steps of: receiving an M-mode ultrasound image of a subject; segmenting a plurality of cardiac tomographic regions within the M-mode ultrasound image by using a segmentation model that is trained so as to segment the M-mode ultrasound image into a plurality of cardiac tomographic regions; and determining measurements for the plurality of segmented cardiac tomographic regions. In addition, the present invention provides a method for providing a user interface for providing information on an M-mode ultrasound image, which is a method for providing information on an M-mode ultrasound image implemented by a processor, wherein the method comprises the steps of: receiving an M-mode ultrasound image of a subject; segmenting a plurality of cardiac tomographic regions within the M-mode ultrasound image by using a first model that is trained so as to segment the M-mode ultrasound image into a plurality of cardiac tomographic regions by using the M-mode ultrasound image as an input; determining a diastolic phase and a systolic phase within the M-mode ultrasound image by using a second model that is trained so as to predict the diastolic phase and the systolic phase of the M-mode ultrasound image by means of using the M-mode ultrasound image as an input; and determining measurements for the plurality of cardiac tomographic regions that are segmented on the basis of the diastolic and systolic phases.

公开(公告)号：EP4511765A1

公开(公告)日：2025-02-26

申请号：EP22728849.5

申请日：2022-05-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： LECONTE, Louis ,  NGUYEN, Van Minh

IPC: G06N3/04 ,  G06N3/08

公开(公告)号：EP4478255A3

公开(公告)日：2025-02-26

申请号：EP24206566.2

申请日：2018-04-24

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： O'SHEA, Timothy James

IPC: G10L19/20 ,  G01R29/02 ,  G06N20/00 ,  G06N3/04 ,  G06N3/08 ,  H04W24/08 ,  G06N3/045 ,  G06N3/006 ,  G06N3/082 ,  G06N3/086 ,  H04B17/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned identification of radio frequency (RF) signals. One of the methods includes: determining an RF signal configured to be transmitted through an RF band of a communication medium; determining first classification information associated with the RF signal, including a representation of a characteristic of the RF signal or a characteristic of an environment in which the RF signal is communicated; using at least one machine-learning network to process the RF signal and generate second classification information as a prediction of the first classification information; calculating a measure of distance between the second classification information and the first classification information; and updating the at least one machine-learning network based on the measure of distance.

公开(公告)号：EP4508581A1

公开(公告)日：2025-02-19

申请号：EP23788963.9

申请日：2023-04-13

Applicant: C3.ai, Inc.

Inventor： HOLTAN, Timothy P. ,  LI, Qiwei ,  MANI, Shouvik ,  TRIPATHY, Suman

IPC: G06N20/00 ,  G06N3/08 ,  G06N3/0985

公开(公告)号：EP4047596B1

公开(公告)日：2025-02-19

申请号：EP22166641.5

申请日：2020-06-03

Inventor： SAINATH, Tara C. ,  PANG, Ruoming ,  RYBACH, David ,  HE, Yanzhang ,  PRABHAVALKAR, Rohit ,  WEI, Li ,  VISONTAI, Mirkó ,  LIANG, Qiao ,  STROHMAN, Trevor ,  WU, Yonghui ,  MCGRAW, Ian C. ,  CHIU, Chung-Cheng

IPC: G10L15/06 ,  G10L15/32 ,  G10L15/16 ,  G06N3/04 ,  G06N3/08

公开(公告)号：EP4507260A1

公开(公告)日：2025-02-12

申请号：EP23190208.1

申请日：2023-08-08

Applicant: Nokia Solutions and Networks Oy

Inventor： DROOGHAAG, Benoît ,  BOSTOEN, Tom

IPC: H04L41/0896 ,  G06N3/08 ,  G06N20/00 ,  H04L41/14 ,  H04Q11/00 ,  H04L41/16 ,  H04L41/142

Abstract: A computer-implemented method for selecting candidates end points,
the method comprising:
- providing a first training dataset identifying training candidate end points to be allocated a bandwidth increment for a short time period,
- providing a first training success list identifying successful training candidate end points to be allocated a bandwidth increment for a long time period, wherein the successful training candidate end points are a subset of the first training candidate end points;
- performing supervised training of a first success prediction model for predicting the first training success list from the first training dataset
- determining a first predicted list by implementing the first success prediction model on a first reservoir dataset identifying first potential candidate end points belonging to the fixed communications network wherein the first predicted list identifies candidates end points as a subset of the first potential candidate end points,
- selecting a first candidate list identifying first candidate end points to be allocated a bandwidth increment, wherein the first candidate end points belong to the fixed communications network,
wherein the first candidate list includes part or all of the first predicted list.

公开(公告)号：EP4504067A1

公开(公告)日：2025-02-12

申请号：EP23785283.5

申请日：2023-04-04

Applicant: Icahn School of Medicine at Mount Sinai

Inventor： VAID, Akhil ,  NADKARNI, Girish N. ,  GLICKSBERG, Benjamin S.

IPC: A61B8/14 ,  G06N3/08 ,  G16H50/20 ,  G16H50/30 ,  G16H50/70

公开(公告)号：EP4502921A1

公开(公告)日：2025-02-05

申请号：EP23806559.3

申请日：2023-03-01

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： WANG, Liqiang ,  CHANG, Renjie

IPC: G06T5/00 ,  G06T7/11 ,  G06T9/00 ,  G06N3/04 ,  G06N3/08

Abstract: The present application provides an image filtering method and apparatus and a device. The image filtering method comprises: obtaining an image to be filtered (S801); determining a neural network-based filter; according to a block division mode corresponding to the neural network-based filter, dividing said image to obtain N image blocks to be filtered, N being a positive integer (S802); and respectively filtering said N image blocks by using the neural network-based filter so as to obtain a filtered image (S803). The block division mode is a block division mode for image training used by the neural network-based filter, i.e., in embodiments of the present application, the block division mode of the neural network-based filter in actual use is consistent with the block division mode used in training, so that the neural network-based filter exerts optimal filtering performance, thereby improving the filtering effect of the image.

公开(公告)号：EP4502913A1

公开(公告)日：2025-02-05

申请号：EP22938613.1

申请日：2022-04-19

Applicant: LG Electronics Inc.

Inventor： KIM, Jaehong ,  CHOI, Heeyeon

IPC: G06Q50/06 ,  H02J3/00 ,  G06N3/08

Abstract: The present disclosure relates to an artificial intelligence device and method capable of predicting an amount of power consumption occurring in a home, can obtain power consumption data for pre-registered electronic devices, check whether there is a specific electronic device for which the power consumption data has not been obtained, and if there is a specific electronic device for which the power consumption data has not been obtained, obtain mixed power data consumed in a current home, classify the obtained mixed power data into a plurality of individual power data, extracts individual power data matching the specific electronic device, estimate power consumption data for the specific electronic device based on the extracted individual power data, and predict an amount of power consumption in a home based on power consumption data for all pre-registered electronic devices.