-
1.发明公开
公开(公告)号：EP4462693A1
公开(公告)日：2024-11-13
申请号：EP23218640.3
申请日：2023-12-20
发明人： HE, Ziming , TONG, Fei , FLETCHER, Paul Nicholas
IPC分类号： H04B7/06 , G06N3/0455 , G06N3/0464 , H04L25/02
摘要： A computer-implemented method performed by a first electronic device for reducing a feedback overhead of beamforming in a wireless communication system, includes: transmitting a first data to a second electronic device; transmitting a data packet to the second electronic device, receiving a second data from the second electronic device; extracting a compressed steering matrix from the second data; obtain uncompressed steering matrix by using a décoder part of an autoencoder, based on the extracted compressed steering matrix; and transmitting, to the second electronic device, a third data via a radio signal beamformed based on the obtained uncompressed steering matrix.
-
公开(公告)号：EP4462523A1
公开(公告)日：2024-11-13
申请号：EP23172561.5
申请日：2023-05-10
摘要： Es wird ein Verfahren zur wenigstens teilweisen Zerlegung einer Batterie mittels einer Zerlegeeinheit vorgeschlagen, wobei die Zerlegeeinheit eine Erfassungseinheit zur optischen Erfassung eines Zerlegebereiches umfasst, und die Batterie innerhalb des Zerlegebereiches angeordnet ist. Das Verfahren ist gekennzeichnet dadurch, dass mittels der Zerlegeeinheit basierend auf durch die Erfassungseinheit optisch erfassten Daten und hinterlegten batteriespezifischen Daten ein oder mehrere kritische Bereiche des Zerlegebereiches ermittelt werden, innerhalb welchen keine Zerlegemaßnahmen durch die Zerlegeeinheit erfolgen.
Weiterhin betrifft die Erfindung eine Zerlegeeinheit, die zur Durchführung des Verfahrens ausgebildet ist.-
3.发明公开
公开(公告)号：EP4462383A1
公开(公告)日：2024-11-13
申请号：EP22918973.3
申请日：2022-09-19
发明人： KIM, Yong-Hyun , MA, Young-Gil , KIM, Dae-Won
摘要： Disclosed are an artificial intelligence-based method for detecting a lane using a spectrogram pattern, and an apparatus for same. The method for detecting a lane according to one embodiment of the present invention comprises the steps of: generating a time-frequency spectrogram pattern on the basis of a magnetic signal of a magnetic paint lane to which an alternating magnetic pattern has been applied; inputting the spectrogram pattern of the magnetic signal, detected in real time from the magnetic paint lane, to an artificial intelligence model trained using training data corresponding to the spectrogram pattern; and detecting the magnetic paint lane on the basis of an output value of the artificial intelligence model.
-
公开(公告)号：EP4462344A1
公开(公告)日：2024-11-13
申请号：EP24175543.8
申请日：2024-05-13
申请人： Rnwl Ltd
IPC分类号： G06Q40/08 , G06Q30/0601 , G06Q30/0251 , G06F21/62 , G06N20/00
摘要： There is provided a data processing system (100), for example configured as an insurance management system (1000). The data processing system (100) comprises a processing arrangement (110) and a user interface (130; 1200, 1400, 1500) for interacting with a given user (1106). The processing arrangement (110) is configured to gather user data comprising information; for example, the user data is used to determine at least one of a user profile, existing insurance policies, insurance preferences, and assets of the given user (140; 1106). The processing arrangement (110) is configured to parse the user data, error correct the user data when in error, augment the user data when sparse, store the user data in encrypted form in a data memory arrangement (150) and then generate a profile (1104) of the given user (1106) based on the user data stored in the data memory arrangement (150). The user interface (130; 1200, 1400, 1500) is configured to display the insurance profile of the given user (140; 1106), including details of the existing insurance policies and one or more user actions required for managing of the existing insurance policies. There is also provided a method for using the aforementioned data processing system (100; 1000) to manage insurance requirements for the given user (140; 1106).
-
公开(公告)号：EP4462316A1
公开(公告)日：2024-11-13
申请号：EP24170676.1
申请日：2024-04-17
摘要： Disclosed is a method comprising receiving a plurality of local growing neural gas models from a plurality of distributed trainers, wherein a local growing neural gas model of the plurality of local growing neural gas models represents a local state model of at least one radio access network node; and training a global growing neural gas model based on the plurality of local growing neural gas models, wherein the global growing neural gas model represents a global state model of a plurality of radio access network nodes.
-
公开(公告)号：EP4462314A1
公开(公告)日：2024-11-13
申请号：EP23759084.9
申请日：2023-02-16
发明人： WANG, Sihai , QIN, Cheng , YANG, Rui
IPC分类号： G06N3/08
摘要： An artificial intelligence algorithm model obtaining method and an apparatus, to select an appropriate artificial intelligence algorithm model for data, and may be used in various communication systems. The method includes: A network device determines N artificial intelligence algorithm models in M artificial intelligence algorithm models based on data feature information and M pieces of model feature information, and sends, to a terminal device, configuration information corresponding to at least one of the N artificial intelligence algorithm models, where the M pieces of model feature information correspond one-to-one to the M artificial intelligence algorithm models, the N artificial intelligence algorithm models are more suitable for processing data than remaining (M-N) artificial intelligence algorithm models of the M artificial intelligence algorithm models, an i th piece of model feature information in the M pieces of model feature information includes a feature of an i th artificial intelligence algorithm model, and the data feature information includes a feature of first data.
-
公开(公告)号：EP4462312A1
公开(公告)日：2024-11-13
申请号：EP23172163.0
申请日：2023-05-08
发明人： Klochkov, Yegor , Ton, Jean-Francois , Guo, Ruocheng , Liu, Yang , Li, Hang
摘要： A system for removing a concept from a trained neural network for executing a classification task, the system comprising: the trained neural network, wherein the trained neural network comprises a hidden layer; and a classifier applied at a layer of the hidden layer, wherein: the classifier defines a representation vector at the layer of the hidden layer, wherein the representation vector classifies instances of the concept and non-instances of the concept at the layer; the classifier defines a concept activation vector, wherein the concept activation vector is a normal vector to the representation vector and the concept activation vector comprises an adversarial penalty objective to reduce the instances of the concept at the layer; and a loss function of the trained neural network is optimised based on a downstream loss of the classification task and the adversarial penalty objective.
-
公开(公告)号：EP4462308A1
公开(公告)日：2024-11-13
申请号：EP24168419.0
申请日：2024-04-04
申请人： GOOGLE LLC
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a classification task on a data item. In particular, a system classifying an input data item using key and value embeddings of memory data items.
-
公开(公告)号：EP4462294A1
公开(公告)日：2024-11-13
申请号：EP23186680.7
申请日：2023-07-20
申请人： Featurespace Limited
发明人： EXCELL, David
摘要： A request-based variable is generated using data associated with a received request as input to a request-based variable generation model. In response to determining that using further data as further input to the model may alter the request-based variable, it is determined whether or not to retrieve the further data based on a comparison involving a data retrieval loss indicator and a data non-retrieval loss indicator. A decision associated with the request is made based on a determinative request-based variable. When the comparison indicates that the data retrieval loss outweighs the data non-retrieval loss, the determination is not to retrieve the further data and the request-based variable is used as the determinative request-based variable. When the comparison indicates that the data non-retrieval loss outweighs the data retrieval loss, a regenerated request-based variable is used as the determinative request-based variable.
-
公开(公告)号：EP4462282A1
公开(公告)日：2024-11-13
申请号：EP24175192.4
申请日：2024-05-10
发明人： CAICEDO RUEDA, Juan C. , QUACH, Alex , FONNEGRA, Ruben , VALI SANIAN, Mohammad , PAAVOLAINEN, Lassi , CHEN, Zitong
IPC分类号： G06F16/55 , G06F16/906 , G06N3/00
摘要： Decoupled encoder-decoder networks for image simulation and modification are described. An encoder network outputs feature representations of an input image of a biological sample, and a manipulation engine modifies the feature representations output by the encoder network by applying a variable associated with an experimental condition. A decoder network receives the modified feature representations from the manipulation engine and generates a simulated image by decoding the modified feature representations. The simulated image is a modified version of the input image that includes an estimated outcome of the experimental condition on the biological sample. The encoder network is trained separately from the decoder network, and the decoder network is adapted to the encoder network via at least one loss that is dependent on an output of the encoder network.
-
-
-
-
-
-
-
-
-
搜索结果
21165 条记录 (耗时 0.035 秒)
