-
1.发明公开
公开(公告)号：EP4300959A1
公开(公告)日：2024-01-03
申请号：EP22212075.0
申请日：2022-12-07
IPC分类号： H04N19/172 , H04N19/114 , G06T9/00
摘要： The present disclosure provides video frame processing method and apparatus, model training method and apparatus, a device and a storage medium, relates to a field of artificial intelligence, and in particular, to cloud computing, video processing, and medium cloud technology, and may be applied in an intelligent cloud scenario. The video frame processing method includes: acquiring (S101) a target characteristic corresponding to a current video frame in a video frame sequence to be encoded, in the case of the video frame sequence to be encoded satisfies a preset condition; inputting (S102) the target characteristic corresponding to the current video frame to a first target model, to obtain a first output result corresponding to the current video frame; and determining (S103) a first target group of pictures, GOP, length corresponding to the current video frame, based on the first output result corresponding to the current video frame.
-
2.发明公开
公开(公告)号：EP4300363A1
公开(公告)日：2024-01-03
申请号：EP22925241.6
申请日：2022-11-02
发明人： CHEN, Weihang , WANG, Haifeng , ZHANG, Yunfei , YUAN, Risheng , CHEN, Tianyu , LIU, Hongyu , HU, Xiaoguang , YU, Dianhai , MA, Yanjun
IPC分类号： G06N3/04
摘要： The present disclosure provides an operator processing method of a deep learning framework, which relates to a field of computer technology, especially in a field of artificial intelligence technology such as deep learning. The specific implementation scheme is: acquiring an operator to be processed, where the operator to be processed includes a template parameter independent of the deep learning framework and an operator kernel function; parsing, in response to receiving an input information for the operator to be processed, the template parameter by using the input information to obtain a plurality of complete template parameters related to the deep learning framework; and processing the operator kernel function according to the plurality of complete template parameters, to obtain an available operator for the deep learning framework. The present disclosure also provides an operator processing apparatus of a deep learning framework, an electronic device, and a storage medium.
-
3.发明公开
公开(公告)号：EP4290482A1
公开(公告)日：2023-12-13
申请号：EP23157994.7
申请日：2023-02-22
发明人： XIANG, Yubo , WANG, Jiayang , HE, Huihui , SHEN, Junyu , SU, Cuicong , ZHANG, Hongguang
IPC分类号： G06V30/412 , G06V30/414
摘要： A method and an apparatus of processing a text, an electronic device, a storage medium, and a program product, which relates to a field of an image processing technology, in particular to a field of computer vision technology. The method includes: determining similarities between a plurality of fields contained in a text image to be processed and a plurality of predetermined field names; determining, from the plurality of fields, a field having a similarity greater than a similarity threshold as a target field name; determining a target field value corresponding to the target field name from M remaining field among the plurality of fields other than the target field name, where M≥1; and outputting a correspondence between the target field name and the target field value.
-
公开(公告)号：EP4276822A1
公开(公告)日：2023-11-15
申请号：EP22198778.7
申请日：2022-09-29
发明人： ZHAO, Qingen
IPC分类号： G10L21/007 , G10L13/033 , G10L25/30
摘要： Provided are a method and an apparatus for processing audio, an electronic device and a storage medium. A specific implementation solution includes: obtaining a first target feature vector from original audio, where the first target feature vector is used for representing a phoneme feature of the original audio; obtaining a second target feature vector and a third target feature vector from audio to be transferred, where the second target feature vector is used for representing a style prosody feature of the audio to be transferred, and the third target feature vector is used for representing a speaker feature of the audio to be transferred; performing spectrogram decoding on the first target feature vector, the second target feature vector and the third target feature vector to obtain a target spectrogram feature; and converting the target spectrogram feature into target audio.
-
5.发明公开
公开(公告)号：EP4261819A1
公开(公告)日：2023-10-18
申请号：EP22826640.9
申请日：2022-07-27
发明人： WANG, Yipeng
摘要： The present disclosure provides an audio data processing method and apparatus, an electronic device, a computer-readable storage medium and a computer program product and relates to the field of artificial intelligence, in particular to an audio processing technology. An implementation solution is: obtaining human voice audio data to be adjusted and reference human voice audio data, wherein the reference human voice audio data and the human voice audio data to be adjusted are obtained based on the same text information; performing framing on the human voice audio data to be adjusted and the reference human voice audio data respectively so as to obtain a first audio frame set and a second audio frame set respectively; recognizing a pronunciation unit corresponding to each audio frame respectively; determining, based on a timestamp of each audio frame, a timestamp of each pronunciation unit in the human voice audio data to be adjusted and the reference human voice audio data respectively; and adjusting the timestamp of at least one pronunciation unit in the human voice audio data to be adjusted to make the timestamp of the pronunciation unit in the human voice audio data to be adjusted to be consistent with the timestamp of the corresponding pronunciation unit in the reference human voice audio data.
-
6.发明公开
公开(公告)号：EP4246310A1
公开(公告)日：2023-09-20
申请号：EP23161801.8
申请日：2023-03-14
发明人： LIU, Xiaohe
摘要： Provided are a method and apparatus for acquiring a random number for a blockchain, a device and a storage medium. The method includes: in a process of executing a business transaction request, calling (S 110) an oracle contract to generate a random number acquisition request; processing (S 120) the random number acquisition request through the oracle contract, and making at least two oracle nodes arranged outside the blockchain generate random factors based on private keys of the at least two oracle nodes; acquiring (S 130) the random factors fed back by the at least two oracle nodes through the oracle contract; aggregating (S 140) the random factors through the oracle contract to form an aggregation factor, and generating a random number according to the aggregation factor and an on-chain random algorithm; and feeding back (S 150) the random number to the business transaction request through the oracle contract.
-
公开(公告)号：EP4138047A3
公开(公告)日：2023-09-13
申请号：EP22217349.4
申请日：2022-12-30
发明人： He, Dongliang , Ding, Errui , Wang, Haifeng
IPC分类号： G06V20/40 , G06N3/02 , G06V10/44 , G06V10/50 , G06V10/82 , G06F16/783 , G06N3/0455 , G06N3/08 , G06N3/0464
摘要： The present disclosure provides a method of processing a video, a method of querying a video, and a method of training a video processing model, which relate to a field of artificial intelligence, in particular to fields of computer vision, video understanding and deep learning technologies, and may be applied to smart city, intelligent transportation and other scenarios. A specific implementation solution of the method of processing the video includes: extracting, for a video to be processed, a plurality of video features under a plurality of receptive fields; extracting a local feature of the video to be processed according to a video feature under a target receptive field in the plurality of receptive fields; obtaining a global feature of the video to be processed according to a video feature under a largest receptive field in the plurality of receptive fields; and merging the local feature and the global feature to obtain a target feature of the video to be processed.
-
8.发明公开
公开(公告)号：EP4224317A1
公开(公告)日：2023-08-09
申请号：EP22847523.2
申请日：2022-06-07
发明人： WANG, Shuaijian , LI, Shiyong , ZHANG, Henghua , LI, Panpan , HU, Zaibin , LUO, Baotong
IPC分类号： G06F9/455
摘要： The present disclosure provides a method for controlling a distributed operation system, an apparatus for controlling a distributed operation system, a device, a medium and a program product, which relate to a computer application technology field, and in particular to a distributed operation technology field. A specific implementation includes: for a first container carrying a first process, determining a current fault type of a failure in the first container in response to detecting that the first process is triggered to terminate based on the failure in the first container; and reconstructing the first container and restarting the first process based on the first container reconstructed in response to determining that the current fault type is consistent with a target fault type. In the present disclosure, for a fault type of a container which allows the container to be successfully reconstructed, the container will be reconstructed, while for a fault type of a container which does not allow the container to be successfully reconstructed, the container will not be reconstructed, so as to save system operation costs and meet operation requirements.
-
9.发明公开
公开(公告)号：EP4187504A8
公开(公告)日：2023-07-26
申请号：EP22190160.6
申请日：2022-08-12
发明人： LIU, Shanshan , QIAO, Meina , WU, Liang , LYU, Pengyuan , FAN, Sen , ZHANG, Chengquan , YAO, Kun
IPC分类号： G06V30/413 , G06V10/82
摘要： The present disclosure provides a method for training a text classification model, a method for recognizing text content and apparatuses thereof, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning and computer vision, and may be applied to scenarios such as optical character recognition or text recognition. The method for training includes: acquiring a set of to-be-trained images, the set of to-be-trained images including at least one sample image; determining predicted position information and predicted attribute information of each text line in each sample image based on each sample image; and training to obtain the text classification model, based on the annotation position information and the annotation attribute information of each text line in each sample image, and the predicted position information and the predicted attribute information of each text line in each sample image, and the text classification model is used to detect attribute information of each text line in an to-be-recognized image. The method improves the accuracy of training, so that when attribute information of a text line is determined based on the text classification model, the reliability of classification is improved.
-
公开(公告)号：EP4198734A3
公开(公告)日：2023-07-12
申请号：EP22207889.1
申请日：2022-11-16
发明人： PENG, Yang , FENG, Lei , CAO, Zhenxing , LIAO, Weida , LU, Huanan , CHEN, Yuzhen
摘要： A method and an apparatus for locating a fault information, an electronic device, and a storage medium are provided, relates to the field of computer technologies, and in particular, to the technical fields of information flow, intelligent search, and the like. A specific implementation solution includes: parsing error information of a target application to obtain version information and an error attribute of the target application; determining, based on the version information, a target mapping file corresponding to the error information; and determining a target location by utilizing the error attribute and the target mapping file, where the target location is used to determine a location of fault description content.
-
-
-
-
-
-
-
-
-
搜索结果
642 条记录 (耗时 0.022 秒)
