-
11.发明公开
公开(公告)号：EP4113354A2
公开(公告)日：2023-01-04
申请号：EP22185752.7
申请日：2022-07-19
发明人： LIU, Tongyang , WANG, Shu , CHANG, Wanli , ZHENG, Wei , FENG, Zhifan , CHAI, Chunguang , ZHU, Yong
IPC分类号： G06F40/103 , G06F40/117 , G06F40/216 , G06F40/30
摘要： A method for generating a pre-trained language model, includes: obtaining sample files; obtaining typography structure information and text information of the sample files by parsing the sample files; obtaining a plurality of task models of a pre-trained language model; obtaining a trained pre-trained language model by jointly training the pre-trained language model and the plurality of task models according to the typography structure information and the text information; and generating a target pre-trained language model by fine-tuning the trained pre-trained language model according to the typography structure information and the text information.
-
12.发明公开
公开(公告)号：EP4053751A1
公开(公告)日：2022-09-07
申请号：EP21201915.2
申请日：2021-10-11
发明人： HE, Feng , WANG, Qi , FENG, Zhifan , YANG, Hu , CHAI, Chunguang
摘要： The present disclosure discloses a method and apparatus for training a cross-modal retrieval model, a device and a storage medium, and relates to the field of computer technologies, and particularly to the field of artificial intelligence technologies, such as knowledge graph technologies, computer vision technologies, deep learning technologies, or the like. The method for training a cross-modal retrieval model includes: determining (101) similarity of a cross-modal sample pair according to the cross-modal sample pair, the cross-modal sample pair including a sample of a first modal and a sample of a second modal, and the first modal being different from the second modal; determining (102) a soft margin based on the similarity, and determining (102) a soft margin loss function based on the soft margin; and determining (103) a total loss function based on the soft margin loss function, and training (103) a cross-modal retrieval model according to the total loss function. With the present disclosure, a retrieval effect of the cross-modal retrieval model may be improved.
-
公开(公告)号：EP3945456A1
公开(公告)日：2022-02-02
申请号：EP21179704.8
申请日：2021-06-16
发明人： WANG, Qi , FENG, Zhifan , YANG, Hu , HE, Feng , CHAI, Chunguang , ZHU, Yong
IPC分类号： G06K9/00 , G06F16/71 , G06F16/732
摘要： The present disclosure discloses a video event recognition method and apparatus, an electronic device and a storage medium, and relates to the fields of knowledge graphs, deep learning and computer vision. The method may include: constructing a video event graph, each event in the video event graph including: M argument roles of the event and respective arguments of the argument roles, M being a positive integer greater than one; acquiring, for a to-be-recognized video, respective arguments of the M argument roles of a to-be-recognized event corresponding to the video; and selecting, according to the arguments acquired, an event from the video event graph as a recognized event corresponding to the video. Accurate and efficient video event recognition can be implemented by using the solution of the present disclosure.
-
公开(公告)号：EP3923591A1
公开(公告)日：2021-12-15
申请号：EP21170889.6
申请日：2021-04-28
发明人： YANG, Hu , WANG, Shu , ZHANG, Xiaohan , WANG, Qi , FENG, Zhifan , CHAI, Chunguang
IPC分类号： H04N21/439 , G06F16/74 , H04N21/44 , H04N21/462 , H04N21/845
摘要： The disclosure provides a method for processing a video, an electronic device, and a computer storage medium. The method includes: determining a plurality of first identifiers related to a first object based on a plurality of frames including the first object in a target video; determining a plurality of attribute values associated with the plurality of first identifiers based on a knowledge base related to the first object; determining a set of frames from the plurality of frames, in which one or more attribute values associated with one or more first identifiers determined from each one of the set of frames are predetermined values; and splitting the target video into a plurality of video clips based on positions of the set of frames in the plurality of frames.
-
15.发明公开
公开(公告)号：EP3859562A3
公开(公告)日：2021-09-29
申请号：EP21165605.3
申请日：2021-03-29
发明人： WANG, Shu , REN, Kexin , ZHANG, Xiaohan , FENG, Zhifan , CHAI, Chunguang , ZHU, Yong
IPC分类号： G06F16/78 , G06F16/735 , G06N3/08 , G06N5/02
摘要： A method, apparatus, electronic device, storage medium, and computer program product for generating information are disclosed. The method includes: acquiring a plurality of tag entity words from a target video, the tag entity words including a person entity word, a work entity word, a video category entity word, and a video core entity word, the video core entity word including an entity word for characterizing a content related to the target video; linking, for a tag entity word among the plurality of tag entity words, the tag entity word to a node of a preset knowledge graph; determining semantic information of the target video based on a linking result of each of the tag entity words; and structuring the semantic information of the target video based on a relationship between the node and an edge of the knowledge graph, to obtain structured semantic information of the target video.
-
公开(公告)号：EP3690672A1
公开(公告)日：2020-08-05
申请号：EP19210678.9
申请日：2019-11-21
发明人： XU, Ye , FENG, Zhifan , FANG, Zhou , ZHANG, Yang , ZHU, Yong
IPC分类号： G06F16/33 , G06F40/216
摘要： According to some embodiments of the present disclosure, a method, apparatus, device and medium for determining text relevance is provided. The method for determining text relevance may include: identifying, from a predefined knowledge base, a first set of knowledge elements associated with a first text and a second set of knowledge elements associated with a second text. The knowledge base includes a knowledge representation consist of knowledge elements. The method further includes determining knowledge element relevance between the first set of knowledge elements and the second set of knowledge elements, and determining text relevance between the second text and the first text based at least on the knowledge element relevance.
-
17.发明公开
公开(公告)号：EP4113354A3
公开(公告)日：2023-01-18
申请号：EP22185752.7
申请日：2022-07-19
发明人： LIU, Tongyang , WANG, Shu , CHANG, Wanli , ZHENG, Wei , FENG, Zhifan , CHAI, Chunguang , ZHU, Yong
IPC分类号： G06F40/216 , G06F40/30 , G06F40/117 , G06F40/137 , G06F40/289
摘要： A method for generating a pre-trained language model, includes: obtaining sample files; obtaining typography structure information and text information of the sample files by parsing the sample files; obtaining a plurality of task models of a pre-trained language model; obtaining a trained pre-trained language model by jointly training the pre-trained language model and the plurality of task models according to the typography structure information and the text information; and generating a target pre-trained language model by fine-tuning the trained pre-trained language model according to the typography structure information and the text information.
-
公开(公告)号：EP3862907A1
公开(公告)日：2021-08-11
申请号：EP21151484.9
申请日：2021-01-14
发明人： WANG, Shu , REN, Kexin , ZHANG, Xiaohan , FENG, Zhifan , ZHANG, Yang , ZHU, Yong
IPC分类号： G06F40/295
摘要： Embodiments of the disclosure provide a method and an apparatus for labelling a core entity, and a related electronic device. A character vector sequence, a first word vector sequence and an entity vector sequence corresponding to a target text are obtained (101) by performing character vector mapping, word vector mapping and entity vector mapping are performed on the target text, to obtain (102) a target vector sequence corresponding to the target text. A first probability that each character of the target text is a starting character of a core entity and a second probability that each character of the target text is an ending character of a core entity are determined (103) by encoding and decoding the target vector sequence. One or more core entities of the target text are determined (104) based on the first probability and the second probability.
-
19.发明公开
公开(公告)号：EP3859562A2
公开(公告)日：2021-08-04
申请号：EP21165605.3
申请日：2021-03-29
发明人： WANG, Shu , REN, Kexin , ZHANG, Xiaohan , FENG, Zhifan , CHAI, Chunguang , ZHU, Yong
IPC分类号： G06F16/78 , G06F16/735
摘要： A method, apparatus, electronic device, storage medium, and computer program product for generating information are disclosed. The method includes: acquiring a plurality of tag entity words from a target video, the tag entity words including a person entity word, a work entity word, a video category entity word, and a video core entity word, the video core entity word including an entity word for characterizing a content related to the target video; linking, for a tag entity word among the plurality of tag entity words, the tag entity word to a node of a preset knowledge graph; determining semantic information of the target video based on a linking result of each of the tag entity words; and structuring the semantic information of the target video based on a relationship between the node and an edge of the knowledge graph, to obtain structured semantic information of the target video.
-
-
-
-
-
-
-
-
搜索结果
19 条记录 (耗时 0.021 秒)
