-
公开(公告)号：EP3896594A1
公开(公告)日：2021-10-20
申请号：EP20201845.3
申请日：2020-10-14
发明人： LIU, Zhijie , WANG, Qi , FENG, Zhifan , FANG, Zhou , CHAI, Chunguang , ZHU, Yong
IPC分类号： G06F40/279 , G06F40/30
摘要： The present disclosure provides a method, a device, an equipment and a storage medium for mining a topic concept. The method includes: acquiring a plurality of candidate topic concepts based on a query; performing word segmentation on the plurality of candidate topic concepts and performing part-of-speech tagging on words obtained after performing the word segmentation, to obtain a part-of-speech sequence of each of the plurality of candidate topic concepts; and filtering the plurality of candidate topic concepts based on the part-of-speech sequence, to filter out a topic concept corresponding to a target part-of-speech sequence among the plurality of candidate topic concepts, in which a proportion of accurate topic concepts in the target part-of-speech sequence is lower than or equal to a first preset threshold, or a proportion of inaccurate topic concepts in the target part-of-speech sequence is higher than or equal to a second preset threshold. The present disclosure can reduce the labor cost required for mining the topic concept.
-
公开(公告)号：EP3866026A1
公开(公告)日：2021-08-18
申请号：EP20202345.3
申请日：2020-10-16
发明人： WANG, Qi , FENG, Zhifan , LIU, Zhijie , CHAI, Chunguang , ZHU, Yong
摘要： Embodiments of the present disclosure relate to a theme classification method based on multimodality, a device and a storage medium, more particularly to a field of a knowledge map. The method includes obtaining text information and non-text information of an object to be classified. The non-text information includes at least one of visual information and audio information. The method also includes determining an entity set of the text information based on a pre-established knowledge base, and then extracting a text feature of the object based on the text information and the entity set. The method also includes determining a theme classification of the object based on the text feature and a non-text feature of the object.
-
公开(公告)号：EP3709207A1
公开(公告)日：2020-09-16
申请号：EP20150895.9
申请日：2020-01-09
发明人： HUANG, Jianhui , QIAO, Min , HUANG, Pingping , ZHU, Yong , LYU, Yajuan , LI, Ying
摘要： Embodiments of the present disclosure disclose a visual question answering model, an electronic device and a storage medium. The visual question answering model includes an image encoder and a text encoder. The text encoder is configured to perform pooling on a word vector sequence of a question text inputted, so as to extract a semantic representation vector of the question text; and the image encoder is configured to extract an image feature of a given image in combination with the semantic representation vector. By processing a text vector through pooling, the embodiments according to the present disclosure ensure that model training efficiency is effectively improved on the premise of a small loss of prediction accuracy of the visual question answering model, and thus the model is beneficial to the use in engineering.
-
公开(公告)号：EP3686749A1
公开(公告)日：2020-07-29
申请号：EP20153635.6
申请日：2020-01-24
发明人： LI, Qian , SHI, Yabing , LIANG, Haijin , ZHANG, Yang , ZHU, Yong
摘要： Embodiments of the present disclosure provide to a method and a device for acquiring a data model in a knowledge graph, an apparatus and a storage medium. The method includes: receiving a knowledge entry describing a relationship between an entity and an object; determining a plurality of candidate object types of the object according to at least one of the entity, the relationship and the object; determining an object type for generating a data model that matches the knowledge entry from the plurality of candidate object types based on a preset rule; and generating the data model based at least on the object type.
-
公开(公告)号：EP3514702A1
公开(公告)日：2019-07-24
申请号：EP18215238.9
申请日：2018-12-21
发明人： FENG, Zhifan , LU, Chao , ZHU, Yong , LI, Ying
摘要： The present disclosure provides a text processing method and device based on ambiguous entity words. The method includes: obtaining (101) a context of a text to be disambiguated and at least two candidate entities represented by the text to be disambiguated; generating (102) a semantic vector of the context based on a trained word vector model; generating (103) a first entity vector of each of the at least two candidate entities based on a trained unsupervised neural network model; determining (104) a similarity between the context and each candidate entity; and determining (105) a target entity represented by the text to be disambiguated in the context. By the present disclosure, entity information of the text to be disambiguated is completely depicted, and accuracy disambiguation for the text to be disambiguated is improved.
-
6.发明公开
公开(公告)号：EP4152176A1
公开(公告)日：2023-03-22
申请号：EP22186185.9
申请日：2022-07-21
发明人： JIANG, Wenbin , LYU, Yajuan , ZHU, Yong , WU, Hua , WANG, Haifeng
IPC分类号： G06F16/332 , G06F16/33 , G06N3/04 , G06N3/06
摘要： The present disclosure provides a method for processing intelligent question-answering, an intelligent question-answering system, an electronic device and a storage medium, and relates to the field of artificial intelligence technologies, such as machine learning technologies, natural language processing technologies, or the like. An implementation includes: acquiring an input question and input data information; and based on the question, the data information and a plurality of knowledge bases, deciding an answer to the question by multilayer appreciation using a plurality of understanding module layers. The technical solution according to the present disclosure may effectively improve an intelligent question-answering efficiency, and enhances intelligence.
-
7.发明公开
公开(公告)号：EP4123516A1
公开(公告)日：2023-01-25
申请号：EP22184865.8
申请日：2022-07-14
发明人： JIANG, Wenbin , FENG, Zhifan , FENG, Xinwei , LYU, Yajuan , ZHU, Yong
IPC分类号： G06N3/08
摘要： The present disclosure provides a method and apparatus for acquiring a pre-trained model, an electronic device and a storage medium, and relates to the fields such as deep learning, natural language processing, knowledge graph and intelligent voice. The method may include: acquiring a pre-training task set composed of M pre-training tasks, M being a positive integer greater than 1, the pre-training tasks including: N question-answering tasks corresponding to different question-answering forms, N being a positive integer greater than 1 and less than or equal to M; and jointly pre-training the pre-trained model according to the M pre-training tasks. By use of the solutions of the present disclosure, resource consumption may be reduced, and time costs may be saved.
-
公开(公告)号：EP4044045A1
公开(公告)日：2022-08-17
申请号：EP20767703.0
申请日：2020-04-07
发明人： WANG, Quan , HUANG, Pingping , WANG, Haifeng , JIANG, Wenbin , LYU, Yajuan , ZHU, Yong , WU, Hua
IPC分类号： G06F16/36
摘要： structure context model.
19. An electronic device, comprising:
at least one processor; and
a memory, communicatively coupled to the at least one processor,
wherein the memory is configured to store instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute the method for generating the vector representation of the knowledge graph according to any one of claims 1-9.
20. A non-transitory computer readable storage medium having computer instructions stored thereon, wherein the computer instructions are configured to cause a computer to execute the method for generating the vector representation of the knowledge graph according to any one of claims 1-9.-
9.发明公开
公开(公告)号：EP3869358A1
公开(公告)日：2021-08-25
申请号：EP21157264.9
申请日：2021-02-16
发明人： SHI, Yabing , LI, Shuangjie , JIANG, Ye , ZHANG, Yang , ZHU, Yong
IPC分类号： G06F16/332 , G06F16/36
摘要： The disclosure discloses a method and an apparatus for recognizing an entity word, and relates to a field of information processing technologies in artificial intelligence technologies. The method includes: obtaining (101) an entity word category and a document to be recognized; generating (102) an entity word question based on the entity word category; segmenting (103) the document to be recognized to generate a plurality of candidate sentences; inputting (104) the entity word question and the plurality of candidate sentences into a question-answer model trained in advance to obtain an entity word recognizing result; and obtaining (105) an entity word set corresponding to the entity word question based on the entity word recognizing result. In this way, it is implemented that the method for recognizing the entity word is used in a wide range, the recall rate of the entity word and the intelligence of entity word recognition are improved.
-
10.发明公开
公开(公告)号：EP3859559A2
公开(公告)日：2021-08-04
申请号：EP21165606.1
申请日：2021-03-29
发明人： WANG, Qi , FENG, Zhifan , LIU, Zhijie , WANG, Siqi , CHAI, Chunguang , ZHU, Yong
摘要： A method, apparatus, device, storage medium, and computer program product for entity linking are disclosed. The method includes: acquiring a target text; determining at least one entity mention included in the target text; determining a candidate entity corresponding to each of the entity mention based on a preset knowledge base; determining a reference text of each of the candidate entity and determining additional feature information of each of the candidate entity; and determining an entity linking result based on the target text, each of the reference text, and each piece of the additional feature information.
-
-
-
-
-
-
-
-
-
搜索结果
32 条记录 (耗时 0.017 秒)
