-
公开(公告)号：US20190220749A1
公开(公告)日：2019-07-18
申请号：US16236570
申请日：2018-12-30
Inventor： Zhifan FENG , Chao LU , Yong ZHU , Ying LI
CPC classification number: G06N3/088 , G06F17/278 , G06F17/2785 , G06N3/0454 , G06N5/02 , G06N5/022 , G06N20/00
Abstract: The present disclosure provides a text processing method and device based on ambiguous entity words. The method includes: obtaining a context of a text to be disambiguated and at least two candidate entities represented by the text to be disambiguated; generating a semantic vector of the context based on a trained word vector model; generating a first entity vector of each of the at least two candidate entities based on a trained unsupervised neural network model; determining a similarity between the context and each candidate entity; and determining a target entity represented by the text to be disambiguated in the context.
-
12.发明申请公开(公告)号：US20210319335A1
公开(公告)日：2021-10-14
申请号：US17037612
申请日：2020-09-29
Inventor： Wenbin JIANG , Huanyu ZHOU , Meng TIAN , Ying LI , Xinwei FENG , Xunchao SONG , Pengcheng YUAN , Yajuan LYU , Yong ZHU
Abstract: The present disclosure discloses a question analysis method, a device, a knowledge base question answering system and an electronic equipment. The method includes: analyzing a question to obtain N linearized sequences, N being an integer greater than 1; converting the N linearized sequences into N network topology maps; separately calculating a semantic matching degree of each of the N network topology maps to the question; and selecting a network topology map having a highest semantic matching degree to the question as a query graph of the question from the N network topology maps. According to the technology of the present disclosure, the query graph of the question can be obtained more accurately, and the accuracy of the question to the query graph is improved, thereby improving the accuracy of question analysis.
-
公开(公告)号：US20210216882A1
公开(公告)日：2021-07-15
申请号：US17025952
申请日：2020-09-18
Inventor： Fang HUANG , Shuangjie LI , Yabing SHI , Ye JIANG , Yang ZHANG , Yong ZHU
Abstract: A method and apparatus for generating a temporal knowledge graph, a device and a medium. An embodiment of the method comprises: acquiring corpus including time information; performing multivariate data extraction on the corpus, multivariate data including an entity pair, an entity relationship and a target time interval of the entity relationship, the target time interval being used to indicate a valid period of the entity relationship; and generating a temporal knowledge graph based on the entity pair, the entity relationship and the target time interval of the entity relationship.
-
公开(公告)号：US20210216712A1
公开(公告)日：2021-07-15
申请号：US17149185
申请日：2021-01-14
Inventor： Shu WANG , Kexin REN , Xiaohan ZHANG , Zhifan FENG , Yang ZHANG , Yong ZHU
IPC: G06F40/279 , G06F17/16 , G06F17/18
Abstract: A method and an apparatus for labelling a core entity, and a related electronic device are proposed. A character vector sequence, a first word vector sequence and an entity vector sequence corresponding to a target text are obtained by performing character vector mapping, word vector mapping and entity vector mapping are performed on the target text, to obtain 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 by encoding and decoding the target vector sequence. One or more core entities of the target text are determined based on the first probability and the second probability.
-
公开(公告)号：US20200293905A1
公开(公告)日：2020-09-17
申请号：US16665882
申请日：2019-10-28
Inventor： Jianhui HUANG , Min QIAO , Zhifan FENG , Pingping HUANG , Yong ZHU , Yajuan LYU , Ying LI
Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating a neural network. The method includes: acquiring a target neural network, the target neural network corresponding to a preset association relationship, and being configured to use two entity vectors corresponding to two entities in a target knowledge graph as an input, to determine whether an association relationship between the two entities corresponding to the inputted two entity vectors is the preset association relationship, the target neural network comprising a relational tensor predetermined for the preset association relationship; converting the relational tensor in the target neural network into a product of a target number of relationship matrices, and generating a candidate neural network comprising the target number of converted relationship matrices; and generating a resulting neural network using the candidate neural network.
-
Patent Agency Ranking
16.发明申请公开(公告)号：US20200257659A1
公开(公告)日：2020-08-13
申请号：US16692028
申请日：2019-11-22
Inventor： Yilin ZHANG , Tianxing YANG , Xunchao SONG , Yong ZHU
Abstract: Embodiments of the present disclosure relate to a method and apparatus for determining description information, an electronic device and a computer readable storage medium. The method includes: determining a feature representation of received query information. The method further includes determining an element representation matching the feature representation in an event element library, the element representation being generated on the basis of an event recorded in a knowledge base. In addition, the method further includes: acquiring description information of an event corresponding to the matching element representation from the knowledge base; and determining description information corresponding to the query information on the basis of the acquired description information. A technical solution according to the present disclosure may determine a processing method for decision-making work accurately and automatically, thereby significantly improving the working efficiency and providing more valuable references for users inside and outside the industry.
-
公开(公告)号：US20190220752A1
公开(公告)日：2019-07-18
申请号：US16213610
申请日：2018-12-07
Inventor： Ye XU , Zhifan FENG , Chao LU , Yang ZHANG , Zhou FANG , Shu WANG , Yong ZHU , Ying LI
IPC: G06N5/02 , G06N5/04 , G06N7/00 , G06F16/28 , G06F16/901 , G06F16/951 , G06F16/955 , G06F16/2458 , G06K9/62
CPC classification number: G06N5/022 , G06F16/2468 , G06F16/288 , G06F16/9024 , G06F16/951 , G06F16/955 , G06K9/6215 , G06K9/6276 , G06N5/04 , G06N7/005
Abstract: Embodiments of the disclosure disclose a method, apparatus, server, and storage medium for incorporating a structured entity, wherein the method for incorporating a structured entity can comprise: selecting a candidate entity associated with a to-be-incorporated structured entity from a knowledge graph, determining the to-be-incorporated structured entity being an associated entity based on prior attribute information of a category of the candidate entity and a preset model, merging the associated entity and the candidate entity, and incorporating the associated entity into the knowledge graph. The embodiments can select a candidate entity, and then integrate a preset model using prior knowledge, which can effectively improve the efficiency and accuracy in associating entities, and reduce the amount of calculation, to enable the structured entity to be simply and efficiently incorporated into the knowledge graph.
-
公开(公告)号：US20210383069A1
公开(公告)日：2021-12-09
申请号：US17117553
申请日：2020-12-10
Inventor： Zhijie LIU , Qi WANG , Zhifan FENG , Chunguang CHAI , Yong ZHU
IPC: G06F40/30 , G06F40/295 , G06F17/16
Abstract: A method, apparatus, device, and storage medium for linking an entity, relates to the technical fields of knowledge graph and deep learning are provided. The method may include: acquiring a target text; determining at least one entity mention included in the target text and a candidate entity corresponding to each entity mention; determining an embedding vector of each candidate entity based on the each candidate entity and a preset entity embedding vector determination model; determining context semantic information of the target text based on the target text and each embedding vector; determining type information of the at least one entity mention; and determining an entity linking result of the at least one entity mention, based on the each embedding vector, the context semantic information, and each type information.
-
公开(公告)号：US20210256051A1
公开(公告)日：2021-08-19
申请号：US17069410
申请日：2020-10-13
Inventor： Qi WANG , Zhifan FENG , Zhijie LIU , Chunguang CHAI , Yong ZHU
Abstract: A theme classification method based on multimodality is related 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：US20210216819A1
公开(公告)日：2021-07-15
申请号：US17149267
申请日：2021-01-14
Inventor： Wei HE , Shuangjie LI , Yabing SHI , Ye JIANG , Yang ZHANG , Yong ZHU
IPC: G06K9/62 , G06F40/205 , G06N20/00
Abstract: A method and an apparatus for extracting SPO triples, an electronic device, and a storage medium are related to the field of artificial intelligence technologies. The solution may include: inputting annotated training data into each of multiple extraction models; predicting SPO triples satisfying defined relations in the annotated training data through each of multiple extraction models; combining the predicted SPO triples corresponding to each of multiple extraction models; extracting SPO triples satisfying screening conditions from the combined SPO triples; mining SPO triples with missing annotations from the annotated training data based on the SPO triples satisfying screening conditions, in response to that the SPO triples satisfying screening conditions do not satisfy output conditions; supplementing the SPO triples with missing annotations into the annotated training data; repeating the inputting, predicting, combining, extracting, mining and supplementing until the SPO triples satisfying screening conditions satisfy the output conditions.
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.021 seconds)
