-
1.发明公开
公开(公告)号：EP3822875A2
公开(公告)日：2021-05-19
申请号：EP21163447.2
申请日：2021-03-18
发明人： WANG, Haiwei , WANG, Haifeng , HE, Wei , LI, Ying , ZHU, Yong , WANG, Jie
IPC分类号： G06Q10/00
摘要： A method and apparatus for outputting information, a device, a storage medium, and a computer program product are provided. An implementation of the method may include: acquiring knowledge data from at least one data source; acquiring information related to at least one user and a preset entity set; determining an entity, metadata of the entity and a relationship between entities, based on the related information, the knowledge data and the preset entity set; creating a knowledge graph based on the entity, the metadata and the relationship; and outputting the knowledge graph.
-
公开(公告)号：EP4131024A1
公开(公告)日：2023-02-08
申请号：EP22191894.9
申请日：2022-08-24
发明人： GAN, Jingru , WANG, Haiwei , LUO, Jinchang , CHEN, Kunbin , HE, Wei , WANG, Shuhui
摘要： A method for extracting information, includes: obtaining an information stream comprising text and an image; generating, according to the text, embedded representations of textual entity mentions and a textual similarity matrix of the textual entity mentions and candidate textual entities; generating, according to the image, embedded representations of image entity mentions and an image similarity matrix of the image entity mentions and candidate image entities; and determining, based on an optimal transport, target textual entities of the textual entity mentions and target image entities of the image entity mentions according to the embedded representations of the textual entity mentions, the embedded representations of the image entity mentions, the textual similarity matrix and the image similarity matrix.
-
公开(公告)号：EP3961426A3
公开(公告)日：2022-06-29
申请号：EP21218467.5
申请日：2021-12-31
发明人： XU, Wei , XIA, Xiaoling , HE, Bolei , CHEN, Kunbin , LIU, Zhun , HE, Wei
IPC分类号： G06F16/35
摘要： The present disclosure provides a method and apparatus of recommending a document, a device, a medium, and a product, relating to fields of intelligent recommendation, deep learning etc. The method of recommending a document includes: acquiring a document operated by a user, as a reference document; determining, from a plurality of initial documents, at least one candidate document for the reference document, wherein a document content of each candidate document is associated with a document content of the reference document, based on preset knowledge system data; and recommending a target document in the at least one candidate document to the user, the target document including a document that the user is currently interested in and a document that the user is interested in after a preset time period.
-
公开(公告)号：EP3961426A2
公开(公告)日：2022-03-02
申请号：EP21218467.5
申请日：2021-12-31
发明人： XU, Wei , XIA, Xiaoling , HE, Bolei , CHEN, Kunbin , LIU, Zhun , HE, Wei
IPC分类号： G06F16/35
摘要： The present disclosure provides a method and apparatus of recommending a document, a device, a medium, and a product, relating to fields of intelligent recommendation, deep learning etc. The method of recommending a document includes: acquiring a document operated by a user, as a reference document; determining, from a plurality of initial documents, at least one candidate document for the reference document, wherein a document content of each candidate document is associated with a document content of the reference document, based on preset knowledge system data; and recommending a target document in the at least one candidate document to the user, the target document including a document that the user is currently interested in and a document that the user is interested in after a preset time period.
-
5.发明公开
公开(公告)号：EP4116884A3
公开(公告)日：2023-05-24
申请号：EP22208688.6
申请日：2022-11-22
发明人： LUO, Jinchang , WANG, Haiwei , BU, Junzhao , CHEN, Kunbin , HE, Wei
IPC分类号： G06N5/022 , G06N3/09 , G06N5/04 , G06N3/0464 , G06N3/048
摘要： The disclosure provides a method for training a tag recommendation model. The method includes: collecting training materials that comprise interest tags in response to receiving an instruction for collecting training materials; obtaining training semantic vectors that comprise the interest tags by representing features of the training materials using a semantic enhanced representation frame; obtaining training encoding vectors by aggregating social networks into the training semantic vectors; and obtaining a tag recommendation model by training a double-layer neural network structure using the training encoding vectors as inputs and the interest tags as outputs. Therefore, the interest tags obtained in the disclosure are more accurate.
-
6.发明公开
公开(公告)号：EP4116884A2
公开(公告)日：2023-01-11
申请号：EP22208688.6
申请日：2022-11-22
发明人： LUO, Jinchang , WANG, Haiwei , BU, Junzhao , CHEN, Kunbin , HE, Wei
摘要： The disclosure provides a method for training a tag recommendation model. The method includes: collecting training materials that comprise interest tags in response to receiving an instruction for collecting training materials; obtaining training semantic vectors that comprise the interest tags by representing features of the training materials using a semantic enhanced representation frame; obtaining training encoding vectors by aggregating social networks into the training semantic vectors; and obtaining a tag recommendation model by training a double-layer neural network structure using the training encoding vectors as inputs and the interest tags as outputs. Therefore, the interest tags obtained in the disclosure are more accurate.
-
7.发明公开
公开(公告)号：EP3822875A3
公开(公告)日：2021-09-22
申请号：EP21163447.2
申请日：2021-03-18
发明人： WANG, Haiwei , WANG, Haifeng , HE, Wei , LI, Ying , ZHU, Yong , WANG, Jie
IPC分类号： G06Q10/00
摘要： A method and apparatus for outputting information, a device, a storage medium, and a computer program product are provided. An implementation of the method may include: acquiring knowledge data from at least one data source; acquiring information related to at least one user and a preset entity set; determining an entity, metadata of the entity and a relationship between entities, based on the related information, the knowledge data and the preset entity set; creating a knowledge graph based on the entity, the metadata and the relationship; and outputting the knowledge graph.
-
公开(公告)号：EP4123479A3
公开(公告)日：2023-05-17
申请号：EP22211845.7
申请日：2022-12-07
发明人： XU, Wei , XIA, Xiaoling , JIANG, Junxiang , CAO, Chengtai , HE, Bolei , CHEN, Kunbin , HE, Wei
IPC分类号： G06F16/958 , G06F16/901 , G06F16/906 , G06F16/9535
摘要： The invention relates to technical fields of big data and cloud services. The invention includes: acquiring a set of click data that includes pieces of first click data and a real label for each piece of first click data; extracting a feature vector of each piece of first click data with a graph model; dividing feature vectors into feature vector sets; obtaining trained binary classification models by training binary classification models with the feature vector sets; for each feature vector, obtaining prediction values by predicting the feature vector with the trained binary classification models, and calculating a prediction label of the feature vector based on the prediction values; and removing noise data in the first click data, based on the first click data, the real labels and the prediction labels of the first click data. The invention may denoise click data without event tracking in the application program in advance.
-
公开(公告)号：EP4123479A2
公开(公告)日：2023-01-25
申请号：EP22211845.7
申请日：2022-12-07
发明人： XU, Wei , XIA, Xiaoling , JIANG, Junxiang , CAO, Chengtai , HE, Bolei , CHEN, Kunbin , HE, Wei
IPC分类号： G06F16/958
摘要： The invention relates to technical fields of big data and cloud services. The invention includes: acquiring a set of click data that includes pieces of first click data and a real label for each piece of first click data; extracting a feature vector of each piece of first click data with a graph model; dividing feature vectors into feature vector sets; obtaining trained binary classification models by training binary classification models with the feature vector sets; for each feature vector, obtaining prediction values by predicting the feature vector with the trained binary classification models, and calculating a prediction label of the feature vector based on the prediction values; and removing noise data in the first click data, based on the first click data, the real labels and the prediction labels of the first click data. The invention may denoise click data without event tracking in the application program in advance.
-
10.发明公开
公开(公告)号：EP3929769A1
公开(公告)日：2021-12-29
申请号：EP20217087.4
申请日：2020-12-23
IPC分类号： G06F16/35 , G06F16/36 , G06F16/9535
摘要： The present disclosure provides an information recommendation method, which relates to a field of knowledge graph. The method includes: acquiring request information; extracting a request entity word representing an entity from the request information; determining recommendation information based on the request entity word and a pre-constructed knowledge graph; and pushing the recommendation information, wherein the knowledge graph is constructed based on a text, and the knowledge graph indicates a first word representing a source of the text. The present disclosure further provides an information recommendation apparatus, an electronic device and a computer-readable storage medium.
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.015 秒)
