-
公开(公告)号:US11429680B2
公开(公告)日:2022-08-30
申请号:US16234337
申请日:2018-12-27
Inventor: Hao Tian , Daren Li , Bo Huang , Dai Dai , Chengxiang Liu , Anjun Wei , Kexin Ren , Haiguang Yuan
IPC: G06F16/00 , G06F16/953 , G06F16/33 , G06F16/31 , G06F16/174
Abstract: Embodiments of the present disclosure disclose a method and apparatus for subscribing to a topic. The method includes: matching a persistent topic for a retrieval keyword based on the retrieval keyword of a user combined with at least one of historical behavior or a subscription record of the user; returning the persistent topic to a client for display, so that the user performs subscription; and saving the persistent topic subscribed to by the user, and when a matching resource corresponding to the persistent topic subscribed to by the user is updated, recommending the updated matching resource to the user. Since a recommendation strategy can be timely adjusted according to real-time behavior of a user combined with historical behavior, the probability of hitting a topic of interest to the user is increased.
-
公开(公告)号:US11349680B2
公开(公告)日:2022-05-31
申请号:US16054812
申请日:2018-08-03
Inventor: Jianqing Cui , Yingchao Shi , Hao Tian , Qiaoqiao She , Shiqi Zhao
Abstract: Embodiments of the disclosure disclose a method and apparatus for pushing information based on artificial intelligence. A specific embodiment of the method includes: mining, in response to a new match occurring, real-time match data of the match and real-time associated data of the match; generating structured data using the real-time match data; generating a to-be-recommended item using the real-time associated data and an offline item; determining whether a current time point is a recommendation node based on the structured data and real-time match state information acquired from a state manager; generating a to-be-pushed message based on the to-be-recommended item, the real-time match state information, and basic match information acquired from the state manager, and updating a to-be-pushed message record in the state manager, if the current time point is the recommendation node; and pushing the to-be-pushed message. The embodiment has improved the quality and timeliness of pushing a to-be-pushed message.
-
公开(公告)号:US20210232765A1
公开(公告)日:2021-07-29
申请号:US16988907
申请日:2020-08-10
Inventor: Han Zhang , Dongling Xiao , Yukun Li , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
IPC: G06F40/274 , G06F40/30 , G06F40/56 , G06K9/62
Abstract: The present disclosure discloses a method and an apparatus for generating a text based on a semantic representation and relates to a field of natural language processing (NLP) technologies. The method for generating the text includes: obtaining an input text, the input text comprising a source text; obtaining a placeholder of an ith word to be predicted in a target text; obtaining a vector representation of the ith word to be predicted, in which the vector representation of the ith word to be predicted is obtained by calculating the placeholder of the ith word to be predicted, the source text and 1st to (i−1)th predicted words by employing a self-attention mechanism; and generating an ith predicted word based on the vector representation of the ith word to be predicted, to obtain a target text.
-
公开(公告)号:US11562150B2
公开(公告)日:2023-01-24
申请号:US17031569
申请日:2020-09-24
Inventor: Han Zhang , Dongling Xiao , Yukun Li , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
Abstract: The present disclosure proposes a language generation method and apparatus. The method includes: performing encoding processing on an input sequence by using a preset encoder to generate a hidden state vector corresponding to the input sequence; in response to a granularity category of a second target segment being a phrase, decoding a first target segment vector, the hidden state vector, and a position vector corresponding to the second target segment by using N decoders to generate N second target segments; determining a loss value based on differences between respective N second target segments and a second target annotated segment; and performing parameter updating on the preset encoder, a preset classifier, and the N decoders based on the loss value to generate an updated language generation model for performing language generation.
-
公开(公告)号:US11520991B2
公开(公告)日:2022-12-06
申请号:US16885358
申请日:2020-05-28
Inventor: Yu Sun , Haifeng Wang , Shuohuan Wang , Yukun Li , Shikun Feng , Hao Tian , Hua Wu
Abstract: The present disclosure provides a method, apparatus, electronic device and storage medium for processing a semantic representation model, and relates to the field of artificial intelligence technologies. A specific implementation solution is: collecting a training corpus set including a plurality of training corpuses; training the semantic representation model using the training corpus set based on at least one of lexicon, grammar and semantics. In the present disclosure, by building the unsupervised or weakly-supervised training task at three different levels, namely, lexicon, grammar and semantics, the semantic representation model is enabled to learn knowledge at levels of lexicon, grammar and semantics from massive data, enhance the capability of universal semantic representation and improve the processing effect of the NLP task.
-
公开(公告)号:US20190155856A1
公开(公告)日:2019-05-23
申请号:US16234337
申请日:2018-12-27
Inventor: Hao Tian , Daren Li , Bo Huang , Dai Dai , Chengxiang Liu , Anjun Wei , Kexin Ren , Haiguang Yuan
IPC: G06F16/953 , G06F16/33 , G06F16/31 , G06F16/174
Abstract: Embodiments of the present disclosure disclose a method and apparatus for subscribing to a topic. The method includes: matching a persistent topic for a retrieval keyword based on the retrieval keyword of a user combined with at least one of historical behavior or a subscription record of the user; returning the persistent topic to a client for display, so that the user performs subscription; and saving the persistent topic subscribed to by the user, and when a matching resource corresponding to the persistent topic subscribed to by the user is updated, recommending the updated matching resource to the user. Since a recommendation strategy can be timely adjusted according to real-time behavior of a user combined with historical behavior, the probability of hitting a topic of interest to the user is increased.
-
7.
公开(公告)号:US11995405B2
公开(公告)日:2024-05-28
申请号:US17348104
申请日:2021-06-15
Inventor: Xuan Ouyang , Shuohuan Wang , Chao Pang , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
Abstract: The present disclosure provides a multi-lingual model training method, apparatus, electronic device and readable storage medium and relates to the technical field of deep learning and natural language processing. A technical solution of the present disclosure when training the multi-lingual model is: obtaining training corpuses comprising a plurality of bilingual corpuses and a plurality of monolingual corpuses; training a multi-lingual model with a first training task by using the plurality of bilingual corpuses; training the multi-lingual model with a second training task by using the plurality of monolingual corpuses; and completing the training of the multi-lingual model in a case of determining that loss functions of the first training task and second training task converge. In the present disclosure, the multi-lingual model can be enabled to achieve semantic interaction between different languages and improve the accuracy of the multi-lingual model in learning the semantic representations of the multi-lingual model.
-
公开(公告)号:US11928432B2
公开(公告)日:2024-03-12
申请号:US17319189
申请日:2021-05-13
Inventor: Fei Yu , Jiji Tang , Weichong Yin , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
CPC classification number: G06F40/284 , G06F40/30 , G06N5/04 , G06N20/00 , G06V10/811 , G06V20/30
Abstract: A multi-modal pre-training model acquisition method, an electronic device and a storage medium, which relate to the fields of deep learning and natural language processing, are disclosed. The method may include: determining, for each image-text pair as training data, to-be-processed fine-grained semantic word in the text; masking the to-be-processed fine-grained semantic words; and training the multi-modal pre-training model using the training data with the fine-grained semantic words masked.
-
公开(公告)号:US11461549B2
公开(公告)日:2022-10-04
申请号:US16988907
申请日:2020-08-10
Inventor: Han Zhang , Dongling Xiao , Yukun Li , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
IPC: G06F40/274 , G06F40/56 , G06F40/30 , G06K9/62
Abstract: The present disclosure discloses a method and an apparatus for generating a text based on a semantic representation and relates to a field of natural language processing (NLP) technologies. The method for generating the text includes: obtaining an input text, the input text comprising a source text; obtaining a placeholder of an ith word to be predicted in a target text; obtaining a vector representation of the ith word to be predicted, in which the vector representation of the ith word to be predicted is obtained by calculating the placeholder of the ith word to be predicted, the source text and 1st to (i−1)th predicted words by employing a self-attention mechanism; and generating an ith predicted word based on the vector representation of the ith word to be predicted, to obtain a target text.
-
公开(公告)号:US11645547B2
公开(公告)日:2023-05-09
申请号:US16317526
申请日:2017-01-23
Inventor: Hao Tian , Shiqi Zhao , Zhou Xin , Quan Wen , Wentao Ma , Teng Xu , Xinnuo Xu , Haisong Zhang , Xiangyang Zhou , Rui Yan
IPC: G06N5/02 , G06F16/9032 , G06F16/00 , G06F40/40
CPC classification number: G06N5/02 , G06F16/00 , G06F16/90332 , G06F40/40
Abstract: The present disclosure provides a human-machine interactive method based on artificial intelligence and a human-machine interactive device based on artificial intelligence. The method includes: receiving a query from a user; processing the query based on a pre-generated model, and obtaining an answer with a human conversation style corresponding to the query, wherein the model is generated based on a human conversation corpus; and feeding back the answer to the user.
-
-
-
-
-
-
-
-
-