公开(公告)号：US12175379B2

公开(公告)日：2024-12-24

申请号：US17119651

申请日：2020-12-11

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Hongjian Shi ,  Wenbin Jiang ,  Xinwei Feng ,  Miao Yu ,  Huanyu Zhou ,  Meng Tian ,  Xueqian Wu ,  Xunchao Song

IPC: G06N5/04 ,  G06N20/00 ,  G06F40/30

Abstract: The present disclosure discloses a method, apparatus, device, and storage medium for training a model, relates to the technical fields of knowledge graph, natural language processing, and deep learning. The method may include: acquiring a first annotation data set, the first annotation data set including sample data and a annotation classification result corresponding to the sample data; training a preset initial classification model based on the first annotation data set to obtain an intermediate model; performing prediction on the sample data in the first annotation data set using the intermediate model to obtain a prediction classification result corresponding to the sample data; generating a second annotation data set based on the sample data, the corresponding annotation classification result, and the corresponding prediction classification result; and training the intermediate model based on the second annotation data set to obtain a classification model.

公开(公告)号：US20210390428A1

公开(公告)日：2021-12-16

申请号：US17119651

申请日：2020-12-11

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Hongjian Shi ,  Wenbin Jiang ,  Xinwei Feng ,  Miao Yu ,  Huanyu Zhou ,  Meng Tian ,  Xueqian Wu ,  Xunchao Song

IPC: G06N5/04 ,  G06N20/00

Abstract: The present disclosure discloses a method, apparatus, device, and storage medium for training a model, relates to the technical fields of knowledge graph, natural language processing, and deep learning. The method may include: acquiring a first annotation data set, the first annotation data set including sample data and a annotation classification result corresponding to the sample data; training a preset initial classification model based on the first annotation data set to obtain an intermediate model; performing prediction on the sample data in the first annotation data set using the intermediate model to obtain a prediction classification result corresponding to the sample data; generating a second annotation data set based on the sample data, the corresponding annotation classification result, and the corresponding prediction classification result; and training the intermediate model based on the second annotation data set to obtain a classification model.

公开(公告)号：US20210209309A1

公开(公告)日：2021-07-08

申请号：US17212511

申请日：2021-03-25

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Meng Tian ,  Miao Yu ,  Wenbin Jiang ,  Xinwei Feng ,  Huanyu Zhou ,  Pengcheng Yuan ,  Xunchao Song ,  Xueqian Wu ,  Hongjian Shi

IPC: G06F40/30 ,  G06F40/205 ,  G06F40/242

Abstract: The disclosure discloses a semantics processing method, a semantics processing apparatus, an electronic device, and a medium, and relates to a field of knowledge graph technologies. The detailed implementation includes: determining a target semantic element rule matching a text to be parsed, and parsing the text to be parsed by employing the target semantic element rule to obtain a semantic element parsing result; generating a semantic tree based on the semantic element parsing result by employing a target structured rule associated with the target semantic element rule; and performing semantic understanding on the text to be parsed based on the semantic tree.