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.

公开(公告)号：US12236361B2

公开(公告)日：2025-02-25

申请号：US17037612

申请日：2020-09-29

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Wenbin Jiang ,  Huanyu Zhou ,  Meng Tian ,  Ying Li ,  Xinwei Feng ,  Xunchao Song ,  Pengcheng Yuan ,  Yajuan Lyu ,  Yong Zhu

IPC: G06F40/30 ,  G06N5/02 ,  G06N5/04

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：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：US20210390260A1

公开(公告)日：2021-12-16

申请号：US17119323

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: G06F40/30 ,  G06N5/02

Abstract: The present disclosure discloses a method, apparatus, device, and storage medium for matching semantics, relates to the technical fields of knowledge graph, natural language processing, and deep learning. The method may include: acquiring a first text and a second text; acquiring language knowledge related to the first text and the second text; determining a target embedding vector based on the first text, the second text, and the language knowledge; and determining a semantic matching result of the first text and the second text, based on the target embedding vector.