公开(公告)号：US20210407499A1

公开(公告)日：2021-12-30

申请号：US17061353

申请日：2020-10-01

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

Inventor： Ke SUN ,  Ying LIU ,  Kai LIU ,  Lei HAN ,  Chao WANG ,  Yingzhuo SONG ,  Shuai GAO ,  Liyan YANG ,  Qianqian WANG ,  Jing LIU ,  Di WEI

IPC: G10L15/183 ,  G10L15/26 ,  H04L12/18

Abstract: A conference minutes generation method is provided, which relates to the technical field of natural language processing. The conference minutes generation method comprises: acquiring a text conference record; dividing the text conference record into a plurality of conference paragraphs, generating a conference paragraph summary for each conference paragraph, and generating a conference record summary based on the conference paragraph summary of each conference paragraph; extracting conference instructions based on the text conference record; and generating the conference minutes based on the conference record summary and the conference instructions.

公开(公告)号：US20220179858A1

公开(公告)日：2022-06-09

申请号：US17407272

申请日：2021-08-20

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

Inventor： Yan CHEN ,  Kai LIU ,  Jing LIU

IPC: G06F16/2458 ,  G06F16/2453 ,  G06N5/02 ,  G06F40/30

Abstract: The present disclosure provides a generalization processing method, apparatus, device and computer storage medium, and relates to technical field of artificial intelligence and specifically to a deep learning technique. A specific implementation solution is: determining a set of candidate queries in a query library that are similar to a requested query in at least one of a literal matching manner, a semantic matching manner and a query rewriting manner; determining a generalized query corresponding to the requested query from the set of candidate queries by using a pre-trained query matching model; wherein the query matching model is obtained by pre-training based on a cross attention model. The generalization for the requested query can be achieved according to the present disclosure.

公开(公告)号：US20210398028A1

公开(公告)日：2021-12-23

申请号：US17084548

申请日：2020-10-29

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

Inventor： Ke SUN ,  Ying LIU ,  Yuanyuan ZHAO ,  Chao WANG ,  Yingzhuo SONG ,  Shuai GAO ,  Jing LIU ,  Di WEI ,  Huifeng SUN ,  Jianglu HU ,  Haohao GUO

IPC: G06Q10/02 ,  G06Q10/10 ,  G06F40/205 ,  H04L12/18

Abstract: A computer-implemented conference reservation method is provided, which relate to the field of natural language processing. The method comprises: receiving a conference reservation request that is initiated by a conference organizer to reserve a conference, the conference reservation request being a text input or a speech input from the conference organizer; parsing, by means of a dialog understanding technology, the conference reservation request to obtain predefined elements of the conference, the predefined elements comprising a list of participants; determining, according to a pre-recorded schedule of the participants, a period of time during which all the participants are idle as a conferencing time; generating a conference invitation message, the conference invitation message specifying the conferencing time; and sending the conference invitation message to the participants.

公开(公告)号：US20220100786A1

公开(公告)日：2022-03-31

申请号：US17407320

申请日：2021-08-20

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

Inventor： Yuchen DING ,  Yingqi QU ,  Jing LIU ,  Kai LIU ,  Dou HONG ,  Hua WU ,  Haifeng WANG

IPC: G06F16/33 ,  G06N20/20

Abstract: The present application discloses a method and apparatus for training a retrieval model, device and computer storage medium that relate to intelligent search and natural language processing technologies. An implementation includes: acquiring initial training data; performing a training operation using the initial training data to obtain an initial retrieval model; selecting texts with the correlation degrees with a query in the training data meeting a preset first requirement from candidate texts using the initial retrieval model; performing a training operation using the updated training data to obtain a first retrieval model; and selecting texts with the correlation degrees with the query in the training data meeting a preset second requirement from the candidate texts using the first retrieval model; and/or selecting texts with the correlation degrees with the query meeting a preset third requirement; and performing a training operation using the expanded training data to obtain a second retrieval model.

公开(公告)号：US20210406467A1

公开(公告)日：2021-12-30

申请号：US16951000

申请日：2020-11-18

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

Inventor： Hongyu LI ,  Jing LIU

IPC: G06F40/279 ,  G06F40/35 ,  G06N20/00

Abstract: A method and apparatus for generating a triple sample, an electronic device and a storage medium are disclosed, which relates to the field of natural language processing technologies based on artificial intelligence and the field of deep learning technologies. An implementation includes acquiring a paragraph text in the triple sample; extracting at least one answer fragment from the paragraph text; and generating corresponding questions by adopting a pre-trained question generating model based on the paragraph text and each answer fragment respectively, so as to obtain the triple sample. In the present application, since trained based on a pre-trained semantic representation model, the pre-trained question generating model has quite good accuracy, and therefore, the triple sample (Q, P, A) generated with the question generating model has quite high accuracy.

公开(公告)号：US20210200956A1

公开(公告)日：2021-07-01

申请号：US16886244

申请日：2020-05-28

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

Inventor： Yuchen DING ,  Kai LIU ,  Jing LIU ,  Yan CHEN

IPC: G06F40/30 ,  G09B7/02 ,  G06F40/258 ,  G06N3/08

Abstract: The present disclosure discloses a method and an apparatus for processing questions and answers, an electronic device and a storage medium. The implementation solution includes: in a process of determining an answer to a question to be answered, determining the semantic representation on the question to be answered respectively with a first semantic representation model of question and a second semantic representation model of question, splicing semantic representation vectors obtained through the first semantic representation model of question and the second semantic representation model of question, determining a spliced semantic vector as a semantic representation vector of the question to be answered, acquiring an answer semantic vector matching the semantic representation vector of the question to be answered from a vector index library of answer, and determining an answer corresponding to the answer semantic vector as a target answer to the question to be answered.