公开(公告)号：US11151182B2

公开(公告)日：2021-10-19

申请号：US16596938

申请日：2019-10-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yasheng Wang ,  Yang Zhang ,  Shuzhan Bi ,  Youliang Yan

IPC: G06F16/36 ,  G06F40/237 ,  G06K9/62 ,  G06N20/00 ,  G06N3/04 ,  G06N20/10 ,  G06F40/00

Abstract: A classification model training method includes obtaining a positive training set and a first negative training set, where the positive training set includes samples of a positive sample set in a corpus, where the first negative training set includes samples of an unlabeled sample set in the corpus, training, using the positive training set and the first negative training set, to obtain a first classification model, determining, using the first classification model, a pseudo negative sample in the first negative training set, removing the pseudo negative sample from the first negative training set, updating the first negative training set to a second negative training set, and training, using the positive training set and the second negative training set, to obtain a target classification model.

公开(公告)号：US11630957B2

公开(公告)日：2023-04-18

申请号：US16807997

申请日：2020-03-03

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yasheng Wang ,  Jiansheng Wei ,  Yang Zhang

IPC: G06F40/30 ,  G06F40/242 ,  G06N20/00

Abstract: A natural language processing method includes obtaining a to-be-processed phrase, where the to-be-processed phrase includes M words, determining polarity characteristic information of m to-be-processed words in the M words, where polarity characteristic information of an ith word in the m to-be-processed words includes n polarity characteristic values, and each polarity characteristic value corresponds to one sentiment polarity, determining a polarity characteristic vector of the to-be-processed phrase based on the polarity characteristic information of the m to-be-processed words, where the polarity characteristic vector includes n groups of components in a one-to-one correspondence with n sentiment polarities, and determining a sentiment polarity of the to-be-processed phrase based on the polarity characteristic vector of the to-be-processed phrase using a preset classifier, and outputting the sentiment polarity.

公开(公告)号：US20200042829A1

公开(公告)日：2020-02-06

申请号：US16596938

申请日：2019-10-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yasheng Wang ,  Yang Zhang ,  Shuzhan Bi ,  Youliang Yan

IPC: G06K9/62

Abstract: A classification model training method includes obtaining a positive training set and a first negative training set, where the positive training set includes samples of a positive sample set in a corpus, where the first negative training set includes samples of an unlabeled sample set in the corpus, training, using the positive training set and the first negative training set, to obtain a first classification model, determining, using the first classification model, a pseudo negative sample in the first negative training set, removing the pseudo negative sample from the first negative training set, updating the first negative training set to a second negative training set, and training, using the positive training set and the second negative training set, to obtain a target classification model.

公开(公告)号：US12204859B2

公开(公告)日：2025-01-21

申请号：US17526832

申请日：2021-11-15

Applicant: Huawei Technologies Co., Ltd. ,  TSINGHUA UNIVERSITY

Inventor： Yasheng Wang ,  Xin Jiang ,  Xiao Chen ,  Qun Liu ,  Zhengyan Zhang ,  Fanchao Qi ,  Zhiyuan Liu

IPC: G06F40/295 ,  G06F40/211 ,  G06F40/30 ,  G06F40/237 ,  G06F40/279 ,  G06F40/284

Abstract: A text processing method, a model training method, and an apparatus related to the field of artificial intelligence is provided. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.

公开(公告)号：US11210292B2

公开(公告)日：2021-12-28

申请号：US16396381

申请日：2019-04-26

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yasheng Wang ,  Yang Zhang ,  Hongbo Zhang

IPC: G06F16/00 ,  G06F16/2455 ,  G16H10/60

Abstract: Embodiments of the present invention relate to the field of computer technologies, and provide a search method and apparatus to resolve a problem that a reference text, of a text in a professional field, that is determined by using the prior art has relatively low accuracy. The method includes: obtaining n named entities in a current to-be-analyzed target case (S300); determining a first characteristic and a second characteristic (S301); generating, based on the first characteristic and the second characteristic and according to a preset vector generation rule, a target characteristic vector corresponding to the target case (S302); obtaining each historical case in a database and a characteristic vector corresponding to each historical case (S303); and separately calculating a similarity between the target characteristic vector and the characteristic vector corresponding to each historical case, and selecting a historical case whose similarity result meets a preset condition as a reference case (S304).

公开(公告)号：US12260854B2

公开(公告)日：2025-03-25

申请号：US17989756

申请日：2022-11-18

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yulong Zeng ,  Yasheng Wang ,  Yadao Wang

IPC: G10L15/22 ,  G10L15/06 ,  G10L15/18

Abstract: The technology of this application relates to a response method in a human-computer dialogue, a dialogue system, and a storage medium, and belongs to the field of artificial intelligence. In a process of a dialogue between a user and a machine, a user intent of a current dialogue is determined based on an expected user intent associated with a sentence replied by the machine to the user in a previous dialogue, so that a response is made. Because processing logic for an expected user intent is introduced, accuracy of a generated response sentence is improved.

公开(公告)号：US20240386274A1

公开(公告)日：2024-11-21

申请号：US18787328

申请日：2024-07-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Pingyi Zhou ,  Xiaozhe Ren ,  Yasheng Wang ,  Bin He ,  Xinfan Meng ,  Xin Jiang

IPC: G06N3/08

Abstract: A data processing method includes processing target data through a target neural network to obtain a data processing result, where a target header of the target neural network is used to process, through a first transformation matrix, a first vector corresponding to first subdata, and process, through a second transformation matrix, a second vector corresponding to the first subdata, where the first vector corresponds to position information of the first subdata in the target data, and the second vector corresponds to semantic information of the first subdata.

公开(公告)号：US12135941B2

公开(公告)日：2024-11-05

申请号：US17530197

申请日：2021-11-18

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yulong Zeng ,  Jiansheng Wei ,  Yasheng Wang ,  Liqun Deng ,  Anqi Cui

IPC: G06F40/30 ,  G06F40/289 ,  G06N5/01

Abstract: A missing semantics complementing method in the field of natural language processing in the artificial intelligence field is provided. The method includes: obtaining a question statement and a historical dialog statement; resolving a to-be-resolved item in the question statement based on the historical dialog statement and location information of the to-be-resolved item, to obtain a resolved question statement; determining whether a component in the question statement is ellipted, and if a component in the question statement is ellipted, complementing the ellipted component based on the historical dialog statement, to obtain a question statement after ellipsis resolution; merging the resolved question statement and the question statement after ellipsis resolution, to obtain a merged question statement; and determining a target complemented question statement from the resolved question statement, the question statement after ellipsis resolution, and the merged question statement.