公开(公告)号：US20230229898A1

公开(公告)日：2023-07-20

申请号：US18186942

申请日：2023-03-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zichao Li ,  Lu Hou ,  Xin Jiang

IPC: G06N3/0499 ,  G06N3/08

CPC classification number: G06N3/0499 ,  G06N3/08

Abstract: A data processing method includes: obtaining to-be-processed data and a target neural network model, where the target neural network model includes a first transformer layer, the first transformer layer includes a first residual branch and a second residual branch, the first residual branch includes a first attention head, and the second residual branch includes a target feed-forward network (FFN) layer; and performing target task related processing on the to-be-processed data based on the target neural network model, to obtain a data processing result, where the target neural network model is for performing a target operation on an output of the first attention head and a first weight value to obtain an output of the first residual branch, and/or the target neural network model is for performing a target operation on an output of the target FFN and a second weight value to obtain an output of the second residual branch.

公开(公告)号：US11500954B2

公开(公告)日：2022-11-15

申请号：US16538174

申请日：2019-08-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： Weiguo Li ,  Xin Jiang ,  Hang Li

IPC: G06F16/9538 ,  G06N20/00

Abstract: A learning-to-rank method based on reinforcement learning, including obtaining, by a server, a historical search word, and obtaining M documents corresponding to the historical search word; ranking, by the server, the M documents to obtain a target document ranking list; obtaining, by the server, a ranking effect evaluation value of the target document ranking list; using, by the server, the historical search word, the M documents, the target document ranking list, and the ranking effect evaluation value as a training sample, and adding the training sample into a training sample set.

公开(公告)号：US10255129B2

公开(公告)日：2019-04-09

申请号：US15292561

申请日：2016-10-13

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xin Jiang ,  Hang Li

IPC: G06F11/00 ,  G06F11/07 ,  G05B23/02 ,  H04L12/24

Abstract: A fault diagnosis method for a big-data network system includes extracting fault information from historical data in the network system, to form training sample data, which is trained to obtain a deep sum product network model that can be used to perform fault diagnosis; and diagnosing a fault of the network system based on the deep sum product network model. The embodiments of the present application resolve a problem that it is difficult to diagnose a fault of a big-data network system.

公开(公告)号：US20180276525A1

公开(公告)日：2018-09-27

申请号：US15993619

申请日：2018-05-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xin Jiang ,  Zhengdong Lu ,  Hang Li

IPC: G06N3/00 ,  G06N3/04 ,  G06F17/27

CPC classification number: G06N3/006 ,  G06F16/3329 ,  G06F17/2715 ,  G06F17/2785 ,  G06N3/0427 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/084

Abstract: A method and neural network system for human-computer interaction, and user equipment are disclosed. According to the method for human-computer interaction, a natural language question and a knowledge base are vectorized, and an intermediate result vector that is based on the knowledge base and that represents a similarity between a natural language question and a knowledge base answer is obtained by means of vector calculation, and then a fact-based correct natural language answer is obtained by means of calculation according to the question vector and the intermediate result vector. By means of this method, a dialog and knowledge base-based question-answering are combined by means of vector calculation, so that natural language interaction can be performed with a user, and a fact-based correct natural language answer can be given according to the knowledge base.

公开(公告)号：US20170102984A1

公开(公告)日：2017-04-13

申请号：US15292561

申请日：2016-10-13

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xin Jiang ,  Hang Li

IPC: G06F11/07

CPC classification number: G06F11/079 ,  G05B23/02 ,  G06F11/0709 ,  G06F11/0751 ,  G06F11/0787 ,  H04L41/0631 ,  H04L41/142

Abstract: A fault diagnosis method for a big-data network system includes extracting fault information from historical data in the network system, to form training sample data, which is trained to obtain a deep sum product network model that can be used to perform fault diagnosis; and diagnosing a fault of the network system based on the deep sum product network model. The embodiments of the present application resolve a problem that it is difficult to diagnose a fault of a big-data network system.