公开(公告)号：EP4123496A3

公开(公告)日：2023-06-14

申请号：EP22206520.3

申请日：2022-11-10

申请人： Beijing Baidu Netcom Science Technology Co., Ltd.

发明人： LIU, Han ,  HU, Teng ,  FENG, Shikun ,  CHEN, Yongfeng

IPC分类号： G06F40/279 ,  G06F16/31 ,  G06F16/36 ,  G06F40/216 ,  G06F40/30

摘要： A method for extracting text information includes: acquiring a text to be extracted and a target field name; extracting candidate text information matching the target field name from the text to be extracted based on the text to be extracted and the target field name; and acquiring target text information matching fusion semantics of the text to be extracted, the target field name and the candidate text information by filtering the candidate text information based on the fusion semantics. Therefore, when the candidate text information matching the target field name is extracted from the text to be extracted, the candidate text information is filtered based on the fusion semantics of the text to be extracted, the target field name and the candidate text information, which improves the accuracy of extracting text information.

公开(公告)号：EP4123496A2

公开(公告)日：2023-01-25

申请号：EP22206520.3

申请日：2022-11-10

申请人： Beijing Baidu Netcom Science Technology Co., Ltd.

发明人： LIU, Han ,  HU, Teng ,  FENG, Shikun ,  CHEN, Yongfeng

IPC分类号： G06F40/279 ,  G06F40/216 ,  G06F40/30

摘要： A method for extracting text information includes: acquiring a text to be extracted and a target field name; extracting candidate text information matching the target field name from the text to be extracted based on the text to be extracted and the target field name; and acquiring target text information matching fusion semantics of the text to be extracted, the target field name and the candidate text information by filtering the candidate text information based on the fusion semantics. Therefore, when the candidate text information matching the target field name is extracted from the text to be extracted, the candidate text information is filtered based on the fusion semantics of the text to be extracted, the target field name and the candidate text information, which improves the accuracy of extracting text information.

公开(公告)号：EP4033415A1

公开(公告)日：2022-07-27

申请号：EP22150836.9

申请日：2022-01-11

申请人： BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

发明人： LU, Yuxiang ,  LIU, Jiaxiang ,  CHEN, Xuyi ,  FENG, Shikun ,  WANG, Shuohuan ,  SUN, Yu ,  HUANG, Shiwei ,  HE, Jingzhou

IPC分类号： G06N3/08 ,  G06N3/04

摘要： A pre-training method of a neural network model, an electronic device, and a medium. The method includes obtaining (601, 701, 801) pre-training data; inputting (602, 702) the pre-training data to an initial neural network model, and pre-training the initial neural network model in a first training mode; obtaining (603, 805) a loss value of the initial neural network model; and when the loss value of the initial neural network model is less than a preset threshold, continuing (604, 706, 806) pre-training the initial neural network model in a second training mode.