公开(公告)号：US20220121812A1

公开(公告)日：2022-04-21

申请号：US17646665

申请日：2021-12-30

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

Inventor： Yipeng ZHANG ,  Duohao QIN ,  Minghao LIU

IPC: G06F40/186 ,  G06F40/174 ,  G06F40/279 ,  G06F17/18 ,  G01W1/00

Abstract: Embodiments of the present disclosure disclose a method and apparatus for processing a weather alert text, an electronic device, a computer readable storage medium, and a computer program product, relate to the field of artificial intelligence technology such as natural language processing, cloud services, and computer vision. An implementation of the method includes: acquiring a to-be-processed weather alert text; extracting actual weather alert elements from the to-be-processed weather alert text using preset element matching templates, the element matching templates being obtained by clustering from contexts of a sample weather alert elements; and performing normalization processing on the actual weather alert elements, and combining obtained normalized alert elements in a preset order to obtain a key weather alert text. The application of this implementation may improve an accuracy of extracting weather alert elements and a generalization processing capability for various to-be-processed weather alert texts.

公开(公告)号：US20210312125A1

公开(公告)日：2021-10-07

申请号：US17121500

申请日：2020-12-14

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

Inventor： Yipeng ZHANG ,  Zhen ZHANG ,  Minghao LIU ,  Rongjie YAO ,  Jiangliang GUO

IPC: G06F40/221 ,  G06F40/143 ,  G06F40/103 ,  G06F40/123 ,  G06F16/93 ,  G06F16/23

Abstract: The disclosure provides a method and an apparatus for parsing a document, a device and a storage medium, and relates to a field of document parsing. The implementing solution includes: receiving a request for parsing the document; downloading the document based on the request; converting the document into an extensible markup language (XML) file; parsing the XML file to extract document content from the XML file; and storing the document content in a JavaScript Object Notation (JSON) format into a database. With the method for parsing the document according to embodiments of the disclosure, an efficiency of parsing the document may be improved.