Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD, APPARATUS AND DEVICE FOR IDENTIFYING TEXT TYPE
Document Type and Number:
WIPO Patent Application WO/2018/040343
Kind Code:
A1
Abstract:
Disclosed are a method, apparatus and device for identifying a text type. One particular embodiment of the method comprises: implementing a pre-process on a pre-acquired text to obtain a key word set of the text (201); calculating an appearance probability value of each key word in the key word set in the text (202); for each key word in the key word set, introducing the key word and the appearance probability value corresponding to the key word into a pre-established document theme generation model and determining an appearance probability value of each pre-arranged theme in the text in the document theme generation model (203); and according to the appearance probability value of each pre-arranged theme in the text, identifying the type to which the text belongs (204). The method improves the accuracy rate for identifying a text type.

Inventors:
YUE AIZHEN (CN)
CUI YAN (CN)
ZHAO HUI (CN)
GAO XIAN (CN)
WANG SIJIANG (CN)
TAN JING (CN)
Application Number:
PCT/CN2016/108421
Publication Date:
March 08, 2018
Filing Date:
December 02, 2016
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BAIDU ONLINE NETWORK TECHNOLOGY BEIJING CO LTD (CN)
International Classes:
G06F17/27
Foreign References:
CN105893606A2016-08-24
CN104915356A2015-09-16
CN105354184A2016-02-24
US20070203885A12007-08-30
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF: