Text processing method and device, computing equipment and computer program product

The invention provides a text processing method which comprises the following steps: converting a target query text provided by a user into a query vector by utilizing a trained first model; screening out a target vector of which the similarity with the query vector meets a first preset condition in...

Full description

Saved in:
Bibliographic Details
Main Authors LYU ZHENGWEI, LEI TAO, LIANG XIAO, SHI ZHIZHONG
Format Patent
LanguageChinese
English
Published 08.12.2023
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The invention provides a text processing method which comprises the following steps: converting a target query text provided by a user into a query vector by utilizing a trained first model; screening out a target vector of which the similarity with the query vector meets a first preset condition in the first data source, wherein each vector in the first data source is obtained by converting a text fragment of each text in the first text set by utilizing a trained first model; converting the target query text into a query keyword set by utilizing a trained second model; screening out a target keyword set meeting a second preset condition with the query keyword set in a second data source, wherein each keyword set in the second data source is obtained by converting a text fragment of each text in a second text set by utilizing a trained second model; and based on the target vector and the target keyword set, determining a first target matching text corresponding to the target query text. 本公开提供了一种文本处理方法,其包括:利用经
Bibliography:Application Number: CN202311201679