Text information processing method and device for video file and server

Abstract

The invention provides a text information processing method and device for a video file and a server, and relates to the technical field of the Internet, and the method comprises the steps of carrying out the feature extraction of a first word vector sequence corresponding to the first text information of a to-be-processed video file, the first word vector sequence being a word vector sequence corresponding to a first word segmentation sequence obtained after word segmentation of the first text information. Therefore, after feature extraction is carried out on the first word vector, the semantics of each segmented word in the first segmented word sequence and the context relationship among the segmented words can be obtained, so that the extracted first semantic feature vector can comprise the semantic feature and the context feature of the first text information. According to the invention, the first text information is subjected to style rewriting according to the first semantic feature vector, so that text rewriting can be performed by combining semantic features and context features of segmented words in the first text information, the grammar problem caused by directly filling a text information template through keywords is prevented, and the text rewriting accuracy is improved.

Description

technical field [0001] The present disclosure relates to the technical field of the Internet, in particular to a method, device and server for processing text information of video files. Background technique [0002] Video creators can upload video files in the video application, and add title information to the uploaded video files, and attract other users to watch through the added title information. However, these title information needs to be reviewed before publication to determine whether the style of the title information meets the standard. When the style of the title information of the video file does not meet the standard, it is necessary to rewrite the style of the title information of the video file into the target style. [0003] In related technologies, reviewers design text information templates with multiple target styles in advance, and when rewriting title information, reviewers can obtain text information templates that realize the designed target styles, ...

AI Technical Summary

Problems solved by technology

[0004] In the above-mentioned related technologies, the text information template designed according to the target style has limitations in design form and quantity, and a large number of video files will share the same text information template, and because the text information template is a template with a fixed grammar, and The extracted keywords may not match the syntax of the text message template

Therefore, filling keywords into the text information template may cause grammatical problems, or may not conform to the true intention of the original text information, resulting in grammatical or semantic flaws, resulting in unsmooth sentences in the rewritten text information

Images