Unlock instant, AI-driven research and patent intelligence for your innovation.

Topic-based social media hashtag generation method

A social media and topic technology, applied in the computer field, can solve the problems of sparse post data, topic features ignore post word order information, and inaccurate topic tag generation, etc., to eliminate training gaps, enrich post features, and improve the average precision.

Active Publication Date: 2022-08-05
NAT UNIV OF DEFENSE TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide a topic-based social media hashtag generation method for the problem that social media post data is sparse and topic features ignore post word order information, resulting in inaccurate generation of post hashtags

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Topic-based social media hashtag generation method
  • Topic-based social media hashtag generation method
  • Topic-based social media hashtag generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] like figure 2 As shown, the present invention comprises the following steps:

[0089] Step 1: Build a social media hashtag generation system. The system such as figure 1 As shown, it consists of an encoding module, a feature fusion module, a topic module and a generation module.

[0090] The encoding module is connected with the feature fusion module and the generation module, and its function is to extract the feature vector of the post, which is composed of a word embedding layer and a sequence encoding layer. The encoding module extracts N in the input post s feature vector of words, the N s The feature vector of each word is aggregated into the feature vector of the entire post, which is referred to as the post feature vector. put N s The feature vector of each word is sent to the generation module, and the feature vector of the entire post is sent to the feature fusion module and the generation module. N s is the total number of words in the post, as a po...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a topic-based social media topic tag generation method, which aims to generate topic tags of posts in social media and improve the average precision of the generated topic tags. The technical solution is to first build a social media hashtag generation system; prepare a microblog data set for training the social media hashtag generation system, and obtain a training set and a verification set. The training set is divided into two steps. The first step uses the multi-round cyclic gradient descent method to train the part_block in the generation system, and the second step uses the multi-round cyclic gradient descent method to train the all_block in the generation system and use it for verification. Sets are verified to obtain the optimal network weight parameters. The trained social media hashtag generation system performs hashtag generation on user-inputted posts. By adopting the invention, the average precision of the generated tags can be improved, and the generated topic tags are credible and reliable.

Description

technical field [0001] The invention relates to an information processing method in the computer field, in particular to a topic-based method for generating social media hashtags. Background technique [0002] Social media refers to the content generation and exchange platform based on user relationship on the Internet. In the Internet age, social media has become an important channel for individuals to express their opinions and communicate. Users share opinions, insights, experiences and viewpoints on social media. At this stage, social media mainly include social media sites, Weibo, WeChat, blogs, forums, etc. Hashtag (also known as topic tag), title, etc., consists of a pound sign (or a pound sign before and after each) plus a word, word, or a sentence without spaces. It is commonly used in social media posts to identify a topic the post is about. Hashtags can be used to associate independent posts together, which is convenient for users to browse and search. In additi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/216G06F40/258G06F40/284G06N3/08G06Q50/00
CPCG06F40/216G06F40/258G06N3/084G06F40/284G06Q50/01
Inventor 黄震于修彬窦勇郭敏王思杰郭振梁苏鑫鑫陈中午
Owner NAT UNIV OF DEFENSE TECH