Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Social network comment generation method based on LSTM

A social network and text technology, which is applied in network data retrieval, network data indexing, neural learning methods, etc., can solve the problems of narrow and single scenes, unable to provide material library for public opinion guidance, etc., to purify the network environment and ensure national security and stability. Develop and weaken the effect of hostile forces

Pending Publication Date: 2019-10-29
HARBIN INST OF TECH
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to understand the problem that the existing social network comment generation technology is too narrow and single to provide a material library for public opinion, the present invention further proposes an LSTM-based social network comment generation method

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
  • Social network comment generation method based on LSTM
  • Social network comment generation method based on LSTM
  • Social network comment generation method based on LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In conjunction with the accompanying drawings, the realization of the overall solution of the present invention is set forth as follows:

[0056] 1. Due to the diversity, randomness, and casualness of Twitter comment texts, the comment texts are classified according to the characteristics of comments in the five fields of politics, health, education, entertainment, and technology, while taking into account the structural characteristics of language. For different categories, different LSTM models are designed to encode the visual semantics of word structure, word types and individual words through the learned probability structure. The semantic and syntactical aspects of the comment information to be expressed are fused to generate initial comments of different categories. According to the characteristics of different categories, formulate corresponding text processing strategies to modify the model. Generate high-quality review text that is nearly identical to real re...

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 social network comment generation method based on LSTM, and belongs to the technical field of social network comment generation. The social network comment generation methodand device solve the problem that a material library cannot be provided for public opinions due to the fact that an applied scene of an existing social network comment generation technology is too narrow and single. According to the method, an NLG technology based on LSTM learning is used, and the visual semantics of a sentence structure, the types of characters and each character are coded through the probability relation between the characters obtained through learning. Semantic and syntactic fusion is carried out on comment information to be expressed, and a vivid, smooth and variable high-quality comment text which is almost consistent with a social network is generated through methods such as specific word replacement in the later period. A favorable material corpus is provided for public opinion guidance, and a positive energy network environment is restored by spreading more real and trustworthy languages. The method can serve as a material corpus to be input into an existing public opinion guiding system, and is used for generating comments in the specific field of the social network.

Description

technical field [0001] The invention relates to an LSTM-based social network comment generation method, belonging to the technical field of social network comment generation. Background technique [0002] Nowadays, online social networking platforms have greatly promoted the life and communication of netizens. People and things around the world are closely connected because of the Internet, and people's participation in network events is getting higher and higher, resulting in numerous social network comments. Comments represent a discourse, a voice, and a reflection of ideology, with concise text sentences, clear intentions, and diverse structures, making them an ideal place to test automatic text generation techniques. Some users express their opinions and positions by posting posts on a certain hot event, or agree, or neutral, or deny, or it is an Internet rumor driven by a kind of interest. This patent locks the social network on the Twitter platform, collects user-gene...

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 Applications(China)
IPC IPC(8): G06F16/35G06F16/951G06N3/04G06N3/08G06Q50/00
CPCG06F16/35G06F16/951G06Q50/01G06N3/08G06N3/044G06N3/045
Inventor 何慧张伟哲方滨兴邰煜
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products