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

Natural language processing-based social network advertisement pushing method

A natural language processing and social network technology, applied in the field of social network advertisement push based on natural language processing, can solve the problem of rough push and achieve the effect of improving the click-through rate

Inactive Publication Date: 2018-07-31
SUZHOU INST FOR ADVANCED STUDY USTC
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the past, the advertising push of the platform was too rough, and it was simply recommended based on gender, age, and query information

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
  • Natural language processing-based social network advertisement pushing method
  • Natural language processing-based social network advertisement pushing method
  • Natural language processing-based social network advertisement pushing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] The social network of the social network advertisement push method based on natural language processing of the present invention refers to social platforms such as WeChat and Weibo for expressing personal opinions, recording life, and reposting articles. The content of the text includes the positioning of the user, the original text published, the title of the reprinted article, and the official account. User similarity calculation refers to the distance between user portrait vectors.

[0040] Such as figure 1 As shown, the social network advertisement push method based on natural language processing of the present invention comprises the following steps:

[0041] 1. Social network crawling and preprocessing

[0042] Such as figure 2 As shown, after crawling data from social networks, set a timer, and when the time is greater than 30 days, crawl the latest one-month social network dynamics and save them to the database. Then reset the timer to 0, add 1 to the timer...

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 natural language processing-based social network advertisement pushing method. The method includes the following steps that: the social network data of a user are acquired; word segmentation is performed on the social network data, so that word vectors can be generated; a plurality of prediction models are trained so as to be used for predicting different user attributes,user profiles are generated; user profile vectors are generated on the basis of the user profiles, commodity vectors are generated for commodities according to different dimensions; and commodities with high click rates of users who have high user profile vector similarity are calculated, commodities which have high commodity vector similarity with the commodities with high click rates are calculated and are pushed to users who have high user profile similarity. The method is simple and efficient. With the method adopted, the user profiles are automatically generated according to social network information, and the accuracy and click rate of advertisement delivery can be improved.

Description

technical field [0001] The present invention relates to a social network advertisement push method, in particular to a social network advertisement push method based on natural language processing. Background technique [0002] At present, the total number of Internet users in the world has exceeded 3 billion, and social networks have the characteristics of a long development time and a huge number of users. Among them, the monthly active users of Facebook reached 1.35 billion, close to the total population of China. Qzone, an interactive website owned by Chinese Internet giant Tencent, has 645 million active accounts, and the number of users such as WeChat Moments is also huge. [0003] Such a huge number of user platforms are good platforms for selling goods both for the platform itself and for users, because in social networks such as Qzone, Moments, and Weibo, people like to post texts, pictures, positioning, share Your own hobbies, what you have seen and heard, reprin...

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
IPC IPC(8): G06Q30/02G06Q50/00G06F17/27G06F17/30G06K9/62
CPCG06F16/9535G06Q30/0251G06Q50/01G06F40/289G06F18/2411
Inventor 杨威刘艳黄刘生
Owner SUZHOU INST FOR ADVANCED STUDY USTC
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com