Collaborative filtering-based mobile internet advertisement recommendation method

A mobile Internet and collaborative filtering technology, applied in the field of mobile Internet advertisement recommendation based on collaborative filtering, can solve the problems of low delivery efficiency, random user dislike of advertisement delivery, etc., and achieve the best matching effect.

Active Publication Date: 2016-11-09
杭州掌维科技有限公司
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, many advertisements are placed randomly, that is, each time a user comes, an advertisement is randomly selected to serve him, and the delivery efficiency is very low
At the same time, the arbitrariness of advertising also makes users feel disgusted

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
  • Collaborative filtering-based mobile internet advertisement recommendation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0035] as attached figure 1 Shown, the inventive method carries out according to the following steps:

[0036] Step 1: Obtain user check-in data and microblog text data posted by users, where user check-in data includes user ID, check-in location, check-in time, and check-in date, etc., and check-in location includes the latitude and longitude of the geographic location where the user checks in and the check-in "point of interest" (Point of Interest, POI);

[0037] Location-based mobile social networks (LBSN) such as Sina Weibo, Jiepang, Renren, Foursquare, and Gowalla have developed rapidly in recent years. A large number of users use these services to record spatio-temporal behavior trajectories in the form of check-in. Therefore, they can provide API to capture the required user sign-in data;

[0038] As a sharing and communication platform, Weibo allows users ...

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 collaborative filtering-based mobile internet advertisement recommendation method. The method comprises the steps of 1, obtaining user sign-in data and microblog text data; 2, preprocessing the user sign-in data and the microblog text data; 3, calculating interest similarity of users; 4, analyzing the user sign-in data by adopting a hierarchical clustering method, comparing the similarity of user behavior traces globally and locally according to a time-space intersection condition of the user behavior traces, and obtaining the similarity of the user behavior traces through linear combination; and 5, calculating recommendation values of mobile internet advertisements by adopting a collaborative filtering method through comprehensively considering the interest similarity of the users, the similarity of the user behavior traces, behavior similarity of the users at different time segments and influence of popularity indexes of the advertisements, and recommending the top-rank advertisements to the users.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a collaborative filtering-based mobile Internet advertisement recommendation method. Background technique [0002] Advertising is a media method used to persuade potential consumers to take some action (purchase, registration or attention, etc.). , ads are everywhere. With the rapid development of mobile Internet technology, the attention of many advertisers has shifted from traditional media advertising to mobile Internet advertising. However, at present, many advertisements are placed randomly, that is, each time a user comes, an advertisement is randomly selected to be served to him, and the delivery efficiency is very low. At the same time, the arbitrariness of advertising also disgusts users. In the face of this situation, the personalized and precise placement of mobile Internet advertisements has attracted extensive attention from researchers. [0003] In terms of advertisin...

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): G06F17/30G06K9/62G06Q30/02
CPCG06F16/9535G06Q30/0251G06F18/231G06F18/22
Inventor 刘兴伟田雪松夏梅宸牟峰张晓丽严兵
Owner 杭州掌维科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products