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

User behavior recommendation model establishment method and position recommendation method based on spatio-temporal information

A technology for model building and behavior, applied in fuzzy logic-based systems, genetic models, digital data information retrieval, etc.

Active Publication Date: 2021-06-01
NORTHWEST UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a user location prediction model establishment, prediction method and system based on spatio-temporal information to solve the problem in the prior art that the behavior recommendation method based on social media data does not consider the correlation of spatio-temporal 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
  • User behavior recommendation model establishment method and position recommendation method based on spatio-temporal information
  • User behavior recommendation model establishment method and position recommendation method based on spatio-temporal information
  • User behavior recommendation model establishment method and position recommendation method based on spatio-temporal information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment discloses a method for establishing a user behavior recommendation model, including the following steps:

[0050] Step 1: Obtain the user sign-in data set, delete the sign-in data belonging to the cold start in the user sign-in data set, and obtain the sign-in data set, and each piece of sign-in data in the sign-in data set includes user, location, location type and check-in time;

[0051] Step 2: Use the genetic algorithm to calculate the influence degree of the position type of each check-in data in the check-in data set obtained in step 1 on the check-in time in the check-in data, and obtain the time influence degree of each position type;

[0052] Step 3: According to the time influence degree of each location type obtained in step 2, use the fuzzy assignment method to map each piece of check-in data to multiple time periods to obtain multiple behaviors, and obtain a behavior data set. Each behavior in the behavior data set There is a corresponding u...

Embodiment 2

[0106] This embodiment provides a personalized location recommendation method that integrates spatio-temporal information. The overall framework is as follows figure 1 , is mainly divided into three modules: a real-time behavioral recommendation model, a spatial model based on attractiveness, and a personalized location recommendation model that integrates spatiotemporal information. The concrete implementation steps of this method are as follows:

[0107] The first part of the real-time behavior recommendation model:

[0108] This method mainly considers the correlation of the user's historical access behavior at the time level. Firstly, the learning model based on the genetic algorithm is used to determine the degree of influence of different location types on the time level; Multiple user behaviors, and build a behavioral data set that incorporates temporal correlation; in addition, use an incremental random walk algorithm to update the preference relationship between user...

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 belongs to the technical field of data mining and recommendation systems, and discloses a user behavior recommendation model establishment method and a position recommendation method based on spatio-temporal information. Firstly, time level influence degrees of different position types are learned; secondly, the sign-in data is mapped into a plurality of time periods and constructing a behavior data set fusing time correlation; then, the preference relationship between the user and the behavior is updated in real time; and finally, the attraction degree of the aggregation phenomenon of the same type of positions on the geographic space to the users is researched, a personalized position recommendation model is constructed by fusing the spatio-temporal information of the user behaviors, and the most suitable position is recommended to each user. The method is novel in that the model considers the time correlation of user access behaviors, in addition, the model provides a real-time behavior prediction method and provides a new angle to research the attraction degree of a position aggregation phenomenon to the user, and finally the accuracy of personalized position recommendation is improved by fusing spatio-temporal information.

Description

technical field [0001] The invention belongs to the technical field of data mining and recommendation systems, and in particular relates to a user behavior recommendation model establishment and a position recommendation method based on spatio-temporal information. Background technique [0002] Social media data is composed of access check-in data shared by users on social media platforms. Each check-in data is composed of five necessary elements <user ID, location ID, access timestamp, location latitude and longitude, location category>. Social media data can be Effectively record the user's behavior pattern within a certain period of time. With the continuous innovation of positioning technology and the popularity of smart phones, a large number of social media platforms based on location services (LBS) have integrated into our lives. For example, Weibo, WeChat, Dianping, Foursquare, Twitter, Facebook, etc. The rise of these media platforms enables users to share i...

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): G06F16/9537G06F16/9535G06F16/901G06F30/27G06K9/62G06N7/02G06N3/12
CPCG06F16/9537G06F16/9535G06F16/9024G06F30/27G06N3/126G06N7/02G06F18/23Y02D10/00
Inventor 王欣任鑫宇冯筠
Owner NORTHWEST UNIV
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