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

Method for predicting access position of social network user in given time in future

An access location and social network technology, applied in the field of access location prediction, can solve the problems of ignoring user movement patterns and access preferences, difficult to predict user access locations, etc. effect of ability

Active Publication Date: 2021-06-25
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the existing location prediction technology ignores the user's movement patterns and access preferences in a specific time window, it is difficult to predict the user's access location at a specified time in the future

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
  • Method for predicting access position of social network user in given time in future
  • Method for predicting access position of social network user in given time in future
  • Method for predicting access position of social network user in given time in future

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0090] The invention describes a method for predicting the access location of social network users at a given time in the future, which can effectively predict the location of mobile social network users u at a given time in the future t access location, such as figure 2 shown.

[0091] It should be noted that the present invention can realize visit location prediction at the level of points of interest, such as fine-grained geographical areas such as restaurants, theaters, or hotels. Unless otherwise specified, the "location" mentioned below refers to fine-grained points of interest.

[0092] Before the inventive method is described, at first provide following definition:

[0093] Define the user's historical location track set in the mobile social network as L ,gather L Each element in represents a check-in record of the user. gather L...

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 method for predicting an access position of a social network user at a given time in the future. The method comprises the following steps: obtaining a user implicit preference representation based on time window sensitivity; obtaining an interest point implicit representation; obtaining geographical influence implicit representation; splicing the user implicit preference representation, the interest point implicit representation and the geographical influence implicit representation, and inputting a multilayer neural network to calculate the access probability of the user for the interest point in a specific time window; constructing an objective function, optimizing the objective function by using Bayesian personalized sorting, and obtaining model parameters by using a gradient descent algorithm; and utilizing the trained multilayer neural network model to predict the access position of the target user, and selecting candidate positions corresponding to the top-K probability value to form an ordered list as a final access position prediction result. According to the method, the access position of the target user at the given time in the future can be effectively predicted.

Description

technical field [0001] The invention relates to a method for predicting the access position of a social network user at a given time in the future. Background technique [0002] Mobile social network is a combination of location and social networking. It supports users to record and share their geographic location information anytime, anywhere, and builds a bridge between the online virtual world and the offline physical space. The mobile social network has information service characteristics such as socialization, localization, and mobility. The massive location trajectory data generated by it records the moving process of people in the real physical world, reflects people's life and travel habits, and contains extremely rich time and space. semantic information. [0003] Through in-depth analysis and mining of user location trajectories in mobile social networks, various user mobile behavior patterns and personal access preferences hidden behind the location trajectories ...

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): G06F16/9536G06F16/9537G06N3/04G06N3/08G06Q50/00
CPCG06F16/9536G06F16/9537G06Q50/01G06N3/08G06N3/048
Inventor 胥帅许建秋
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS