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

A Vectorized Modeling Method for Social Network Position

A position vector and modeling method technology, applied in the field of social network position vector modeling, can solve the problem that multiple features cannot be integrated into position modeling, so as to alleviate the problem of data sparsity and improve the quality of recommendation results

Active Publication Date: 2022-04-19
GUILIN UNIV OF ELECTRONIC TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art, provide a social network location vector modeling method, and solve the technical problem that various features cannot be effectively integrated into location modeling

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
  • A Vectorized Modeling Method for Social Network Position
  • A Vectorized Modeling Method for Social Network Position
  • A Vectorized Modeling Method for Social Network Position

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Such as figure 1 As shown, the present invention provides a kind of social network position vectorization modeling method, comprises the following steps:

[0067] Step 1. According to the feature information in the public data set, construct the feature matrix of the location.

[0068] Step 1.1. Construct a location co-visit matrix based on the user's check-in records, where the co-visit counts between locations are recorded in pairs.

[0069] Step 1.2. Construct a geographic proximity matrix of locations based on the physical distance between locations.

[0070] Step 1.3, constructing a category correlation matrix of the location according to the category information of the location.

[0071] Step 1.4. Construct the access time matrix of the location according to the user's check-in time stamp.

[0072] Step 2. Convert the feature matrix into latent factors of features according to the decomposition method.

[0073] Step 2.1, convert the common access matrix into 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 relates to a vectorized modeling method for social network positions, which belongs to the technical field of personalized recommendation and aims to solve the technical problem that various features cannot be effectively integrated into position modeling, which includes: according to the features in the public data set Information, construct the feature matrix of the location; convert the feature matrix into the latent factor of the feature according to the decomposition method; splicing the latent factor of the feature to get the feature vector of the location according to the user-location map to obtain the latent factor of the location according to the latent factor of the location and the location The eigenvectors of are concatenated as the position vector z j , so as to complete the vectorized modeling. The invention can improve the quality of the recommendation result and alleviate the problem of data sparseness.

Description

technical field [0001] The invention relates to a vectorized modeling method for social network positions, belonging to the technical field of personalized recommendation. Background technique [0002] Most of the current location recommendation methods only use the user's check-in information in the process of location modeling, ignoring the rich location feature information in LBSNs (location-based social networks); some methods use The geographical features of the location are reached, but only the linear or low-order interactions between the features can be learned, and it cannot effectively integrate multiple features into location modeling. As a result, personalized location recommendations cannot be effectively provided, and the problem of data sparsity cannot be alleviated; in order to solve the above problems, this application proposes a vectorized modeling method for social network locations. Contents of the invention [0003] The purpose of the present inventio...

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 Patents(China)
IPC IPC(8): G06F16/9537G06F16/9536G06Q50/00G06N3/04G06N3/08
CPCG06F16/9537G06F16/9536G06Q50/01G06N3/08G06N3/045
Inventor 蔡国永陈心怡
Owner GUILIN UNIV OF ELECTRONIC TECH