Continuous POI Recommendation Method Based on Check-in Time Interval Pattern

A technology of time interval and recommendation method, which is applied in the field of recommendation system, can solve problems such as not considering the diversity of user behavior patterns, and achieve the effect of accurate and efficient continuous point of interest recommendation service

Active Publication Date: 2022-03-29
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In fact, users of different occupations have different office hours, and their corresponding behavior patterns are also different, but the current research work does not take into account the diversity of user behavior patterns

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
  • Continuous POI Recommendation Method Based on Check-in Time Interval Pattern
  • Continuous POI Recommendation Method Based on Check-in Time Interval Pattern
  • Continuous POI Recommendation Method Based on Check-in Time Interval Pattern

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0063] image 3 For the check-in data in New York City in the Foursquare dataset, the relationship between the user's preference for points of interest (Probability) and the time interval (Transition Interval (hr.)) is depicted. in, image 3 (a) shows the probability distribution of visiting restaurants (Food) and nightclubs (Nightlife) as the time interval changes after users check in to the workplace (Work). We found that the probability of users transferring from the workplace to the restaurant achieves a maximum value when the time interval is 4 hours, 12 hours and 23 hours, respectively. This observation suggests that people typically eat lunch 4 hours after work, dinner 12 hours after work, and breakfast 1 hour before work. In addition, the peak of user check-ins in nightclubs occurs around 10 hours after work, indicating that people usually g...

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 method for recommending continuous points of interest based on a check-in time interval mode, which belongs to the field of recommendation systems; according to each user's check-in data, combined with personalized preferences, geographical distance preferences and check-in time interval preferences to jointly model and form user docking For the comprehensive preference of the points of interest to be visited, a third-order tensor model is used to model the continuous check-in behavior; and a probabilistic model is constructed to learn the user's comprehensive preference for the points of interest by treating the check-in time interval preference as a latent variable. Preference degree; in the parameter learning stage, an expectation maximization algorithm is designed to optimize the parameters of the probability model, and finally realizes the task of recommending points of interest for users to visit next; to supplement the missing information in tensors and matrices, tensors are used / Matrix factorization algorithm implementation. Compared with the prior art, the method of the present invention effectively solves the sparsity problem of the user-POI check-in matrix, and provides users with accurate and efficient continuous POI recommendation services.

Description

technical field [0001] The invention relates to a method for recommending continuous points of interest, in particular to a method for recommending continuous points of interest based on a check-in time interval mode, and belongs to the field of recommendation systems. Background technique [0002] In recent years, Location-based Social Networks (LBSNs), such as Foursquare, Gowalla, GeoLife, etc., have developed rapidly, enabling users to share their check-in experience online. Point-of-interest recommendation has become more important and practical, which can not only help users discover their favorite points of interest, but also help enterprises acquire more target customers. At present, many research institutions have carried out research on POI recommendation tasks. However, since the check-in data for each user is highly sparse, it is challenging to achieve accurate POI recommendation tasks. Current research work considers all check-in data as a whole, and the sequen...

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 & AuthorityPatents(China)
IPC IPC(8): G06F16/9537G06F16/9535
Inventor礼欣江明明石雨
OwnerBEIJING INSTITUTE OF TECHNOLOGYGY