A Point-of-Interest Recommendation Method Based on User Positive and Negative Preference Learning

Abstract

The present invention provides a method for recommending points of interest based on user's positive and negative preference learning, which uses a neural network to learn deep-level features of interaction between users and scenic spots, and simultaneously trains two neural network models, a positive preference neural model and a negative preference neural model; The positive preference neural network model generates a list of attractions that users like, and then optimizes and obtains the final recommendation list through the negative preference neural network model to provide users with more accurate recommendation of attractions; in order to solve the traditional point of interest recommendation accuracy is not high and the recommendation results are personalized problems such as low level of chemistry.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for recommending points of interest based on user positive and negative preference learning. Background technique [0002] In recent years, with the rapid development of cloud computing, Internet of Things, mobile Internet, artificial intelligence and other technologies, it has brought a lot of convenience for people to go out, such as watching movies, dining and traveling. However, the continuous emergence of various applications in the Internet space has led to the explosive growth of data. How to obtain valuable information from the complex data and recommend suitable points of interest for users is particularly important. The traditional location-based recommendation is mainly based on the statistical information of interest points or combined with the characteristics of users and points of interest. However, it takes a long time to process complex data, and can on...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a point-of-interest recommendation method based on the user's positive and negative preference learning, using the neural network to learn the deep-level characteristics of the interaction between the user and the scenic spot, and training two neural network models at the same time, the positive preference neural model and the negative preference neural model. model; the positive preference neural network model generates a list of attractions that users like, and then optimizes through the negative preference neural network model to obtain the final recommendation list to provide users with more accurate scenic spot recommendations; Issues such as low degree of personalization of results

Images