Travel plan recommendation method and device based on neural network, computer equipment and storage medium

Abstract

The invention provides a travel plan recommendation method based on a neural network. The method comprises the steps of obtaining travel history records of multiple users to serve as training samplesof a travel plan recommendation model, wherein the travel plan recommendation model comprises a first gating cycle unit network, a second gating cycle unit network, an attention network and a negativelog likelihood loss function model; respectively inputting the travel history record of each user into the first gating cycle unit network to generate a travel history representation vector; connecting and inputting the travel history representation vector and the embedded vector of the user into the attention network to obtain a user representation vector, and obtaining a scenic spot transfer vector of each scenic spot according to co-occurrence of scenic spots in the training sample; inputting the user representation vector and the scenic spot transfer vector into the second gating cycle unit network to generate a travel recommended scenic spot list with a sequence; and receiving the input of the user by the trained travel plan recommendation model and generating a travel plan recommendation list.

Description

【Technical field】 [0001] The present invention relates to the field of recommendation methods, in particular to a neural network-based travel plan recommendation method, device, computer equipment and storage medium. 【Background technique】 [0002] With the booming development of online travel service platforms, people usually buy some travel products and share their travel experiences on these platforms, this trend causes a large amount of travel data to accumulate on these platforms, which may lead to the problem of information overload . [0003] To solve this problem, recommender systems are widely deployed on these platforms. The functions of most of the current travel recommendation systems include generating the shortest path from the travel start point to the travel destination under a given time constraint, or recommending the next possible place of interest based on the user's visit record, or reminding the user of various scenic spots. queue time. In conclusion...

AI Technical Summary

Problems solved by technology

Based on these pioneer methods, some methods add the queue time constraint, and some methods add the must see the point of interest in the trajectory as a new constraint

Images