Recommendation method based on multi-dimensional information portrait of travel agency users

Abstract

The invention discloses a recommending method of multi-dimensional information portrait based on travel agency user, which comprises the following steps: obtaining feature vector of target user and portrait information of user; Comparing the similarity between the user portrait information and the pre-constructed user portrait group, the similar user portrait group with the highest similarity withthe target user is obtained. Calculating similarity between the target user and each sample user in a similar user portrait group to obtain neighboring users; According to the similarity between thetarget user and each neighbor user, the interest degree of the target user to the used tourism products, and the interest degree of each neighbor user to the used tourism products which are not used by the target user, the recommended product list is calculated and generated. The method of the invention integrates collaborative filtering and content recommendation, avoids the cold start problem ofthe prior art recommendation method, can accurately recommend marketing products for users, and is suitable for small amount of data and more dimensions of users and products.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a recommendation method based on multi-dimensional information portraits of travel agency users. Background technique [0002] With the development and application of big data technology, more and more enterprises and government agencies have an increasing need to accurately locate the characteristics of a person. The most important thing in the process of big data project integration is to target different types of people. Need for precise marketing and personalized solutions. On the one hand, users need to select the products they are interested in from a large amount of product information; on the other hand, enterprises need to accurately sell suitable products to suitable users through modification of product characteristic parameters. Currently commonly used recommendation algorithms include: content-based recommendation, user behavior-based recommendat...

AI Technical Summary

Problems solved by technology

Currently commonly used recommendation algorithms include: content-based recommendation, user behavior-based recommendation, hybrid model-based recommendation, label-based recommendation, etc.; for the operation model with relatively small product volume and large user volume, precise matching is required In , these commonly used recommended methods are not very practical

Images