A cluster-based collaborative filtering recommendation method and device

Abstract

The embodiment of the present invention provides a clustering-based collaborative filtering recommendation method and device, including: obtaining the tag genome vector of the first item; based on the tag genome vector of the first item, classifying the first item into a first number of clusters; For each target item: when the target item and the second item belong to the same cluster, calculate the correlation coefficient based on the distance of the preset type between the target item and the second item; when the target item and the second item belong to different When clustering, the correlation coefficient is calculated based on the Poisson correlation coefficient between the target item and the second item; the target user’s preset score for the second item and the correlation coefficient between the target item and the second item are weighted and, obtain the target user's predicted score for the target item; recommend the target item whose predicted score meets the preset condition to the target user. The application of the embodiment of the present invention can improve the objectivity of the recommendation score.

Description

technical field [0001] The present invention relates to the technical field of recommendation algorithms, in particular to a cluster-based collaborative filtering recommendation method and device. Background technique [0002] With the rapid development of Internet technology, the Internet provides users with a variety of massive information, enriching and facilitating people's work and life. But at the same time, it has become a time-consuming and labor-intensive task for users to obtain interesting information from massive amounts of information. For this reason, a recommendation algorithm is produced. The recommendation algorithm does not require the user to provide a clear demand, but analyzes the user's interest and demand through the user's historical behavior, so as to recommend items that can meet the interest and demand for the user. [0003] Specifically, the collaborative filtering recommendation algorithm is one of the widely used recommendation algorithms, and ...

AI Technical Summary

Problems solved by technology

[0012] It can be seen that in the above collaborative filtering recommendation algorithm, the correlation coefficient between the target item and other items depends on the rating obtained by the item, and the rating is given subjectively by the user, which easily affects the objectivity of the calculated predicted rating

For example, item A only gets a low score given by a user in a bad mood, but in fact the quality of item A is very good, which makes the predicted score of item A calculated according to the above collaborative filtering recommendation algorithm low , poor objectivity

Images