Recommending method and equipment for sequencing-oriented collaborative filtering

Abstract

The invention discloses a recommending method and equipment for sequencing-oriented collaborative filtering. The method comprises the steps of: acquiring preference data of a user to sequenced item pairs; establishing a probability potential preference analysis model based on a user preference according to the preference data and data related to the user and items; and predicting item sequencing based on the user preference by utilizing the probability potential preference analysis model so as to make recommend to the user. By means of the recommending method and equipment, the user preference sequencing of other items can be directly predicted by using the predicted user preference to the item pairs, thus, sequencing prediction can be instantly made without the searching in the whole preference database. Therefore, not only can calculation expense be reduced, but also the accuracy and the convenience in making recommends to the user are improved.

Description

technical field [0001] The present invention relates generally to information filtering and, more particularly, to recommendation methods and apparatus for ranking-oriented collaborative filtering. Background technique [0002] With the explosive growth of accessible information on the Internet, information filtering techniques that help people efficiently sift through large amounts of information have become indispensable in order to be able to overcome the information overload problem caused by the large amount of information obtained. A recommender system is such an information filtering technique that automatically generates a list of item recommendations from a large amount of data items for user selection and reference based on past feedback from users. [0003] The existing technologies that constitute the recommendation system are generally divided into two categories: content-based filtering and collaborative filtering. Compared with content-based filtering, collab...

AI Technical Summary

Problems solved by technology

[0007] Although neighborhood-based methods are widely used due to their conceptual simplicity and intuitiveness, such methods also have shortcomings

First, the accuracy of neighborhood-based methods is usually not optimal

Second, although neighborhood-based methods can produce predictions, they do not involve much learning and thus can only gain little knowledge about users or items from the data

Third, neighborhood-based methods often require direct manipulation of the entire training dataset at prediction time, which incurs significant computational overhead

Finally, adopting a neighborhood-based approach to optimize different objects associated with a specific task or application domain is difficult because there is no suitable model

Images