Article recommendation method and device, medium and computer equipment

Abstract

The invention relates to an article recommendation method. The method comprises the steps: obtaining user behavior data, wherein the user behavior data comprises article access data of a plurality ofaccounts; performing feature extraction according to the user behavior data to obtain a plurality of feature vectors; obtaining an article recommendation list corresponding to each account according to the feature vector, the article access data and a preset recommendation model; when an article recommendation request submitted by a current account is received, acquiring an article recommendationlist matched with the article recommendation request according to the article recommendation list corresponding to each account; and feeding back an article recommendation list matched with the article recommendation request to the terminal of the current account for display. According to the method, feature extraction can be performed according to the historical behavior data of each user, and different articles are recommended to different accounts according to the extracted features, so the article recommendation granularity is finer and more flexible, and the recommendation accuracy is improved.

Description

technical field [0001] The present application relates to the field of data processing technology, in particular to an item recommendation method, device, medium and computer equipment. Background technique [0002] For modern Internet users who cannot do without social platforms, news, online shopping and financial services, personalized recommendations are nothing new. With the development of information technology and the Internet industry, information overload has become a challenge for the public to process information. For users, how to quickly and accurately locate the items they need in the exponentially growing information is a very important and challenging task; for merchants, how to present appropriate items to users in a timely manner , which is also quite difficult. [0003] Traditional customer segmentation (Customer Segmentation) is to divide users into multiple groups, and different groups adopt different marketing strategies. A classic method in the fi...

AI Technical Summary

Problems solved by technology

[0004] Therefore, in the traditional technical solution, item recommendations are made according to different groups of people. However, even different individuals of the same group may have different preferences. Therefore, the granularity of the traditional technical solution recommendation is not fine enough, and it is not flexible enough, which may easily lead to inaccurate recommendations. The problem

Images