Article recommendation sorting method and device, computer equipment and storage medium

Abstract

The invention belongs to the field of computers, and provides an article recommendation sorting method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring log information of a target user and to-be-recommended articles, wherein the log information comprises user information and a user click sequence; preprocessing the obtained user information and the user click sequence to generate first-order features, and processing part of the first-order features to obtain second-order features; determining one-hot codes of the articles to be recommended, and mapping the one-hot codes of the articles to be recommended into distinguishable low-dimensional vectors; according to the first-order features, the second-order features and the low-dimensional vectors of the to-be-recommended articles, constructing a training set and training a Light GBM model; and generating the similarity result of the user click sequence and the to-be-recommended articles according to the LightGBM model, and recommending articles in the to-be-recommended articles to a target user according to the similarity result. According to the invention, the storage space of the model can be reduced, the updating and iteration speed of the model can be increased, and the efficiency of article recommendation sorting is further improved.

Description

technical field [0001] The present application belongs to the field of computers, and in particular relates to a method, device, computer equipment and storage medium for recommending and sorting items. Background technique [0002] The ranking model plays an important role in the recommendation system. A good ranking model can make the items recommended by the system to the user more personalized, and can effectively improve the user's personal experience. At present, the mainstream recommendation system generally adopts the ranking model of DNN, such as the model of DIN, Deep&wide network, DeepFM and other technologies. However, although the DNN sorting model has superior performance, the DNN-based sorting model has high requirements on hardware. The larger the scale of recommended sorting, the more hardware resources will be consumed, so it cannot be applied to all application scenarios. [0003] At the same time, due to the training characteristics of DNN, training a ra...

AI Technical Summary

Problems solved by technology

[0004] The purpose of this application is to provide a method, device, computer equipment and storage medium for item recommendation and sorting, aiming to solve the technical problems of slow iteration speed of the sorting model and low efficiency of item recommendation sorting in the prior art

Images