Personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning

Abstract

The invention discloses a personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning, and the method comprises the steps: taking an interaction behavior between a user and a commodity as an edge, constructing a multilayer heterogeneous attribute network, and carrying out the decoupling of the multilayer heterogeneous attribute network into a plurality of simple binary networks; performing weighted accumulation on the adjacency matrixes of all the binary networks to obtain a newly combined adjacency matrix, and performingspectrogram conversion; fusing the adjacency matrix and the node attribute characteristic matrix after spectrum conversion, and finally obtaining representation vectors of all nodes by using a randomprojection method; obtaining a verification set from the historical data to perform parameter adjustment, and obtaining a representation vector of each node; and measuring the preference of the user to the commodity by utilizing cosine similarity so as to carry out personalized recommendation. According to the invention, various interaction behaviors between the user and the commodity are considered at the same time; the interactive relationship among various behaviors can be captured without human intervention; attribute information of users and commodities is effectively fused; network representation learning is carried out by using random projection so that the method efficiency is greatly improved and the recommendation performance is improved.

Description

technical field [0001] The invention relates to a product recommendation method and system based on multi-layer heterogeneous attribute network representation learning, belonging to the technical field of e-commerce. Background technique [0002] In recent years, with the rapid development of e-commerce and mobile Internet, e-commerce platforms such as Taobao, JD.com, Vipshop, and Pinduoduo have emerged one after another to meet people's online shopping needs. Nowadays, online shopping has become an indispensable part of people's daily life. While providing people with convenient services, it has also greatly promoted economic growth. The huge amount of commodity information in the e-commerce platform has brought huge challenges to both the provider of the commodity and the buyer of the commodity: how the commodity provider discloses the appropriate commodity information to the commodity buyer; how the commodity buyer Filter out the product information you need from a large...

AI Technical Summary

Problems solved by technology

Although the above two methods have achieved remarkable results in recommendation, these methods only use some historical interactive products of users as a collection of products directly, and make recommendations by analyzing the collection.

In short, they only make recommendations by mining the static correlation between users and items, while ignoring the transfer of preferences hidden in users' sequential behaviors, and cannot model complex relationships in sequence data

[0005] Through the analysis and summary of the existing product recommendation methods, the traditional methods have deficiencies in the following aspects: 1) ignoring or failing to model multiple interactive behaviors of users at the same time, resulting in inaccurate recommended products and reducing user experience; 2) current Some network representation learning methods are extremely complex and inefficient, cannot be updated in time, and cannot be applied to dynamic environments to capture changes in users' dynamic preferences; 3) Ignoring or not paying attention to the attributes of users and products, such as the user's geographical location, gender , consumption amount, etc., commodity category, price, description information, etc., effective use of these peripheral information can further improve the recommendation performance

Images