Article matching method and article matching device

Abstract

The invention discloses an article matching method and an article matching device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of generating a seed scene set according to user behavior data and article attribute data, and determining a scene vector of the seed scene set; obtaining a target article, and marking a target seed scene label to which the target article belongs for the target article based on the scene vector of the seed scene set; and according to the target seed scene label, obtaining a target matching article matched with the target article. According to the embodiment, the user behavior data and the article attribute data can be analyzed, the seed scene set is generated, and the user experience and the matching accuracy are improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an item matching method and an item matching device. Background technique [0002] The e-commerce platform gradually optimizes services such as item recommendation. After discovering that a user is interested in an item, it recommends a candidate item that matches the item to the user to maximize the user experience. Therefore, item matching and combination is one of the important means of item recommendation. . The existing item collocation technology is mainly divided into three methods: 1. Manually organize and maintain the item collocation list; 2. Analyze and mine item collocation relationships based on association rules; 3. Mining item collocation relationships based on machine learning and deep learning technology. [0003] In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: 1. Th...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: 1. The method based on manually sorting and maintaining the list of item collocations requires a huge amount of manpower and material resources, and the number of collocation combinations is limited, which cannot meet the growing Second, the method of mining item matching relationships based on association rule analysis, the obtained item matching relationships are poorly interpretable, which is easy to cause user complaints, and the number of item matching relationships obtained is small; third, based on machine learning and in-depth The method of learning technology to mine the collocation relationship of items, the applicable scenarios are limited, and the number of collocation relationships obtained is small

Images